mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2026-10-11 23:38:25 +08:00
Add and Update samples for CUDA 10.0
This commit is contained in:
Mahesh Doijade
300
Samples/simpleCudaGraphs/Makefile
Normal file
300
Samples/simpleCudaGraphs/Makefile
Normal file
@@ -0,0 +1,300 @@
|
||||
################################################################################
|
||||
# Copyright (c) 2018, 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 $(TARGET_ARCH),x86_64 aarch64 ppc64le armv7l))
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 ppc64le))
|
||||
TARGET_SIZE := 64
|
||||
else ifneq (,$(filter $(TARGET_ARCH),armv7l))
|
||||
TARGET_SIZE := 32
|
||||
endif
|
||||
else
|
||||
TARGET_SIZE := $(shell getconf LONG_BIT)
|
||||
endif
|
||||
else
|
||||
$(error ERROR - unsupported value $(TARGET_ARCH) for TARGET_ARCH!)
|
||||
endif
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq (,$(filter $(HOST_ARCH)-$(TARGET_ARCH),aarch64-armv7l x86_64-armv7l x86_64-aarch64 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 ?= $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.0.0-g++
|
||||
else ifeq ($(TARGET_OS), android)
|
||||
HOST_COMPILER ?= aarch64-linux-android-clang++
|
||||
endif
|
||||
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)/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
|
||||
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_OS),qnx)
|
||||
CCFLAGS += -DWIN_INTERFACE_CUSTOM
|
||||
LDFLAGS += -lsocket
|
||||
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),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
|
||||
|
||||
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 ?= 30 35 37 50 52 60 61 70 75
|
||||
|
||||
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
|
||||
|
||||
ifeq ($(SAMPLE_ENABLED),0)
|
||||
EXEC ?= @echo "[@]"
|
||||
endif
|
||||
|
||||
################################################################################
|
||||
|
||||
# Target rules
|
||||
all: build
|
||||
|
||||
build: simpleCudaGraphs
|
||||
|
||||
check.deps:
|
||||
ifeq ($(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
|
||||
|
||||
simpleCudaGraphs.o:simpleCudaGraphs.cu
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
simpleCudaGraphs: simpleCudaGraphs.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
|
||||
$(EXEC) ./simpleCudaGraphs
|
||||
|
||||
clean:
|
||||
rm -f simpleCudaGraphs simpleCudaGraphs.o
|
||||
rm -rf ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/simpleCudaGraphs
|
||||
|
||||
clobber: clean
|
||||
78
Samples/simpleCudaGraphs/NsightEclipse.xml
Normal file
78
Samples/simpleCudaGraphs/NsightEclipse.xml
Normal file
@@ -0,0 +1,78 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
||||
<entry>
|
||||
<name>simpleCudaGraphs</name>
|
||||
<cuda_api_list>
|
||||
<toolkit>cudaStreamBeginCapture</toolkit>
|
||||
<toolkit>cudaStreamEndCapture</toolkit>
|
||||
<toolkit>cudaLaunchHostFunc</toolkit>
|
||||
<toolkit>cudaGraphCreate</toolkit>
|
||||
<toolkit>cudaGraphLaunch</toolkit>
|
||||
<toolkit>cudaGraphInstantiate</toolkit>
|
||||
<toolkit>cudaGraphAddHostNode</toolkit>
|
||||
<toolkit>cudaGraphAddMemcpyNode</toolkit>
|
||||
<toolkit>cudaGraphAddKernelNode</toolkit>
|
||||
<toolkit>cudaGraphAddMemsetNode</toolkit>
|
||||
<toolkit>cudaGraphExecDestroy</toolkit>
|
||||
<toolkit>cudaGraphDestroy</toolkit>
|
||||
</cuda_api_list>
|
||||
<description><![CDATA[A demonstration of CUDA Graphs creation, instantiation and launch using Graphs APIs and Stream Capture APIs.]]></description>
|
||||
<devicecompilation>whole</devicecompilation>
|
||||
<includepaths>
|
||||
<path>./</path>
|
||||
<path>../</path>
|
||||
<path>../../common/inc</path>
|
||||
</includepaths>
|
||||
<keyconcepts>
|
||||
<concept level="basic">CUDA Graphs</concept>
|
||||
<concept level="basic">Stream Capture</concept>
|
||||
</keyconcepts>
|
||||
<keywords>
|
||||
<keyword>CUDA</keyword>
|
||||
<keyword>GPGPU</keyword>
|
||||
<keyword>CUDA Graphs</keyword>
|
||||
</keywords>
|
||||
<libraries>
|
||||
</libraries>
|
||||
<librarypaths>
|
||||
</librarypaths>
|
||||
<nsight_eclipse>true</nsight_eclipse>
|
||||
<primary_file>simpleCudaGraphs.cu</primary_file>
|
||||
<scopes>
|
||||
<scope>1:CUDA</scope>
|
||||
</scopes>
|
||||
<sm-arch>sm30</sm-arch>
|
||||
<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>sm75</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>
|
||||
<env>
|
||||
<arch>arm</arch>
|
||||
</env>
|
||||
<env>
|
||||
<arch>ppc64le</arch>
|
||||
<platform>linux</platform>
|
||||
</env>
|
||||
</supported_envs>
|
||||
<supported_sm_architectures>
|
||||
<from>3.0</from>
|
||||
</supported_sm_architectures>
|
||||
<title>Simple CUDA Graphs</title>
|
||||
<type>exe</type>
|
||||
</entry>
|
||||
94
Samples/simpleCudaGraphs/README.md
Normal file
94
Samples/simpleCudaGraphs/README.md
Normal file
@@ -0,0 +1,94 @@
|
||||
# simpleCudaGraphs - Simple CUDA Graphs
|
||||
|
||||
## Description
|
||||
|
||||
A demonstration of CUDA Graphs creation, instantiation and launch using Graphs APIs and Stream Capture APIs.
|
||||
|
||||
## Key Concepts
|
||||
|
||||
CUDA Graphs, Stream Capture
|
||||
|
||||
## Supported SM Architectures
|
||||
|
||||
[SM 3.0 ](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 7.5 ](https://developer.nvidia.com/cuda-gpus)
|
||||
|
||||
## Supported OSes
|
||||
|
||||
Linux, Windows, MacOSX
|
||||
|
||||
## Supported CPU Architecture
|
||||
|
||||
x86_64, ppc64le, armv7l
|
||||
|
||||
## CUDA APIs involved
|
||||
|
||||
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
|
||||
cudaStreamBeginCapture, cudaStreamEndCapture, cudaLaunchHostFunc, cudaGraphCreate, cudaGraphLaunch, cudaGraphInstantiate, cudaGraphAddHostNode, cudaGraphAddMemcpyNode, cudaGraphAddKernelNode, cudaGraphAddMemsetNode, cudaGraphExecDestroy, cudaGraphDestroy
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Download and install the [CUDA Toolkit 10.0](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
|
||||
|
||||
## 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++
|
||||
```
|
||||
|
||||
### Mac
|
||||
The Mac samples are built using makefiles. To use the makefiles, change directory into the sample directory you wish to build, and run make:
|
||||
```
|
||||
$ cd <sample_dir>
|
||||
$ make
|
||||
```
|
||||
|
||||
The samples makefiles can take advantage of certain options:
|
||||
|
||||
* **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="A B ..."
|
||||
```
|
||||
|
||||
* **HOST_COMPILER=<host_compiler>** - override the default clang host compiler. See the [Mac Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-mac-os-x/index.html#system-requirements) for a list of supported host compilers.
|
||||
```
|
||||
$ make HOST_COMPILER=clang
|
||||
```
|
||||
|
||||
## References (for more details)
|
||||
|
||||
399
Samples/simpleCudaGraphs/simpleCudaGraphs.cu
Normal file
399
Samples/simpleCudaGraphs/simpleCudaGraphs.cu
Normal file
@@ -0,0 +1,399 @@
|
||||
/* Copyright (c) 2018, 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.
|
||||
*/
|
||||
|
||||
|
||||
#include <cooperative_groups.h>
|
||||
#include <cuda_runtime.h>
|
||||
#include <helper_cuda.h>
|
||||
#include <vector>
|
||||
|
||||
namespace cg = cooperative_groups;
|
||||
|
||||
#define THREADS_PER_BLOCK 512
|
||||
#define GRAPH_LAUNCH_ITERATIONS 3
|
||||
|
||||
typedef struct callBackData {
|
||||
const char *fn_name;
|
||||
double *data;
|
||||
} callBackData_t;
|
||||
|
||||
__global__ void reduce(float *inputVec, double *outputVec, size_t inputSize,
|
||||
size_t outputSize) {
|
||||
__shared__ double tmp[THREADS_PER_BLOCK];
|
||||
|
||||
cg::thread_block cta = cg::this_thread_block();
|
||||
size_t globaltid = blockIdx.x * blockDim.x + threadIdx.x;
|
||||
|
||||
double temp_sum = 0.0;
|
||||
for (int i = globaltid; i < inputSize; i += gridDim.x * blockDim.x) {
|
||||
temp_sum += (double)inputVec[i];
|
||||
}
|
||||
tmp[cta.thread_rank()] = temp_sum;
|
||||
|
||||
cg::sync(cta);
|
||||
|
||||
cg::thread_block_tile<32> tile32 = cg::tiled_partition<32>(cta);
|
||||
|
||||
double beta = temp_sum;
|
||||
double temp;
|
||||
|
||||
for (int i = tile32.size() / 2; i > 0; i >>= 1) {
|
||||
if (tile32.thread_rank() < i) {
|
||||
temp = tmp[cta.thread_rank() + i];
|
||||
beta += temp;
|
||||
tmp[cta.thread_rank()] = beta;
|
||||
}
|
||||
cg::sync(tile32);
|
||||
}
|
||||
cg::sync(cta);
|
||||
|
||||
if (cta.thread_rank() == 0 && blockIdx.x < outputSize) {
|
||||
beta = 0.0;
|
||||
for (int i = 0; i < cta.size(); i += tile32.size()) {
|
||||
beta += tmp[i];
|
||||
}
|
||||
outputVec[blockIdx.x] = beta;
|
||||
}
|
||||
}
|
||||
|
||||
__global__ void reduceFinal(double *inputVec, double *result,
|
||||
size_t inputSize) {
|
||||
__shared__ double tmp[THREADS_PER_BLOCK];
|
||||
|
||||
cg::thread_block cta = cg::this_thread_block();
|
||||
size_t globaltid = blockIdx.x * blockDim.x + threadIdx.x;
|
||||
|
||||
double temp_sum = 0.0;
|
||||
for (int i = globaltid; i < inputSize; i += gridDim.x * blockDim.x) {
|
||||
temp_sum += (double)inputVec[i];
|
||||
}
|
||||
tmp[cta.thread_rank()] = temp_sum;
|
||||
|
||||
cg::sync(cta);
|
||||
|
||||
cg::thread_block_tile<32> tile32 = cg::tiled_partition<32>(cta);
|
||||
|
||||
// do reduction in shared mem
|
||||
if ((blockDim.x >= 512) && (cta.thread_rank() < 256)) {
|
||||
tmp[cta.thread_rank()] = temp_sum = temp_sum + tmp[cta.thread_rank() + 256];
|
||||
}
|
||||
|
||||
cg::sync(cta);
|
||||
|
||||
if ((blockDim.x >= 256) && (cta.thread_rank() < 128)) {
|
||||
tmp[cta.thread_rank()] = temp_sum = temp_sum + tmp[cta.thread_rank() + 128];
|
||||
}
|
||||
|
||||
cg::sync(cta);
|
||||
|
||||
if ((blockDim.x >= 128) && (cta.thread_rank() < 64)) {
|
||||
tmp[cta.thread_rank()] = temp_sum = temp_sum + tmp[cta.thread_rank() + 64];
|
||||
}
|
||||
|
||||
cg::sync(cta);
|
||||
|
||||
if (cta.thread_rank() < 32) {
|
||||
// Fetch final intermediate sum from 2nd warp
|
||||
if (blockDim.x >= 64) temp_sum += tmp[cta.thread_rank() + 32];
|
||||
// Reduce final warp using shuffle
|
||||
for (int offset = tile32.size() / 2; offset > 0; offset /= 2) {
|
||||
temp_sum += tile32.shfl_down(temp_sum, offset);
|
||||
}
|
||||
}
|
||||
// write result for this block to global mem
|
||||
if (cta.thread_rank() == 0) result[0] = temp_sum;
|
||||
}
|
||||
|
||||
void init_input(float *a, size_t size) {
|
||||
for (size_t i = 0; i < size; i++) a[i] = (rand() & 0xFF) / (float)RAND_MAX;
|
||||
}
|
||||
|
||||
void CUDART_CB myHostNodeCallback(void *data) {
|
||||
// Check status of GPU after stream operations are done
|
||||
callBackData_t *tmp = (callBackData_t *)(data);
|
||||
// checkCudaErrors(tmp->status);
|
||||
|
||||
double *result = (double *)(tmp->data);
|
||||
char *function = (char *)(tmp->fn_name);
|
||||
printf("[%s] Host callback final reduced sum = %lf\n", function, *result);
|
||||
*result = 0.0; // reset the result
|
||||
}
|
||||
|
||||
void cudaGraphsManual(float *inputVec_h, float *inputVec_d, double *outputVec_d,
|
||||
double *result_d, size_t inputSize, size_t numOfBlocks) {
|
||||
cudaStream_t streamForGraph;
|
||||
cudaGraph_t graph;
|
||||
std::vector<cudaGraphNode_t> nodeDependencies;
|
||||
cudaGraphNode_t memcpyNode, kernelNode, memsetNode;
|
||||
double result_h = 0.0;
|
||||
|
||||
checkCudaErrors(cudaStreamCreate(&streamForGraph));
|
||||
|
||||
cudaKernelNodeParams kernelNodeParams = {0};
|
||||
cudaMemcpy3DParms memcpyParams = {0};
|
||||
cudaMemsetParams memsetParams = {0};
|
||||
|
||||
memcpyParams.srcArray = NULL;
|
||||
memcpyParams.srcPos = make_cudaPos(0, 0, 0);
|
||||
memcpyParams.srcPtr =
|
||||
make_cudaPitchedPtr(inputVec_h, sizeof(float) * inputSize, inputSize, 1);
|
||||
memcpyParams.dstArray = NULL;
|
||||
memcpyParams.dstPos = make_cudaPos(0, 0, 0);
|
||||
memcpyParams.dstPtr =
|
||||
make_cudaPitchedPtr(inputVec_d, sizeof(float) * inputSize, inputSize, 1);
|
||||
memcpyParams.extent = make_cudaExtent(sizeof(float) * inputSize, 1, 1);
|
||||
memcpyParams.kind = cudaMemcpyHostToDevice;
|
||||
|
||||
memsetParams.dst = (void *)outputVec_d;
|
||||
memsetParams.value = 0;
|
||||
memsetParams.pitch = 0;
|
||||
memsetParams.elementSize = sizeof(float); // elementSize can be max 4 bytes
|
||||
memsetParams.width = numOfBlocks * 2;
|
||||
memsetParams.height = 1;
|
||||
|
||||
checkCudaErrors(cudaGraphCreate(&graph, 0));
|
||||
checkCudaErrors(
|
||||
cudaGraphAddMemcpyNode(&memcpyNode, graph, NULL, 0, &memcpyParams));
|
||||
checkCudaErrors(
|
||||
cudaGraphAddMemsetNode(&memsetNode, graph, NULL, 0, &memsetParams));
|
||||
|
||||
nodeDependencies.push_back(memsetNode);
|
||||
nodeDependencies.push_back(memcpyNode);
|
||||
|
||||
void *kernelArgs[4] = {(void *)&inputVec_d, (void *)&outputVec_d, &inputSize,
|
||||
&numOfBlocks};
|
||||
|
||||
kernelNodeParams.func = (void *)reduce;
|
||||
kernelNodeParams.gridDim = dim3(numOfBlocks, 1, 1);
|
||||
kernelNodeParams.blockDim = dim3(THREADS_PER_BLOCK, 1, 1);
|
||||
kernelNodeParams.sharedMemBytes = 0;
|
||||
kernelNodeParams.kernelParams = (void **)kernelArgs;
|
||||
kernelNodeParams.extra = NULL;
|
||||
|
||||
checkCudaErrors(
|
||||
cudaGraphAddKernelNode(&kernelNode, graph, nodeDependencies.data(),
|
||||
nodeDependencies.size(), &kernelNodeParams));
|
||||
|
||||
nodeDependencies.clear();
|
||||
nodeDependencies.push_back(kernelNode);
|
||||
|
||||
memset(&memsetParams, 0, sizeof(memsetParams));
|
||||
memsetParams.dst = result_d;
|
||||
memsetParams.value = 0;
|
||||
memsetParams.elementSize = sizeof(float);
|
||||
memsetParams.width = 2;
|
||||
memsetParams.height = 1;
|
||||
checkCudaErrors(
|
||||
cudaGraphAddMemsetNode(&memsetNode, graph, NULL, 0, &memsetParams));
|
||||
|
||||
nodeDependencies.push_back(memsetNode);
|
||||
|
||||
memset(&kernelNodeParams, 0, sizeof(kernelNodeParams));
|
||||
kernelNodeParams.func = (void *)reduceFinal;
|
||||
kernelNodeParams.gridDim = dim3(1, 1, 1);
|
||||
kernelNodeParams.blockDim = dim3(THREADS_PER_BLOCK, 1, 1);
|
||||
kernelNodeParams.sharedMemBytes = 0;
|
||||
void *kernelArgs2[3] = {(void *)&outputVec_d, (void *)&result_d,
|
||||
&numOfBlocks};
|
||||
kernelNodeParams.kernelParams = kernelArgs2;
|
||||
kernelNodeParams.extra = NULL;
|
||||
|
||||
checkCudaErrors(
|
||||
cudaGraphAddKernelNode(&kernelNode, graph, nodeDependencies.data(),
|
||||
nodeDependencies.size(), &kernelNodeParams));
|
||||
nodeDependencies.clear();
|
||||
nodeDependencies.push_back(kernelNode);
|
||||
|
||||
memset(&memcpyParams, 0, sizeof(memcpyParams));
|
||||
|
||||
memcpyParams.srcArray = NULL;
|
||||
memcpyParams.srcPos = make_cudaPos(0, 0, 0);
|
||||
memcpyParams.srcPtr = make_cudaPitchedPtr(result_d, sizeof(double), 1, 1);
|
||||
memcpyParams.dstArray = NULL;
|
||||
memcpyParams.dstPos = make_cudaPos(0, 0, 0);
|
||||
memcpyParams.dstPtr = make_cudaPitchedPtr(&result_h, sizeof(double), 1, 1);
|
||||
memcpyParams.extent = make_cudaExtent(sizeof(double), 1, 1);
|
||||
memcpyParams.kind = cudaMemcpyDeviceToHost;
|
||||
checkCudaErrors(
|
||||
cudaGraphAddMemcpyNode(&memcpyNode, graph, nodeDependencies.data(),
|
||||
nodeDependencies.size(), &memcpyParams));
|
||||
nodeDependencies.clear();
|
||||
nodeDependencies.push_back(memcpyNode);
|
||||
|
||||
cudaGraphNode_t hostNode;
|
||||
cudaHostNodeParams hostParams = {0};
|
||||
hostParams.fn = myHostNodeCallback;
|
||||
callBackData_t hostFnData;
|
||||
hostFnData.data = &result_h;
|
||||
hostFnData.fn_name = "cudaGraphsManual";
|
||||
hostParams.userData = &hostFnData;
|
||||
|
||||
checkCudaErrors(cudaGraphAddHostNode(&hostNode, graph,
|
||||
nodeDependencies.data(),
|
||||
nodeDependencies.size(), &hostParams));
|
||||
|
||||
cudaGraphNode_t *nodes = NULL;
|
||||
size_t numNodes = 0;
|
||||
checkCudaErrors(cudaGraphGetNodes(graph, nodes, &numNodes));
|
||||
printf("\nNum of nodes in the graph created manually = %zu\n", numNodes);
|
||||
|
||||
cudaGraphExec_t graphExec;
|
||||
checkCudaErrors(cudaGraphInstantiate(&graphExec, graph, NULL, NULL, 0));
|
||||
|
||||
cudaGraph_t clonedGraph;
|
||||
cudaGraphExec_t clonedGraphExec;
|
||||
checkCudaErrors(cudaGraphClone(&clonedGraph, graph));
|
||||
checkCudaErrors(
|
||||
cudaGraphInstantiate(&clonedGraphExec, clonedGraph, NULL, NULL, 0));
|
||||
|
||||
for (int i = 0; i < GRAPH_LAUNCH_ITERATIONS; i++) {
|
||||
checkCudaErrors(cudaGraphLaunch(graphExec, streamForGraph));
|
||||
}
|
||||
|
||||
checkCudaErrors(cudaStreamSynchronize(streamForGraph));
|
||||
|
||||
printf("Cloned Graph Output.. \n");
|
||||
for (int i = 0; i < GRAPH_LAUNCH_ITERATIONS; i++) {
|
||||
checkCudaErrors(cudaGraphLaunch(clonedGraphExec, streamForGraph));
|
||||
}
|
||||
checkCudaErrors(cudaStreamSynchronize(streamForGraph));
|
||||
|
||||
checkCudaErrors(cudaGraphExecDestroy(graphExec));
|
||||
checkCudaErrors(cudaGraphExecDestroy(clonedGraphExec));
|
||||
checkCudaErrors(cudaGraphDestroy(graph));
|
||||
checkCudaErrors(cudaGraphDestroy(clonedGraph));
|
||||
checkCudaErrors(cudaStreamDestroy(streamForGraph));
|
||||
}
|
||||
|
||||
void cudaGraphsUsingStreamCapture(float *inputVec_h, float *inputVec_d,
|
||||
double *outputVec_d, double *result_d,
|
||||
size_t inputSize, size_t numOfBlocks) {
|
||||
cudaStream_t stream1, stream2, streamForGraph;
|
||||
cudaEvent_t reduceKernelEvent;
|
||||
cudaGraph_t graph;
|
||||
double result_h = 0.0;
|
||||
|
||||
checkCudaErrors(cudaStreamCreate(&stream1));
|
||||
checkCudaErrors(cudaStreamCreate(&stream2));
|
||||
checkCudaErrors(cudaStreamCreate(&streamForGraph));
|
||||
checkCudaErrors(cudaEventCreate(&reduceKernelEvent));
|
||||
|
||||
checkCudaErrors(cudaStreamBeginCapture(stream1));
|
||||
|
||||
checkCudaErrors(cudaMemcpyAsync(inputVec_d, inputVec_h,
|
||||
sizeof(float) * inputSize, cudaMemcpyDefault,
|
||||
stream1));
|
||||
checkCudaErrors(
|
||||
cudaMemsetAsync(outputVec_d, 0, sizeof(double) * numOfBlocks, stream1));
|
||||
reduce<<<numOfBlocks, THREADS_PER_BLOCK, 0, stream1>>>(
|
||||
inputVec_d, outputVec_d, inputSize, numOfBlocks);
|
||||
checkCudaErrors(cudaEventRecord(reduceKernelEvent, stream1));
|
||||
|
||||
checkCudaErrors(cudaStreamWaitEvent(stream2, reduceKernelEvent, 0));
|
||||
checkCudaErrors(cudaMemsetAsync(result_d, 0, sizeof(double), stream2));
|
||||
reduceFinal<<<1, THREADS_PER_BLOCK, 0, stream2>>>(outputVec_d, result_d,
|
||||
numOfBlocks);
|
||||
checkCudaErrors(cudaMemcpyAsync(&result_h, result_d, sizeof(double),
|
||||
cudaMemcpyDefault, stream2));
|
||||
checkCudaErrors(cudaEventRecord(reduceKernelEvent, stream2));
|
||||
checkCudaErrors(cudaStreamWaitEvent(stream1, reduceKernelEvent, 0));
|
||||
|
||||
callBackData_t hostFnData = {0};
|
||||
hostFnData.data = &result_h;
|
||||
hostFnData.fn_name = "cudaGraphsUsingStreamCapture";
|
||||
cudaHostFn_t fn = myHostNodeCallback;
|
||||
checkCudaErrors(cudaLaunchHostFunc(stream1, fn, &hostFnData));
|
||||
checkCudaErrors(cudaStreamEndCapture(stream1, &graph));
|
||||
|
||||
cudaGraphNode_t *nodes = NULL;
|
||||
size_t numNodes = 0;
|
||||
checkCudaErrors(cudaGraphGetNodes(graph, nodes, &numNodes));
|
||||
printf("\nNum of nodes in the graph created using stream capture API = %zu\n",
|
||||
numNodes);
|
||||
|
||||
cudaGraphExec_t graphExec;
|
||||
checkCudaErrors(cudaGraphInstantiate(&graphExec, graph, NULL, NULL, 0));
|
||||
|
||||
cudaGraph_t clonedGraph;
|
||||
cudaGraphExec_t clonedGraphExec;
|
||||
checkCudaErrors(cudaGraphClone(&clonedGraph, graph));
|
||||
checkCudaErrors(
|
||||
cudaGraphInstantiate(&clonedGraphExec, clonedGraph, NULL, NULL, 0));
|
||||
|
||||
for (int i = 0; i < GRAPH_LAUNCH_ITERATIONS; i++) {
|
||||
checkCudaErrors(cudaGraphLaunch(graphExec, streamForGraph));
|
||||
}
|
||||
|
||||
checkCudaErrors(cudaStreamSynchronize(streamForGraph));
|
||||
|
||||
printf("Cloned Graph Output.. \n");
|
||||
for (int i = 0; i < GRAPH_LAUNCH_ITERATIONS; i++) {
|
||||
checkCudaErrors(cudaGraphLaunch(clonedGraphExec, streamForGraph));
|
||||
}
|
||||
|
||||
checkCudaErrors(cudaStreamSynchronize(streamForGraph));
|
||||
|
||||
checkCudaErrors(cudaGraphExecDestroy(graphExec));
|
||||
checkCudaErrors(cudaGraphExecDestroy(clonedGraphExec));
|
||||
checkCudaErrors(cudaGraphDestroy(graph));
|
||||
checkCudaErrors(cudaGraphDestroy(clonedGraph));
|
||||
checkCudaErrors(cudaStreamDestroy(stream1));
|
||||
checkCudaErrors(cudaStreamDestroy(stream2));
|
||||
checkCudaErrors(cudaStreamDestroy(streamForGraph));
|
||||
}
|
||||
|
||||
int main(int argc, char **argv) {
|
||||
size_t size = 1 << 24; // number of elements to reduce
|
||||
size_t maxBlocks = 512;
|
||||
|
||||
// This will pick the best possible CUDA capable device
|
||||
int devID = findCudaDevice(argc, (const char **)argv);
|
||||
|
||||
printf("%zu elements\n", size);
|
||||
printf("threads per block = %d\n", THREADS_PER_BLOCK);
|
||||
printf("Graph Launch iterations = %d\n", GRAPH_LAUNCH_ITERATIONS);
|
||||
|
||||
float *inputVec_d = NULL, *inputVec_h = NULL;
|
||||
double *outputVec_d = NULL, *result_d;
|
||||
|
||||
inputVec_h = (float *)malloc(sizeof(float) * size);
|
||||
checkCudaErrors(cudaMalloc(&inputVec_d, sizeof(float) * size));
|
||||
checkCudaErrors(cudaMalloc(&outputVec_d, sizeof(double) * maxBlocks));
|
||||
checkCudaErrors(cudaMalloc(&result_d, sizeof(double)));
|
||||
|
||||
init_input(inputVec_h, size);
|
||||
|
||||
cudaGraphsManual(inputVec_h, inputVec_d, outputVec_d, result_d, size,
|
||||
maxBlocks);
|
||||
cudaGraphsUsingStreamCapture(inputVec_h, inputVec_d, outputVec_d, result_d,
|
||||
size, maxBlocks);
|
||||
|
||||
checkCudaErrors(cudaFree(inputVec_d));
|
||||
checkCudaErrors(cudaFree(outputVec_d));
|
||||
checkCudaErrors(cudaFree(result_d));
|
||||
return EXIT_SUCCESS;
|
||||
}
|
||||
20
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2012.sln
Normal file
20
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2012.sln
Normal file
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2012
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "simpleCudaGraphs", "simpleCudaGraphs_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
|
||||
107
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2012.vcxproj
Normal file
107
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2012.vcxproj
Normal file
@@ -0,0 +1,107 @@
|
||||
<?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>simpleCudaGraphs_vs2012</RootNamespace>
|
||||
<ProjectName>simpleCudaGraphs</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="$(CUDAPropsPath)\CUDA 10.0.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(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>$(OutDir)/simpleCudaGraphs.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_30,sm_30;compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
|
||||
<Include>./;../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(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="'$(Configuration)'=='Release'">
|
||||
<ClCompile>
|
||||
<Optimization>MaxSpeed</Optimization>
|
||||
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>false</GenerateDebugInformation>
|
||||
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<Runtime>MT</Runtime>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<CudaCompile Include="simpleCudaGraphs.cu" />
|
||||
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 10.0.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
20
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2013.sln
Normal file
20
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2013.sln
Normal file
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 13.00
|
||||
# Visual Studio 2013
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "simpleCudaGraphs", "simpleCudaGraphs_vs2013.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
|
||||
EndProject
|
||||
Global
|
||||
GlobalSection(SolutionConfigurationPlatforms) = preSolution
|
||||
Debug|x64 = Debug|x64
|
||||
Release|x64 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(ProjectConfigurationPlatforms) = postSolution
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(SolutionProperties) = preSolution
|
||||
HideSolutionNode = FALSE
|
||||
EndGlobalSection
|
||||
EndGlobal
|
||||
107
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2013.vcxproj
Normal file
107
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2013.vcxproj
Normal file
@@ -0,0 +1,107 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
|
||||
<PropertyGroup>
|
||||
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||
</PropertyGroup>
|
||||
<ItemGroup Label="ProjectConfigurations">
|
||||
<ProjectConfiguration Include="Debug|x64">
|
||||
<Configuration>Debug</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
<ProjectConfiguration Include="Release|x64">
|
||||
<Configuration>Release</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
</ItemGroup>
|
||||
<PropertyGroup Label="Globals">
|
||||
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||
<RootNamespace>simpleCudaGraphs_vs2013</RootNamespace>
|
||||
<ProjectName>simpleCudaGraphs</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup>
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v120</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 10.0.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)/simpleCudaGraphs.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_30,sm_30;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;</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="simpleCudaGraphs.cu" />
|
||||
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 10.0.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
20
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2015.sln
Normal file
20
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2015.sln
Normal file
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 14.00
|
||||
# Visual Studio 2015
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "simpleCudaGraphs", "simpleCudaGraphs_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
|
||||
107
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2015.vcxproj
Normal file
107
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2015.vcxproj
Normal file
@@ -0,0 +1,107 @@
|
||||
<?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>simpleCudaGraphs_vs2015</RootNamespace>
|
||||
<ProjectName>simpleCudaGraphs</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="$(CUDAPropsPath)\CUDA 10.0.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(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>$(OutDir)/simpleCudaGraphs.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_30,sm_30;compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
|
||||
<Include>./;../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(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="'$(Configuration)'=='Release'">
|
||||
<ClCompile>
|
||||
<Optimization>MaxSpeed</Optimization>
|
||||
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>false</GenerateDebugInformation>
|
||||
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<Runtime>MT</Runtime>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<CudaCompile Include="simpleCudaGraphs.cu" />
|
||||
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 10.0.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
20
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2017.sln
Normal file
20
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2017.sln
Normal file
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2017
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "simpleCudaGraphs", "simpleCudaGraphs_vs2017.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
|
||||
EndProject
|
||||
Global
|
||||
GlobalSection(SolutionConfigurationPlatforms) = preSolution
|
||||
Debug|x64 = Debug|x64
|
||||
Release|x64 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(ProjectConfigurationPlatforms) = postSolution
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(SolutionProperties) = preSolution
|
||||
HideSolutionNode = FALSE
|
||||
EndGlobalSection
|
||||
EndGlobal
|
||||
108
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj
Normal file
108
Samples/simpleCudaGraphs/simpleCudaGraphs_vs2017.vcxproj
Normal file
@@ -0,0 +1,108 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
|
||||
<PropertyGroup>
|
||||
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||
</PropertyGroup>
|
||||
<ItemGroup Label="ProjectConfigurations">
|
||||
<ProjectConfiguration Include="Debug|x64">
|
||||
<Configuration>Debug</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
<ProjectConfiguration Include="Release|x64">
|
||||
<Configuration>Release</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
</ItemGroup>
|
||||
<PropertyGroup Label="Globals">
|
||||
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||
<RootNamespace>simpleCudaGraphs_vs2017</RootNamespace>
|
||||
<ProjectName>simpleCudaGraphs</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup>
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v141</PlatformToolset>
|
||||
<WindowsTargetPlatformVersion>10.0.15063.0</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 10.0.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)/simpleCudaGraphs.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_30,sm_30;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;</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="simpleCudaGraphs.cu" />
|
||||
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 10.0.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
Reference in New Issue
Block a user