mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2024-11-24 19:09:14 +08:00
Updating graphConditionalNodes orphan directory
This commit is contained in:
Rob Nertney
parent
3559ca4d08
commit
5f97d7d0df
18
Samples/3_CUDA_Features/graphConditionalNodes/.vscode/c_cpp_properties.json
vendored
Normal file
18
Samples/3_CUDA_Features/graphConditionalNodes/.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/3_CUDA_Features/graphConditionalNodes/.vscode/extensions.json
vendored
Normal file
7
Samples/3_CUDA_Features/graphConditionalNodes/.vscode/extensions.json
vendored
Normal file
|
|
@ -0,0 +1,7 @@
|
||||||
|
{
|
||||||
|
"recommendations": [
|
||||||
|
"nvidia.nsight-vscode-edition",
|
||||||
|
"ms-vscode.cpptools",
|
||||||
|
"ms-vscode.makefile-tools"
|
||||||
|
]
|
||||||
|
}
|
||||||
10
Samples/3_CUDA_Features/graphConditionalNodes/.vscode/launch.json
vendored
Normal file
10
Samples/3_CUDA_Features/graphConditionalNodes/.vscode/launch.json
vendored
Normal file
|
|
@ -0,0 +1,10 @@
|
||||||
|
{
|
||||||
|
"configurations": [
|
||||||
|
{
|
||||||
|
"name": "CUDA C++: Launch",
|
||||||
|
"type": "cuda-gdb",
|
||||||
|
"request": "launch",
|
||||||
|
"program": "${workspaceFolder}/graphConditionalNodes"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
15
Samples/3_CUDA_Features/graphConditionalNodes/.vscode/tasks.json
vendored
Normal file
15
Samples/3_CUDA_Features/graphConditionalNodes/.vscode/tasks.json
vendored
Normal file
|
|
@ -0,0 +1,15 @@
|
||||||
|
{
|
||||||
|
"version": "2.0.0",
|
||||||
|
"tasks": [
|
||||||
|
{
|
||||||
|
"label": "sample",
|
||||||
|
"type": "shell",
|
||||||
|
"command": "make dbg=1",
|
||||||
|
"problemMatcher": ["$nvcc"],
|
||||||
|
"group": {
|
||||||
|
"kind": "build",
|
||||||
|
"isDefault": true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
350
Samples/3_CUDA_Features/graphConditionalNodes/Makefile
Normal file
350
Samples/3_CUDA_Features/graphConditionalNodes/Makefile
Normal file
|
|
@ -0,0 +1,350 @@
|
||||||
|
################################################################################
|
||||||
|
# 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 $(TARGET_OS) for TARGET_OS!)
|
||||||
|
endif
|
||||||
|
|
||||||
|
# host compiler
|
||||||
|
ifdef HOST_COMPILER
|
||||||
|
CUSTOM_HOST_COMPILER = 1
|
||||||
|
endif
|
||||||
|
|
||||||
|
ifeq ($(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 Mac OSX
|
||||||
|
ifeq ($(TARGET_OS),darwin)
|
||||||
|
$(info >>> WARNING - graphConditionalNodes is not supported on Mac OSX - waiving sample <<<)
|
||||||
|
SAMPLE_ENABLED := 0
|
||||||
|
endif
|
||||||
|
|
||||||
|
ALL_LDFLAGS :=
|
||||||
|
ALL_LDFLAGS += $(ALL_CCFLAGS)
|
||||||
|
ALL_LDFLAGS += $(addprefix -Xlinker ,$(LDFLAGS))
|
||||||
|
ALL_LDFLAGS += $(addprefix -Xlinker ,$(EXTRA_LDFLAGS))
|
||||||
|
|
||||||
|
# Common includes and paths for CUDA
|
||||||
|
INCLUDES := -I../../../Common
|
||||||
|
LIBRARIES :=
|
||||||
|
|
||||||
|
################################################################################
|
||||||
|
|
||||||
|
# Gencode arguments
|
||||||
|
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
|
||||||
|
SMS ?= 53 61 70 72 75 80 86 87 90
|
||||||
|
else
|
||||||
|
SMS ?= 50 52 60 61 70 75 80 86 89 90
|
||||||
|
endif
|
||||||
|
|
||||||
|
ifeq ($(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 ($(SAMPLE_ENABLED),0)
|
||||||
|
EXEC ?= @echo "[@]"
|
||||||
|
endif
|
||||||
|
|
||||||
|
################################################################################
|
||||||
|
|
||||||
|
# Target rules
|
||||||
|
all: build
|
||||||
|
|
||||||
|
build: graphConditionalNodes
|
||||||
|
|
||||||
|
check.deps:
|
||||||
|
ifeq ($(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
|
||||||
|
|
||||||
|
graphConditionalNodes.o:graphConditionalNodes.cu
|
||||||
|
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||||
|
|
||||||
|
graphConditionalNodes: graphConditionalNodes.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
|
||||||
|
$(EXEC) ./graphConditionalNodes
|
||||||
|
|
||||||
|
testrun: build
|
||||||
|
|
||||||
|
clean:
|
||||||
|
rm -f graphConditionalNodes graphConditionalNodes.o
|
||||||
|
rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/graphConditionalNodes
|
||||||
|
|
||||||
|
clobber: clean
|
||||||
|
|
@ -0,0 +1,86 @@
|
||||||
|
<?xml version="1.0" encoding="UTF-8"?>
|
||||||
|
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
||||||
|
<entry>
|
||||||
|
<name>graphConditionalNodes</name>
|
||||||
|
<cuda_api_list>
|
||||||
|
<toolkit>cudaDeviceSynchronize</toolkit>
|
||||||
|
<toolkit>cudaDriverGetVersion</toolkit>
|
||||||
|
<toolkit>cudaFree</toolkit>
|
||||||
|
<toolkit>cudaGraphAddNode</toolkit>
|
||||||
|
<toolkit>cudaGraphConditionalHandleCreate</toolkit>
|
||||||
|
<toolkit>cudaGraphCreate</toolkit>
|
||||||
|
<toolkit>cudaGraphDestroy</toolkit>
|
||||||
|
<toolkit>cudaGraphExecDestroy</toolkit>
|
||||||
|
<toolkit>cudaGraphInstantiate</toolkit>
|
||||||
|
<toolkit>cudaGraphLaunch</toolkit>
|
||||||
|
<toolkit>cudaGraphSetConditional</toolkit>
|
||||||
|
<toolkit>cudaMalloc</toolkit>
|
||||||
|
<toolkit>cudaMemset</toolkit>
|
||||||
|
<toolkit>cudaStreamBeginCapture</toolkit>
|
||||||
|
<toolkit>cudaStreamBeginCaptureToGraph</toolkit>
|
||||||
|
<toolkit>cudaStreamCreate</toolkit>
|
||||||
|
<toolkit>cudaStreamDestroy</toolkit>
|
||||||
|
<toolkit>cudaStreamEndCapture</toolkit>
|
||||||
|
<toolkit>cudaStreamGetCaptureInfo</toolkit>
|
||||||
|
</cuda_api_list>
|
||||||
|
<description><![CDATA[A demonstration of CUDA graphs conditional nodes.]]></description>
|
||||||
|
<devicecompilation>whole</devicecompilation>
|
||||||
|
<includepaths>
|
||||||
|
<path>./</path>
|
||||||
|
<path>../</path>
|
||||||
|
<path>../../../Common</path>
|
||||||
|
</includepaths>
|
||||||
|
<keyconcepts>
|
||||||
|
<concept level="basic">CUDA Graphs</concept>
|
||||||
|
</keyconcepts>
|
||||||
|
<keywords>
|
||||||
|
<keyword>CUDA</keyword>
|
||||||
|
<keyword>CUDA Graphs</keyword>
|
||||||
|
<keyword>Streams</keyword>
|
||||||
|
<keyword>GPGPU</keyword>
|
||||||
|
<keyword>Graph Conditional Nodes</keyword>
|
||||||
|
</keywords>
|
||||||
|
<libraries>
|
||||||
|
</libraries>
|
||||||
|
<librarypaths>
|
||||||
|
</librarypaths>
|
||||||
|
<nsight_eclipse>true</nsight_eclipse>
|
||||||
|
<primary_file>graphConditionalNodes.cu</primary_file>
|
||||||
|
<scopes>
|
||||||
|
<scope>1:CUDA Basic Topics</scope>
|
||||||
|
</scopes>
|
||||||
|
<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>
|
||||||
|
<sm-arch>sm89</sm-arch>
|
||||||
|
<sm-arch>sm90</sm-arch>
|
||||||
|
<supported_envs>
|
||||||
|
<env>
|
||||||
|
<arch>x86_64</arch>
|
||||||
|
<platform>linux</platform>
|
||||||
|
</env>
|
||||||
|
<env>
|
||||||
|
<platform>windows7</platform>
|
||||||
|
</env>
|
||||||
|
<env>
|
||||||
|
<arch>arm</arch>
|
||||||
|
</env>
|
||||||
|
<env>
|
||||||
|
<arch>sbsa</arch>
|
||||||
|
</env>
|
||||||
|
<env>
|
||||||
|
<arch>ppc64le</arch>
|
||||||
|
<platform>linux</platform>
|
||||||
|
</env>
|
||||||
|
</supported_envs>
|
||||||
|
<supported_sm_architectures>
|
||||||
|
<from>6.0</from>
|
||||||
|
</supported_sm_architectures>
|
||||||
|
<title>Graph Conditional Nodes</title>
|
||||||
|
<type>exe</type>
|
||||||
|
</entry>
|
||||||
70
Samples/3_CUDA_Features/graphConditionalNodes/README.md
Normal file
70
Samples/3_CUDA_Features/graphConditionalNodes/README.md
Normal file
|
|
@ -0,0 +1,70 @@
|
||||||
|
# graphConditionalNodes - Graph Conditional Nodes
|
||||||
|
|
||||||
|
## Description
|
||||||
|
|
||||||
|
A demonstration of CUDA graphs conditional nodes.
|
||||||
|
|
||||||
|
## Key Concepts
|
||||||
|
|
||||||
|
CUDA Graphs
|
||||||
|
|
||||||
|
## Supported SM Architectures
|
||||||
|
|
||||||
|
[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) [SM 8.9 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
|
||||||
|
|
||||||
|
## Supported OSes
|
||||||
|
|
||||||
|
Linux, Windows
|
||||||
|
|
||||||
|
## Supported CPU Architecture
|
||||||
|
|
||||||
|
x86_64, ppc64le, armv7l
|
||||||
|
|
||||||
|
## CUDA APIs involved
|
||||||
|
|
||||||
|
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
|
||||||
|
cudaDeviceSynchronize, cudaDriverGetVersion, cudaFree, cudaGraphAddNode, cudaGraphConditionalHandleCreate, cudaGraphCreate, cudaGraphDestroy, cudaGraphExecDestroy, cudaGraphInstantiate, cudaGraphLaunch, cudaGraphSetConditional, cudaMalloc, cudaMemset, cudaStreamBeginCapture, cudaStreamBeginCaptureToGraph, cudaStreamCreate, cudaStreamDestroy, cudaStreamEndCapture, cudaStreamGetCaptureInfo
|
||||||
|
|
||||||
|
## Prerequisites
|
||||||
|
|
||||||
|
Download and install the [CUDA Toolkit 12.4](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++
|
||||||
|
```
|
||||||
|
|
||||||
|
## References (for more details)
|
||||||
|
|
||||||
|
|
@ -0,0 +1,356 @@
|
||||||
|
/* Copyright (c) 2023, 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.
|
||||||
|
*/
|
||||||
|
|
||||||
|
/*
|
||||||
|
* This file demonstrates the usage of conditional graph nodes with
|
||||||
|
* a series of *simple* example graphs.
|
||||||
|
*
|
||||||
|
* For more information on conditional nodes, see the programming guide:
|
||||||
|
*
|
||||||
|
* https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#conditional-graph-nodes
|
||||||
|
*
|
||||||
|
*/
|
||||||
|
|
||||||
|
// System includes
|
||||||
|
#include <cassert>
|
||||||
|
#include <cstdio>
|
||||||
|
|
||||||
|
// CUDA runtime
|
||||||
|
#include <cuda_runtime.h>
|
||||||
|
|
||||||
|
// helper functions and utilities to work with CUDA
|
||||||
|
#include <helper_cuda.h>
|
||||||
|
#include <helper_functions.h>
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Create a graph containing two nodes.
|
||||||
|
* The first node, A, is a kernel and the second node, B, is a conditional IF node.
|
||||||
|
* The kernel sets the condition variable to true if a device memory location
|
||||||
|
* contains an odd number. Otherwise the condition variable is set to false.
|
||||||
|
* There is a single kernel, C, within the conditional body which prints a message.
|
||||||
|
*
|
||||||
|
* A -> B [ C ]
|
||||||
|
*
|
||||||
|
*/
|
||||||
|
|
||||||
|
__global__ void ifGraphKernelA(char *dPtr, cudaGraphConditionalHandle handle)
|
||||||
|
{
|
||||||
|
// In this example, condition is set if *dPtr is odd
|
||||||
|
unsigned int value = *dPtr & 0x01;
|
||||||
|
cudaGraphSetConditional(handle, value);
|
||||||
|
printf("GPU: Handle set to %d\n", value);
|
||||||
|
}
|
||||||
|
|
||||||
|
// This kernel will only be executed if the condition is true
|
||||||
|
__global__ void ifGraphKernelC(void)
|
||||||
|
{
|
||||||
|
printf("GPU: Hello from the GPU!\n");
|
||||||
|
}
|
||||||
|
|
||||||
|
// Setup and launch the graph
|
||||||
|
void simpleIfGraph(void)
|
||||||
|
{
|
||||||
|
cudaGraph_t graph;
|
||||||
|
cudaGraphExec_t graphExec;
|
||||||
|
cudaGraphNode_t node;
|
||||||
|
|
||||||
|
void *kernelArgs[2];
|
||||||
|
|
||||||
|
// Allocate a byte of device memory to use as input
|
||||||
|
char *dPtr;
|
||||||
|
checkCudaErrors(cudaMalloc((void**)&dPtr, 1));
|
||||||
|
|
||||||
|
printf("simpleIfGraph: Building graph...\n");
|
||||||
|
cudaGraphCreate(&graph, 0);
|
||||||
|
|
||||||
|
// Create conditional handle.
|
||||||
|
cudaGraphConditionalHandle handle;
|
||||||
|
cudaGraphConditionalHandleCreate(&handle, graph);
|
||||||
|
|
||||||
|
// Use a kernel upstream of the conditional to set the handle value
|
||||||
|
cudaGraphNodeParams params = { cudaGraphNodeTypeKernel };
|
||||||
|
params.kernel.func = (void *)ifGraphKernelA;
|
||||||
|
params.kernel.gridDim.x = params.kernel.gridDim.y = params.kernel.gridDim.z = 1;
|
||||||
|
params.kernel.blockDim.x = params.kernel.blockDim.y = params.kernel.blockDim.z = 1;
|
||||||
|
params.kernel.kernelParams = kernelArgs;
|
||||||
|
kernelArgs[0] = &dPtr;
|
||||||
|
kernelArgs[1] = &handle;
|
||||||
|
checkCudaErrors(cudaGraphAddNode(&node, graph, NULL, 0, ¶ms));
|
||||||
|
|
||||||
|
cudaGraphNodeParams cParams = { cudaGraphNodeTypeConditional };
|
||||||
|
cParams.conditional.handle = handle;
|
||||||
|
cParams.conditional.type = cudaGraphCondTypeIf;
|
||||||
|
cParams.conditional.size = 1;
|
||||||
|
checkCudaErrors(cudaGraphAddNode(&node, graph, &node, 1, &cParams));
|
||||||
|
|
||||||
|
cudaGraph_t bodyGraph = cParams.conditional.phGraph_out[0];
|
||||||
|
|
||||||
|
// Populate the body of the conditional node
|
||||||
|
cudaGraphNode_t bodyNode;
|
||||||
|
params.kernel.func = (void *)ifGraphKernelC;
|
||||||
|
params.kernel.kernelParams = nullptr;
|
||||||
|
checkCudaErrors(cudaGraphAddNode(&bodyNode, bodyGraph, NULL, 0, ¶ms));
|
||||||
|
|
||||||
|
checkCudaErrors(cudaGraphInstantiate(&graphExec, graph, NULL, NULL, 0));
|
||||||
|
|
||||||
|
// Initialize device memory and launch the graph
|
||||||
|
checkCudaErrors(cudaMemset(dPtr, 0, 1)); // Set dPtr to 0
|
||||||
|
printf("Host: Launching graph with conditional value set to false\n");
|
||||||
|
checkCudaErrors(cudaGraphLaunch(graphExec, 0));
|
||||||
|
checkCudaErrors(cudaDeviceSynchronize());
|
||||||
|
|
||||||
|
// Initialize device memory and launch the graph
|
||||||
|
checkCudaErrors(cudaMemset(dPtr, 1, 1)); // Set dPtr to 1
|
||||||
|
printf("Host: Launching graph with conditional value set to true\n");
|
||||||
|
checkCudaErrors(cudaGraphLaunch(graphExec, 0));
|
||||||
|
checkCudaErrors(cudaDeviceSynchronize());
|
||||||
|
|
||||||
|
// Cleanup
|
||||||
|
checkCudaErrors(cudaGraphExecDestroy(graphExec));
|
||||||
|
checkCudaErrors(cudaGraphDestroy(graph));
|
||||||
|
checkCudaErrors(cudaFree(dPtr));
|
||||||
|
|
||||||
|
printf("simpleIfGraph: Complete\n\n");
|
||||||
|
}
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Create a graph containing a single conditional while node.
|
||||||
|
* The default value of the conditional variable is set to true, so this
|
||||||
|
* effectively becomes a do-while loop as the conditional body will always
|
||||||
|
* execute at least once. The body of the conditional contains 3 kernel nodes:
|
||||||
|
* A [ B -> C -> D ]
|
||||||
|
* Nodes B and C are just dummy nodes for demonstrative purposes. Node D
|
||||||
|
* will decrement a device memory location and set the condition value to false
|
||||||
|
* when the value reaches zero, terminating the loop.
|
||||||
|
* In this example, stream capture is used to populate the conditional body.
|
||||||
|
*/
|
||||||
|
|
||||||
|
// This kernel will only be executed if the condition is true
|
||||||
|
__global__ void doWhileEmptyKernel(void)
|
||||||
|
{
|
||||||
|
printf("GPU: doWhileEmptyKernel()\n");
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
|
__global__ void doWhileLoopKernel(char *dPtr, cudaGraphConditionalHandle handle)
|
||||||
|
{
|
||||||
|
if (--(*dPtr) == 0) {
|
||||||
|
cudaGraphSetConditional(handle, 0);
|
||||||
|
}
|
||||||
|
printf("GPU: counter = %d\n", *dPtr);
|
||||||
|
}
|
||||||
|
|
||||||
|
void simpleDoWhileGraph(void)
|
||||||
|
{
|
||||||
|
cudaGraph_t graph;
|
||||||
|
cudaGraphExec_t graphExec;
|
||||||
|
cudaGraphNode_t node;
|
||||||
|
|
||||||
|
// Allocate a byte of device memory to use as input
|
||||||
|
char *dPtr;
|
||||||
|
checkCudaErrors(cudaMalloc((void**)&dPtr, 1));
|
||||||
|
|
||||||
|
printf("simpleDoWhileGraph: Building graph...\n");
|
||||||
|
checkCudaErrors(cudaGraphCreate(&graph, 0));
|
||||||
|
|
||||||
|
cudaGraphConditionalHandle handle;
|
||||||
|
checkCudaErrors(cudaGraphConditionalHandleCreate(&handle, graph, 1, cudaGraphCondAssignDefault));
|
||||||
|
|
||||||
|
cudaGraphNodeParams cParams = { cudaGraphNodeTypeConditional };
|
||||||
|
cParams.conditional.handle = handle;
|
||||||
|
cParams.conditional.type = cudaGraphCondTypeWhile;
|
||||||
|
cParams.conditional.size = 1;
|
||||||
|
checkCudaErrors(cudaGraphAddNode(&node, graph, NULL, 0, &cParams));
|
||||||
|
|
||||||
|
cudaGraph_t bodyGraph = cParams.conditional.phGraph_out[0];
|
||||||
|
|
||||||
|
cudaStream_t captureStream;
|
||||||
|
checkCudaErrors(cudaStreamCreate(&captureStream));
|
||||||
|
|
||||||
|
checkCudaErrors(cudaStreamBeginCaptureToGraph(captureStream, bodyGraph, nullptr, nullptr, 0, cudaStreamCaptureModeRelaxed));
|
||||||
|
doWhileEmptyKernel<<<1, 1, 0, captureStream>>>();
|
||||||
|
doWhileEmptyKernel<<<1, 1, 0, captureStream>>>();
|
||||||
|
doWhileLoopKernel<<<1, 1, 0, captureStream>>>(dPtr, handle);
|
||||||
|
checkCudaErrors(cudaStreamEndCapture(captureStream, nullptr));
|
||||||
|
checkCudaErrors(cudaStreamDestroy(captureStream));
|
||||||
|
|
||||||
|
checkCudaErrors(cudaGraphInstantiate(&graphExec, graph, NULL, NULL, 0));
|
||||||
|
|
||||||
|
// Initialize device memory and launch the graph
|
||||||
|
checkCudaErrors(cudaMemset(dPtr, 10, 1)); // Set dPtr to 10
|
||||||
|
printf("Host: Launching graph with loop counter set to 10\n");
|
||||||
|
checkCudaErrors(cudaGraphLaunch(graphExec, 0));
|
||||||
|
checkCudaErrors(cudaDeviceSynchronize());
|
||||||
|
|
||||||
|
// Cleanup
|
||||||
|
checkCudaErrors(cudaGraphExecDestroy(graphExec));
|
||||||
|
checkCudaErrors(cudaGraphDestroy(graph));
|
||||||
|
checkCudaErrors(cudaFree(dPtr));
|
||||||
|
|
||||||
|
printf("simpleDoWhileGraph: Complete\n\n");
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Create a graph containing a conditional while loop using stream capture.
|
||||||
|
* This demonstrates how to insert a conditional node into a stream which is
|
||||||
|
* being captured. The graph consists of a kernel node followed by a conditional
|
||||||
|
* while node which contains a single kernel node:
|
||||||
|
*
|
||||||
|
* A -> B [ C ]
|
||||||
|
*
|
||||||
|
* The same kernel will be used for both nodes A and C. This kernel will test
|
||||||
|
* a device memory location and set the condition when the location is non-zero.
|
||||||
|
* We must run the kernel before the loop as well as inside the loop in order
|
||||||
|
* to behave like a while loop. We need to evaluate the device memory location
|
||||||
|
* before the conditional node is evaluated in order to set the condition variable
|
||||||
|
* properly. Because we're using a kernel upstream of the conditional node,
|
||||||
|
* there is no need to use the handle default value to initialize the conditional
|
||||||
|
* value.
|
||||||
|
*/
|
||||||
|
|
||||||
|
__global__ void capturedWhileKernel(char *dPtr, cudaGraphConditionalHandle handle)
|
||||||
|
{
|
||||||
|
printf("GPU: counter = %d\n", *dPtr);
|
||||||
|
if (*dPtr) {
|
||||||
|
(*dPtr)--;
|
||||||
|
}
|
||||||
|
cudaGraphSetConditional(handle, *dPtr);
|
||||||
|
}
|
||||||
|
|
||||||
|
__global__ void capturedWhileEmptyKernel(void)
|
||||||
|
{
|
||||||
|
printf("GPU: capturedWhileEmptyKernel()\n");
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
|
void capturedWhileGraph(void)
|
||||||
|
{
|
||||||
|
cudaGraph_t graph;
|
||||||
|
cudaGraphExec_t graphExec;
|
||||||
|
|
||||||
|
cudaStreamCaptureStatus status;
|
||||||
|
const cudaGraphNode_t *dependencies;
|
||||||
|
size_t numDependencies;
|
||||||
|
|
||||||
|
// Allocate a byte of device memory to use as input
|
||||||
|
char *dPtr;
|
||||||
|
checkCudaErrors(cudaMalloc((void**)&dPtr, 1));
|
||||||
|
|
||||||
|
printf("capturedWhileGraph: Building graph...\n");
|
||||||
|
cudaStream_t captureStream;
|
||||||
|
checkCudaErrors(cudaStreamCreate(&captureStream));
|
||||||
|
|
||||||
|
checkCudaErrors(cudaStreamBeginCapture(captureStream, cudaStreamCaptureModeRelaxed));
|
||||||
|
|
||||||
|
// Obtain the handle of the graph
|
||||||
|
checkCudaErrors(cudaStreamGetCaptureInfo(captureStream, &status, NULL, &graph, &dependencies, &numDependencies));
|
||||||
|
|
||||||
|
// Create the conditional handle
|
||||||
|
cudaGraphConditionalHandle handle;
|
||||||
|
checkCudaErrors(cudaGraphConditionalHandleCreate(&handle, graph));
|
||||||
|
|
||||||
|
// Insert kernel node A
|
||||||
|
capturedWhileKernel<<<1, 1, 0, captureStream>>>(dPtr, handle);
|
||||||
|
|
||||||
|
// Obtain the handle for node A
|
||||||
|
checkCudaErrors(cudaStreamGetCaptureInfo(captureStream, &status, NULL, &graph, &dependencies, &numDependencies));
|
||||||
|
|
||||||
|
// Insert conditional node B
|
||||||
|
cudaGraphNode_t node;
|
||||||
|
cudaGraphNodeParams cParams = { cudaGraphNodeTypeConditional };
|
||||||
|
cParams.conditional.handle = handle;
|
||||||
|
cParams.conditional.type = cudaGraphCondTypeWhile;
|
||||||
|
cParams.conditional.size = 1;
|
||||||
|
checkCudaErrors(cudaGraphAddNode(&node, graph, dependencies, numDependencies, &cParams));
|
||||||
|
|
||||||
|
cudaGraph_t bodyGraph = cParams.conditional.phGraph_out[0];
|
||||||
|
|
||||||
|
// Update stream capture dependencies to account for the node we manually added
|
||||||
|
checkCudaErrors(cudaStreamUpdateCaptureDependencies(captureStream, &node, 1, cudaStreamSetCaptureDependencies));
|
||||||
|
|
||||||
|
// Insert kernel node D
|
||||||
|
capturedWhileEmptyKernel<<<1, 1, 0, captureStream>>>();
|
||||||
|
|
||||||
|
checkCudaErrors(cudaStreamEndCapture(captureStream, &graph));
|
||||||
|
checkCudaErrors(cudaStreamDestroy(captureStream));
|
||||||
|
|
||||||
|
// Populate conditional body graph using stream capture
|
||||||
|
cudaStream_t bodyStream;
|
||||||
|
checkCudaErrors(cudaStreamCreate(&bodyStream));
|
||||||
|
|
||||||
|
checkCudaErrors(cudaStreamBeginCaptureToGraph(bodyStream, bodyGraph, nullptr, nullptr, 0, cudaStreamCaptureModeRelaxed));
|
||||||
|
|
||||||
|
// Insert kernel node C
|
||||||
|
capturedWhileKernel<<<1, 1, 0, bodyStream>>>(dPtr, handle);
|
||||||
|
checkCudaErrors(cudaStreamEndCapture(bodyStream, nullptr));
|
||||||
|
checkCudaErrors(cudaStreamDestroy(bodyStream));
|
||||||
|
|
||||||
|
checkCudaErrors(cudaGraphInstantiate(&graphExec, graph, NULL, NULL, 0));
|
||||||
|
|
||||||
|
// Initialize device memory and launch the graph
|
||||||
|
// Device memory is zero, so the conditional node will not execute
|
||||||
|
checkCudaErrors(cudaMemset(dPtr, 0, 1)); // Set dPtr to 0
|
||||||
|
printf("Host: Launching graph with loop counter set to 0\n");
|
||||||
|
checkCudaErrors(cudaGraphLaunch(graphExec, 0));
|
||||||
|
checkCudaErrors(cudaDeviceSynchronize());
|
||||||
|
|
||||||
|
// Initialize device memory and launch the graph
|
||||||
|
checkCudaErrors(cudaMemset(dPtr, 10, 1)); // Set dPtr to 10
|
||||||
|
printf("Host: Launching graph with loop counter set to 10\n");
|
||||||
|
checkCudaErrors(cudaGraphLaunch(graphExec, 0));
|
||||||
|
checkCudaErrors(cudaDeviceSynchronize());
|
||||||
|
|
||||||
|
// Cleanup
|
||||||
|
checkCudaErrors(cudaGraphExecDestroy(graphExec));
|
||||||
|
checkCudaErrors(cudaGraphDestroy(graph));
|
||||||
|
checkCudaErrors(cudaFree(dPtr));
|
||||||
|
|
||||||
|
printf("capturedWhileGraph: Complete\n\n");
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
int main(int argc, char **argv) {
|
||||||
|
int device = findCudaDevice(argc, (const char **)argv);
|
||||||
|
|
||||||
|
int driverVersion = 0;
|
||||||
|
|
||||||
|
cudaDriverGetVersion(&driverVersion);
|
||||||
|
printf("Driver version is: %d.%d\n", driverVersion / 1000,
|
||||||
|
(driverVersion % 100) / 10);
|
||||||
|
|
||||||
|
if (driverVersion < 12030) {
|
||||||
|
printf("Waiving execution as driver does not support Graph Conditional Nodes\n");
|
||||||
|
exit(EXIT_WAIVED);
|
||||||
|
}
|
||||||
|
|
||||||
|
simpleIfGraph();
|
||||||
|
simpleDoWhileGraph();
|
||||||
|
capturedWhileGraph();
|
||||||
|
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,20 @@
|
||||||
|
|
||||||
|
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||||
|
# Visual Studio 2017
|
||||||
|
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "graphConditionalNodes", "graphConditionalNodes_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 +1,112 @@
|
||||||
|
<?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>graphConditionalNodes_vs2017</RootNamespace>
|
||||||
|
<ProjectName>graphConditionalNodes</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 12.4.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)/graphConditionalNodes.exe</OutputFile>
|
||||||
|
</Link>
|
||||||
|
<CudaCompile>
|
||||||
|
<CodeGeneration>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;compute_89,sm_89;compute_90,sm_90;</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>
|
||||||
|
<ItemGroup>
|
||||||
|
<CudaCompile Include="graphConditionalNodes.cu" />
|
||||||
|
|
||||||
|
</ItemGroup>
|
||||||
|
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||||
|
<ImportGroup Label="ExtensionTargets">
|
||||||
|
<Import Project="$(CUDAPropsPath)\CUDA 12.4.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}") = "graphConditionalNodes", "graphConditionalNodes_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 +1,108 @@
|
||||||
|
<?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>graphConditionalNodes_vs2019</RootNamespace>
|
||||||
|
<ProjectName>graphConditionalNodes</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="$(CUDAPropsPath)\CUDA 12.4.props" />
|
||||||
|
</ImportGroup>
|
||||||
|
<ImportGroup Label="PropertySheets">
|
||||||
|
<Import Condition="exists('$(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>$(OutDir)/graphConditionalNodes.exe</OutputFile>
|
||||||
|
</Link>
|
||||||
|
<CudaCompile>
|
||||||
|
<CodeGeneration>compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;compute_89,sm_89;compute_90,sm_90;</CodeGeneration>
|
||||||
|
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
|
||||||
|
<Include>./;../../../Common</Include>
|
||||||
|
<Defines>WIN32</Defines>
|
||||||
|
</CudaCompile>
|
||||||
|
</ItemDefinitionGroup>
|
||||||
|
<ItemDefinitionGroup Condition="'$(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="'$(Configuration)'=='Release'">
|
||||||
|
<ClCompile>
|
||||||
|
<Optimization>MaxSpeed</Optimization>
|
||||||
|
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
|
||||||
|
</ClCompile>
|
||||||
|
<Link>
|
||||||
|
<GenerateDebugInformation>false</GenerateDebugInformation>
|
||||||
|
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
|
||||||
|
</Link>
|
||||||
|
<CudaCompile>
|
||||||
|
<Runtime>MT</Runtime>
|
||||||
|
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||||
|
</CudaCompile>
|
||||||
|
</ItemDefinitionGroup>
|
||||||
|
<ItemGroup>
|
||||||
|
<CudaCompile Include="graphConditionalNodes.cu" />
|
||||||
|
|
||||||
|
</ItemGroup>
|
||||||
|
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||||
|
<ImportGroup Label="ExtensionTargets">
|
||||||
|
<Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
|
||||||
|
</ImportGroup>
|
||||||
|
</Project>
|
||||||
|
|
@ -0,0 +1,20 @@
|
||||||
|
|
||||||
|
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||||
|
# Visual Studio 2022
|
||||||
|
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "graphConditionalNodes", "graphConditionalNodes_vs2022.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
|
||||||
|
EndProject
|
||||||
|
Global
|
||||||
|
GlobalSection(SolutionConfigurationPlatforms) = preSolution
|
||||||
|
Debug|x64 = Debug|x64
|
||||||
|
Release|x64 = Release|x64
|
||||||
|
EndGlobalSection
|
||||||
|
GlobalSection(ProjectConfigurationPlatforms) = postSolution
|
||||||
|
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
|
||||||
|
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
|
||||||
|
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
|
||||||
|
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
|
||||||
|
EndGlobalSection
|
||||||
|
GlobalSection(SolutionProperties) = preSolution
|
||||||
|
HideSolutionNode = FALSE
|
||||||
|
EndGlobalSection
|
||||||
|
EndGlobal
|
||||||
|
|
@ -0,0 +1,108 @@
|
||||||
|
<?xml version="1.0" encoding="utf-8"?>
|
||||||
|
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
|
||||||
|
<PropertyGroup>
|
||||||
|
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||||
|
</PropertyGroup>
|
||||||
|
<ItemGroup Label="ProjectConfigurations">
|
||||||
|
<ProjectConfiguration Include="Debug|x64">
|
||||||
|
<Configuration>Debug</Configuration>
|
||||||
|
<Platform>x64</Platform>
|
||||||
|
</ProjectConfiguration>
|
||||||
|
<ProjectConfiguration Include="Release|x64">
|
||||||
|
<Configuration>Release</Configuration>
|
||||||
|
<Platform>x64</Platform>
|
||||||
|
</ProjectConfiguration>
|
||||||
|
</ItemGroup>
|
||||||
|
<PropertyGroup Label="Globals">
|
||||||
|
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||||
|
<RootNamespace>graphConditionalNodes_vs2022</RootNamespace>
|
||||||
|
<ProjectName>graphConditionalNodes</ProjectName>
|
||||||
|
<CudaToolkitCustomDir />
|
||||||
|
</PropertyGroup>
|
||||||
|
<Import Project="$(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 12.4.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)/graphConditionalNodes.exe</OutputFile>
|
||||||
|
</Link>
|
||||||
|
<CudaCompile>
|
||||||
|
<CodeGeneration>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;compute_89,sm_89;compute_90,sm_90;</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>
|
||||||
|
<ItemGroup>
|
||||||
|
<CudaCompile Include="graphConditionalNodes.cu" />
|
||||||
|
|
||||||
|
</ItemGroup>
|
||||||
|
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||||
|
<ImportGroup Label="ExtensionTargets">
|
||||||
|
<Import Project="$(CUDAPropsPath)\CUDA 12.4.targets" />
|
||||||
|
</ImportGroup>
|
||||||
|
</Project>
|
||||||
Loading…
Reference in New Issue
Block a user