mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2026-10-23 21:28:17 +08:00
add and update samples for CUDA 11.6
This commit is contained in:
Rutwik Choughule
18
Samples/5_Domain_Specific/quasirandomGenerator/.vscode/c_cpp_properties.json
vendored
Normal file
18
Samples/5_Domain_Specific/quasirandomGenerator/.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/5_Domain_Specific/quasirandomGenerator/.vscode/extensions.json
vendored
Normal file
7
Samples/5_Domain_Specific/quasirandomGenerator/.vscode/extensions.json
vendored
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"recommendations": [
|
||||
"nvidia.nsight-vscode-edition",
|
||||
"ms-vscode.cpptools",
|
||||
"ms-vscode.makefile-tools"
|
||||
]
|
||||
}
|
||||
10
Samples/5_Domain_Specific/quasirandomGenerator/.vscode/launch.json
vendored
Normal file
10
Samples/5_Domain_Specific/quasirandomGenerator/.vscode/launch.json
vendored
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"configurations": [
|
||||
{
|
||||
"name": "CUDA C++: Launch",
|
||||
"type": "cuda-gdb",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/quasirandomGenerator"
|
||||
}
|
||||
]
|
||||
}
|
||||
15
Samples/5_Domain_Specific/quasirandomGenerator/.vscode/tasks.json
vendored
Normal file
15
Samples/5_Domain_Specific/quasirandomGenerator/.vscode/tasks.json
vendored
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"version": "2.0.0",
|
||||
"tasks": [
|
||||
{
|
||||
"label": "sample",
|
||||
"type": "shell",
|
||||
"command": "make dbg=1",
|
||||
"problemMatcher": ["$nvcc"],
|
||||
"group": {
|
||||
"kind": "build",
|
||||
"isDefault": true
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
346
Samples/5_Domain_Specific/quasirandomGenerator/Makefile
Normal file
346
Samples/5_Domain_Specific/quasirandomGenerator/Makefile
Normal file
@@ -0,0 +1,346 @@
|
||||
################################################################################
|
||||
# Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved.
|
||||
#
|
||||
# Redistribution and use in source and binary forms, with or without
|
||||
# modification, are permitted provided that the following conditions
|
||||
# are met:
|
||||
# * Redistributions of source code must retain the above copyright
|
||||
# notice, this list of conditions and the following disclaimer.
|
||||
# * Redistributions in binary form must reproduce the above copyright
|
||||
# notice, this list of conditions and the following disclaimer in the
|
||||
# documentation and/or other materials provided with the distribution.
|
||||
# * Neither the name of NVIDIA CORPORATION nor the names of its
|
||||
# contributors may be used to endorse or promote products derived
|
||||
# from this software without specific prior written permission.
|
||||
#
|
||||
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
|
||||
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
||||
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
||||
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
#
|
||||
################################################################################
|
||||
#
|
||||
# Makefile project only supported on Mac OS X and Linux Platforms)
|
||||
#
|
||||
################################################################################
|
||||
|
||||
# Location of the CUDA Toolkit
|
||||
CUDA_PATH ?= /usr/local/cuda
|
||||
|
||||
##############################
|
||||
# start deprecated interface #
|
||||
##############################
|
||||
ifeq ($(x86_64),1)
|
||||
$(info WARNING - x86_64 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=x86_64 instead)
|
||||
TARGET_ARCH ?= x86_64
|
||||
endif
|
||||
ifeq ($(ARMv7),1)
|
||||
$(info WARNING - ARMv7 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=armv7l instead)
|
||||
TARGET_ARCH ?= armv7l
|
||||
endif
|
||||
ifeq ($(aarch64),1)
|
||||
$(info WARNING - aarch64 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=aarch64 instead)
|
||||
TARGET_ARCH ?= aarch64
|
||||
endif
|
||||
ifeq ($(ppc64le),1)
|
||||
$(info WARNING - ppc64le variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=ppc64le instead)
|
||||
TARGET_ARCH ?= ppc64le
|
||||
endif
|
||||
ifneq ($(GCC),)
|
||||
$(info WARNING - GCC variable has been deprecated)
|
||||
$(info WARNING - please use HOST_COMPILER=$(GCC) instead)
|
||||
HOST_COMPILER ?= $(GCC)
|
||||
endif
|
||||
ifneq ($(abi),)
|
||||
$(error ERROR - abi variable has been removed)
|
||||
endif
|
||||
############################
|
||||
# end deprecated interface #
|
||||
############################
|
||||
|
||||
# architecture
|
||||
HOST_ARCH := $(shell uname -m)
|
||||
TARGET_ARCH ?= $(HOST_ARCH)
|
||||
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le armv7l))
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le))
|
||||
TARGET_SIZE := 64
|
||||
else ifneq (,$(filter $(TARGET_ARCH),armv7l))
|
||||
TARGET_SIZE := 32
|
||||
endif
|
||||
else
|
||||
TARGET_SIZE := $(shell getconf LONG_BIT)
|
||||
endif
|
||||
else
|
||||
$(error ERROR - unsupported value $(TARGET_ARCH) for TARGET_ARCH!)
|
||||
endif
|
||||
|
||||
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
|
||||
ifeq ($(HOST_ARCH),aarch64)
|
||||
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
|
||||
HOST_ARCH := sbsa
|
||||
TARGET_ARCH := sbsa
|
||||
endif
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq (,$(filter $(HOST_ARCH)-$(TARGET_ARCH),aarch64-armv7l x86_64-armv7l x86_64-aarch64 x86_64-sbsa x86_64-ppc64le))
|
||||
$(error ERROR - cross compiling from $(HOST_ARCH) to $(TARGET_ARCH) is not supported!)
|
||||
endif
|
||||
endif
|
||||
|
||||
# When on native aarch64 system with userspace of 32-bit, change TARGET_ARCH to armv7l
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_SIZE),aarch64-aarch64-32)
|
||||
TARGET_ARCH = armv7l
|
||||
endif
|
||||
|
||||
# operating system
|
||||
HOST_OS := $(shell uname -s 2>/dev/null | tr "[:upper:]" "[:lower:]")
|
||||
TARGET_OS ?= $(HOST_OS)
|
||||
ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
|
||||
$(error ERROR - unsupported value $(TARGET_OS) for TARGET_OS!)
|
||||
endif
|
||||
|
||||
# host compiler
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
ifeq ($(shell expr `xcodebuild -version | grep -i xcode | awk '{print $$2}' | cut -d'.' -f1` \>= 5),1)
|
||||
HOST_COMPILER ?= clang++
|
||||
endif
|
||||
else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l)
|
||||
ifeq ($(TARGET_OS),linux)
|
||||
HOST_COMPILER ?= arm-linux-gnueabihf-g++
|
||||
else ifeq ($(TARGET_OS),qnx)
|
||||
ifeq ($(QNX_HOST),)
|
||||
$(error ERROR - QNX_HOST must be passed to the QNX host toolchain)
|
||||
endif
|
||||
ifeq ($(QNX_TARGET),)
|
||||
$(error ERROR - QNX_TARGET must be passed to the QNX target toolchain)
|
||||
endif
|
||||
export QNX_HOST
|
||||
export QNX_TARGET
|
||||
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/arm-unknown-nto-qnx6.6.0eabi-g++
|
||||
else ifeq ($(TARGET_OS),android)
|
||||
HOST_COMPILER ?= arm-linux-androideabi-g++
|
||||
endif
|
||||
else ifeq ($(TARGET_ARCH),aarch64)
|
||||
ifeq ($(TARGET_OS), linux)
|
||||
HOST_COMPILER ?= aarch64-linux-gnu-g++
|
||||
else ifeq ($(TARGET_OS),qnx)
|
||||
ifeq ($(QNX_HOST),)
|
||||
$(error ERROR - QNX_HOST must be passed to the QNX host toolchain)
|
||||
endif
|
||||
ifeq ($(QNX_TARGET),)
|
||||
$(error ERROR - QNX_TARGET must be passed to the QNX target toolchain)
|
||||
endif
|
||||
export QNX_HOST
|
||||
export QNX_TARGET
|
||||
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
|
||||
else ifeq ($(TARGET_OS), android)
|
||||
HOST_COMPILER ?= aarch64-linux-android-clang++
|
||||
endif
|
||||
else ifeq ($(TARGET_ARCH),sbsa)
|
||||
HOST_COMPILER ?= aarch64-linux-gnu-g++
|
||||
else ifeq ($(TARGET_ARCH),ppc64le)
|
||||
HOST_COMPILER ?= powerpc64le-linux-gnu-g++
|
||||
endif
|
||||
endif
|
||||
HOST_COMPILER ?= g++
|
||||
NVCC := $(CUDA_PATH)/bin/nvcc -ccbin $(HOST_COMPILER)
|
||||
|
||||
# internal flags
|
||||
NVCCFLAGS := -m${TARGET_SIZE}
|
||||
CCFLAGS :=
|
||||
LDFLAGS :=
|
||||
|
||||
# build flags
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
LDFLAGS += -rpath $(CUDA_PATH)/lib
|
||||
CCFLAGS += -arch $(HOST_ARCH)
|
||||
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-armv7l-linux)
|
||||
LDFLAGS += --dynamic-linker=/lib/ld-linux-armhf.so.3
|
||||
CCFLAGS += -mfloat-abi=hard
|
||||
else ifeq ($(TARGET_OS),android)
|
||||
LDFLAGS += -pie
|
||||
CCFLAGS += -fpie -fpic -fexceptions
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
|
||||
ifneq ($(TARGET_FS),)
|
||||
GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
|
||||
ifeq ($(GCCVERSIONLTEQ46),1)
|
||||
CCFLAGS += --sysroot=$(TARGET_FS)
|
||||
endif
|
||||
LDFLAGS += --sysroot=$(TARGET_FS)
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/arm-linux-gnueabihf
|
||||
endif
|
||||
endif
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
|
||||
ifneq ($(TARGET_FS),)
|
||||
GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
|
||||
ifeq ($(GCCVERSIONLTEQ46),1)
|
||||
CCFLAGS += --sysroot=$(TARGET_FS)
|
||||
endif
|
||||
LDFLAGS += --sysroot=$(TARGET_FS)
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib -L$(TARGET_FS)/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib/aarch64-linux-gnu -L$(TARGET_FS)/lib/aarch64-linux-gnu
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
|
||||
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
|
||||
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
|
||||
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
|
||||
endif
|
||||
endif
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
|
||||
NVCCFLAGS += -D_QNX_SOURCE
|
||||
NVCCFLAGS += --qpp-config 8.3.0,gcc_ntoaarch64le
|
||||
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
|
||||
LDFLAGS += -lsocket
|
||||
LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
|
||||
CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
|
||||
ifdef TARGET_OVERRIDE
|
||||
LDFLAGS += -lslog2
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_FS),)
|
||||
LDFLAGS += -L$(TARGET_FS)/usr/lib
|
||||
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
|
||||
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
|
||||
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
|
||||
CCFLAGS += -I$(TARGET_FS)/../include
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
ifdef TARGET_OVERRIDE # cuda toolkit targets override
|
||||
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
|
||||
endif
|
||||
|
||||
# Install directory of different arch
|
||||
CUDA_INSTALL_TARGET_DIR :=
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-gnueabihf/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),sbsa-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/sbsa-linux/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-android)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-androideabi/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-android)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux-androideabi/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-qnx)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/ARMv7-linux-QNX/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-qnx/
|
||||
else ifeq ($(TARGET_ARCH),ppc64le)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/ppc64le-linux/
|
||||
endif
|
||||
|
||||
# Debug build flags
|
||||
ifeq ($(dbg),1)
|
||||
NVCCFLAGS += -g -G
|
||||
BUILD_TYPE := debug
|
||||
else
|
||||
BUILD_TYPE := release
|
||||
endif
|
||||
|
||||
ALL_CCFLAGS :=
|
||||
ALL_CCFLAGS += $(NVCCFLAGS)
|
||||
ALL_CCFLAGS += $(EXTRA_NVCCFLAGS)
|
||||
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS))
|
||||
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS))
|
||||
|
||||
SAMPLE_ENABLED := 1
|
||||
|
||||
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 $(TARGET_ARCH),armv7l aarch64 sbsa))
|
||||
SMS ?= 53 61 70 72 75 80 86 87
|
||||
else
|
||||
SMS ?= 35 37 50 52 60 61 70 75 80 86
|
||||
endif
|
||||
|
||||
ifeq ($(SMS),)
|
||||
$(info >>> WARNING - no SM architectures have been specified - waiving sample <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
|
||||
ifeq ($(GENCODE_FLAGS),)
|
||||
# Generate SASS code for each SM architecture listed in $(SMS)
|
||||
$(foreach sm,$(SMS),$(eval GENCODE_FLAGS += -gencode arch=compute_$(sm),code=sm_$(sm)))
|
||||
|
||||
# Generate PTX code from the highest SM architecture in $(SMS) to guarantee forward-compatibility
|
||||
HIGHEST_SM := $(lastword $(sort $(SMS)))
|
||||
ifneq ($(HIGHEST_SM),)
|
||||
GENCODE_FLAGS += -gencode arch=compute_$(HIGHEST_SM),code=compute_$(HIGHEST_SM)
|
||||
endif
|
||||
endif
|
||||
|
||||
ALL_CCFLAGS += --threads 0 --std=c++11
|
||||
|
||||
ifeq ($(SAMPLE_ENABLED),0)
|
||||
EXEC ?= @echo "[@]"
|
||||
endif
|
||||
|
||||
################################################################################
|
||||
|
||||
# Target rules
|
||||
all: build
|
||||
|
||||
build: quasirandomGenerator
|
||||
|
||||
check.deps:
|
||||
ifeq ($(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
|
||||
|
||||
quasirandomGenerator.o:quasirandomGenerator.cpp
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
quasirandomGenerator_gold.o:quasirandomGenerator_gold.cpp
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
quasirandomGenerator_kernel.o:quasirandomGenerator_kernel.cu
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
quasirandomGenerator: quasirandomGenerator.o quasirandomGenerator_gold.o quasirandomGenerator_kernel.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
|
||||
$(EXEC) ./quasirandomGenerator
|
||||
|
||||
testrun: build
|
||||
|
||||
clean:
|
||||
rm -f quasirandomGenerator quasirandomGenerator.o quasirandomGenerator_gold.o quasirandomGenerator_kernel.o
|
||||
rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/quasirandomGenerator
|
||||
|
||||
clobber: clean
|
||||
@@ -0,0 +1,80 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
||||
<entry>
|
||||
<name>quasirandomGenerator</name>
|
||||
<cuda_api_list>
|
||||
<toolkit>cudaMemcpyToSymbol</toolkit>
|
||||
<toolkit>cudaMemset</toolkit>
|
||||
<toolkit>cudaFree</toolkit>
|
||||
<toolkit>cudaDeviceSynchronize</toolkit>
|
||||
<toolkit>cudaMalloc</toolkit>
|
||||
<toolkit>cudaMemcpy</toolkit>
|
||||
</cuda_api_list>
|
||||
<description><![CDATA[This sample implements Niederreiter Quasirandom Sequence Generator and Inverse Cumulative Normal Distribution functions for the generation of Standard Normal Distributions.]]></description>
|
||||
<devicecompilation>whole</devicecompilation>
|
||||
<includepaths>
|
||||
<path>./</path>
|
||||
<path>../</path>
|
||||
<path>../../../Common</path>
|
||||
</includepaths>
|
||||
<keyconcepts>
|
||||
<concept level="advanced">Computational Finance</concept>
|
||||
</keyconcepts>
|
||||
<keywords>
|
||||
<keyword>CUDA</keyword>
|
||||
<keyword>Advanced Topics</keyword>
|
||||
<keyword>Quasi-Monte Carlo Integration</keyword>
|
||||
<keyword>Computational Finance.</keyword>
|
||||
</keywords>
|
||||
<libraries>
|
||||
</libraries>
|
||||
<librarypaths>
|
||||
</librarypaths>
|
||||
<nsight_eclipse>true</nsight_eclipse>
|
||||
<primary_file>quasirandomGenerator.cpp</primary_file>
|
||||
<scopes>
|
||||
<scope>1:CUDA Advanced Topics</scope>
|
||||
<scope>3:Computational Finance</scope>
|
||||
</scopes>
|
||||
<sm-arch>sm35</sm-arch>
|
||||
<sm-arch>sm37</sm-arch>
|
||||
<sm-arch>sm50</sm-arch>
|
||||
<sm-arch>sm52</sm-arch>
|
||||
<sm-arch>sm53</sm-arch>
|
||||
<sm-arch>sm60</sm-arch>
|
||||
<sm-arch>sm61</sm-arch>
|
||||
<sm-arch>sm70</sm-arch>
|
||||
<sm-arch>sm72</sm-arch>
|
||||
<sm-arch>sm75</sm-arch>
|
||||
<sm-arch>sm80</sm-arch>
|
||||
<sm-arch>sm86</sm-arch>
|
||||
<sm-arch>sm87</sm-arch>
|
||||
<supported_envs>
|
||||
<env>
|
||||
<arch>x86_64</arch>
|
||||
<platform>linux</platform>
|
||||
</env>
|
||||
<env>
|
||||
<platform>windows7</platform>
|
||||
</env>
|
||||
<env>
|
||||
<arch>x86_64</arch>
|
||||
<platform>macosx</platform>
|
||||
</env>
|
||||
<env>
|
||||
<arch>arm</arch>
|
||||
</env>
|
||||
<env>
|
||||
<arch>sbsa</arch>
|
||||
</env>
|
||||
<env>
|
||||
<arch>ppc64le</arch>
|
||||
<platform>linux</platform>
|
||||
</env>
|
||||
</supported_envs>
|
||||
<supported_sm_architectures>
|
||||
<include>all</include>
|
||||
</supported_sm_architectures>
|
||||
<title>Niederreiter Quasirandom Sequence Generator</title>
|
||||
<type>exe</type>
|
||||
</entry>
|
||||
70
Samples/5_Domain_Specific/quasirandomGenerator/README.md
Normal file
70
Samples/5_Domain_Specific/quasirandomGenerator/README.md
Normal file
@@ -0,0 +1,70 @@
|
||||
# quasirandomGenerator - Niederreiter Quasirandom Sequence Generator
|
||||
|
||||
## Description
|
||||
|
||||
This sample implements Niederreiter Quasirandom Sequence Generator and Inverse Cumulative Normal Distribution functions for the generation of Standard Normal Distributions.
|
||||
|
||||
## Key Concepts
|
||||
|
||||
Computational Finance
|
||||
|
||||
## Supported SM Architectures
|
||||
|
||||
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 5.3 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus)
|
||||
|
||||
## Supported OSes
|
||||
|
||||
Linux, Windows
|
||||
|
||||
## Supported CPU Architecture
|
||||
|
||||
x86_64, ppc64le, armv7l
|
||||
|
||||
## CUDA APIs involved
|
||||
|
||||
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
|
||||
cudaMemcpyToSymbol, cudaMemset, cudaFree, cudaDeviceSynchronize, cudaMalloc, cudaMemcpy
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Download and install the [CUDA Toolkit 11.6](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 +1,183 @@
|
||||
/* 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.
|
||||
*/
|
||||
|
||||
// CUDA Runtime
|
||||
#include <cuda_runtime.h>
|
||||
|
||||
// Utilities and system includes
|
||||
#include <helper_functions.h>
|
||||
#include <helper_cuda.h>
|
||||
|
||||
#include "quasirandomGenerator_common.h"
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// CPU code
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
extern "C" void initQuasirandomGenerator(
|
||||
unsigned int table[QRNG_DIMENSIONS][QRNG_RESOLUTION]);
|
||||
|
||||
extern "C" float getQuasirandomValue(
|
||||
unsigned int table[QRNG_DIMENSIONS][QRNG_RESOLUTION], int i, int dim);
|
||||
|
||||
extern "C" double getQuasirandomValue63(INT64 i, int dim);
|
||||
extern "C" double MoroInvCNDcpu(unsigned int p);
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// GPU code
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
extern "C" void initTableGPU(
|
||||
unsigned int tableCPU[QRNG_DIMENSIONS][QRNG_RESOLUTION]);
|
||||
extern "C" void quasirandomGeneratorGPU(float *d_Output, unsigned int seed,
|
||||
unsigned int N);
|
||||
extern "C" void inverseCNDgpu(float *d_Output, unsigned int *d_Input,
|
||||
unsigned int N);
|
||||
|
||||
const int N = 1048576;
|
||||
|
||||
int main(int argc, char **argv) {
|
||||
// Start logs
|
||||
printf("%s Starting...\n\n", argv[0]);
|
||||
|
||||
unsigned int tableCPU[QRNG_DIMENSIONS][QRNG_RESOLUTION];
|
||||
|
||||
float *h_OutputGPU, *d_Output;
|
||||
|
||||
int dim, pos;
|
||||
double delta, ref, sumDelta, sumRef, L1norm, gpuTime;
|
||||
|
||||
StopWatchInterface *hTimer = NULL;
|
||||
|
||||
if (sizeof(INT64) != 8) {
|
||||
printf("sizeof(INT64) != 8\n");
|
||||
return 0;
|
||||
}
|
||||
|
||||
sdkCreateTimer(&hTimer);
|
||||
|
||||
printf("Allocating GPU memory...\n");
|
||||
checkCudaErrors(
|
||||
cudaMalloc((void **)&d_Output, QRNG_DIMENSIONS * N * sizeof(float)));
|
||||
|
||||
printf("Allocating CPU memory...\n");
|
||||
h_OutputGPU = (float *)malloc(QRNG_DIMENSIONS * N * sizeof(float));
|
||||
|
||||
printf("Initializing QRNG tables...\n\n");
|
||||
initQuasirandomGenerator(tableCPU);
|
||||
|
||||
initTableGPU(tableCPU);
|
||||
|
||||
printf("Testing QRNG...\n\n");
|
||||
checkCudaErrors(cudaMemset(d_Output, 0, QRNG_DIMENSIONS * N * sizeof(float)));
|
||||
int numIterations = 20;
|
||||
|
||||
for (int i = -1; i < numIterations; i++) {
|
||||
if (i == 0) {
|
||||
checkCudaErrors(cudaDeviceSynchronize());
|
||||
sdkResetTimer(&hTimer);
|
||||
sdkStartTimer(&hTimer);
|
||||
}
|
||||
|
||||
quasirandomGeneratorGPU(d_Output, 0, N);
|
||||
}
|
||||
|
||||
checkCudaErrors(cudaDeviceSynchronize());
|
||||
sdkStopTimer(&hTimer);
|
||||
gpuTime = sdkGetTimerValue(&hTimer) / (double)numIterations * 1e-3;
|
||||
printf(
|
||||
"quasirandomGenerator, Throughput = %.4f GNumbers/s, Time = %.5f s, Size "
|
||||
"= %u Numbers, NumDevsUsed = %u, Workgroup = %u\n",
|
||||
(double)QRNG_DIMENSIONS * (double)N * 1.0E-9 / gpuTime, gpuTime,
|
||||
QRNG_DIMENSIONS * N, 1, 128 * QRNG_DIMENSIONS);
|
||||
|
||||
printf("\nReading GPU results...\n");
|
||||
checkCudaErrors(cudaMemcpy(h_OutputGPU, d_Output,
|
||||
QRNG_DIMENSIONS * N * sizeof(float),
|
||||
cudaMemcpyDeviceToHost));
|
||||
|
||||
printf("Comparing to the CPU results...\n\n");
|
||||
sumDelta = 0;
|
||||
sumRef = 0;
|
||||
|
||||
for (dim = 0; dim < QRNG_DIMENSIONS; dim++)
|
||||
for (pos = 0; pos < N; pos++) {
|
||||
ref = getQuasirandomValue63(pos, dim);
|
||||
delta = (double)h_OutputGPU[dim * N + pos] - ref;
|
||||
sumDelta += fabs(delta);
|
||||
sumRef += fabs(ref);
|
||||
}
|
||||
|
||||
printf("L1 norm: %E\n", sumDelta / sumRef);
|
||||
|
||||
printf("\nTesting inverseCNDgpu()...\n\n");
|
||||
checkCudaErrors(cudaMemset(d_Output, 0, QRNG_DIMENSIONS * N * sizeof(float)));
|
||||
|
||||
for (int i = -1; i < numIterations; i++) {
|
||||
if (i == 0) {
|
||||
checkCudaErrors(cudaDeviceSynchronize());
|
||||
sdkResetTimer(&hTimer);
|
||||
sdkStartTimer(&hTimer);
|
||||
}
|
||||
|
||||
inverseCNDgpu(d_Output, NULL, QRNG_DIMENSIONS * N);
|
||||
}
|
||||
|
||||
checkCudaErrors(cudaDeviceSynchronize());
|
||||
sdkStopTimer(&hTimer);
|
||||
gpuTime = sdkGetTimerValue(&hTimer) / (double)numIterations * 1e-3;
|
||||
printf(
|
||||
"quasirandomGenerator-inverse, Throughput = %.4f GNumbers/s, Time = %.5f "
|
||||
"s, Size = %u Numbers, NumDevsUsed = %u, Workgroup = %u\n",
|
||||
(double)QRNG_DIMENSIONS * (double)N * 1E-9 / gpuTime, gpuTime,
|
||||
QRNG_DIMENSIONS * N, 1, 128);
|
||||
|
||||
printf("Reading GPU results...\n");
|
||||
checkCudaErrors(cudaMemcpy(h_OutputGPU, d_Output,
|
||||
QRNG_DIMENSIONS * N * sizeof(float),
|
||||
cudaMemcpyDeviceToHost));
|
||||
|
||||
printf("\nComparing to the CPU results...\n");
|
||||
sumDelta = 0;
|
||||
sumRef = 0;
|
||||
unsigned int distance = ((unsigned int)-1) / (QRNG_DIMENSIONS * N + 1);
|
||||
|
||||
for (pos = 0; pos < QRNG_DIMENSIONS * N; pos++) {
|
||||
unsigned int d = (pos + 1) * distance;
|
||||
ref = MoroInvCNDcpu(d);
|
||||
delta = (double)h_OutputGPU[pos] - ref;
|
||||
sumDelta += fabs(delta);
|
||||
sumRef += fabs(ref);
|
||||
}
|
||||
|
||||
printf("L1 norm: %E\n\n", L1norm = sumDelta / sumRef);
|
||||
|
||||
printf("Shutting down...\n");
|
||||
sdkDeleteTimer(&hTimer);
|
||||
free(h_OutputGPU);
|
||||
checkCudaErrors(cudaFree(d_Output));
|
||||
|
||||
exit(L1norm < 1e-6 ? EXIT_SUCCESS : EXIT_FAILURE);
|
||||
}
|
||||
@@ -0,0 +1,40 @@
|
||||
/* 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.
|
||||
*/
|
||||
|
||||
#ifndef QUASIRANDOMGENERATOR_COMMON_H
|
||||
#define QUASIRANDOMGENERATOR_COMMON_H
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Global types and constants
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
typedef long long int INT64;
|
||||
|
||||
#define QRNG_DIMENSIONS 3
|
||||
#define QRNG_RESOLUTION 31
|
||||
#define INT_SCALE (1.0f / (float)0x80000001U)
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,325 @@
|
||||
/* 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.
|
||||
*/
|
||||
|
||||
#include <stdio.h>
|
||||
#include <math.h>
|
||||
|
||||
#include "quasirandomGenerator_common.h"
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Table generation functions
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Internal 64(63)-bit table
|
||||
static INT64 cjn[63][QRNG_DIMENSIONS];
|
||||
|
||||
static int GeneratePolynomials(int buffer[QRNG_DIMENSIONS], bool primitive) {
|
||||
int i, j, n, p1, p2, l;
|
||||
int e_p1, e_p2, e_b;
|
||||
|
||||
// generate all polynomials to buffer
|
||||
for (n = 1, buffer[0] = 0x2, p2 = 0, l = 0; n < QRNG_DIMENSIONS; ++n) {
|
||||
// search for the next irreducible polynomial
|
||||
for (p1 = buffer[n - 1] + 1;; ++p1) {
|
||||
// find degree of polynomial p1
|
||||
for (e_p1 = 30; (p1 & (1 << e_p1)) == 0; --e_p1) {
|
||||
}
|
||||
|
||||
// try to divide p1 by all polynomials in buffer
|
||||
for (i = 0; i < n; ++i) {
|
||||
// find the degree of buffer[i]
|
||||
for (e_b = e_p1; (buffer[i] & (1 << e_b)) == 0; --e_b) {
|
||||
}
|
||||
|
||||
// divide p2 by buffer[i] until the end
|
||||
for (p2 = (buffer[i] << ((e_p2 = e_p1) - e_b)) ^ p1; p2 >= buffer[i];
|
||||
p2 = (buffer[i] << (e_p2 - e_b)) ^ p2) {
|
||||
for (; (p2 & (1 << e_p2)) == 0; --e_p2) {
|
||||
}
|
||||
} // compute new degree of p2
|
||||
|
||||
// division without remainder!!! p1 is not irreducible
|
||||
if (p2 == 0) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// all divisions were with remainder - p1 is irreducible
|
||||
if (p2 != 0) {
|
||||
e_p2 = 0;
|
||||
|
||||
if (primitive) {
|
||||
// check that p1 has only one cycle (i.e. is monic, or primitive)
|
||||
j = ~(0xffffffff << (e_p1 + 1));
|
||||
e_b = (1 << e_p1) | 0x1;
|
||||
|
||||
for (p2 = e_b, e_p2 = (1 << e_p1) - 2; e_p2 > 0; --e_p2) {
|
||||
p2 <<= 1;
|
||||
i = p2 & p1;
|
||||
i = (i & 0x55555555) + ((i >> 1) & 0x55555555);
|
||||
i = (i & 0x33333333) + ((i >> 2) & 0x33333333);
|
||||
i = (i & 0x07070707) + ((i >> 4) & 0x07070707);
|
||||
p2 |= (i % 255) & 1;
|
||||
|
||||
if ((p2 & j) == e_b) break;
|
||||
}
|
||||
}
|
||||
|
||||
// it is monic - add it to the list of polynomials
|
||||
if (e_p2 == 0) {
|
||||
buffer[n] = p1;
|
||||
l += e_p1;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return l + 1;
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// @misc{Bratley92:LDS,
|
||||
// author = "B. Fox and P. Bratley and H. Niederreiter",
|
||||
// title = "Implementation and test of low discrepancy sequences",
|
||||
// text = "B. L. Fox, P. Bratley, and H. Niederreiter. Implementation and
|
||||
// test of
|
||||
// low discrepancy sequences. ACM Trans. Model. Comput. Simul.,
|
||||
// 2(3):195--213,
|
||||
// July 1992.",
|
||||
// year = "1992" }
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
static void GenerateCJ() {
|
||||
int buffer[QRNG_DIMENSIONS];
|
||||
int *polynomials;
|
||||
int n, p1, l, e_p1;
|
||||
|
||||
// Niederreiter (in contrast to Sobol) allows to use not primitive, but just
|
||||
// irreducible polynomials
|
||||
l = GeneratePolynomials(buffer, false);
|
||||
|
||||
// convert all polynomials from buffer to polynomials table
|
||||
polynomials = new int[l + 2 * QRNG_DIMENSIONS + 1];
|
||||
|
||||
for (n = 0, l = 0; n < QRNG_DIMENSIONS; ++n) {
|
||||
// find degree of polynomial p1
|
||||
for (p1 = buffer[n], e_p1 = 30; (p1 & (1 << e_p1)) == 0; --e_p1) {
|
||||
}
|
||||
|
||||
// fill polynomials table with values for this polynomial
|
||||
polynomials[l++] = 1;
|
||||
|
||||
for (--e_p1; e_p1 >= 0; --e_p1) {
|
||||
polynomials[l++] = (p1 >> e_p1) & 1;
|
||||
}
|
||||
|
||||
polynomials[l++] = -1;
|
||||
}
|
||||
|
||||
polynomials[l] = -1;
|
||||
|
||||
// irreducible polynomial p
|
||||
int *p = polynomials, e, d;
|
||||
// polynomial b
|
||||
int b_arr[1024], *b, m;
|
||||
// v array
|
||||
int v_arr[1024], *v;
|
||||
// temporary polynomial, required to do multiplication of p and b
|
||||
int t_arr[1024], *t;
|
||||
// subsidiary variables
|
||||
int i, j, u, m1, ip, it;
|
||||
|
||||
// cycle over monic irreducible polynomials
|
||||
for (d = 0; p[0] != -1; p += e + 2) {
|
||||
// allocate memory for cj array for dimension (ip + 1)
|
||||
for (i = 0; i < 63; ++i) {
|
||||
cjn[i][d] = 0;
|
||||
}
|
||||
|
||||
// determine the power of irreducible polynomial
|
||||
for (e = 0; p[e + 1] != -1; ++e) {
|
||||
}
|
||||
|
||||
// polynomial b in the beginning is just '1'
|
||||
(b = b_arr + 1023)[m = 0] = 1;
|
||||
// v array needs only (63 + e - 2) length
|
||||
v = v_arr + 1023 - (63 + e - 2);
|
||||
|
||||
// cycle over all coefficients
|
||||
for (j = 63 - 1, u = e; j >= 0; --j, ++u) {
|
||||
if (u == e) {
|
||||
u = 0;
|
||||
|
||||
// multiply b by p (polynomials multiplication)
|
||||
for (i = 0, t = t_arr + 1023 - (m1 = m); i <= m; ++i) {
|
||||
t[i] = b[i];
|
||||
}
|
||||
|
||||
b = b_arr + 1023 - (m += e);
|
||||
|
||||
for (i = 0; i <= m; ++i) {
|
||||
b[i] = 0;
|
||||
|
||||
for (ip = e - (m - i), it = m1; ip <= e && it >= 0; ++ip, --it) {
|
||||
if (ip >= 0) {
|
||||
b[i] ^= p[ip] & t[it];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// multiplication of polynomials finished
|
||||
|
||||
// calculate v
|
||||
for (i = 0; i < m1; ++i) {
|
||||
v[i] = 0;
|
||||
}
|
||||
|
||||
for (; i < m; ++i) {
|
||||
v[i] = 1;
|
||||
}
|
||||
|
||||
for (; i <= 63 + e - 2; ++i) {
|
||||
v[i] = 0;
|
||||
|
||||
for (it = 1; it <= m; ++it) {
|
||||
v[i] ^= v[i - it] & b[it];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// copy calculated v to cj
|
||||
for (i = 0; i < 63; i++) {
|
||||
cjn[i][d] |= (INT64)v[i + u] << j;
|
||||
}
|
||||
}
|
||||
|
||||
++d;
|
||||
}
|
||||
|
||||
delete[] polynomials;
|
||||
}
|
||||
|
||||
// Generate 63-bit quasirandom number for given index and dimension and
|
||||
// normalize
|
||||
extern "C" double getQuasirandomValue63(INT64 i, int dim) {
|
||||
const double INT63_SCALE = (1.0 / (double)0x8000000000000001ULL);
|
||||
INT64 result = 0;
|
||||
|
||||
for (int bit = 0; bit < 63; bit++, i >>= 1)
|
||||
if (i & 1) result ^= cjn[bit][dim];
|
||||
|
||||
return (double)(result + 1) * INT63_SCALE;
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Initialization (table setup)
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
extern "C" void initQuasirandomGenerator(
|
||||
unsigned int table[QRNG_DIMENSIONS][QRNG_RESOLUTION]) {
|
||||
GenerateCJ();
|
||||
|
||||
for (int dim = 0; dim < QRNG_DIMENSIONS; dim++)
|
||||
for (int bit = 0; bit < QRNG_RESOLUTION; bit++)
|
||||
table[dim][bit] = (int)((cjn[bit][dim] >> 32) & 0x7FFFFFFF);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Generate 31-bit quasirandom number for given index and dimension
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
extern "C" float getQuasirandomValue(
|
||||
unsigned int table[QRNG_DIMENSIONS][QRNG_RESOLUTION], int i, int dim) {
|
||||
int result = 0;
|
||||
|
||||
for (int bit = 0; bit < QRNG_RESOLUTION; bit++, i >>= 1)
|
||||
if (i & 1) result ^= table[dim][bit];
|
||||
|
||||
return (float)(result + 1) * INT_SCALE;
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Moro's Inverse Cumulative Normal Distribution function approximation
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
extern "C" double MoroInvCNDcpu(unsigned int x) {
|
||||
const double a1 = 2.50662823884;
|
||||
const double a2 = -18.61500062529;
|
||||
const double a3 = 41.39119773534;
|
||||
const double a4 = -25.44106049637;
|
||||
const double b1 = -8.4735109309;
|
||||
const double b2 = 23.08336743743;
|
||||
const double b3 = -21.06224101826;
|
||||
const double b4 = 3.13082909833;
|
||||
const double c1 = 0.337475482272615;
|
||||
const double c2 = 0.976169019091719;
|
||||
const double c3 = 0.160797971491821;
|
||||
const double c4 = 2.76438810333863E-02;
|
||||
const double c5 = 3.8405729373609E-03;
|
||||
const double c6 = 3.951896511919E-04;
|
||||
const double c7 = 3.21767881768E-05;
|
||||
const double c8 = 2.888167364E-07;
|
||||
const double c9 = 3.960315187E-07;
|
||||
|
||||
double z;
|
||||
|
||||
bool negate = false;
|
||||
|
||||
// Ensure the conversion to floating point will give a value in the
|
||||
// range (0,0.5] by restricting the input to the bottom half of the
|
||||
// input domain. We will later reflect the result if the input was
|
||||
// originally in the top half of the input domain
|
||||
if (x >= 0x80000000UL) {
|
||||
x = 0xffffffffUL - x;
|
||||
negate = true;
|
||||
}
|
||||
|
||||
// x is now in the range [0,0x80000000) (i.e. [0,0x7fffffff])
|
||||
// Convert to floating point in (0,0.5]
|
||||
const double x1 = 1.0 / static_cast<double>(0xffffffffUL);
|
||||
const double x2 = x1 / 2.0;
|
||||
double p1 = x * x1 + x2;
|
||||
// Convert to floating point in (-0.5,0]
|
||||
double p2 = p1 - 0.5;
|
||||
|
||||
// The input to the Moro inversion is p2 which is in the range
|
||||
// (-0.5,0]. This means that our output will be the negative side
|
||||
// of the bell curve (which we will reflect if "negate" is true).
|
||||
|
||||
// Main body of the bell curve for |p| < 0.42
|
||||
if (p2 > -0.42) {
|
||||
z = p2 * p2;
|
||||
z = p2 * (((a4 * z + a3) * z + a2) * z + a1) /
|
||||
((((b4 * z + b3) * z + b2) * z + b1) * z + 1.0);
|
||||
}
|
||||
// Special case (Chebychev) for tail
|
||||
else {
|
||||
z = log(-log(p1));
|
||||
z = -(c1 + z * (c2 + z * (c3 + z * (c4 + z * (c5 + z * (c6 + z *
|
||||
(c7 + z * (c8 + z * c9))))))));
|
||||
}
|
||||
|
||||
// If the original input (x) was in the top half of the range, reflect
|
||||
// to get the positive side of the bell curve
|
||||
return negate ? -z : z;
|
||||
}
|
||||
@@ -0,0 +1,178 @@
|
||||
/* 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.
|
||||
*/
|
||||
|
||||
#ifndef QUASIRANDOMGENERATOR_KERNEL_CUH
|
||||
#define QUASIRANDOMGENERATOR_KERNEL_CUH
|
||||
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <helper_cuda.h>
|
||||
#include "quasirandomGenerator_common.h"
|
||||
|
||||
// Fast integer multiplication
|
||||
#define MUL(a, b) __umul24(a, b)
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Niederreiter quasirandom number generation kernel
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
static __constant__ unsigned int c_Table[QRNG_DIMENSIONS][QRNG_RESOLUTION];
|
||||
|
||||
static __global__ void quasirandomGeneratorKernel(float *d_Output,
|
||||
unsigned int seed,
|
||||
unsigned int N) {
|
||||
unsigned int *dimBase = &c_Table[threadIdx.y][0];
|
||||
unsigned int tid = MUL(blockDim.x, blockIdx.x) + threadIdx.x;
|
||||
unsigned int threadN = MUL(blockDim.x, gridDim.x);
|
||||
|
||||
for (unsigned int pos = tid; pos < N; pos += threadN) {
|
||||
unsigned int result = 0;
|
||||
unsigned int data = seed + pos;
|
||||
|
||||
for (int bit = 0; bit < QRNG_RESOLUTION; bit++, data >>= 1)
|
||||
if (data & 1) {
|
||||
result ^= dimBase[bit];
|
||||
}
|
||||
|
||||
d_Output[MUL(threadIdx.y, N) + pos] = (float)(result + 1) * INT_SCALE;
|
||||
}
|
||||
}
|
||||
|
||||
// Table initialization routine
|
||||
extern "C" void initTableGPU(
|
||||
unsigned int tableCPU[QRNG_DIMENSIONS][QRNG_RESOLUTION]) {
|
||||
checkCudaErrors(cudaMemcpyToSymbol(
|
||||
c_Table, tableCPU,
|
||||
QRNG_DIMENSIONS * QRNG_RESOLUTION * sizeof(unsigned int)));
|
||||
}
|
||||
|
||||
// Host-side interface
|
||||
extern "C" void quasirandomGeneratorGPU(float *d_Output, unsigned int seed,
|
||||
unsigned int N) {
|
||||
dim3 threads(128, QRNG_DIMENSIONS);
|
||||
quasirandomGeneratorKernel<<<128, threads>>>(d_Output, seed, N);
|
||||
getLastCudaError("quasirandomGeneratorKernel() execution failed.\n");
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Moro's Inverse Cumulative Normal Distribution function approximation
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
__device__ inline float MoroInvCNDgpu(unsigned int x) {
|
||||
const float a1 = 2.50662823884f;
|
||||
const float a2 = -18.61500062529f;
|
||||
const float a3 = 41.39119773534f;
|
||||
const float a4 = -25.44106049637f;
|
||||
const float b1 = -8.4735109309f;
|
||||
const float b2 = 23.08336743743f;
|
||||
const float b3 = -21.06224101826f;
|
||||
const float b4 = 3.13082909833f;
|
||||
const float c1 = 0.337475482272615f;
|
||||
const float c2 = 0.976169019091719f;
|
||||
const float c3 = 0.160797971491821f;
|
||||
const float c4 = 2.76438810333863E-02f;
|
||||
const float c5 = 3.8405729373609E-03f;
|
||||
const float c6 = 3.951896511919E-04f;
|
||||
const float c7 = 3.21767881768E-05f;
|
||||
const float c8 = 2.888167364E-07f;
|
||||
const float c9 = 3.960315187E-07f;
|
||||
|
||||
float z;
|
||||
|
||||
bool negate = false;
|
||||
|
||||
// Ensure the conversion to floating point will give a value in the
|
||||
// range (0,0.5] by restricting the input to the bottom half of the
|
||||
// input domain. We will later reflect the result if the input was
|
||||
// originally in the top half of the input domain
|
||||
if (x >= 0x80000000UL) {
|
||||
x = 0xffffffffUL - x;
|
||||
negate = true;
|
||||
}
|
||||
|
||||
// x is now in the range [0,0x80000000) (i.e. [0,0x7fffffff])
|
||||
// Convert to floating point in (0,0.5]
|
||||
const float x1 = 1.0f / static_cast<float>(0xffffffffUL);
|
||||
const float x2 = x1 / 2.0f;
|
||||
float p1 = x * x1 + x2;
|
||||
// Convert to floating point in (-0.5,0]
|
||||
float p2 = p1 - 0.5f;
|
||||
|
||||
// The input to the Moro inversion is p2 which is in the range
|
||||
// (-0.5,0]. This means that our output will be the negative side
|
||||
// of the bell curve (which we will reflect if "negate" is true).
|
||||
|
||||
// Main body of the bell curve for |p| < 0.42
|
||||
if (p2 > -0.42f) {
|
||||
z = p2 * p2;
|
||||
z = p2 * (((a4 * z + a3) * z + a2) * z + a1) /
|
||||
((((b4 * z + b3) * z + b2) * z + b1) * z + 1.0f);
|
||||
}
|
||||
// Special case (Chebychev) for tail
|
||||
else {
|
||||
z = __logf(-__logf(p1));
|
||||
z = -(c1 + z * (c2 + z * (c3 + z * (c4 + z * (c5 + z * (c6 + z * (c7 + z
|
||||
* (c8 + z * c9))))))));
|
||||
}
|
||||
|
||||
// If the original input (x) was in the top half of the range, reflect
|
||||
// to get the positive side of the bell curve
|
||||
return negate ? -z : z;
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Main kernel. Choose between transforming
|
||||
// input sequence and uniform ascending (0, 1) sequence
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
static __global__ void inverseCNDKernel(float *d_Output, unsigned int *d_Input,
|
||||
unsigned int pathN) {
|
||||
unsigned int distance = ((unsigned int)-1) / (pathN + 1);
|
||||
unsigned int tid = MUL(blockDim.x, blockIdx.x) + threadIdx.x;
|
||||
unsigned int threadN = MUL(blockDim.x, gridDim.x);
|
||||
|
||||
// Transform input number sequence if it's supplied
|
||||
if (d_Input) {
|
||||
for (unsigned int pos = tid; pos < pathN; pos += threadN) {
|
||||
unsigned int d = d_Input[pos];
|
||||
d_Output[pos] = (float)MoroInvCNDgpu(d);
|
||||
}
|
||||
}
|
||||
// Else generate input uniformly placed samples on the fly
|
||||
// and write to destination
|
||||
else {
|
||||
for (unsigned int pos = tid; pos < pathN; pos += threadN) {
|
||||
unsigned int d = (pos + 1) * distance;
|
||||
d_Output[pos] = (float)MoroInvCNDgpu(d);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
extern "C" void inverseCNDgpu(float *d_Output, unsigned int *d_Input,
|
||||
unsigned int N) {
|
||||
inverseCNDKernel<<<128, 128>>>(d_Output, d_Input, N);
|
||||
getLastCudaError("inverseCNDKernel() execution failed.\n");
|
||||
}
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2017
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "quasirandomGenerator", "quasirandomGenerator_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 +1,114 @@
|
||||
<?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>quasirandomGenerator_vs2017</RootNamespace>
|
||||
<ProjectName>quasirandomGenerator</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(WindowsTargetPlatformVersion)'==''">
|
||||
<LatestTargetPlatformVersion>$([Microsoft.Build.Utilities.ToolLocationHelper]::GetLatestSDKTargetPlatformVersion('Windows', '10.0'))</LatestTargetPlatformVersion>
|
||||
<WindowsTargetPlatformVersion Condition="'$(WindowsTargetPlatformVersion)' == ''">$(LatestTargetPlatformVersion)</WindowsTargetPlatformVersion>
|
||||
<TargetPlatformVersion>$(WindowsTargetPlatformVersion)</TargetPlatformVersion>
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup>
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v141</PlatformToolset>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
|
||||
<UseDebugLibraries>true</UseDebugLibraries>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Release'">
|
||||
<WholeProgramOptimization>true</WholeProgramOptimization>
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
|
||||
<ImportGroup Label="ExtensionSettings">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
|
||||
</ImportGroup>
|
||||
<PropertyGroup Label="UserMacros" />
|
||||
<PropertyGroup>
|
||||
<IntDir>$(Platform)/$(Configuration)/</IntDir>
|
||||
<IncludePath>$(IncludePath)</IncludePath>
|
||||
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
|
||||
<CodeAnalysisRules />
|
||||
<CodeAnalysisRuleAssemblies />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Platform)'=='x64'">
|
||||
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
|
||||
</PropertyGroup>
|
||||
<ItemDefinitionGroup>
|
||||
<ClCompile>
|
||||
<WarningLevel>Level3</WarningLevel>
|
||||
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
|
||||
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cudart_static.lib;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)/quasirandomGenerator.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
|
||||
<Include>./;../../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
|
||||
<ClCompile>
|
||||
<Optimization>Disabled</Optimization>
|
||||
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>true</GenerateDebugInformation>
|
||||
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<Runtime>MTd</Runtime>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
|
||||
<ClCompile>
|
||||
<Optimization>MaxSpeed</Optimization>
|
||||
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>false</GenerateDebugInformation>
|
||||
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<Runtime>MT</Runtime>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="quasirandomGenerator.cpp" />
|
||||
<ClCompile Include="quasirandomGenerator_gold.cpp" />
|
||||
<CudaCompile Include="quasirandomGenerator_kernel.cu" />
|
||||
<ClInclude Include="quasirandomGenerator_common.h" />
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2019
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "quasirandomGenerator", "quasirandomGenerator_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 +1,110 @@
|
||||
<?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>quasirandomGenerator_vs2019</RootNamespace>
|
||||
<ProjectName>quasirandomGenerator</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup>
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v142</PlatformToolset>
|
||||
<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
|
||||
<UseDebugLibraries>true</UseDebugLibraries>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Release'">
|
||||
<WholeProgramOptimization>true</WholeProgramOptimization>
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
|
||||
<ImportGroup Label="ExtensionSettings">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
|
||||
</ImportGroup>
|
||||
<PropertyGroup Label="UserMacros" />
|
||||
<PropertyGroup>
|
||||
<IntDir>$(Platform)/$(Configuration)/</IntDir>
|
||||
<IncludePath>$(IncludePath)</IncludePath>
|
||||
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
|
||||
<CodeAnalysisRules />
|
||||
<CodeAnalysisRuleAssemblies />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Platform)'=='x64'">
|
||||
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
|
||||
</PropertyGroup>
|
||||
<ItemDefinitionGroup>
|
||||
<ClCompile>
|
||||
<WarningLevel>Level3</WarningLevel>
|
||||
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
|
||||
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cudart_static.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
|
||||
<OutputFile>$(OutDir)/quasirandomGenerator.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
|
||||
<Include>./;../../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
|
||||
<ClCompile>
|
||||
<Optimization>Disabled</Optimization>
|
||||
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>true</GenerateDebugInformation>
|
||||
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<Runtime>MTd</Runtime>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
|
||||
<ClCompile>
|
||||
<Optimization>MaxSpeed</Optimization>
|
||||
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>false</GenerateDebugInformation>
|
||||
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<Runtime>MT</Runtime>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="quasirandomGenerator.cpp" />
|
||||
<ClCompile Include="quasirandomGenerator_gold.cpp" />
|
||||
<CudaCompile Include="quasirandomGenerator_kernel.cu" />
|
||||
<ClInclude Include="quasirandomGenerator_common.h" />
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2022
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "quasirandomGenerator", "quasirandomGenerator_vs2022.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
|
||||
EndProject
|
||||
Global
|
||||
GlobalSection(SolutionConfigurationPlatforms) = preSolution
|
||||
Debug|x64 = Debug|x64
|
||||
Release|x64 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(ProjectConfigurationPlatforms) = postSolution
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(SolutionProperties) = preSolution
|
||||
HideSolutionNode = FALSE
|
||||
EndGlobalSection
|
||||
EndGlobal
|
||||
@@ -0,0 +1,110 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
|
||||
<PropertyGroup>
|
||||
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||
</PropertyGroup>
|
||||
<ItemGroup Label="ProjectConfigurations">
|
||||
<ProjectConfiguration Include="Debug|x64">
|
||||
<Configuration>Debug</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
<ProjectConfiguration Include="Release|x64">
|
||||
<Configuration>Release</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
</ItemGroup>
|
||||
<PropertyGroup Label="Globals">
|
||||
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||
<RootNamespace>quasirandomGenerator_vs2022</RootNamespace>
|
||||
<ProjectName>quasirandomGenerator</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup>
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v143</PlatformToolset>
|
||||
<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
|
||||
<UseDebugLibraries>true</UseDebugLibraries>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Release'">
|
||||
<WholeProgramOptimization>true</WholeProgramOptimization>
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
|
||||
<ImportGroup Label="ExtensionSettings">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
|
||||
</ImportGroup>
|
||||
<PropertyGroup Label="UserMacros" />
|
||||
<PropertyGroup>
|
||||
<IntDir>$(Platform)/$(Configuration)/</IntDir>
|
||||
<IncludePath>$(IncludePath)</IncludePath>
|
||||
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
|
||||
<CodeAnalysisRules />
|
||||
<CodeAnalysisRuleAssemblies />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Platform)'=='x64'">
|
||||
<OutDir>../../../bin/win64/$(Configuration)/</OutDir>
|
||||
</PropertyGroup>
|
||||
<ItemDefinitionGroup>
|
||||
<ClCompile>
|
||||
<WarningLevel>Level3</WarningLevel>
|
||||
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
|
||||
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../../Common;</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cudart_static.lib;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)/quasirandomGenerator.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
|
||||
<Include>./;../../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Configuration)'=='Debug'">
|
||||
<ClCompile>
|
||||
<Optimization>Disabled</Optimization>
|
||||
<RuntimeLibrary>MultiThreadedDebug</RuntimeLibrary>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>true</GenerateDebugInformation>
|
||||
<LinkTimeCodeGeneration>Default</LinkTimeCodeGeneration>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<Runtime>MTd</Runtime>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Configuration)'=='Release'">
|
||||
<ClCompile>
|
||||
<Optimization>MaxSpeed</Optimization>
|
||||
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>false</GenerateDebugInformation>
|
||||
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<Runtime>MT</Runtime>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="quasirandomGenerator.cpp" />
|
||||
<ClCompile Include="quasirandomGenerator_gold.cpp" />
|
||||
<CudaCompile Include="quasirandomGenerator_kernel.cu" />
|
||||
<ClInclude Include="quasirandomGenerator_common.h" />
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
Reference in New Issue
Block a user