8 Commits
v11.0 ... v11.2

Author SHA1 Message Date
Mahesh Doijade
b882fa00ee -- Add freeglut and glew64 libs for simpleGL
-- delete freeimage libs and headers, user needs to install it for
building samples depending on it
2020-12-11 17:34:13 +05:30
Mahesh Doijade
1cd3264681 Add and update samples with CUDA 11.2 support 2020-12-10 01:05:32 +05:30
Mahesh Doijade
92b0568792 Add cudaNvSciNvMedia sample with/without nvsci* APIs, it takes RGBA image as input and produces YUV via nvmedia
this YUV is consumed by cuda which converts it to grayscale image which is written to file as output
2020-11-24 16:28:04 +05:30
Mahesh Doijade
c4e2869a2b add multi-warp cooperative groups based reduction kernel in reduction sample 2020-09-24 16:49:58 +05:30
Mahesh Doijade
dd2dba3489 helper_string: fix the missing "/" at end of 3 up path in sdkFindFilePath() 2020-09-17 20:45:23 +05:30
Mahesh Doijade
44052982a7 add ewp tags to VS project of conjugateGradientMultiDeviceCG 2020-09-17 20:01:41 +05:30
Mahesh Doijade
cd76533c3f Add and update samples for cuda 11.1 support 2020-09-15 23:45:56 +05:30
Mahesh Doijade
e6ce58fef4 [p2pBandwidthLatency] increase default buffer size and add support to specific buffer size through command line 2020-06-30 19:05:55 +05:30
594 changed files with 43097 additions and 18093 deletions

View File

@@ -1,142 +0,0 @@
FreeImage Public License - Version 1.0
---------------------------------------------
1. Definitions.
1.1. "Contributor" means each entity that creates or contributes to the creation of Modifications.
1.2. "Contributor Version" means the combination of the Original Code, prior Modifications used by a Contributor, and the Modifications made by that particular Contributor.
1.3. "Covered Code" means the Original Code or Modifications or the combination of the Original Code and Modifications, in each case including portions thereof.
1.4. "Electronic Distribution Mechanism" means a mechanism generally accepted in the software development community for the electronic transfer of data.
1.5. "Executable" means Covered Code in any form other than Source Code.
1.6. "Initial Developer" means the individual or entity identified as the Initial Developer in the Source Code notice required by Exhibit A.
1.7. "Larger Work" means a work which combines Covered Code or portions thereof with code not governed by the terms of this License.
1.8. "License" means this document.
1.9. "Modifications" means any addition to or deletion from the substance or structure of either the Original Code or any previous Modifications. When Covered Code is released as a series of files, a
Modification is:
A. Any addition to or deletion from the contents of a file containing Original Code or previous Modifications.
B. Any new file that contains any part of the Original Code or previous Modifications.
1.10. "Original Code" means Source Code of computer software code which is described in the Source Code notice required by Exhibit A as Original Code, and which, at the time of its release under this License is not already Covered Code governed by this License.
1.11. "Source Code" means the preferred form of the Covered Code for making modifications to it, including all modules it contains, plus any associated interface definition files, scripts used to control
compilation and installation of an Executable, or a list of source code differential comparisons against either the Original Code or another well known, available Covered Code of the Contributor's choice. The Source Code can be in a compressed or archival form, provided the appropriate decompression or de-archiving software is widely available for no charge.
1.12. "You" means an individual or a legal entity exercising rights under, and complying with all of the terms of, this License or a future version of this License issued under Section 6.1. For legal entities, "You" includes any entity which controls, is controlled by, or is under common control with You. For purposes of this definition, "control" means (a) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or otherwise, or (b) ownership of fifty percent (50%) or more of the outstanding shares or beneficial ownership of such entity.
2. Source Code License.
2.1. The Initial Developer Grant.
The Initial Developer hereby grants You a world-wide, royalty-free, non-exclusive license, subject to third party intellectual property claims:
(a) to use, reproduce, modify, display, perform, sublicense and distribute the Original Code (or portions thereof) with or without Modifications, or as part of a Larger Work; and
(b) under patents now or hereafter owned or controlled by Initial Developer, to make, have made, use and sell ("Utilize") the Original Code (or portions thereof), but solely to the extent that
any such patent is reasonably necessary to enable You to Utilize the Original Code (or portions thereof) and not to any greater extent that may be necessary to Utilize further Modifications or
combinations.
2.2. Contributor Grant.
Each Contributor hereby grants You a world-wide, royalty-free, non-exclusive license, subject to third party intellectual property claims:
(a) to use, reproduce, modify, display, perform, sublicense and distribute the Modifications created by such Contributor (or portions thereof) either on an unmodified basis, with other Modifications, as Covered Code or as part of a Larger Work; and
(b) under patents now or hereafter owned or controlled by Contributor, to Utilize the Contributor Version (or portions thereof), but solely to the extent that any such patent is reasonably necessary to enable You to Utilize the Contributor Version (or portions thereof), and not to any greater extent that
may be necessary to Utilize further Modifications or combinations.
3. Distribution Obligations.
3.1. Application of License.
The Modifications which You create or to which You contribute are governed by the terms of this License, including without limitation Section 2.2. The Source Code version of Covered Code may be distributed only under the terms of this License or a future version of this License released under Section 6.1, and You must include a copy of this License with every copy of the Source Code You distribute. You may not offer or impose any terms on any Source Code version that alters or
restricts the applicable version of this License or the recipients' rights hereunder. However, You may include an additional document offering the additional rights described in Section 3.5.
3.2. Availability of Source Code.
Any Modification which You create or to which You contribute must be made available in Source Code form under the terms of this License either on the same media as an Executable version or via an accepted Electronic Distribution Mechanism to anyone to whom you made an Executable version available; and if made available via Electronic Distribution Mechanism, must remain available for at least twelve (12) months after the date it initially became available, or at least six (6) months after a subsequent version of that particular Modification has been made available to such recipients. You are responsible for ensuring that the Source Code version remains available even if the Electronic Distribution Mechanism is maintained by a third party.
3.3. Description of Modifications.
You must cause all Covered Code to which you contribute to contain a file documenting the changes You made to create that Covered Code and the date of any change. You must include a prominent statement that the Modification is derived, directly or indirectly, from Original Code provided by the Initial Developer and including the name of the Initial Developer in (a) the Source Code, and (b) in any notice in an Executable version or related documentation in which You describe the origin or ownership of the Covered Code.
3.4. Intellectual Property Matters
(a) Third Party Claims.
If You have knowledge that a party claims an intellectual property right in particular functionality or code (or its utilization under this License), you must include a text file with the source code distribution titled "LEGAL" which describes the claim and the party making the claim in sufficient detail that a recipient will know whom to contact. If you obtain such knowledge after You make Your Modification available as described in Section 3.2, You shall promptly modify the LEGAL file in all copies You make
available thereafter and shall take other steps (such as notifying appropriate mailing lists or newsgroups) reasonably calculated to inform those who received the Covered Code that new knowledge has been obtained.
(b) Contributor APIs.
If Your Modification is an application programming interface and You own or control patents which are reasonably necessary to implement that API, you must also include this information in the LEGAL file.
3.5. Required Notices.
You must duplicate the notice in Exhibit A in each file of the Source Code, and this License in any documentation for the Source Code, where You describe recipients' rights relating to Covered Code. If You created one or more Modification(s), You may add your name as a Contributor to the notice described in Exhibit A. If it is not possible to put such notice in a particular Source Code file due to its
structure, then you must include such notice in a location (such as a relevant directory file) where a user would be likely to look for such a notice. You may choose to offer, and to charge a fee for, warranty, support, indemnity or liability obligations to one or more recipients of Covered Code. However, You may do so only on Your own behalf, and not on behalf of the Initial Developer or any Contributor. You must make it absolutely clear than any such warranty, support, indemnity or
liability obligation is offered by You alone, and You hereby agree to indemnify the Initial Developer and every Contributor for any liability incurred by the Initial Developer or such Contributor as a result of
warranty, support, indemnity or liability terms You offer.
3.6. Distribution of Executable Versions.
You may distribute Covered Code in Executable form only if the requirements of Section 3.1-3.5 have been met for that Covered Code, and if You include a notice stating that the Source Code version of the Covered Code is available under the terms of this License, including a description of how and where You have fulfilled the obligations of Section 3.2. The notice must be conspicuously included in any notice in an Executable version, related documentation or collateral in which You
describe recipients' rights relating to the Covered Code. You may distribute the Executable version of Covered Code under a license of Your choice, which may contain terms different from this License,
provided that You are in compliance with the terms of this License and that the license for the Executable version does not attempt to limit or alter the recipient's rights in the Source Code version from the rights set forth in this License. If You distribute the Executable version under a different license You must make it absolutely clear that any terms which differ from this License are offered by You alone, not by the Initial Developer or any Contributor. You hereby agree to indemnify the Initial Developer and every Contributor for any liability incurred by the Initial Developer or such Contributor as a result of any such terms You offer.
3.7. Larger Works.
You may create a Larger Work by combining Covered Code with other code not governed by the terms of this License and distribute the Larger Work as a single product. In such a case, You must make sure the requirements of this License are fulfilled for the Covered Code.
4. Inability to Comply Due to Statute or Regulation.
If it is impossible for You to comply with any of the terms of this License with respect to some or all of the Covered Code due to statute or regulation then You must: (a) comply with the terms of this License to the maximum extent possible; and (b) describe the limitations and the code they affect. Such description must be included in the LEGAL file described in Section 3.4 and must be included with all distributions of the Source Code. Except to the extent prohibited by statute or regulation, such description must be sufficiently detailed for a recipient of ordinary skill to be able to understand it.
5. Application of this License.
This License applies to code to which the Initial Developer has attached the notice in Exhibit A, and to related Covered Code.
6. Versions of the License.
6.1. New Versions.
Floris van den Berg may publish revised and/or new versions of the License from time to time. Each version will be given a distinguishing version number.
6.2. Effect of New Versions.
Once Covered Code has been published under a particular version of the License, You may always continue to use it under the terms of that version. You may also choose to use such Covered Code under the terms of any subsequent version of the License published by Floris van den Berg
No one other than Floris van den Berg has the right to modify the terms applicable to Covered Code created under this License.
6.3. Derivative Works.
If you create or use a modified version of this License (which you may only do in order to apply it to code which is not already Covered Code governed by this License), you must (a) rename Your license so that the phrases "FreeImage", `FreeImage Public License", "FIPL", or any confusingly similar phrase do not appear anywhere in your license and (b) otherwise make it clear that your version of the license contains terms which differ from the FreeImage Public License. (Filling in the name of the Initial Developer, Original Code or Contributor in the notice described in Exhibit A shall not of themselves be deemed to be modifications of this License.)
7. DISCLAIMER OF WARRANTY.
COVERED CODE IS PROVIDED UNDER THIS LICENSE ON AN "AS IS" BASIS, WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, WITHOUT LIMITATION, WARRANTIES THAT THE COVERED CODE IS FREE OF DEFECTS, MERCHANTABLE, FIT FOR A PARTICULAR PURPOSE OR NON-INFRINGING. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE COVERED CODE IS WITH YOU. SHOULD ANY COVERED CODE PROVE DEFECTIVE IN ANY RESPECT, YOU (NOT THE INITIAL DEVELOPER OR ANY OTHER CONTRIBUTOR) ASSUME THE COST OF ANY NECESSARY SERVICING, REPAIR OR CORRECTION. THIS DISCLAIMER OF WARRANTY CONSTITUTES AN ESSENTIAL PART OF THIS LICENSE. NO USE OF ANY COVERED CODE IS AUTHORIZED HEREUNDER EXCEPT UNDER THIS DISCLAIMER.
8. TERMINATION.
This License and the rights granted hereunder will terminate automatically if You fail to comply with terms herein and fail to cure such breach within 30 days of becoming aware of the breach. All sublicenses to the Covered Code which are properly granted shall survive any termination of this License. Provisions which, by their nature, must remain in effect beyond the termination of this License shall survive.
9. LIMITATION OF LIABILITY.
UNDER NO CIRCUMSTANCES AND UNDER NO LEGAL THEORY, WHETHER TORT (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE, SHALL THE INITIAL DEVELOPER, ANY OTHER CONTRIBUTOR, OR ANY DISTRIBUTOR OF COVERED CODE, OR ANY SUPPLIER OF ANY OF SUCH PARTIES, BE LIABLE TO YOU OR ANY OTHER PERSON FOR ANY INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES OF ANY CHARACTER INCLUDING, WITHOUT LIMITATION, DAMAGES FOR LOSS OF GOODWILL, WORK STOPPAGE, COMPUTER FAILURE OR MALFUNCTION, OR ANY AND ALL OTHER COMMERCIAL DAMAGES OR LOSSES, EVEN IF SUCH PARTY SHALL HAVE BEEN INFORMED OF THE POSSIBILITY OF SUCH DAMAGES. THIS LIMITATION OF LIABILITY SHALL NOT APPLY TO LIABILITY FOR DEATH OR PERSONAL INJURY RESULTING FROM SUCH PARTY'S NEGLIGENCE TO THE EXTENT APPLICABLE LAW PROHIBITS SUCH LIMITATION. SOME JURISDICTIONS DO NOT ALLOW THE
EXCLUSION OR LIMITATION OF INCIDENTAL OR CONSEQUENTIAL DAMAGES, SO THAT EXCLUSION AND LIMITATION MAY NOT APPLY TO YOU.
10. U.S. GOVERNMENT END USERS.
The Covered Code is a "commercial item," as that term is defined in 48 C.F.R. 2.101 (Oct. 1995), consisting of "commercial computer software" and "commercial computer software documentation," as such terms are used in 48 C.F.R. 12.212 (Sept. 1995). Consistent with 48 C.F.R. 12.212 and 48 C.F.R. 227.7202-1 through 227.7202-4 (June 1995), all U.S. Government End Users acquire Covered Code with only those rights set forth herein.
11. MISCELLANEOUS.
This License represents the complete agreement concerning subject matter hereof. If any provision of this License is held to be unenforceable, such provision shall be reformed only to the extent necessary to make it enforceable. This License shall be governed by Dutch law provisions (except to the extent applicable law, if any, provides otherwise), excluding its conflict-of-law provisions. With respect to disputes in which at least one party is a citizen of, or an entity chartered or registered to do business in, the The Netherlands: (a) unless otherwise agreed in writing, all disputes relating to this License (excepting any dispute relating to intellectual property rights) shall be subject to final and binding arbitration, with the losing party paying all costs of arbitration; (b) any arbitration relating to this Agreement shall be held in Almelo, The Netherlands; and (c) any litigation relating to this Agreement shall be subject to the jurisdiction of the court of Almelo, The Netherlands with the losing party responsible for costs, including without limitation, court costs and reasonable attorneys fees and expenses. Any law or regulation which provides that the language of a contract shall be construed against the drafter shall not apply to this License.
12. RESPONSIBILITY FOR CLAIMS.
Except in cases where another Contributor has failed to comply with Section 3.4, You are responsible for damages arising, directly or indirectly, out of Your utilization of rights under this License, based
on the number of copies of Covered Code you made available, the revenues you received from utilizing such rights, and other relevant factors. You agree to work with affected parties to distribute
responsibility on an equitable basis.
EXHIBIT A.
"The contents of this file are subject to the FreeImage Public License Version 1.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://home.wxs.nl/~flvdberg/freeimage-license.txt
Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific language governing rights and limitations under the License.

File diff suppressed because it is too large Load Diff

22
Common/GL/freeglut.h Normal file
View File

@@ -0,0 +1,22 @@
#ifndef __FREEGLUT_H__
#define __FREEGLUT_H__
/*
* freeglut.h
*
* The freeglut library include file
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
* OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* PAWEL W. OLSZTA BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
* IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#include "freeglut_std.h"
#include "freeglut_ext.h"
/*** END OF FILE ***/
#endif /* __FREEGLUT_H__ */

115
Common/GL/freeglut_ext.h Normal file
View File

@@ -0,0 +1,115 @@
#ifndef __FREEGLUT_EXT_H__
#define __FREEGLUT_EXT_H__
/*
* freeglut_ext.h
*
* The non-GLUT-compatible extensions to the freeglut library include file
*
* Copyright (c) 1999-2000 Pawel W. Olszta. All Rights Reserved.
* Written by Pawel W. Olszta, <olszta@sourceforge.net>
* Creation date: Thu Dec 2 1999
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included
* in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
* OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* PAWEL W. OLSZTA BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
* IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#ifdef __cplusplus
extern "C" {
#endif
/*
* GLUT API Extension macro definitions -- behaviour when the user clicks on an "x" to close a window
*/
#define GLUT_ACTION_EXIT 0
#define GLUT_ACTION_GLUTMAINLOOP_RETURNS 1
#define GLUT_ACTION_CONTINUE_EXECUTION 2
/*
* Create a new rendering context when the user opens a new window?
*/
#define GLUT_CREATE_NEW_CONTEXT 0
#define GLUT_USE_CURRENT_CONTEXT 1
/*
* GLUT API Extension macro definitions -- the glutGet parameters
*/
#define GLUT_ACTION_ON_WINDOW_CLOSE 0x01F9
#define GLUT_WINDOW_BORDER_WIDTH 0x01FA
#define GLUT_WINDOW_HEADER_HEIGHT 0x01FB
#define GLUT_VERSION 0x01FC
#define GLUT_RENDERING_CONTEXT 0x01FD
/*
* Process loop function, see freeglut_main.c
*/
FGAPI void FGAPIENTRY glutMainLoopEvent(void);
FGAPI void FGAPIENTRY glutLeaveMainLoop(void);
/*
* Window-specific callback functions, see freeglut_callbacks.c
*/
FGAPI void FGAPIENTRY glutMouseWheelFunc(void (* callback)(int, int, int, int));
FGAPI void FGAPIENTRY glutCloseFunc(void (* callback)(void));
FGAPI void FGAPIENTRY glutWMCloseFunc(void (* callback)(void));
/* A. Donev: Also a destruction callback for menus */
FGAPI void FGAPIENTRY glutMenuDestroyFunc(void (* callback)(void));
/*
* State setting and retrieval functions, see freeglut_state.c
*/
FGAPI void FGAPIENTRY glutSetOption(GLenum option_flag, int value) ;
/* A.Donev: User-data manipulation */
FGAPI void *FGAPIENTRY glutGetWindowData(void);
FGAPI void FGAPIENTRY glutSetWindowData(void *data);
FGAPI void *FGAPIENTRY glutGetMenuData(void);
FGAPI void FGAPIENTRY glutSetMenuData(void *data);
/*
* Font stuff, see freeglut_font.c
*/
FGAPI int FGAPIENTRY glutBitmapHeight(void *font);
FGAPI GLfloat FGAPIENTRY glutStrokeHeight(void *font);
FGAPI void FGAPIENTRY glutBitmapString(void *font, const unsigned char *string);
FGAPI void FGAPIENTRY glutStrokeString(void *font, const unsigned char *string);
/*
* Geometry functions, see freeglut_geometry.c
*/
FGAPI void FGAPIENTRY glutWireRhombicDodecahedron(void);
FGAPI void FGAPIENTRY glutSolidRhombicDodecahedron(void);
FGAPI void FGAPIENTRY glutWireSierpinskiSponge(int num_levels, GLdouble offset[3], GLdouble scale) ;
FGAPI void FGAPIENTRY glutSolidSierpinskiSponge(int num_levels, GLdouble offset[3], GLdouble scale) ;
FGAPI void FGAPIENTRY glutWireCylinder(GLdouble radius, GLdouble height, GLint slices, GLint stacks);
FGAPI void FGAPIENTRY glutSolidCylinder(GLdouble radius, GLdouble height, GLint slices, GLint stacks);
/*
* Extension functions, see freeglut_ext.c
*/
FGAPI void *FGAPIENTRY glutGetProcAddress(const char *procName);
#ifdef __cplusplus
}
#endif
/*** END OF FILE ***/
#endif /* __FREEGLUT_EXT_H__ */

547
Common/GL/freeglut_std.h Normal file
View File

@@ -0,0 +1,547 @@
#ifndef __FREEGLUT_STD_H__
#define __FREEGLUT_STD_H__
/*
* freeglut_std.h
*
* The GLUT-compatible part of the freeglut library include file
*
* Copyright (c) 1999-2000 Pawel W. Olszta. All Rights Reserved.
* Written by Pawel W. Olszta, <olszta@sourceforge.net>
* Creation date: Thu Dec 2 1999
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included
* in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
* OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* PAWEL W. OLSZTA BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
* IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#ifdef __cplusplus
extern "C" {
#endif
/*
* Under windows, we have to differentiate between static and dynamic libraries
*/
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
# include <windows.h>
# include <windowsx.h>
# include <mmsystem.h>
# define WINDOWS
#ifdef FREEGLUT_STATIC
# define FGAPI
# define FGAPIENTRY
# pragma comment (lib, "freeglut_static.lib") /* link with Win32 static freeglut lib */
#else
# if defined(FREEGLUT_EXPORTS)
# define FGAPI __declspec(dllexport)
/* # define FGAPI */
# else
# define FGAPI __declspec(dllimport)
# pragma comment (lib, "freeglut.lib") /* link with Win32 freeglut lib */
# endif
# define FGAPIENTRY __stdcall
#endif
#pragma comment (lib, "winmm.lib") /* link with Windows MultiMedia lib */
#pragma comment (lib, "user32.lib") /* link with Windows user lib */
#pragma comment (lib, "gdi32.lib") /* link with Windows GDI lib */
#pragma comment (lib, "opengl32.lib") /* link with Microsoft OpenGL lib */
#pragma comment (lib, "glu32.lib") /* link with OpenGL Utility lib */
#else
# define FGAPI
# define FGAPIENTRY
#endif
/*
* The freeglut and GLUT API versions
*/
#define FREEGLUT 1
#define GLUT_API_VERSION 4
#define FREEGLUT_VERSION_2_0 1
/*
* Always include OpenGL and GLU headers
*/
#include <GL/gl.h>
#include <GL/glu.h>
/*
* GLUT API macro definitions -- the special key codes:
*/
#define GLUT_KEY_F1 0x0001
#define GLUT_KEY_F2 0x0002
#define GLUT_KEY_F3 0x0003
#define GLUT_KEY_F4 0x0004
#define GLUT_KEY_F5 0x0005
#define GLUT_KEY_F6 0x0006
#define GLUT_KEY_F7 0x0007
#define GLUT_KEY_F8 0x0008
#define GLUT_KEY_F9 0x0009
#define GLUT_KEY_F10 0x000A
#define GLUT_KEY_F11 0x000B
#define GLUT_KEY_F12 0x000C
#define GLUT_KEY_LEFT 0x0064
#define GLUT_KEY_UP 0x0065
#define GLUT_KEY_RIGHT 0x0066
#define GLUT_KEY_DOWN 0x0067
#define GLUT_KEY_PAGE_UP 0x0068
#define GLUT_KEY_PAGE_DOWN 0x0069
#define GLUT_KEY_HOME 0x006A
#define GLUT_KEY_END 0x006B
#define GLUT_KEY_INSERT 0x006C
/*
* GLUT API macro definitions -- mouse state definitions
*/
#define GLUT_LEFT_BUTTON 0x0000
#define GLUT_MIDDLE_BUTTON 0x0001
#define GLUT_RIGHT_BUTTON 0x0002
#define GLUT_DOWN 0x0000
#define GLUT_UP 0x0001
#define GLUT_LEFT 0x0000
#define GLUT_ENTERED 0x0001
/*
* GLUT API macro definitions -- the display mode definitions
*/
#define GLUT_RGB 0x0000
#define GLUT_RGBA 0x0000
#define GLUT_INDEX 0x0001
#define GLUT_SINGLE 0x0000
#define GLUT_DOUBLE 0x0002
#define GLUT_ACCUM 0x0004
#define GLUT_ALPHA 0x0008
#define GLUT_DEPTH 0x0010
#define GLUT_STENCIL 0x0020
#define GLUT_MULTISAMPLE 0x0080
#define GLUT_STEREO 0x0100
#define GLUT_LUMINANCE 0x0200
/*
* GLUT API macro definitions -- windows and menu related definitions
*/
#define GLUT_MENU_NOT_IN_USE 0x0000
#define GLUT_MENU_IN_USE 0x0001
#define GLUT_NOT_VISIBLE 0x0000
#define GLUT_VISIBLE 0x0001
#define GLUT_HIDDEN 0x0000
#define GLUT_FULLY_RETAINED 0x0001
#define GLUT_PARTIALLY_RETAINED 0x0002
#define GLUT_FULLY_COVERED 0x0003
/*
* GLUT API macro definitions -- fonts definitions
*
* Steve Baker suggested to make it binary compatible with GLUT:
*/
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
# define GLUT_STROKE_ROMAN ((void *)0x0000)
# define GLUT_STROKE_MONO_ROMAN ((void *)0x0001)
# define GLUT_BITMAP_9_BY_15 ((void *)0x0002)
# define GLUT_BITMAP_8_BY_13 ((void *)0x0003)
# define GLUT_BITMAP_TIMES_ROMAN_10 ((void *)0x0004)
# define GLUT_BITMAP_TIMES_ROMAN_24 ((void *)0x0005)
# define GLUT_BITMAP_HELVETICA_10 ((void *)0x0006)
# define GLUT_BITMAP_HELVETICA_12 ((void *)0x0007)
# define GLUT_BITMAP_HELVETICA_18 ((void *)0x0008)
#else
/*
* I don't really know if it's a good idea... But here it goes:
*/
extern void *glutStrokeRoman;
extern void *glutStrokeMonoRoman;
extern void *glutBitmap9By15;
extern void *glutBitmap8By13;
extern void *glutBitmapTimesRoman10;
extern void *glutBitmapTimesRoman24;
extern void *glutBitmapHelvetica10;
extern void *glutBitmapHelvetica12;
extern void *glutBitmapHelvetica18;
/*
* Those pointers will be used by following definitions:
*/
# define GLUT_STROKE_ROMAN ((void *) &glutStrokeRoman)
# define GLUT_STROKE_MONO_ROMAN ((void *) &glutStrokeMonoRoman)
# define GLUT_BITMAP_9_BY_15 ((void *) &glutBitmap9By15)
# define GLUT_BITMAP_8_BY_13 ((void *) &glutBitmap8By13)
# define GLUT_BITMAP_TIMES_ROMAN_10 ((void *) &glutBitmapTimesRoman10)
# define GLUT_BITMAP_TIMES_ROMAN_24 ((void *) &glutBitmapTimesRoman24)
# define GLUT_BITMAP_HELVETICA_10 ((void *) &glutBitmapHelvetica10)
# define GLUT_BITMAP_HELVETICA_12 ((void *) &glutBitmapHelvetica12)
# define GLUT_BITMAP_HELVETICA_18 ((void *) &glutBitmapHelvetica18)
#endif
/*
* GLUT API macro definitions -- the glutGet parameters
*/
#define GLUT_WINDOW_X 0x0064
#define GLUT_WINDOW_Y 0x0065
#define GLUT_WINDOW_WIDTH 0x0066
#define GLUT_WINDOW_HEIGHT 0x0067
#define GLUT_WINDOW_BUFFER_SIZE 0x0068
#define GLUT_WINDOW_STENCIL_SIZE 0x0069
#define GLUT_WINDOW_DEPTH_SIZE 0x006A
#define GLUT_WINDOW_RED_SIZE 0x006B
#define GLUT_WINDOW_GREEN_SIZE 0x006C
#define GLUT_WINDOW_BLUE_SIZE 0x006D
#define GLUT_WINDOW_ALPHA_SIZE 0x006E
#define GLUT_WINDOW_ACCUM_RED_SIZE 0x006F
#define GLUT_WINDOW_ACCUM_GREEN_SIZE 0x0070
#define GLUT_WINDOW_ACCUM_BLUE_SIZE 0x0071
#define GLUT_WINDOW_ACCUM_ALPHA_SIZE 0x0072
#define GLUT_WINDOW_DOUBLEBUFFER 0x0073
#define GLUT_WINDOW_RGBA 0x0074
#define GLUT_WINDOW_PARENT 0x0075
#define GLUT_WINDOW_NUM_CHILDREN 0x0076
#define GLUT_WINDOW_COLORMAP_SIZE 0x0077
#define GLUT_WINDOW_NUM_SAMPLES 0x0078
#define GLUT_WINDOW_STEREO 0x0079
#define GLUT_WINDOW_CURSOR 0x007A
#define GLUT_SCREEN_WIDTH 0x00C8
#define GLUT_SCREEN_HEIGHT 0x00C9
#define GLUT_SCREEN_WIDTH_MM 0x00CA
#define GLUT_SCREEN_HEIGHT_MM 0x00CB
#define GLUT_MENU_NUM_ITEMS 0x012C
#define GLUT_DISPLAY_MODE_POSSIBLE 0x0190
#define GLUT_INIT_WINDOW_X 0x01F4
#define GLUT_INIT_WINDOW_Y 0x01F5
#define GLUT_INIT_WINDOW_WIDTH 0x01F6
#define GLUT_INIT_WINDOW_HEIGHT 0x01F7
#define GLUT_INIT_DISPLAY_MODE 0x01F8
#define GLUT_ELAPSED_TIME 0x02BC
#define GLUT_WINDOW_FORMAT_ID 0x007B
#define GLUT_INIT_STATE 0x007C
/*
* GLUT API macro definitions -- the glutDeviceGet parameters
*/
#define GLUT_HAS_KEYBOARD 0x0258
#define GLUT_HAS_MOUSE 0x0259
#define GLUT_HAS_SPACEBALL 0x025A
#define GLUT_HAS_DIAL_AND_BUTTON_BOX 0x025B
#define GLUT_HAS_TABLET 0x025C
#define GLUT_NUM_MOUSE_BUTTONS 0x025D
#define GLUT_NUM_SPACEBALL_BUTTONS 0x025E
#define GLUT_NUM_BUTTON_BOX_BUTTONS 0x025F
#define GLUT_NUM_DIALS 0x0260
#define GLUT_NUM_TABLET_BUTTONS 0x0261
#define GLUT_DEVICE_IGNORE_KEY_REPEAT 0x0262
#define GLUT_DEVICE_KEY_REPEAT 0x0263
#define GLUT_HAS_JOYSTICK 0x0264
#define GLUT_OWNS_JOYSTICK 0x0265
#define GLUT_JOYSTICK_BUTTONS 0x0266
#define GLUT_JOYSTICK_AXES 0x0267
#define GLUT_JOYSTICK_POLL_RATE 0x0268
/*
* GLUT API macro definitions -- the glutLayerGet parameters
*/
#define GLUT_OVERLAY_POSSIBLE 0x0320
#define GLUT_LAYER_IN_USE 0x0321
#define GLUT_HAS_OVERLAY 0x0322
#define GLUT_TRANSPARENT_INDEX 0x0323
#define GLUT_NORMAL_DAMAGED 0x0324
#define GLUT_OVERLAY_DAMAGED 0x0325
/*
* GLUT API macro definitions -- the glutVideoResizeGet parameters
*/
#define GLUT_VIDEO_RESIZE_POSSIBLE 0x0384
#define GLUT_VIDEO_RESIZE_IN_USE 0x0385
#define GLUT_VIDEO_RESIZE_X_DELTA 0x0386
#define GLUT_VIDEO_RESIZE_Y_DELTA 0x0387
#define GLUT_VIDEO_RESIZE_WIDTH_DELTA 0x0388
#define GLUT_VIDEO_RESIZE_HEIGHT_DELTA 0x0389
#define GLUT_VIDEO_RESIZE_X 0x038A
#define GLUT_VIDEO_RESIZE_Y 0x038B
#define GLUT_VIDEO_RESIZE_WIDTH 0x038C
#define GLUT_VIDEO_RESIZE_HEIGHT 0x038D
/*
* GLUT API macro definitions -- the glutUseLayer parameters
*/
#define GLUT_NORMAL 0x0000
#define GLUT_OVERLAY 0x0001
/*
* GLUT API macro definitions -- the glutGetModifiers parameters
*/
#define GLUT_ACTIVE_SHIFT 0x0001
#define GLUT_ACTIVE_CTRL 0x0002
#define GLUT_ACTIVE_ALT 0x0004
/*
* GLUT API macro definitions -- the glutSetCursor parameters
*/
#define GLUT_CURSOR_RIGHT_ARROW 0x0000
#define GLUT_CURSOR_LEFT_ARROW 0x0001
#define GLUT_CURSOR_INFO 0x0002
#define GLUT_CURSOR_DESTROY 0x0003
#define GLUT_CURSOR_HELP 0x0004
#define GLUT_CURSOR_CYCLE 0x0005
#define GLUT_CURSOR_SPRAY 0x0006
#define GLUT_CURSOR_WAIT 0x0007
#define GLUT_CURSOR_TEXT 0x0008
#define GLUT_CURSOR_CROSSHAIR 0x0009
#define GLUT_CURSOR_UP_DOWN 0x000A
#define GLUT_CURSOR_LEFT_RIGHT 0x000B
#define GLUT_CURSOR_TOP_SIDE 0x000C
#define GLUT_CURSOR_BOTTOM_SIDE 0x000D
#define GLUT_CURSOR_LEFT_SIDE 0x000E
#define GLUT_CURSOR_RIGHT_SIDE 0x000F
#define GLUT_CURSOR_TOP_LEFT_CORNER 0x0010
#define GLUT_CURSOR_TOP_RIGHT_CORNER 0x0011
#define GLUT_CURSOR_BOTTOM_RIGHT_CORNER 0x0012
#define GLUT_CURSOR_BOTTOM_LEFT_CORNER 0x0013
#define GLUT_CURSOR_INHERIT 0x0064
#define GLUT_CURSOR_NONE 0x0065
#define GLUT_CURSOR_FULL_CROSSHAIR 0x0066
/*
* GLUT API macro definitions -- RGB color component specification definitions
*/
#define GLUT_RED 0x0000
#define GLUT_GREEN 0x0001
#define GLUT_BLUE 0x0002
/*
* GLUT API macro definitions -- additional keyboard and joystick definitions
*/
#define GLUT_KEY_REPEAT_OFF 0x0000
#define GLUT_KEY_REPEAT_ON 0x0001
#define GLUT_KEY_REPEAT_DEFAULT 0x0002
#define GLUT_JOYSTICK_BUTTON_A 0x0001
#define GLUT_JOYSTICK_BUTTON_B 0x0002
#define GLUT_JOYSTICK_BUTTON_C 0x0004
#define GLUT_JOYSTICK_BUTTON_D 0x0008
/*
* GLUT API macro definitions -- game mode definitions
*/
#define GLUT_GAME_MODE_ACTIVE 0x0000
#define GLUT_GAME_MODE_POSSIBLE 0x0001
#define GLUT_GAME_MODE_WIDTH 0x0002
#define GLUT_GAME_MODE_HEIGHT 0x0003
#define GLUT_GAME_MODE_PIXEL_DEPTH 0x0004
#define GLUT_GAME_MODE_REFRESH_RATE 0x0005
#define GLUT_GAME_MODE_DISPLAY_CHANGED 0x0006
/*
* Initialization functions, see fglut_init.c
*/
FGAPI void FGAPIENTRY glutInit(int *pargc, char **argv);
FGAPI void FGAPIENTRY glutInitWindowPosition(int x, int y);
FGAPI void FGAPIENTRY glutInitWindowSize(int width, int height);
FGAPI void FGAPIENTRY glutInitDisplayMode(unsigned int displayMode);
FGAPI void FGAPIENTRY glutInitDisplayString(const char *displayMode);
/*
* Process loop function, see freeglut_main.c
*/
FGAPI void FGAPIENTRY glutMainLoop(void);
/*
* Window management functions, see freeglut_window.c
*/
FGAPI int FGAPIENTRY glutCreateWindow(const char *title);
FGAPI int FGAPIENTRY glutCreateSubWindow(int window, int x, int y, int width, int height);
FGAPI void FGAPIENTRY glutDestroyWindow(int window);
FGAPI void FGAPIENTRY glutSetWindow(int window);
FGAPI int FGAPIENTRY glutGetWindow(void);
FGAPI void FGAPIENTRY glutSetWindowTitle(const char *title);
FGAPI void FGAPIENTRY glutSetIconTitle(const char *title);
FGAPI void FGAPIENTRY glutReshapeWindow(int width, int height);
FGAPI void FGAPIENTRY glutPositionWindow(int x, int y);
FGAPI void FGAPIENTRY glutShowWindow(void);
FGAPI void FGAPIENTRY glutHideWindow(void);
FGAPI void FGAPIENTRY glutIconifyWindow(void);
FGAPI void FGAPIENTRY glutPushWindow(void);
FGAPI void FGAPIENTRY glutPopWindow(void);
FGAPI void FGAPIENTRY glutFullScreen(void);
/*
* Display-connected functions, see freeglut_display.c
*/
FGAPI void FGAPIENTRY glutPostWindowRedisplay(int window);
FGAPI void FGAPIENTRY glutPostRedisplay(void);
FGAPI void FGAPIENTRY glutSwapBuffers(void);
/*
* Mouse cursor functions, see freeglut_cursor.c
*/
FGAPI void FGAPIENTRY glutWarpPointer(int x, int y);
FGAPI void FGAPIENTRY glutSetCursor(int cursor);
/*
* Overlay stuff, see freeglut_overlay.c
*/
FGAPI void FGAPIENTRY glutEstablishOverlay(void);
FGAPI void FGAPIENTRY glutRemoveOverlay(void);
FGAPI void FGAPIENTRY glutUseLayer(GLenum layer);
FGAPI void FGAPIENTRY glutPostOverlayRedisplay(void);
FGAPI void FGAPIENTRY glutPostWindowOverlayRedisplay(int window);
FGAPI void FGAPIENTRY glutShowOverlay(void);
FGAPI void FGAPIENTRY glutHideOverlay(void);
/*
* Menu stuff, see freeglut_menu.c
*/
FGAPI int FGAPIENTRY glutCreateMenu(void (* callback)(int menu));
FGAPI void FGAPIENTRY glutDestroyMenu(int menu);
FGAPI int FGAPIENTRY glutGetMenu(void);
FGAPI void FGAPIENTRY glutSetMenu(int menu);
FGAPI void FGAPIENTRY glutAddMenuEntry(const char *label, int value);
FGAPI void FGAPIENTRY glutAddSubMenu(const char *label, int subMenu);
FGAPI void FGAPIENTRY glutChangeToMenuEntry(int item, const char *label, int value);
FGAPI void FGAPIENTRY glutChangeToSubMenu(int item, const char *label, int value);
FGAPI void FGAPIENTRY glutRemoveMenuItem(int item);
FGAPI void FGAPIENTRY glutAttachMenu(int button);
FGAPI void FGAPIENTRY glutDetachMenu(int button);
/*
* Global callback functions, see freeglut_callbacks.c
*/
FGAPI void FGAPIENTRY glutTimerFunc(unsigned int time, void (* callback)(int), int value);
FGAPI void FGAPIENTRY glutIdleFunc(void (* callback)(void));
/*
* Window-specific callback functions, see freeglut_callbacks.c
*/
FGAPI void FGAPIENTRY glutKeyboardFunc(void (* callback)(unsigned char, int, int));
FGAPI void FGAPIENTRY glutSpecialFunc(void (* callback)(int, int, int));
FGAPI void FGAPIENTRY glutReshapeFunc(void (* callback)(int, int));
FGAPI void FGAPIENTRY glutVisibilityFunc(void (* callback)(int));
FGAPI void FGAPIENTRY glutDisplayFunc(void (* callback)(void));
FGAPI void FGAPIENTRY glutMouseFunc(void (* callback)(int, int, int, int));
FGAPI void FGAPIENTRY glutMotionFunc(void (* callback)(int, int));
FGAPI void FGAPIENTRY glutPassiveMotionFunc(void (* callback)(int, int));
FGAPI void FGAPIENTRY glutEntryFunc(void (* callback)(int));
FGAPI void FGAPIENTRY glutKeyboardUpFunc(void (* callback)(unsigned char, int, int));
FGAPI void FGAPIENTRY glutSpecialUpFunc(void (* callback)(int, int, int));
FGAPI void FGAPIENTRY glutJoystickFunc(void (* callback)(unsigned int, int, int, int), int pollInterval);
FGAPI void FGAPIENTRY glutMenuStateFunc(void (* callback)(int));
FGAPI void FGAPIENTRY glutMenuStatusFunc(void (* callback)(int, int, int));
FGAPI void FGAPIENTRY glutOverlayDisplayFunc(void (* callback)(void));
FGAPI void FGAPIENTRY glutWindowStatusFunc(void (* callback)(int));
FGAPI void FGAPIENTRY glutSpaceballMotionFunc(void (* callback)(int, int, int));
FGAPI void FGAPIENTRY glutSpaceballRotateFunc(void (* callback)(int, int, int));
FGAPI void FGAPIENTRY glutSpaceballButtonFunc(void (* callback)(int, int));
FGAPI void FGAPIENTRY glutButtonBoxFunc(void (* callback)(int, int));
FGAPI void FGAPIENTRY glutDialsFunc(void (* callback)(int, int));
FGAPI void FGAPIENTRY glutTabletMotionFunc(void (* callback)(int, int));
FGAPI void FGAPIENTRY glutTabletButtonFunc(void (* callback)(int, int, int, int));
/*
* State setting and retrieval functions, see freeglut_state.c
*/
FGAPI int FGAPIENTRY glutGet(GLenum query);
FGAPI int FGAPIENTRY glutDeviceGet(GLenum query);
FGAPI int FGAPIENTRY glutGetModifiers(void);
FGAPI int FGAPIENTRY glutLayerGet(GLenum query);
/*
* Font stuff, see freeglut_font.c
*/
FGAPI void FGAPIENTRY glutBitmapCharacter(void *font, int character);
FGAPI int FGAPIENTRY glutBitmapWidth(void *font, int character);
FGAPI void FGAPIENTRY glutStrokeCharacter(void *font, int character);
FGAPI int FGAPIENTRY glutStrokeWidth(void *font, int character);
FGAPI int FGAPIENTRY glutBitmapLength(void *font, const unsigned char *string);
FGAPI int FGAPIENTRY glutStrokeLength(void *font, const unsigned char *string);
/*
* Geometry functions, see freeglut_geometry.c
*/
FGAPI void FGAPIENTRY glutWireCube(GLdouble size);
FGAPI void FGAPIENTRY glutSolidCube(GLdouble size);
FGAPI void FGAPIENTRY glutWireSphere(GLdouble radius, GLint slices, GLint stacks);
FGAPI void FGAPIENTRY glutSolidSphere(GLdouble radius, GLint slices, GLint stacks);
FGAPI void FGAPIENTRY glutWireCone(GLdouble base, GLdouble height, GLint slices, GLint stacks);
FGAPI void FGAPIENTRY glutSolidCone(GLdouble base, GLdouble height, GLint slices, GLint stacks);
FGAPI void FGAPIENTRY glutWireTorus(GLdouble innerRadius, GLdouble outerRadius, GLint sides, GLint rings);
FGAPI void FGAPIENTRY glutSolidTorus(GLdouble innerRadius, GLdouble outerRadius, GLint sides, GLint rings);
FGAPI void FGAPIENTRY glutWireDodecahedron(void);
FGAPI void FGAPIENTRY glutSolidDodecahedron(void);
FGAPI void FGAPIENTRY glutWireOctahedron(void);
FGAPI void FGAPIENTRY glutSolidOctahedron(void);
FGAPI void FGAPIENTRY glutWireTetrahedron(void);
FGAPI void FGAPIENTRY glutSolidTetrahedron(void);
FGAPI void FGAPIENTRY glutWireIcosahedron(void);
FGAPI void FGAPIENTRY glutSolidIcosahedron(void);
/*
* Teapot rendering functions, found in freeglut_teapot.c
*/
FGAPI void FGAPIENTRY glutWireTeapot(GLdouble size);
FGAPI void FGAPIENTRY glutSolidTeapot(GLdouble size);
/*
* Game mode functions, see freeglut_gamemode.c
*/
FGAPI void FGAPIENTRY glutGameModeString(const char *string);
FGAPI int FGAPIENTRY glutEnterGameMode(void);
FGAPI void FGAPIENTRY glutLeaveGameMode(void);
FGAPI int FGAPIENTRY glutGameModeGet(GLenum query);
/*
* Video resize functions, see freeglut_videoresize.c
*/
FGAPI int FGAPIENTRY glutVideoResizeGet(GLenum query);
FGAPI void FGAPIENTRY glutSetupVideoResizing(void);
FGAPI void FGAPIENTRY glutStopVideoResizing(void);
FGAPI void FGAPIENTRY glutVideoResize(int x, int y, int width, int height);
FGAPI void FGAPIENTRY glutVideoPan(int x, int y, int width, int height);
/*
* Colormap functions, see freeglut_misc.c
*/
FGAPI void FGAPIENTRY glutSetColor(int color, GLfloat red, GLfloat green, GLfloat blue);
FGAPI GLfloat FGAPIENTRY glutGetColor(int color, int component);
FGAPI void FGAPIENTRY glutCopyColormap(int window);
/*
* Misc keyboard and joystick functions, see freeglut_misc.c
*/
FGAPI void FGAPIENTRY glutIgnoreKeyRepeat(int ignore);
FGAPI void FGAPIENTRY glutSetKeyRepeat(int repeatMode); /* DEPRECATED 11/4/02 - Do not use */
FGAPI void FGAPIENTRY glutForceJoystickFunc(void);
/*
* Misc functions, see freeglut_misc.c
*/
FGAPI int FGAPIENTRY glutExtensionSupported(const char *extension);
FGAPI void FGAPIENTRY glutReportErrors(void);
#ifdef __cplusplus
}
#endif
/*** END OF FILE ***/
#endif /* __FREEGLUT_STD_H__ */

14457
Common/GL/glew.h Normal file

File diff suppressed because it is too large Load Diff

7125
Common/GL/glext.h Normal file

File diff suppressed because it is too large Load Diff

597
Common/GL/glut.h Normal file
View File

@@ -0,0 +1,597 @@
#ifndef __glut_h__
#define __glut_h__
/* Copyright (c) Mark J. Kilgard, 1994, 1995, 1996, 1998. */
/* This program is freely distributable without licensing fees and is
provided without guarantee or warrantee expressed or implied. This
program is -not- in the public domain. */
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
/* GLUT 3.7 now tries to avoid including <windows.h>
to avoid name space pollution, but Win32's <GL/gl.h>
needs APIENTRY and WINGDIAPI defined properly. */
# if 0
# define WIN32_LEAN_AND_MEAN
# include <windows.h>
# else
/* XXX This is from Win32's <windef.h> */
# ifndef APIENTRY
# define GLUT_APIENTRY_DEFINED
# if (_MSC_VER >= 800) || defined(_STDCALL_SUPPORTED)
# define APIENTRY __stdcall
# else
# define APIENTRY
# endif
# endif
/* XXX This is from Win32's <winnt.h> */
# ifndef CALLBACK
# if (defined(_M_MRX000) || defined(_M_IX86) || defined(_M_ALPHA) || defined(_M_PPC)) && !defined(MIDL_PASS)
# define CALLBACK __stdcall
# else
# define CALLBACK
# endif
# endif
/* XXX This is from Win32's <wingdi.h> and <winnt.h> */
# ifndef WINGDIAPI
# define GLUT_WINGDIAPI_DEFINED
# define WINGDIAPI __declspec(dllimport)
# endif
/* XXX This is from Win32's <ctype.h> */
# ifndef _WCHAR_T_DEFINED
typedef unsigned short wchar_t;
# define _WCHAR_T_DEFINED
# endif
# endif
#pragma comment (lib, "winmm.lib") /* link with Windows MultiMedia lib */
#pragma comment (lib, "opengl32.lib") /* link with Microsoft OpenGL lib */
#pragma comment (lib, "glu32.lib") /* link with OpenGL Utility lib */
#pragma message("Note: including lib: glut32.lib\n")
#pragma comment (lib, "glut32.lib") /* link with Win32 GLUT lib */
#pragma warning (disable:4244) /* Disable bogus conversion warnings. */
#pragma warning (disable:4305) /* VC++ 5.0 version of above warning. */
#endif
#include <GL/gl.h>
#include <GL/glu.h>
/* define APIENTRY and CALLBACK to null string if we aren't on Win32 */
#if !defined(WIN32)
#define APIENTRY
#define GLUT_APIENTRY_DEFINED
#define CALLBACK
#endif
#ifdef __cplusplus
extern "C" {
#endif
/**
GLUT API revision history:
GLUT_API_VERSION is updated to reflect incompatible GLUT
API changes (interface changes, semantic changes, deletions,
or additions).
GLUT_API_VERSION=1 First public release of GLUT. 11/29/94
GLUT_API_VERSION=2 Added support for OpenGL/GLX multisampling,
extension. Supports new input devices like tablet, dial and button
box, and Spaceball. Easy to query OpenGL extensions.
GLUT_API_VERSION=3 glutMenuStatus added.
GLUT_API_VERSION=4 glutInitDisplayString, glutWarpPointer,
glutBitmapLength, glutStrokeLength, glutWindowStatusFunc, dynamic
video resize subAPI, glutPostWindowRedisplay, glutKeyboardUpFunc,
glutSpecialUpFunc, glutIgnoreKeyRepeat, glutSetKeyRepeat,
glutJoystickFunc, glutForceJoystickFunc (NOT FINALIZED!).
**/
#ifndef GLUT_API_VERSION /* allow this to be overriden */
#define GLUT_API_VERSION 3
#endif
/**
GLUT implementation revision history:
GLUT_XLIB_IMPLEMENTATION is updated to reflect both GLUT
API revisions and implementation revisions (ie, bug fixes).
GLUT_XLIB_IMPLEMENTATION=1 mjk's first public release of
GLUT Xlib-based implementation. 11/29/94
GLUT_XLIB_IMPLEMENTATION=2 mjk's second public release of
GLUT Xlib-based implementation providing GLUT version 2
interfaces.
GLUT_XLIB_IMPLEMENTATION=3 mjk's GLUT 2.2 images. 4/17/95
GLUT_XLIB_IMPLEMENTATION=4 mjk's GLUT 2.3 images. 6/?/95
GLUT_XLIB_IMPLEMENTATION=5 mjk's GLUT 3.0 images. 10/?/95
GLUT_XLIB_IMPLEMENTATION=7 mjk's GLUT 3.1+ with glutWarpPoitner. 7/24/96
GLUT_XLIB_IMPLEMENTATION=8 mjk's GLUT 3.1+ with glutWarpPoitner
and video resize. 1/3/97
GLUT_XLIB_IMPLEMENTATION=9 mjk's GLUT 3.4 release with early GLUT 4 routines.
GLUT_XLIB_IMPLEMENTATION=11 Mesa 2.5's GLUT 3.6 release.
GLUT_XLIB_IMPLEMENTATION=12 mjk's GLUT 3.6 release with early GLUT 4 routines + signal handling.
GLUT_XLIB_IMPLEMENTATION=13 mjk's GLUT 3.7 release with GameGLUT support.
**/
#ifndef GLUT_XLIB_IMPLEMENTATION /* Allow this to be overriden. */
#define GLUT_XLIB_IMPLEMENTATION 13
#endif
/* Display mode bit masks. */
#define GLUT_RGB 0
#define GLUT_RGBA GLUT_RGB
#define GLUT_INDEX 1
#define GLUT_SINGLE 0
#define GLUT_DOUBLE 2
#define GLUT_ACCUM 4
#define GLUT_ALPHA 8
#define GLUT_DEPTH 16
#define GLUT_STENCIL 32
#if (GLUT_API_VERSION >= 2)
#define GLUT_MULTISAMPLE 128
#define GLUT_STEREO 256
#endif
#if (GLUT_API_VERSION >= 3)
#define GLUT_LUMINANCE 512
#endif
/* Mouse buttons. */
#define GLUT_LEFT_BUTTON 0
#define GLUT_MIDDLE_BUTTON 1
#define GLUT_RIGHT_BUTTON 2
/* Mouse button state. */
#define GLUT_DOWN 0
#define GLUT_UP 1
#if (GLUT_API_VERSION >= 2)
/* function keys */
#define GLUT_KEY_F1 1
#define GLUT_KEY_F2 2
#define GLUT_KEY_F3 3
#define GLUT_KEY_F4 4
#define GLUT_KEY_F5 5
#define GLUT_KEY_F6 6
#define GLUT_KEY_F7 7
#define GLUT_KEY_F8 8
#define GLUT_KEY_F9 9
#define GLUT_KEY_F10 10
#define GLUT_KEY_F11 11
#define GLUT_KEY_F12 12
/* directional keys */
#define GLUT_KEY_LEFT 100
#define GLUT_KEY_UP 101
#define GLUT_KEY_RIGHT 102
#define GLUT_KEY_DOWN 103
#define GLUT_KEY_PAGE_UP 104
#define GLUT_KEY_PAGE_DOWN 105
#define GLUT_KEY_HOME 106
#define GLUT_KEY_END 107
#define GLUT_KEY_INSERT 108
#endif
/* Entry/exit state. */
#define GLUT_LEFT 0
#define GLUT_ENTERED 1
/* Menu usage state. */
#define GLUT_MENU_NOT_IN_USE 0
#define GLUT_MENU_IN_USE 1
/* Visibility state. */
#define GLUT_NOT_VISIBLE 0
#define GLUT_VISIBLE 1
/* Window status state. */
#define GLUT_HIDDEN 0
#define GLUT_FULLY_RETAINED 1
#define GLUT_PARTIALLY_RETAINED 2
#define GLUT_FULLY_COVERED 3
/* Color index component selection values. */
#define GLUT_RED 0
#define GLUT_GREEN 1
#define GLUT_BLUE 2
/* Layers for use. */
#define GLUT_NORMAL 0
#define GLUT_OVERLAY 1
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
/* Stroke font constants (use these in GLUT program). */
#define GLUT_STROKE_ROMAN ((void*)0)
#define GLUT_STROKE_MONO_ROMAN ((void*)1)
/* Bitmap font constants (use these in GLUT program). */
#define GLUT_BITMAP_9_BY_15 ((void*)2)
#define GLUT_BITMAP_8_BY_13 ((void*)3)
#define GLUT_BITMAP_TIMES_ROMAN_10 ((void*)4)
#define GLUT_BITMAP_TIMES_ROMAN_24 ((void*)5)
#if (GLUT_API_VERSION >= 3)
#define GLUT_BITMAP_HELVETICA_10 ((void*)6)
#define GLUT_BITMAP_HELVETICA_12 ((void*)7)
#define GLUT_BITMAP_HELVETICA_18 ((void*)8)
#endif
#else
/* Stroke font opaque addresses (use constants instead in source code). */
extern void *glutStrokeRoman;
extern void *glutStrokeMonoRoman;
/* Stroke font constants (use these in GLUT program). */
#define GLUT_STROKE_ROMAN (&glutStrokeRoman)
#define GLUT_STROKE_MONO_ROMAN (&glutStrokeMonoRoman)
/* Bitmap font opaque addresses (use constants instead in source code). */
extern void *glutBitmap9By15;
extern void *glutBitmap8By13;
extern void *glutBitmapTimesRoman10;
extern void *glutBitmapTimesRoman24;
extern void *glutBitmapHelvetica10;
extern void *glutBitmapHelvetica12;
extern void *glutBitmapHelvetica18;
/* Bitmap font constants (use these in GLUT program). */
#define GLUT_BITMAP_9_BY_15 (&glutBitmap9By15)
#define GLUT_BITMAP_8_BY_13 (&glutBitmap8By13)
#define GLUT_BITMAP_TIMES_ROMAN_10 (&glutBitmapTimesRoman10)
#define GLUT_BITMAP_TIMES_ROMAN_24 (&glutBitmapTimesRoman24)
#if (GLUT_API_VERSION >= 3)
#define GLUT_BITMAP_HELVETICA_10 (&glutBitmapHelvetica10)
#define GLUT_BITMAP_HELVETICA_12 (&glutBitmapHelvetica12)
#define GLUT_BITMAP_HELVETICA_18 (&glutBitmapHelvetica18)
#endif
#endif
/* glutGet parameters. */
#define GLUT_WINDOW_X 100
#define GLUT_WINDOW_Y 101
#define GLUT_WINDOW_WIDTH 102
#define GLUT_WINDOW_HEIGHT 103
#define GLUT_WINDOW_BUFFER_SIZE 104
#define GLUT_WINDOW_STENCIL_SIZE 105
#define GLUT_WINDOW_DEPTH_SIZE 106
#define GLUT_WINDOW_RED_SIZE 107
#define GLUT_WINDOW_GREEN_SIZE 108
#define GLUT_WINDOW_BLUE_SIZE 109
#define GLUT_WINDOW_ALPHA_SIZE 110
#define GLUT_WINDOW_ACCUM_RED_SIZE 111
#define GLUT_WINDOW_ACCUM_GREEN_SIZE 112
#define GLUT_WINDOW_ACCUM_BLUE_SIZE 113
#define GLUT_WINDOW_ACCUM_ALPHA_SIZE 114
#define GLUT_WINDOW_DOUBLEBUFFER 115
#define GLUT_WINDOW_RGBA 116
#define GLUT_WINDOW_PARENT 117
#define GLUT_WINDOW_NUM_CHILDREN 118
#define GLUT_WINDOW_COLORMAP_SIZE 119
#if (GLUT_API_VERSION >= 2)
#define GLUT_WINDOW_NUM_SAMPLES 120
#define GLUT_WINDOW_STEREO 121
#endif
#if (GLUT_API_VERSION >= 3)
#define GLUT_WINDOW_CURSOR 122
#endif
#define GLUT_SCREEN_WIDTH 200
#define GLUT_SCREEN_HEIGHT 201
#define GLUT_SCREEN_WIDTH_MM 202
#define GLUT_SCREEN_HEIGHT_MM 203
#define GLUT_MENU_NUM_ITEMS 300
#define GLUT_DISPLAY_MODE_POSSIBLE 400
#define GLUT_INIT_WINDOW_X 500
#define GLUT_INIT_WINDOW_Y 501
#define GLUT_INIT_WINDOW_WIDTH 502
#define GLUT_INIT_WINDOW_HEIGHT 503
#define GLUT_INIT_DISPLAY_MODE 504
#if (GLUT_API_VERSION >= 2)
#define GLUT_ELAPSED_TIME 700
#endif
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 13)
#define GLUT_WINDOW_FORMAT_ID 123
#endif
#if (GLUT_API_VERSION >= 2)
/* glutDeviceGet parameters. */
#define GLUT_HAS_KEYBOARD 600
#define GLUT_HAS_MOUSE 601
#define GLUT_HAS_SPACEBALL 602
#define GLUT_HAS_DIAL_AND_BUTTON_BOX 603
#define GLUT_HAS_TABLET 604
#define GLUT_NUM_MOUSE_BUTTONS 605
#define GLUT_NUM_SPACEBALL_BUTTONS 606
#define GLUT_NUM_BUTTON_BOX_BUTTONS 607
#define GLUT_NUM_DIALS 608
#define GLUT_NUM_TABLET_BUTTONS 609
#endif
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 13)
#define GLUT_DEVICE_IGNORE_KEY_REPEAT 610
#define GLUT_DEVICE_KEY_REPEAT 611
#define GLUT_HAS_JOYSTICK 612
#define GLUT_OWNS_JOYSTICK 613
#define GLUT_JOYSTICK_BUTTONS 614
#define GLUT_JOYSTICK_AXES 615
#define GLUT_JOYSTICK_POLL_RATE 616
#endif
#if (GLUT_API_VERSION >= 3)
/* glutLayerGet parameters. */
#define GLUT_OVERLAY_POSSIBLE 800
#define GLUT_LAYER_IN_USE 801
#define GLUT_HAS_OVERLAY 802
#define GLUT_TRANSPARENT_INDEX 803
#define GLUT_NORMAL_DAMAGED 804
#define GLUT_OVERLAY_DAMAGED 805
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 9)
/* glutVideoResizeGet parameters. */
#define GLUT_VIDEO_RESIZE_POSSIBLE 900
#define GLUT_VIDEO_RESIZE_IN_USE 901
#define GLUT_VIDEO_RESIZE_X_DELTA 902
#define GLUT_VIDEO_RESIZE_Y_DELTA 903
#define GLUT_VIDEO_RESIZE_WIDTH_DELTA 904
#define GLUT_VIDEO_RESIZE_HEIGHT_DELTA 905
#define GLUT_VIDEO_RESIZE_X 906
#define GLUT_VIDEO_RESIZE_Y 907
#define GLUT_VIDEO_RESIZE_WIDTH 908
#define GLUT_VIDEO_RESIZE_HEIGHT 909
#endif
/* glutUseLayer parameters. */
#define GLUT_NORMAL 0
#define GLUT_OVERLAY 1
/* glutGetModifiers return mask. */
#define GLUT_ACTIVE_SHIFT 1
#define GLUT_ACTIVE_CTRL 2
#define GLUT_ACTIVE_ALT 4
/* glutSetCursor parameters. */
/* Basic arrows. */
#define GLUT_CURSOR_RIGHT_ARROW 0
#define GLUT_CURSOR_LEFT_ARROW 1
/* Symbolic cursor shapes. */
#define GLUT_CURSOR_INFO 2
#define GLUT_CURSOR_DESTROY 3
#define GLUT_CURSOR_HELP 4
#define GLUT_CURSOR_CYCLE 5
#define GLUT_CURSOR_SPRAY 6
#define GLUT_CURSOR_WAIT 7
#define GLUT_CURSOR_TEXT 8
#define GLUT_CURSOR_CROSSHAIR 9
/* Directional cursors. */
#define GLUT_CURSOR_UP_DOWN 10
#define GLUT_CURSOR_LEFT_RIGHT 11
/* Sizing cursors. */
#define GLUT_CURSOR_TOP_SIDE 12
#define GLUT_CURSOR_BOTTOM_SIDE 13
#define GLUT_CURSOR_LEFT_SIDE 14
#define GLUT_CURSOR_RIGHT_SIDE 15
#define GLUT_CURSOR_TOP_LEFT_CORNER 16
#define GLUT_CURSOR_TOP_RIGHT_CORNER 17
#define GLUT_CURSOR_BOTTOM_RIGHT_CORNER 18
#define GLUT_CURSOR_BOTTOM_LEFT_CORNER 19
/* Inherit from parent window. */
#define GLUT_CURSOR_INHERIT 100
/* Blank cursor. */
#define GLUT_CURSOR_NONE 101
/* Fullscreen crosshair (if available). */
#define GLUT_CURSOR_FULL_CROSSHAIR 102
#endif
/* GLUT initialization sub-API. */
extern void APIENTRY glutInit(int *argcp, char **argv);
extern void APIENTRY glutInitDisplayMode(unsigned int mode);
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 9)
extern void APIENTRY glutInitDisplayString(const char *string);
#endif
extern void APIENTRY glutInitWindowPosition(int x, int y);
extern void APIENTRY glutInitWindowSize(int width, int height);
extern void APIENTRY glutMainLoop(void);
/* GLUT window sub-API. */
extern int APIENTRY glutCreateWindow(const char *title);
extern int APIENTRY glutCreateSubWindow(int win, int x, int y, int width, int height);
extern void APIENTRY glutDestroyWindow(int win);
extern void APIENTRY glutPostRedisplay(void);
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 11)
extern void APIENTRY glutPostWindowRedisplay(int win);
#endif
extern void APIENTRY glutSwapBuffers(void);
extern int APIENTRY glutGetWindow(void);
extern void APIENTRY glutSetWindow(int win);
extern void APIENTRY glutSetWindowTitle(const char *title);
extern void APIENTRY glutSetIconTitle(const char *title);
extern void APIENTRY glutPositionWindow(int x, int y);
extern void APIENTRY glutReshapeWindow(int width, int height);
extern void APIENTRY glutPopWindow(void);
extern void APIENTRY glutPushWindow(void);
extern void APIENTRY glutIconifyWindow(void);
extern void APIENTRY glutShowWindow(void);
extern void APIENTRY glutHideWindow(void);
#if (GLUT_API_VERSION >= 3)
extern void APIENTRY glutFullScreen(void);
extern void APIENTRY glutSetCursor(int cursor);
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 9)
extern void APIENTRY glutWarpPointer(int x, int y);
#endif
/* GLUT overlay sub-API. */
extern void APIENTRY glutEstablishOverlay(void);
extern void APIENTRY glutRemoveOverlay(void);
extern void APIENTRY glutUseLayer(GLenum layer);
extern void APIENTRY glutPostOverlayRedisplay(void);
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 11)
extern void APIENTRY glutPostWindowOverlayRedisplay(int win);
#endif
extern void APIENTRY glutShowOverlay(void);
extern void APIENTRY glutHideOverlay(void);
#endif
/* GLUT menu sub-API. */
extern int APIENTRY glutCreateMenu(void ( *)(int));
extern void APIENTRY glutDestroyMenu(int menu);
extern int APIENTRY glutGetMenu(void);
extern void APIENTRY glutSetMenu(int menu);
extern void APIENTRY glutAddMenuEntry(const char *label, int value);
extern void APIENTRY glutAddSubMenu(const char *label, int submenu);
extern void APIENTRY glutChangeToMenuEntry(int item, const char *label, int value);
extern void APIENTRY glutChangeToSubMenu(int item, const char *label, int submenu);
extern void APIENTRY glutRemoveMenuItem(int item);
extern void APIENTRY glutAttachMenu(int button);
extern void APIENTRY glutDetachMenu(int button);
/* GLUT window callback sub-API. */
extern void APIENTRY glutDisplayFunc(void (*func)(void));
extern void APIENTRY glutReshapeFunc(void (*func)(int width, int height));
extern void APIENTRY glutKeyboardFunc(void (*func)(unsigned char key, int x, int y));
extern void APIENTRY glutMouseFunc(void (*func)(int button, int state, int x, int y));
extern void APIENTRY glutMotionFunc(void (*func)(int x, int y));
extern void APIENTRY glutPassiveMotionFunc(void (*func)(int x, int y));
extern void APIENTRY glutEntryFunc(void (*func)(int state));
extern void APIENTRY glutVisibilityFunc(void (*func)(int state));
extern void APIENTRY glutIdleFunc(void (*func)(void));
extern void APIENTRY glutTimerFunc(unsigned int millis, void (*func)(int value), int value);
extern void APIENTRY glutMenuStateFunc(void (*func)(int state));
#if (GLUT_API_VERSION >= 2)
extern void APIENTRY glutSpecialFunc(void (*func)(int key, int x, int y));
extern void APIENTRY glutSpaceballMotionFunc(void (*func)(int x, int y, int z));
extern void APIENTRY glutSpaceballRotateFunc(void (*func)(int x, int y, int z));
extern void APIENTRY glutSpaceballButtonFunc(void (*func)(int button, int state));
extern void APIENTRY glutButtonBoxFunc(void (*func)(int button, int state));
extern void APIENTRY glutDialsFunc(void (*func)(int dial, int value));
extern void APIENTRY glutTabletMotionFunc(void (*func)(int x, int y));
extern void APIENTRY glutTabletButtonFunc(void (*func)(int button, int state, int x, int y));
#if (GLUT_API_VERSION >= 3)
extern void APIENTRY glutMenuStatusFunc(void (*func)(int status, int x, int y));
extern void APIENTRY glutOverlayDisplayFunc(void (*func)(void));
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 9)
extern void APIENTRY glutWindowStatusFunc(void (*func)(int state));
#endif
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 13)
extern void APIENTRY glutKeyboardUpFunc(void (*func)(unsigned char key, int x, int y));
extern void APIENTRY glutSpecialUpFunc(void (*func)(int key, int x, int y));
extern void APIENTRY glutJoystickFunc(void (*func)(unsigned int buttonMask, int x, int y, int z), int pollInterval);
#endif
#endif
#endif
/* GLUT color index sub-API. */
extern void APIENTRY glutSetColor(int, GLfloat red, GLfloat green, GLfloat blue);
extern GLfloat APIENTRY glutGetColor(int ndx, int component);
extern void APIENTRY glutCopyColormap(int win);
/* GLUT state retrieval sub-API. */
extern int APIENTRY glutGet(GLenum type);
extern int APIENTRY glutDeviceGet(GLenum type);
#if (GLUT_API_VERSION >= 2)
/* GLUT extension support sub-API */
extern int APIENTRY glutExtensionSupported(const char *name);
#endif
#if (GLUT_API_VERSION >= 3)
extern int APIENTRY glutGetModifiers(void);
extern int APIENTRY glutLayerGet(GLenum type);
#endif
/* GLUT font sub-API */
extern void APIENTRY glutBitmapCharacter(void *font, int character);
extern int APIENTRY glutBitmapWidth(void *font, int character);
extern void APIENTRY glutStrokeCharacter(void *font, int character);
extern int APIENTRY glutStrokeWidth(void *font, int character);
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 9)
extern int APIENTRY glutBitmapLength(void *font, const unsigned char *string);
extern int APIENTRY glutStrokeLength(void *font, const unsigned char *string);
#endif
/* GLUT pre-built models sub-API */
extern void APIENTRY glutWireSphere(GLdouble radius, GLint slices, GLint stacks);
extern void APIENTRY glutSolidSphere(GLdouble radius, GLint slices, GLint stacks);
extern void APIENTRY glutWireCone(GLdouble base, GLdouble height, GLint slices, GLint stacks);
extern void APIENTRY glutSolidCone(GLdouble base, GLdouble height, GLint slices, GLint stacks);
extern void APIENTRY glutWireCube(GLdouble size);
extern void APIENTRY glutSolidCube(GLdouble size);
extern void APIENTRY glutWireTorus(GLdouble innerRadius, GLdouble outerRadius, GLint sides, GLint rings);
extern void APIENTRY glutSolidTorus(GLdouble innerRadius, GLdouble outerRadius, GLint sides, GLint rings);
extern void APIENTRY glutWireDodecahedron(void);
extern void APIENTRY glutSolidDodecahedron(void);
extern void APIENTRY glutWireTeapot(GLdouble size);
extern void APIENTRY glutSolidTeapot(GLdouble size);
extern void APIENTRY glutWireOctahedron(void);
extern void APIENTRY glutSolidOctahedron(void);
extern void APIENTRY glutWireTetrahedron(void);
extern void APIENTRY glutSolidTetrahedron(void);
extern void APIENTRY glutWireIcosahedron(void);
extern void APIENTRY glutSolidIcosahedron(void);
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 9)
/* GLUT video resize sub-API. */
extern int APIENTRY glutVideoResizeGet(GLenum param);
extern void APIENTRY glutSetupVideoResizing(void);
extern void APIENTRY glutStopVideoResizing(void);
extern void APIENTRY glutVideoResize(int x, int y, int width, int height);
extern void APIENTRY glutVideoPan(int x, int y, int width, int height);
/* GLUT debugging sub-API. */
extern void APIENTRY glutReportErrors(void);
#endif
#if (GLUT_API_VERSION >= 4 || GLUT_XLIB_IMPLEMENTATION >= 13)
/* GLUT device control sub-API. */
/* glutSetKeyRepeat modes. */
#define GLUT_KEY_REPEAT_OFF 0
#define GLUT_KEY_REPEAT_ON 1
#define GLUT_KEY_REPEAT_DEFAULT 2
/* Joystick button masks. */
#define GLUT_JOYSTICK_BUTTON_A 1
#define GLUT_JOYSTICK_BUTTON_B 2
#define GLUT_JOYSTICK_BUTTON_C 4
#define GLUT_JOYSTICK_BUTTON_D 8
extern void APIENTRY glutIgnoreKeyRepeat(int ignore);
extern void APIENTRY glutSetKeyRepeat(int repeatMode);
extern void APIENTRY glutForceJoystickFunc(void);
/* GLUT game mode sub-API. */
/* glutGameModeGet. */
#define GLUT_GAME_MODE_ACTIVE 0
#define GLUT_GAME_MODE_POSSIBLE 1
#define GLUT_GAME_MODE_WIDTH 2
#define GLUT_GAME_MODE_HEIGHT 3
#define GLUT_GAME_MODE_PIXEL_DEPTH 4
#define GLUT_GAME_MODE_REFRESH_RATE 5
#define GLUT_GAME_MODE_DISPLAY_CHANGED 6
extern void APIENTRY glutGameModeString(const char *string);
extern int APIENTRY glutEnterGameMode(void);
extern void APIENTRY glutLeaveGameMode(void);
extern int APIENTRY glutGameModeGet(GLenum mode);
#endif
#ifdef __cplusplus
}
#endif
#ifdef GLUT_APIENTRY_DEFINED
# undef GLUT_APIENTRY_DEFINED
# undef APIENTRY
#endif
#ifdef GLUT_WINGDIAPI_DEFINED
# undef GLUT_WINGDIAPI_DEFINED
# undef WINGDIAPI
#endif
#endif /* __glut_h__ */

1121
Common/GL/glxew.h Normal file

File diff suppressed because it is too large Load Diff

805
Common/GL/glxext.h Normal file
View File

@@ -0,0 +1,805 @@
#ifndef __glxext_h_
#define __glxext_h_
#ifdef __cplusplus
extern "C" {
#endif
/*
** License Applicability. Except to the extent portions of this file are
** made subject to an alternative license as permitted in the SGI Free
** Software License B, Version 1.1 (the "License"), the contents of this
** file are subject only to the provisions of the License. You may not use
** this file except in compliance with the License. You may obtain a copy
** of the License at Silicon Graphics, Inc., attn: Legal Services, 1600
** Amphitheatre Parkway, Mountain View, CA 94043-1351, or at:
**
** http://oss.sgi.com/projects/FreeB
**
** Note that, as provided in the License, the Software is distributed on an
** "AS IS" basis, with ALL EXPRESS AND IMPLIED WARRANTIES AND CONDITIONS
** DISCLAIMED, INCLUDING, WITHOUT LIMITATION, ANY IMPLIED WARRANTIES AND
** CONDITIONS OF MERCHANTABILITY, SATISFACTORY QUALITY, FITNESS FOR A
** PARTICULAR PURPOSE, AND NON-INFRINGEMENT.
**
** Original Code. The Original Code is: OpenGL Sample Implementation,
** Version 1.2.1, released January 26, 2000, developed by Silicon Graphics,
** Inc. The Original Code is Copyright (c) 1991-2004 Silicon Graphics, Inc.
** Copyright in any portions created by third parties is as indicated
** elsewhere herein. All Rights Reserved.
**
** Additional Notice Provisions: This software was created using the
** OpenGL(R) version 1.2.1 Sample Implementation published by SGI, but has
** not been independently verified as being compliant with the OpenGL(R)
** version 1.2.1 Specification.
*/
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64) && !defined(APIENTRY) && !defined(__CYGWIN__) && !defined(__SCITECH_SNAP__)
#define WIN32_LEAN_AND_MEAN 1
#include <windows.h>
#endif
#ifndef APIENTRY
#define APIENTRY
#endif
#ifndef APIENTRYP
#define APIENTRYP APIENTRY *
#endif
#ifndef GLAPI
#define GLAPI extern
#endif
/*************************************************************/
/* Header file version number, required by OpenGL ABI for Linux */
/* glxext.h last updated 2005/01/20 */
/* Current version at http://oss.sgi.com/projects/ogl-sample/registry/ */
#define GLX_GLXEXT_VERSION 10
#ifndef GLX_ARB_get_proc_address
#endif
#ifndef GLX_ARB_multisample
#define GLX_SAMPLE_BUFFERS_ARB 100000
#define GLX_SAMPLES_ARB 100001
#endif
#ifndef GLX_ARB_fbconfig_float
#define GLX_RGBA_FLOAT_TYPE_ARB 0x20B9
#define GLX_RGBA_FLOAT_BIT_ARB 0x00000004
#endif
#ifndef GLX_SGIS_multisample
#define GLX_SAMPLE_BUFFERS_SGIS 100000
#define GLX_SAMPLES_SGIS 100001
#endif
#ifndef GLX_EXT_visual_info
#define GLX_X_VISUAL_TYPE_EXT 0x22
#define GLX_TRANSPARENT_TYPE_EXT 0x23
#define GLX_TRANSPARENT_INDEX_VALUE_EXT 0x24
#define GLX_TRANSPARENT_RED_VALUE_EXT 0x25
#define GLX_TRANSPARENT_GREEN_VALUE_EXT 0x26
#define GLX_TRANSPARENT_BLUE_VALUE_EXT 0x27
#define GLX_TRANSPARENT_ALPHA_VALUE_EXT 0x28
#define GLX_NONE_EXT 0x8000
#define GLX_TRUE_COLOR_EXT 0x8002
#define GLX_DIRECT_COLOR_EXT 0x8003
#define GLX_PSEUDO_COLOR_EXT 0x8004
#define GLX_STATIC_COLOR_EXT 0x8005
#define GLX_GRAY_SCALE_EXT 0x8006
#define GLX_STATIC_GRAY_EXT 0x8007
#define GLX_TRANSPARENT_RGB_EXT 0x8008
#define GLX_TRANSPARENT_INDEX_EXT 0x8009
#endif
#ifndef GLX_SGI_swap_control
#endif
#ifndef GLX_SGI_video_sync
#endif
#ifndef GLX_SGI_make_current_read
#endif
#ifndef GLX_SGIX_video_source
#endif
#ifndef GLX_EXT_visual_rating
#define GLX_VISUAL_CAVEAT_EXT 0x20
#define GLX_SLOW_VISUAL_EXT 0x8001
#define GLX_NON_CONFORMANT_VISUAL_EXT 0x800D
/* reuse GLX_NONE_EXT */
#endif
#ifndef GLX_EXT_import_context
#define GLX_SHARE_CONTEXT_EXT 0x800A
#define GLX_VISUAL_ID_EXT 0x800B
#define GLX_SCREEN_EXT 0x800C
#endif
#ifndef GLX_SGIX_fbconfig
#define GLX_WINDOW_BIT_SGIX 0x00000001
#define GLX_PIXMAP_BIT_SGIX 0x00000002
#define GLX_RGBA_BIT_SGIX 0x00000001
#define GLX_COLOR_INDEX_BIT_SGIX 0x00000002
#define GLX_DRAWABLE_TYPE_SGIX 0x8010
#define GLX_RENDER_TYPE_SGIX 0x8011
#define GLX_X_RENDERABLE_SGIX 0x8012
#define GLX_FBCONFIG_ID_SGIX 0x8013
#define GLX_RGBA_TYPE_SGIX 0x8014
#define GLX_COLOR_INDEX_TYPE_SGIX 0x8015
/* reuse GLX_SCREEN_EXT */
#endif
#ifndef GLX_SGIX_pbuffer
#define GLX_PBUFFER_BIT_SGIX 0x00000004
#define GLX_BUFFER_CLOBBER_MASK_SGIX 0x08000000
#define GLX_FRONT_LEFT_BUFFER_BIT_SGIX 0x00000001
#define GLX_FRONT_RIGHT_BUFFER_BIT_SGIX 0x00000002
#define GLX_BACK_LEFT_BUFFER_BIT_SGIX 0x00000004
#define GLX_BACK_RIGHT_BUFFER_BIT_SGIX 0x00000008
#define GLX_AUX_BUFFERS_BIT_SGIX 0x00000010
#define GLX_DEPTH_BUFFER_BIT_SGIX 0x00000020
#define GLX_STENCIL_BUFFER_BIT_SGIX 0x00000040
#define GLX_ACCUM_BUFFER_BIT_SGIX 0x00000080
#define GLX_SAMPLE_BUFFERS_BIT_SGIX 0x00000100
#define GLX_MAX_PBUFFER_WIDTH_SGIX 0x8016
#define GLX_MAX_PBUFFER_HEIGHT_SGIX 0x8017
#define GLX_MAX_PBUFFER_PIXELS_SGIX 0x8018
#define GLX_OPTIMAL_PBUFFER_WIDTH_SGIX 0x8019
#define GLX_OPTIMAL_PBUFFER_HEIGHT_SGIX 0x801A
#define GLX_PRESERVED_CONTENTS_SGIX 0x801B
#define GLX_LARGEST_PBUFFER_SGIX 0x801C
#define GLX_WIDTH_SGIX 0x801D
#define GLX_HEIGHT_SGIX 0x801E
#define GLX_EVENT_MASK_SGIX 0x801F
#define GLX_DAMAGED_SGIX 0x8020
#define GLX_SAVED_SGIX 0x8021
#define GLX_WINDOW_SGIX 0x8022
#define GLX_PBUFFER_SGIX 0x8023
#endif
#ifndef GLX_SGI_cushion
#endif
#ifndef GLX_SGIX_video_resize
#define GLX_SYNC_FRAME_SGIX 0x00000000
#define GLX_SYNC_SWAP_SGIX 0x00000001
#endif
#ifndef GLX_SGIX_dmbuffer
#define GLX_DIGITAL_MEDIA_PBUFFER_SGIX 0x8024
#endif
#ifndef GLX_SGIX_swap_group
#endif
#ifndef GLX_SGIX_swap_barrier
#endif
#ifndef GLX_SGIS_blended_overlay
#define GLX_BLENDED_RGBA_SGIS 0x8025
#endif
#ifndef GLX_SGIS_shared_multisample
#define GLX_MULTISAMPLE_SUB_RECT_WIDTH_SGIS 0x8026
#define GLX_MULTISAMPLE_SUB_RECT_HEIGHT_SGIS 0x8027
#endif
#ifndef GLX_SUN_get_transparent_index
#endif
#ifndef GLX_3DFX_multisample
#define GLX_SAMPLE_BUFFERS_3DFX 0x8050
#define GLX_SAMPLES_3DFX 0x8051
#endif
#ifndef GLX_MESA_copy_sub_buffer
#endif
#ifndef GLX_MESA_pixmap_colormap
#endif
#ifndef GLX_MESA_release_buffers
#endif
#ifndef GLX_MESA_set_3dfx_mode
#define GLX_3DFX_WINDOW_MODE_MESA 0x1
#define GLX_3DFX_FULLSCREEN_MODE_MESA 0x2
#endif
#ifndef GLX_SGIX_visual_select_group
#define GLX_VISUAL_SELECT_GROUP_SGIX 0x8028
#endif
#ifndef GLX_OML_swap_method
#define GLX_SWAP_METHOD_OML 0x8060
#define GLX_SWAP_EXCHANGE_OML 0x8061
#define GLX_SWAP_COPY_OML 0x8062
#define GLX_SWAP_UNDEFINED_OML 0x8063
#endif
#ifndef GLX_OML_sync_control
#endif
#ifndef GLX_NV_float_buffer
#define GLX_FLOAT_COMPONENTS_NV 0x20B0
#endif
#ifndef GLX_SGIX_hyperpipe
#define GLX_HYPERPIPE_PIPE_NAME_LENGTH_SGIX 80
#define GLX_BAD_HYPERPIPE_CONFIG_SGIX 91
#define GLX_BAD_HYPERPIPE_SGIX 92
#define GLX_HYPERPIPE_DISPLAY_PIPE_SGIX 0x00000001
#define GLX_HYPERPIPE_RENDER_PIPE_SGIX 0x00000002
#define GLX_PIPE_RECT_SGIX 0x00000001
#define GLX_PIPE_RECT_LIMITS_SGIX 0x00000002
#define GLX_HYPERPIPE_STEREO_SGIX 0x00000003
#define GLX_HYPERPIPE_PIXEL_AVERAGE_SGIX 0x00000004
#define GLX_HYPERPIPE_ID_SGIX 0x8030
#endif
#ifndef GLX_MESA_agp_offset
#endif
/*************************************************************/
#ifndef GLX_ARB_get_proc_address
/*
* Linux OpenGL ABI specifies glXGetProcAddressARB should be
* in glx.h moving related defines there as well.
*/
#endif
#ifndef GLX_SGIX_video_source
typedef XID GLXVideoSourceSGIX;
#endif
#ifndef GLX_SGIX_fbconfig
typedef XID GLXFBConfigIDSGIX;
typedef struct __GLXFBConfigRec *GLXFBConfigSGIX;
#endif
#ifndef GLX_SGIX_pbuffer
typedef XID GLXPbufferSGIX;
typedef struct
{
int type;
unsigned long serial; /* # of last request processed by server */
Bool send_event; /* true if this came for SendEvent request */
Display *display; /* display the event was read from */
GLXDrawable drawable; /* i.d. of Drawable */
int event_type; /* GLX_DAMAGED_SGIX or GLX_SAVED_SGIX */
int draw_type; /* GLX_WINDOW_SGIX or GLX_PBUFFER_SGIX */
unsigned int mask; /* mask indicating which buffers are affected*/
int x, y;
int width, height;
int count; /* if nonzero, at least this many more */
} GLXBufferClobberEventSGIX;
#endif
#ifndef GLX_NV_swap_group
#endif
#ifndef GLX_NV_video_out
/*
* GLXVideoDeviceNV is an opaque handle to a video device (part of the
* GLX_NV_video_out extension).
*/
typedef unsigned int GLXVideoDeviceNV;
/* glXBindVideoImageNV iVideoBuffer values (NV_video_out) */
#define GLX_VIDEO_OUT_COLOR_NV 0x20C3
#define GLX_VIDEO_OUT_ALPHA_NV 0x20C4
#define GLX_VIDEO_OUT_DEPTH_NV 0x20C5
#define GLX_VIDEO_OUT_COLOR_AND_ALPHA_NV 0x20C6
#define GLX_VIDEO_OUT_COLOR_AND_DEPTH_NV 0x20C7
/* glXSendPbufferToVideoNV iBufferType values (NV_video_out) */
#define GLX_VIDEO_OUT_FRAME_NV 0x20C8
#define GLX_VIDEO_OUT_FIELD_1_NV 0x20C9
#define GLX_VIDEO_OUT_FIELD_2_NV 0x20CA
#endif
#ifndef GLX_EXT_texture_from_pixmap
/* New glXGetFBConfigAttrib <attrib_list> tokens */
#define GLX_BIND_TO_TEXTURE_RGB_EXT 0x20D0
#define GLX_BIND_TO_TEXTURE_RGBA_EXT 0x20D1
#define GLX_BIND_TO_MIPMAP_TEXTURE_EXT 0x20D2
#define GLX_BIND_TO_TEXTURE_TARGETS_EXT 0x20D3
#define GLX_Y_INVERTED_EXT 0x20D4
/* New glXCreatePixmap attributes and glXQueryDrawable attributes */
#define GLX_TEXTURE_FORMAT_EXT 0x20D5
#define GLX_TEXTURE_TARGET_EXT 0x20D6
#define GLX_MIPMAP_TEXTURE_EXT 0x20D7
/* Values for GLX_TEXTURE_FORMAT_EXT */
#define GLX_TEXTURE_FORMAT_NONE_EXT 0x20D8
#define GLX_TEXTURE_FORMAT_RGB_EXT 0x20D9
#define GLX_TEXTURE_FORMAT_RGBA_EXT 0x20DA
/* Bits for GLX_BIND_TO_TEXTURE_TARGETS_EXT mask */
#define GLX_TEXTURE_1D_BIT_EXT 0x00000001
#define GLX_TEXTURE_2D_BIT_EXT 0x00000002
#define GLX_TEXTURE_RECTANGLE_BIT_EXT 0x00000004
/* Values for GLX_TEXTURE_TARGET_EXT */
#define GLX_TEXTURE_1D_EXT 0x20DB
#define GLX_TEXTURE_2D_EXT 0x20DC
#define GLX_TEXTURE_RECTANGLE_EXT 0x20DD
/*
* Values for the buffer parameter of glXBindTexImageEXT and
* glXReleaseTexImageEXT
*/
#define GLX_FRONT_LEFT_EXT 0x20DE
#define GLX_FRONT_RIGHT_EXT 0x20DF
#define GLX_BACK_LEFT_EXT 0x20E0
#define GLX_BACK_RIGHT_EXT 0x20E1
#define GLX_FRONT_EXT GLX_FRONT_LEFT_EXT
#define GLX_BACK_EXT GLX_BACK_LEFT_EXT
#define GLX_AUX0_EXT 0x20E2
#define GLX_AUX1_EXT 0x20E3
#define GLX_AUX2_EXT 0x20E4
#define GLX_AUX3_EXT 0x20E5
#define GLX_AUX4_EXT 0x20E6
#define GLX_AUX5_EXT 0x20E7
#define GLX_AUX6_EXT 0x20E8
#define GLX_AUX7_EXT 0x20E9
#define GLX_AUX8_EXT 0x20EA
#define GLX_AUX9_EXT 0x20EB
#endif
/* Define int32_t and int64_t types for UST/MSC */
/* (as used in the GLX_OML_sync_control extension). */
#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
#include <inttypes.h>
#elif defined( __VMS ) || defined(__FreeBSD__)
#include <inttypes.h>
#elif (defined(__sun__) && defined(__svr4__)) || (defined(__sun) && defined(__SVR4))
#include <inttypes.h>
#elif defined(__SCO__) || defined(__USLC__) || defined(__linux__)
#include <stdint.h>
#elif defined(__UNIXOS2__) || defined(__SOL64__)
typedef long int int32_t;
typedef long long int int64_t;
#else
#error "int32_t and int64_t are undefined!"
#endif
#ifndef GLX_ARB_get_proc_address
/* Moved to glx.h */
#endif
#ifndef GLX_ARB_multisample
#define GLX_ARB_multisample 1
#endif
#ifndef GLX_ARB_fbconfig_float
#define GLX_ARB_fbconfig_float 1
#endif
#ifndef GLX_SGIS_multisample
#define GLX_SGIS_multisample 1
#endif
#ifndef GLX_EXT_visual_info
#define GLX_EXT_visual_info 1
#endif
#ifndef GLX_SGI_swap_control
#define GLX_SGI_swap_control 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern int glXSwapIntervalSGI(int);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef int (* PFNGLXSWAPINTERVALSGIPROC)(int interval);
#endif
#ifndef GLX_SGI_video_sync
#define GLX_SGI_video_sync 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern int glXGetVideoSyncSGI(unsigned int *);
extern int glXWaitVideoSyncSGI(int, int, unsigned int *);
extern int glXGetRefreshRateSGI(unsigned int *);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef int (* PFNGLXGETVIDEOSYNCSGIPROC)(unsigned int *count);
typedef int (* PFNGLXWAITVIDEOSYNCSGIPROC)(int divisor, int remainder, unsigned int *count);
typedef int (* PFNGLXGETREFRESHRATESGIPROC)(unsigned int *);
#endif
#ifndef GLX_SGI_make_current_read
#define GLX_SGI_make_current_read 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern Bool glXMakeCurrentReadSGI(Display *, GLXDrawable, GLXDrawable, GLXContext);
extern GLXDrawable glXGetCurrentReadDrawableSGI(void);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef Bool(* PFNGLXMAKECURRENTREADSGIPROC)(Display *dpy, GLXDrawable draw, GLXDrawable read, GLXContext ctx);
typedef GLXDrawable(* PFNGLXGETCURRENTREADDRAWABLESGIPROC)(void);
#endif
#ifndef GLX_SGIX_video_source
#define GLX_SGIX_video_source 1
#ifdef _VL_H
#ifdef GLX_GLXEXT_PROTOTYPES
extern GLXVideoSourceSGIX glXCreateGLXVideoSourceSGIX(Display *, int, VLServer, VLPath, int, VLNode);
extern void glXDestroyGLXVideoSourceSGIX(Display *, GLXVideoSourceSGIX);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef GLXVideoSourceSGIX(* PFNGLXCREATEGLXVIDEOSOURCESGIXPROC)(Display *display, int screen, VLServer server, VLPath path, int nodeClass, VLNode drainNode);
typedef void (* PFNGLXDESTROYGLXVIDEOSOURCESGIXPROC)(Display *dpy, GLXVideoSourceSGIX glxvideosource);
#endif /* _VL_H */
#endif
#ifndef GLX_EXT_visual_rating
#define GLX_EXT_visual_rating 1
#endif
#ifndef GLX_EXT_import_context
#define GLX_EXT_import_context 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern Display *glXGetCurrentDisplayEXT(void);
extern int glXQueryContextInfoEXT(Display *, GLXContext, int, int *);
extern GLXContextID glXGetContextIDEXT(const GLXContext);
extern GLXContext glXImportContextEXT(Display *, GLXContextID);
extern void glXFreeContextEXT(Display *, GLXContext);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef Display *(* PFNGLXGETCURRENTDISPLAYEXTPROC)(void);
typedef int (* PFNGLXQUERYCONTEXTINFOEXTPROC)(Display *dpy, GLXContext context, int attribute, int *value);
typedef GLXContextID(* PFNGLXGETCONTEXTIDEXTPROC)(const GLXContext context);
typedef GLXContext(* PFNGLXIMPORTCONTEXTEXTPROC)(Display *dpy, GLXContextID contextID);
typedef void (* PFNGLXFREECONTEXTEXTPROC)(Display *dpy, GLXContext context);
#endif
#ifndef GLX_SGIX_fbconfig
#define GLX_SGIX_fbconfig 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern int glXGetFBConfigAttribSGIX(Display *, GLXFBConfigSGIX, int, int *);
extern GLXFBConfigSGIX *glXChooseFBConfigSGIX(Display *, int, int *, int *);
extern GLXPixmap glXCreateGLXPixmapWithConfigSGIX(Display *, GLXFBConfigSGIX, Pixmap);
extern GLXContext glXCreateContextWithConfigSGIX(Display *, GLXFBConfigSGIX, int, GLXContext, Bool);
extern XVisualInfo *glXGetVisualFromFBConfigSGIX(Display *, GLXFBConfigSGIX);
extern GLXFBConfigSGIX glXGetFBConfigFromVisualSGIX(Display *, XVisualInfo *);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef int (* PFNGLXGETFBCONFIGATTRIBSGIXPROC)(Display *dpy, GLXFBConfigSGIX config, int attribute, int *value);
typedef GLXFBConfigSGIX *(* PFNGLXCHOOSEFBCONFIGSGIXPROC)(Display *dpy, int screen, int *attrib_list, int *nelements);
typedef GLXPixmap(* PFNGLXCREATEGLXPIXMAPWITHCONFIGSGIXPROC)(Display *dpy, GLXFBConfigSGIX config, Pixmap pixmap);
typedef GLXContext(* PFNGLXCREATECONTEXTWITHCONFIGSGIXPROC)(Display *dpy, GLXFBConfigSGIX config, int render_type, GLXContext share_list, Bool direct);
typedef XVisualInfo *(* PFNGLXGETVISUALFROMFBCONFIGSGIXPROC)(Display *dpy, GLXFBConfigSGIX config);
typedef GLXFBConfigSGIX(* PFNGLXGETFBCONFIGFROMVISUALSGIXPROC)(Display *dpy, XVisualInfo *vis);
#endif
#ifndef GLX_SGIX_pbuffer
#define GLX_SGIX_pbuffer 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern GLXPbufferSGIX glXCreateGLXPbufferSGIX(Display *, GLXFBConfigSGIX, unsigned int, unsigned int, int *);
extern void glXDestroyGLXPbufferSGIX(Display *, GLXPbufferSGIX);
extern int glXQueryGLXPbufferSGIX(Display *, GLXPbufferSGIX, int, unsigned int *);
extern void glXSelectEventSGIX(Display *, GLXDrawable, unsigned long);
extern void glXGetSelectedEventSGIX(Display *, GLXDrawable, unsigned long *);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef GLXPbufferSGIX(* PFNGLXCREATEGLXPBUFFERSGIXPROC)(Display *dpy, GLXFBConfigSGIX config, unsigned int width, unsigned int height, int *attrib_list);
typedef void (* PFNGLXDESTROYGLXPBUFFERSGIXPROC)(Display *dpy, GLXPbufferSGIX pbuf);
typedef int (* PFNGLXQUERYGLXPBUFFERSGIXPROC)(Display *dpy, GLXPbufferSGIX pbuf, int attribute, unsigned int *value);
typedef void (* PFNGLXSELECTEVENTSGIXPROC)(Display *dpy, GLXDrawable drawable, unsigned long mask);
typedef void (* PFNGLXGETSELECTEDEVENTSGIXPROC)(Display *dpy, GLXDrawable drawable, unsigned long *mask);
#endif
#ifndef GLX_SGI_cushion
#define GLX_SGI_cushion 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern void glXCushionSGI(Display *, Window, float);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef void (* PFNGLXCUSHIONSGIPROC)(Display *dpy, Window window, float cushion);
#endif
#ifndef GLX_SGIX_video_resize
#define GLX_SGIX_video_resize 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern int glXBindChannelToWindowSGIX(Display *, int, int, Window);
extern int glXChannelRectSGIX(Display *, int, int, int, int, int, int);
extern int glXQueryChannelRectSGIX(Display *, int, int, int *, int *, int *, int *);
extern int glXQueryChannelDeltasSGIX(Display *, int, int, int *, int *, int *, int *);
extern int glXChannelRectSyncSGIX(Display *, int, int, GLenum);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef int (* PFNGLXBINDCHANNELTOWINDOWSGIXPROC)(Display *display, int screen, int channel, Window window);
typedef int (* PFNGLXCHANNELRECTSGIXPROC)(Display *display, int screen, int channel, int x, int y, int w, int h);
typedef int (* PFNGLXQUERYCHANNELRECTSGIXPROC)(Display *display, int screen, int channel, int *dx, int *dy, int *dw, int *dh);
typedef int (* PFNGLXQUERYCHANNELDELTASSGIXPROC)(Display *display, int screen, int channel, int *x, int *y, int *w, int *h);
typedef int (* PFNGLXCHANNELRECTSYNCSGIXPROC)(Display *display, int screen, int channel, GLenum synctype);
#endif
#ifndef GLX_SGIX_dmbuffer
#define GLX_SGIX_dmbuffer 1
#ifdef _DM_BUFFER_H_
#ifdef GLX_GLXEXT_PROTOTYPES
extern Bool glXAssociateDMPbufferSGIX(Display *, GLXPbufferSGIX, DMparams *, DMbuffer);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef Bool(* PFNGLXASSOCIATEDMPBUFFERSGIXPROC)(Display *dpy, GLXPbufferSGIX pbuffer, DMparams *params, DMbuffer dmbuffer);
#endif /* _DM_BUFFER_H_ */
#endif
#ifndef GLX_SGIX_swap_group
#define GLX_SGIX_swap_group 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern void glXJoinSwapGroupSGIX(Display *, GLXDrawable, GLXDrawable);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef void (* PFNGLXJOINSWAPGROUPSGIXPROC)(Display *dpy, GLXDrawable drawable, GLXDrawable member);
#endif
#ifndef GLX_SGIX_swap_barrier
#define GLX_SGIX_swap_barrier 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern void glXBindSwapBarrierSGIX(Display *, GLXDrawable, int);
extern Bool glXQueryMaxSwapBarriersSGIX(Display *, int, int *);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef void (* PFNGLXBINDSWAPBARRIERSGIXPROC)(Display *dpy, GLXDrawable drawable, int barrier);
typedef Bool(* PFNGLXQUERYMAXSWAPBARRIERSSGIXPROC)(Display *dpy, int screen, int *max);
#endif
#ifndef GLX_SUN_get_transparent_index
#define GLX_SUN_get_transparent_index 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern Status glXGetTransparentIndexSUN(Display *, Window, Window, long *);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef Status(* PFNGLXGETTRANSPARENTINDEXSUNPROC)(Display *dpy, Window overlay, Window underlay, long *pTransparentIndex);
#endif
#ifndef GLX_MESA_copy_sub_buffer
#define GLX_MESA_copy_sub_buffer 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern void glXCopySubBufferMESA(Display *, GLXDrawable, int, int, int, int);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef void (* PFNGLXCOPYSUBBUFFERMESAPROC)(Display *dpy, GLXDrawable drawable, int x, int y, int width, int height);
#endif
#ifndef GLX_MESA_pixmap_colormap
#define GLX_MESA_pixmap_colormap 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern GLXPixmap glXCreateGLXPixmapMESA(Display *, XVisualInfo *, Pixmap, Colormap);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef GLXPixmap(* PFNGLXCREATEGLXPIXMAPMESAPROC)(Display *dpy, XVisualInfo *visual, Pixmap pixmap, Colormap cmap);
#endif
#ifndef GLX_MESA_release_buffers
#define GLX_MESA_release_buffers 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern Bool glXReleaseBuffersMESA(Display *, GLXDrawable);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef Bool(* PFNGLXRELEASEBUFFERSMESAPROC)(Display *dpy, GLXDrawable drawable);
#endif
#ifndef GLX_MESA_set_3dfx_mode
#define GLX_MESA_set_3dfx_mode 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern Bool glXSet3DfxModeMESA(int);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef Bool(* PFNGLXSET3DFXMODEMESAPROC)(int mode);
#endif
#ifndef GLX_SGIX_visual_select_group
#define GLX_SGIX_visual_select_group 1
#endif
#ifndef GLX_OML_swap_method
#define GLX_OML_swap_method 1
#endif
#ifndef GLX_OML_sync_control
#define GLX_OML_sync_control 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern Bool glXGetSyncValuesOML(Display *, GLXDrawable, int64_t *, int64_t *, int64_t *);
extern Bool glXGetMscRateOML(Display *, GLXDrawable, int32_t *, int32_t *);
extern int64_t glXSwapBuffersMscOML(Display *, GLXDrawable, int64_t, int64_t, int64_t);
extern Bool glXWaitForMscOML(Display *, GLXDrawable, int64_t, int64_t, int64_t, int64_t *, int64_t *, int64_t *);
extern Bool glXWaitForSbcOML(Display *, GLXDrawable, int64_t, int64_t *, int64_t *, int64_t *);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef Bool(* PFNGLXGETSYNCVALUESOMLPROC)(Display *dpy, GLXDrawable drawable, int64_t *ust, int64_t *msc, int64_t *sbc);
typedef Bool(* PFNGLXGETMSCRATEOMLPROC)(Display *dpy, GLXDrawable drawable, int32_t *numerator, int32_t *denominator);
typedef int64_t (* PFNGLXSWAPBUFFERSMSCOMLPROC)(Display *dpy, GLXDrawable drawable, int64_t target_msc, int64_t divisor, int64_t remainder);
typedef Bool(* PFNGLXWAITFORMSCOMLPROC)(Display *dpy, GLXDrawable drawable, int64_t target_msc, int64_t divisor, int64_t remainder, int64_t *ust, int64_t *msc, int64_t *sbc);
typedef Bool(* PFNGLXWAITFORSBCOMLPROC)(Display *dpy, GLXDrawable drawable, int64_t target_sbc, int64_t *ust, int64_t *msc, int64_t *sbc);
#endif
#ifndef GLX_NV_float_buffer
#define GLX_NV_float_buffer 1
#endif
#ifndef GLX_SGIX_hyperpipe
#define GLX_SGIX_hyperpipe 1
typedef struct
{
char pipeName[GLX_HYPERPIPE_PIPE_NAME_LENGTH_SGIX];
int networkId;
} GLXHyperpipeNetworkSGIX;
typedef struct
{
char pipeName[GLX_HYPERPIPE_PIPE_NAME_LENGTH_SGIX];
int channel;
unsigned int
participationType;
int timeSlice;
} GLXHyperpipeConfigSGIX;
typedef struct
{
char pipeName[GLX_HYPERPIPE_PIPE_NAME_LENGTH_SGIX];
int srcXOrigin, srcYOrigin, srcWidth, srcHeight;
int destXOrigin, destYOrigin, destWidth, destHeight;
} GLXPipeRect;
typedef struct
{
char pipeName[GLX_HYPERPIPE_PIPE_NAME_LENGTH_SGIX];
int XOrigin, YOrigin, maxHeight, maxWidth;
} GLXPipeRectLimits;
#ifdef GLX_GLXEXT_PROTOTYPES
extern GLXHyperpipeNetworkSGIX *glXQueryHyperpipeNetworkSGIX(Display *, int *);
extern int glXHyperpipeConfigSGIX(Display *, int, int, GLXHyperpipeConfigSGIX *, int *);
extern GLXHyperpipeConfigSGIX *glXQueryHyperpipeConfigSGIX(Display *, int, int *);
extern int glXDestroyHyperpipeConfigSGIX(Display *, int);
extern int glXBindHyperpipeSGIX(Display *, int);
extern int glXQueryHyperpipeBestAttribSGIX(Display *, int, int, int, void *, void *);
extern int glXHyperpipeAttribSGIX(Display *, int, int, int, void *);
extern int glXQueryHyperpipeAttribSGIX(Display *, int, int, int, void *);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef GLXHyperpipeNetworkSGIX *(* PFNGLXQUERYHYPERPIPENETWORKSGIXPROC)(Display *dpy, int *npipes);
typedef int (* PFNGLXHYPERPIPECONFIGSGIXPROC)(Display *dpy, int networkId, int npipes, GLXHyperpipeConfigSGIX *cfg, int *hpId);
typedef GLXHyperpipeConfigSGIX *(* PFNGLXQUERYHYPERPIPECONFIGSGIXPROC)(Display *dpy, int hpId, int *npipes);
typedef int (* PFNGLXDESTROYHYPERPIPECONFIGSGIXPROC)(Display *dpy, int hpId);
typedef int (* PFNGLXBINDHYPERPIPESGIXPROC)(Display *dpy, int hpId);
typedef int (* PFNGLXQUERYHYPERPIPEBESTATTRIBSGIXPROC)(Display *dpy, int timeSlice, int attrib, int size, void *attribList, void *returnAttribList);
typedef int (* PFNGLXHYPERPIPEATTRIBSGIXPROC)(Display *dpy, int timeSlice, int attrib, int size, void *attribList);
typedef int (* PFNGLXQUERYHYPERPIPEATTRIBSGIXPROC)(Display *dpy, int timeSlice, int attrib, int size, void *returnAttribList);
#endif
#ifndef GLX_MESA_agp_offset
#define GLX_MESA_agp_offset 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern unsigned int glXGetAGPOffsetMESA(const void *);
#endif /* GLX_GLXEXT_PROTOTYPES */
typedef unsigned int (* PFNGLXGETAGPOFFSETMESAPROC)(const void *pointer);
#endif
/*
* GLX_NV_vertex_array_range is not a real extension name...
*/
#ifndef GLX_NV_vertex_array_range
#define GLX_NV_vertex_array_range 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern void *glXAllocateMemoryNV(GLsizei size, GLfloat readfreq,
GLfloat writefreq, GLfloat priority);
extern void glXFreeMemoryNV(GLvoid *pointer);
#endif
typedef void *(* PFNGLXALLOCATEMEMORYNVPROC)(GLsizei size,
GLfloat readfreq,
GLfloat writefreq,
GLfloat priority);
typedef void (* PFNGLXFREEMEMORYNVPROC)(GLvoid *pointer);
#endif
#ifndef GLX_NV_swap_group
#define GLX_NV_swap_group 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern Bool glXJoinSwapGroupNV(Display *dpy, GLXDrawable drawable,
GLuint group);
extern Bool glXBindSwapBarrierNV(Display *dpy, GLuint group, GLuint barrier);
extern Bool glXQuerySwapGroupNV(Display *dpy, GLXDrawable drawable,
GLuint *group, GLuint *barrier);
extern Bool glXQueryMaxSwapGroupsNV(Display *dpy, int screen,
GLuint *maxGroups, GLuint *maxBarriers);
extern Bool glXQueryFrameCountNV(Display *dpy, int screen, GLuint *count);
extern Bool glXResetFrameCountNV(Display *dpy, int screen);
#endif
typedef Bool(* PFNGLXJOINSWAPGROUPNVPROC)(Display *dpy,
GLXDrawable drawable,
GLuint group);
typedef Bool(* PFNGLXBINDSWAPBARRIERNVPROC)(Display *dpy,
GLuint group,
GLuint barrier);
typedef Bool(* PFNGLXQUERYSWAPGROUPNVPROC)(Display *dpy,
GLXDrawable drawable,
GLuint *group,
GLuint *barrier);
typedef Bool(* PFNGLXQUERYMAXSWAPGROUPSNVPROC)(Display *dpy,
int screen,
GLuint *maxGroups,
GLuint *maxBarriers);
typedef Bool(* PFNGLXQUERYFRAMECOUNTNVPROC)(Display *dpy,
int screen,
GLuint *count);
typedef Bool(* PFNGLXRESETFRAMECOUNTNVPROC)(Display *dpy, int screen);
#endif
#ifndef GLX_NV_video_out
#define GLX_NV_video_out 1
#ifdef GLX_GLXEXT_PROTOTYPES
extern int glXGetVideoDeviceNV(Display *dpy, int screen, int numVideoDevices,
GLXVideoDeviceNV *pVideoDevice);
extern int glXReleaseVideoDeviceNV(Display *dpy, int screen,
GLXVideoDeviceNV VideoDevice);
extern int glXBindVideoImageNV(Display *dpy, GLXVideoDeviceNV VideoDevice,
GLXPbuffer pbuf, int iVideoBuffer);
extern int glXReleaseVideoImageNV(Display *dpy, GLXPbuffer pbuf);
extern int glXSendPbufferToVideoNV(Display *dpy, GLXPbuffer pbuf,
int iBufferType,
unsigned long *pulCounterPbuffer,
GLboolean bBlock);
extern int glXGetVideoInfoNV(Display *dpy, int screen,
GLXVideoDeviceNV VideoDevice,
unsigned long *pulCounterOutputVideo,
unsigned long *pulCounterOutputPbuffer);
#endif
typedef int (* PFNGLXGETVIDEODEVICENVPROC)(Display *dpy,
int screen,
int numVideoDevices,
GLXVideoDeviceNV *pVideoDevice);
typedef int (* PFNGLXRELEASEVIDEODEVICENVPROC)(Display *dpy,
int screen,
GLXVideoDeviceNV VideoDevice);
typedef int (* PFNGLXBINDVIDEOIMAGENVPROC)(Display *dpy,
GLXVideoDeviceNV VideoDevice,
GLXPbuffer pbuf,
int iVideoBuffer);
typedef int (* PFNGLXRELEASEVIDEOIMAGENVPROC)(Display *dpy,
GLXPbuffer pbuf);
typedef int (* PFNGLXSENDPBUFFERTOVIDEONVPROC)(Display *dpy,
GLXPbuffer pbuf,
int iBufferType,
unsigned long *pulCounterPbuffer,
GLboolean bBlock);
typedef int (* PFNGLXGETVIDEOINFONVPROC)(Display *dpy, int screen,
GLXVideoDeviceNV VideoDevice,
unsigned long *pulCounterOutputVideo,
unsigned long *pulCounterOutputPbuffer);
#endif
#ifndef GLX_EXT_texture_from_pixmap
#define GLX_EXT_texture_from_pixmap
#ifdef GLX_GLXEXT_PROTOTYPES
extern void glXBindTexImageEXT(Display *dpy, GLXDrawable drawable,
int buffer, const int *attrib_list);
extern void glXReleaseTexImageEXT(Display *dpy, GLXDrawable drawable,
int buffer);
#endif
typedef void (* PFNGLXBINDTEXIMAGEEXTPROC)(Display *dpy,
GLXDrawable drawable,
int buffer,
const int *attrib_list);
typedef void (* PFNGLXRELEASETEXIMAGEEXTPROC)(Display *dpy,
GLXDrawable drawable,
int buffer);
#endif
#ifdef __cplusplus
}
#endif
#endif

958
Common/GL/wglew.h Normal file
View File

@@ -0,0 +1,958 @@
/*
** The OpenGL Extension Wrangler Library
** Copyright (C) 2002-2006, Milan Ikits <milan ikits[]ieee org>
** Copyright (C) 2002-2006, Marcelo E. Magallon <mmagallo[]debian org>
** Copyright (C) 2002, Lev Povalahev
** All rights reserved.
**
** Redistribution and use in source and binary forms, with or without
** modification, are permitted provided that the following conditions are met:
**
** * Redistributions of source code must retain the above copyright notice,
** this list of conditions and the following disclaimer.
** * Redistributions in binary form must reproduce the above copyright notice,
** this list of conditions and the following disclaimer in the documentation
** and/or other materials provided with the distribution.
** * The name of the author may be used to endorse or promote products
** derived from this software without specific prior written permission.
**
** THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
** AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
** IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
** ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
** LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
** CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
** SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
** INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
** CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
** ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
** THE POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef __wglew_h__
#define __wglew_h__
#define __WGLEW_H__
#ifdef __wglext_h_
#error wglext.h included before wglew.h
#endif
#define __wglext_h_
#if !defined(APIENTRY) && !defined(__CYGWIN__)
# ifndef WIN32_LEAN_AND_MEAN
# define WIN32_LEAN_AND_MEAN 1
# endif
#include <windows.h>
#endif
/*
* GLEW_STATIC needs to be set when using the static version.
* GLEW_BUILD is set when building the DLL version.
*/
#ifdef GLEW_STATIC
# define GLEWAPI extern
#else
# ifdef GLEW_BUILD
# define GLEWAPI extern __declspec(dllexport)
# else
# define GLEWAPI extern __declspec(dllimport)
# endif
#endif
#ifdef __cplusplus
extern "C" {
#endif
/* -------------------------- WGL_3DFX_multisample ------------------------- */
#ifndef WGL_3DFX_multisample
#define WGL_3DFX_multisample 1
#define WGL_SAMPLE_BUFFERS_3DFX 0x2060
#define WGL_SAMPLES_3DFX 0x2061
#define WGLEW_3DFX_multisample WGLEW_GET_VAR(__WGLEW_3DFX_multisample)
#endif /* WGL_3DFX_multisample */
/* ------------------------- WGL_3DL_stereo_control ------------------------ */
#ifndef WGL_3DL_stereo_control
#define WGL_3DL_stereo_control 1
#define WGL_STEREO_EMITTER_ENABLE_3DL 0x2055
#define WGL_STEREO_EMITTER_DISABLE_3DL 0x2056
#define WGL_STEREO_POLARITY_NORMAL_3DL 0x2057
#define WGL_STEREO_POLARITY_INVERT_3DL 0x2058
typedef BOOL (WINAPI *PFNWGLSETSTEREOEMITTERSTATE3DLPROC)(HDC hDC, UINT uState);
#define wglSetStereoEmitterState3DL WGLEW_GET_FUN(__wglewSetStereoEmitterState3DL)
#define WGLEW_3DL_stereo_control WGLEW_GET_VAR(__WGLEW_3DL_stereo_control)
#endif /* WGL_3DL_stereo_control */
/* ------------------------- WGL_ARB_buffer_region ------------------------- */
#ifndef WGL_ARB_buffer_region
#define WGL_ARB_buffer_region 1
#define WGL_FRONT_COLOR_BUFFER_BIT_ARB 0x00000001
#define WGL_BACK_COLOR_BUFFER_BIT_ARB 0x00000002
#define WGL_DEPTH_BUFFER_BIT_ARB 0x00000004
#define WGL_STENCIL_BUFFER_BIT_ARB 0x00000008
typedef HANDLE(WINAPI *PFNWGLCREATEBUFFERREGIONARBPROC)(HDC hDC, int iLayerPlane, UINT uType);
typedef VOID (WINAPI *PFNWGLDELETEBUFFERREGIONARBPROC)(HANDLE hRegion);
typedef BOOL (WINAPI *PFNWGLRESTOREBUFFERREGIONARBPROC)(HANDLE hRegion, int x, int y, int width, int height, int xSrc, int ySrc);
typedef BOOL (WINAPI *PFNWGLSAVEBUFFERREGIONARBPROC)(HANDLE hRegion, int x, int y, int width, int height);
#define wglCreateBufferRegionARB WGLEW_GET_FUN(__wglewCreateBufferRegionARB)
#define wglDeleteBufferRegionARB WGLEW_GET_FUN(__wglewDeleteBufferRegionARB)
#define wglRestoreBufferRegionARB WGLEW_GET_FUN(__wglewRestoreBufferRegionARB)
#define wglSaveBufferRegionARB WGLEW_GET_FUN(__wglewSaveBufferRegionARB)
#define WGLEW_ARB_buffer_region WGLEW_GET_VAR(__WGLEW_ARB_buffer_region)
#endif /* WGL_ARB_buffer_region */
/* ----------------------- WGL_ARB_extensions_string ----------------------- */
#ifndef WGL_ARB_extensions_string
#define WGL_ARB_extensions_string 1
typedef const char *(WINAPI *PFNWGLGETEXTENSIONSSTRINGARBPROC)(HDC hdc);
#define wglGetExtensionsStringARB WGLEW_GET_FUN(__wglewGetExtensionsStringARB)
#define WGLEW_ARB_extensions_string WGLEW_GET_VAR(__WGLEW_ARB_extensions_string)
#endif /* WGL_ARB_extensions_string */
/* ----------------------- WGL_ARB_make_current_read ----------------------- */
#ifndef WGL_ARB_make_current_read
#define WGL_ARB_make_current_read 1
typedef HDC(WINAPI *PFNWGLGETCURRENTREADDCARBPROC)(VOID);
typedef BOOL (WINAPI *PFNWGLMAKECONTEXTCURRENTARBPROC)(HDC hDrawDC, HDC hReadDC, HGLRC hglrc);
#define wglGetCurrentReadDCARB WGLEW_GET_FUN(__wglewGetCurrentReadDCARB)
#define wglMakeContextCurrentARB WGLEW_GET_FUN(__wglewMakeContextCurrentARB)
#define WGLEW_ARB_make_current_read WGLEW_GET_VAR(__WGLEW_ARB_make_current_read)
#endif /* WGL_ARB_make_current_read */
/* -------------------------- WGL_ARB_multisample -------------------------- */
#ifndef WGL_ARB_multisample
#define WGL_ARB_multisample 1
#define WGL_SAMPLE_BUFFERS_ARB 0x2041
#define WGL_SAMPLES_ARB 0x2042
#define WGLEW_ARB_multisample WGLEW_GET_VAR(__WGLEW_ARB_multisample)
#endif /* WGL_ARB_multisample */
/* ---------------------------- WGL_ARB_pbuffer ---------------------------- */
#ifndef WGL_ARB_pbuffer
#define WGL_ARB_pbuffer 1
#define WGL_DRAW_TO_PBUFFER_ARB 0x202D
#define WGL_MAX_PBUFFER_PIXELS_ARB 0x202E
#define WGL_MAX_PBUFFER_WIDTH_ARB 0x202F
#define WGL_MAX_PBUFFER_HEIGHT_ARB 0x2030
#define WGL_PBUFFER_LARGEST_ARB 0x2033
#define WGL_PBUFFER_WIDTH_ARB 0x2034
#define WGL_PBUFFER_HEIGHT_ARB 0x2035
#define WGL_PBUFFER_LOST_ARB 0x2036
DECLARE_HANDLE(HPBUFFERARB);
typedef HPBUFFERARB(WINAPI *PFNWGLCREATEPBUFFERARBPROC)(HDC hDC, int iPixelFormat, int iWidth, int iHeight, const int *piAttribList);
typedef BOOL (WINAPI *PFNWGLDESTROYPBUFFERARBPROC)(HPBUFFERARB hPbuffer);
typedef HDC(WINAPI *PFNWGLGETPBUFFERDCARBPROC)(HPBUFFERARB hPbuffer);
typedef BOOL (WINAPI *PFNWGLQUERYPBUFFERARBPROC)(HPBUFFERARB hPbuffer, int iAttribute, int *piValue);
typedef int (WINAPI *PFNWGLRELEASEPBUFFERDCARBPROC)(HPBUFFERARB hPbuffer, HDC hDC);
#define wglCreatePbufferARB WGLEW_GET_FUN(__wglewCreatePbufferARB)
#define wglDestroyPbufferARB WGLEW_GET_FUN(__wglewDestroyPbufferARB)
#define wglGetPbufferDCARB WGLEW_GET_FUN(__wglewGetPbufferDCARB)
#define wglQueryPbufferARB WGLEW_GET_FUN(__wglewQueryPbufferARB)
#define wglReleasePbufferDCARB WGLEW_GET_FUN(__wglewReleasePbufferDCARB)
#define WGLEW_ARB_pbuffer WGLEW_GET_VAR(__WGLEW_ARB_pbuffer)
#endif /* WGL_ARB_pbuffer */
/* -------------------------- WGL_ARB_pixel_format ------------------------- */
#ifndef WGL_ARB_pixel_format
#define WGL_ARB_pixel_format 1
#define WGL_NUMBER_PIXEL_FORMATS_ARB 0x2000
#define WGL_DRAW_TO_WINDOW_ARB 0x2001
#define WGL_DRAW_TO_BITMAP_ARB 0x2002
#define WGL_ACCELERATION_ARB 0x2003
#define WGL_NEED_PALETTE_ARB 0x2004
#define WGL_NEED_SYSTEM_PALETTE_ARB 0x2005
#define WGL_SWAP_LAYER_BUFFERS_ARB 0x2006
#define WGL_SWAP_METHOD_ARB 0x2007
#define WGL_NUMBER_OVERLAYS_ARB 0x2008
#define WGL_NUMBER_UNDERLAYS_ARB 0x2009
#define WGL_TRANSPARENT_ARB 0x200A
#define WGL_SHARE_DEPTH_ARB 0x200C
#define WGL_SHARE_STENCIL_ARB 0x200D
#define WGL_SHARE_ACCUM_ARB 0x200E
#define WGL_SUPPORT_GDI_ARB 0x200F
#define WGL_SUPPORT_OPENGL_ARB 0x2010
#define WGL_DOUBLE_BUFFER_ARB 0x2011
#define WGL_STEREO_ARB 0x2012
#define WGL_PIXEL_TYPE_ARB 0x2013
#define WGL_COLOR_BITS_ARB 0x2014
#define WGL_RED_BITS_ARB 0x2015
#define WGL_RED_SHIFT_ARB 0x2016
#define WGL_GREEN_BITS_ARB 0x2017
#define WGL_GREEN_SHIFT_ARB 0x2018
#define WGL_BLUE_BITS_ARB 0x2019
#define WGL_BLUE_SHIFT_ARB 0x201A
#define WGL_ALPHA_BITS_ARB 0x201B
#define WGL_ALPHA_SHIFT_ARB 0x201C
#define WGL_ACCUM_BITS_ARB 0x201D
#define WGL_ACCUM_RED_BITS_ARB 0x201E
#define WGL_ACCUM_GREEN_BITS_ARB 0x201F
#define WGL_ACCUM_BLUE_BITS_ARB 0x2020
#define WGL_ACCUM_ALPHA_BITS_ARB 0x2021
#define WGL_DEPTH_BITS_ARB 0x2022
#define WGL_STENCIL_BITS_ARB 0x2023
#define WGL_AUX_BUFFERS_ARB 0x2024
#define WGL_NO_ACCELERATION_ARB 0x2025
#define WGL_GENERIC_ACCELERATION_ARB 0x2026
#define WGL_FULL_ACCELERATION_ARB 0x2027
#define WGL_SWAP_EXCHANGE_ARB 0x2028
#define WGL_SWAP_COPY_ARB 0x2029
#define WGL_SWAP_UNDEFINED_ARB 0x202A
#define WGL_TYPE_RGBA_ARB 0x202B
#define WGL_TYPE_COLORINDEX_ARB 0x202C
#define WGL_TRANSPARENT_RED_VALUE_ARB 0x2037
#define WGL_TRANSPARENT_GREEN_VALUE_ARB 0x2038
#define WGL_TRANSPARENT_BLUE_VALUE_ARB 0x2039
#define WGL_TRANSPARENT_ALPHA_VALUE_ARB 0x203A
#define WGL_TRANSPARENT_INDEX_VALUE_ARB 0x203B
typedef BOOL (WINAPI *PFNWGLCHOOSEPIXELFORMATARBPROC)(HDC hdc, const int *piAttribIList, const FLOAT *pfAttribFList, UINT nMaxFormats, int *piFormats, UINT *nNumFormats);
typedef BOOL (WINAPI *PFNWGLGETPIXELFORMATATTRIBFVARBPROC)(HDC hdc, int iPixelFormat, int iLayerPlane, UINT nAttributes, const int *piAttributes, FLOAT *pfValues);
typedef BOOL (WINAPI *PFNWGLGETPIXELFORMATATTRIBIVARBPROC)(HDC hdc, int iPixelFormat, int iLayerPlane, UINT nAttributes, const int *piAttributes, int *piValues);
#define wglChoosePixelFormatARB WGLEW_GET_FUN(__wglewChoosePixelFormatARB)
#define wglGetPixelFormatAttribfvARB WGLEW_GET_FUN(__wglewGetPixelFormatAttribfvARB)
#define wglGetPixelFormatAttribivARB WGLEW_GET_FUN(__wglewGetPixelFormatAttribivARB)
#define WGLEW_ARB_pixel_format WGLEW_GET_VAR(__WGLEW_ARB_pixel_format)
#endif /* WGL_ARB_pixel_format */
/* ----------------------- WGL_ARB_pixel_format_float ---------------------- */
#ifndef WGL_ARB_pixel_format_float
#define WGL_ARB_pixel_format_float 1
#define WGL_TYPE_RGBA_FLOAT_ARB 0x21A0
#define WGLEW_ARB_pixel_format_float WGLEW_GET_VAR(__WGLEW_ARB_pixel_format_float)
#endif /* WGL_ARB_pixel_format_float */
/* ------------------------- WGL_ARB_render_texture ------------------------ */
#ifndef WGL_ARB_render_texture
#define WGL_ARB_render_texture 1
#define WGL_BIND_TO_TEXTURE_RGB_ARB 0x2070
#define WGL_BIND_TO_TEXTURE_RGBA_ARB 0x2071
#define WGL_TEXTURE_FORMAT_ARB 0x2072
#define WGL_TEXTURE_TARGET_ARB 0x2073
#define WGL_MIPMAP_TEXTURE_ARB 0x2074
#define WGL_TEXTURE_RGB_ARB 0x2075
#define WGL_TEXTURE_RGBA_ARB 0x2076
#define WGL_NO_TEXTURE_ARB 0x2077
#define WGL_TEXTURE_CUBE_MAP_ARB 0x2078
#define WGL_TEXTURE_1D_ARB 0x2079
#define WGL_TEXTURE_2D_ARB 0x207A
#define WGL_MIPMAP_LEVEL_ARB 0x207B
#define WGL_CUBE_MAP_FACE_ARB 0x207C
#define WGL_TEXTURE_CUBE_MAP_POSITIVE_X_ARB 0x207D
#define WGL_TEXTURE_CUBE_MAP_NEGATIVE_X_ARB 0x207E
#define WGL_TEXTURE_CUBE_MAP_POSITIVE_Y_ARB 0x207F
#define WGL_TEXTURE_CUBE_MAP_NEGATIVE_Y_ARB 0x2080
#define WGL_TEXTURE_CUBE_MAP_POSITIVE_Z_ARB 0x2081
#define WGL_TEXTURE_CUBE_MAP_NEGATIVE_Z_ARB 0x2082
#define WGL_FRONT_LEFT_ARB 0x2083
#define WGL_FRONT_RIGHT_ARB 0x2084
#define WGL_BACK_LEFT_ARB 0x2085
#define WGL_BACK_RIGHT_ARB 0x2086
#define WGL_AUX0_ARB 0x2087
#define WGL_AUX1_ARB 0x2088
#define WGL_AUX2_ARB 0x2089
#define WGL_AUX3_ARB 0x208A
#define WGL_AUX4_ARB 0x208B
#define WGL_AUX5_ARB 0x208C
#define WGL_AUX6_ARB 0x208D
#define WGL_AUX7_ARB 0x208E
#define WGL_AUX8_ARB 0x208F
#define WGL_AUX9_ARB 0x2090
typedef BOOL (WINAPI *PFNWGLBINDTEXIMAGEARBPROC)(HPBUFFERARB hPbuffer, int iBuffer);
typedef BOOL (WINAPI *PFNWGLRELEASETEXIMAGEARBPROC)(HPBUFFERARB hPbuffer, int iBuffer);
typedef BOOL (WINAPI *PFNWGLSETPBUFFERATTRIBARBPROC)(HPBUFFERARB hPbuffer, const int *piAttribList);
#define wglBindTexImageARB WGLEW_GET_FUN(__wglewBindTexImageARB)
#define wglReleaseTexImageARB WGLEW_GET_FUN(__wglewReleaseTexImageARB)
#define wglSetPbufferAttribARB WGLEW_GET_FUN(__wglewSetPbufferAttribARB)
#define WGLEW_ARB_render_texture WGLEW_GET_VAR(__WGLEW_ARB_render_texture)
#endif /* WGL_ARB_render_texture */
/* ----------------------- WGL_ATI_pixel_format_float ---------------------- */
#ifndef WGL_ATI_pixel_format_float
#define WGL_ATI_pixel_format_float 1
#define WGL_TYPE_RGBA_FLOAT_ATI 0x21A0
#define GL_RGBA_FLOAT_MODE_ATI 0x8820
#define GL_COLOR_CLEAR_UNCLAMPED_VALUE_ATI 0x8835
#define WGLEW_ATI_pixel_format_float WGLEW_GET_VAR(__WGLEW_ATI_pixel_format_float)
#endif /* WGL_ATI_pixel_format_float */
/* -------------------- WGL_ATI_render_texture_rectangle ------------------- */
#ifndef WGL_ATI_render_texture_rectangle
#define WGL_ATI_render_texture_rectangle 1
#define WGL_TEXTURE_RECTANGLE_ATI 0x21A5
#define WGLEW_ATI_render_texture_rectangle WGLEW_GET_VAR(__WGLEW_ATI_render_texture_rectangle)
#endif /* WGL_ATI_render_texture_rectangle */
/* -------------------------- WGL_EXT_depth_float -------------------------- */
#ifndef WGL_EXT_depth_float
#define WGL_EXT_depth_float 1
#define WGL_DEPTH_FLOAT_EXT 0x2040
#define WGLEW_EXT_depth_float WGLEW_GET_VAR(__WGLEW_EXT_depth_float)
#endif /* WGL_EXT_depth_float */
/* ---------------------- WGL_EXT_display_color_table ---------------------- */
#ifndef WGL_EXT_display_color_table
#define WGL_EXT_display_color_table 1
typedef GLboolean(WINAPI *PFNWGLBINDDISPLAYCOLORTABLEEXTPROC)(GLushort id);
typedef GLboolean(WINAPI *PFNWGLCREATEDISPLAYCOLORTABLEEXTPROC)(GLushort id);
typedef void (WINAPI *PFNWGLDESTROYDISPLAYCOLORTABLEEXTPROC)(GLushort id);
typedef GLboolean(WINAPI *PFNWGLLOADDISPLAYCOLORTABLEEXTPROC)(GLushort *table, GLuint length);
#define wglBindDisplayColorTableEXT WGLEW_GET_FUN(__wglewBindDisplayColorTableEXT)
#define wglCreateDisplayColorTableEXT WGLEW_GET_FUN(__wglewCreateDisplayColorTableEXT)
#define wglDestroyDisplayColorTableEXT WGLEW_GET_FUN(__wglewDestroyDisplayColorTableEXT)
#define wglLoadDisplayColorTableEXT WGLEW_GET_FUN(__wglewLoadDisplayColorTableEXT)
#define WGLEW_EXT_display_color_table WGLEW_GET_VAR(__WGLEW_EXT_display_color_table)
#endif /* WGL_EXT_display_color_table */
/* ----------------------- WGL_EXT_extensions_string ----------------------- */
#ifndef WGL_EXT_extensions_string
#define WGL_EXT_extensions_string 1
typedef const char *(WINAPI *PFNWGLGETEXTENSIONSSTRINGEXTPROC)(void);
#define wglGetExtensionsStringEXT WGLEW_GET_FUN(__wglewGetExtensionsStringEXT)
#define WGLEW_EXT_extensions_string WGLEW_GET_VAR(__WGLEW_EXT_extensions_string)
#endif /* WGL_EXT_extensions_string */
/* ------------------------ WGL_EXT_framebuffer_sRGB ----------------------- */
#ifndef WGL_EXT_framebuffer_sRGB
#define WGL_EXT_framebuffer_sRGB 1
#define WGL_FRAMEBUFFER_SRGB_CAPABLE_EXT 0x20A9
#define WGLEW_EXT_framebuffer_sRGB WGLEW_GET_VAR(__WGLEW_EXT_framebuffer_sRGB)
#endif /* WGL_EXT_framebuffer_sRGB */
/* ----------------------- WGL_EXT_make_current_read ----------------------- */
#ifndef WGL_EXT_make_current_read
#define WGL_EXT_make_current_read 1
typedef HDC(WINAPI *PFNWGLGETCURRENTREADDCEXTPROC)(VOID);
typedef BOOL (WINAPI *PFNWGLMAKECONTEXTCURRENTEXTPROC)(HDC hDrawDC, HDC hReadDC, HGLRC hglrc);
#define wglGetCurrentReadDCEXT WGLEW_GET_FUN(__wglewGetCurrentReadDCEXT)
#define wglMakeContextCurrentEXT WGLEW_GET_FUN(__wglewMakeContextCurrentEXT)
#define WGLEW_EXT_make_current_read WGLEW_GET_VAR(__WGLEW_EXT_make_current_read)
#endif /* WGL_EXT_make_current_read */
/* -------------------------- WGL_EXT_multisample -------------------------- */
#ifndef WGL_EXT_multisample
#define WGL_EXT_multisample 1
#define WGL_SAMPLE_BUFFERS_EXT 0x2041
#define WGL_SAMPLES_EXT 0x2042
#define WGLEW_EXT_multisample WGLEW_GET_VAR(__WGLEW_EXT_multisample)
#endif /* WGL_EXT_multisample */
/* ---------------------------- WGL_EXT_pbuffer ---------------------------- */
#ifndef WGL_EXT_pbuffer
#define WGL_EXT_pbuffer 1
#define WGL_DRAW_TO_PBUFFER_EXT 0x202D
#define WGL_MAX_PBUFFER_PIXELS_EXT 0x202E
#define WGL_MAX_PBUFFER_WIDTH_EXT 0x202F
#define WGL_MAX_PBUFFER_HEIGHT_EXT 0x2030
#define WGL_OPTIMAL_PBUFFER_WIDTH_EXT 0x2031
#define WGL_OPTIMAL_PBUFFER_HEIGHT_EXT 0x2032
#define WGL_PBUFFER_LARGEST_EXT 0x2033
#define WGL_PBUFFER_WIDTH_EXT 0x2034
#define WGL_PBUFFER_HEIGHT_EXT 0x2035
DECLARE_HANDLE(HPBUFFEREXT);
typedef HPBUFFEREXT(WINAPI *PFNWGLCREATEPBUFFEREXTPROC)(HDC hDC, int iPixelFormat, int iWidth, int iHeight, const int *piAttribList);
typedef BOOL (WINAPI *PFNWGLDESTROYPBUFFEREXTPROC)(HPBUFFEREXT hPbuffer);
typedef HDC(WINAPI *PFNWGLGETPBUFFERDCEXTPROC)(HPBUFFEREXT hPbuffer);
typedef BOOL (WINAPI *PFNWGLQUERYPBUFFEREXTPROC)(HPBUFFEREXT hPbuffer, int iAttribute, int *piValue);
typedef int (WINAPI *PFNWGLRELEASEPBUFFERDCEXTPROC)(HPBUFFEREXT hPbuffer, HDC hDC);
#define wglCreatePbufferEXT WGLEW_GET_FUN(__wglewCreatePbufferEXT)
#define wglDestroyPbufferEXT WGLEW_GET_FUN(__wglewDestroyPbufferEXT)
#define wglGetPbufferDCEXT WGLEW_GET_FUN(__wglewGetPbufferDCEXT)
#define wglQueryPbufferEXT WGLEW_GET_FUN(__wglewQueryPbufferEXT)
#define wglReleasePbufferDCEXT WGLEW_GET_FUN(__wglewReleasePbufferDCEXT)
#define WGLEW_EXT_pbuffer WGLEW_GET_VAR(__WGLEW_EXT_pbuffer)
#endif /* WGL_EXT_pbuffer */
/* -------------------------- WGL_EXT_pixel_format ------------------------- */
#ifndef WGL_EXT_pixel_format
#define WGL_EXT_pixel_format 1
#define WGL_NUMBER_PIXEL_FORMATS_EXT 0x2000
#define WGL_DRAW_TO_WINDOW_EXT 0x2001
#define WGL_DRAW_TO_BITMAP_EXT 0x2002
#define WGL_ACCELERATION_EXT 0x2003
#define WGL_NEED_PALETTE_EXT 0x2004
#define WGL_NEED_SYSTEM_PALETTE_EXT 0x2005
#define WGL_SWAP_LAYER_BUFFERS_EXT 0x2006
#define WGL_SWAP_METHOD_EXT 0x2007
#define WGL_NUMBER_OVERLAYS_EXT 0x2008
#define WGL_NUMBER_UNDERLAYS_EXT 0x2009
#define WGL_TRANSPARENT_EXT 0x200A
#define WGL_TRANSPARENT_VALUE_EXT 0x200B
#define WGL_SHARE_DEPTH_EXT 0x200C
#define WGL_SHARE_STENCIL_EXT 0x200D
#define WGL_SHARE_ACCUM_EXT 0x200E
#define WGL_SUPPORT_GDI_EXT 0x200F
#define WGL_SUPPORT_OPENGL_EXT 0x2010
#define WGL_DOUBLE_BUFFER_EXT 0x2011
#define WGL_STEREO_EXT 0x2012
#define WGL_PIXEL_TYPE_EXT 0x2013
#define WGL_COLOR_BITS_EXT 0x2014
#define WGL_RED_BITS_EXT 0x2015
#define WGL_RED_SHIFT_EXT 0x2016
#define WGL_GREEN_BITS_EXT 0x2017
#define WGL_GREEN_SHIFT_EXT 0x2018
#define WGL_BLUE_BITS_EXT 0x2019
#define WGL_BLUE_SHIFT_EXT 0x201A
#define WGL_ALPHA_BITS_EXT 0x201B
#define WGL_ALPHA_SHIFT_EXT 0x201C
#define WGL_ACCUM_BITS_EXT 0x201D
#define WGL_ACCUM_RED_BITS_EXT 0x201E
#define WGL_ACCUM_GREEN_BITS_EXT 0x201F
#define WGL_ACCUM_BLUE_BITS_EXT 0x2020
#define WGL_ACCUM_ALPHA_BITS_EXT 0x2021
#define WGL_DEPTH_BITS_EXT 0x2022
#define WGL_STENCIL_BITS_EXT 0x2023
#define WGL_AUX_BUFFERS_EXT 0x2024
#define WGL_NO_ACCELERATION_EXT 0x2025
#define WGL_GENERIC_ACCELERATION_EXT 0x2026
#define WGL_FULL_ACCELERATION_EXT 0x2027
#define WGL_SWAP_EXCHANGE_EXT 0x2028
#define WGL_SWAP_COPY_EXT 0x2029
#define WGL_SWAP_UNDEFINED_EXT 0x202A
#define WGL_TYPE_RGBA_EXT 0x202B
#define WGL_TYPE_COLORINDEX_EXT 0x202C
typedef BOOL (WINAPI *PFNWGLCHOOSEPIXELFORMATEXTPROC)(HDC hdc, const int *piAttribIList, const FLOAT *pfAttribFList, UINT nMaxFormats, int *piFormats, UINT *nNumFormats);
typedef BOOL (WINAPI *PFNWGLGETPIXELFORMATATTRIBFVEXTPROC)(HDC hdc, int iPixelFormat, int iLayerPlane, UINT nAttributes, int *piAttributes, FLOAT *pfValues);
typedef BOOL (WINAPI *PFNWGLGETPIXELFORMATATTRIBIVEXTPROC)(HDC hdc, int iPixelFormat, int iLayerPlane, UINT nAttributes, int *piAttributes, int *piValues);
#define wglChoosePixelFormatEXT WGLEW_GET_FUN(__wglewChoosePixelFormatEXT)
#define wglGetPixelFormatAttribfvEXT WGLEW_GET_FUN(__wglewGetPixelFormatAttribfvEXT)
#define wglGetPixelFormatAttribivEXT WGLEW_GET_FUN(__wglewGetPixelFormatAttribivEXT)
#define WGLEW_EXT_pixel_format WGLEW_GET_VAR(__WGLEW_EXT_pixel_format)
#endif /* WGL_EXT_pixel_format */
/* ------------------- WGL_EXT_pixel_format_packed_float ------------------- */
#ifndef WGL_EXT_pixel_format_packed_float
#define WGL_EXT_pixel_format_packed_float 1
#define WGL_TYPE_RGBA_UNSIGNED_FLOAT_EXT 0x20A8
#define WGLEW_EXT_pixel_format_packed_float WGLEW_GET_VAR(__WGLEW_EXT_pixel_format_packed_float)
#endif /* WGL_EXT_pixel_format_packed_float */
/* -------------------------- WGL_EXT_swap_control ------------------------- */
#ifndef WGL_EXT_swap_control
#define WGL_EXT_swap_control 1
typedef int (WINAPI *PFNWGLGETSWAPINTERVALEXTPROC)(void);
typedef BOOL (WINAPI *PFNWGLSWAPINTERVALEXTPROC)(int interval);
#define wglGetSwapIntervalEXT WGLEW_GET_FUN(__wglewGetSwapIntervalEXT)
#define wglSwapIntervalEXT WGLEW_GET_FUN(__wglewSwapIntervalEXT)
#define WGLEW_EXT_swap_control WGLEW_GET_VAR(__WGLEW_EXT_swap_control)
#endif /* WGL_EXT_swap_control */
/* --------------------- WGL_I3D_digital_video_control --------------------- */
#ifndef WGL_I3D_digital_video_control
#define WGL_I3D_digital_video_control 1
#define WGL_DIGITAL_VIDEO_CURSOR_ALPHA_FRAMEBUFFER_I3D 0x2050
#define WGL_DIGITAL_VIDEO_CURSOR_ALPHA_VALUE_I3D 0x2051
#define WGL_DIGITAL_VIDEO_CURSOR_INCLUDED_I3D 0x2052
#define WGL_DIGITAL_VIDEO_GAMMA_CORRECTED_I3D 0x2053
typedef BOOL (WINAPI *PFNWGLGETDIGITALVIDEOPARAMETERSI3DPROC)(HDC hDC, int iAttribute, int *piValue);
typedef BOOL (WINAPI *PFNWGLSETDIGITALVIDEOPARAMETERSI3DPROC)(HDC hDC, int iAttribute, const int *piValue);
#define wglGetDigitalVideoParametersI3D WGLEW_GET_FUN(__wglewGetDigitalVideoParametersI3D)
#define wglSetDigitalVideoParametersI3D WGLEW_GET_FUN(__wglewSetDigitalVideoParametersI3D)
#define WGLEW_I3D_digital_video_control WGLEW_GET_VAR(__WGLEW_I3D_digital_video_control)
#endif /* WGL_I3D_digital_video_control */
/* ----------------------------- WGL_I3D_gamma ----------------------------- */
#ifndef WGL_I3D_gamma
#define WGL_I3D_gamma 1
#define WGL_GAMMA_TABLE_SIZE_I3D 0x204E
#define WGL_GAMMA_EXCLUDE_DESKTOP_I3D 0x204F
typedef BOOL (WINAPI *PFNWGLGETGAMMATABLEI3DPROC)(HDC hDC, int iEntries, USHORT *puRed, USHORT *puGreen, USHORT *puBlue);
typedef BOOL (WINAPI *PFNWGLGETGAMMATABLEPARAMETERSI3DPROC)(HDC hDC, int iAttribute, int *piValue);
typedef BOOL (WINAPI *PFNWGLSETGAMMATABLEI3DPROC)(HDC hDC, int iEntries, const USHORT *puRed, const USHORT *puGreen, const USHORT *puBlue);
typedef BOOL (WINAPI *PFNWGLSETGAMMATABLEPARAMETERSI3DPROC)(HDC hDC, int iAttribute, const int *piValue);
#define wglGetGammaTableI3D WGLEW_GET_FUN(__wglewGetGammaTableI3D)
#define wglGetGammaTableParametersI3D WGLEW_GET_FUN(__wglewGetGammaTableParametersI3D)
#define wglSetGammaTableI3D WGLEW_GET_FUN(__wglewSetGammaTableI3D)
#define wglSetGammaTableParametersI3D WGLEW_GET_FUN(__wglewSetGammaTableParametersI3D)
#define WGLEW_I3D_gamma WGLEW_GET_VAR(__WGLEW_I3D_gamma)
#endif /* WGL_I3D_gamma */
/* ---------------------------- WGL_I3D_genlock ---------------------------- */
#ifndef WGL_I3D_genlock
#define WGL_I3D_genlock 1
#define WGL_GENLOCK_SOURCE_MULTIVIEW_I3D 0x2044
#define WGL_GENLOCK_SOURCE_EXTERNAL_SYNC_I3D 0x2045
#define WGL_GENLOCK_SOURCE_EXTERNAL_FIELD_I3D 0x2046
#define WGL_GENLOCK_SOURCE_EXTERNAL_TTL_I3D 0x2047
#define WGL_GENLOCK_SOURCE_DIGITAL_SYNC_I3D 0x2048
#define WGL_GENLOCK_SOURCE_DIGITAL_FIELD_I3D 0x2049
#define WGL_GENLOCK_SOURCE_EDGE_FALLING_I3D 0x204A
#define WGL_GENLOCK_SOURCE_EDGE_RISING_I3D 0x204B
#define WGL_GENLOCK_SOURCE_EDGE_BOTH_I3D 0x204C
typedef BOOL (WINAPI *PFNWGLDISABLEGENLOCKI3DPROC)(HDC hDC);
typedef BOOL (WINAPI *PFNWGLENABLEGENLOCKI3DPROC)(HDC hDC);
typedef BOOL (WINAPI *PFNWGLGENLOCKSAMPLERATEI3DPROC)(HDC hDC, UINT uRate);
typedef BOOL (WINAPI *PFNWGLGENLOCKSOURCEDELAYI3DPROC)(HDC hDC, UINT uDelay);
typedef BOOL (WINAPI *PFNWGLGENLOCKSOURCEEDGEI3DPROC)(HDC hDC, UINT uEdge);
typedef BOOL (WINAPI *PFNWGLGENLOCKSOURCEI3DPROC)(HDC hDC, UINT uSource);
typedef BOOL (WINAPI *PFNWGLGETGENLOCKSAMPLERATEI3DPROC)(HDC hDC, UINT *uRate);
typedef BOOL (WINAPI *PFNWGLGETGENLOCKSOURCEDELAYI3DPROC)(HDC hDC, UINT *uDelay);
typedef BOOL (WINAPI *PFNWGLGETGENLOCKSOURCEEDGEI3DPROC)(HDC hDC, UINT *uEdge);
typedef BOOL (WINAPI *PFNWGLGETGENLOCKSOURCEI3DPROC)(HDC hDC, UINT *uSource);
typedef BOOL (WINAPI *PFNWGLISENABLEDGENLOCKI3DPROC)(HDC hDC, BOOL *pFlag);
typedef BOOL (WINAPI *PFNWGLQUERYGENLOCKMAXSOURCEDELAYI3DPROC)(HDC hDC, UINT *uMaxLineDelay, UINT *uMaxPixelDelay);
#define wglDisableGenlockI3D WGLEW_GET_FUN(__wglewDisableGenlockI3D)
#define wglEnableGenlockI3D WGLEW_GET_FUN(__wglewEnableGenlockI3D)
#define wglGenlockSampleRateI3D WGLEW_GET_FUN(__wglewGenlockSampleRateI3D)
#define wglGenlockSourceDelayI3D WGLEW_GET_FUN(__wglewGenlockSourceDelayI3D)
#define wglGenlockSourceEdgeI3D WGLEW_GET_FUN(__wglewGenlockSourceEdgeI3D)
#define wglGenlockSourceI3D WGLEW_GET_FUN(__wglewGenlockSourceI3D)
#define wglGetGenlockSampleRateI3D WGLEW_GET_FUN(__wglewGetGenlockSampleRateI3D)
#define wglGetGenlockSourceDelayI3D WGLEW_GET_FUN(__wglewGetGenlockSourceDelayI3D)
#define wglGetGenlockSourceEdgeI3D WGLEW_GET_FUN(__wglewGetGenlockSourceEdgeI3D)
#define wglGetGenlockSourceI3D WGLEW_GET_FUN(__wglewGetGenlockSourceI3D)
#define wglIsEnabledGenlockI3D WGLEW_GET_FUN(__wglewIsEnabledGenlockI3D)
#define wglQueryGenlockMaxSourceDelayI3D WGLEW_GET_FUN(__wglewQueryGenlockMaxSourceDelayI3D)
#define WGLEW_I3D_genlock WGLEW_GET_VAR(__WGLEW_I3D_genlock)
#endif /* WGL_I3D_genlock */
/* -------------------------- WGL_I3D_image_buffer ------------------------- */
#ifndef WGL_I3D_image_buffer
#define WGL_I3D_image_buffer 1
#define WGL_IMAGE_BUFFER_MIN_ACCESS_I3D 0x00000001
#define WGL_IMAGE_BUFFER_LOCK_I3D 0x00000002
typedef BOOL (WINAPI *PFNWGLASSOCIATEIMAGEBUFFEREVENTSI3DPROC)(HDC hdc, HANDLE *pEvent, LPVOID *pAddress, DWORD *pSize, UINT count);
typedef LPVOID (WINAPI *PFNWGLCREATEIMAGEBUFFERI3DPROC)(HDC hDC, DWORD dwSize, UINT uFlags);
typedef BOOL (WINAPI *PFNWGLDESTROYIMAGEBUFFERI3DPROC)(HDC hDC, LPVOID pAddress);
typedef BOOL (WINAPI *PFNWGLRELEASEIMAGEBUFFEREVENTSI3DPROC)(HDC hdc, LPVOID *pAddress, UINT count);
#define wglAssociateImageBufferEventsI3D WGLEW_GET_FUN(__wglewAssociateImageBufferEventsI3D)
#define wglCreateImageBufferI3D WGLEW_GET_FUN(__wglewCreateImageBufferI3D)
#define wglDestroyImageBufferI3D WGLEW_GET_FUN(__wglewDestroyImageBufferI3D)
#define wglReleaseImageBufferEventsI3D WGLEW_GET_FUN(__wglewReleaseImageBufferEventsI3D)
#define WGLEW_I3D_image_buffer WGLEW_GET_VAR(__WGLEW_I3D_image_buffer)
#endif /* WGL_I3D_image_buffer */
/* ------------------------ WGL_I3D_swap_frame_lock ------------------------ */
#ifndef WGL_I3D_swap_frame_lock
#define WGL_I3D_swap_frame_lock 1
typedef BOOL (WINAPI *PFNWGLDISABLEFRAMELOCKI3DPROC)(VOID);
typedef BOOL (WINAPI *PFNWGLENABLEFRAMELOCKI3DPROC)(VOID);
typedef BOOL (WINAPI *PFNWGLISENABLEDFRAMELOCKI3DPROC)(BOOL *pFlag);
typedef BOOL (WINAPI *PFNWGLQUERYFRAMELOCKMASTERI3DPROC)(BOOL *pFlag);
#define wglDisableFrameLockI3D WGLEW_GET_FUN(__wglewDisableFrameLockI3D)
#define wglEnableFrameLockI3D WGLEW_GET_FUN(__wglewEnableFrameLockI3D)
#define wglIsEnabledFrameLockI3D WGLEW_GET_FUN(__wglewIsEnabledFrameLockI3D)
#define wglQueryFrameLockMasterI3D WGLEW_GET_FUN(__wglewQueryFrameLockMasterI3D)
#define WGLEW_I3D_swap_frame_lock WGLEW_GET_VAR(__WGLEW_I3D_swap_frame_lock)
#endif /* WGL_I3D_swap_frame_lock */
/* ------------------------ WGL_I3D_swap_frame_usage ----------------------- */
#ifndef WGL_I3D_swap_frame_usage
#define WGL_I3D_swap_frame_usage 1
typedef BOOL (WINAPI *PFNWGLBEGINFRAMETRACKINGI3DPROC)(void);
typedef BOOL (WINAPI *PFNWGLENDFRAMETRACKINGI3DPROC)(void);
typedef BOOL (WINAPI *PFNWGLGETFRAMEUSAGEI3DPROC)(float *pUsage);
typedef BOOL (WINAPI *PFNWGLQUERYFRAMETRACKINGI3DPROC)(DWORD *pFrameCount, DWORD *pMissedFrames, float *pLastMissedUsage);
#define wglBeginFrameTrackingI3D WGLEW_GET_FUN(__wglewBeginFrameTrackingI3D)
#define wglEndFrameTrackingI3D WGLEW_GET_FUN(__wglewEndFrameTrackingI3D)
#define wglGetFrameUsageI3D WGLEW_GET_FUN(__wglewGetFrameUsageI3D)
#define wglQueryFrameTrackingI3D WGLEW_GET_FUN(__wglewQueryFrameTrackingI3D)
#define WGLEW_I3D_swap_frame_usage WGLEW_GET_VAR(__WGLEW_I3D_swap_frame_usage)
#endif /* WGL_I3D_swap_frame_usage */
/* -------------------------- WGL_NV_float_buffer -------------------------- */
#ifndef WGL_NV_float_buffer
#define WGL_NV_float_buffer 1
#define WGL_FLOAT_COMPONENTS_NV 0x20B0
#define WGL_BIND_TO_TEXTURE_RECTANGLE_FLOAT_R_NV 0x20B1
#define WGL_BIND_TO_TEXTURE_RECTANGLE_FLOAT_RG_NV 0x20B2
#define WGL_BIND_TO_TEXTURE_RECTANGLE_FLOAT_RGB_NV 0x20B3
#define WGL_BIND_TO_TEXTURE_RECTANGLE_FLOAT_RGBA_NV 0x20B4
#define WGL_TEXTURE_FLOAT_R_NV 0x20B5
#define WGL_TEXTURE_FLOAT_RG_NV 0x20B6
#define WGL_TEXTURE_FLOAT_RGB_NV 0x20B7
#define WGL_TEXTURE_FLOAT_RGBA_NV 0x20B8
#define WGLEW_NV_float_buffer WGLEW_GET_VAR(__WGLEW_NV_float_buffer)
#endif /* WGL_NV_float_buffer */
/* ---------------------- WGL_NV_render_depth_texture ---------------------- */
#ifndef WGL_NV_render_depth_texture
#define WGL_NV_render_depth_texture 1
#define WGL_NO_TEXTURE_ARB 0x2077
#define WGL_BIND_TO_TEXTURE_DEPTH_NV 0x20A3
#define WGL_BIND_TO_TEXTURE_RECTANGLE_DEPTH_NV 0x20A4
#define WGL_DEPTH_TEXTURE_FORMAT_NV 0x20A5
#define WGL_TEXTURE_DEPTH_COMPONENT_NV 0x20A6
#define WGL_DEPTH_COMPONENT_NV 0x20A7
#define WGLEW_NV_render_depth_texture WGLEW_GET_VAR(__WGLEW_NV_render_depth_texture)
#endif /* WGL_NV_render_depth_texture */
/* -------------------- WGL_NV_render_texture_rectangle -------------------- */
#ifndef WGL_NV_render_texture_rectangle
#define WGL_NV_render_texture_rectangle 1
#define WGL_BIND_TO_TEXTURE_RECTANGLE_RGB_NV 0x20A0
#define WGL_BIND_TO_TEXTURE_RECTANGLE_RGBA_NV 0x20A1
#define WGL_TEXTURE_RECTANGLE_NV 0x20A2
#define WGLEW_NV_render_texture_rectangle WGLEW_GET_VAR(__WGLEW_NV_render_texture_rectangle)
#endif /* WGL_NV_render_texture_rectangle */
/* ----------------------- WGL_NV_vertex_array_range ----------------------- */
#ifndef WGL_NV_vertex_array_range
#define WGL_NV_vertex_array_range 1
typedef void *(WINAPI *PFNWGLALLOCATEMEMORYNVPROC)(GLsizei size, GLfloat readFrequency, GLfloat writeFrequency, GLfloat priority);
typedef void (WINAPI *PFNWGLFREEMEMORYNVPROC)(void *pointer);
#define wglAllocateMemoryNV WGLEW_GET_FUN(__wglewAllocateMemoryNV)
#define wglFreeMemoryNV WGLEW_GET_FUN(__wglewFreeMemoryNV)
#define WGLEW_NV_vertex_array_range WGLEW_GET_VAR(__WGLEW_NV_vertex_array_range)
#endif /* WGL_NV_vertex_array_range */
/* -------------------------- WGL_OML_sync_control ------------------------- */
#ifndef WGL_OML_sync_control
#define WGL_OML_sync_control 1
typedef BOOL (WINAPI *PFNWGLGETMSCRATEOMLPROC)(HDC hdc, INT32 *numerator, INT32 *denominator);
typedef BOOL (WINAPI *PFNWGLGETSYNCVALUESOMLPROC)(HDC hdc, INT64 *ust, INT64 *msc, INT64 *sbc);
typedef INT64(WINAPI *PFNWGLSWAPBUFFERSMSCOMLPROC)(HDC hdc, INT64 target_msc, INT64 divisor, INT64 remainder);
typedef INT64(WINAPI *PFNWGLSWAPLAYERBUFFERSMSCOMLPROC)(HDC hdc, INT fuPlanes, INT64 target_msc, INT64 divisor, INT64 remainder);
typedef BOOL (WINAPI *PFNWGLWAITFORMSCOMLPROC)(HDC hdc, INT64 target_msc, INT64 divisor, INT64 remainder, INT64 *ust, INT64 *msc, INT64 *sbc);
typedef BOOL (WINAPI *PFNWGLWAITFORSBCOMLPROC)(HDC hdc, INT64 target_sbc, INT64 *ust, INT64 *msc, INT64 *sbc);
#define wglGetMscRateOML WGLEW_GET_FUN(__wglewGetMscRateOML)
#define wglGetSyncValuesOML WGLEW_GET_FUN(__wglewGetSyncValuesOML)
#define wglSwapBuffersMscOML WGLEW_GET_FUN(__wglewSwapBuffersMscOML)
#define wglSwapLayerBuffersMscOML WGLEW_GET_FUN(__wglewSwapLayerBuffersMscOML)
#define wglWaitForMscOML WGLEW_GET_FUN(__wglewWaitForMscOML)
#define wglWaitForSbcOML WGLEW_GET_FUN(__wglewWaitForSbcOML)
#define WGLEW_OML_sync_control WGLEW_GET_VAR(__WGLEW_OML_sync_control)
#endif /* WGL_OML_sync_control */
/* ------------------------------------------------------------------------- */
#ifdef GLEW_MX
#define WGLEW_EXPORT
#else
#define WGLEW_EXPORT GLEWAPI
#endif /* GLEW_MX */
#ifdef GLEW_MX
struct WGLEWContextStruct
{
#endif /* GLEW_MX */
WGLEW_EXPORT PFNWGLSETSTEREOEMITTERSTATE3DLPROC __wglewSetStereoEmitterState3DL;
WGLEW_EXPORT PFNWGLCREATEBUFFERREGIONARBPROC __wglewCreateBufferRegionARB;
WGLEW_EXPORT PFNWGLDELETEBUFFERREGIONARBPROC __wglewDeleteBufferRegionARB;
WGLEW_EXPORT PFNWGLRESTOREBUFFERREGIONARBPROC __wglewRestoreBufferRegionARB;
WGLEW_EXPORT PFNWGLSAVEBUFFERREGIONARBPROC __wglewSaveBufferRegionARB;
WGLEW_EXPORT PFNWGLGETEXTENSIONSSTRINGARBPROC __wglewGetExtensionsStringARB;
WGLEW_EXPORT PFNWGLGETCURRENTREADDCARBPROC __wglewGetCurrentReadDCARB;
WGLEW_EXPORT PFNWGLMAKECONTEXTCURRENTARBPROC __wglewMakeContextCurrentARB;
WGLEW_EXPORT PFNWGLCREATEPBUFFERARBPROC __wglewCreatePbufferARB;
WGLEW_EXPORT PFNWGLDESTROYPBUFFERARBPROC __wglewDestroyPbufferARB;
WGLEW_EXPORT PFNWGLGETPBUFFERDCARBPROC __wglewGetPbufferDCARB;
WGLEW_EXPORT PFNWGLQUERYPBUFFERARBPROC __wglewQueryPbufferARB;
WGLEW_EXPORT PFNWGLRELEASEPBUFFERDCARBPROC __wglewReleasePbufferDCARB;
WGLEW_EXPORT PFNWGLCHOOSEPIXELFORMATARBPROC __wglewChoosePixelFormatARB;
WGLEW_EXPORT PFNWGLGETPIXELFORMATATTRIBFVARBPROC __wglewGetPixelFormatAttribfvARB;
WGLEW_EXPORT PFNWGLGETPIXELFORMATATTRIBIVARBPROC __wglewGetPixelFormatAttribivARB;
WGLEW_EXPORT PFNWGLBINDTEXIMAGEARBPROC __wglewBindTexImageARB;
WGLEW_EXPORT PFNWGLRELEASETEXIMAGEARBPROC __wglewReleaseTexImageARB;
WGLEW_EXPORT PFNWGLSETPBUFFERATTRIBARBPROC __wglewSetPbufferAttribARB;
WGLEW_EXPORT PFNWGLBINDDISPLAYCOLORTABLEEXTPROC __wglewBindDisplayColorTableEXT;
WGLEW_EXPORT PFNWGLCREATEDISPLAYCOLORTABLEEXTPROC __wglewCreateDisplayColorTableEXT;
WGLEW_EXPORT PFNWGLDESTROYDISPLAYCOLORTABLEEXTPROC __wglewDestroyDisplayColorTableEXT;
WGLEW_EXPORT PFNWGLLOADDISPLAYCOLORTABLEEXTPROC __wglewLoadDisplayColorTableEXT;
WGLEW_EXPORT PFNWGLGETEXTENSIONSSTRINGEXTPROC __wglewGetExtensionsStringEXT;
WGLEW_EXPORT PFNWGLGETCURRENTREADDCEXTPROC __wglewGetCurrentReadDCEXT;
WGLEW_EXPORT PFNWGLMAKECONTEXTCURRENTEXTPROC __wglewMakeContextCurrentEXT;
WGLEW_EXPORT PFNWGLCREATEPBUFFEREXTPROC __wglewCreatePbufferEXT;
WGLEW_EXPORT PFNWGLDESTROYPBUFFEREXTPROC __wglewDestroyPbufferEXT;
WGLEW_EXPORT PFNWGLGETPBUFFERDCEXTPROC __wglewGetPbufferDCEXT;
WGLEW_EXPORT PFNWGLQUERYPBUFFEREXTPROC __wglewQueryPbufferEXT;
WGLEW_EXPORT PFNWGLRELEASEPBUFFERDCEXTPROC __wglewReleasePbufferDCEXT;
WGLEW_EXPORT PFNWGLCHOOSEPIXELFORMATEXTPROC __wglewChoosePixelFormatEXT;
WGLEW_EXPORT PFNWGLGETPIXELFORMATATTRIBFVEXTPROC __wglewGetPixelFormatAttribfvEXT;
WGLEW_EXPORT PFNWGLGETPIXELFORMATATTRIBIVEXTPROC __wglewGetPixelFormatAttribivEXT;
WGLEW_EXPORT PFNWGLGETSWAPINTERVALEXTPROC __wglewGetSwapIntervalEXT;
WGLEW_EXPORT PFNWGLSWAPINTERVALEXTPROC __wglewSwapIntervalEXT;
WGLEW_EXPORT PFNWGLGETDIGITALVIDEOPARAMETERSI3DPROC __wglewGetDigitalVideoParametersI3D;
WGLEW_EXPORT PFNWGLSETDIGITALVIDEOPARAMETERSI3DPROC __wglewSetDigitalVideoParametersI3D;
WGLEW_EXPORT PFNWGLGETGAMMATABLEI3DPROC __wglewGetGammaTableI3D;
WGLEW_EXPORT PFNWGLGETGAMMATABLEPARAMETERSI3DPROC __wglewGetGammaTableParametersI3D;
WGLEW_EXPORT PFNWGLSETGAMMATABLEI3DPROC __wglewSetGammaTableI3D;
WGLEW_EXPORT PFNWGLSETGAMMATABLEPARAMETERSI3DPROC __wglewSetGammaTableParametersI3D;
WGLEW_EXPORT PFNWGLDISABLEGENLOCKI3DPROC __wglewDisableGenlockI3D;
WGLEW_EXPORT PFNWGLENABLEGENLOCKI3DPROC __wglewEnableGenlockI3D;
WGLEW_EXPORT PFNWGLGENLOCKSAMPLERATEI3DPROC __wglewGenlockSampleRateI3D;
WGLEW_EXPORT PFNWGLGENLOCKSOURCEDELAYI3DPROC __wglewGenlockSourceDelayI3D;
WGLEW_EXPORT PFNWGLGENLOCKSOURCEEDGEI3DPROC __wglewGenlockSourceEdgeI3D;
WGLEW_EXPORT PFNWGLGENLOCKSOURCEI3DPROC __wglewGenlockSourceI3D;
WGLEW_EXPORT PFNWGLGETGENLOCKSAMPLERATEI3DPROC __wglewGetGenlockSampleRateI3D;
WGLEW_EXPORT PFNWGLGETGENLOCKSOURCEDELAYI3DPROC __wglewGetGenlockSourceDelayI3D;
WGLEW_EXPORT PFNWGLGETGENLOCKSOURCEEDGEI3DPROC __wglewGetGenlockSourceEdgeI3D;
WGLEW_EXPORT PFNWGLGETGENLOCKSOURCEI3DPROC __wglewGetGenlockSourceI3D;
WGLEW_EXPORT PFNWGLISENABLEDGENLOCKI3DPROC __wglewIsEnabledGenlockI3D;
WGLEW_EXPORT PFNWGLQUERYGENLOCKMAXSOURCEDELAYI3DPROC __wglewQueryGenlockMaxSourceDelayI3D;
WGLEW_EXPORT PFNWGLASSOCIATEIMAGEBUFFEREVENTSI3DPROC __wglewAssociateImageBufferEventsI3D;
WGLEW_EXPORT PFNWGLCREATEIMAGEBUFFERI3DPROC __wglewCreateImageBufferI3D;
WGLEW_EXPORT PFNWGLDESTROYIMAGEBUFFERI3DPROC __wglewDestroyImageBufferI3D;
WGLEW_EXPORT PFNWGLRELEASEIMAGEBUFFEREVENTSI3DPROC __wglewReleaseImageBufferEventsI3D;
WGLEW_EXPORT PFNWGLDISABLEFRAMELOCKI3DPROC __wglewDisableFrameLockI3D;
WGLEW_EXPORT PFNWGLENABLEFRAMELOCKI3DPROC __wglewEnableFrameLockI3D;
WGLEW_EXPORT PFNWGLISENABLEDFRAMELOCKI3DPROC __wglewIsEnabledFrameLockI3D;
WGLEW_EXPORT PFNWGLQUERYFRAMELOCKMASTERI3DPROC __wglewQueryFrameLockMasterI3D;
WGLEW_EXPORT PFNWGLBEGINFRAMETRACKINGI3DPROC __wglewBeginFrameTrackingI3D;
WGLEW_EXPORT PFNWGLENDFRAMETRACKINGI3DPROC __wglewEndFrameTrackingI3D;
WGLEW_EXPORT PFNWGLGETFRAMEUSAGEI3DPROC __wglewGetFrameUsageI3D;
WGLEW_EXPORT PFNWGLQUERYFRAMETRACKINGI3DPROC __wglewQueryFrameTrackingI3D;
WGLEW_EXPORT PFNWGLALLOCATEMEMORYNVPROC __wglewAllocateMemoryNV;
WGLEW_EXPORT PFNWGLFREEMEMORYNVPROC __wglewFreeMemoryNV;
WGLEW_EXPORT PFNWGLGETMSCRATEOMLPROC __wglewGetMscRateOML;
WGLEW_EXPORT PFNWGLGETSYNCVALUESOMLPROC __wglewGetSyncValuesOML;
WGLEW_EXPORT PFNWGLSWAPBUFFERSMSCOMLPROC __wglewSwapBuffersMscOML;
WGLEW_EXPORT PFNWGLSWAPLAYERBUFFERSMSCOMLPROC __wglewSwapLayerBuffersMscOML;
WGLEW_EXPORT PFNWGLWAITFORMSCOMLPROC __wglewWaitForMscOML;
WGLEW_EXPORT PFNWGLWAITFORSBCOMLPROC __wglewWaitForSbcOML;
WGLEW_EXPORT GLboolean __WGLEW_3DFX_multisample;
WGLEW_EXPORT GLboolean __WGLEW_3DL_stereo_control;
WGLEW_EXPORT GLboolean __WGLEW_ARB_buffer_region;
WGLEW_EXPORT GLboolean __WGLEW_ARB_extensions_string;
WGLEW_EXPORT GLboolean __WGLEW_ARB_make_current_read;
WGLEW_EXPORT GLboolean __WGLEW_ARB_multisample;
WGLEW_EXPORT GLboolean __WGLEW_ARB_pbuffer;
WGLEW_EXPORT GLboolean __WGLEW_ARB_pixel_format;
WGLEW_EXPORT GLboolean __WGLEW_ARB_pixel_format_float;
WGLEW_EXPORT GLboolean __WGLEW_ARB_render_texture;
WGLEW_EXPORT GLboolean __WGLEW_ATI_pixel_format_float;
WGLEW_EXPORT GLboolean __WGLEW_ATI_render_texture_rectangle;
WGLEW_EXPORT GLboolean __WGLEW_EXT_depth_float;
WGLEW_EXPORT GLboolean __WGLEW_EXT_display_color_table;
WGLEW_EXPORT GLboolean __WGLEW_EXT_extensions_string;
WGLEW_EXPORT GLboolean __WGLEW_EXT_framebuffer_sRGB;
WGLEW_EXPORT GLboolean __WGLEW_EXT_make_current_read;
WGLEW_EXPORT GLboolean __WGLEW_EXT_multisample;
WGLEW_EXPORT GLboolean __WGLEW_EXT_pbuffer;
WGLEW_EXPORT GLboolean __WGLEW_EXT_pixel_format;
WGLEW_EXPORT GLboolean __WGLEW_EXT_pixel_format_packed_float;
WGLEW_EXPORT GLboolean __WGLEW_EXT_swap_control;
WGLEW_EXPORT GLboolean __WGLEW_I3D_digital_video_control;
WGLEW_EXPORT GLboolean __WGLEW_I3D_gamma;
WGLEW_EXPORT GLboolean __WGLEW_I3D_genlock;
WGLEW_EXPORT GLboolean __WGLEW_I3D_image_buffer;
WGLEW_EXPORT GLboolean __WGLEW_I3D_swap_frame_lock;
WGLEW_EXPORT GLboolean __WGLEW_I3D_swap_frame_usage;
WGLEW_EXPORT GLboolean __WGLEW_NV_float_buffer;
WGLEW_EXPORT GLboolean __WGLEW_NV_render_depth_texture;
WGLEW_EXPORT GLboolean __WGLEW_NV_render_texture_rectangle;
WGLEW_EXPORT GLboolean __WGLEW_NV_vertex_array_range;
WGLEW_EXPORT GLboolean __WGLEW_OML_sync_control;
#ifdef GLEW_MX
}; /* WGLEWContextStruct */
#endif /* GLEW_MX */
/* ------------------------------------------------------------------------- */
#ifdef GLEW_MX
typedef struct WGLEWContextStruct WGLEWContext;
GLEWAPI GLenum wglewContextInit(WGLEWContext *ctx);
GLEWAPI GLboolean wglewContextIsSupported(WGLEWContext *ctx, const char *name);
#define wglewInit() wglewContextInit(wglewGetContext())
#define wglewIsSupported(x) wglewContextIsSupported(wglewGetContext(), x)
#define WGLEW_GET_VAR(x) wglewGetContext()->x
#define WGLEW_GET_FUN(x) wglewGetContext()->x
#else /* GLEW_MX */
#define WGLEW_GET_VAR(x) x
#define WGLEW_GET_FUN(x) x
GLEWAPI GLboolean wglewIsSupported(const char *name);
#endif /* GLEW_MX */
GLEWAPI GLboolean wglewGetExtension(const char *name);
#ifdef __cplusplus
}
#endif
#undef GLEWAPI
#endif /* __wglew_h__ */

696
Common/GL/wglext.h Normal file
View File

@@ -0,0 +1,696 @@
#ifndef __wglext_h_
#define __wglext_h_
#ifdef __cplusplus
extern "C" {
#endif
/*
** License Applicability. Except to the extent portions of this file are
** made subject to an alternative license as permitted in the SGI Free
** Software License B, Version 1.1 (the "License"), the contents of this
** file are subject only to the provisions of the License. You may not use
** this file except in compliance with the License. You may obtain a copy
** of the License at Silicon Graphics, Inc., attn: Legal Services, 1600
** Amphitheatre Parkway, Mountain View, CA 94043-1351, or at:
**
** http://oss.sgi.com/projects/FreeB
**
** Note that, as provided in the License, the Software is distributed on an
** "AS IS" basis, with ALL EXPRESS AND IMPLIED WARRANTIES AND CONDITIONS
** DISCLAIMED, INCLUDING, WITHOUT LIMITATION, ANY IMPLIED WARRANTIES AND
** CONDITIONS OF MERCHANTABILITY, SATISFACTORY QUALITY, FITNESS FOR A
** PARTICULAR PURPOSE, AND NON-INFRINGEMENT.
**
** Original Code. The Original Code is: OpenGL Sample Implementation,
** Version 1.2.1, released January 26, 2000, developed by Silicon Graphics,
** Inc. The Original Code is Copyright (c) 1991-2004 Silicon Graphics, Inc.
** Copyright in any portions created by third parties is as indicated
** elsewhere herein. All Rights Reserved.
**
** Additional Notice Provisions: This software was created using the
** OpenGL(R) version 1.2.1 Sample Implementation published by SGI, but has
** not been independently verified as being compliant with the OpenGL(R)
** version 1.2.1 Specification.
*/
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64) && !defined(APIENTRY) && !defined(__CYGWIN__) && !defined(__SCITECH_SNAP__)
#define WIN32_LEAN_AND_MEAN 1
#include <windows.h>
#endif
#ifndef APIENTRY
#define APIENTRY
#endif
#ifndef APIENTRYP
#define APIENTRYP APIENTRY *
#endif
#ifndef GLAPI
#define GLAPI extern
#endif
/*************************************************************/
/* Header file version number */
/* wglext.h last updated 2005/01/07 */
/* Current version at http://oss.sgi.com/projects/ogl-sample/registry/ */
#define WGL_WGLEXT_VERSION 6
#ifndef WGL_ARB_buffer_region
#define WGL_FRONT_COLOR_BUFFER_BIT_ARB 0x00000001
#define WGL_BACK_COLOR_BUFFER_BIT_ARB 0x00000002
#define WGL_DEPTH_BUFFER_BIT_ARB 0x00000004
#define WGL_STENCIL_BUFFER_BIT_ARB 0x00000008
#endif
#ifndef WGL_ARB_multisample
#define WGL_SAMPLE_BUFFERS_ARB 0x2041
#define WGL_SAMPLES_ARB 0x2042
#endif
#ifndef WGL_ARB_extensions_string
#endif
#ifndef WGL_ARB_pixel_format
#define WGL_NUMBER_PIXEL_FORMATS_ARB 0x2000
#define WGL_DRAW_TO_WINDOW_ARB 0x2001
#define WGL_DRAW_TO_BITMAP_ARB 0x2002
#define WGL_ACCELERATION_ARB 0x2003
#define WGL_NEED_PALETTE_ARB 0x2004
#define WGL_NEED_SYSTEM_PALETTE_ARB 0x2005
#define WGL_SWAP_LAYER_BUFFERS_ARB 0x2006
#define WGL_SWAP_METHOD_ARB 0x2007
#define WGL_NUMBER_OVERLAYS_ARB 0x2008
#define WGL_NUMBER_UNDERLAYS_ARB 0x2009
#define WGL_TRANSPARENT_ARB 0x200A
#define WGL_TRANSPARENT_RED_VALUE_ARB 0x2037
#define WGL_TRANSPARENT_GREEN_VALUE_ARB 0x2038
#define WGL_TRANSPARENT_BLUE_VALUE_ARB 0x2039
#define WGL_TRANSPARENT_ALPHA_VALUE_ARB 0x203A
#define WGL_TRANSPARENT_INDEX_VALUE_ARB 0x203B
#define WGL_SHARE_DEPTH_ARB 0x200C
#define WGL_SHARE_STENCIL_ARB 0x200D
#define WGL_SHARE_ACCUM_ARB 0x200E
#define WGL_SUPPORT_GDI_ARB 0x200F
#define WGL_SUPPORT_OPENGL_ARB 0x2010
#define WGL_DOUBLE_BUFFER_ARB 0x2011
#define WGL_STEREO_ARB 0x2012
#define WGL_PIXEL_TYPE_ARB 0x2013
#define WGL_COLOR_BITS_ARB 0x2014
#define WGL_RED_BITS_ARB 0x2015
#define WGL_RED_SHIFT_ARB 0x2016
#define WGL_GREEN_BITS_ARB 0x2017
#define WGL_GREEN_SHIFT_ARB 0x2018
#define WGL_BLUE_BITS_ARB 0x2019
#define WGL_BLUE_SHIFT_ARB 0x201A
#define WGL_ALPHA_BITS_ARB 0x201B
#define WGL_ALPHA_SHIFT_ARB 0x201C
#define WGL_ACCUM_BITS_ARB 0x201D
#define WGL_ACCUM_RED_BITS_ARB 0x201E
#define WGL_ACCUM_GREEN_BITS_ARB 0x201F
#define WGL_ACCUM_BLUE_BITS_ARB 0x2020
#define WGL_ACCUM_ALPHA_BITS_ARB 0x2021
#define WGL_DEPTH_BITS_ARB 0x2022
#define WGL_STENCIL_BITS_ARB 0x2023
#define WGL_AUX_BUFFERS_ARB 0x2024
#define WGL_NO_ACCELERATION_ARB 0x2025
#define WGL_GENERIC_ACCELERATION_ARB 0x2026
#define WGL_FULL_ACCELERATION_ARB 0x2027
#define WGL_SWAP_EXCHANGE_ARB 0x2028
#define WGL_SWAP_COPY_ARB 0x2029
#define WGL_SWAP_UNDEFINED_ARB 0x202A
#define WGL_TYPE_RGBA_ARB 0x202B
#define WGL_TYPE_COLORINDEX_ARB 0x202C
#endif
#ifndef WGL_ARB_make_current_read
#define ERROR_INVALID_PIXEL_TYPE_ARB 0x2043
#define ERROR_INCOMPATIBLE_DEVICE_CONTEXTS_ARB 0x2054
#endif
#ifndef WGL_ARB_pbuffer
#define WGL_DRAW_TO_PBUFFER_ARB 0x202D
#define WGL_MAX_PBUFFER_PIXELS_ARB 0x202E
#define WGL_MAX_PBUFFER_WIDTH_ARB 0x202F
#define WGL_MAX_PBUFFER_HEIGHT_ARB 0x2030
#define WGL_PBUFFER_LARGEST_ARB 0x2033
#define WGL_PBUFFER_WIDTH_ARB 0x2034
#define WGL_PBUFFER_HEIGHT_ARB 0x2035
#define WGL_PBUFFER_LOST_ARB 0x2036
#endif
#ifndef WGL_ARB_render_texture
#define WGL_BIND_TO_TEXTURE_RGB_ARB 0x2070
#define WGL_BIND_TO_TEXTURE_RGBA_ARB 0x2071
#define WGL_TEXTURE_FORMAT_ARB 0x2072
#define WGL_TEXTURE_TARGET_ARB 0x2073
#define WGL_MIPMAP_TEXTURE_ARB 0x2074
#define WGL_TEXTURE_RGB_ARB 0x2075
#define WGL_TEXTURE_RGBA_ARB 0x2076
#define WGL_NO_TEXTURE_ARB 0x2077
#define WGL_TEXTURE_CUBE_MAP_ARB 0x2078
#define WGL_TEXTURE_1D_ARB 0x2079
#define WGL_TEXTURE_2D_ARB 0x207A
#define WGL_MIPMAP_LEVEL_ARB 0x207B
#define WGL_CUBE_MAP_FACE_ARB 0x207C
#define WGL_TEXTURE_CUBE_MAP_POSITIVE_X_ARB 0x207D
#define WGL_TEXTURE_CUBE_MAP_NEGATIVE_X_ARB 0x207E
#define WGL_TEXTURE_CUBE_MAP_POSITIVE_Y_ARB 0x207F
#define WGL_TEXTURE_CUBE_MAP_NEGATIVE_Y_ARB 0x2080
#define WGL_TEXTURE_CUBE_MAP_POSITIVE_Z_ARB 0x2081
#define WGL_TEXTURE_CUBE_MAP_NEGATIVE_Z_ARB 0x2082
#define WGL_FRONT_LEFT_ARB 0x2083
#define WGL_FRONT_RIGHT_ARB 0x2084
#define WGL_BACK_LEFT_ARB 0x2085
#define WGL_BACK_RIGHT_ARB 0x2086
#define WGL_AUX0_ARB 0x2087
#define WGL_AUX1_ARB 0x2088
#define WGL_AUX2_ARB 0x2089
#define WGL_AUX3_ARB 0x208A
#define WGL_AUX4_ARB 0x208B
#define WGL_AUX5_ARB 0x208C
#define WGL_AUX6_ARB 0x208D
#define WGL_AUX7_ARB 0x208E
#define WGL_AUX8_ARB 0x208F
#define WGL_AUX9_ARB 0x2090
#endif
#ifndef WGL_ARB_pixel_format_float
#define WGL_TYPE_RGBA_FLOAT_ARB 0x21A0
#endif
#ifndef WGL_EXT_make_current_read
#define ERROR_INVALID_PIXEL_TYPE_EXT 0x2043
#endif
#ifndef WGL_EXT_pixel_format
#define WGL_NUMBER_PIXEL_FORMATS_EXT 0x2000
#define WGL_DRAW_TO_WINDOW_EXT 0x2001
#define WGL_DRAW_TO_BITMAP_EXT 0x2002
#define WGL_ACCELERATION_EXT 0x2003
#define WGL_NEED_PALETTE_EXT 0x2004
#define WGL_NEED_SYSTEM_PALETTE_EXT 0x2005
#define WGL_SWAP_LAYER_BUFFERS_EXT 0x2006
#define WGL_SWAP_METHOD_EXT 0x2007
#define WGL_NUMBER_OVERLAYS_EXT 0x2008
#define WGL_NUMBER_UNDERLAYS_EXT 0x2009
#define WGL_TRANSPARENT_EXT 0x200A
#define WGL_TRANSPARENT_VALUE_EXT 0x200B
#define WGL_SHARE_DEPTH_EXT 0x200C
#define WGL_SHARE_STENCIL_EXT 0x200D
#define WGL_SHARE_ACCUM_EXT 0x200E
#define WGL_SUPPORT_GDI_EXT 0x200F
#define WGL_SUPPORT_OPENGL_EXT 0x2010
#define WGL_DOUBLE_BUFFER_EXT 0x2011
#define WGL_STEREO_EXT 0x2012
#define WGL_PIXEL_TYPE_EXT 0x2013
#define WGL_COLOR_BITS_EXT 0x2014
#define WGL_RED_BITS_EXT 0x2015
#define WGL_RED_SHIFT_EXT 0x2016
#define WGL_GREEN_BITS_EXT 0x2017
#define WGL_GREEN_SHIFT_EXT 0x2018
#define WGL_BLUE_BITS_EXT 0x2019
#define WGL_BLUE_SHIFT_EXT 0x201A
#define WGL_ALPHA_BITS_EXT 0x201B
#define WGL_ALPHA_SHIFT_EXT 0x201C
#define WGL_ACCUM_BITS_EXT 0x201D
#define WGL_ACCUM_RED_BITS_EXT 0x201E
#define WGL_ACCUM_GREEN_BITS_EXT 0x201F
#define WGL_ACCUM_BLUE_BITS_EXT 0x2020
#define WGL_ACCUM_ALPHA_BITS_EXT 0x2021
#define WGL_DEPTH_BITS_EXT 0x2022
#define WGL_STENCIL_BITS_EXT 0x2023
#define WGL_AUX_BUFFERS_EXT 0x2024
#define WGL_NO_ACCELERATION_EXT 0x2025
#define WGL_GENERIC_ACCELERATION_EXT 0x2026
#define WGL_FULL_ACCELERATION_EXT 0x2027
#define WGL_SWAP_EXCHANGE_EXT 0x2028
#define WGL_SWAP_COPY_EXT 0x2029
#define WGL_SWAP_UNDEFINED_EXT 0x202A
#define WGL_TYPE_RGBA_EXT 0x202B
#define WGL_TYPE_COLORINDEX_EXT 0x202C
#endif
#ifndef WGL_EXT_pbuffer
#define WGL_DRAW_TO_PBUFFER_EXT 0x202D
#define WGL_MAX_PBUFFER_PIXELS_EXT 0x202E
#define WGL_MAX_PBUFFER_WIDTH_EXT 0x202F
#define WGL_MAX_PBUFFER_HEIGHT_EXT 0x2030
#define WGL_OPTIMAL_PBUFFER_WIDTH_EXT 0x2031
#define WGL_OPTIMAL_PBUFFER_HEIGHT_EXT 0x2032
#define WGL_PBUFFER_LARGEST_EXT 0x2033
#define WGL_PBUFFER_WIDTH_EXT 0x2034
#define WGL_PBUFFER_HEIGHT_EXT 0x2035
#endif
#ifndef WGL_EXT_depth_float
#define WGL_DEPTH_FLOAT_EXT 0x2040
#endif
#ifndef WGL_3DFX_multisample
#define WGL_SAMPLE_BUFFERS_3DFX 0x2060
#define WGL_SAMPLES_3DFX 0x2061
#endif
#ifndef WGL_EXT_multisample
#define WGL_SAMPLE_BUFFERS_EXT 0x2041
#define WGL_SAMPLES_EXT 0x2042
#endif
#ifndef WGL_I3D_digital_video_control
#define WGL_DIGITAL_VIDEO_CURSOR_ALPHA_FRAMEBUFFER_I3D 0x2050
#define WGL_DIGITAL_VIDEO_CURSOR_ALPHA_VALUE_I3D 0x2051
#define WGL_DIGITAL_VIDEO_CURSOR_INCLUDED_I3D 0x2052
#define WGL_DIGITAL_VIDEO_GAMMA_CORRECTED_I3D 0x2053
#endif
#ifndef WGL_I3D_gamma
#define WGL_GAMMA_TABLE_SIZE_I3D 0x204E
#define WGL_GAMMA_EXCLUDE_DESKTOP_I3D 0x204F
#endif
#ifndef WGL_I3D_genlock
#define WGL_GENLOCK_SOURCE_MULTIVIEW_I3D 0x2044
#define WGL_GENLOCK_SOURCE_EXTENAL_SYNC_I3D 0x2045
#define WGL_GENLOCK_SOURCE_EXTENAL_FIELD_I3D 0x2046
#define WGL_GENLOCK_SOURCE_EXTENAL_TTL_I3D 0x2047
#define WGL_GENLOCK_SOURCE_DIGITAL_SYNC_I3D 0x2048
#define WGL_GENLOCK_SOURCE_DIGITAL_FIELD_I3D 0x2049
#define WGL_GENLOCK_SOURCE_EDGE_FALLING_I3D 0x204A
#define WGL_GENLOCK_SOURCE_EDGE_RISING_I3D 0x204B
#define WGL_GENLOCK_SOURCE_EDGE_BOTH_I3D 0x204C
#endif
#ifndef WGL_I3D_image_buffer
#define WGL_IMAGE_BUFFER_MIN_ACCESS_I3D 0x00000001
#define WGL_IMAGE_BUFFER_LOCK_I3D 0x00000002
#endif
#ifndef WGL_I3D_swap_frame_lock
#endif
#ifndef WGL_NV_render_depth_texture
#define WGL_BIND_TO_TEXTURE_DEPTH_NV 0x20A3
#define WGL_BIND_TO_TEXTURE_RECTANGLE_DEPTH_NV 0x20A4
#define WGL_DEPTH_TEXTURE_FORMAT_NV 0x20A5
#define WGL_TEXTURE_DEPTH_COMPONENT_NV 0x20A6
#define WGL_DEPTH_COMPONENT_NV 0x20A7
#endif
#ifndef WGL_NV_render_texture_rectangle
#define WGL_BIND_TO_TEXTURE_RECTANGLE_RGB_NV 0x20A0
#define WGL_BIND_TO_TEXTURE_RECTANGLE_RGBA_NV 0x20A1
#define WGL_TEXTURE_RECTANGLE_NV 0x20A2
#endif
#ifndef WGL_ATI_pixel_format_float
#define WGL_TYPE_RGBA_FLOAT_ATI 0x21A0
#define WGL_RGBA_FLOAT_MODE_ATI 0x8820
#define WGL_COLOR_CLEAR_UNCLAMPED_VALUE_ATI 0x8835
#endif
#ifndef WGL_NV_float_buffer
#define WGL_FLOAT_COMPONENTS_NV 0x20B0
#define WGL_BIND_TO_TEXTURE_RECTANGLE_FLOAT_R_NV 0x20B1
#define WGL_BIND_TO_TEXTURE_RECTANGLE_FLOAT_RG_NV 0x20B2
#define WGL_BIND_TO_TEXTURE_RECTANGLE_FLOAT_RGB_NV 0x20B3
#define WGL_BIND_TO_TEXTURE_RECTANGLE_FLOAT_RGBA_NV 0x20B4
#define WGL_TEXTURE_FLOAT_R_NV 0x20B5
#define WGL_TEXTURE_FLOAT_RG_NV 0x20B6
#define WGL_TEXTURE_FLOAT_RGB_NV 0x20B7
#define WGL_TEXTURE_FLOAT_RGBA_NV 0x20B8
#endif
#ifndef WGL_NV_swap_group
#endif
#ifndef WGL_NV_gpu_affinity
#define WGL_ERROR_INCOMPATIBLE_AFFINITY_MASKS_NV 0x20D0
#define WGL_ERROR_MISSING_AFFINITY_MASK_NV 0x20D1
#endif
/*************************************************************/
#ifndef WGL_ARB_pbuffer
DECLARE_HANDLE(HPBUFFERARB);
#endif
#ifndef WGL_EXT_pbuffer
DECLARE_HANDLE(HPBUFFEREXT);
#endif
#ifndef WGL_NV_gpu_affinity
DECLARE_HANDLE(HGPUNV);
typedef struct _GPU_DEVICE
{
DWORD cb;
CHAR DeviceName[32];
CHAR DeviceString[128];
DWORD Flags;
RECT rcVirtualScreen;
} GPU_DEVICE, *PGPU_DEVICE;
#endif
#ifndef WGL_ARB_buffer_region
#define WGL_ARB_buffer_region 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern HANDLE WINAPI wglCreateBufferRegionARB(HDC, int, UINT);
extern VOID WINAPI wglDeleteBufferRegionARB(HANDLE);
extern BOOL WINAPI wglSaveBufferRegionARB(HANDLE, int, int, int, int);
extern BOOL WINAPI wglRestoreBufferRegionARB(HANDLE, int, int, int, int, int, int);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef HANDLE(WINAPI *PFNWGLCREATEBUFFERREGIONARBPROC)(HDC hDC, int iLayerPlane, UINT uType);
typedef VOID (WINAPI *PFNWGLDELETEBUFFERREGIONARBPROC)(HANDLE hRegion);
typedef BOOL (WINAPI *PFNWGLSAVEBUFFERREGIONARBPROC)(HANDLE hRegion, int x, int y, int width, int height);
typedef BOOL (WINAPI *PFNWGLRESTOREBUFFERREGIONARBPROC)(HANDLE hRegion, int x, int y, int width, int height, int xSrc, int ySrc);
#endif
#ifndef WGL_ARB_multisample
#define WGL_ARB_multisample 1
#endif
#ifndef WGL_ARB_extensions_string
#define WGL_ARB_extensions_string 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern const char *WINAPI wglGetExtensionsStringARB(HDC);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef const char *(WINAPI *PFNWGLGETEXTENSIONSSTRINGARBPROC)(HDC hdc);
#endif
#ifndef WGL_ARB_pixel_format
#define WGL_ARB_pixel_format 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglGetPixelFormatAttribivARB(HDC, int, int, UINT, const int *, int *);
extern BOOL WINAPI wglGetPixelFormatAttribfvARB(HDC, int, int, UINT, const int *, FLOAT *);
extern BOOL WINAPI wglChoosePixelFormatARB(HDC, const int *, const FLOAT *, UINT, int *, UINT *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLGETPIXELFORMATATTRIBIVARBPROC)(HDC hdc, int iPixelFormat, int iLayerPlane, UINT nAttributes, const int *piAttributes, int *piValues);
typedef BOOL (WINAPI *PFNWGLGETPIXELFORMATATTRIBFVARBPROC)(HDC hdc, int iPixelFormat, int iLayerPlane, UINT nAttributes, const int *piAttributes, FLOAT *pfValues);
typedef BOOL (WINAPI *PFNWGLCHOOSEPIXELFORMATARBPROC)(HDC hdc, const int *piAttribIList, const FLOAT *pfAttribFList, UINT nMaxFormats, int *piFormats, UINT *nNumFormats);
#endif
#ifndef WGL_ARB_make_current_read
#define WGL_ARB_make_current_read 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglMakeContextCurrentARB(HDC, HDC, HGLRC);
extern HDC WINAPI wglGetCurrentReadDCARB(void);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLMAKECONTEXTCURRENTARBPROC)(HDC hDrawDC, HDC hReadDC, HGLRC hglrc);
typedef HDC(WINAPI *PFNWGLGETCURRENTREADDCARBPROC)(void);
#endif
#ifndef WGL_ARB_pbuffer
#define WGL_ARB_pbuffer 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern HPBUFFERARB WINAPI wglCreatePbufferARB(HDC, int, int, int, const int *);
extern HDC WINAPI wglGetPbufferDCARB(HPBUFFERARB);
extern int WINAPI wglReleasePbufferDCARB(HPBUFFERARB, HDC);
extern BOOL WINAPI wglDestroyPbufferARB(HPBUFFERARB);
extern BOOL WINAPI wglQueryPbufferARB(HPBUFFERARB, int, int *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef HPBUFFERARB(WINAPI *PFNWGLCREATEPBUFFERARBPROC)(HDC hDC, int iPixelFormat, int iWidth, int iHeight, const int *piAttribList);
typedef HDC(WINAPI *PFNWGLGETPBUFFERDCARBPROC)(HPBUFFERARB hPbuffer);
typedef int (WINAPI *PFNWGLRELEASEPBUFFERDCARBPROC)(HPBUFFERARB hPbuffer, HDC hDC);
typedef BOOL (WINAPI *PFNWGLDESTROYPBUFFERARBPROC)(HPBUFFERARB hPbuffer);
typedef BOOL (WINAPI *PFNWGLQUERYPBUFFERARBPROC)(HPBUFFERARB hPbuffer, int iAttribute, int *piValue);
#endif
#ifndef WGL_ARB_render_texture
#define WGL_ARB_render_texture 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglBindTexImageARB(HPBUFFERARB, int);
extern BOOL WINAPI wglReleaseTexImageARB(HPBUFFERARB, int);
extern BOOL WINAPI wglSetPbufferAttribARB(HPBUFFERARB, const int *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLBINDTEXIMAGEARBPROC)(HPBUFFERARB hPbuffer, int iBuffer);
typedef BOOL (WINAPI *PFNWGLRELEASETEXIMAGEARBPROC)(HPBUFFERARB hPbuffer, int iBuffer);
typedef BOOL (WINAPI *PFNWGLSETPBUFFERATTRIBARBPROC)(HPBUFFERARB hPbuffer, const int *piAttribList);
#endif
#ifndef WGL_ARB_pixel_format_float
#define WGL_ARB_pixel_format_float 1
#endif
#ifndef WGL_EXT_display_color_table
#define WGL_EXT_display_color_table 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern GLboolean WINAPI wglCreateDisplayColorTableEXT(GLushort);
extern GLboolean WINAPI wglLoadDisplayColorTableEXT(const GLushort *, GLuint);
extern GLboolean WINAPI wglBindDisplayColorTableEXT(GLushort);
extern VOID WINAPI wglDestroyDisplayColorTableEXT(GLushort);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef GLboolean(WINAPI *PFNWGLCREATEDISPLAYCOLORTABLEEXTPROC)(GLushort id);
typedef GLboolean(WINAPI *PFNWGLLOADDISPLAYCOLORTABLEEXTPROC)(const GLushort *table, GLuint length);
typedef GLboolean(WINAPI *PFNWGLBINDDISPLAYCOLORTABLEEXTPROC)(GLushort id);
typedef VOID (WINAPI *PFNWGLDESTROYDISPLAYCOLORTABLEEXTPROC)(GLushort id);
#endif
#ifndef WGL_EXT_extensions_string
#define WGL_EXT_extensions_string 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern const char *WINAPI wglGetExtensionsStringEXT(void);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef const char *(WINAPI *PFNWGLGETEXTENSIONSSTRINGEXTPROC)(void);
#endif
#ifndef WGL_EXT_make_current_read
#define WGL_EXT_make_current_read 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglMakeContextCurrentEXT(HDC, HDC, HGLRC);
extern HDC WINAPI wglGetCurrentReadDCEXT(void);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLMAKECONTEXTCURRENTEXTPROC)(HDC hDrawDC, HDC hReadDC, HGLRC hglrc);
typedef HDC(WINAPI *PFNWGLGETCURRENTREADDCEXTPROC)(void);
#endif
#ifndef WGL_EXT_pbuffer
#define WGL_EXT_pbuffer 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern HPBUFFEREXT WINAPI wglCreatePbufferEXT(HDC, int, int, int, const int *);
extern HDC WINAPI wglGetPbufferDCEXT(HPBUFFEREXT);
extern int WINAPI wglReleasePbufferDCEXT(HPBUFFEREXT, HDC);
extern BOOL WINAPI wglDestroyPbufferEXT(HPBUFFEREXT);
extern BOOL WINAPI wglQueryPbufferEXT(HPBUFFEREXT, int, int *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef HPBUFFEREXT(WINAPI *PFNWGLCREATEPBUFFEREXTPROC)(HDC hDC, int iPixelFormat, int iWidth, int iHeight, const int *piAttribList);
typedef HDC(WINAPI *PFNWGLGETPBUFFERDCEXTPROC)(HPBUFFEREXT hPbuffer);
typedef int (WINAPI *PFNWGLRELEASEPBUFFERDCEXTPROC)(HPBUFFEREXT hPbuffer, HDC hDC);
typedef BOOL (WINAPI *PFNWGLDESTROYPBUFFEREXTPROC)(HPBUFFEREXT hPbuffer);
typedef BOOL (WINAPI *PFNWGLQUERYPBUFFEREXTPROC)(HPBUFFEREXT hPbuffer, int iAttribute, int *piValue);
#endif
#ifndef WGL_EXT_pixel_format
#define WGL_EXT_pixel_format 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglGetPixelFormatAttribivEXT(HDC, int, int, UINT, int *, int *);
extern BOOL WINAPI wglGetPixelFormatAttribfvEXT(HDC, int, int, UINT, int *, FLOAT *);
extern BOOL WINAPI wglChoosePixelFormatEXT(HDC, const int *, const FLOAT *, UINT, int *, UINT *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLGETPIXELFORMATATTRIBIVEXTPROC)(HDC hdc, int iPixelFormat, int iLayerPlane, UINT nAttributes, int *piAttributes, int *piValues);
typedef BOOL (WINAPI *PFNWGLGETPIXELFORMATATTRIBFVEXTPROC)(HDC hdc, int iPixelFormat, int iLayerPlane, UINT nAttributes, int *piAttributes, FLOAT *pfValues);
typedef BOOL (WINAPI *PFNWGLCHOOSEPIXELFORMATEXTPROC)(HDC hdc, const int *piAttribIList, const FLOAT *pfAttribFList, UINT nMaxFormats, int *piFormats, UINT *nNumFormats);
#endif
#ifndef WGL_EXT_swap_control
#define WGL_EXT_swap_control 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglSwapIntervalEXT(int);
extern int WINAPI wglGetSwapIntervalEXT(void);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLSWAPINTERVALEXTPROC)(int interval);
typedef int (WINAPI *PFNWGLGETSWAPINTERVALEXTPROC)(void);
#endif
#ifndef WGL_EXT_depth_float
#define WGL_EXT_depth_float 1
#endif
#ifndef WGL_NV_vertex_array_range
#define WGL_NV_vertex_array_range 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern void *WINAPI wglAllocateMemoryNV(GLsizei, GLfloat, GLfloat, GLfloat);
extern void WINAPI wglFreeMemoryNV(void *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef void *(WINAPI *PFNWGLALLOCATEMEMORYNVPROC)(GLsizei size, GLfloat readfreq, GLfloat writefreq, GLfloat priority);
typedef void (WINAPI *PFNWGLFREEMEMORYNVPROC)(void *pointer);
#endif
#ifndef WGL_3DFX_multisample
#define WGL_3DFX_multisample 1
#endif
#ifndef WGL_EXT_multisample
#define WGL_EXT_multisample 1
#endif
#ifndef WGL_OML_sync_control
#define WGL_OML_sync_control 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglGetSyncValuesOML(HDC, INT64 *, INT64 *, INT64 *);
extern BOOL WINAPI wglGetMscRateOML(HDC, INT32 *, INT32 *);
extern INT64 WINAPI wglSwapBuffersMscOML(HDC, INT64, INT64, INT64);
extern INT64 WINAPI wglSwapLayerBuffersMscOML(HDC, int, INT64, INT64, INT64);
extern BOOL WINAPI wglWaitForMscOML(HDC, INT64, INT64, INT64, INT64 *, INT64 *, INT64 *);
extern BOOL WINAPI wglWaitForSbcOML(HDC, INT64, INT64 *, INT64 *, INT64 *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLGETSYNCVALUESOMLPROC)(HDC hdc, INT64 *ust, INT64 *msc, INT64 *sbc);
typedef BOOL (WINAPI *PFNWGLGETMSCRATEOMLPROC)(HDC hdc, INT32 *numerator, INT32 *denominator);
typedef INT64(WINAPI *PFNWGLSWAPBUFFERSMSCOMLPROC)(HDC hdc, INT64 target_msc, INT64 divisor, INT64 remainder);
typedef INT64(WINAPI *PFNWGLSWAPLAYERBUFFERSMSCOMLPROC)(HDC hdc, int fuPlanes, INT64 target_msc, INT64 divisor, INT64 remainder);
typedef BOOL (WINAPI *PFNWGLWAITFORMSCOMLPROC)(HDC hdc, INT64 target_msc, INT64 divisor, INT64 remainder, INT64 *ust, INT64 *msc, INT64 *sbc);
typedef BOOL (WINAPI *PFNWGLWAITFORSBCOMLPROC)(HDC hdc, INT64 target_sbc, INT64 *ust, INT64 *msc, INT64 *sbc);
#endif
#ifndef WGL_I3D_digital_video_control
#define WGL_I3D_digital_video_control 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglGetDigitalVideoParametersI3D(HDC, int, int *);
extern BOOL WINAPI wglSetDigitalVideoParametersI3D(HDC, int, const int *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLGETDIGITALVIDEOPARAMETERSI3DPROC)(HDC hDC, int iAttribute, int *piValue);
typedef BOOL (WINAPI *PFNWGLSETDIGITALVIDEOPARAMETERSI3DPROC)(HDC hDC, int iAttribute, const int *piValue);
#endif
#ifndef WGL_I3D_gamma
#define WGL_I3D_gamma 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglGetGammaTableParametersI3D(HDC, int, int *);
extern BOOL WINAPI wglSetGammaTableParametersI3D(HDC, int, const int *);
extern BOOL WINAPI wglGetGammaTableI3D(HDC, int, USHORT *, USHORT *, USHORT *);
extern BOOL WINAPI wglSetGammaTableI3D(HDC, int, const USHORT *, const USHORT *, const USHORT *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLGETGAMMATABLEPARAMETERSI3DPROC)(HDC hDC, int iAttribute, int *piValue);
typedef BOOL (WINAPI *PFNWGLSETGAMMATABLEPARAMETERSI3DPROC)(HDC hDC, int iAttribute, const int *piValue);
typedef BOOL (WINAPI *PFNWGLGETGAMMATABLEI3DPROC)(HDC hDC, int iEntries, USHORT *puRed, USHORT *puGreen, USHORT *puBlue);
typedef BOOL (WINAPI *PFNWGLSETGAMMATABLEI3DPROC)(HDC hDC, int iEntries, const USHORT *puRed, const USHORT *puGreen, const USHORT *puBlue);
#endif
#ifndef WGL_I3D_genlock
#define WGL_I3D_genlock 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglEnableGenlockI3D(HDC);
extern BOOL WINAPI wglDisableGenlockI3D(HDC);
extern BOOL WINAPI wglIsEnabledGenlockI3D(HDC, BOOL *);
extern BOOL WINAPI wglGenlockSourceI3D(HDC, UINT);
extern BOOL WINAPI wglGetGenlockSourceI3D(HDC, UINT *);
extern BOOL WINAPI wglGenlockSourceEdgeI3D(HDC, UINT);
extern BOOL WINAPI wglGetGenlockSourceEdgeI3D(HDC, UINT *);
extern BOOL WINAPI wglGenlockSampleRateI3D(HDC, UINT);
extern BOOL WINAPI wglGetGenlockSampleRateI3D(HDC, UINT *);
extern BOOL WINAPI wglGenlockSourceDelayI3D(HDC, UINT);
extern BOOL WINAPI wglGetGenlockSourceDelayI3D(HDC, UINT *);
extern BOOL WINAPI wglQueryGenlockMaxSourceDelayI3D(HDC, UINT *, UINT *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLENABLEGENLOCKI3DPROC)(HDC hDC);
typedef BOOL (WINAPI *PFNWGLDISABLEGENLOCKI3DPROC)(HDC hDC);
typedef BOOL (WINAPI *PFNWGLISENABLEDGENLOCKI3DPROC)(HDC hDC, BOOL *pFlag);
typedef BOOL (WINAPI *PFNWGLGENLOCKSOURCEI3DPROC)(HDC hDC, UINT uSource);
typedef BOOL (WINAPI *PFNWGLGETGENLOCKSOURCEI3DPROC)(HDC hDC, UINT *uSource);
typedef BOOL (WINAPI *PFNWGLGENLOCKSOURCEEDGEI3DPROC)(HDC hDC, UINT uEdge);
typedef BOOL (WINAPI *PFNWGLGETGENLOCKSOURCEEDGEI3DPROC)(HDC hDC, UINT *uEdge);
typedef BOOL (WINAPI *PFNWGLGENLOCKSAMPLERATEI3DPROC)(HDC hDC, UINT uRate);
typedef BOOL (WINAPI *PFNWGLGETGENLOCKSAMPLERATEI3DPROC)(HDC hDC, UINT *uRate);
typedef BOOL (WINAPI *PFNWGLGENLOCKSOURCEDELAYI3DPROC)(HDC hDC, UINT uDelay);
typedef BOOL (WINAPI *PFNWGLGETGENLOCKSOURCEDELAYI3DPROC)(HDC hDC, UINT *uDelay);
typedef BOOL (WINAPI *PFNWGLQUERYGENLOCKMAXSOURCEDELAYI3DPROC)(HDC hDC, UINT *uMaxLineDelay, UINT *uMaxPixelDelay);
#endif
#ifndef WGL_I3D_image_buffer
#define WGL_I3D_image_buffer 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern LPVOID WINAPI wglCreateImageBufferI3D(HDC, DWORD, UINT);
extern BOOL WINAPI wglDestroyImageBufferI3D(HDC, LPVOID);
extern BOOL WINAPI wglAssociateImageBufferEventsI3D(HDC, const HANDLE *, const LPVOID *, const DWORD *, UINT);
extern BOOL WINAPI wglReleaseImageBufferEventsI3D(HDC, const LPVOID *, UINT);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef LPVOID (WINAPI *PFNWGLCREATEIMAGEBUFFERI3DPROC)(HDC hDC, DWORD dwSize, UINT uFlags);
typedef BOOL (WINAPI *PFNWGLDESTROYIMAGEBUFFERI3DPROC)(HDC hDC, LPVOID pAddress);
typedef BOOL (WINAPI *PFNWGLASSOCIATEIMAGEBUFFEREVENTSI3DPROC)(HDC hDC, const HANDLE *pEvent, const LPVOID *pAddress, const DWORD *pSize, UINT count);
typedef BOOL (WINAPI *PFNWGLRELEASEIMAGEBUFFEREVENTSI3DPROC)(HDC hDC, const LPVOID *pAddress, UINT count);
#endif
#ifndef WGL_I3D_swap_frame_lock
#define WGL_I3D_swap_frame_lock 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglEnableFrameLockI3D(void);
extern BOOL WINAPI wglDisableFrameLockI3D(void);
extern BOOL WINAPI wglIsEnabledFrameLockI3D(BOOL *);
extern BOOL WINAPI wglQueryFrameLockMasterI3D(BOOL *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLENABLEFRAMELOCKI3DPROC)(void);
typedef BOOL (WINAPI *PFNWGLDISABLEFRAMELOCKI3DPROC)(void);
typedef BOOL (WINAPI *PFNWGLISENABLEDFRAMELOCKI3DPROC)(BOOL *pFlag);
typedef BOOL (WINAPI *PFNWGLQUERYFRAMELOCKMASTERI3DPROC)(BOOL *pFlag);
#endif
#ifndef WGL_I3D_swap_frame_usage
#define WGL_I3D_swap_frame_usage 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglGetFrameUsageI3D(float *);
extern BOOL WINAPI wglBeginFrameTrackingI3D(void);
extern BOOL WINAPI wglEndFrameTrackingI3D(void);
extern BOOL WINAPI wglQueryFrameTrackingI3D(DWORD *, DWORD *, float *);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLGETFRAMEUSAGEI3DPROC)(float *pUsage);
typedef BOOL (WINAPI *PFNWGLBEGINFRAMETRACKINGI3DPROC)(void);
typedef BOOL (WINAPI *PFNWGLENDFRAMETRACKINGI3DPROC)(void);
typedef BOOL (WINAPI *PFNWGLQUERYFRAMETRACKINGI3DPROC)(DWORD *pFrameCount, DWORD *pMissedFrames, float *pLastMissedUsage);
#endif
#ifndef WGL_ATI_pixel_format_float
#define WGL_ATI_pixel_format_float 1
#endif
#ifndef WGL_NV_render_depth_texture
#define WGL_NV_render_depth_texture 1
#endif
#ifndef WGL_NV_render_texture_rectangle
#define WGL_NV_render_texture_rectangle 1
#endif
#ifndef WGL_NV_float_buffer
#define WGL_NV_float_buffer 1
#endif
#ifndef WGL_NV_swap_group
#define WGL_NV_swap_group 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglJoinSwapGroupNV(HDC hDC, GLuint group);
extern BOOL WINAPI wglBindSwapBarrierNV(GLuint group, GLuint barrier);
extern BOOL WINAPI wglQuerySwapGroupNV(HDC hDC, GLuint *group, GLuint *barrier);
extern BOOL WINAPI wglQueryMaxSwapGroupsNV(HDC hDC, GLuint *maxGroups, GLuint *maxBarriers);
extern BOOL WINAPI wglQueryFrameCountNV(HDC hDC, GLuint *count);
extern BOOL WINAPI wglResetFrameCountNV(HDC hDC);
#endif /* WGL_WGLEXT_PROTOTYPES */
typedef BOOL (WINAPI *PFNWGLJOINSWAPGROUPNVPROC)(HDC hDC, GLuint group);
typedef BOOL (WINAPI *PFNWGLBINDSWAPBARRIERNVPROC)(GLuint group, GLuint barrier);
typedef BOOL (WINAPI *PFNWGLQUERYSWAPGROUPNVPROC)(HDC hDC, GLuint *group, GLuint *barrier);
typedef BOOL (WINAPI *PFNWGLQUERYMAXSWAPGROUPSNVPROC)(HDC hDC, GLuint *maxGroups, GLuint *maxBarriers);
typedef BOOL (WINAPI *PFNWGLQUERYFRAMECOUNTNVPROC)(HDC hDC, GLuint *count);
typedef BOOL (WINAPI *PFNWGLRESETFRAMECOUNTNVPROC)(HDC hDC);
#endif
#ifndef WGL_NV_gpu_affinity
#define WGL_NV_gpu_affinity 1
#ifdef WGL_WGLEXT_PROTOTYPES
extern BOOL WINAPI wglEnumGpusNV(UINT iIndex, HGPUNV *hGpu);
extern BOOL WINAPI wglEnumGpuDevicesNV(HGPUNV hGpu, UINT iIndex, PGPU_DEVICE pGpuDevice);
extern HDC WINAPI wglCreateAffinityDCNV(const HGPUNV *pGpuList);
extern BOOL WINAPI wglEnumGpusFromAffinityDCNV(HDC hAffinityDC, UINT iIndex, HGPUNV *hGpu);
extern BOOL WINAPI wglDeleteDCNV(HDC hAffinityDC);
#else
typedef BOOL (WINAPI *PFNWGLENUMGPUSNVPROC)(UINT iIndex, HGPUNV *hGpu);
typedef BOOL (WINAPI *PFNWGLENUMGPUDEVICESNVPROC)(HGPUNV hGpu, UINT iIndex, PGPU_DEVICE pGpuDevice);
typedef HDC(WINAPI *PFNWGLCREATEAFFINITYDCNVPROC)(const HGPUNV *pGpuList);
typedef BOOL (WINAPI *PFNWGLENUMGPUSFROMAFFINITYDCNVPROC)(HDC hAffinityDC, UINT iIndex, HGPUNV *hGpu);
typedef BOOL (WINAPI *PFNWGLDELETEDCNVPROC)(HDC hAffinityDC);
#endif
#endif
#ifdef __cplusplus
}
#endif
#endif

Binary file not shown.

Binary file not shown.

File diff suppressed because one or more lines are too long

Binary file not shown.

Binary file not shown.

Binary file not shown.

File diff suppressed because one or more lines are too long

Binary file not shown.

View File

@@ -664,6 +664,7 @@ inline int _ConvertSMVer2Cores(int major, int minor) {
{0x72, 64}, {0x72, 64},
{0x75, 64}, {0x75, 64},
{0x80, 64}, {0x80, 64},
{0x86, 128},
{-1, -1}}; {-1, -1}};
int index = 0; int index = 0;
@@ -709,6 +710,7 @@ inline const char* _ConvertSMVer2ArchName(int major, int minor) {
{0x72, "Xavier"}, {0x72, "Xavier"},
{0x75, "Turing"}, {0x75, "Turing"},
{0x80, "Ampere"}, {0x80, "Ampere"},
{0x86, "Ampere"},
{-1, "Graphics Device"}}; {-1, "Graphics Device"}};
int index = 0; int index = 0;

View File

@@ -33,8 +33,10 @@
#include <stdio.h> #include <stdio.h>
#include <stdlib.h> #include <stdlib.h>
#include <string.h> #include <string.h>
#include <iostream>
#include <cstring>
#include <sstream>
#include <drvapi_error_string.h>
#include <helper_string.h> #include <helper_string.h>
#ifndef MAX #ifndef MAX
@@ -66,48 +68,22 @@ inline int ftoi(float value) {
// These are the inline versions for all of the SDK helper functions // These are the inline versions for all of the SDK helper functions
inline void __checkCudaErrors(CUresult err, const char *file, const int line) { inline void __checkCudaErrors(CUresult err, const char *file, const int line) {
if (CUDA_SUCCESS != err) { if (CUDA_SUCCESS != err) {
const char *errorStr = NULL;
cuGetErrorString(err, &errorStr);
fprintf(stderr, fprintf(stderr,
"checkCudaErrors() Driver API error = %04d \"%s\" from file <%s>, " "checkCudaErrors() Driver API error = %04d \"%s\" from file <%s>, "
"line %i.\n", "line %i.\n",
err, getCudaDrvErrorString(err), file, line); err, errorStr, file, line);
exit(EXIT_FAILURE); exit(EXIT_FAILURE);
} }
} }
#endif #endif
#ifdef getLastCudaDrvErrorMsg
#undef getLastCudaDrvErrorMsg
#endif
#define getLastCudaDrvErrorMsg(msg) \
__getLastCudaDrvErrorMsg(msg, __FILE__, __LINE__)
inline void __getLastCudaDrvErrorMsg(const char *msg, const char *file,
const int line) {
CUresult err = cuCtxSynchronize();
if (CUDA_SUCCESS != err) {
fprintf(stderr, "getLastCudaDrvErrorMsg -> %s", msg);
fprintf(stderr,
"getLastCudaDrvErrorMsg -> cuCtxSynchronize API error = %04d "
"\"%s\" in file <%s>, line %i.\n",
err, getCudaDrvErrorString(err), file, line);
exit(EXIT_FAILURE);
}
}
// This function wraps the CUDA Driver API into a template function // This function wraps the CUDA Driver API into a template function
template <class T> template <class T>
inline void getCudaAttribute(T *attribute, CUdevice_attribute device_attribute, inline void getCudaAttribute(T *attribute, CUdevice_attribute device_attribute,
int device) { int device) {
CUresult error_result = checkCudaErrors(cuDeviceGetAttribute(attribute, device_attribute, device));
cuDeviceGetAttribute(attribute, device_attribute, device);
if (error_result != CUDA_SUCCESS) {
printf("cuDeviceGetAttribute returned %d\n-> %s\n",
static_cast<int>(error_result), getCudaDrvErrorString(error_result));
exit(EXIT_SUCCESS);
}
} }
#endif #endif
@@ -135,6 +111,8 @@ inline int _ConvertSMVer2CoresDRV(int major, int minor) {
{0x70, 64}, {0x70, 64},
{0x72, 64}, {0x72, 64},
{0x75, 64}, {0x75, 64},
{0x80, 64},
{0x86, 128},
{-1, -1}}; {-1, -1}};
int index = 0; int index = 0;
@@ -161,11 +139,9 @@ inline int _ConvertSMVer2CoresDRV(int major, int minor) {
inline int gpuDeviceInitDRV(int ARGC, const char **ARGV) { inline int gpuDeviceInitDRV(int ARGC, const char **ARGV) {
int cuDevice = 0; int cuDevice = 0;
int deviceCount = 0; int deviceCount = 0;
CUresult err = cuInit(0); checkCudaErrors(cuInit(0));
if (CUDA_SUCCESS == err) { checkCudaErrors(cuDeviceGetCount(&deviceCount));
checkCudaErrors(cuDeviceGetCount(&deviceCount));
}
if (deviceCount == 0) { if (deviceCount == 0) {
fprintf(stderr, "cudaDeviceInit error: no devices supporting CUDA\n"); fprintf(stderr, "cudaDeviceInit error: no devices supporting CUDA\n");
@@ -192,7 +168,7 @@ inline int gpuDeviceInitDRV(int ARGC, const char **ARGV) {
checkCudaErrors(cuDeviceGet(&cuDevice, dev)); checkCudaErrors(cuDeviceGet(&cuDevice, dev));
char name[100]; char name[100];
cuDeviceGetName(name, 100, cuDevice); checkCudaErrors(cuDeviceGetName(name, 100, cuDevice));
int computeMode; int computeMode;
getCudaAttribute<int>(&computeMode, CU_DEVICE_ATTRIBUTE_COMPUTE_MODE, dev); getCudaAttribute<int>(&computeMode, CU_DEVICE_ATTRIBUTE_COMPUTE_MODE, dev);
@@ -218,7 +194,6 @@ inline int gpuGetMaxGflopsDeviceIdDRV() {
int device_count = 0; int device_count = 0;
int sm_per_multiproc = 0; int sm_per_multiproc = 0;
unsigned long long max_compute_perf = 0; unsigned long long max_compute_perf = 0;
int best_SM_arch = 0;
int major = 0; int major = 0;
int minor = 0; int minor = 0;
int multiProcessorCount; int multiProcessorCount;
@@ -234,19 +209,6 @@ inline int gpuGetMaxGflopsDeviceIdDRV() {
exit(EXIT_FAILURE); exit(EXIT_FAILURE);
} }
// Find the best major SM Architecture GPU device
while (current_device < device_count) {
checkCudaErrors(cuDeviceGetAttribute(
&major, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR, current_device));
checkCudaErrors(cuDeviceGetAttribute(
&minor, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR, current_device));
if (major > 0 && major < 9999) {
best_SM_arch = MAX(best_SM_arch, major);
}
current_device++;
}
// Find the best CUDA capable GPU device // Find the best CUDA capable GPU device
current_device = 0; current_device = 0;
@@ -277,17 +239,8 @@ inline int gpuGetMaxGflopsDeviceIdDRV() {
clockRate); clockRate);
if (compute_perf > max_compute_perf) { if (compute_perf > max_compute_perf) {
// If we find GPU with SM major > 2, search only these
if (best_SM_arch > 2) {
// If our device==dest_SM_arch, choose this, or else pass
if (major == best_SM_arch) {
max_compute_perf = compute_perf;
max_perf_device = current_device;
}
} else {
max_compute_perf = compute_perf; max_compute_perf = compute_perf;
max_perf_device = current_device; max_perf_device = current_device;
}
} }
} else { } else {
devices_prohibited++; devices_prohibited++;
@@ -414,7 +367,39 @@ inline bool checkCudaCapabilitiesDRV(int major_version, int minor_version,
} }
} }
#endif #endif
bool inline findFatbinPath(const char *module_file, std::string &module_path, char **argv, std::ostringstream &ostrm)
{
char *actual_path = sdkFindFilePath(module_file, argv[0]);
// end of CUDA Helper Functions if (actual_path)
{
module_path = actual_path;
}
else
{
printf("> findModulePath file not found: <%s> \n", module_file);
return false;
}
if (module_path.empty())
{
printf("> findModulePath could not find file: <%s> \n", module_file);
return false;
}
else
{
printf("> findModulePath found file at <%s>\n", module_path.c_str());
if (module_path.rfind("fatbin") != std::string::npos)
{
std::ifstream fileIn(module_path.c_str(), std::ios::binary);
ostrm << fileIn.rdbuf();
fileIn.close();
}
return true;
}
}
// end of CUDA Helper Functions
#endif // COMMON_HELPER_CUDA_DRVAPI_H_ #endif // COMMON_HELPER_CUDA_DRVAPI_H_

267
Common/helper_gl.h Normal file
View File

@@ -0,0 +1,267 @@
/* Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of NVIDIA CORPORATION nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
* OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
// These are helper functions for the SDK samples (OpenGL)
#ifndef HELPER_GL_H
#define HELPER_GL_H
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
#include <GL/glew.h>
#endif
#if defined(__APPLE__) || defined(MACOSX)
#include <OpenGL/gl.h>
#else
#include <GL/gl.h>
#ifdef __linux__
#include <GL/glx.h>
#endif /* __linux__ */
#endif
#include <iostream>
#include <cstdio>
#include <string>
#include <sstream>
#include <algorithm>
#include <iterator>
#include <vector>
#include <assert.h>
/* Prototypes */
namespace __HelperGL {
static int isGLVersionSupported(unsigned reqMajor, unsigned reqMinor);
static int areGLExtensionsSupported(const std::string &);
#ifdef __linux__
#ifndef HELPERGL_EXTERN_GL_FUNC_IMPLEMENTATION
#define USE_GL_FUNC(name, proto) proto name = (proto) glXGetProcAddress ((const GLubyte *)#name)
#else
#define USE_GL_FUNC(name, proto) extern proto name
#endif
USE_GL_FUNC(glBindBuffer, PFNGLBINDBUFFERPROC);
USE_GL_FUNC(glDeleteBuffers, PFNGLDELETEBUFFERSPROC);
USE_GL_FUNC(glBufferData, PFNGLBUFFERDATAPROC);
USE_GL_FUNC(glBufferSubData, PFNGLBUFFERSUBDATAPROC);
USE_GL_FUNC(glGenBuffers, PFNGLGENBUFFERSPROC);
USE_GL_FUNC(glCreateProgram, PFNGLCREATEPROGRAMPROC);
USE_GL_FUNC(glBindProgramARB, PFNGLBINDPROGRAMARBPROC);
USE_GL_FUNC(glGenProgramsARB, PFNGLGENPROGRAMSARBPROC);
USE_GL_FUNC(glDeleteProgramsARB, PFNGLDELETEPROGRAMSARBPROC);
USE_GL_FUNC(glDeleteProgram, PFNGLDELETEPROGRAMPROC);
USE_GL_FUNC(glGetProgramInfoLog, PFNGLGETPROGRAMINFOLOGPROC);
USE_GL_FUNC(glGetProgramiv, PFNGLGETPROGRAMIVPROC);
USE_GL_FUNC(glProgramParameteriEXT, PFNGLPROGRAMPARAMETERIEXTPROC);
USE_GL_FUNC(glProgramStringARB, PFNGLPROGRAMSTRINGARBPROC);
USE_GL_FUNC(glUnmapBuffer, PFNGLUNMAPBUFFERPROC);
USE_GL_FUNC(glMapBuffer, PFNGLMAPBUFFERPROC);
USE_GL_FUNC(glGetBufferParameteriv, PFNGLGETBUFFERPARAMETERIVPROC);
USE_GL_FUNC(glLinkProgram, PFNGLLINKPROGRAMPROC);
USE_GL_FUNC(glUseProgram, PFNGLUSEPROGRAMPROC);
USE_GL_FUNC(glAttachShader, PFNGLATTACHSHADERPROC);
USE_GL_FUNC(glCreateShader, PFNGLCREATESHADERPROC);
USE_GL_FUNC(glShaderSource, PFNGLSHADERSOURCEPROC);
USE_GL_FUNC(glCompileShader, PFNGLCOMPILESHADERPROC);
USE_GL_FUNC(glDeleteShader, PFNGLDELETESHADERPROC);
USE_GL_FUNC(glGetShaderInfoLog, PFNGLGETSHADERINFOLOGPROC);
USE_GL_FUNC(glGetShaderiv, PFNGLGETSHADERIVPROC);
USE_GL_FUNC(glUniform1i, PFNGLUNIFORM1IPROC);
USE_GL_FUNC(glUniform1f, PFNGLUNIFORM1FPROC);
USE_GL_FUNC(glUniform2f, PFNGLUNIFORM2FPROC);
USE_GL_FUNC(glUniform3f, PFNGLUNIFORM3FPROC);
USE_GL_FUNC(glUniform4f, PFNGLUNIFORM4FPROC);
USE_GL_FUNC(glUniform1fv, PFNGLUNIFORM1FVPROC);
USE_GL_FUNC(glUniform2fv, PFNGLUNIFORM2FVPROC);
USE_GL_FUNC(glUniform3fv, PFNGLUNIFORM3FVPROC);
USE_GL_FUNC(glUniform4fv, PFNGLUNIFORM4FVPROC);
USE_GL_FUNC(glUniformMatrix4fv, PFNGLUNIFORMMATRIX4FVPROC);
USE_GL_FUNC(glSecondaryColor3fv, PFNGLSECONDARYCOLOR3FVPROC);
USE_GL_FUNC(glGetUniformLocation, PFNGLGETUNIFORMLOCATIONPROC);
USE_GL_FUNC(glGenFramebuffersEXT, PFNGLGENFRAMEBUFFERSEXTPROC);
USE_GL_FUNC(glBindFramebufferEXT, PFNGLBINDFRAMEBUFFEREXTPROC);
USE_GL_FUNC(glDeleteFramebuffersEXT, PFNGLDELETEFRAMEBUFFERSEXTPROC);
USE_GL_FUNC(glCheckFramebufferStatusEXT, PFNGLCHECKFRAMEBUFFERSTATUSEXTPROC);
USE_GL_FUNC(glGetFramebufferAttachmentParameterivEXT, PFNGLGETFRAMEBUFFERATTACHMENTPARAMETERIVEXTPROC);
USE_GL_FUNC(glFramebufferTexture1DEXT, PFNGLFRAMEBUFFERTEXTURE1DEXTPROC);
USE_GL_FUNC(glFramebufferTexture2DEXT, PFNGLFRAMEBUFFERTEXTURE2DEXTPROC);
USE_GL_FUNC(glFramebufferTexture3DEXT, PFNGLFRAMEBUFFERTEXTURE3DEXTPROC);
USE_GL_FUNC(glGenerateMipmapEXT, PFNGLGENERATEMIPMAPEXTPROC);
USE_GL_FUNC(glGenRenderbuffersEXT, PFNGLGENRENDERBUFFERSEXTPROC);
USE_GL_FUNC(glDeleteRenderbuffersEXT, PFNGLDELETERENDERBUFFERSEXTPROC);
USE_GL_FUNC(glBindRenderbufferEXT, PFNGLBINDRENDERBUFFEREXTPROC);
USE_GL_FUNC(glRenderbufferStorageEXT, PFNGLRENDERBUFFERSTORAGEEXTPROC);
USE_GL_FUNC(glFramebufferRenderbufferEXT, PFNGLFRAMEBUFFERRENDERBUFFEREXTPROC);
USE_GL_FUNC(glClampColorARB, PFNGLCLAMPCOLORARBPROC);
USE_GL_FUNC(glBindFragDataLocationEXT, PFNGLBINDFRAGDATALOCATIONEXTPROC);
#if !defined(GLX_EXTENSION_NAME) || !defined(GL_VERSION_1_3)
USE_GL_FUNC(glActiveTexture, PFNGLACTIVETEXTUREPROC);
USE_GL_FUNC(glClientActiveTexture, PFNGLACTIVETEXTUREPROC);
#endif
#undef USE_GL_FUNC
#endif /*__linux__ */
}
namespace __HelperGL {
namespace __Int {
static std::vector<std::string> split(const std::string &str)
{
std::istringstream ss(str);
std::istream_iterator<std::string> it(ss);
return std::vector<std::string> (it, std::istream_iterator<std::string>());
}
/* Sort the vector passed by reference */
template<typename T> static inline void sort(std::vector<T> &a)
{
std::sort(a.begin(), a.end());
}
/* Compare two vectors */
template<typename T> static int equals(std::vector<T> a, std::vector<T> b)
{
if (a.size() != b.size()) return 0;
sort(a);
sort(b);
return std::equal(a.begin(), a.end(), b.begin());
}
template<typename T> static std::vector<T> getIntersection(std::vector<T> a, std::vector<T> b)
{
sort(a);
sort(b);
std::vector<T> rc;
std::set_intersection(a.begin(), a.end(), b.begin(), b.end(),
std::back_inserter<std::vector<std::string> >(rc));
return rc;
}
static std::vector<std::string> getGLExtensions()
{
std::string extensionsStr( (const char *)glGetString(GL_EXTENSIONS));
return split (extensionsStr);
}
}
static int areGLExtensionsSupported(const std::string &extensions)
{
std::vector<std::string> all = __Int::getGLExtensions();
std::vector<std::string> requested = __Int::split(extensions);
std::vector<std::string> matched = __Int::getIntersection(all, requested);
return __Int::equals(matched, requested);
}
static int isGLVersionSupported(unsigned reqMajor, unsigned reqMinor)
{
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
if (glewInit() != GLEW_OK)
{
std::cerr << "glewInit() failed!" << std::endl;
return 0;
}
#endif
std::string version ((const char *) glGetString (GL_VERSION));
std::stringstream stream (version);
unsigned major, minor;
char dot;
stream >> major >> dot >> minor;
assert (dot == '.');
return major > reqMajor || (major == reqMajor && minor >= reqMinor);
}
static inline const char* glErrorToString(GLenum err)
{
#define CASE_RETURN_MACRO(arg) case arg: return #arg
switch(err)
{
CASE_RETURN_MACRO(GL_NO_ERROR);
CASE_RETURN_MACRO(GL_INVALID_ENUM);
CASE_RETURN_MACRO(GL_INVALID_VALUE);
CASE_RETURN_MACRO(GL_INVALID_OPERATION);
CASE_RETURN_MACRO(GL_OUT_OF_MEMORY);
CASE_RETURN_MACRO(GL_STACK_UNDERFLOW);
CASE_RETURN_MACRO(GL_STACK_OVERFLOW);
#ifdef GL_INVALID_FRAMEBUFFER_OPERATION
CASE_RETURN_MACRO(GL_INVALID_FRAMEBUFFER_OPERATION);
#endif
default: break;
}
#undef CASE_RETURN_MACRO
return "*UNKNOWN*";
}
////////////////////////////////////////////////////////////////////////////
//! Check for OpenGL error
//! @return bool if no GL error has been encountered, otherwise 0
//! @param file __FILE__ macro
//! @param line __LINE__ macro
//! @note The GL error is listed on stderr
//! @note This function should be used via the CHECK_ERROR_GL() macro
////////////////////////////////////////////////////////////////////////////
inline bool sdkCheckErrorGL(const char *file, const int line)
{
bool ret_val = true;
// check for error
GLenum gl_error = glGetError();
if (gl_error != GL_NO_ERROR)
{
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
char tmpStr[512];
// NOTE: "%s(%i) : " allows Visual Studio to directly jump to the file at the right line
// when the user double clicks on the error line in the Output pane. Like any compile error.
sprintf_s(tmpStr, 255, "\n%s(%i) : GL Error : %s\n\n", file, line, glErrorToString(gl_error));
fprintf(stderr, "%s", tmpStr);
#endif
fprintf(stderr, "GL Error in file '%s' in line %d :\n", file, line);
fprintf(stderr, "%s\n", glErrorToString(gl_error));
ret_val = false;
}
return ret_val;
}
#define SDK_CHECK_ERROR_GL() \
if( false == sdkCheckErrorGL( __FILE__, __LINE__)) { \
exit(EXIT_FAILURE); \
}
} /* of namespace __HelperGL*/
using namespace __HelperGL;
#endif /*HELPER_GL_H*/

View File

@@ -293,6 +293,9 @@ inline char *sdkFindFilePath(const char *filename,
"../../../../Samples/<executable_name>/data/", // up 4 in tree "../../../../Samples/<executable_name>/data/", // up 4 in tree
"../../../Samples/<executable_name>/data/", // up 3 in tree "../../../Samples/<executable_name>/data/", // up 3 in tree
"../../Samples/<executable_name>/data/", // up 2 in tree "../../Samples/<executable_name>/data/", // up 2 in tree
"../../../../Common/data/", // up 4 in tree
"../../../Common/data/", // up 3 in tree
"../../Common/data/" // up 2 in tree
}; };
// Extract the executable name // Extract the executable name

BIN
Common/lib/x64/freeglut.lib Normal file

Binary file not shown.

BIN
Common/lib/x64/glew64.lib Normal file

Binary file not shown.

View File

@@ -47,8 +47,8 @@
} \ } \
} while (0) } while (0)
void compileFileToPTX(char *filename, int argc, char **argv, char **ptxResult, void compileFileToCUBIN(char *filename, int argc, char **argv, char **cubinResult,
size_t *ptxResultSize, int requiresCGheaders) { size_t *cubinResultSize, int requiresCGheaders) {
std::ifstream inputFile(filename, std::ifstream inputFile(filename,
std::ios::in | std::ios::binary | std::ios::ate); std::ios::in | std::ios::binary | std::ios::ate);
@@ -83,9 +83,9 @@ void compileFileToPTX(char *filename, int argc, char **argv, char **ptxResult,
&minor, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR, cuDevice)); &minor, CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR, cuDevice));
{ {
// Compile for the GPU arch on which are going to run cuda kernel. // Compile cubin for the GPU arch on which are going to run cuda kernel.
std::string compileOptions; std::string compileOptions;
compileOptions = "--gpu-architecture=compute_"; compileOptions = "--gpu-architecture=sm_";
compileParams[numCompileOptions] = reinterpret_cast<char *>( compileParams[numCompileOptions] = reinterpret_cast<char *>(
malloc(sizeof(char) * (compileOptions.length() + 10))); malloc(sizeof(char) * (compileOptions.length() + 10)));
@@ -158,21 +158,20 @@ void compileFileToPTX(char *filename, int argc, char **argv, char **ptxResult,
free(log); free(log);
NVRTC_SAFE_CALL("nvrtcCompileProgram", res); NVRTC_SAFE_CALL("nvrtcCompileProgram", res);
// fetch PTX
size_t ptxSize; size_t codeSize;
NVRTC_SAFE_CALL("nvrtcGetPTXSize", nvrtcGetPTXSize(prog, &ptxSize)); NVRTC_SAFE_CALL("nvrtcGetCUBINSize", nvrtcGetCUBINSize(prog, &codeSize));
char *ptx = reinterpret_cast<char *>(malloc(sizeof(char) * ptxSize)); char *code = new char[codeSize];
NVRTC_SAFE_CALL("nvrtcGetPTX", nvrtcGetPTX(prog, ptx)); NVRTC_SAFE_CALL("nvrtcGetCUBIN", nvrtcGetCUBIN(prog, code));
NVRTC_SAFE_CALL("nvrtcDestroyProgram", nvrtcDestroyProgram(&prog)); *cubinResult = code;
*ptxResult = ptx; *cubinResultSize = codeSize;
*ptxResultSize = ptxSize;
for (int i = 0; i < numCompileOptions; i++) { for (int i = 0; i < numCompileOptions; i++) {
free(compileParams[i]); free(compileParams[i]);
} }
} }
CUmodule loadPTX(char *ptx, int argc, char **argv) { CUmodule loadCUBIN(char *cubin, int argc, char **argv) {
CUmodule module; CUmodule module;
CUcontext context; CUcontext context;
int major = 0, minor = 0; int major = 0, minor = 0;
@@ -190,11 +189,10 @@ CUmodule loadPTX(char *ptx, int argc, char **argv) {
printf("> GPU Device has SM %d.%d compute capability\n", major, minor); printf("> GPU Device has SM %d.%d compute capability\n", major, minor);
checkCudaErrors(cuInit(0)); checkCudaErrors(cuInit(0));
checkCudaErrors(cuDeviceGet(&cuDevice, 0));
checkCudaErrors(cuCtxCreate(&context, 0, cuDevice)); checkCudaErrors(cuCtxCreate(&context, 0, cuDevice));
checkCudaErrors(cuModuleLoadDataEx(&module, ptx, 0, 0, 0)); checkCudaErrors(cuModuleLoadData(&module, cubin));
free(ptx); free(cubin);
return module; return module;
} }

View File

@@ -1,11 +1,30 @@
# CUDA Samples # CUDA Samples
Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads). Samples for CUDA Developers which demonstrates features in CUDA Toolkit. This version supports [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads).
## Release Notes ## Release Notes
This section describes the release notes for the CUDA Samples on GitHub only. This section describes the release notes for the CUDA Samples on GitHub only.
### CUDA 11.2
* Added `streamOrderedAllocation`. Demonstrates stream ordered memory allocation on a GPU using cudaMallocAsync and cudaMemPool family of APIs.
* Added `streamOrderedAllocationP2P`. Demonstrates peer-to-peer access of stream ordered memory allocated using cudaMallocAsync and cudaMemPool family of APIs.
* Dropped Visual Studio 2015 support from all the windows supported samples.
* FreeImage is no longer distributed with the CUDA Samples. On Windows, see the [Dependencies](#freeimage) section for more details on how to set up FreeImage. On Linux, it is recommended to install FreeImage with your distribution's package manager.
* All the samples using CUDA Pipeline & Arrive-wait barriers are been updated to use new `cuda::pipeline` and `cuda::barrier` interfaces.
* Updated all the samples to build with parallel build option `--threads` of `nvcc` cuda compiler.
* Added `cudaNvSciNvMedia`. Demonstrates CUDA-NvMedia interop via NvSciBuf/NvSciSync APIs.
* Added `simpleGL`. Demonstrates interoperability between CUDA and OpenGL.
### CUDA 11.1
* Added `watershedSegmentationNPP`. Demonstrates how to use the NPP watershed segmentation function.
* Added `batchedLabelMarkersAndLabelCompressionNPP`. Demonstrates how to use the NPP label markers generation and label compression functions based on a Union Find (UF) algorithm including both single image and batched image versions.
* Dropped Visual Studio 2012, 2013 support from all the windows supported samples.
* Added kernel performing warp aggregated atomic max in multi buckets using cg::labeled_partition & cg::reduce in `warpAggregatedAtomicsCG`.
* Added extended CG shuffle mechanics to `shfl_scan` sample.
* Added `cudaOpenMP`. Demonstrates how to use OpenMP API to write an application for multiple GPUs.
* Added `simpleZeroCopy`. Demonstrates how to use zero copy, kernels can read and write directly to pinned system memory.
### CUDA 11.0 ### CUDA 11.0
* Added `dmmaTensorCoreGemm`. Demonstrates double precision GEMM computation using the Double precision Warp Matrix Multiply and Accumulate (WMMA) API introduced with CUDA 11 in Ampere chip family tensor cores. * Added `dmmaTensorCoreGemm`. Demonstrates double precision GEMM computation using the Double precision Warp Matrix Multiply and Accumulate (WMMA) API introduced with CUDA 11 in Ampere chip family tensor cores.
* Added `bf16TensorCoreGemm`. Demonstrates __nv_bfloat16 (e8m7) GEMM computation using the __nv_bfloat16 WMMA API introduced with CUDA 11 in Ampere chip family tensor cores. * Added `bf16TensorCoreGemm`. Demonstrates __nv_bfloat16 (e8m7) GEMM computation using the __nv_bfloat16 WMMA API introduced with CUDA 11 in Ampere chip family tensor cores.
@@ -84,7 +103,7 @@ This is the first release of CUDA Samples on GitHub:
### Prerequisites ### Prerequisites
Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
For system requirements and installation instructions of cuda toolkit, please refer to the [Linux Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-linux/), and the [Windows Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html). For system requirements and installation instructions of cuda toolkit, please refer to the [Linux Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-linux/), and the [Windows Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html).
### Getting the CUDA Samples ### Getting the CUDA Samples
@@ -141,34 +160,38 @@ The samples makefiles can take advantage of certain options:
### Samples by OS ### Samples by OS
#### Linux #### Linux
**[warpAggregatedAtomicsCG](./Samples/warpAggregatedAtomicsCG)** | **[boxFilterNPP](./Samples/boxFilterNPP)** | **[binaryPartitionCG](./Samples/binaryPartitionCG)** | **[dmmaTensorCoreGemm](./Samples/dmmaTensorCoreGemm)** | **[warpAggregatedAtomicsCG](./Samples/warpAggregatedAtomicsCG)** | **[boxFilterNPP](./Samples/boxFilterNPP)** | **[streamOrderedAllocationP2P](./Samples/streamOrderedAllocationP2P)** | **[binaryPartitionCG](./Samples/binaryPartitionCG)** |
---|---|---|---| ---|---|---|---|
**[EGLStream_CUDA_Interop](./Samples/EGLStream_CUDA_Interop)** | **[conjugateGradientMultiBlockCG](./Samples/conjugateGradientMultiBlockCG)** | **[simpleIPC](./Samples/simpleIPC)** | **[memMapIPCDrv](./Samples/memMapIPCDrv)** | **[dmmaTensorCoreGemm](./Samples/dmmaTensorCoreGemm)** | **[EGLStream_CUDA_Interop](./Samples/EGLStream_CUDA_Interop)** | **[conjugateGradientMultiBlockCG](./Samples/conjugateGradientMultiBlockCG)** | **[simpleIPC](./Samples/simpleIPC)** |
**[vectorAddMMAP](./Samples/vectorAddMMAP)** | **[shfl_scan](./Samples/shfl_scan)** | **[conjugateGradientCudaGraphs](./Samples/conjugateGradientCudaGraphs)** | **[globalToShmemAsyncCopy](./Samples/globalToShmemAsyncCopy)** | **[memMapIPCDrv](./Samples/memMapIPCDrv)** | **[vectorAddMMAP](./Samples/vectorAddMMAP)** | **[shfl_scan](./Samples/shfl_scan)** | **[simpleZeroCopy](./Samples/simpleZeroCopy)** |
**[nvJPEG](./Samples/nvJPEG)** | **[simpleCudaGraphs](./Samples/simpleCudaGraphs)** | **[deviceQuery](./Samples/deviceQuery)** | **[simpleVoteIntrinsics](./Samples/simpleVoteIntrinsics)** | **[conjugateGradientCudaGraphs](./Samples/conjugateGradientCudaGraphs)** | **[globalToShmemAsyncCopy](./Samples/globalToShmemAsyncCopy)** | **[cudaNvSciNvMedia](./Samples/cudaNvSciNvMedia)** | **[nvJPEG](./Samples/nvJPEG)** |
**[simpleCUBLASXT](./Samples/simpleCUBLASXT)** | **[simpleAttributes](./Samples/simpleAttributes)** | **[cudaNvSci](./Samples/cudaNvSci)** | **[tf32TensorCoreGemm](./Samples/tf32TensorCoreGemm)** | **[batchedLabelMarkersAndLabelCompressionNPP](./Samples/batchedLabelMarkersAndLabelCompressionNPP)** | **[watershedSegmentationNPP](./Samples/watershedSegmentationNPP)** | **[simpleCudaGraphs](./Samples/simpleCudaGraphs)** | **[streamOrderedAllocation](./Samples/streamOrderedAllocation)** |
**[deviceQuery](./Samples/deviceQuery)** | **[simpleVoteIntrinsics](./Samples/simpleVoteIntrinsics)** | **[simpleCUBLASXT](./Samples/simpleCUBLASXT)** | **[simpleAttributes](./Samples/simpleAttributes)** |
**[cudaNvSci](./Samples/cudaNvSci)** | **[tf32TensorCoreGemm](./Samples/tf32TensorCoreGemm)** | **[UnifiedMemoryPerf](./Samples/UnifiedMemoryPerf)** | **[cudaCompressibleMemory](./Samples/cudaCompressibleMemory)** |
**[bf16TensorCoreGemm](./Samples/bf16TensorCoreGemm)** | **[cuSolverDn_LinearSolver](./Samples/cuSolverDn_LinearSolver)** | **[vulkanImageCUDA](./Samples/vulkanImageCUDA)** | **[conjugateGradientMultiDeviceCG](./Samples/conjugateGradientMultiDeviceCG)** |
**[matrixMulDrv](./Samples/matrixMulDrv)** | **[cuSolverSp_LinearSolver](./Samples/cuSolverSp_LinearSolver)** | **[simpleCUFFT](./Samples/simpleCUFFT)** | **[reduction](./Samples/reduction)** |
**[nvJPEG_encoder](./Samples/nvJPEG_encoder)** | **[simpleDrvRuntime](./Samples/simpleDrvRuntime)** | **[MersenneTwisterGP11213](./Samples/MersenneTwisterGP11213)** | **[simpleAWBarrier](./Samples/simpleAWBarrier)** |
**[immaTensorCoreGemm](./Samples/immaTensorCoreGemm)** | **[bandwidthTest](./Samples/bandwidthTest)** | **[concurrentKernels](./Samples/concurrentKernels)** | **[simpleCUBLAS](./Samples/simpleCUBLAS)** |
**[NV12toBGRandResize](./Samples/NV12toBGRandResize)** | **[simpleGL](./Samples/simpleGL)** | **[cudaTensorCoreGemm](./Samples/cudaTensorCoreGemm)** | **[jacobiCudaGraphs](./Samples/jacobiCudaGraphs)** |
**[simpleVulkan](./Samples/simpleVulkan)** | **[vectorAdd_nvrtc](./Samples/vectorAdd_nvrtc)** | **[cannyEdgeDetectorNPP](./Samples/cannyEdgeDetectorNPP)** | **[p2pBandwidthLatencyTest](./Samples/p2pBandwidthLatencyTest)** |
**[simpleVulkanMMAP](./Samples/simpleVulkanMMAP)** | **[cudaOpenMP](./Samples/cudaOpenMP)** | **[matrixMul](./Samples/matrixMul)** | **[systemWideAtomics](./Samples/systemWideAtomics)** |
#### Windows
**[warpAggregatedAtomicsCG](./Samples/warpAggregatedAtomicsCG)** | **[boxFilterNPP](./Samples/boxFilterNPP)** | **[streamOrderedAllocationP2P](./Samples/streamOrderedAllocationP2P)** | **[binaryPartitionCG](./Samples/binaryPartitionCG)** |
---|---|---|---|
**[dmmaTensorCoreGemm](./Samples/dmmaTensorCoreGemm)** | **[conjugateGradientMultiBlockCG](./Samples/conjugateGradientMultiBlockCG)** | **[simpleIPC](./Samples/simpleIPC)** | **[memMapIPCDrv](./Samples/memMapIPCDrv)** |
**[vectorAddMMAP](./Samples/vectorAddMMAP)** | **[shfl_scan](./Samples/shfl_scan)** | **[simpleZeroCopy](./Samples/simpleZeroCopy)** | **[conjugateGradientCudaGraphs](./Samples/conjugateGradientCudaGraphs)** |
**[globalToShmemAsyncCopy](./Samples/globalToShmemAsyncCopy)** | **[nvJPEG](./Samples/nvJPEG)** | **[batchedLabelMarkersAndLabelCompressionNPP](./Samples/batchedLabelMarkersAndLabelCompressionNPP)** | **[simpleD3D12](./Samples/simpleD3D12)** |
**[watershedSegmentationNPP](./Samples/watershedSegmentationNPP)** | **[simpleCudaGraphs](./Samples/simpleCudaGraphs)** | **[streamOrderedAllocation](./Samples/streamOrderedAllocation)** | **[deviceQuery](./Samples/deviceQuery)** |
**[simpleVoteIntrinsics](./Samples/simpleVoteIntrinsics)** | **[simpleCUBLASXT](./Samples/simpleCUBLASXT)** | **[simpleAttributes](./Samples/simpleAttributes)** | **[tf32TensorCoreGemm](./Samples/tf32TensorCoreGemm)** |
**[UnifiedMemoryPerf](./Samples/UnifiedMemoryPerf)** | **[cudaCompressibleMemory](./Samples/cudaCompressibleMemory)** | **[bf16TensorCoreGemm](./Samples/bf16TensorCoreGemm)** | **[cuSolverDn_LinearSolver](./Samples/cuSolverDn_LinearSolver)** | **[UnifiedMemoryPerf](./Samples/UnifiedMemoryPerf)** | **[cudaCompressibleMemory](./Samples/cudaCompressibleMemory)** | **[bf16TensorCoreGemm](./Samples/bf16TensorCoreGemm)** | **[cuSolverDn_LinearSolver](./Samples/cuSolverDn_LinearSolver)** |
**[vulkanImageCUDA](./Samples/vulkanImageCUDA)** | **[conjugateGradientMultiDeviceCG](./Samples/conjugateGradientMultiDeviceCG)** | **[matrixMulDrv](./Samples/matrixMulDrv)** | **[cuSolverSp_LinearSolver](./Samples/cuSolverSp_LinearSolver)** | **[vulkanImageCUDA](./Samples/vulkanImageCUDA)** | **[conjugateGradientMultiDeviceCG](./Samples/conjugateGradientMultiDeviceCG)** | **[matrixMulDrv](./Samples/matrixMulDrv)** | **[cuSolverSp_LinearSolver](./Samples/cuSolverSp_LinearSolver)** |
**[simpleCUFFT](./Samples/simpleCUFFT)** | **[reduction](./Samples/reduction)** | **[nvJPEG_encoder](./Samples/nvJPEG_encoder)** | **[simpleDrvRuntime](./Samples/simpleDrvRuntime)** | **[simpleCUFFT](./Samples/simpleCUFFT)** | **[reduction](./Samples/reduction)** | **[nvJPEG_encoder](./Samples/nvJPEG_encoder)** | **[simpleDrvRuntime](./Samples/simpleDrvRuntime)** |
**[MersenneTwisterGP11213](./Samples/MersenneTwisterGP11213)** | **[simpleAWBarrier](./Samples/simpleAWBarrier)** | **[immaTensorCoreGemm](./Samples/immaTensorCoreGemm)** | **[bandwidthTest](./Samples/bandwidthTest)** | **[simpleD3D11](./Samples/simpleD3D11)** | **[MersenneTwisterGP11213](./Samples/MersenneTwisterGP11213)** | **[simpleAWBarrier](./Samples/simpleAWBarrier)** | **[immaTensorCoreGemm](./Samples/immaTensorCoreGemm)** |
**[concurrentKernels](./Samples/concurrentKernels)** | **[simpleCUBLAS](./Samples/simpleCUBLAS)** | **[NV12toBGRandResize](./Samples/NV12toBGRandResize)** | **[cudaTensorCoreGemm](./Samples/cudaTensorCoreGemm)** | **[bandwidthTest](./Samples/bandwidthTest)** | **[concurrentKernels](./Samples/concurrentKernels)** | **[simpleCUBLAS](./Samples/simpleCUBLAS)** | **[NV12toBGRandResize](./Samples/NV12toBGRandResize)** |
**[jacobiCudaGraphs](./Samples/jacobiCudaGraphs)** | **[simpleVulkan](./Samples/simpleVulkan)** | **[vectorAdd_nvrtc](./Samples/vectorAdd_nvrtc)** | **[cannyEdgeDetectorNPP](./Samples/cannyEdgeDetectorNPP)** | **[simpleGL](./Samples/simpleGL)** | **[cudaTensorCoreGemm](./Samples/cudaTensorCoreGemm)** | **[jacobiCudaGraphs](./Samples/jacobiCudaGraphs)** | **[simpleVulkan](./Samples/simpleVulkan)** |
**[p2pBandwidthLatencyTest](./Samples/p2pBandwidthLatencyTest)** | **[simpleVulkanMMAP](./Samples/simpleVulkanMMAP)** | **[matrixMul](./Samples/matrixMul)** | **[systemWideAtomics](./Samples/systemWideAtomics)** | **[vectorAdd_nvrtc](./Samples/vectorAdd_nvrtc)** | **[cannyEdgeDetectorNPP](./Samples/cannyEdgeDetectorNPP)** | **[p2pBandwidthLatencyTest](./Samples/p2pBandwidthLatencyTest)** | **[simpleVulkanMMAP](./Samples/simpleVulkanMMAP)** |
**[cudaOpenMP](./Samples/cudaOpenMP)** | **[matrixMul](./Samples/matrixMul)** |
#### Windows
**[warpAggregatedAtomicsCG](./Samples/warpAggregatedAtomicsCG)** | **[boxFilterNPP](./Samples/boxFilterNPP)** | **[binaryPartitionCG](./Samples/binaryPartitionCG)** | **[dmmaTensorCoreGemm](./Samples/dmmaTensorCoreGemm)** |
---|---|---|---|
**[conjugateGradientMultiBlockCG](./Samples/conjugateGradientMultiBlockCG)** | **[simpleIPC](./Samples/simpleIPC)** | **[memMapIPCDrv](./Samples/memMapIPCDrv)** | **[vectorAddMMAP](./Samples/vectorAddMMAP)** |
**[shfl_scan](./Samples/shfl_scan)** | **[conjugateGradientCudaGraphs](./Samples/conjugateGradientCudaGraphs)** | **[globalToShmemAsyncCopy](./Samples/globalToShmemAsyncCopy)** | **[nvJPEG](./Samples/nvJPEG)** |
**[simpleD3D12](./Samples/simpleD3D12)** | **[simpleCudaGraphs](./Samples/simpleCudaGraphs)** | **[deviceQuery](./Samples/deviceQuery)** | **[simpleVoteIntrinsics](./Samples/simpleVoteIntrinsics)** |
**[simpleCUBLASXT](./Samples/simpleCUBLASXT)** | **[simpleAttributes](./Samples/simpleAttributes)** | **[tf32TensorCoreGemm](./Samples/tf32TensorCoreGemm)** | **[UnifiedMemoryPerf](./Samples/UnifiedMemoryPerf)** |
**[cudaCompressibleMemory](./Samples/cudaCompressibleMemory)** | **[bf16TensorCoreGemm](./Samples/bf16TensorCoreGemm)** | **[cuSolverDn_LinearSolver](./Samples/cuSolverDn_LinearSolver)** | **[vulkanImageCUDA](./Samples/vulkanImageCUDA)** |
**[conjugateGradientMultiDeviceCG](./Samples/conjugateGradientMultiDeviceCG)** | **[matrixMulDrv](./Samples/matrixMulDrv)** | **[cuSolverSp_LinearSolver](./Samples/cuSolverSp_LinearSolver)** | **[simpleCUFFT](./Samples/simpleCUFFT)** |
**[reduction](./Samples/reduction)** | **[nvJPEG_encoder](./Samples/nvJPEG_encoder)** | **[simpleDrvRuntime](./Samples/simpleDrvRuntime)** | **[simpleD3D11](./Samples/simpleD3D11)** |
**[MersenneTwisterGP11213](./Samples/MersenneTwisterGP11213)** | **[simpleAWBarrier](./Samples/simpleAWBarrier)** | **[immaTensorCoreGemm](./Samples/immaTensorCoreGemm)** | **[bandwidthTest](./Samples/bandwidthTest)** |
**[concurrentKernels](./Samples/concurrentKernels)** | **[simpleCUBLAS](./Samples/simpleCUBLAS)** | **[NV12toBGRandResize](./Samples/NV12toBGRandResize)** | **[cudaTensorCoreGemm](./Samples/cudaTensorCoreGemm)** |
**[jacobiCudaGraphs](./Samples/jacobiCudaGraphs)** | **[simpleVulkan](./Samples/simpleVulkan)** | **[vectorAdd_nvrtc](./Samples/vectorAdd_nvrtc)** | **[cannyEdgeDetectorNPP](./Samples/cannyEdgeDetectorNPP)** |
**[p2pBandwidthLatencyTest](./Samples/p2pBandwidthLatencyTest)** | **[simpleVulkanMMAP](./Samples/simpleVulkanMMAP)** | **[matrixMul](./Samples/matrixMul)** |
## Dependencies ## Dependencies
@@ -184,7 +207,9 @@ These third-party dependencies are required by some CUDA samples. If available,
#### FreeImage #### FreeImage
FreeImage is an open source imaging library. FreeImage can usually be installed on Linux using your distribution's package manager system. FreeImage can also be downloaded from the [FreeImage website](http://freeimage.sourceforge.net/). FreeImage is also redistributed with the CUDA Samples. FreeImage is an open source imaging library. FreeImage can usually be installed on Linux using your distribution's package manager system. FreeImage can also be downloaded from the FreeImage website.
To set up FreeImage on a Windows system, extract the FreeImage DLL distribution into the folder `../../Common/FreeImage/Dist/x64` such that it contains the .h, .dll, and .lib files.
#### Message Passing Interface #### Message Passing Interface
@@ -239,8 +264,13 @@ EGLOutput is a set of EGL extensions which allow EGL to render directly to the d
EGLSync is a set of EGL extensions which provides sync objects that are synchronization primitive, representing events whose completion can be tested or waited upon. EGLSync is a set of EGL extensions which provides sync objects that are synchronization primitive, representing events whose completion can be tested or waited upon.
#### NVSCI #### NVSCI
NvSci is a set of communication interface libraries out of which CUDA interops with NvSciBuf and NvSciSync. NvSciBuf allows applications to allocate and exchange buffers in memory. NvSciSync allows applications to manage synchronization objects which coordinate when sequences of operations begin and end. NvSci is a set of communication interface libraries out of which CUDA interops with NvSciBuf and NvSciSync. NvSciBuf allows applications to allocate and exchange buffers in memory. NvSciSync allows applications to manage synchronization objects which coordinate when sequences of operations begin and end.
#### NvMedia
NvMedia provides powerful processing of multimedia data for true hardware acceleration across NVIDIA Tegra devices. Applications leverage the NvMedia Application Programming Interface (API) to process the image and video data.
### CUDA Features ### CUDA Features
These CUDA features are needed by some CUDA samples. They are provided by either the CUDA Toolkit or CUDA Driver. Some features may not be available on your system. These CUDA features are needed by some CUDA samples. They are provided by either the CUDA Toolkit or CUDA Driver. Some features may not be available on your system.

View File

@@ -88,7 +88,7 @@ endif
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now. # sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
ifeq ($(HOST_ARCH),aarch64) ifeq ($(HOST_ARCH),aarch64)
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux)) ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
HOST_ARCH := sbsa HOST_ARCH := sbsa
TARGET_ARCH := sbsa TARGET_ARCH := sbsa
endif endif
@@ -146,7 +146,7 @@ else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
endif endif
export QNX_HOST export QNX_HOST
export QNX_TARGET export QNX_TARGET
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.0.0-g++ HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
else ifeq ($(TARGET_OS), android) else ifeq ($(TARGET_OS), android)
HOST_COMPILER ?= aarch64-linux-android-clang++ HOST_COMPILER ?= aarch64-linux-android-clang++
endif endif
@@ -201,24 +201,34 @@ ifneq ($(TARGET_ARCH),$(HOST_ARCH))
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
endif endif
endif endif
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
NVCCFLAGS += --qpp-config 5.4.0,gcc_ntoaarch64le
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
LDFLAGS += -lsocket LDFLAGS += -lsocket
LDFLAGS += -rpath=/usr/lib/aarch64-qnx-gnu -L/usr/lib/aarch64-qnx-gnu LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
ifneq ($(TARGET_FS),) CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
LDFLAGS += -rpath=$(TARGET_FS)/usr/lib -L $(TARGET_FS)/usr/lib ifdef TARGET_OVERRIDE
LDFLAGS += -rpath=$(TARGET_FS)/usr/libnvidia -L $(TARGET_FS)/usr/libnvidia LDFLAGS += -lslog2
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE) ifneq ($(TARGET_FS),)
LDFLAGS += -L$(TARGET_FS)/usr/lib
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
CCFLAGS += -I$(TARGET_FS)/../include
endif endif
endif endif
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
endif
# Install directory of different arch # Install directory of different arch
CUDA_INSTALL_TARGET_DIR := CUDA_INSTALL_TARGET_DIR :=
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
@@ -351,6 +361,8 @@ else
endif endif
endif endif
ALL_CCFLAGS += --threads 0
ifeq ($(SAMPLE_ENABLED),0) ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]" EXEC ?= @echo "[@]"
endif endif

View File

@@ -59,6 +59,7 @@
<sm-arch>sm72</sm-arch> <sm-arch>sm72</sm-arch>
<sm-arch>sm75</sm-arch> <sm-arch>sm75</sm-arch>
<sm-arch>sm80</sm-arch> <sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<supported_envs> <supported_envs>
<env> <env>
<arch>x86_64</arch> <arch>x86_64</arch>

View File

@@ -10,7 +10,7 @@ EGLStreams Interop
## Supported SM Architectures ## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes ## Supported OSes
@@ -30,7 +30,7 @@ cuDeviceGet, cuDeviceGetAttribute, cuDeviceComputeCapability, cuDeviceGetCount,
## Prerequisites ## Prerequisites
Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed. Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run ## Build and Run

View File

@@ -88,7 +88,7 @@ endif
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now. # sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
ifeq ($(HOST_ARCH),aarch64) ifeq ($(HOST_ARCH),aarch64)
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux)) ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
HOST_ARCH := sbsa HOST_ARCH := sbsa
TARGET_ARCH := sbsa TARGET_ARCH := sbsa
endif endif
@@ -146,7 +146,7 @@ else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
endif endif
export QNX_HOST export QNX_HOST
export QNX_TARGET export QNX_TARGET
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.0.0-g++ HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
else ifeq ($(TARGET_OS), android) else ifeq ($(TARGET_OS), android)
HOST_COMPILER ?= aarch64-linux-android-clang++ HOST_COMPILER ?= aarch64-linux-android-clang++
endif endif
@@ -201,24 +201,34 @@ ifneq ($(TARGET_ARCH),$(HOST_ARCH))
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
endif endif
endif endif
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
NVCCFLAGS += --qpp-config 5.4.0,gcc_ntoaarch64le
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
LDFLAGS += -lsocket LDFLAGS += -lsocket
LDFLAGS += -rpath=/usr/lib/aarch64-qnx-gnu -L/usr/lib/aarch64-qnx-gnu LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
ifneq ($(TARGET_FS),) CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
LDFLAGS += -rpath=$(TARGET_FS)/usr/lib -L $(TARGET_FS)/usr/lib ifdef TARGET_OVERRIDE
LDFLAGS += -rpath=$(TARGET_FS)/usr/libnvidia -L $(TARGET_FS)/usr/libnvidia LDFLAGS += -lslog2
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE) ifneq ($(TARGET_FS),)
LDFLAGS += -L$(TARGET_FS)/usr/lib
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
CCFLAGS += -I$(TARGET_FS)/../include
endif endif
endif endif
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
endif
# Install directory of different arch # Install directory of different arch
CUDA_INSTALL_TARGET_DIR := CUDA_INSTALL_TARGET_DIR :=
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
@@ -283,6 +293,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif endif
endif endif
ALL_CCFLAGS += --threads 0
LIBRARIES += -lcurand_static -lculibos LIBRARIES += -lcurand_static -lculibos
################################################################################ ################################################################################

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 13.00
# Visual Studio 2013
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "MersenneTwisterGP11213", "MersenneTwisterGP11213_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "MersenneTwisterGP11213", "MersenneTwisterGP11213_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>MersenneTwisterGP11213_vs2015</RootNamespace>
<ProjectName>MersenneTwisterGP11213</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>curand.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/MersenneTwisterGP11213.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,compute_35;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="MersenneTwister.cpp" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
</ImportGroup>
</Project>

View File

@@ -38,7 +38,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -71,6 +71,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -34,7 +34,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,6 +67,7 @@
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -45,6 +45,7 @@
<sm-arch>sm72</sm-arch> <sm-arch>sm72</sm-arch>
<sm-arch>sm75</sm-arch> <sm-arch>sm75</sm-arch>
<sm-arch>sm80</sm-arch> <sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<supported_envs> <supported_envs>
<env> <env>
<arch>x86_64</arch> <arch>x86_64</arch>

View File

@@ -10,7 +10,7 @@ CURAND Library
## Supported SM Architectures ## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes ## Supported OSes
@@ -27,7 +27,7 @@ x86_64, ppc64le, armv7l
## Prerequisites ## Prerequisites
Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed. Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run ## Build and Run

View File

@@ -88,7 +88,7 @@ endif
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now. # sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
ifeq ($(HOST_ARCH),aarch64) ifeq ($(HOST_ARCH),aarch64)
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux)) ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
HOST_ARCH := sbsa HOST_ARCH := sbsa
TARGET_ARCH := sbsa TARGET_ARCH := sbsa
endif endif
@@ -146,7 +146,7 @@ else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
endif endif
export QNX_HOST export QNX_HOST
export QNX_TARGET export QNX_TARGET
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.0.0-g++ HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
else ifeq ($(TARGET_OS), android) else ifeq ($(TARGET_OS), android)
HOST_COMPILER ?= aarch64-linux-android-clang++ HOST_COMPILER ?= aarch64-linux-android-clang++
endif endif
@@ -201,24 +201,34 @@ ifneq ($(TARGET_ARCH),$(HOST_ARCH))
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
endif endif
endif endif
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
NVCCFLAGS += --qpp-config 5.4.0,gcc_ntoaarch64le
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
LDFLAGS += -lsocket LDFLAGS += -lsocket
LDFLAGS += -rpath=/usr/lib/aarch64-qnx-gnu -L/usr/lib/aarch64-qnx-gnu LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
ifneq ($(TARGET_FS),) CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
LDFLAGS += -rpath=$(TARGET_FS)/usr/lib -L $(TARGET_FS)/usr/lib ifdef TARGET_OVERRIDE
LDFLAGS += -rpath=$(TARGET_FS)/usr/libnvidia -L $(TARGET_FS)/usr/libnvidia LDFLAGS += -lslog2
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE) ifneq ($(TARGET_FS),)
LDFLAGS += -L$(TARGET_FS)/usr/lib
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
CCFLAGS += -I$(TARGET_FS)/../include
endif endif
endif endif
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
endif
# Install directory of different arch # Install directory of different arch
CUDA_INSTALL_TARGET_DIR := CUDA_INSTALL_TARGET_DIR :=
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
@@ -274,9 +284,9 @@ LIBRARIES :=
# Gencode arguments # Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64)) ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
SMS ?= 35 37 50 52 60 61 70 72 75 80 SMS ?= 35 37 50 52 60 61 70 72 75 80 86
else else
SMS ?= 35 37 50 52 60 61 70 75 80 SMS ?= 35 37 50 52 60 61 70 75 80 86
endif endif
ifeq ($(SMS),) ifeq ($(SMS),)
@@ -295,6 +305,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif endif
endif endif
ALL_CCFLAGS += --threads 0
ifeq ($(SAMPLE_ENABLED),0) ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]" EXEC ?= @echo "[@]"
endif endif

View File

@@ -1,112 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>NV12toBGRandResize_vs2012</RootNamespace>
<ProjectName>NV12toBGRandResize</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v110</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/NV12toBGRandResize.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="bgr_resize.cu" />
<CudaCompile Include="nv12_resize.cu" />
<CudaCompile Include="nv12_to_bgr_planar.cu" />
<ClCompile Include="resize_convert_main.cpp" />
<CudaCompile Include="utils.cu" />
<ClInclude Include="resize_convert.h" />
<ClInclude Include="utils.h" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
</ImportGroup>
</Project>

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 13.00
# Visual Studio 2013
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "NV12toBGRandResize", "NV12toBGRandResize_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "NV12toBGRandResize", "NV12toBGRandResize_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -38,7 +38,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,10 +67,11 @@
<OutputFile>$(OutDir)/NV12toBGRandResize.exe</OutputFile> <OutputFile>$(OutDir)/NV12toBGRandResize.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration> <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -112,6 +113,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -34,7 +34,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,10 +63,11 @@
<OutputFile>$(OutDir)/NV12toBGRandResize.exe</OutputFile> <OutputFile>$(OutDir)/NV12toBGRandResize.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration> <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -108,6 +109,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -42,6 +42,7 @@
<sm-arch>sm72</sm-arch> <sm-arch>sm72</sm-arch>
<sm-arch>sm75</sm-arch> <sm-arch>sm75</sm-arch>
<sm-arch>sm80</sm-arch> <sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<supported_envs> <supported_envs>
<env> <env>
<arch>x86_64</arch> <arch>x86_64</arch>

View File

@@ -10,7 +10,7 @@ Graphics Interop, Image Processing, Video Processing
## Supported SM Architectures ## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes ## Supported OSes
@@ -27,7 +27,7 @@ cudaMemcpy2D, cudaMallocManaged
## Prerequisites ## Prerequisites
Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run ## Build and Run

View File

@@ -88,7 +88,7 @@ endif
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now. # sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
ifeq ($(HOST_ARCH),aarch64) ifeq ($(HOST_ARCH),aarch64)
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux)) ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
HOST_ARCH := sbsa HOST_ARCH := sbsa
TARGET_ARCH := sbsa TARGET_ARCH := sbsa
endif endif
@@ -146,7 +146,7 @@ else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
endif endif
export QNX_HOST export QNX_HOST
export QNX_TARGET export QNX_TARGET
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.0.0-g++ HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
else ifeq ($(TARGET_OS), android) else ifeq ($(TARGET_OS), android)
HOST_COMPILER ?= aarch64-linux-android-clang++ HOST_COMPILER ?= aarch64-linux-android-clang++
endif endif
@@ -201,24 +201,34 @@ ifneq ($(TARGET_ARCH),$(HOST_ARCH))
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
endif endif
endif endif
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
NVCCFLAGS += --qpp-config 5.4.0,gcc_ntoaarch64le
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
LDFLAGS += -lsocket LDFLAGS += -lsocket
LDFLAGS += -rpath=/usr/lib/aarch64-qnx-gnu -L/usr/lib/aarch64-qnx-gnu LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
ifneq ($(TARGET_FS),) CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
LDFLAGS += -rpath=$(TARGET_FS)/usr/lib -L $(TARGET_FS)/usr/lib ifdef TARGET_OVERRIDE
LDFLAGS += -rpath=$(TARGET_FS)/usr/libnvidia -L $(TARGET_FS)/usr/libnvidia LDFLAGS += -lslog2
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE) ifneq ($(TARGET_FS),)
LDFLAGS += -L$(TARGET_FS)/usr/lib
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
CCFLAGS += -I$(TARGET_FS)/../include
endif endif
endif endif
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
endif
# Install directory of different arch # Install directory of different arch
CUDA_INSTALL_TARGET_DIR := CUDA_INSTALL_TARGET_DIR :=
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
@@ -274,9 +284,9 @@ LIBRARIES :=
# Gencode arguments # Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64)) ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
SMS ?= 35 37 50 52 60 61 70 72 75 80 SMS ?= 35 37 50 52 60 61 70 72 75 80 86
else else
SMS ?= 35 37 50 52 60 61 70 75 80 SMS ?= 35 37 50 52 60 61 70 75 80 86
endif endif
ifeq ($(SMS),) ifeq ($(SMS),)
@@ -295,6 +305,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif endif
endif endif
ALL_CCFLAGS += --threads 0
ifeq ($(SAMPLE_ENABLED),0) ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]" EXEC ?= @echo "[@]"
endif endif

View File

@@ -28,7 +28,7 @@ cudaMallocManaged, cudaStreamAttachMemAsync, cudaMemcpyAsync, cudaMallocHost, cu
## Prerequisites ## Prerequisites
Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed. Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run ## Build and Run

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 13.00
# Visual Studio 2013
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "UnifiedMemoryPerf", "UnifiedMemoryPerf_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "UnifiedMemoryPerf", "UnifiedMemoryPerf_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -1,110 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>UnifiedMemoryPerf_vs2015</RootNamespace>
<ProjectName>UnifiedMemoryPerf</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="commonKernels.cu" />
<ClCompile Include="helperFunctions.cpp" />
<CudaCompile Include="matrixMultiplyPerf.cu" />
<ClInclude Include="commonDefs.hpp" />
<ClInclude Include="commonKernels.hpp" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
</ImportGroup>
</Project>

View File

@@ -38,7 +38,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,10 +67,11 @@
<OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile> <OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration> <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -110,6 +111,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -34,7 +34,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,10 +63,11 @@
<OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile> <OutputFile>$(OutDir)/UnifiedMemoryPerf.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration> <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -106,6 +107,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -33,7 +33,7 @@
#define VERIFY_GPU_CORRECTNESS 0 #define VERIFY_GPU_CORRECTNESS 0
size_t maxSampleSizeInMb = 64; size_t maxSampleSizeInMb = 64;
int numKernelRuns = 100; int numKernelRuns = 20;
int verboseResults = 0; int verboseResults = 0;
const char *memAllocTypeStr[MEMALLOC_TYPE_COUNT] = { const char *memAllocTypeStr[MEMALLOC_TYPE_COUNT] = {

View File

@@ -88,7 +88,7 @@ endif
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now. # sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
ifeq ($(HOST_ARCH),aarch64) ifeq ($(HOST_ARCH),aarch64)
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux)) ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
HOST_ARCH := sbsa HOST_ARCH := sbsa
TARGET_ARCH := sbsa TARGET_ARCH := sbsa
endif endif
@@ -146,7 +146,7 @@ else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
endif endif
export QNX_HOST export QNX_HOST
export QNX_TARGET export QNX_TARGET
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.0.0-g++ HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
else ifeq ($(TARGET_OS), android) else ifeq ($(TARGET_OS), android)
HOST_COMPILER ?= aarch64-linux-android-clang++ HOST_COMPILER ?= aarch64-linux-android-clang++
endif endif
@@ -201,24 +201,34 @@ ifneq ($(TARGET_ARCH),$(HOST_ARCH))
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
endif endif
endif endif
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
NVCCFLAGS += --qpp-config 5.4.0,gcc_ntoaarch64le
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
LDFLAGS += -lsocket LDFLAGS += -lsocket
LDFLAGS += -rpath=/usr/lib/aarch64-qnx-gnu -L/usr/lib/aarch64-qnx-gnu LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
ifneq ($(TARGET_FS),) CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
LDFLAGS += -rpath=$(TARGET_FS)/usr/lib -L $(TARGET_FS)/usr/lib ifdef TARGET_OVERRIDE
LDFLAGS += -rpath=$(TARGET_FS)/usr/libnvidia -L $(TARGET_FS)/usr/libnvidia LDFLAGS += -lslog2
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE) ifneq ($(TARGET_FS),)
LDFLAGS += -L$(TARGET_FS)/usr/lib
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
CCFLAGS += -I$(TARGET_FS)/../include
endif endif
endif endif
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
endif
# Install directory of different arch # Install directory of different arch
CUDA_INSTALL_TARGET_DIR := CUDA_INSTALL_TARGET_DIR :=
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
@@ -268,9 +278,9 @@ LIBRARIES :=
# Gencode arguments # Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64)) ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
SMS ?= 35 37 50 52 60 61 70 72 75 80 SMS ?= 35 37 50 52 60 61 70 72 75 80 86
else else
SMS ?= 35 37 50 52 60 61 70 75 80 SMS ?= 35 37 50 52 60 61 70 75 80 86
endif endif
ifeq ($(SMS),) ifeq ($(SMS),)
@@ -289,6 +299,8 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif endif
endif endif
ALL_CCFLAGS += --threads 0
ifeq ($(SAMPLE_ENABLED),0) ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]" EXEC ?= @echo "[@]"
endif endif

View File

@@ -51,6 +51,7 @@
<sm-arch>sm72</sm-arch> <sm-arch>sm72</sm-arch>
<sm-arch>sm75</sm-arch> <sm-arch>sm75</sm-arch>
<sm-arch>sm80</sm-arch> <sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<supported_envs> <supported_envs>
<env> <env>
<arch>x86_64</arch> <arch>x86_64</arch>

View File

@@ -10,7 +10,7 @@ CUDA Streams and Events, Performance Strategies
## Supported SM Architectures ## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes ## Supported OSes
@@ -27,7 +27,7 @@ cudaSetDevice, cudaHostAlloc, cudaFree, cudaMallocHost, cudaFreeHost, cudaMemcpy
## Prerequisites ## Prerequisites
Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run ## Build and Run

View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>bandwidthTest_vs2012</RootNamespace>
<ProjectName>bandwidthTest</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v110</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/bandwidthTest.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="bandwidthTest.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
</ImportGroup>
</Project>

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 13.00
# Visual Studio 2013
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "bandwidthTest", "bandwidthTest_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "bandwidthTest", "bandwidthTest_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -38,7 +38,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,10 +67,11 @@
<OutputFile>$(OutDir)/bandwidthTest.exe</OutputFile> <OutputFile>$(OutDir)/bandwidthTest.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration> <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -34,7 +34,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,10 +63,11 @@
<OutputFile>$(OutDir)/bandwidthTest.exe</OutputFile> <OutputFile>$(OutDir)/bandwidthTest.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration> <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -0,0 +1,341 @@
################################################################################
# Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
# * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
# * Neither the name of NVIDIA CORPORATION nor the names of its
# contributors may be used to endorse or promote products derived
# from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#
################################################################################
#
# Makefile project only supported on Mac OS X and Linux Platforms)
#
################################################################################
# Location of the CUDA Toolkit
CUDA_PATH ?= /usr/local/cuda
##############################
# start deprecated interface #
##############################
ifeq ($(x86_64),1)
$(info WARNING - x86_64 variable has been deprecated)
$(info WARNING - please use TARGET_ARCH=x86_64 instead)
TARGET_ARCH ?= x86_64
endif
ifeq ($(ARMv7),1)
$(info WARNING - ARMv7 variable has been deprecated)
$(info WARNING - please use TARGET_ARCH=armv7l instead)
TARGET_ARCH ?= armv7l
endif
ifeq ($(aarch64),1)
$(info WARNING - aarch64 variable has been deprecated)
$(info WARNING - please use TARGET_ARCH=aarch64 instead)
TARGET_ARCH ?= aarch64
endif
ifeq ($(ppc64le),1)
$(info WARNING - ppc64le variable has been deprecated)
$(info WARNING - please use TARGET_ARCH=ppc64le instead)
TARGET_ARCH ?= ppc64le
endif
ifneq ($(GCC),)
$(info WARNING - GCC variable has been deprecated)
$(info WARNING - please use HOST_COMPILER=$(GCC) instead)
HOST_COMPILER ?= $(GCC)
endif
ifneq ($(abi),)
$(error ERROR - abi variable has been removed)
endif
############################
# end deprecated interface #
############################
# architecture
HOST_ARCH := $(shell uname -m)
TARGET_ARCH ?= $(HOST_ARCH)
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le armv7l))
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le))
TARGET_SIZE := 64
else ifneq (,$(filter $(TARGET_ARCH),armv7l))
TARGET_SIZE := 32
endif
else
TARGET_SIZE := $(shell getconf LONG_BIT)
endif
else
$(error ERROR - unsupported value $(TARGET_ARCH) for TARGET_ARCH!)
endif
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
ifeq ($(HOST_ARCH),aarch64)
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
HOST_ARCH := sbsa
TARGET_ARCH := sbsa
endif
endif
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
ifeq (,$(filter $(HOST_ARCH)-$(TARGET_ARCH),aarch64-armv7l x86_64-armv7l x86_64-aarch64 x86_64-sbsa x86_64-ppc64le))
$(error ERROR - cross compiling from $(HOST_ARCH) to $(TARGET_ARCH) is not supported!)
endif
endif
# When on native aarch64 system with userspace of 32-bit, change TARGET_ARCH to armv7l
ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_SIZE),aarch64-aarch64-32)
TARGET_ARCH = armv7l
endif
# operating system
HOST_OS := $(shell uname -s 2>/dev/null | tr "[:upper:]" "[:lower:]")
TARGET_OS ?= $(HOST_OS)
ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
$(error ERROR - unsupported value $(TARGET_OS) for TARGET_OS!)
endif
# host compiler
ifeq ($(TARGET_OS),darwin)
ifeq ($(shell expr `xcodebuild -version | grep -i xcode | awk '{print $$2}' | cut -d'.' -f1` \>= 5),1)
HOST_COMPILER ?= clang++
endif
else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l)
ifeq ($(TARGET_OS),linux)
HOST_COMPILER ?= arm-linux-gnueabihf-g++
else ifeq ($(TARGET_OS),qnx)
ifeq ($(QNX_HOST),)
$(error ERROR - QNX_HOST must be passed to the QNX host toolchain)
endif
ifeq ($(QNX_TARGET),)
$(error ERROR - QNX_TARGET must be passed to the QNX target toolchain)
endif
export QNX_HOST
export QNX_TARGET
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/arm-unknown-nto-qnx6.6.0eabi-g++
else ifeq ($(TARGET_OS),android)
HOST_COMPILER ?= arm-linux-androideabi-g++
endif
else ifeq ($(TARGET_ARCH),aarch64)
ifeq ($(TARGET_OS), linux)
HOST_COMPILER ?= aarch64-linux-gnu-g++
else ifeq ($(TARGET_OS),qnx)
ifeq ($(QNX_HOST),)
$(error ERROR - QNX_HOST must be passed to the QNX host toolchain)
endif
ifeq ($(QNX_TARGET),)
$(error ERROR - QNX_TARGET must be passed to the QNX target toolchain)
endif
export QNX_HOST
export QNX_TARGET
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
else ifeq ($(TARGET_OS), android)
HOST_COMPILER ?= aarch64-linux-android-clang++
endif
else ifeq ($(TARGET_ARCH),sbsa)
HOST_COMPILER ?= aarch64-linux-gnu-g++
else ifeq ($(TARGET_ARCH),ppc64le)
HOST_COMPILER ?= powerpc64le-linux-gnu-g++
endif
endif
HOST_COMPILER ?= g++
NVCC := $(CUDA_PATH)/bin/nvcc -ccbin $(HOST_COMPILER)
# internal flags
NVCCFLAGS := -m${TARGET_SIZE}
CCFLAGS :=
LDFLAGS :=
# build flags
ifeq ($(TARGET_OS),darwin)
LDFLAGS += -rpath $(CUDA_PATH)/lib
CCFLAGS += -arch $(HOST_ARCH)
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-armv7l-linux)
LDFLAGS += --dynamic-linker=/lib/ld-linux-armhf.so.3
CCFLAGS += -mfloat-abi=hard
else ifeq ($(TARGET_OS),android)
LDFLAGS += -pie
CCFLAGS += -fpie -fpic -fexceptions
endif
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
ifneq ($(TARGET_FS),)
GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
ifeq ($(GCCVERSIONLTEQ46),1)
CCFLAGS += --sysroot=$(TARGET_FS)
endif
LDFLAGS += --sysroot=$(TARGET_FS)
LDFLAGS += -rpath-link=$(TARGET_FS)/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/arm-linux-gnueabihf
endif
endif
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
ifneq ($(TARGET_FS),)
GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
ifeq ($(GCCVERSIONLTEQ46),1)
CCFLAGS += --sysroot=$(TARGET_FS)
endif
LDFLAGS += --sysroot=$(TARGET_FS)
LDFLAGS += -rpath-link=$(TARGET_FS)/lib -L$(TARGET_FS)/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/lib/aarch64-linux-gnu -L$(TARGET_FS)/lib/aarch64-linux-gnu
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
endif
endif
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
NVCCFLAGS += --qpp-config 5.4.0,gcc_ntoaarch64le
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
LDFLAGS += -lsocket
LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
ifdef TARGET_OVERRIDE
LDFLAGS += -lslog2
endif
ifneq ($(TARGET_FS),)
LDFLAGS += -L$(TARGET_FS)/usr/lib
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
CCFLAGS += -I$(TARGET_FS)/../include
endif
endif
endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
endif
# Install directory of different arch
CUDA_INSTALL_TARGET_DIR :=
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-gnueabihf/
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux/
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),sbsa-linux)
CUDA_INSTALL_TARGET_DIR = targets/sbsa-linux/
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-android)
CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-androideabi/
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-android)
CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux-androideabi/
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-qnx)
CUDA_INSTALL_TARGET_DIR = targets/ARMv7-linux-QNX/
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
CUDA_INSTALL_TARGET_DIR = targets/aarch64-qnx/
else ifeq ($(TARGET_ARCH),ppc64le)
CUDA_INSTALL_TARGET_DIR = targets/ppc64le-linux/
endif
# Debug build flags
ifeq ($(dbg),1)
NVCCFLAGS += -g -G
BUILD_TYPE := debug
else
BUILD_TYPE := release
endif
ALL_CCFLAGS :=
ALL_CCFLAGS += $(NVCCFLAGS)
ALL_CCFLAGS += $(EXTRA_NVCCFLAGS)
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS))
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS))
SAMPLE_ENABLED := 1
# This sample is not supported on Mac OSX
ifeq ($(TARGET_OS),darwin)
$(info >>> WARNING - batchedLabelMarkersAndLabelCompressionNPP is not supported on Mac OSX - waiving sample <<<)
SAMPLE_ENABLED := 0
endif
ALL_LDFLAGS :=
ALL_LDFLAGS += $(ALL_CCFLAGS)
ALL_LDFLAGS += $(addprefix -Xlinker ,$(LDFLAGS))
ALL_LDFLAGS += $(addprefix -Xlinker ,$(EXTRA_LDFLAGS))
# Common includes and paths for CUDA
INCLUDES := -I../../Common
LIBRARIES :=
################################################################################
# Gencode arguments
SMS ?=
ifeq ($(GENCODE_FLAGS),)
# Generate SASS code for each SM architecture listed in $(SMS)
$(foreach sm,$(SMS),$(eval GENCODE_FLAGS += -gencode arch=compute_$(sm),code=sm_$(sm)))
ifeq ($(SMS),)
# Generate PTX code from SM 35
GENCODE_FLAGS += -gencode arch=compute_35,code=compute_35
endif
# Generate PTX code from the highest SM architecture in $(SMS) to guarantee forward-compatibility
HIGHEST_SM := $(lastword $(sort $(SMS)))
ifneq ($(HIGHEST_SM),)
GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif
endif
ALL_CCFLAGS += --threads 0
LIBRARIES += -lnppisu_static -lnppif_static -lnppc_static -lculibos
ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]"
endif
################################################################################
# Target rules
all: build
build: batchedLabelMarkersAndLabelCompressionNPP
check.deps:
ifeq ($(SAMPLE_ENABLED),0)
@echo "Sample will be waived due to the above missing dependencies"
else
@echo "Sample is ready - all dependencies have been met"
endif
batchedLabelMarkersAndLabelCompressionNPP.o:batchedLabelMarkersAndLabelCompressionNPP.cpp
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
batchedLabelMarkersAndLabelCompressionNPP: batchedLabelMarkersAndLabelCompressionNPP.o
$(EXEC) $(NVCC) $(ALL_LDFLAGS) $(GENCODE_FLAGS) -o $@ $+ $(LIBRARIES)
$(EXEC) mkdir -p ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
$(EXEC) cp $@ ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
run: build
$(EXEC) ./batchedLabelMarkersAndLabelCompressionNPP
clean:
rm -f batchedLabelMarkersAndLabelCompressionNPP batchedLabelMarkersAndLabelCompressionNPP.o
rm -rf ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/batchedLabelMarkersAndLabelCompressionNPP
clobber: clean

View File

@@ -0,0 +1,76 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
<entry>
<name>batchedLabelMarkersAndLabelCompressionNPP</name>
<description><![CDATA[An NPP CUDA Sample that demonstrates how to use the NPP label markers generation and label compression functions based on a Union Find (UF) algorithm including both
single image and batched image versions.]]></description>
<devicecompilation>whole</devicecompilation>
<fallback_min_ptx>true</fallback_min_ptx>
<includepaths>
<path>./</path>
<path>../</path>
<path>../../common/inc</path>
</includepaths>
<keyconcepts>
<concept level="basic">Performance Strategies</concept>
<concept level="basic">Image Processing</concept>
<concept level="basic">NPP Library</concept>
<concept level="basic">Using NPP Batch Functions</concept>
</keyconcepts>
<keywords>
<keyword>CUDA</keyword>
<keyword>NPP</keyword>
<keyword>Image Processing</keyword>
</keywords>
<libraries>
<library>nppisu_static</library>
<library>nppif_static</library>
<library>nppc_static</library>
<library>culibos</library>
</libraries>
<librarypaths>
</librarypaths>
<nsight_eclipse>true</nsight_eclipse>
<primary_file>batchedLabelMarkersAndLabelCompressionNPP.cpp</primary_file>
<required_dependencies>
<dependency>NPP</dependency>
</required_dependencies>
<scopes>
<scope>1:CUDA Basic Topics</scope>
<scope>1:Performance Strategies</scope>
<scope>2:Image Processing</scope>
<scope>2:Computer Vision</scope>
</scopes>
<sm-arch>sm35</sm-arch>
<sm-arch>sm37</sm-arch>
<sm-arch>sm50</sm-arch>
<sm-arch>sm52</sm-arch>
<sm-arch>sm60</sm-arch>
<sm-arch>sm61</sm-arch>
<sm-arch>sm70</sm-arch>
<sm-arch>sm72</sm-arch>
<sm-arch>sm75</sm-arch>
<sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<supported_envs>
<env>
<arch>x86_64</arch>
<platform>linux</platform>
</env>
<env>
<platform>windows7</platform>
</env>
<env>
<arch>arm</arch>
</env>
<env>
<arch>ppc64le</arch>
<platform>linux</platform>
</env>
</supported_envs>
<supported_sm_architectures>
<include>all</include>
</supported_sm_architectures>
<title>Batched Label Markers And Label Compression NPP</title>
<type>exe</type>
</entry>

View File

@@ -0,0 +1,72 @@
# batchedLabelMarkersAndLabelCompressionNPP - Batched Label Markers And Label Compression NPP
## Description
An NPP CUDA Sample that demonstrates how to use the NPP label markers generation and label compression functions based on a Union Find (UF) algorithm including both
single image and batched image versions.
## Key Concepts
Performance Strategies, Image Processing, NPP Library, Using NPP Batch Functions
## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes
Linux, Windows
## Supported CPU Architecture
x86_64, ppc64le, armv7l
## CUDA APIs involved
## Dependencies needed to build/run
[NPP](../../README.md#npp)
## Prerequisites
Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run
### Windows
The Windows samples are built using the Visual Studio IDE. Solution files (.sln) are provided for each supported version of Visual Studio, using the format:
```
*_vs<version>.sln - for Visual Studio <version>
```
Each individual sample has its own set of solution files in its directory:
To build/examine all the samples at once, the complete solution files should be used. To build/examine a single sample, the individual sample solution files should be used.
> **Note:** Some samples require that the Microsoft DirectX SDK (June 2010 or newer) be installed and that the VC++ directory paths are properly set up (**Tools > Options...**). Check DirectX Dependencies section for details."
### Linux
The Linux samples are built using makefiles. To use the makefiles, change the current directory to the sample directory you wish to build, and run make:
```
$ cd <sample_dir>
$ make
```
The samples makefiles can take advantage of certain options:
* **TARGET_ARCH=<arch>** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le, armv7l.
By default, TARGET_ARCH is set to HOST_ARCH. On a x86_64 machine, not setting TARGET_ARCH is the equivalent of setting TARGET_ARCH=x86_64.<br/>
`$ make TARGET_ARCH=x86_64` <br/> `$ make TARGET_ARCH=ppc64le` <br/> `$ make TARGET_ARCH=armv7l` <br/>
See [here](http://docs.nvidia.com/cuda/cuda-samples/index.html#cross-samples) for more details.
* **dbg=1** - build with debug symbols
```
$ make dbg=1
```
* **SMS="A B ..."** - override the SM architectures for which the sample will be built, where `"A B ..."` is a space-delimited list of SM architectures. For example, to generate SASS for SM 50 and SM 60, use `SMS="50 60"`.
```
$ make SMS="50 60"
```
* **HOST_COMPILER=<host_compiler>** - override the default g++ host compiler. See the [Linux Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#system-requirements) for a list of supported host compilers.
```
$ make HOST_COMPILER=g++
```
## References (for more details)

View File

@@ -0,0 +1,798 @@
/* Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of NVIDIA CORPORATION nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
* OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
#define WINDOWS_LEAN_AND_MEAN
#define NOMINMAX
#include <windows.h>
#pragma warning(disable : 4819)
#endif
#include <stdio.h>
#include <string.h>
#include <fstream>
#include <helper_cuda.h>
#include <npp.h>
// Note: If you want to view these images we HIGHLY recommend using imagej
// which is free on the internet and works on most platforms
// because it is one of the few image viewing apps that can display 32
// bit integer image data. While it normalizes the data to floating
// point values for viewing it still provides a good representation of
// the relative brightness of each label value. Note that label
// compression output results in smaller differences between label values
// making it visually more difficult to detect differences in labeled
// regions. If you have an editor that can display hex values you can
// see what the exact values of each label is, every 4 bytes represents 1
// 32 bit integer label value.
//
// The files read and written by this sample app use RAW image format,
// that is, only the image data itself exists in the files with no image
// format information. When viewing RAW files with imagej just enter
// the image size and bit depth values that are part of the file name
// when requested by imagej.
//
// This sample app works in 2 stages, first it processes all of the
// images individually then it processes them all again in 1 batch using
// the Batch_Advanced versions of the NPP batch functions which allow
// each image to have it's own ROI. The 2 stages are completely
// separable but in this sample the second stage takes advantage of some
// of the data that has already been initialized.
//
// Note that there is a small amount of variability in the number of
// unique label markers generated from one run to the next by the UF
// algorithm.
//
// Performance of ALL NPP image batch functions is limited by the maximum
// ROI height in the list of images.
// Batched label compression support is only available on NPP versions > 11.0,
// comment out if using NPP 11.0
#define USE_BATCHED_LABEL_COMPRESSION 1
#define NUMBER_OF_IMAGES 5
Npp8u *pInputImageDev[NUMBER_OF_IMAGES];
Npp8u *pInputImageHost[NUMBER_OF_IMAGES];
Npp8u *pUFGenerateLabelsScratchBufferDev[NUMBER_OF_IMAGES];
Npp8u *pUFCompressedLabelsScratchBufferDev[NUMBER_OF_IMAGES];
Npp32u *pUFLabelDev[NUMBER_OF_IMAGES];
Npp32u *pUFLabelHost[NUMBER_OF_IMAGES];
NppiImageDescriptor *pUFBatchSrcImageListDev = 0;
NppiImageDescriptor *pUFBatchSrcDstImageListDev = 0;
NppiImageDescriptor *pUFBatchSrcImageListHost = 0;
NppiImageDescriptor *pUFBatchSrcDstImageListHost = 0;
NppiBufferDescriptor *pUFBatchSrcDstScratchBufferListDev =
0; // from nppi_filtering_functions.h
NppiBufferDescriptor *pUFBatchSrcDstScratchBufferListHost = 0;
Npp32u *pUFBatchPerImageCompressedCountListDev = 0;
Npp32u *pUFBatchPerImageCompressedCountListHost = 0;
void tearDown() // Clean up and tear down
{
if (pUFBatchPerImageCompressedCountListDev != 0)
cudaFree(pUFBatchPerImageCompressedCountListDev);
if (pUFBatchSrcDstScratchBufferListDev != 0)
cudaFree(pUFBatchSrcDstScratchBufferListDev);
if (pUFBatchSrcDstImageListDev != 0) cudaFree(pUFBatchSrcDstImageListDev);
if (pUFBatchSrcImageListDev != 0) cudaFree(pUFBatchSrcImageListDev);
if (pUFBatchPerImageCompressedCountListHost != 0)
free(pUFBatchPerImageCompressedCountListHost);
if (pUFBatchSrcDstScratchBufferListHost != 0)
free(pUFBatchSrcDstScratchBufferListHost);
if (pUFBatchSrcDstImageListHost != 0) free(pUFBatchSrcDstImageListHost);
if (pUFBatchSrcImageListHost != 0) free(pUFBatchSrcImageListHost);
for (int j = 0; j < NUMBER_OF_IMAGES; j++) {
if (pUFCompressedLabelsScratchBufferDev[j] != 0)
cudaFree(pUFCompressedLabelsScratchBufferDev[j]);
if (pUFGenerateLabelsScratchBufferDev[j] != 0)
cudaFree(pUFGenerateLabelsScratchBufferDev[j]);
if (pUFLabelDev[j] != 0) cudaFree(pUFLabelDev[j]);
if (pInputImageDev[j] != 0) cudaFree(pInputImageDev[j]);
if (pUFLabelHost[j] != 0) free(pUFLabelHost[j]);
if (pInputImageHost[j] != 0) free(pInputImageHost[j]);
}
}
const std::string &LabelMarkersOutputFile0 =
"Lena_LabelMarkersUF_8Way_512x512_32u.raw";
const std::string &LabelMarkersOutputFile1 =
"CT_skull_LabelMarkersUF_8Way_512x512_32u.raw";
const std::string &LabelMarkersOutputFile2 =
"PCB_METAL_LabelMarkersUF_8Way_509x335_32u.raw";
const std::string &LabelMarkersOutputFile3 =
"PCB2_LabelMarkersUF_8Way_1024x683_32u.raw";
const std::string &LabelMarkersOutputFile4 =
"PCB_LabelMarkersUF_8Way_1280x720_32u.raw";
const std::string &CompressedMarkerLabelsOutputFile0 =
"Lena_CompressedMarkerLabelsUF_8Way_512x512_32u.raw";
const std::string &CompressedMarkerLabelsOutputFile1 =
"CT_skull_CompressedMarkerLabelsUF_8Way_512x512_32u.raw";
const std::string &CompressedMarkerLabelsOutputFile2 =
"PCB_METAL_CompressedMarkerLabelsUF_8Way_509x335_32u.raw";
const std::string &CompressedMarkerLabelsOutputFile3 =
"PCB2_CompressedMarkerLabelsUF_8Way_1024x683_32u.raw";
const std::string &CompressedMarkerLabelsOutputFile4 =
"PCB_CompressedMarkerLabelsUF_8Way_1280x720_32u.raw";
const std::string &LabelMarkersBatchOutputFile0 =
"Lena_LabelMarkersUFBatch_8Way_512x512_32u.raw";
const std::string &LabelMarkersBatchOutputFile1 =
"CT_skull_LabelMarkersUFBatch_8Way_512x512_32u.raw";
const std::string &LabelMarkersBatchOutputFile2 =
"PCB_METAL_LabelMarkersUFBatch_8Way_509x335_32u.raw";
const std::string &LabelMarkersBatchOutputFile3 =
"PCB2_LabelMarkersUFBatch_8Way_1024x683_32u.raw";
const std::string &LabelMarkersBatchOutputFile4 =
"PCB_LabelMarkersUFBatch_8Way_1280x720_32u.raw";
const std::string &CompressedMarkerLabelsBatchOutputFile0 =
"Lena_CompressedMarkerLabelsUFBatch_8Way_512x512_32u.raw";
const std::string &CompressedMarkerLabelsBatchOutputFile1 =
"CT_skull_CompressedMarkerLabelsUFBatch_8Way_512x512_32u.raw";
const std::string &CompressedMarkerLabelsBatchOutputFile2 =
"PCB_METAL_CompressedMarkerLabelsUFBatch_8Way_509x335_32u.raw";
const std::string &CompressedMarkerLabelsBatchOutputFile3 =
"PCB2_CompressedMarkerLabelsUFBatch_8Way_1024x683_32u.raw";
const std::string &CompressedMarkerLabelsBatchOutputFile4 =
"PCB_CompressedMarkerLabelsUFBatch_8Way_1280x720_32u.raw";
int loadRaw8BitImage(Npp8u *pImage, int nWidth, int nHeight, int nImage) {
FILE *bmpFile;
size_t nSize;
if (nImage == 0) {
if (nWidth != 512 || nHeight != 512) return -1;
const char *fileName = "lena_512x512_8u.raw";
const char *InputFile = sdkFindFilePath(fileName, ".");
if (InputFile == NULL) {
printf("%s file not found.. exiting\n", fileName);
exit(EXIT_WAIVED);
}
bmpFile = fopen(InputFile, "rb");
} else if (nImage == 1) {
if (nWidth != 512 || nHeight != 512) return -1;
const char *fileName = "CT_skull_512x512_8u.raw";
const char *InputFile = sdkFindFilePath(fileName, ".");
if (InputFile == NULL) {
printf("%s file not found.. exiting\n", fileName);
exit(EXIT_WAIVED);
}
bmpFile = fopen(InputFile, "rb");
} else if (nImage == 2) {
if (nWidth != 509 || nHeight != 335) return -1;
const char *fileName = "PCB_METAL_509x335_8u.raw";
const char *InputFile = sdkFindFilePath(fileName, ".");
if (InputFile == NULL) {
printf("%s file not found.. exiting\n", fileName);
exit(EXIT_WAIVED);
}
bmpFile = fopen(InputFile, "rb");
} else if (nImage == 3) {
if (nWidth != 1024 || nHeight != 683) return -1;
const char *fileName = "PCB2_1024x683_8u.raw";
const char *InputFile = sdkFindFilePath(fileName, ".");
if (InputFile == NULL) {
printf("%s file not found.. exiting\n", fileName);
exit(EXIT_WAIVED);
}
bmpFile = fopen(InputFile, "rb");
} else if (nImage == 4) {
if (nWidth != 1280 || nHeight != 720) return -1;
const char *fileName = "PCB_1280x720_8u.raw";
const char *InputFile = sdkFindFilePath(fileName, ".");
if (InputFile == NULL) {
printf("%s file not found.. exiting\n", fileName);
exit(EXIT_WAIVED);
}
bmpFile = fopen(InputFile, "rb");
} else {
printf("Input file load failed.\n");
return -1;
}
if (bmpFile == NULL) return -1;
nSize = fread(pImage, 1, nWidth * nHeight, bmpFile);
if (nSize < nWidth * nHeight) {
fclose(bmpFile);
return -1;
}
fclose(bmpFile);
printf("Input file load succeeded.\n");
return 0;
}
int main(int argc, char **argv) {
int aGenerateLabelsScratchBufferSize[NUMBER_OF_IMAGES];
int aCompressLabelsScratchBufferSize[NUMBER_OF_IMAGES];
int nCompressedLabelCount = 0;
cudaError_t cudaError;
NppStatus nppStatus;
NppStreamContext nppStreamCtx;
FILE *bmpFile;
for (int j = 0; j < NUMBER_OF_IMAGES; j++) {
pInputImageDev[j] = 0;
pInputImageHost[j] = 0;
pUFGenerateLabelsScratchBufferDev[j] = 0;
pUFCompressedLabelsScratchBufferDev[j] = 0;
pUFLabelDev[j] = 0;
pUFLabelHost[j] = 0;
}
nppStreamCtx.hStream = 0; // The NULL stream by default, set this to whatever
// your stream ID is if not the NULL stream.
cudaError = cudaGetDevice(&nppStreamCtx.nCudaDeviceId);
if (cudaError != cudaSuccess) {
printf("CUDA error: no devices supporting CUDA.\n");
return NPP_NOT_SUFFICIENT_COMPUTE_CAPABILITY;
}
const NppLibraryVersion *libVer = nppGetLibVersion();
printf("NPP Library Version %d.%d.%d\n", libVer->major, libVer->minor,
libVer->build);
int driverVersion, runtimeVersion;
cudaDriverGetVersion(&driverVersion);
cudaRuntimeGetVersion(&runtimeVersion);
printf("CUDA Driver Version: %d.%d\n", driverVersion / 1000,
(driverVersion % 100) / 10);
printf("CUDA Runtime Version: %d.%d\n\n", runtimeVersion / 1000,
(runtimeVersion % 100) / 10);
cudaError = cudaDeviceGetAttribute(
&nppStreamCtx.nCudaDevAttrComputeCapabilityMajor,
cudaDevAttrComputeCapabilityMajor, nppStreamCtx.nCudaDeviceId);
if (cudaError != cudaSuccess) return NPP_NOT_SUFFICIENT_COMPUTE_CAPABILITY;
cudaError = cudaDeviceGetAttribute(
&nppStreamCtx.nCudaDevAttrComputeCapabilityMinor,
cudaDevAttrComputeCapabilityMinor, nppStreamCtx.nCudaDeviceId);
if (cudaError != cudaSuccess) return NPP_NOT_SUFFICIENT_COMPUTE_CAPABILITY;
cudaError =
cudaStreamGetFlags(nppStreamCtx.hStream, &nppStreamCtx.nStreamFlags);
cudaDeviceProp oDeviceProperties;
cudaError =
cudaGetDeviceProperties(&oDeviceProperties, nppStreamCtx.nCudaDeviceId);
nppStreamCtx.nMultiProcessorCount = oDeviceProperties.multiProcessorCount;
nppStreamCtx.nMaxThreadsPerMultiProcessor =
oDeviceProperties.maxThreadsPerMultiProcessor;
nppStreamCtx.nMaxThreadsPerBlock = oDeviceProperties.maxThreadsPerBlock;
nppStreamCtx.nSharedMemPerBlock = oDeviceProperties.sharedMemPerBlock;
NppiSize oSizeROI[NUMBER_OF_IMAGES];
for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
if (nImage == 0) {
oSizeROI[nImage].width = 512;
oSizeROI[nImage].height = 512;
} else if (nImage == 1) {
oSizeROI[nImage].width = 512;
oSizeROI[nImage].height = 512;
} else if (nImage == 2) {
oSizeROI[nImage].width = 509;
oSizeROI[nImage].height = 335;
} else if (nImage == 3) {
oSizeROI[nImage].width = 1024;
oSizeROI[nImage].height = 683;
} else if (nImage == 4) {
oSizeROI[nImage].width = 1280;
oSizeROI[nImage].height = 720;
}
// NOTE: While using cudaMallocPitch() to allocate device memory for NPP can
// significantly improve the performance of many NPP functions, for UF
// function label markers generation or compression DO NOT USE
// cudaMallocPitch(). Doing so could result in incorrect output.
cudaError = cudaMalloc(
(void **)&pInputImageDev[nImage],
oSizeROI[nImage].width * sizeof(Npp8u) * oSizeROI[nImage].height);
if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
// For images processed with UF label markers functions ROI width and height
// for label markers generation output AND marker compression functions MUST
// be the same AND line pitch MUST be equal to ROI.width * sizeof(Npp32u).
// Also the image pointer used for label markers generation output must
// start at the same position in the image as it does in the marker
// compression function. Also note that actual input image size and ROI do
// not necessarily need to be related other than ROI being less than or
// equal to image size and image starting position does not necessarily have
// to be at pixel 0 in the input image.
cudaError = cudaMalloc(
(void **)&pUFLabelDev[nImage],
oSizeROI[nImage].width * sizeof(Npp32u) * oSizeROI[nImage].height);
if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
pInputImageHost[nImage] = reinterpret_cast<Npp8u *>(malloc(
oSizeROI[nImage].width * sizeof(Npp8u) * oSizeROI[nImage].height));
pUFLabelHost[nImage] = reinterpret_cast<Npp32u *>(malloc(
oSizeROI[nImage].width * sizeof(Npp32u) * oSizeROI[nImage].height));
// Use UF functions throughout this sample.
nppStatus = nppiLabelMarkersUFGetBufferSize_32u_C1R(
oSizeROI[nImage], &aGenerateLabelsScratchBufferSize[nImage]);
// One at a time image processing
cudaError = cudaMalloc((void **)&pUFGenerateLabelsScratchBufferDev[nImage],
aGenerateLabelsScratchBufferSize[nImage]);
if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
if (loadRaw8BitImage(pInputImageHost[nImage],
oSizeROI[nImage].width * sizeof(Npp8u),
oSizeROI[nImage].height, nImage) == 0) {
cudaError = cudaMemcpy2DAsync(
pInputImageDev[nImage], oSizeROI[nImage].width * sizeof(Npp8u),
pInputImageHost[nImage], oSizeROI[nImage].width * sizeof(Npp8u),
oSizeROI[nImage].width * sizeof(Npp8u), oSizeROI[nImage].height,
cudaMemcpyHostToDevice, nppStreamCtx.hStream);
nppStatus = nppiLabelMarkersUF_8u32u_C1R_Ctx(
pInputImageDev[nImage], oSizeROI[nImage].width * sizeof(Npp8u),
pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
oSizeROI[nImage], nppiNormInf,
pUFGenerateLabelsScratchBufferDev[nImage], nppStreamCtx);
if (nppStatus != NPP_SUCCESS) {
if (nImage == 0)
printf("Lena_LabelMarkersUF_8Way_512x512_32u failed.\n");
else if (nImage == 1)
printf("CT_skull_LabelMarkersUF_8Way_512x512_32u failed.\n");
else if (nImage == 2)
printf("PCB_METAL_LabelMarkersUF_8Way_509x335_32u failed.\n");
else if (nImage == 3)
printf("PCB2_LabelMarkersUF_8Way_1024x683_32u failed.\n");
else if (nImage == 4)
printf("PCB_LabelMarkersUF_8Way_1280x720_32u failed.\n");
tearDown();
return -1;
}
cudaError = cudaMemcpy2DAsync(
pUFLabelHost[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
oSizeROI[nImage].width * sizeof(Npp32u), oSizeROI[nImage].height,
cudaMemcpyDeviceToHost, nppStreamCtx.hStream);
// Wait host image read backs to complete, not necessary if no need to
// synchronize
if ((cudaError = cudaStreamSynchronize(nppStreamCtx.hStream)) !=
cudaSuccess) {
printf("Post label generation cudaStreamSynchronize failed\n");
tearDown();
return -1;
}
if (nImage == 0)
bmpFile = fopen(LabelMarkersOutputFile0.c_str(), "wb");
else if (nImage == 1)
bmpFile = fopen(LabelMarkersOutputFile1.c_str(), "wb");
else if (nImage == 2)
bmpFile = fopen(LabelMarkersOutputFile2.c_str(), "wb");
else if (nImage == 3)
bmpFile = fopen(LabelMarkersOutputFile3.c_str(), "wb");
else if (nImage == 4)
bmpFile = fopen(LabelMarkersOutputFile4.c_str(), "wb");
if (bmpFile == NULL) return -1;
size_t nSize = 0;
for (int j = 0; j < oSizeROI[nImage].height; j++) {
nSize += fwrite(&pUFLabelHost[nImage][j * oSizeROI[nImage].width],
sizeof(Npp32u), oSizeROI[nImage].width, bmpFile);
}
fclose(bmpFile);
nppStatus = nppiCompressMarkerLabelsGetBufferSize_32u_C1R(
oSizeROI[nImage].width * oSizeROI[nImage].height,
&aCompressLabelsScratchBufferSize[nImage]);
if (nppStatus != NPP_NO_ERROR) return nppStatus;
cudaError =
cudaMalloc((void **)&pUFCompressedLabelsScratchBufferDev[nImage],
aCompressLabelsScratchBufferSize[nImage]);
if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
nCompressedLabelCount = 0;
nppStatus = nppiCompressMarkerLabelsUF_32u_C1IR(
pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
oSizeROI[nImage], oSizeROI[nImage].width * oSizeROI[nImage].height,
&nCompressedLabelCount, pUFCompressedLabelsScratchBufferDev[nImage]);
if (nppStatus != NPP_SUCCESS) {
if (nImage == 0)
printf("Lena_CompressedLabelMarkersUF_8Way_512x512_32u failed.\n");
else if (nImage == 1)
printf(
"CT_Skull_CompressedLabelMarkersUF_8Way_512x512_32u failed.\n");
else if (nImage == 2)
printf(
"PCB_METAL_CompressedLabelMarkersUF_8Way_509x335_32u failed.\n");
else if (nImage == 3)
printf("PCB2_CompressedLabelMarkersUF_8Way_1024x683_32u failed.\n");
else if (nImage == 4)
printf("PCB_CompressedLabelMarkersUF_8Way_1280x720_32u failed.\n");
tearDown();
return -1;
}
cudaError = cudaMemcpy2DAsync(
pUFLabelHost[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
oSizeROI[nImage].width * sizeof(Npp32u), oSizeROI[nImage].height,
cudaMemcpyDeviceToHost, nppStreamCtx.hStream);
// Wait for host image read backs to finish, not necessary if no need to
// synchronize
if ((cudaError = cudaStreamSynchronize(nppStreamCtx.hStream)) !=
cudaSuccess ||
nCompressedLabelCount == 0) {
printf("Post label compression cudaStreamSynchronize failed\n");
tearDown();
return -1;
}
if (nImage == 0)
bmpFile = fopen(CompressedMarkerLabelsOutputFile0.c_str(), "wb");
else if (nImage == 1)
bmpFile = fopen(CompressedMarkerLabelsOutputFile1.c_str(), "wb");
else if (nImage == 2)
bmpFile = fopen(CompressedMarkerLabelsOutputFile2.c_str(), "wb");
else if (nImage == 3)
bmpFile = fopen(CompressedMarkerLabelsOutputFile3.c_str(), "wb");
else if (nImage == 4)
bmpFile = fopen(CompressedMarkerLabelsOutputFile4.c_str(), "wb");
if (bmpFile == NULL) return -1;
nSize = 0;
for (int j = 0; j < oSizeROI[nImage].height; j++) {
nSize += fwrite(&pUFLabelHost[nImage][j * oSizeROI[nImage].width],
sizeof(Npp32u), oSizeROI[nImage].width, bmpFile);
}
fclose(bmpFile);
if (nImage == 0)
printf(
"Lena_CompressedMarkerLabelsUF_8Way_512x512_32u succeeded, "
"compressed label count is %d.\n",
nCompressedLabelCount);
else if (nImage == 1)
printf(
"CT_Skull_CompressedMarkerLabelsUF_8Way_512x512_32u succeeded, "
"compressed label count is %d.\n",
nCompressedLabelCount);
else if (nImage == 2)
printf(
"PCB_METAL_CompressedMarkerLabelsUF_8Way_509x335_32u succeeded, "
"compressed label count is %d.\n",
nCompressedLabelCount);
else if (nImage == 3)
printf(
"PCB2_CompressedMarkerLabelsUF_8Way_1024x683_32u succeeded, "
"compressed label count is %d.\n",
nCompressedLabelCount);
else if (nImage == 4)
printf(
"PCB_CompressedMarkerLabelsUF_8Way_1280x720_32u succeeded, "
"compressed label count is %d.\n",
nCompressedLabelCount);
}
}
// Batch image processing
// We want to allocate scratch buffers more efficiently for batch processing
// so first we free up the scratch buffers for image 0 and reallocate them.
// This is not required but helps cudaMalloc to work more efficiently.
cudaFree(pUFCompressedLabelsScratchBufferDev[0]);
int nTotalBatchedUFCompressLabelsScratchBufferDevSize = 0;
for (int k = 0; k < NUMBER_OF_IMAGES; k++)
nTotalBatchedUFCompressLabelsScratchBufferDevSize +=
aCompressLabelsScratchBufferSize[k];
cudaError = cudaMalloc((void **)&pUFCompressedLabelsScratchBufferDev[0],
nTotalBatchedUFCompressLabelsScratchBufferDevSize);
if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
// Now allocate batch lists
int nBatchImageListBytes = NUMBER_OF_IMAGES * sizeof(NppiImageDescriptor);
cudaError =
cudaMalloc((void **)&pUFBatchSrcImageListDev, nBatchImageListBytes);
if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
cudaError =
cudaMalloc((void **)&pUFBatchSrcDstImageListDev, nBatchImageListBytes);
if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
pUFBatchSrcImageListHost =
reinterpret_cast<NppiImageDescriptor *>(malloc(nBatchImageListBytes));
pUFBatchSrcDstImageListHost =
reinterpret_cast<NppiImageDescriptor *>(malloc(nBatchImageListBytes));
NppiSize oMaxROISize = {0, 0};
for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
pUFBatchSrcImageListHost[nImage].pData = pInputImageDev[nImage];
pUFBatchSrcImageListHost[nImage].nStep =
oSizeROI[nImage].width * sizeof(Npp8u);
// src image oSize parameter is ignored in these NPP functions
pUFBatchSrcDstImageListHost[nImage].pData = pUFLabelDev[nImage];
pUFBatchSrcDstImageListHost[nImage].nStep =
oSizeROI[nImage].width * sizeof(Npp32u);
pUFBatchSrcDstImageListHost[nImage].oSize = oSizeROI[nImage];
if (oSizeROI[nImage].width > oMaxROISize.width)
oMaxROISize.width = oSizeROI[nImage].width;
if (oSizeROI[nImage].height > oMaxROISize.height)
oMaxROISize.height = oSizeROI[nImage].height;
}
// Copy label generation batch lists from CPU to GPU
cudaError = cudaMemcpyAsync(pUFBatchSrcImageListDev, pUFBatchSrcImageListHost,
nBatchImageListBytes, cudaMemcpyHostToDevice,
nppStreamCtx.hStream);
if (cudaError != cudaSuccess) return NPP_MEMCPY_ERROR;
cudaError = cudaMemcpyAsync(pUFBatchSrcDstImageListDev,
pUFBatchSrcDstImageListHost, nBatchImageListBytes,
cudaMemcpyHostToDevice, nppStreamCtx.hStream);
if (cudaError != cudaSuccess) return NPP_MEMCPY_ERROR;
// We use 8-way neighbor search throughout this example
nppStatus = nppiLabelMarkersUFBatch_8u32u_C1R_Advanced_Ctx(
pUFBatchSrcImageListDev, pUFBatchSrcDstImageListDev, NUMBER_OF_IMAGES,
oMaxROISize, nppiNormInf, nppStreamCtx);
if (nppStatus != NPP_SUCCESS) {
printf("LabelMarkersUFBatch_8Way_8u32u failed.\n");
tearDown();
return -1;
}
// Now read back generated device images to the host
for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
cudaError = cudaMemcpy2DAsync(
pUFLabelHost[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
oSizeROI[nImage].width * sizeof(Npp32u), oSizeROI[nImage].height,
cudaMemcpyDeviceToHost, nppStreamCtx.hStream);
}
// Wait for host image read backs to complete, not necessary if no need to
// synchronize
if ((cudaError = cudaStreamSynchronize(nppStreamCtx.hStream)) !=
cudaSuccess) {
printf("Post label generation cudaStreamSynchronize failed\n");
tearDown();
return -1;
}
// Save output to files
for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
if (nImage == 0)
bmpFile = fopen(LabelMarkersBatchOutputFile0.c_str(), "wb");
else if (nImage == 1)
bmpFile = fopen(LabelMarkersBatchOutputFile1.c_str(), "wb");
else if (nImage == 2)
bmpFile = fopen(LabelMarkersBatchOutputFile2.c_str(), "wb");
else if (nImage == 3)
bmpFile = fopen(LabelMarkersBatchOutputFile3.c_str(), "wb");
else if (nImage == 4)
bmpFile = fopen(LabelMarkersBatchOutputFile4.c_str(), "wb");
if (bmpFile == NULL) return -1;
size_t nSize = 0;
for (int j = 0; j < oSizeROI[nImage].height; j++) {
nSize += fwrite(&pUFLabelHost[nImage][j * oSizeROI[nImage].width],
sizeof(Npp32u), oSizeROI[nImage].width, bmpFile);
}
fclose(bmpFile);
}
#ifdef USE_BATCHED_LABEL_COMPRESSION
// Now allocate scratch buffer memory for batched label compression
cudaError = cudaMalloc((void **)&pUFBatchSrcDstScratchBufferListDev,
NUMBER_OF_IMAGES * sizeof(NppiBufferDescriptor));
if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
cudaError = cudaMalloc((void **)&pUFBatchPerImageCompressedCountListDev,
NUMBER_OF_IMAGES * sizeof(Npp32u));
if (cudaError != cudaSuccess) return NPP_MEMORY_ALLOCATION_ERR;
// Allocate host side scratch buffer point and size list and initialize with
// device scratch buffer pointers
pUFBatchSrcDstScratchBufferListHost =
reinterpret_cast<NppiBufferDescriptor *>(
malloc(NUMBER_OF_IMAGES * sizeof(NppiBufferDescriptor)));
pUFBatchPerImageCompressedCountListHost =
reinterpret_cast<Npp32u *>(malloc(NUMBER_OF_IMAGES * sizeof(Npp32u)));
// Start buffer pointer at beginning of full per image buffer list sized
// pUFCompressedLabelsScratchBufferDev[0]
Npp32u *pCurUFCompressedLabelsScratchBufferDev =
reinterpret_cast<Npp32u *>(pUFCompressedLabelsScratchBufferDev[0]);
int nMaxUFCompressedLabelsScratchBufferSize = 0;
for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
// This particular function works on in-place data and SrcDst image batch
// list has already been initialized in batched label generation function
// setup
// Initialize each per image buffer descriptor
pUFBatchSrcDstScratchBufferListHost[nImage].pData =
reinterpret_cast<void *>(pCurUFCompressedLabelsScratchBufferDev);
pUFBatchSrcDstScratchBufferListHost[nImage].nBufferSize =
aCompressLabelsScratchBufferSize[nImage];
if (aCompressLabelsScratchBufferSize[nImage] >
nMaxUFCompressedLabelsScratchBufferSize)
nMaxUFCompressedLabelsScratchBufferSize =
aCompressLabelsScratchBufferSize[nImage];
// Offset buffer pointer to next per image buffer
Npp8u *pTempBuffer =
reinterpret_cast<Npp8u *>(pCurUFCompressedLabelsScratchBufferDev);
pTempBuffer += aCompressLabelsScratchBufferSize[nImage];
pCurUFCompressedLabelsScratchBufferDev =
reinterpret_cast<Npp32u *>((void *)(pTempBuffer));
}
// Copy compression batch scratch buffer list from CPU to GPU
cudaError = cudaMemcpyAsync(pUFBatchSrcDstScratchBufferListDev,
pUFBatchSrcDstScratchBufferListHost,
NUMBER_OF_IMAGES * sizeof(NppiBufferDescriptor),
cudaMemcpyHostToDevice, nppStreamCtx.hStream);
if (cudaError != cudaSuccess) return NPP_MEMCPY_ERROR;
nppStatus = nppiCompressMarkerLabelsUFBatch_32u_C1IR_Advanced_Ctx(
pUFBatchSrcDstImageListDev, pUFBatchSrcDstScratchBufferListDev,
pUFBatchPerImageCompressedCountListDev, NUMBER_OF_IMAGES, oMaxROISize,
nMaxUFCompressedLabelsScratchBufferSize, nppStreamCtx);
if (nppStatus != NPP_SUCCESS) {
printf("BatchCompressedLabelMarkersUF_8Way_32u failed.\n");
tearDown();
return -1;
}
// Copy output compressed label images back to host
for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
cudaError = cudaMemcpy2DAsync(
pUFLabelHost[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
pUFLabelDev[nImage], oSizeROI[nImage].width * sizeof(Npp32u),
oSizeROI[nImage].width * sizeof(Npp32u), oSizeROI[nImage].height,
cudaMemcpyDeviceToHost, nppStreamCtx.hStream);
}
// Wait for host image read backs to complete, not necessary if no need to
// synchronize
if ((cudaError = cudaStreamSynchronize(nppStreamCtx.hStream)) !=
cudaSuccess) {
printf("Post label compression cudaStreamSynchronize failed\n");
tearDown();
return -1;
}
// Save compressed label images into files
for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
if (nImage == 0)
bmpFile = fopen(CompressedMarkerLabelsBatchOutputFile0.c_str(), "wb");
else if (nImage == 1)
bmpFile = fopen(CompressedMarkerLabelsBatchOutputFile1.c_str(), "wb");
else if (nImage == 2)
bmpFile = fopen(CompressedMarkerLabelsBatchOutputFile2.c_str(), "wb");
else if (nImage == 3)
bmpFile = fopen(CompressedMarkerLabelsBatchOutputFile3.c_str(), "wb");
else if (nImage == 4)
bmpFile = fopen(CompressedMarkerLabelsBatchOutputFile4.c_str(), "wb");
if (bmpFile == NULL) return -1;
size_t nSize = 0;
for (int j = 0; j < oSizeROI[nImage].height; j++) {
nSize += fwrite(&pUFLabelHost[nImage][j * oSizeROI[nImage].width],
sizeof(Npp32u), oSizeROI[nImage].width, bmpFile);
}
fclose(bmpFile);
}
// Read back per image compressed label count.
cudaError = cudaMemcpyAsync(pUFBatchPerImageCompressedCountListHost,
pUFBatchPerImageCompressedCountListDev,
NUMBER_OF_IMAGES * sizeof(Npp32u),
cudaMemcpyDeviceToHost, nppStreamCtx.hStream);
if (cudaError != cudaSuccess) {
tearDown();
return NPP_MEMCPY_ERROR;
}
// Wait for host read back to complete
cudaError = cudaStreamSynchronize(nppStreamCtx.hStream);
printf("\n\n");
for (int nImage = 0; nImage < NUMBER_OF_IMAGES; nImage++) {
if (nImage == 0)
printf(
"Lena_CompressedMarkerLabelsUFBatch_8Way_512x512_32u succeeded, "
"compressed label count is %d.\n",
pUFBatchPerImageCompressedCountListHost[nImage]);
else if (nImage == 1)
printf(
"CT_Skull_CompressedMarkerLabelsUFBatch_8Way_512x512_32u succeeded, "
"compressed label count is %d.\n",
pUFBatchPerImageCompressedCountListHost[nImage]);
else if (nImage == 2)
printf(
"PCB_METAL_CompressedMarkerLabelsUFBatch_8Way_509x335_32u succeeded, "
"compressed label count is %d.\n",
pUFBatchPerImageCompressedCountListHost[nImage]);
else if (nImage == 3)
printf(
"PCB2_CompressedMarkerLabelsUFBatch_8Way_1024x683_32u succeeded, "
"compressed label count is %d.\n",
pUFBatchPerImageCompressedCountListHost[nImage]);
else if (nImage == 4)
printf(
"PCB_CompressedMarkerLabelsUFBatch_8Way_1280x720_32u succeeded, "
"compressed label count is %d.\n",
pUFBatchPerImageCompressedCountListHost[nImage]);
}
#endif // USE_BATCHED_LABEL_COMPRESSION
tearDown();
return 0;
}

View File

@@ -1,7 +1,7 @@
 
Microsoft Visual Studio Solution File, Format Version 12.00 Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 2012 # Visual Studio 2017
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "matrixMul", "matrixMul_vs2012.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}" Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "batchedLabelMarkersAndLabelCompressionNPP", "batchedLabelMarkersAndLabelCompressionNPP_vs2017.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject EndProject
Global Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution GlobalSection(SolutionConfigurationPlatforms) = preSolution

View File

@@ -15,15 +15,20 @@
</ItemGroup> </ItemGroup>
<PropertyGroup Label="Globals"> <PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid> <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>boxFilterNPP_vs2015</RootNamespace> <RootNamespace>batchedLabelMarkersAndLabelCompressionNPP_vs2017</RootNamespace>
<ProjectName>boxFilterNPP</ProjectName> <ProjectName>batchedLabelMarkersAndLabelCompressionNPP</ProjectName>
<CudaToolkitCustomDir /> <CudaToolkitCustomDir />
</PropertyGroup> </PropertyGroup>
<PropertyGroup Condition="'$(WindowsTargetPlatformVersion)'==''">
<LatestTargetPlatformVersion>$([Microsoft.Build.Utilities.ToolLocationHelper]::GetLatestSDKTargetPlatformVersion('Windows', '10.0'))</LatestTargetPlatformVersion>
<WindowsTargetPlatformVersion Condition="'$(WindowsTargetPlatformVersion)' == ''">$(LatestTargetPlatformVersion)</WindowsTargetPlatformVersion>
<TargetPlatformVersion>$(WindowsTargetPlatformVersion)</TargetPlatformVersion>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup> <PropertyGroup>
<ConfigurationType>Application</ConfigurationType> <ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet> <CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset> <PlatformToolset>v141</PlatformToolset>
</PropertyGroup> </PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'"> <PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries> <UseDebugLibraries>true</UseDebugLibraries>
@@ -33,7 +38,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -53,19 +58,20 @@
<ClCompile> <ClCompile>
<WarningLevel>Level3</WarningLevel> <WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions> <PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories> <AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
</ClCompile> </ClCompile>
<Link> <Link>
<SubSystem>Console</SubSystem> <SubSystem>Console</SubSystem>
<AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies> <AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories> <AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/boxFilterNPP.exe</OutputFile> <OutputFile>$(OutDir)/batchedLabelMarkersAndLabelCompressionNPP.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_35,compute_35;</CodeGeneration> <CodeGeneration>compute_35,compute_35;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -96,22 +102,12 @@
<TargetMachinePlatform>64</TargetMachinePlatform> <TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
<Link>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
<Link>
<AdditionalDependencies>freeimage.lib;%(AdditionalDependencies)</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemGroup> <ItemGroup>
<ClCompile Include="boxFilterNPP.cpp" /> <ClCompile Include="batchedLabelMarkersAndLabelCompressionNPP.cpp" />
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -0,0 +1,20 @@

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 2019
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "batchedLabelMarkersAndLabelCompressionNPP", "batchedLabelMarkersAndLabelCompressionNPP_vs2019.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -15,15 +15,16 @@
</ItemGroup> </ItemGroup>
<PropertyGroup Label="Globals"> <PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid> <ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>MersenneTwisterGP11213_vs2013</RootNamespace> <RootNamespace>batchedLabelMarkersAndLabelCompressionNPP_vs2019</RootNamespace>
<ProjectName>MersenneTwisterGP11213</ProjectName> <ProjectName>batchedLabelMarkersAndLabelCompressionNPP</ProjectName>
<CudaToolkitCustomDir /> <CudaToolkitCustomDir />
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup> <PropertyGroup>
<ConfigurationType>Application</ConfigurationType> <ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet> <CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v120</PlatformToolset> <PlatformToolset>v142</PlatformToolset>
<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
</PropertyGroup> </PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'"> <PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries> <UseDebugLibraries>true</UseDebugLibraries>
@@ -33,7 +34,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -57,15 +58,16 @@
</ClCompile> </ClCompile>
<Link> <Link>
<SubSystem>Console</SubSystem> <SubSystem>Console</SubSystem>
<AdditionalDependencies>curand.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies> <AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories> <AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/MersenneTwisterGP11213.exe</OutputFile> <OutputFile>$(OutDir)/batchedLabelMarkersAndLabelCompressionNPP.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_35,compute_35;</CodeGeneration> <CodeGeneration>compute_35,compute_35;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -97,11 +99,11 @@
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemGroup> <ItemGroup>
<ClCompile Include="MersenneTwister.cpp" /> <ClCompile Include="batchedLabelMarkersAndLabelCompressionNPP.cpp" />
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -88,7 +88,7 @@ endif
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now. # sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
ifeq ($(HOST_ARCH),aarch64) ifeq ($(HOST_ARCH),aarch64)
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux)) ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
HOST_ARCH := sbsa HOST_ARCH := sbsa
TARGET_ARCH := sbsa TARGET_ARCH := sbsa
endif endif
@@ -146,7 +146,7 @@ else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
endif endif
export QNX_HOST export QNX_HOST
export QNX_TARGET export QNX_TARGET
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.0.0-g++ HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
else ifeq ($(TARGET_OS), android) else ifeq ($(TARGET_OS), android)
HOST_COMPILER ?= aarch64-linux-android-clang++ HOST_COMPILER ?= aarch64-linux-android-clang++
endif endif
@@ -201,24 +201,34 @@ ifneq ($(TARGET_ARCH),$(HOST_ARCH))
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
endif endif
endif endif
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
NVCCFLAGS += --qpp-config 5.4.0,gcc_ntoaarch64le
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
LDFLAGS += -lsocket LDFLAGS += -lsocket
LDFLAGS += -rpath=/usr/lib/aarch64-qnx-gnu -L/usr/lib/aarch64-qnx-gnu LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
ifneq ($(TARGET_FS),) CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
LDFLAGS += -rpath=$(TARGET_FS)/usr/lib -L $(TARGET_FS)/usr/lib ifdef TARGET_OVERRIDE
LDFLAGS += -rpath=$(TARGET_FS)/usr/libnvidia -L $(TARGET_FS)/usr/libnvidia LDFLAGS += -lslog2
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE) ifneq ($(TARGET_FS),)
LDFLAGS += -L$(TARGET_FS)/usr/lib
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
CCFLAGS += -I$(TARGET_FS)/../include
endif endif
endif endif
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
endif
# Install directory of different arch # Install directory of different arch
CUDA_INSTALL_TARGET_DIR := CUDA_INSTALL_TARGET_DIR :=
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
@@ -291,11 +301,9 @@ ifeq ($(TARGET_OS),linux)
GCCVERSION += 00 GCCVERSION += 00
# Remove spaces from the version number # Remove spaces from the version number
GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION)) GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION))
# Crop the version number to 3 decimals.
GCCVERSION := $(shell expr `echo $(GCCVERSION)` | cut -b1-3)
#$(warning $(GCCVERSION)) #$(warning $(GCCVERSION))
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 500) IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 50000)
ifeq ($(IS_MIN_VERSION), 1) ifeq ($(IS_MIN_VERSION), 1)
$(info >>> GCC Version is greater or equal to 5.0.0 <<<) $(info >>> GCC Version is greater or equal to 5.0.0 <<<)
@@ -306,7 +314,7 @@ ifeq ($(TARGET_OS),linux)
endif endif
# Gencode arguments # Gencode arguments
SMS ?= 80 SMS ?= 80 86
ifeq ($(SMS),) ifeq ($(SMS),)
$(info >>> WARNING - no SM architectures have been specified - waiving sample <<<) $(info >>> WARNING - no SM architectures have been specified - waiving sample <<<)
@@ -324,7 +332,7 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif endif
endif endif
ALL_CCFLAGS += --std=c++11 ALL_CCFLAGS += --std=c++11 --threads 0
ifeq ($(SAMPLE_ENABLED),0) ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]" EXEC ?= @echo "[@]"

View File

@@ -43,6 +43,7 @@
<scope>1:CUDA Basic Topics</scope> <scope>1:CUDA Basic Topics</scope>
</scopes> </scopes>
<sm-arch>sm80</sm-arch> <sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<supported_envs> <supported_envs>
<env> <env>
<arch>x86_64</arch> <arch>x86_64</arch>

View File

@@ -10,7 +10,7 @@ Matrix Multiply, WMMA, Tensor Cores
## Supported SM Architectures ## Supported SM Architectures
[SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes ## Supported OSes
@@ -27,7 +27,7 @@ cudaMallocManaged, cudaDeviceSynchronize, cudaFuncSetAttribute, cudaEventCreate,
## Prerequisites ## Prerequisites
Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run ## Build and Run

View File

@@ -62,7 +62,7 @@
#include <cuda.h> #include <cuda.h>
#include <cuda_bf16.h> #include <cuda_bf16.h>
#include <mma.h> #include <mma.h>
#include <cuda_pipeline.h> #include <cuda/pipeline>
// helper functions and utilities to work with CUDA // helper functions and utilities to work with CUDA
#include <helper_functions.h> #include <helper_functions.h>
@@ -70,10 +70,6 @@
// Externally configurable parameters. // Externally configurable parameters.
// Switch for choosing cpp interface for cuda pipeline
// vs primitives interface.
#define USE_CPP_API 0
#ifndef CPU_DEBUG #ifndef CPU_DEBUG
// Set this to 1 to verify the correctness of the GPU-computed matrix. // Set this to 1 to verify the correctness of the GPU-computed matrix.
#define CPU_DEBUG 0 #define CPU_DEBUG 0
@@ -183,7 +179,6 @@ const char* kernelNames[] = {"compute_bf16gemm_async_copy", "compute_bf16gemm",
"simple_wmma_bf16gemm"}; "simple_wmma_bf16gemm"};
using namespace nvcuda; using namespace nvcuda;
namespace nvcuda_namespace = nvcuda::experimental;
__host__ void init_host_matrices(__nv_bfloat16 *a, __nv_bfloat16 *b, float *c) __host__ void init_host_matrices(__nv_bfloat16 *a, __nv_bfloat16 *b, float *c)
{ {
@@ -369,8 +364,8 @@ __global__ void compute_bf16gemm(const __nv_bfloat16 *A, const __nv_bfloat16 *B,
#pragma unroll #pragma unroll
for (int i = 0; i < N; i++) { for (int i = 0; i < N; i++) {
*((int4*)(dst_gmem_warp_stream_ptr + GLOBAL_MEM_STRIDE * i) + laneId) = *((float4*)(dst_gmem_warp_stream_ptr + GLOBAL_MEM_STRIDE * i) + laneId) =
*((int4*)(shmem_warp_stream_ptr + SHMEM_STRIDE * i) + laneId); *((float4*)(shmem_warp_stream_ptr + SHMEM_STRIDE * i) + laneId);
} }
__syncthreads(); __syncthreads();
@@ -388,7 +383,7 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
const unsigned int laneId = threadIdx.x % WARP_SIZE; const unsigned int laneId = threadIdx.x % WARP_SIZE;
// Offset in shared memory from which the B matrix is stored. // Offset in shared memory from which the B matrix is stored.
const size_t shmem_idx_b_off = BLOCK_COL_TILES * M; constexpr size_t shmem_idx_b_off = BLOCK_COL_TILES * M;
// This pointer is used to access the C and D matrix tiles this warp computes. // This pointer is used to access the C and D matrix tiles this warp computes.
float *shmem_warp_tile_ptr = (float*)&shmem[0][0] + (warpId / BLOCK_ROW_WARPS) * SHMEM_STRIDE * N * BLOCK_ROW_WARPS + (warpId % BLOCK_ROW_WARPS) * SHMEM_OFFSET; float *shmem_warp_tile_ptr = (float*)&shmem[0][0] + (warpId / BLOCK_ROW_WARPS) * SHMEM_STRIDE * N * BLOCK_ROW_WARPS + (warpId % BLOCK_ROW_WARPS) * SHMEM_OFFSET;
@@ -401,9 +396,10 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
// in a loss of precision). Zero still needs to be specially handled though. // in a loss of precision). Zero still needs to be specially handled though.
beta /= alpha; beta /= alpha;
#if USE_CPP_API cuda::pipeline<cuda::thread_scope_thread> pipe = cuda::make_pipeline();
nvcuda_namespace::pipeline pipe; const auto shape4 = cuda::aligned_size_t<alignof(float4)>(sizeof(float4));
#endif constexpr int loadStride = 2; // load 4 floats, left-shift by 2.
// Each CTA slides along the 128 x 128 tiles from the top left corner of the matrix to the // Each CTA slides along the 128 x 128 tiles from the top left corner of the matrix to the
// right and down, and selects the next tile to compute. Once there's no such tile, // right and down, and selects the next tile to compute. Once there's no such tile,
// all warps in this CTA exit. // all warps in this CTA exit.
@@ -423,24 +419,17 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
// Stream multiple C tiles to shared memory. // Stream multiple C tiles to shared memory.
#pragma unroll #pragma unroll
for (int i = 0; i < N; i++) { for (int i = 0; i < N; i++) {
#if USE_CPP_API pipe.producer_acquire();
nvcuda_namespace::memcpy_async(*((int4*)(shmem_warp_stream_ptr + SHMEM_STRIDE * i) + laneId),
*((int4*)(src_gmem_warp_stream_ptr + GLOBAL_MEM_STRIDE * i) + laneId), cuda::memcpy_async(&shmem_warp_stream_ptr[(SHMEM_STRIDE * i) + (laneId << loadStride)],
pipe); &src_gmem_warp_stream_ptr[(GLOBAL_MEM_STRIDE * i) + (laneId << loadStride)],
pipe.commit(); shape4, pipe);
#else
__pipeline_memcpy_async((reinterpret_cast<int4*>(&shmem_warp_stream_ptr[(SHMEM_STRIDE * i)])) + laneId, pipe.producer_commit();
(reinterpret_cast<const int4*>(&src_gmem_warp_stream_ptr[(GLOBAL_MEM_STRIDE * i)])) + laneId,
sizeof(int4));
__pipeline_commit();
#endif
} }
#if USE_CPP_API // Now wait for all the above issued 8 batches to complete.
pipe.wait_prior<0>(); cuda::pipeline_consumer_wait_prior<0>(pipe);
#else
__pipeline_wait_prior(0);
#endif
__syncthreads(); __syncthreads();
// These fragments will accumulate the result of A and B matrix fragment multiplications // These fragments will accumulate the result of A and B matrix fragment multiplications
@@ -455,16 +444,7 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
const float *tile_ptr = shmem_warp_tile_ptr + i * SHMEM_STRIDE * N + j * N; const float *tile_ptr = shmem_warp_tile_ptr + i * SHMEM_STRIDE * N + j * N;
wmma::load_matrix_sync(c[i][j], tile_ptr, SHMEM_STRIDE, C_LAYOUT); wmma::load_matrix_sync(c[i][j], tile_ptr, SHMEM_STRIDE, C_LAYOUT);
} // Scale the C matrix.
}
__syncthreads();
// Scale the C matrix.
#pragma unroll
for (int i = 0; i < WARP_COL_TILES; i++) {
#pragma unroll
for (int j = 0; j < WARP_ROW_TILES; j++) {
#pragma unroll #pragma unroll
for (int t = 0; t < c[i][j].num_elements; t++) { for (int t = 0; t < c[i][j].num_elements; t++) {
c[i][j].x[t] *= beta; c[i][j].x[t] *= beta;
@@ -472,48 +452,46 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
} }
} }
pipe.consumer_release();
// sync here so that shared memory can then be used for loading A & B matrices.
__syncthreads();
// Select what warp copies what matrix to shared memory. // Select what warp copies what matrix to shared memory.
// Warps 0-3 copy the A matrix, warps 4-7 copy the B matrix. // Warps 0-3 copy the A matrix, warps 4-7 copy the B matrix.
const __nv_bfloat16 *warp_ptr = (warpId < (WARPS_PER_BLOCK/2)) ? (&A[block_tile_i * M * K_GLOBAL] + M * K_GLOBAL * (warpId % (WARPS_PER_BLOCK/2)) * 2) : const __nv_bfloat16 *warp_ptr = (warpId < (WARPS_PER_BLOCK/2)) ? (&A[block_tile_i * M * K_GLOBAL] + M * K_GLOBAL * (warpId % (WARPS_PER_BLOCK/2)) * 2) :
(&B[block_tile_j * N * K_GLOBAL] + N * K_GLOBAL * (warpId % (WARPS_PER_BLOCK/2)) * 2); (&B[block_tile_j * N * K_GLOBAL] + N * K_GLOBAL * (warpId % (WARPS_PER_BLOCK/2)) * 2);
constexpr int chunksPerLane = ((WARP_SIZE/2) / CHUNK_COPY_LINES_PER_WARP) * 2;
constexpr int loadStrideBfloat8 = 3; // load 8 bfloats, left-shift by 3.
const int laneLoadElem = (laneId % CHUNK_COPY_LINE_LANES) << loadStrideBfloat8;
const int stridePerLaneCopy = (laneId / CHUNK_COPY_LINE_LANES);
// Go through the global K dimension by a fixed step at a time. // Go through the global K dimension by a fixed step at a time.
#pragma unroll #pragma unroll
for (int tile_k = 0; tile_k < K_TILES; tile_k += CHUNK_K) { for (int tile_k = 0; tile_k < K_TILES; tile_k += CHUNK_K) {
// Copy slices of the A and B matrices to shared memory. // Copy slices of the A and B matrices to shared memory.
// The first half of the warps in the CTA copy the A matrix, the rest copy the B matrix. // The first half of the warps in the CTA copy the A matrix, the rest copy the B matrix.
size_t shmem_idx = warpId < (WARPS_PER_BLOCK/2) ? (M * (warpId % (WARPS_PER_BLOCK/2)) * 2) : // As for bf16 MMA M == N we use M for warp 4-7 + shmem_idx_b_off.
(N * (warpId % (WARPS_PER_BLOCK/2)) * 2 + shmem_idx_b_off); size_t shmem_idx = (M * (warpId % (WARPS_PER_BLOCK/2)) * 2) + ((warpId / (WARPS_PER_BLOCK/2)) * shmem_idx_b_off);
// First half of the warp copies the first row / column of the matrix, // First half of the warp copies the first row / column of the matrix,
// the second half of the warp copies the next. // the second half of the warp copies the next.
const __nv_bfloat16 *lane_ptr = (warp_ptr + tile_k * K + (laneId / CHUNK_COPY_LINE_LANES) * K_GLOBAL); const __nv_bfloat16 *lane_ptr = warp_ptr + tile_k * K + stridePerLaneCopy * K_GLOBAL + laneLoadElem;
// Shift the second half of the warp to the next row / column in the shared memory. // Shift the second half of the warp to the next row / column in the shared memory.
shmem_idx += laneId / CHUNK_COPY_LINE_LANES; shmem_idx += stridePerLaneCopy;
#pragma unroll #pragma unroll
for(int i = 0; i < ((WARP_SIZE/2) / CHUNK_COPY_LINES_PER_WARP) * 2; i++) { for(int i = 0; i < chunksPerLane; i++) {
// Copy 16 bytes at once in each lane. // Copy 16 bytes at once in each lane.
#if USE_CPP_API pipe.producer_acquire();
nvcuda_namespace::memcpy_async(*((int4*)&shmem[shmem_idx][0] + (laneId % CHUNK_COPY_LINE_LANES)), cuda::memcpy_async(&shmem[shmem_idx][laneLoadElem], lane_ptr, shape4, pipe);
*((int4*)lane_ptr + (laneId % CHUNK_COPY_LINE_LANES)), pipe); pipe.producer_commit();
pipe.commit();
#else
__pipeline_memcpy_async((int4*)&shmem[shmem_idx][0] + (laneId % CHUNK_COPY_LINE_LANES),
(int4*)lane_ptr + (laneId % CHUNK_COPY_LINE_LANES), sizeof(int4));
__pipeline_commit();
#endif
// Advance the global memory pointer and the shared memory index. // Advance the global memory pointer and the shared memory index.
lane_ptr = lane_ptr + K_GLOBAL * CHUNK_COPY_LINES_PER_WARP; lane_ptr = lane_ptr + K_GLOBAL * CHUNK_COPY_LINES_PER_WARP;
shmem_idx += CHUNK_COPY_LINES_PER_WARP; shmem_idx += CHUNK_COPY_LINES_PER_WARP;
} }
cuda::pipeline_consumer_wait_prior<0>(pipe);
#if USE_CPP_API
pipe.wait_prior<0>();
#else
__pipeline_wait_prior(0);
#endif
__syncthreads(); __syncthreads();
// Compute a grid of C matrix tiles in each warp. // Compute a grid of C matrix tiles in each warp.
@@ -545,6 +523,7 @@ __global__ void compute_bf16gemm_async_copy(const __nv_bfloat16 *A, const __nv_b
} }
} }
pipe.consumer_release();
__syncthreads(); __syncthreads();
} }

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "bf16TensorCoreGemm", "bf16TensorCoreGemm_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>bf16TensorCoreGemm_vs2015</RootNamespace>
<ProjectName>bf16TensorCoreGemm</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/bf16TensorCoreGemm.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_80,sm_80;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="bf16TensorCoreGemm.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
</ImportGroup>
</Project>

View File

@@ -38,7 +38,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,10 +67,11 @@
<OutputFile>$(OutDir)/bf16TensorCoreGemm.exe</OutputFile> <OutputFile>$(OutDir)/bf16TensorCoreGemm.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_80,sm_80;</CodeGeneration> <CodeGeneration>compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -34,7 +34,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,10 +63,11 @@
<OutputFile>$(OutDir)/bf16TensorCoreGemm.exe</OutputFile> <OutputFile>$(OutDir)/bf16TensorCoreGemm.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_80,sm_80;</CodeGeneration> <CodeGeneration>compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -88,7 +88,7 @@ endif
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now. # sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
ifeq ($(HOST_ARCH),aarch64) ifeq ($(HOST_ARCH),aarch64)
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux)) ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
HOST_ARCH := sbsa HOST_ARCH := sbsa
TARGET_ARCH := sbsa TARGET_ARCH := sbsa
endif endif
@@ -146,7 +146,7 @@ else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
endif endif
export QNX_HOST export QNX_HOST
export QNX_TARGET export QNX_TARGET
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.0.0-g++ HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
else ifeq ($(TARGET_OS), android) else ifeq ($(TARGET_OS), android)
HOST_COMPILER ?= aarch64-linux-android-clang++ HOST_COMPILER ?= aarch64-linux-android-clang++
endif endif
@@ -201,24 +201,34 @@ ifneq ($(TARGET_ARCH),$(HOST_ARCH))
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
endif endif
endif endif
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
NVCCFLAGS += --qpp-config 5.4.0,gcc_ntoaarch64le
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
LDFLAGS += -lsocket LDFLAGS += -lsocket
LDFLAGS += -rpath=/usr/lib/aarch64-qnx-gnu -L/usr/lib/aarch64-qnx-gnu LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
ifneq ($(TARGET_FS),) CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
LDFLAGS += -rpath=$(TARGET_FS)/usr/lib -L $(TARGET_FS)/usr/lib ifdef TARGET_OVERRIDE
LDFLAGS += -rpath=$(TARGET_FS)/usr/libnvidia -L $(TARGET_FS)/usr/libnvidia LDFLAGS += -lslog2
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE) ifneq ($(TARGET_FS),)
LDFLAGS += -L$(TARGET_FS)/usr/lib
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
CCFLAGS += -I$(TARGET_FS)/../include
endif endif
endif endif
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
endif
# Install directory of different arch # Install directory of different arch
CUDA_INSTALL_TARGET_DIR := CUDA_INSTALL_TARGET_DIR :=
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
@@ -285,11 +295,9 @@ ifeq ($(TARGET_OS),linux)
GCCVERSION += 00 GCCVERSION += 00
# Remove spaces from the version number # Remove spaces from the version number
GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION)) GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION))
# Crop the version number to 3 decimals.
GCCVERSION := $(shell expr `echo $(GCCVERSION)` | cut -b1-3)
#$(warning $(GCCVERSION)) #$(warning $(GCCVERSION))
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 470) IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 47000)
ifeq ($(IS_MIN_VERSION), 1) ifeq ($(IS_MIN_VERSION), 1)
$(info >>> GCC Version is greater or equal to 4.7.0 <<<) $(info >>> GCC Version is greater or equal to 4.7.0 <<<)
@@ -301,9 +309,9 @@ endif
# Gencode arguments # Gencode arguments
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64)) ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
SMS ?= 35 37 50 52 60 61 70 72 75 80 SMS ?= 35 37 50 52 60 61 70 72 75 80 86
else else
SMS ?= 35 37 50 52 60 61 70 75 80 SMS ?= 35 37 50 52 60 61 70 75 80 86
endif endif
ifeq ($(SMS),) ifeq ($(SMS),)
@@ -322,7 +330,7 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif endif
endif endif
ALL_CCFLAGS += --std=c++11 ALL_CCFLAGS += --std=c++11 --threads 0
ifeq ($(SAMPLE_ENABLED),0) ifeq ($(SAMPLE_ENABLED),0)
EXEC ?= @echo "[@]" EXEC ?= @echo "[@]"

View File

@@ -40,6 +40,7 @@
<sm-arch>sm72</sm-arch> <sm-arch>sm72</sm-arch>
<sm-arch>sm75</sm-arch> <sm-arch>sm75</sm-arch>
<sm-arch>sm80</sm-arch> <sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<supported_envs> <supported_envs>
<env> <env>
<arch>x86_64</arch> <arch>x86_64</arch>

View File

@@ -10,7 +10,7 @@ Cooperative Groups
## Supported SM Architectures ## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes ## Supported OSes
@@ -24,7 +24,7 @@ x86_64, ppc64le, armv7l
## Prerequisites ## Prerequisites
Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
## Build and Run ## Build and Run

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 14.00
# Visual Studio 2015
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "binaryPartitionCG", "binaryPartitionCG_vs2015.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -1,107 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>binaryPartitionCG_vs2015</RootNamespace>
<ProjectName>binaryPartitionCG</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v140</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/binaryPartitionCG.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemGroup>
<CudaCompile Include="binaryPartitionCG.cu" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
</ImportGroup>
</Project>

View File

@@ -38,7 +38,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -67,10 +67,11 @@
<OutputFile>$(OutDir)/binaryPartitionCG.exe</OutputFile> <OutputFile>$(OutDir)/binaryPartitionCG.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration> <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -107,6 +108,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -34,7 +34,7 @@
</PropertyGroup> </PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings"> <ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.props" />
</ImportGroup> </ImportGroup>
<ImportGroup Label="PropertySheets"> <ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" /> <Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
@@ -63,10 +63,11 @@
<OutputFile>$(OutDir)/binaryPartitionCG.exe</OutputFile> <OutputFile>$(OutDir)/binaryPartitionCG.exe</OutputFile>
</Link> </Link>
<CudaCompile> <CudaCompile>
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;</CodeGeneration> <CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions> <AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include> <Include>./;../../Common</Include>
<Defines>WIN32</Defines> <Defines>WIN32</Defines>
<AdditionalOptions>--threads 0</AdditionalOptions>
</CudaCompile> </CudaCompile>
</ItemDefinitionGroup> </ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'"> <ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
@@ -103,6 +104,6 @@
</ItemGroup> </ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" /> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets"> <ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" /> <Import Project="$(CUDAPropsPath)\CUDA 11.2.targets" />
</ImportGroup> </ImportGroup>
</Project> </Project>

View File

@@ -88,7 +88,7 @@ endif
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now. # sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
ifeq ($(HOST_ARCH),aarch64) ifeq ($(HOST_ARCH),aarch64)
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux)) ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
HOST_ARCH := sbsa HOST_ARCH := sbsa
TARGET_ARCH := sbsa TARGET_ARCH := sbsa
endif endif
@@ -146,7 +146,7 @@ else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
endif endif
export QNX_HOST export QNX_HOST
export QNX_TARGET export QNX_TARGET
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.0.0-g++ HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
else ifeq ($(TARGET_OS), android) else ifeq ($(TARGET_OS), android)
HOST_COMPILER ?= aarch64-linux-android-clang++ HOST_COMPILER ?= aarch64-linux-android-clang++
endif endif
@@ -201,24 +201,34 @@ ifneq ($(TARGET_ARCH),$(HOST_ARCH))
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
endif endif
endif endif
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx) ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
NVCCFLAGS += --qpp-config 5.4.0,gcc_ntoaarch64le
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
LDFLAGS += -lsocket LDFLAGS += -lsocket
LDFLAGS += -rpath=/usr/lib/aarch64-qnx-gnu -L/usr/lib/aarch64-qnx-gnu LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
ifneq ($(TARGET_FS),) CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
LDFLAGS += -rpath=$(TARGET_FS)/usr/lib -L $(TARGET_FS)/usr/lib ifdef TARGET_OVERRIDE
LDFLAGS += -rpath=$(TARGET_FS)/usr/libnvidia -L $(TARGET_FS)/usr/libnvidia LDFLAGS += -lslog2
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE) ifneq ($(TARGET_FS),)
LDFLAGS += -L$(TARGET_FS)/usr/lib
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
CCFLAGS += -I$(TARGET_FS)/../include
endif endif
endif endif
endif endif
ifdef TARGET_OVERRIDE # cuda toolkit targets override
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
endif
# Install directory of different arch # Install directory of different arch
CUDA_INSTALL_TARGET_DIR := CUDA_INSTALL_TARGET_DIR :=
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux) ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
@@ -291,12 +301,14 @@ GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
endif endif
endif endif
INCLUDES += -I../../Common/UtilNPP -I../../Common/FreeImage/include ALL_CCFLAGS += --threads 0
LIBRARIES += -L../../Common/FreeImage/lib/x64 -L../../Common/FreeImage/lib/$(TARGET_OS) -L../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH) -lnppisu_static -lnppif_static -lnppc_static -lculibos -lfreeimage INCLUDES += -I../../Common/UtilNPP
LIBRARIES += -lnppisu_static -lnppif_static -lnppc_static -lculibos -lfreeimage
# Attempt to compile a minimal application linked against FreeImage. If a.out exists, FreeImage is properly set up. # Attempt to compile a minimal application linked against FreeImage. If a.out exists, FreeImage is properly set up.
$(shell echo "#include \"FreeImage.h\"" > test.c; echo "int main() { return 0; }" >> test.c ; $(NVCC) $(ALL_CCFLAGS) $(INCLUDES) $(LIBRARIES) -l freeimage test.c) $(shell echo "#include \"FreeImage.h\"" > test.c; echo "int main() { return 0; }" >> test.c ; $(NVCC) $(ALL_CCFLAGS) $(INCLUDES) $(ALL_LDFLAGS) $(LIBRARIES) -l freeimage test.c)
FREEIMAGE := $(shell find a.out 2>/dev/null) FREEIMAGE := $(shell find a.out 2>/dev/null)
$(shell rm a.out test.c 2>/dev/null) $(shell rm a.out test.c 2>/dev/null)

View File

@@ -10,7 +10,7 @@
</files> </files>
<includepaths> <includepaths>
<path>../../Common/UtilNPP</path> <path>../../Common/UtilNPP</path>
<path>../../Common/FreeImage/include</path> <path os="Windows">../../Common/FreeImage/Dist/x64</path>
<path>./</path> <path>./</path>
<path>../</path> <path>../</path>
<path>../../common/inc</path> <path>../../common/inc</path>
@@ -34,8 +34,6 @@
<library>freeimage</library> <library>freeimage</library>
</libraries> </libraries>
<librarypaths> <librarypaths>
<path>../../Common/FreeImage/lib/$(TARGET_OS)</path>
<path>../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH)</path>
</librarypaths> </librarypaths>
<nsight_eclipse>true</nsight_eclipse> <nsight_eclipse>true</nsight_eclipse>
<primary_file>boxFilterNPP.cpp</primary_file> <primary_file>boxFilterNPP.cpp</primary_file>
@@ -59,6 +57,7 @@
<sm-arch>sm72</sm-arch> <sm-arch>sm72</sm-arch>
<sm-arch>sm75</sm-arch> <sm-arch>sm75</sm-arch>
<sm-arch>sm80</sm-arch> <sm-arch>sm80</sm-arch>
<sm-arch>sm86</sm-arch>
<supported_envs> <supported_envs>
<env> <env>
<arch>x86_64</arch> <arch>x86_64</arch>

View File

@@ -10,7 +10,7 @@ Performance Strategies, Image Processing, NPP Library
## Supported SM Architectures ## Supported SM Architectures
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
## Supported OSes ## Supported OSes
@@ -27,7 +27,7 @@ x86_64, ppc64le, armv7l
## Prerequisites ## Prerequisites
Download and install the [CUDA Toolkit 11.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform. Download and install the [CUDA Toolkit 11.2](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
Make sure the dependencies mentioned in [Dependencies]() section above are installed. Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## Build and Run ## Build and Run

View File

@@ -1,20 +0,0 @@

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 2012
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "boxFilterNPP", "boxFilterNPP_vs2012.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Release|x64 = Release|x64
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal

View File

@@ -1,117 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
</PropertyGroup>
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
<RootNamespace>boxFilterNPP_vs2012</RootNamespace>
<ProjectName>boxFilterNPP</ProjectName>
<CudaToolkitCustomDir />
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup>
<ConfigurationType>Application</ConfigurationType>
<CharacterSet>MultiByte</CharacterSet>
<PlatformToolset>v110</PlatformToolset>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
<UseDebugLibraries>true</UseDebugLibraries>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)'=='Release'">
<WholeProgramOptimization>true</WholeProgramOptimization>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets">
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup>
<IntDir>$(Platform)/$(Configuration)/</IntDir>
<IncludePath>$(IncludePath)</IncludePath>
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
<CodeAnalysisRules />
<CodeAnalysisRuleAssemblies />
</PropertyGroup>
<PropertyGroup Condition="'$(Platform)'=='x64'">
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
</PropertyGroup>
<ItemDefinitionGroup>
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);../../Common/UtilNPP;../../Common/FreeImage/include;</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<AdditionalDependencies>nppisu.lib;nppif.lib;nppc.lib;cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/FreeImage/lib/x64;../../Common/FreeImage/lib/$(TARGET_OS);../../Common/FreeImage/lib/$(TARGET_OS)/$(TARGET_ARCH);</AdditionalLibraryDirectories>
<OutputFile>$(OutDir)/boxFilterNPP.exe</OutputFile>
</Link>
<CudaCompile>
<CodeGeneration>compute_35,compute_35;</CodeGeneration>
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
<Include>./;../../Common</Include>
<Defines>WIN32</Defines>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
<ClCompile>
<Optimization>Disabled</Optimization>
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>true</GenerateDebugInformation>
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MTd</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
<ClCompile>
<Optimization>MaxSpeed</Optimization>
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
</ClCompile>
<Link>
<GenerateDebugInformation>false</GenerateDebugInformation>
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
</Link>
<CudaCompile>
<Runtime>MT</Runtime>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
<Link>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
<Link>
<AdditionalDependencies>freeimage.lib;%(AdditionalDependencies)</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="boxFilterNPP.cpp" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
<Import Project="$(CUDAPropsPath)\CUDA 11.0.targets" />
</ImportGroup>
</Project>

Some files were not shown because too many files have changed in this diff Show More