mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2026-10-23 21:28:17 +08:00
add and update samples for CUDA 11.6
This commit is contained in:
Rutwik Choughule
18
Samples/0_Introduction/simpleCUDA2GL/.vscode/c_cpp_properties.json
vendored
Normal file
18
Samples/0_Introduction/simpleCUDA2GL/.vscode/c_cpp_properties.json
vendored
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"configurations": [
|
||||
{
|
||||
"name": "Linux",
|
||||
"includePath": [
|
||||
"${workspaceFolder}/**",
|
||||
"${workspaceFolder}/../../../Common"
|
||||
],
|
||||
"defines": [],
|
||||
"compilerPath": "/usr/local/cuda/bin/nvcc",
|
||||
"cStandard": "gnu17",
|
||||
"cppStandard": "gnu++14",
|
||||
"intelliSenseMode": "linux-gcc-x64",
|
||||
"configurationProvider": "ms-vscode.makefile-tools"
|
||||
}
|
||||
],
|
||||
"version": 4
|
||||
}
|
||||
7
Samples/0_Introduction/simpleCUDA2GL/.vscode/extensions.json
vendored
Normal file
7
Samples/0_Introduction/simpleCUDA2GL/.vscode/extensions.json
vendored
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"recommendations": [
|
||||
"nvidia.nsight-vscode-edition",
|
||||
"ms-vscode.cpptools",
|
||||
"ms-vscode.makefile-tools"
|
||||
]
|
||||
}
|
||||
10
Samples/0_Introduction/simpleCUDA2GL/.vscode/launch.json
vendored
Normal file
10
Samples/0_Introduction/simpleCUDA2GL/.vscode/launch.json
vendored
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"configurations": [
|
||||
{
|
||||
"name": "CUDA C++: Launch",
|
||||
"type": "cuda-gdb",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/simpleCUDA2GL"
|
||||
}
|
||||
]
|
||||
}
|
||||
15
Samples/0_Introduction/simpleCUDA2GL/.vscode/tasks.json
vendored
Normal file
15
Samples/0_Introduction/simpleCUDA2GL/.vscode/tasks.json
vendored
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"version": "2.0.0",
|
||||
"tasks": [
|
||||
{
|
||||
"label": "sample",
|
||||
"type": "shell",
|
||||
"command": "make dbg=1",
|
||||
"problemMatcher": ["$nvcc"],
|
||||
"group": {
|
||||
"kind": "build",
|
||||
"isDefault": true
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
376
Samples/0_Introduction/simpleCUDA2GL/Makefile
Normal file
376
Samples/0_Introduction/simpleCUDA2GL/Makefile
Normal file
@@ -0,0 +1,376 @@
|
||||
################################################################################
|
||||
# Copyright (c) 2022, 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 += -D_QNX_SOURCE
|
||||
NVCCFLAGS += --qpp-config 8.3.0,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 ARMv7
|
||||
ifeq ($(TARGET_ARCH),armv7l)
|
||||
$(info >>> WARNING - simpleCUDA2GL is not supported on ARMv7 - waiving sample <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
|
||||
# This sample is not supported on aarch64
|
||||
ifeq ($(TARGET_ARCH),aarch64)
|
||||
$(info >>> WARNING - simpleCUDA2GL is not supported on aarch64 - waiving sample <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
|
||||
# This sample is not supported on sbsa
|
||||
ifeq ($(TARGET_ARCH),sbsa)
|
||||
$(info >>> WARNING - simpleCUDA2GL is not supported on sbsa - 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 :=
|
||||
|
||||
################################################################################
|
||||
|
||||
# Makefile include to help find GL Libraries
|
||||
include ./findgllib.mk
|
||||
|
||||
# OpenGL specific libraries
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
# Mac OSX specific libraries and paths to include
|
||||
LIBRARIES += -L/System/Library/Frameworks/OpenGL.framework/Libraries
|
||||
LIBRARIES += -lGL -lGLU
|
||||
ALL_LDFLAGS += -Xlinker -framework -Xlinker GLUT
|
||||
else
|
||||
LIBRARIES += $(GLLINK)
|
||||
LIBRARIES += -lGL -lGLU -lglut
|
||||
endif
|
||||
|
||||
# Gencode arguments
|
||||
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
|
||||
SMS ?= 53 61 70 72 75 80 86 87
|
||||
else
|
||||
SMS ?= 35 37 50 52 60 61 70 75 80 86
|
||||
endif
|
||||
|
||||
ifeq ($(SMS),)
|
||||
$(info >>> WARNING - no SM architectures have been specified - waiving sample <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
|
||||
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)))
|
||||
|
||||
# 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 --std=c++11
|
||||
|
||||
ifeq ($(SAMPLE_ENABLED),0)
|
||||
EXEC ?= @echo "[@]"
|
||||
endif
|
||||
|
||||
################################################################################
|
||||
|
||||
# Target rules
|
||||
all: build
|
||||
|
||||
build: simpleCUDA2GL
|
||||
|
||||
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
|
||||
|
||||
main.o:main.cpp
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
simpleCUDA2GL.o:simpleCUDA2GL.cu
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
simpleCUDA2GL: main.o simpleCUDA2GL.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) ./simpleCUDA2GL
|
||||
|
||||
testrun: build
|
||||
$(EXEC) ./simpleCUDA2GL -file=ref_simpleCUDA2GL.ppm
|
||||
|
||||
clean:
|
||||
rm -f simpleCUDA2GL main.o simpleCUDA2GL.o
|
||||
rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/simpleCUDA2GL
|
||||
|
||||
clobber: clean
|
||||
100
Samples/0_Introduction/simpleCUDA2GL/NsightEclipse.xml
Normal file
100
Samples/0_Introduction/simpleCUDA2GL/NsightEclipse.xml
Normal file
@@ -0,0 +1,100 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
||||
<entry>
|
||||
<name>simpleCUDA2GL</name>
|
||||
<cuda_api_list>
|
||||
<toolkit>cudaFree</toolkit>
|
||||
<toolkit>cudaGraphicsMapResources</toolkit>
|
||||
<toolkit>cudaGraphicsUnregisterResource</toolkit>
|
||||
<toolkit>cudaMemcpyToArray</toolkit>
|
||||
<toolkit>cudaGraphicsGLRegisterBuffer</toolkit>
|
||||
<toolkit>cudaHostAlloc</toolkit>
|
||||
<toolkit>cudaGraphicsResourceGetMappedPointer</toolkit>
|
||||
<toolkit>cudaProcess</toolkit>
|
||||
<toolkit>cudaDeviceSynchronize</toolkit>
|
||||
<toolkit>cudaMalloc</toolkit>
|
||||
<toolkit>cudaGraphicsSubResourceGetMappedArray</toolkit>
|
||||
<toolkit>cudaGraphicsGLRegisterImage</toolkit>
|
||||
<toolkit>cudaGraphicsUnmapResources</toolkit>
|
||||
</cuda_api_list>
|
||||
<description><![CDATA[This sample shows how to copy CUDA image back to OpenGL using the most efficient methods.]]></description>
|
||||
<devicecompilation>whole</devicecompilation>
|
||||
<files>
|
||||
<file>data\ref_simpleCUDA2GL.ppm</file>
|
||||
</files>
|
||||
<includepaths>
|
||||
<path>./</path>
|
||||
<path>../</path>
|
||||
<path>../../../Common</path>
|
||||
</includepaths>
|
||||
<keyconcepts>
|
||||
<concept level="basic">Graphics Interop</concept>
|
||||
<concept level="basic">Image Processing</concept>
|
||||
<concept level="basic">Performance Strategies</concept>
|
||||
</keyconcepts>
|
||||
<keywords>
|
||||
<keyword>GPGPU</keyword>
|
||||
<keyword>CUDA</keyword>
|
||||
<keyword>Image Processing</keyword>
|
||||
<keyword>Opengl</keyword>
|
||||
<keyword>openGL</keyword>
|
||||
</keywords>
|
||||
<libraries>
|
||||
<library>GLU</library>
|
||||
<library>GL</library>
|
||||
<library framework="true" os="macosx">GLUT</library>
|
||||
<library os="linux">GLEW</library>
|
||||
<library os="linux">glut</library>
|
||||
<library os="linux">X11</library>
|
||||
</libraries>
|
||||
<librarypaths>
|
||||
<path arch="x86_64" os="linux">../../../common/lib/linux/x86_64</path>
|
||||
<path arch="armv7l" os="linux">../../../common/lib/linux/armv7l</path>
|
||||
<path os="macosx">../../../common/lib/darwin</path>
|
||||
</librarypaths>
|
||||
<nsight_eclipse>true</nsight_eclipse>
|
||||
<primary_file>main.cpp</primary_file>
|
||||
<qatests>
|
||||
<qatest>-file=ref_simpleCUDA2GL.ppm</qatest>
|
||||
</qatests>
|
||||
<required_dependencies>
|
||||
<dependency>X11</dependency>
|
||||
<dependency>GL</dependency>
|
||||
</required_dependencies>
|
||||
<scopes>
|
||||
<scope>2:Graphics Interop</scope>
|
||||
<scope>2:Image Processing</scope>
|
||||
<scope>2:Performance Strategies</scope>
|
||||
</scopes>
|
||||
<sm-arch>sm35</sm-arch>
|
||||
<sm-arch>sm37</sm-arch>
|
||||
<sm-arch>sm50</sm-arch>
|
||||
<sm-arch>sm52</sm-arch>
|
||||
<sm-arch>sm53</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>
|
||||
<sm-arch>sm87</sm-arch>
|
||||
<supported_envs>
|
||||
<env>
|
||||
<arch>x86_64</arch>
|
||||
<platform>linux</platform>
|
||||
</env>
|
||||
<env>
|
||||
<platform>windows7</platform>
|
||||
</env>
|
||||
<env>
|
||||
<arch>x86_64</arch>
|
||||
<platform>macosx</platform>
|
||||
</env>
|
||||
</supported_envs>
|
||||
<supported_sm_architectures>
|
||||
<include>all</include>
|
||||
</supported_sm_architectures>
|
||||
<title>CUDA and OpenGL Interop of Images</title>
|
||||
<type>exe</type>
|
||||
</entry>
|
||||
74
Samples/0_Introduction/simpleCUDA2GL/README.md
Normal file
74
Samples/0_Introduction/simpleCUDA2GL/README.md
Normal file
@@ -0,0 +1,74 @@
|
||||
# simpleCUDA2GL - CUDA and OpenGL Interop of Images
|
||||
|
||||
## Description
|
||||
|
||||
This sample shows how to copy CUDA image back to OpenGL using the most efficient methods.
|
||||
|
||||
## Key Concepts
|
||||
|
||||
Graphics Interop, Image Processing, Performance Strategies
|
||||
|
||||
## 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 5.3 ](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) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
|
||||
|
||||
## Supported OSes
|
||||
|
||||
Linux, Windows
|
||||
|
||||
## Supported CPU Architecture
|
||||
|
||||
x86_64
|
||||
|
||||
## CUDA APIs involved
|
||||
|
||||
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
|
||||
cudaFree, cudaGraphicsMapResources, cudaGraphicsUnregisterResource, cudaMemcpyToArray, cudaGraphicsGLRegisterBuffer, cudaHostAlloc, cudaGraphicsResourceGetMappedPointer, cudaProcess, cudaDeviceSynchronize, cudaMalloc, cudaGraphicsSubResourceGetMappedArray, cudaGraphicsGLRegisterImage, cudaGraphicsUnmapResources
|
||||
|
||||
## Dependencies needed to build/run
|
||||
[X11](../../README.md#x11), [GL](../../README.md#gl)
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Download and install the [CUDA Toolkit 11.6](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.
|
||||
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/>
|
||||
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)
|
||||
|
||||
BIN
Samples/0_Introduction/simpleCUDA2GL/data/ref_simpleCUDA2GL.ppm
Normal file
BIN
Samples/0_Introduction/simpleCUDA2GL/data/ref_simpleCUDA2GL.ppm
Normal file
Binary file not shown.
145
Samples/0_Introduction/simpleCUDA2GL/findgllib.mk
Normal file
145
Samples/0_Introduction/simpleCUDA2GL/findgllib.mk
Normal file
@@ -0,0 +1,145 @@
|
||||
################################################################################
|
||||
# Copyright (c) 2022, 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.
|
||||
#
|
||||
################################################################################
|
||||
#
|
||||
# findgllib.mk is used to find the necessary GL Libraries for specific distributions
|
||||
# this is supported on Mac OSX and Linux Platforms
|
||||
#
|
||||
################################################################################
|
||||
|
||||
# Determine OS platform and unix distribution
|
||||
ifeq ("$(TARGET_OS)","linux")
|
||||
# first search lsb_release
|
||||
DISTRO := $(shell lsb_release -i -s 2>/dev/null | tr "[:upper:]" "[:lower:]")
|
||||
ifeq ("$(DISTRO)","")
|
||||
# second search and parse /etc/issue
|
||||
DISTRO := $(shell awk '{print $$1}' /etc/issue | tr -d "[:space:]" | sed -e "/^$$/d" | tr "[:upper:]" "[:lower:]")
|
||||
# ensure data from /etc/issue is valid
|
||||
ifeq (,$(filter $(DISTRO),ubuntu fedora red rhel centos suse))
|
||||
DISTRO :=
|
||||
endif
|
||||
ifeq ("$(DISTRO)","")
|
||||
# third, we can search in /etc/os-release or /etc/{distro}-release
|
||||
DISTRO := $(shell awk '/ID/' /etc/*-release | sed 's/ID=//' | grep -v "VERSION" | grep -v "ID" | grep -v "DISTRIB")
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
ifeq ("$(TARGET_OS)","linux")
|
||||
# $(info) >> findgllib.mk -> LINUX path <<<)
|
||||
# Each set of Linux Distros have different paths for where to find their OpenGL libraries reside
|
||||
UBUNTU = $(shell echo $(DISTRO) | grep -i ubuntu >/dev/null 2>&1; echo $$?)
|
||||
FEDORA = $(shell echo $(DISTRO) | grep -i fedora >/dev/null 2>&1; echo $$?)
|
||||
RHEL = $(shell echo $(DISTRO) | grep -i 'red\|rhel' >/dev/null 2>&1; echo $$?)
|
||||
CENTOS = $(shell echo $(DISTRO) | grep -i centos >/dev/null 2>&1; echo $$?)
|
||||
SUSE = $(shell echo $(DISTRO) | grep -i 'suse\|sles' >/dev/null 2>&1; echo $$?)
|
||||
ifeq ("$(UBUNTU)","0")
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l)
|
||||
GLPATH := /usr/arm-linux-gnueabihf/lib
|
||||
GLLINK := -L/usr/arm-linux-gnueabihf/lib
|
||||
ifneq ($(TARGET_FS),)
|
||||
GLPATH += $(TARGET_FS)/usr/lib/arm-linux-gnueabihf
|
||||
GLLINK += -L$(TARGET_FS)/usr/lib/arm-linux-gnueabihf
|
||||
endif
|
||||
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-aarch64)
|
||||
GLPATH := /usr/aarch64-linux-gnu/lib
|
||||
GLLINK := -L/usr/aarch64-linux-gnu/lib
|
||||
ifneq ($(TARGET_FS),)
|
||||
GLPATH += $(TARGET_FS)/usr/lib
|
||||
GLPATH += $(TARGET_FS)/usr/lib/aarch64-linux-gnu
|
||||
GLLINK += -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
|
||||
endif
|
||||
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-ppc64le)
|
||||
GLPATH := /usr/powerpc64le-linux-gnu/lib
|
||||
GLLINK := -L/usr/powerpc64le-linux-gnu/lib
|
||||
else
|
||||
UBUNTU_PKG_NAME = $(shell which dpkg >/dev/null 2>&1 && dpkg -l 'nvidia-*' | grep '^ii' | awk '{print $$2}' | head -1)
|
||||
ifneq ("$(UBUNTU_PKG_NAME)","")
|
||||
GLPATH ?= /usr/lib/$(UBUNTU_PKG_NAME)
|
||||
GLLINK ?= -L/usr/lib/$(UBUNTU_PKG_NAME)
|
||||
endif
|
||||
|
||||
DFLT_PATH ?= /usr/lib
|
||||
endif
|
||||
endif
|
||||
ifeq ("$(SUSE)","0")
|
||||
GLPATH ?= /usr/X11R6/lib64
|
||||
GLLINK ?= -L/usr/X11R6/lib64
|
||||
DFLT_PATH ?= /usr/lib64
|
||||
endif
|
||||
ifeq ("$(FEDORA)","0")
|
||||
GLPATH ?= /usr/lib64/nvidia
|
||||
GLLINK ?= -L/usr/lib64/nvidia
|
||||
DFLT_PATH ?= /usr/lib64
|
||||
endif
|
||||
ifeq ("$(RHEL)","0")
|
||||
GLPATH ?= /usr/lib64/nvidia
|
||||
GLLINK ?= -L/usr/lib64/nvidia
|
||||
DFLT_PATH ?= /usr/lib64
|
||||
endif
|
||||
ifeq ("$(CENTOS)","0")
|
||||
GLPATH ?= /usr/lib64/nvidia
|
||||
GLLINK ?= -L/usr/lib64/nvidia
|
||||
DFLT_PATH ?= /usr/lib64
|
||||
endif
|
||||
|
||||
# find libGL, libGLU
|
||||
GLLIB := $(shell find -L $(GLPATH) $(DFLT_PATH) -name libGL.so -print 2>/dev/null)
|
||||
GLULIB := $(shell find -L $(GLPATH) $(DFLT_PATH) -name libGLU.so -print 2>/dev/null)
|
||||
|
||||
ifeq ("$(GLLIB)","")
|
||||
$(info >>> WARNING - libGL.so not found, refer to CUDA Getting Started Guide for how to find and install them. <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
ifeq ("$(GLULIB)","")
|
||||
$(info >>> WARNING - libGLU.so not found, refer to CUDA Getting Started Guide for how to find and install them. <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
|
||||
HEADER_SEARCH_PATH ?= $(TARGET_FS)/usr/include
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-armv7l-linux)
|
||||
HEADER_SEARCH_PATH += /usr/arm-linux-gnueabihf/include
|
||||
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-aarch64-linux)
|
||||
HEADER_SEARCH_PATH += /usr/aarch64-linux-gnu/include
|
||||
endif
|
||||
|
||||
GLHEADER := $(shell find -L $(HEADER_SEARCH_PATH) -name gl.h -print 2>/dev/null)
|
||||
GLUHEADER := $(shell find -L $(HEADER_SEARCH_PATH) -name glu.h -print 2>/dev/null)
|
||||
|
||||
ifeq ("$(GLHEADER)","")
|
||||
$(info >>> WARNING - gl.h not found, refer to CUDA Getting Started Guide for how to find and install them. <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
ifeq ("$(GLUHEADER)","")
|
||||
$(info >>> WARNING - glu.h not found, refer to CUDA Getting Started Guide for how to find and install them. <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
else
|
||||
# This would be the Mac OS X path if we had to do anything special
|
||||
endif
|
||||
|
||||
747
Samples/0_Introduction/simpleCUDA2GL/main.cpp
Normal file
747
Samples/0_Introduction/simpleCUDA2GL/main.cpp
Normal file
@@ -0,0 +1,747 @@
|
||||
/* Copyright (c) 2022, 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.
|
||||
*/
|
||||
|
||||
// USE_TEXSUBIMAGE2D uses glTexSubImage2D() to update the final result
|
||||
// commenting it will make the sample use the other way :
|
||||
// map a texture in CUDA and blit the result into it
|
||||
#define USE_TEXSUBIMAGE2D
|
||||
|
||||
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
|
||||
#define WINDOWS_LEAN_AND_MEAN
|
||||
#define NOMINMAX
|
||||
#include <windows.h>
|
||||
#pragma warning(disable : 4996)
|
||||
#endif
|
||||
|
||||
// OpenGL Graphics includes
|
||||
#include <helper_gl.h>
|
||||
#if defined(__APPLE__) || defined(MACOSX)
|
||||
#pragma clang diagnostic ignored "-Wdeprecated-declarations"
|
||||
#include <GLUT/glut.h>
|
||||
// Sorry for Apple : unsigned int sampler is not available to you, yet...
|
||||
// Let's switch to the use of PBO and glTexSubImage
|
||||
#define USE_TEXSUBIMAGE2D
|
||||
#else
|
||||
#include <GL/freeglut.h>
|
||||
#endif
|
||||
|
||||
// CUDA includes
|
||||
#include <cuda_runtime.h>
|
||||
#include <cuda_gl_interop.h>
|
||||
|
||||
// CUDA utilities and system includes
|
||||
#include <helper_cuda.h>
|
||||
#include <helper_functions.h>
|
||||
#include <rendercheck_gl.h>
|
||||
|
||||
// Shared Library Test Functions
|
||||
#define MAX_EPSILON 10
|
||||
#define REFRESH_DELAY 10 // ms
|
||||
|
||||
const char *sSDKname = "simpleCUDA2GL";
|
||||
|
||||
unsigned int g_TotalErrors = 0;
|
||||
|
||||
// CheckFBO/BackBuffer class objects
|
||||
CheckRender *g_CheckRender = NULL;
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// constants / global variables
|
||||
unsigned int window_width = 512;
|
||||
unsigned int window_height = 512;
|
||||
unsigned int image_width = 512;
|
||||
unsigned int image_height = 512;
|
||||
int iGLUTWindowHandle = 0; // handle to the GLUT window
|
||||
|
||||
// pbo and fbo variables
|
||||
#ifdef USE_TEXSUBIMAGE2D
|
||||
GLuint pbo_dest;
|
||||
struct cudaGraphicsResource *cuda_pbo_dest_resource;
|
||||
#else
|
||||
unsigned int *cuda_dest_resource;
|
||||
GLuint shDrawTex; // draws a texture
|
||||
struct cudaGraphicsResource *cuda_tex_result_resource;
|
||||
#endif
|
||||
|
||||
GLuint fbo_source;
|
||||
struct cudaGraphicsResource *cuda_tex_screen_resource;
|
||||
|
||||
unsigned int size_tex_data;
|
||||
unsigned int num_texels;
|
||||
unsigned int num_values;
|
||||
|
||||
// (offscreen) render target fbo variables
|
||||
GLuint tex_screen; // where we render the image
|
||||
GLuint tex_cudaResult; // where we will copy the CUDA result
|
||||
|
||||
char *ref_file = NULL;
|
||||
bool enable_cuda = true;
|
||||
|
||||
int *pArgc = NULL;
|
||||
char **pArgv = NULL;
|
||||
|
||||
// Timer
|
||||
static int fpsCount = 0;
|
||||
static int fpsLimit = 1;
|
||||
StopWatchInterface *timer = NULL;
|
||||
|
||||
#ifndef USE_TEXTURE_RGBA8UI
|
||||
#pragma message("Note: Using Texture fmt GL_RGBA16F_ARB")
|
||||
#else
|
||||
// NOTE: the current issue with regular RGBA8 internal format of textures
|
||||
// is that HW stores them as BGRA8. Therefore CUDA will see BGRA where users
|
||||
// expected RGBA8. To prevent this issue, the driver team decided to prevent
|
||||
// this to happen
|
||||
// instead, use RGBA8UI which required the additional work of scaling the
|
||||
// fragment shader
|
||||
// output from 0-1 to 0-255. This is why we have some GLSL code, in this case
|
||||
#pragma message("Note: Using Texture RGBA8UI + GLSL for rendering")
|
||||
#endif
|
||||
GLuint shDraw;
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
extern "C" void launch_cudaProcess(dim3 grid, dim3 block, int sbytes,
|
||||
unsigned int *g_odata, int imgw);
|
||||
|
||||
// Forward declarations
|
||||
void runStdProgram(int argc, char **argv);
|
||||
void FreeResource();
|
||||
void Cleanup(int iExitCode);
|
||||
|
||||
// GL functionality
|
||||
bool initGL(int *argc, char **argv);
|
||||
|
||||
#ifdef USE_TEXSUBIMAGE2D
|
||||
void createPBO(GLuint *pbo, struct cudaGraphicsResource **pbo_resource);
|
||||
void deletePBO(GLuint *pbo);
|
||||
#endif
|
||||
|
||||
void createTextureDst(GLuint *tex_cudaResult, unsigned int size_x,
|
||||
unsigned int size_y);
|
||||
void deleteTexture(GLuint *tex);
|
||||
|
||||
// rendering callbacks
|
||||
void display();
|
||||
void idle();
|
||||
void keyboard(unsigned char key, int x, int y);
|
||||
void reshape(int w, int h);
|
||||
void mainMenu(int i);
|
||||
|
||||
#ifdef USE_TEXSUBIMAGE2D
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Create PBO
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void createPBO(GLuint *pbo, struct cudaGraphicsResource **pbo_resource) {
|
||||
// set up vertex data parameter
|
||||
num_texels = image_width * image_height;
|
||||
num_values = num_texels * 4;
|
||||
size_tex_data = sizeof(GLubyte) * num_values;
|
||||
void *data = malloc(size_tex_data);
|
||||
|
||||
// create buffer object
|
||||
glGenBuffers(1, pbo);
|
||||
glBindBuffer(GL_ARRAY_BUFFER, *pbo);
|
||||
glBufferData(GL_ARRAY_BUFFER, size_tex_data, data, GL_DYNAMIC_DRAW);
|
||||
free(data);
|
||||
|
||||
glBindBuffer(GL_ARRAY_BUFFER, 0);
|
||||
|
||||
// register this buffer object with CUDA
|
||||
checkCudaErrors(cudaGraphicsGLRegisterBuffer(pbo_resource, *pbo,
|
||||
cudaGraphicsMapFlagsNone));
|
||||
|
||||
SDK_CHECK_ERROR_GL();
|
||||
}
|
||||
|
||||
void deletePBO(GLuint *pbo) {
|
||||
glDeleteBuffers(1, pbo);
|
||||
SDK_CHECK_ERROR_GL();
|
||||
*pbo = 0;
|
||||
}
|
||||
#endif
|
||||
|
||||
const GLenum fbo_targets[] = {
|
||||
GL_COLOR_ATTACHMENT0_EXT, GL_COLOR_ATTACHMENT1_EXT,
|
||||
GL_COLOR_ATTACHMENT2_EXT, GL_COLOR_ATTACHMENT3_EXT};
|
||||
|
||||
#ifndef USE_TEXSUBIMAGE2D
|
||||
static const char *glsl_drawtex_vertshader_src =
|
||||
"void main(void)\n"
|
||||
"{\n"
|
||||
" gl_Position = gl_Vertex;\n"
|
||||
" gl_TexCoord[0].xy = gl_MultiTexCoord0.xy;\n"
|
||||
"}\n";
|
||||
|
||||
static const char *glsl_drawtex_fragshader_src =
|
||||
"#version 130\n"
|
||||
"uniform usampler2D texImage;\n"
|
||||
"void main()\n"
|
||||
"{\n"
|
||||
" vec4 c = texture(texImage, gl_TexCoord[0].xy);\n"
|
||||
" gl_FragColor = c / 255.0;\n"
|
||||
"}\n";
|
||||
#endif
|
||||
|
||||
static const char *glsl_draw_fragshader_src =
|
||||
// WARNING: seems like the gl_FragColor doesn't want to output >1 colors...
|
||||
// you need version 1.3 so you can define a uvec4 output...
|
||||
// but MacOSX complains about not supporting 1.3 !!
|
||||
// for now, the mode where we use RGBA8UI may not work properly for Apple : only
|
||||
// RGBA16F works (default)
|
||||
#if defined(__APPLE__) || defined(MACOSX)
|
||||
"void main()\n"
|
||||
"{"
|
||||
" gl_FragColor = vec4(gl_Color * 255.0);\n"
|
||||
"}\n";
|
||||
#else
|
||||
"#version 130\n"
|
||||
"out uvec4 FragColor;\n"
|
||||
"void main()\n"
|
||||
"{"
|
||||
" FragColor = uvec4(gl_Color.xyz * 255.0, 255.0);\n"
|
||||
"}\n";
|
||||
#endif
|
||||
|
||||
// copy image and process using CUDA
|
||||
void generateCUDAImage() {
|
||||
// run the Cuda kernel
|
||||
unsigned int *out_data;
|
||||
|
||||
#ifdef USE_TEXSUBIMAGE2D
|
||||
checkCudaErrors(cudaGraphicsMapResources(1, &cuda_pbo_dest_resource, 0));
|
||||
size_t num_bytes;
|
||||
checkCudaErrors(cudaGraphicsResourceGetMappedPointer(
|
||||
(void **)&out_data, &num_bytes, cuda_pbo_dest_resource));
|
||||
// printf("CUDA mapped pointer of pbo_out: May access %ld bytes, expected %d\n",
|
||||
// num_bytes, size_tex_data);
|
||||
#else
|
||||
out_data = cuda_dest_resource;
|
||||
#endif
|
||||
// calculate grid size
|
||||
dim3 block(16, 16, 1);
|
||||
// dim3 block(16, 16, 1);
|
||||
dim3 grid(image_width / block.x, image_height / block.y, 1);
|
||||
// execute CUDA kernel
|
||||
launch_cudaProcess(grid, block, 0, out_data, image_width);
|
||||
|
||||
// CUDA generated data in cuda memory or in a mapped PBO made of BGRA 8 bits
|
||||
// 2 solutions, here :
|
||||
// - use glTexSubImage2D(), there is the potential to loose performance in
|
||||
// possible hidden conversion
|
||||
// - map the texture and blit the result thanks to CUDA API
|
||||
#ifdef USE_TEXSUBIMAGE2D
|
||||
checkCudaErrors(cudaGraphicsUnmapResources(1, &cuda_pbo_dest_resource, 0));
|
||||
glBindBuffer(GL_PIXEL_UNPACK_BUFFER_ARB, pbo_dest);
|
||||
|
||||
glBindTexture(GL_TEXTURE_2D, tex_cudaResult);
|
||||
glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, image_width, image_height, GL_RGBA,
|
||||
GL_UNSIGNED_BYTE, NULL);
|
||||
SDK_CHECK_ERROR_GL();
|
||||
glBindBuffer(GL_PIXEL_PACK_BUFFER_ARB, 0);
|
||||
glBindBuffer(GL_PIXEL_UNPACK_BUFFER_ARB, 0);
|
||||
#else
|
||||
// We want to copy cuda_dest_resource data to the texture
|
||||
// map buffer objects to get CUDA device pointers
|
||||
cudaArray *texture_ptr;
|
||||
checkCudaErrors(cudaGraphicsMapResources(1, &cuda_tex_result_resource, 0));
|
||||
checkCudaErrors(cudaGraphicsSubResourceGetMappedArray(
|
||||
&texture_ptr, cuda_tex_result_resource, 0, 0));
|
||||
|
||||
int num_texels = image_width * image_height;
|
||||
int num_values = num_texels * 4;
|
||||
int size_tex_data = sizeof(GLubyte) * num_values;
|
||||
checkCudaErrors(cudaMemcpyToArray(texture_ptr, 0, 0, cuda_dest_resource,
|
||||
size_tex_data, cudaMemcpyDeviceToDevice));
|
||||
|
||||
checkCudaErrors(cudaGraphicsUnmapResources(1, &cuda_tex_result_resource, 0));
|
||||
#endif
|
||||
}
|
||||
|
||||
// display image to the screen as textured quad
|
||||
void displayImage(GLuint texture) {
|
||||
glBindTexture(GL_TEXTURE_2D, texture);
|
||||
glEnable(GL_TEXTURE_2D);
|
||||
glDisable(GL_DEPTH_TEST);
|
||||
glDisable(GL_LIGHTING);
|
||||
glTexEnvf(GL_TEXTURE_ENV, GL_TEXTURE_ENV_MODE, GL_REPLACE);
|
||||
|
||||
glMatrixMode(GL_PROJECTION);
|
||||
glPushMatrix();
|
||||
glLoadIdentity();
|
||||
glOrtho(-1.0, 1.0, -1.0, 1.0, -1.0, 1.0);
|
||||
|
||||
glMatrixMode(GL_MODELVIEW);
|
||||
glLoadIdentity();
|
||||
|
||||
glViewport(0, 0, window_width, window_height);
|
||||
|
||||
// if the texture is a 8 bits UI, scale the fetch with a GLSL shader
|
||||
#ifndef USE_TEXSUBIMAGE2D
|
||||
glUseProgram(shDrawTex);
|
||||
GLint id = glGetUniformLocation(shDrawTex, "texImage");
|
||||
glUniform1i(id, 0); // texture unit 0 to "texImage"
|
||||
SDK_CHECK_ERROR_GL();
|
||||
#endif
|
||||
|
||||
glBegin(GL_QUADS);
|
||||
glTexCoord2f(0.0, 0.0);
|
||||
glVertex3f(-1.0, -1.0, 0.5);
|
||||
glTexCoord2f(1.0, 0.0);
|
||||
glVertex3f(1.0, -1.0, 0.5);
|
||||
glTexCoord2f(1.0, 1.0);
|
||||
glVertex3f(1.0, 1.0, 0.5);
|
||||
glTexCoord2f(0.0, 1.0);
|
||||
glVertex3f(-1.0, 1.0, 0.5);
|
||||
glEnd();
|
||||
|
||||
glMatrixMode(GL_PROJECTION);
|
||||
glPopMatrix();
|
||||
|
||||
glDisable(GL_TEXTURE_2D);
|
||||
|
||||
#ifndef USE_TEXSUBIMAGE2D
|
||||
glUseProgram(0);
|
||||
#endif
|
||||
SDK_CHECK_ERROR_GL();
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Display callback
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void display() {
|
||||
sdkStartTimer(&timer);
|
||||
|
||||
if (enable_cuda) {
|
||||
generateCUDAImage();
|
||||
displayImage(tex_cudaResult);
|
||||
}
|
||||
|
||||
// NOTE: I needed to add this call so the timing is consistent.
|
||||
// Need to investigate why
|
||||
cudaDeviceSynchronize();
|
||||
sdkStopTimer(&timer);
|
||||
|
||||
// flip backbuffer
|
||||
glutSwapBuffers();
|
||||
|
||||
// If specified, Check rendering against reference,
|
||||
if (ref_file && g_CheckRender && g_CheckRender->IsQAReadback()) {
|
||||
static int pass = 0;
|
||||
|
||||
if (pass > 0) {
|
||||
g_CheckRender->readback(window_width, window_height);
|
||||
char currentOutputPPM[256];
|
||||
sprintf(currentOutputPPM, "kilt.ppm");
|
||||
g_CheckRender->savePPM(currentOutputPPM, true, NULL);
|
||||
|
||||
if (!g_CheckRender->PPMvsPPM(currentOutputPPM,
|
||||
sdkFindFilePath(ref_file, pArgv[0]),
|
||||
MAX_EPSILON, 0.30f)) {
|
||||
g_TotalErrors++;
|
||||
}
|
||||
|
||||
Cleanup((g_TotalErrors == 0) ? EXIT_SUCCESS : EXIT_FAILURE);
|
||||
}
|
||||
|
||||
pass++;
|
||||
}
|
||||
|
||||
// Update fps counter, fps/title display and log
|
||||
if (++fpsCount == fpsLimit) {
|
||||
char cTitle[256];
|
||||
float fps = 1000.0f / sdkGetAverageTimerValue(&timer);
|
||||
sprintf(cTitle, "CUDA GL Post Processing (%d x %d): %.1f fps", window_width,
|
||||
window_height, fps);
|
||||
glutSetWindowTitle(cTitle);
|
||||
// printf("%s\n", cTitle);
|
||||
fpsCount = 0;
|
||||
fpsLimit = (int)((fps > 1.0f) ? fps : 1.0f);
|
||||
sdkResetTimer(&timer);
|
||||
}
|
||||
}
|
||||
|
||||
void timerEvent(int value) {
|
||||
glutPostRedisplay();
|
||||
glutTimerFunc(REFRESH_DELAY, timerEvent, 0);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Keyboard events handler
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void keyboard(unsigned char key, int /*x*/, int /*y*/) {
|
||||
switch (key) {
|
||||
case (27):
|
||||
Cleanup(EXIT_SUCCESS);
|
||||
break;
|
||||
|
||||
case ' ':
|
||||
enable_cuda ^= 1;
|
||||
#ifdef USE_TEXTURE_RGBA8UI
|
||||
|
||||
if (enable_cuda) {
|
||||
glClearColorIuiEXT(128, 128, 128, 255);
|
||||
} else {
|
||||
glClearColor(0.5, 0.5, 0.5, 1.0);
|
||||
}
|
||||
|
||||
#endif
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
void reshape(int w, int h) {
|
||||
window_width = w;
|
||||
window_height = h;
|
||||
}
|
||||
|
||||
void mainMenu(int i) { keyboard((unsigned char)i, 0, 0); }
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//!
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void createTextureDst(GLuint *tex_cudaResult, unsigned int size_x,
|
||||
unsigned int size_y) {
|
||||
// create a texture
|
||||
glGenTextures(1, tex_cudaResult);
|
||||
glBindTexture(GL_TEXTURE_2D, *tex_cudaResult);
|
||||
|
||||
// set basic parameters
|
||||
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE);
|
||||
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE);
|
||||
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
|
||||
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
|
||||
|
||||
#ifdef USE_TEXSUBIMAGE2D
|
||||
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA8, size_x, size_y, 0, GL_RGBA,
|
||||
GL_UNSIGNED_BYTE, NULL);
|
||||
SDK_CHECK_ERROR_GL();
|
||||
#else
|
||||
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA8UI_EXT, size_x, size_y, 0,
|
||||
GL_RGBA_INTEGER_EXT, GL_UNSIGNED_BYTE, NULL);
|
||||
SDK_CHECK_ERROR_GL();
|
||||
// register this texture with CUDA
|
||||
checkCudaErrors(cudaGraphicsGLRegisterImage(
|
||||
&cuda_tex_result_resource, *tex_cudaResult, GL_TEXTURE_2D,
|
||||
cudaGraphicsMapFlagsWriteDiscard));
|
||||
#endif
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//!
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void deleteTexture(GLuint *tex) {
|
||||
glDeleteTextures(1, tex);
|
||||
SDK_CHECK_ERROR_GL();
|
||||
|
||||
*tex = 0;
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Program main
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
int main(int argc, char **argv) {
|
||||
#if defined(__linux__)
|
||||
char *Xstatus = getenv("DISPLAY");
|
||||
if (Xstatus == NULL) {
|
||||
printf("Waiving execution as X server is not running\n");
|
||||
exit(EXIT_WAIVED);
|
||||
}
|
||||
setenv("DISPLAY", ":0", 0);
|
||||
#endif
|
||||
|
||||
printf("%s Starting...\n\n", argv[0]);
|
||||
|
||||
if (checkCmdLineFlag(argc, (const char **)argv, "file")) {
|
||||
getCmdLineArgumentString(argc, (const char **)argv, "file", &ref_file);
|
||||
}
|
||||
|
||||
pArgc = &argc;
|
||||
pArgv = argv;
|
||||
|
||||
// use command-line specified CUDA device, otherwise use device with highest
|
||||
// Gflops/s
|
||||
if (checkCmdLineFlag(argc, (const char **)argv, "device")) {
|
||||
printf("[%s]\n", argv[0]);
|
||||
printf(" Does not explicitly support -device=n\n");
|
||||
printf(
|
||||
" This sample requires OpenGL. Only -file=<reference> are "
|
||||
"supported\n");
|
||||
printf("exiting...\n");
|
||||
exit(EXIT_WAIVED);
|
||||
}
|
||||
|
||||
if (ref_file) {
|
||||
printf("(Test with OpenGL verification)\n");
|
||||
runStdProgram(argc, argv);
|
||||
} else {
|
||||
printf("(Interactive OpenGL Demo)\n");
|
||||
runStdProgram(argc, argv);
|
||||
}
|
||||
|
||||
exit(EXIT_SUCCESS);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//!
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void FreeResource() {
|
||||
sdkDeleteTimer(&timer);
|
||||
|
||||
// unregister this buffer object with CUDA
|
||||
// checkCudaErrors(cudaGraphicsUnregisterResource(cuda_tex_screen_resource));
|
||||
#ifdef USE_TEXSUBIMAGE2D
|
||||
checkCudaErrors(cudaGraphicsUnregisterResource(cuda_pbo_dest_resource));
|
||||
deletePBO(&pbo_dest);
|
||||
#else
|
||||
cudaFree(cuda_dest_resource);
|
||||
#endif
|
||||
deleteTexture(&tex_screen);
|
||||
deleteTexture(&tex_cudaResult);
|
||||
|
||||
if (iGLUTWindowHandle) {
|
||||
glutDestroyWindow(iGLUTWindowHandle);
|
||||
}
|
||||
|
||||
// finalize logs and leave
|
||||
printf("simpleCUDA2GL Exiting...\n");
|
||||
}
|
||||
|
||||
void Cleanup(int iExitCode) {
|
||||
FreeResource();
|
||||
printf("PPM Images are %s\n",
|
||||
(iExitCode == EXIT_SUCCESS) ? "Matching" : "Not Matching");
|
||||
exit(iExitCode);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//!
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
GLuint compileGLSLprogram(const char *vertex_shader_src,
|
||||
const char *fragment_shader_src) {
|
||||
GLuint v, f, p = 0;
|
||||
|
||||
p = glCreateProgram();
|
||||
|
||||
if (vertex_shader_src) {
|
||||
v = glCreateShader(GL_VERTEX_SHADER);
|
||||
glShaderSource(v, 1, &vertex_shader_src, NULL);
|
||||
glCompileShader(v);
|
||||
|
||||
// check if shader compiled
|
||||
GLint compiled = 0;
|
||||
glGetShaderiv(v, GL_COMPILE_STATUS, &compiled);
|
||||
|
||||
if (!compiled) {
|
||||
//#ifdef NV_REPORT_COMPILE_ERRORS
|
||||
char temp[256] = "";
|
||||
glGetShaderInfoLog(v, 256, NULL, temp);
|
||||
printf("Vtx Compile failed:\n%s\n", temp);
|
||||
//#endif
|
||||
glDeleteShader(v);
|
||||
return 0;
|
||||
} else {
|
||||
glAttachShader(p, v);
|
||||
}
|
||||
}
|
||||
|
||||
if (fragment_shader_src) {
|
||||
f = glCreateShader(GL_FRAGMENT_SHADER);
|
||||
glShaderSource(f, 1, &fragment_shader_src, NULL);
|
||||
glCompileShader(f);
|
||||
|
||||
// check if shader compiled
|
||||
GLint compiled = 0;
|
||||
glGetShaderiv(f, GL_COMPILE_STATUS, &compiled);
|
||||
|
||||
if (!compiled) {
|
||||
//#ifdef NV_REPORT_COMPILE_ERRORS
|
||||
char temp[256] = "";
|
||||
glGetShaderInfoLog(f, 256, NULL, temp);
|
||||
printf("frag Compile failed:\n%s\n", temp);
|
||||
//#endif
|
||||
glDeleteShader(f);
|
||||
return 0;
|
||||
} else {
|
||||
glAttachShader(p, f);
|
||||
}
|
||||
}
|
||||
|
||||
glLinkProgram(p);
|
||||
|
||||
int infologLength = 0;
|
||||
int charsWritten = 0;
|
||||
|
||||
glGetProgramiv(p, GL_INFO_LOG_LENGTH, (GLint *)&infologLength);
|
||||
|
||||
if (infologLength > 0) {
|
||||
char *infoLog = (char *)malloc(infologLength);
|
||||
glGetProgramInfoLog(p, infologLength, (GLsizei *)&charsWritten, infoLog);
|
||||
printf("Shader compilation error: %s\n", infoLog);
|
||||
free(infoLog);
|
||||
}
|
||||
|
||||
return p;
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Allocate the "render target" of CUDA
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
#ifndef USE_TEXSUBIMAGE2D
|
||||
void initCUDABuffers() {
|
||||
// set up vertex data parameter
|
||||
num_texels = image_width * image_height;
|
||||
num_values = num_texels * 4;
|
||||
size_tex_data = sizeof(GLubyte) * num_values;
|
||||
checkCudaErrors(cudaMalloc((void **)&cuda_dest_resource, size_tex_data));
|
||||
// checkCudaErrors(cudaHostAlloc((void**)&cuda_dest_resource, size_tex_data,
|
||||
// ));
|
||||
}
|
||||
#endif
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//!
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void initGLBuffers() {
|
||||
// create pbo
|
||||
#ifdef USE_TEXSUBIMAGE2D
|
||||
createPBO(&pbo_dest, &cuda_pbo_dest_resource);
|
||||
#endif
|
||||
// create texture that will receive the result of CUDA
|
||||
createTextureDst(&tex_cudaResult, image_width, image_height);
|
||||
// load shader programs
|
||||
shDraw = compileGLSLprogram(NULL, glsl_draw_fragshader_src);
|
||||
|
||||
#ifndef USE_TEXSUBIMAGE2D
|
||||
shDrawTex = compileGLSLprogram(glsl_drawtex_vertshader_src,
|
||||
glsl_drawtex_fragshader_src);
|
||||
#endif
|
||||
SDK_CHECK_ERROR_GL();
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Run standard demo loop with or without GL verification
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void runStdProgram(int argc, char **argv) {
|
||||
// First initialize OpenGL context, so we can properly set the GL for CUDA.
|
||||
// This is necessary in order to achieve optimal performance with OpenGL/CUDA
|
||||
// interop.
|
||||
if (false == initGL(&argc, argv)) {
|
||||
return;
|
||||
}
|
||||
|
||||
// Now initialize CUDA context (GL context has been created already)
|
||||
findCudaDevice(argc, (const char **)argv);
|
||||
|
||||
sdkCreateTimer(&timer);
|
||||
sdkResetTimer(&timer);
|
||||
|
||||
// register callbacks
|
||||
glutDisplayFunc(display);
|
||||
glutKeyboardFunc(keyboard);
|
||||
glutReshapeFunc(reshape);
|
||||
glutTimerFunc(REFRESH_DELAY, timerEvent, 0);
|
||||
|
||||
// create menu
|
||||
glutCreateMenu(mainMenu);
|
||||
glutAddMenuEntry("Quit (esc)", '\033');
|
||||
glutAttachMenu(GLUT_RIGHT_BUTTON);
|
||||
|
||||
initGLBuffers();
|
||||
#ifndef USE_TEXSUBIMAGE2D
|
||||
initCUDABuffers();
|
||||
#endif
|
||||
|
||||
// Creating the Auto-Validation Code
|
||||
if (ref_file) {
|
||||
g_CheckRender = new CheckBackBuffer(window_width, window_height, 4);
|
||||
g_CheckRender->setPixelFormat(GL_RGBA);
|
||||
g_CheckRender->setExecPath(argv[0]);
|
||||
g_CheckRender->EnableQAReadback(true);
|
||||
}
|
||||
|
||||
printf(
|
||||
"\n"
|
||||
"\tControls\n"
|
||||
"\t(right click mouse button for Menu)\n"
|
||||
"\t[esc] - Quit\n\n");
|
||||
|
||||
// start rendering mainloop
|
||||
glutMainLoop();
|
||||
|
||||
// Normally unused return path
|
||||
Cleanup(EXIT_SUCCESS);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Initialize GL
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
bool initGL(int *argc, char **argv) {
|
||||
// Create GL context
|
||||
glutInit(argc, argv);
|
||||
glutInitDisplayMode(GLUT_RGBA | GLUT_ALPHA | GLUT_DOUBLE | GLUT_DEPTH);
|
||||
glutInitWindowSize(window_width, window_height);
|
||||
iGLUTWindowHandle = glutCreateWindow("CUDA OpenGL post-processing");
|
||||
|
||||
// initialize necessary OpenGL extensions
|
||||
if (!isGLVersionSupported(2, 0) ||
|
||||
!areGLExtensionsSupported("GL_ARB_pixel_buffer_object "
|
||||
"GL_EXT_framebuffer_object")) {
|
||||
printf("ERROR: Support for necessary OpenGL extensions missing.");
|
||||
fflush(stderr);
|
||||
return false;
|
||||
}
|
||||
|
||||
// default initialization
|
||||
#ifndef USE_TEXTURE_RGBA8UI
|
||||
glClearColor(0.5, 0.5, 0.5, 1.0);
|
||||
#else
|
||||
glClearColorIuiEXT(128, 128, 128, 255);
|
||||
#endif
|
||||
glDisable(GL_DEPTH_TEST);
|
||||
|
||||
// viewport
|
||||
glViewport(0, 0, window_width, window_height);
|
||||
|
||||
// projection
|
||||
glMatrixMode(GL_PROJECTION);
|
||||
glLoadIdentity();
|
||||
gluPerspective(60.0, (GLfloat)window_width / (GLfloat)window_height, 0.1f,
|
||||
10.0f);
|
||||
|
||||
glPolygonMode(GL_FRONT_AND_BACK, GL_FILL);
|
||||
|
||||
glEnable(GL_LIGHT0);
|
||||
float red[] = {1.0f, 0.1f, 0.1f, 1.0f};
|
||||
float white[] = {1.0f, 1.0f, 1.0f, 1.0f};
|
||||
glMaterialfv(GL_FRONT_AND_BACK, GL_DIFFUSE, red);
|
||||
glMaterialfv(GL_FRONT_AND_BACK, GL_SPECULAR, white);
|
||||
glMaterialf(GL_FRONT_AND_BACK, GL_SHININESS, 60.0f);
|
||||
|
||||
SDK_CHECK_ERROR_GL();
|
||||
|
||||
return true;
|
||||
}
|
||||
62
Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL.cu
Normal file
62
Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL.cu
Normal file
@@ -0,0 +1,62 @@
|
||||
/* Copyright (c) 2022, 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.
|
||||
*/
|
||||
|
||||
// Utilities and system includes
|
||||
|
||||
#include <helper_cuda.h>
|
||||
|
||||
// clamp x to range [a, b]
|
||||
__device__ float clamp(float x, float a, float b) { return max(a, min(b, x)); }
|
||||
|
||||
__device__ int clamp(int x, int a, int b) { return max(a, min(b, x)); }
|
||||
|
||||
// convert floating point rgb color to 8-bit integer
|
||||
__device__ int rgbToInt(float r, float g, float b) {
|
||||
r = clamp(r, 0.0f, 255.0f);
|
||||
g = clamp(g, 0.0f, 255.0f);
|
||||
b = clamp(b, 0.0f, 255.0f);
|
||||
return (int(b) << 16) | (int(g) << 8) | int(r);
|
||||
}
|
||||
|
||||
__global__ void cudaProcess(unsigned int *g_odata, int imgw) {
|
||||
extern __shared__ uchar4 sdata[];
|
||||
|
||||
int tx = threadIdx.x;
|
||||
int ty = threadIdx.y;
|
||||
int bw = blockDim.x;
|
||||
int bh = blockDim.y;
|
||||
int x = blockIdx.x * bw + tx;
|
||||
int y = blockIdx.y * bh + ty;
|
||||
|
||||
uchar4 c4 = make_uchar4((x & 0x20) ? 100 : 0, 0, (y & 0x20) ? 100 : 0, 0);
|
||||
g_odata[y * imgw + x] = rgbToInt(c4.z, c4.y, c4.x);
|
||||
}
|
||||
|
||||
extern "C" void launch_cudaProcess(dim3 grid, dim3 block, int sbytes,
|
||||
unsigned int *g_odata, int imgw) {
|
||||
cudaProcess<<<grid, block, sbytes>>>(g_odata, imgw);
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2017
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "simpleCUDA2GL", "simpleCUDA2GL_vs2017.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
|
||||
@@ -0,0 +1,123 @@
|
||||
<?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)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||
</PropertyGroup>
|
||||
<ItemGroup Label="ProjectConfigurations">
|
||||
<ProjectConfiguration Include="Debug|x64">
|
||||
<Configuration>Debug</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
<ProjectConfiguration Include="Release|x64">
|
||||
<Configuration>Release</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
</ItemGroup>
|
||||
<PropertyGroup Label="Globals">
|
||||
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||
<RootNamespace>simpleCUDA2GL_vs2017</RootNamespace>
|
||||
<ProjectName>simpleCUDA2GL</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(WindowsTargetPlatformVersion)'==''">
|
||||
<LatestTargetPlatformVersion>$([Microsoft.Build.Utilities.ToolLocationHelper]::GetLatestSDKTargetPlatformVersion('Windows', '10.0'))</LatestTargetPlatformVersion>
|
||||
<WindowsTargetPlatformVersion Condition="'$(WindowsTargetPlatformVersion)' == ''">$(LatestTargetPlatformVersion)</WindowsTargetPlatformVersion>
|
||||
<TargetPlatformVersion>$(WindowsTargetPlatformVersion)</TargetPlatformVersion>
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup>
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v141</PlatformToolset>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(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="$(CUDAPropsPath)\CUDA 11.6.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(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>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cudart_static.lib;freeglut.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../../Common/lib/$(PlatformName);</AdditionalLibraryDirectories>
|
||||
<OutputFile>$(OutDir)/simpleCUDA2GL.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;compute_86,sm_86;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </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>glew64.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
</Link>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="main.cpp" />
|
||||
<CudaCompile Include="simpleCUDA2GL.cu" />
|
||||
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2019
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "simpleCUDA2GL", "simpleCUDA2GL_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
|
||||
@@ -0,0 +1,119 @@
|
||||
<?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>simpleCUDA2GL_vs2019</RootNamespace>
|
||||
<ProjectName>simpleCUDA2GL</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup>
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v142</PlatformToolset>
|
||||
<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(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="$(CUDAPropsPath)\CUDA 11.6.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(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>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cudart_static.lib;freeglut.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../../Common/lib/$(PlatformName);</AdditionalLibraryDirectories>
|
||||
<OutputFile>$(OutDir)/simpleCUDA2GL.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;compute_86,sm_86;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </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>glew64.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
</Link>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="main.cpp" />
|
||||
<CudaCompile Include="simpleCUDA2GL.cu" />
|
||||
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2022
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "simpleCUDA2GL", "simpleCUDA2GL_vs2022.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
|
||||
@@ -0,0 +1,119 @@
|
||||
<?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>simpleCUDA2GL_vs2022</RootNamespace>
|
||||
<ProjectName>simpleCUDA2GL</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup>
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v143</PlatformToolset>
|
||||
<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(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="$(CUDAPropsPath)\CUDA 11.6.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(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>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cudart_static.lib;freeglut.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../../Common/lib/$(PlatformName);</AdditionalLibraryDirectories>
|
||||
<OutputFile>$(OutDir)/simpleCUDA2GL.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;compute_86,sm_86;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </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>glew64.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
</Link>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="main.cpp" />
|
||||
<CudaCompile Include="simpleCUDA2GL.cu" />
|
||||
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
Reference in New Issue
Block a user