mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2026-10-23 21:28:17 +08:00
add and update samples for CUDA 11.5
This commit is contained in:
Rutwik Choughule
18
Samples/binomialOptions_nvrtc/.vscode/c_cpp_properties.json
vendored
Normal file
18
Samples/binomialOptions_nvrtc/.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/binomialOptions_nvrtc/.vscode/extensions.json
vendored
Normal file
7
Samples/binomialOptions_nvrtc/.vscode/extensions.json
vendored
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"recommendations": [
|
||||
"nvidia.nsight-vscode-edition",
|
||||
"ms-vscode.cpptools",
|
||||
"ms-vscode.makefile-tools"
|
||||
]
|
||||
}
|
||||
10
Samples/binomialOptions_nvrtc/.vscode/launch.json
vendored
Normal file
10
Samples/binomialOptions_nvrtc/.vscode/launch.json
vendored
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"configurations": [
|
||||
{
|
||||
"name": "CUDA C++: Launch",
|
||||
"type": "cuda-gdb",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/binomialOptions_nvrtc"
|
||||
}
|
||||
]
|
||||
}
|
||||
15
Samples/binomialOptions_nvrtc/.vscode/tasks.json
vendored
Normal file
15
Samples/binomialOptions_nvrtc/.vscode/tasks.json
vendored
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"version": "2.0.0",
|
||||
"tasks": [
|
||||
{
|
||||
"label": "sample",
|
||||
"type": "shell",
|
||||
"command": "make dbg=1",
|
||||
"problemMatcher": ["$nvcc"],
|
||||
"group": {
|
||||
"kind": "build",
|
||||
"isDefault": true
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
425
Samples/binomialOptions_nvrtc/Makefile
Normal file
425
Samples/binomialOptions_nvrtc/Makefile
Normal file
@@ -0,0 +1,425 @@
|
||||
################################################################################
|
||||
# Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
|
||||
#
|
||||
# Redistribution and use in source and binary forms, with or without
|
||||
# modification, are permitted provided that the following conditions
|
||||
# are met:
|
||||
# * Redistributions of source code must retain the above copyright
|
||||
# notice, this list of conditions and the following disclaimer.
|
||||
# * Redistributions in binary form must reproduce the above copyright
|
||||
# notice, this list of conditions and the following disclaimer in the
|
||||
# documentation and/or other materials provided with the distribution.
|
||||
# * Neither the name of NVIDIA CORPORATION nor the names of its
|
||||
# contributors may be used to endorse or promote products derived
|
||||
# from this software without specific prior written permission.
|
||||
#
|
||||
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
|
||||
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
||||
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
||||
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
#
|
||||
################################################################################
|
||||
#
|
||||
# Makefile project only supported on Mac OS X and Linux Platforms)
|
||||
#
|
||||
################################################################################
|
||||
|
||||
# Location of the CUDA Toolkit
|
||||
CUDA_PATH ?= /usr/local/cuda
|
||||
|
||||
##############################
|
||||
# start deprecated interface #
|
||||
##############################
|
||||
ifeq ($(x86_64),1)
|
||||
$(info WARNING - x86_64 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=x86_64 instead)
|
||||
TARGET_ARCH ?= x86_64
|
||||
endif
|
||||
ifeq ($(ARMv7),1)
|
||||
$(info WARNING - ARMv7 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=armv7l instead)
|
||||
TARGET_ARCH ?= armv7l
|
||||
endif
|
||||
ifeq ($(aarch64),1)
|
||||
$(info WARNING - aarch64 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=aarch64 instead)
|
||||
TARGET_ARCH ?= aarch64
|
||||
endif
|
||||
ifeq ($(ppc64le),1)
|
||||
$(info WARNING - ppc64le variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=ppc64le instead)
|
||||
TARGET_ARCH ?= ppc64le
|
||||
endif
|
||||
ifneq ($(GCC),)
|
||||
$(info WARNING - GCC variable has been deprecated)
|
||||
$(info WARNING - please use HOST_COMPILER=$(GCC) instead)
|
||||
HOST_COMPILER ?= $(GCC)
|
||||
endif
|
||||
ifneq ($(abi),)
|
||||
$(error ERROR - abi variable has been removed)
|
||||
endif
|
||||
############################
|
||||
# end deprecated interface #
|
||||
############################
|
||||
|
||||
# architecture
|
||||
HOST_ARCH := $(shell uname -m)
|
||||
TARGET_ARCH ?= $(HOST_ARCH)
|
||||
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le armv7l))
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le))
|
||||
TARGET_SIZE := 64
|
||||
else ifneq (,$(filter $(TARGET_ARCH),armv7l))
|
||||
TARGET_SIZE := 32
|
||||
endif
|
||||
else
|
||||
TARGET_SIZE := $(shell getconf LONG_BIT)
|
||||
endif
|
||||
else
|
||||
$(error ERROR - unsupported value $(TARGET_ARCH) for TARGET_ARCH!)
|
||||
endif
|
||||
|
||||
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
|
||||
ifeq ($(HOST_ARCH),aarch64)
|
||||
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
|
||||
HOST_ARCH := sbsa
|
||||
TARGET_ARCH := sbsa
|
||||
endif
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq (,$(filter $(HOST_ARCH)-$(TARGET_ARCH),aarch64-armv7l x86_64-armv7l x86_64-aarch64 x86_64-sbsa x86_64-ppc64le))
|
||||
$(error ERROR - cross compiling from $(HOST_ARCH) to $(TARGET_ARCH) is not supported!)
|
||||
endif
|
||||
endif
|
||||
|
||||
# When on native aarch64 system with userspace of 32-bit, change TARGET_ARCH to armv7l
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_SIZE),aarch64-aarch64-32)
|
||||
TARGET_ARCH = armv7l
|
||||
endif
|
||||
|
||||
# operating system
|
||||
HOST_OS := $(shell uname -s 2>/dev/null | tr "[:upper:]" "[:lower:]")
|
||||
TARGET_OS ?= $(HOST_OS)
|
||||
ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
|
||||
$(error ERROR - unsupported value $(TARGET_OS) for TARGET_OS!)
|
||||
endif
|
||||
|
||||
# host compiler
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
ifeq ($(shell expr `xcodebuild -version | grep -i xcode | awk '{print $$2}' | cut -d'.' -f1` \>= 5),1)
|
||||
HOST_COMPILER ?= clang++
|
||||
endif
|
||||
else ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l)
|
||||
ifeq ($(TARGET_OS),linux)
|
||||
HOST_COMPILER ?= arm-linux-gnueabihf-g++
|
||||
else ifeq ($(TARGET_OS),qnx)
|
||||
ifeq ($(QNX_HOST),)
|
||||
$(error ERROR - QNX_HOST must be passed to the QNX host toolchain)
|
||||
endif
|
||||
ifeq ($(QNX_TARGET),)
|
||||
$(error ERROR - QNX_TARGET must be passed to the QNX target toolchain)
|
||||
endif
|
||||
export QNX_HOST
|
||||
export QNX_TARGET
|
||||
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/arm-unknown-nto-qnx6.6.0eabi-g++
|
||||
else ifeq ($(TARGET_OS),android)
|
||||
HOST_COMPILER ?= arm-linux-androideabi-g++
|
||||
endif
|
||||
else ifeq ($(TARGET_ARCH),aarch64)
|
||||
ifeq ($(TARGET_OS), linux)
|
||||
HOST_COMPILER ?= aarch64-linux-gnu-g++
|
||||
else ifeq ($(TARGET_OS),qnx)
|
||||
ifeq ($(QNX_HOST),)
|
||||
$(error ERROR - QNX_HOST must be passed to the QNX host toolchain)
|
||||
endif
|
||||
ifeq ($(QNX_TARGET),)
|
||||
$(error ERROR - QNX_TARGET must be passed to the QNX target toolchain)
|
||||
endif
|
||||
export QNX_HOST
|
||||
export QNX_TARGET
|
||||
HOST_COMPILER ?= $(QNX_HOST)/usr/bin/q++
|
||||
else ifeq ($(TARGET_OS), android)
|
||||
HOST_COMPILER ?= aarch64-linux-android-clang++
|
||||
endif
|
||||
else ifeq ($(TARGET_ARCH),sbsa)
|
||||
HOST_COMPILER ?= aarch64-linux-gnu-g++
|
||||
else ifeq ($(TARGET_ARCH),ppc64le)
|
||||
HOST_COMPILER ?= powerpc64le-linux-gnu-g++
|
||||
endif
|
||||
endif
|
||||
HOST_COMPILER ?= g++
|
||||
NVCC := $(CUDA_PATH)/bin/nvcc -ccbin $(HOST_COMPILER)
|
||||
|
||||
# internal flags
|
||||
NVCCFLAGS := -m${TARGET_SIZE}
|
||||
CCFLAGS :=
|
||||
LDFLAGS :=
|
||||
|
||||
# build flags
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
LDFLAGS += -rpath $(CUDA_PATH)/lib
|
||||
CCFLAGS += -arch $(HOST_ARCH)
|
||||
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-armv7l-linux)
|
||||
LDFLAGS += --dynamic-linker=/lib/ld-linux-armhf.so.3
|
||||
CCFLAGS += -mfloat-abi=hard
|
||||
else ifeq ($(TARGET_OS),android)
|
||||
LDFLAGS += -pie
|
||||
CCFLAGS += -fpie -fpic -fexceptions
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
|
||||
ifneq ($(TARGET_FS),)
|
||||
GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
|
||||
ifeq ($(GCCVERSIONLTEQ46),1)
|
||||
CCFLAGS += --sysroot=$(TARGET_FS)
|
||||
endif
|
||||
LDFLAGS += --sysroot=$(TARGET_FS)
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/arm-linux-gnueabihf
|
||||
endif
|
||||
endif
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
|
||||
ifneq ($(TARGET_FS),)
|
||||
GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
|
||||
ifeq ($(GCCVERSIONLTEQ46),1)
|
||||
CCFLAGS += --sysroot=$(TARGET_FS)
|
||||
endif
|
||||
LDFLAGS += --sysroot=$(TARGET_FS)
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib -L$(TARGET_FS)/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib/aarch64-linux-gnu -L$(TARGET_FS)/lib/aarch64-linux-gnu
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
|
||||
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
|
||||
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
|
||||
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
|
||||
endif
|
||||
endif
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
|
||||
NVCCFLAGS += --qpp-config 5.4.0,gcc_ntoaarch64le
|
||||
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
|
||||
LDFLAGS += -lsocket
|
||||
LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
|
||||
CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
|
||||
ifdef TARGET_OVERRIDE
|
||||
LDFLAGS += -lslog2
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_FS),)
|
||||
LDFLAGS += -L$(TARGET_FS)/usr/lib
|
||||
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
|
||||
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
|
||||
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
|
||||
CCFLAGS += -I$(TARGET_FS)/../include
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
ifdef TARGET_OVERRIDE # cuda toolkit targets override
|
||||
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
|
||||
endif
|
||||
|
||||
# Install directory of different arch
|
||||
CUDA_INSTALL_TARGET_DIR :=
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-gnueabihf/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),sbsa-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/sbsa-linux/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-android)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-androideabi/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-android)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux-androideabi/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-qnx)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/ARMv7-linux-QNX/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-qnx/
|
||||
else ifeq ($(TARGET_ARCH),ppc64le)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/ppc64le-linux/
|
||||
endif
|
||||
|
||||
# Debug build flags
|
||||
ifeq ($(dbg),1)
|
||||
CCFLAGS += -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))
|
||||
|
||||
UBUNTU = $(shell lsb_release -i -s 2>/dev/null | grep -i ubuntu)
|
||||
|
||||
SAMPLE_ENABLED := 1
|
||||
|
||||
# This sample is not supported on ARMv7
|
||||
ifeq ($(TARGET_ARCH),armv7l)
|
||||
$(info >>> WARNING - binomialOptions_nvrtc is not supported on ARMv7 - waiving sample <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
|
||||
# This sample is not supported on QNX
|
||||
ifeq ($(TARGET_OS),qnx)
|
||||
$(info >>> WARNING - binomialOptions_nvrtc is not supported on QNX - 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 :=
|
||||
|
||||
################################################################################
|
||||
|
||||
# libNVRTC specific libraries
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
LDFLAGS += -L$(CUDA_PATH)/lib -F/Library/Frameworks -framework CUDA
|
||||
endif
|
||||
|
||||
#Detect if installed version of GCC supports required C++11
|
||||
ifeq ($(TARGET_OS),linux)
|
||||
empty :=
|
||||
space := $(empty) $(empty)
|
||||
GCCVERSIONSTRING := $(shell expr `$(HOST_COMPILER) -dumpversion`)
|
||||
#Create version number without "."
|
||||
GCCVERSION := $(shell expr `echo $(GCCVERSIONSTRING)` | cut -f1 -d.)
|
||||
GCCVERSION += $(shell expr `echo $(GCCVERSIONSTRING)` | cut -f2 -d.)
|
||||
GCCVERSION += $(shell expr `echo $(GCCVERSIONSTRING)` | cut -f3 -d.)
|
||||
# Make sure the version number has at least 3 decimals
|
||||
GCCVERSION += 00
|
||||
# Remove spaces from the version number
|
||||
GCCVERSION := $(subst $(space),$(empty),$(GCCVERSION))
|
||||
#$(warning $(GCCVERSION))
|
||||
|
||||
IS_MIN_VERSION := $(shell expr `echo $(GCCVERSION)` \>= 51000)
|
||||
|
||||
ifeq ($(IS_MIN_VERSION), 1)
|
||||
$(info >>> GCC Version is greater or equal to 5.1.0 <<<)
|
||||
else
|
||||
$(info >>> Waiving build. Minimum GCC version required is 5.1.0<<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
ALL_LDFLAGS += -Xcompiler -F/Library/Frameworks -Xlinker -framework -Xlinker CUDA
|
||||
else
|
||||
ifeq ($(TARGET_ARCH),x86_64)
|
||||
CUDA_SEARCH_PATH ?= $(CUDA_PATH)/lib64/stubs
|
||||
CUDA_SEARCH_PATH += $(CUDA_PATH)/targets/x86_64-linux/lib/stubs
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
|
||||
CUDA_SEARCH_PATH ?= $(CUDA_PATH)/targets/armv7-linux-gnueabihf/lib/stubs
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
|
||||
CUDA_SEARCH_PATH ?= $(CUDA_PATH)/targets/aarch64-linux/lib/stubs
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),sbsa-linux)
|
||||
CUDA_SEARCH_PATH ?= $(CUDA_PATH)/targets/sbsa-linux/lib/stubs
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-android)
|
||||
CUDA_SEARCH_PATH ?= $(CUDA_PATH)/targets/armv7-linux-androideabi/lib/stubs
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-android)
|
||||
CUDA_SEARCH_PATH ?= $(CUDA_PATH)/targets/aarch64-linux-androideabi/lib/stubs
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-qnx)
|
||||
CUDA_SEARCH_PATH ?= $(CUDA_PATH)/targets/ARMv7-linux-QNX/lib/stubs
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
|
||||
CUDA_SEARCH_PATH ?= $(CUDA_PATH)/targets/aarch64-qnx/lib/stubs
|
||||
ifdef TARGET_OVERRIDE
|
||||
CUDA_SEARCH_PATH := $(CUDA_PATH)/targets/$(TARGET_OVERRIDE)/lib/stubs
|
||||
endif
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_ARCH),ppc64le)
|
||||
CUDA_SEARCH_PATH ?= $(CUDA_PATH)/targets/ppc64le-linux/lib/stubs
|
||||
endif
|
||||
|
||||
ifeq ($(HOST_ARCH),ppc64le)
|
||||
CUDA_SEARCH_PATH += $(CUDA_PATH)/lib64/stubs
|
||||
endif
|
||||
|
||||
CUDALIB ?= $(shell find -L $(CUDA_SEARCH_PATH) -maxdepth 1 -name libcuda.so 2> /dev/null)
|
||||
ifeq ("$(CUDALIB)","")
|
||||
$(info >>> WARNING - libcuda.so not found, CUDA Driver is not installed. Please re-install the driver. <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
else
|
||||
CUDALIB := $(shell echo $(CUDALIB) | sed "s/ .*//" | sed "s/\/libcuda.so//" )
|
||||
LIBRARIES += -L$(CUDALIB) -lcuda
|
||||
endif
|
||||
endif
|
||||
|
||||
ALL_CCFLAGS += --threads 0 --std=c++11
|
||||
|
||||
INCLUDES += -I$(CUDA_PATH)/include
|
||||
|
||||
LIBRARIES += -lnvrtc
|
||||
|
||||
ifeq ($(SAMPLE_ENABLED),0)
|
||||
EXEC ?= @echo "[@]"
|
||||
endif
|
||||
|
||||
################################################################################
|
||||
|
||||
# Target rules
|
||||
all: build
|
||||
|
||||
build: binomialOptions_nvrtc
|
||||
|
||||
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
|
||||
|
||||
binomialOptions.o:binomialOptions.cpp
|
||||
$(EXEC) $(HOST_COMPILER) $(INCLUDES) $(CCFLAGS) $(EXTRA_CCFLAGS) -o $@ -c $<
|
||||
|
||||
binomialOptions_gold.o:binomialOptions_gold.cpp
|
||||
$(EXEC) $(HOST_COMPILER) $(INCLUDES) $(CCFLAGS) $(EXTRA_CCFLAGS) -o $@ -c $<
|
||||
|
||||
binomialOptions_gpu.o:binomialOptions_gpu.cpp
|
||||
$(EXEC) $(HOST_COMPILER) $(INCLUDES) $(CCFLAGS) $(EXTRA_CCFLAGS) -o $@ -c $<
|
||||
|
||||
binomialOptions_nvrtc: binomialOptions.o binomialOptions_gold.o binomialOptions_gpu.o
|
||||
$(EXEC) $(HOST_COMPILER) $(LDFLAGS) -o $@ $+ $(LIBRARIES)
|
||||
$(EXEC) mkdir -p ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
|
||||
$(EXEC) cp $@ ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
|
||||
|
||||
run: build
|
||||
$(EXEC) ./binomialOptions_nvrtc
|
||||
|
||||
clean:
|
||||
rm -f binomialOptions_nvrtc binomialOptions.o binomialOptions_gold.o binomialOptions_gpu.o
|
||||
rm -rf ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/binomialOptions_nvrtc
|
||||
|
||||
clobber: clean
|
||||
71
Samples/binomialOptions_nvrtc/README.md
Normal file
71
Samples/binomialOptions_nvrtc/README.md
Normal file
@@ -0,0 +1,71 @@
|
||||
# binomialOptions_nvrtc - Binomial Option Pricing with libNVRTC
|
||||
|
||||
## Description
|
||||
|
||||
This sample evaluates fair call price for a given set of European options under binomial model. This sample makes use of NVRTC for Runtime Compilation.
|
||||
|
||||
## Key Concepts
|
||||
|
||||
Computational Finance, Runtime Compilation
|
||||
|
||||
## Supported SM Architectures
|
||||
|
||||
[SM 3.5 ](https://developer.nvidia.com/cuda-gpus) [SM 3.7 ](https://developer.nvidia.com/cuda-gpus) [SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus)
|
||||
|
||||
## Supported OSes
|
||||
|
||||
Linux, Windows
|
||||
|
||||
## Supported CPU Architecture
|
||||
|
||||
x86_64, ppc64le, aarch64
|
||||
|
||||
## CUDA APIs involved
|
||||
|
||||
## Dependencies needed to build/run
|
||||
[NVRTC](../../README.md#nvrtc)
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Download and install the [CUDA Toolkit 11.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
|
||||
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
|
||||
|
||||
## Build and Run
|
||||
|
||||
### Windows
|
||||
The Windows samples are built using the Visual Studio IDE. Solution files (.sln) are provided for each supported version of Visual Studio, using the format:
|
||||
```
|
||||
*_vs<version>.sln - for Visual Studio <version>
|
||||
```
|
||||
Each individual sample has its own set of solution files in its directory:
|
||||
|
||||
To build/examine all the samples at once, the complete solution files should be used. To build/examine a single sample, the individual sample solution files should be used.
|
||||
> **Note:** Some samples require that the Microsoft DirectX SDK (June 2010 or newer) be installed and that the VC++ directory paths are properly set up (**Tools > Options...**). Check DirectX Dependencies section for details."
|
||||
|
||||
### Linux
|
||||
The Linux samples are built using makefiles. To use the makefiles, change the current directory to the sample directory you wish to build, and run make:
|
||||
```
|
||||
$ cd <sample_dir>
|
||||
$ make
|
||||
```
|
||||
The samples makefiles can take advantage of certain options:
|
||||
* **TARGET_ARCH=<arch>** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le, aarch64.
|
||||
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=aarch64` <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)
|
||||
|
||||
198
Samples/binomialOptions_nvrtc/binomialOptions.cpp
Normal file
198
Samples/binomialOptions_nvrtc/binomialOptions.cpp
Normal file
@@ -0,0 +1,198 @@
|
||||
/* Copyright (c) 2021, 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 sample evaluates fair call price for a
|
||||
* given set of European options under binomial model.
|
||||
* See supplied whitepaper for more explanations.
|
||||
*/
|
||||
|
||||
#include <stdlib.h>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <math.h>
|
||||
|
||||
#include <cuda_runtime.h>
|
||||
#include <cuda.h>
|
||||
|
||||
#include <helper_functions.h>
|
||||
|
||||
#include "binomialOptions_common.h"
|
||||
#include "realtype.h"
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Black-Scholes formula for binomial tree results validation
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
extern "C" void BlackScholesCall(real &callResult, TOptionData optionData);
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Process single option on CPU
|
||||
// Note that CPU code is for correctness testing only and not for benchmarking.
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
extern "C" void binomialOptionsCPU(real &callResult, TOptionData optionData);
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Process an array of OptN options on GPU
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
extern "C" void binomialOptionsGPU(real *callValue, TOptionData *optionData,
|
||||
int optN, int argc, char **argv);
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Helper function, returning uniformly distributed
|
||||
// random float in [low, high] range
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
real randData(real low, real high) {
|
||||
real t = (real)rand() / (real)RAND_MAX;
|
||||
return ((real)1.0 - t) * low + t * high;
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Main program
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
int main(int argc, char **argv) {
|
||||
printf("[%s] - Starting...\n", argv[0]);
|
||||
|
||||
const int OPT_N = MAX_OPTIONS;
|
||||
|
||||
TOptionData optionData[MAX_OPTIONS];
|
||||
real callValueBS[MAX_OPTIONS], callValueGPU[MAX_OPTIONS],
|
||||
callValueCPU[MAX_OPTIONS];
|
||||
|
||||
real sumDelta, sumRef, gpuTime, errorVal;
|
||||
|
||||
StopWatchInterface *hTimer = NULL;
|
||||
|
||||
int i;
|
||||
|
||||
sdkCreateTimer(&hTimer);
|
||||
|
||||
printf("Generating input data...\n");
|
||||
|
||||
// Generate options set
|
||||
srand(123);
|
||||
|
||||
for (i = 0; i < OPT_N; i++) {
|
||||
optionData[i].S = randData(5.0f, 30.0f);
|
||||
optionData[i].X = randData(1.0f, 100.0f);
|
||||
optionData[i].T = randData(0.25f, 10.0f);
|
||||
optionData[i].R = 0.06f;
|
||||
optionData[i].V = 0.10f;
|
||||
|
||||
BlackScholesCall(callValueBS[i], optionData[i]);
|
||||
}
|
||||
|
||||
printf("Running GPU binomial tree...\n");
|
||||
|
||||
sdkResetTimer(&hTimer);
|
||||
sdkStartTimer(&hTimer);
|
||||
|
||||
binomialOptionsGPU(callValueGPU, optionData, OPT_N, argc, argv);
|
||||
|
||||
sdkStopTimer(&hTimer);
|
||||
|
||||
gpuTime = sdkGetTimerValue(&hTimer);
|
||||
|
||||
printf("Options count : %i \n", OPT_N);
|
||||
printf("Time steps : %i \n", NUM_STEPS);
|
||||
printf("binomialOptionsGPU() time: %f msec\n", gpuTime);
|
||||
printf("Options per second : %f \n", OPT_N / (gpuTime * 0.001));
|
||||
|
||||
printf("Running CPU binomial tree...\n");
|
||||
|
||||
for (i = 0; i < OPT_N; i++) {
|
||||
binomialOptionsCPU(callValueCPU[i], optionData[i]);
|
||||
}
|
||||
|
||||
printf("Comparing the results...\n");
|
||||
|
||||
sumDelta = 0;
|
||||
sumRef = 0;
|
||||
printf("GPU binomial vs. Black-Scholes\n");
|
||||
|
||||
for (i = 0; i < OPT_N; i++) {
|
||||
sumDelta += fabs(callValueBS[i] - callValueGPU[i]);
|
||||
sumRef += fabs(callValueBS[i]);
|
||||
}
|
||||
|
||||
if (sumRef > 1E-5) {
|
||||
printf("L1 norm: %E\n", (double)(sumDelta / sumRef));
|
||||
} else {
|
||||
printf("Avg. diff: %E\n", (double)(sumDelta / (real)OPT_N));
|
||||
}
|
||||
|
||||
printf("CPU binomial vs. Black-Scholes\n");
|
||||
sumDelta = 0;
|
||||
sumRef = 0;
|
||||
|
||||
for (i = 0; i < OPT_N; i++) {
|
||||
sumDelta += fabs(callValueBS[i] - callValueCPU[i]);
|
||||
sumRef += fabs(callValueBS[i]);
|
||||
}
|
||||
|
||||
if (sumRef > 1E-5) {
|
||||
printf("L1 norm: %E\n", sumDelta / sumRef);
|
||||
} else {
|
||||
printf("Avg. diff: %E\n", (double)(sumDelta / (real)OPT_N));
|
||||
}
|
||||
|
||||
printf("CPU binomial vs. GPU binomial\n");
|
||||
sumDelta = 0;
|
||||
sumRef = 0;
|
||||
|
||||
for (i = 0; i < OPT_N; i++) {
|
||||
sumDelta += fabs(callValueGPU[i] - callValueCPU[i]);
|
||||
sumRef += callValueCPU[i];
|
||||
}
|
||||
|
||||
if (sumRef > 1E-5) {
|
||||
printf("L1 norm: %E\n", errorVal = sumDelta / sumRef);
|
||||
} else {
|
||||
printf("Avg. diff: %E\n", (double)(sumDelta / (real)OPT_N));
|
||||
}
|
||||
|
||||
printf("Shutting down...\n");
|
||||
|
||||
sdkDeleteTimer(&hTimer);
|
||||
|
||||
printf(
|
||||
"\nNOTE: The CUDA Samples are not meant for performance measurements. "
|
||||
"Results may vary when GPU Boost is enabled.\n\n");
|
||||
|
||||
if (errorVal > 5e-4) {
|
||||
printf("Test failed!\n");
|
||||
exit(EXIT_FAILURE);
|
||||
}
|
||||
|
||||
printf("Test passed\n");
|
||||
|
||||
exit(EXIT_SUCCESS);
|
||||
}
|
||||
53
Samples/binomialOptions_nvrtc/binomialOptions_common.h
Normal file
53
Samples/binomialOptions_nvrtc/binomialOptions_common.h
Normal file
@@ -0,0 +1,53 @@
|
||||
/* Copyright (c) 2021, 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 BINOMIALOPTIONS_COMMON_H
|
||||
#define BINOMIALOPTIONS_COMMON_H
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Global types
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
typedef struct {
|
||||
float S;
|
||||
float X;
|
||||
float T;
|
||||
float R;
|
||||
float V;
|
||||
} TOptionData;
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Global parameters
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
// Number of time steps
|
||||
#define NUM_STEPS 2048
|
||||
|
||||
// Max option batch size
|
||||
#define MAX_OPTIONS 1024
|
||||
|
||||
#endif
|
||||
126
Samples/binomialOptions_nvrtc/binomialOptions_gold.cpp
Normal file
126
Samples/binomialOptions_nvrtc/binomialOptions_gold.cpp
Normal file
@@ -0,0 +1,126 @@
|
||||
/* Copyright (c) 2021, 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 "binomialOptions_common.h"
|
||||
|
||||
///////////////////////////////////////////////////////////////////////////////
|
||||
// Polynomial approximation of cumulative normal distribution function
|
||||
///////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
static double CND(double d) {
|
||||
const double A1 = 0.31938153;
|
||||
const double A2 = -0.356563782;
|
||||
const double A3 = 1.781477937;
|
||||
const double A4 = -1.821255978;
|
||||
const double A5 = 1.330274429;
|
||||
const double RSQRT2PI = 0.39894228040143267793994605993438;
|
||||
|
||||
double K = 1.0 / (1.0 + 0.2316419 * fabs(d));
|
||||
|
||||
double cnd = RSQRT2PI * exp(-0.5 * d * d) *
|
||||
(K * (A1 + K * (A2 + K * (A3 + K * (A4 + K * A5)))));
|
||||
|
||||
if (d > 0) cnd = 1.0 - cnd;
|
||||
|
||||
return cnd;
|
||||
}
|
||||
|
||||
extern "C" void BlackScholesCall(float &callResult, TOptionData optionData) {
|
||||
double S = optionData.S;
|
||||
double X = optionData.X;
|
||||
double T = optionData.T;
|
||||
double R = optionData.R;
|
||||
double V = optionData.V;
|
||||
double sqrtT = sqrt(T);
|
||||
|
||||
double d1 = (log(S / X) + (R + 0.5 * V * V) * T) / (V * sqrtT);
|
||||
double d2 = d1 - V * sqrtT;
|
||||
|
||||
double CNDD1 = CND(d1);
|
||||
double CNDD2 = CND(d2);
|
||||
|
||||
// Calculate Call and Put simultaneously
|
||||
double expRT = exp(-R * T);
|
||||
|
||||
callResult = (float)(S * CNDD1 - X * expRT * CNDD2);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Process an array of OptN options on CPU
|
||||
// Note that CPU code is for correctness testing only and not for benchmarking.
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
static double expiryCallValue(double S, double X, double vDt, int i) {
|
||||
double d = S * exp(vDt * (2.0 * i - NUM_STEPS)) - X;
|
||||
return (d > 0) ? d : 0;
|
||||
}
|
||||
|
||||
extern "C" void binomialOptionsCPU(float &callResult, TOptionData optionData) {
|
||||
static double Call[NUM_STEPS + 1];
|
||||
const double S = optionData.S;
|
||||
const double X = optionData.X;
|
||||
const double T = optionData.T;
|
||||
const double R = optionData.R;
|
||||
const double V = optionData.V;
|
||||
|
||||
const double dt = T / (double)NUM_STEPS;
|
||||
const double vDt = V * sqrt(dt);
|
||||
const double rDt = R * dt;
|
||||
|
||||
// Per-step interest and discount factors
|
||||
const double If = exp(rDt);
|
||||
const double Df = exp(-rDt);
|
||||
|
||||
// Values and pseudoprobabilities of upward and downward moves
|
||||
const double u = exp(vDt);
|
||||
const double d = exp(-vDt);
|
||||
const double pu = (If - d) / (u - d);
|
||||
const double pd = 1.0 - pu;
|
||||
const double puByDf = pu * Df;
|
||||
const double pdByDf = pd * Df;
|
||||
|
||||
///////////////////////////////////////////////////////////////////////
|
||||
// Compute values at expiration date:
|
||||
// call option value at period end is V(T) = S(T) - X
|
||||
// if S(T) is greater than X, or zero otherwise.
|
||||
// The computation is similar for put options.
|
||||
///////////////////////////////////////////////////////////////////////
|
||||
|
||||
for (int i = 0; i <= NUM_STEPS; i++) Call[i] = expiryCallValue(S, X, vDt, i);
|
||||
|
||||
////////////////////////////////////////////////////////////////////////
|
||||
// Walk backwards up binomial tree
|
||||
////////////////////////////////////////////////////////////////////////
|
||||
|
||||
for (int i = NUM_STEPS; i > 0; i--)
|
||||
for (int j = 0; j <= i - 1; j++)
|
||||
Call[j] = puByDf * Call[j + 1] + pdByDf * Call[j];
|
||||
|
||||
callResult = (float)Call[0];
|
||||
}
|
||||
127
Samples/binomialOptions_nvrtc/binomialOptions_gpu.cpp
Normal file
127
Samples/binomialOptions_nvrtc/binomialOptions_gpu.cpp
Normal file
@@ -0,0 +1,127 @@
|
||||
/* Copyright (c) 2021, 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.
|
||||
*/
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Global types and parameters
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <cmath>
|
||||
|
||||
#include <helper_cuda.h>
|
||||
#include <nvrtc_helper.h>
|
||||
#include <cuda_runtime.h>
|
||||
|
||||
#include "binomialOptions_common.h"
|
||||
|
||||
#include "common_gpu_header.h"
|
||||
#include "realtype.h"
|
||||
|
||||
// Preprocessed input option data
|
||||
typedef struct {
|
||||
real S;
|
||||
real X;
|
||||
real vDt;
|
||||
real puByDf;
|
||||
real pdByDf;
|
||||
|
||||
} __TOptionData;
|
||||
|
||||
static bool moduleLoaded = false;
|
||||
char *cubin, *kernel_file;
|
||||
size_t cubinSize;
|
||||
CUmodule module;
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Host-side interface to GPU binomialOptions
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
extern "C" void binomialOptionsGPU(real *callValue, TOptionData *optionData,
|
||||
int optN, int argc, char **argv) {
|
||||
if (!moduleLoaded) {
|
||||
kernel_file = sdkFindFilePath("binomialOptions_kernel.cu", argv[0]);
|
||||
compileFileToCUBIN(kernel_file, argc, argv, &cubin, &cubinSize, 0);
|
||||
module = loadCUBIN(cubin, argc, argv);
|
||||
moduleLoaded = true;
|
||||
}
|
||||
|
||||
__TOptionData h_OptionData[MAX_OPTIONS];
|
||||
|
||||
for (int i = 0; i < optN; i++) {
|
||||
const real T = optionData[i].T;
|
||||
const real R = optionData[i].R;
|
||||
const real V = optionData[i].V;
|
||||
|
||||
const real dt = T / (real)NUM_STEPS;
|
||||
const real vDt = V * sqrt(dt);
|
||||
const real rDt = R * dt;
|
||||
// Per-step interest and discount factors
|
||||
const real If = exp(rDt);
|
||||
const real Df = exp(-rDt);
|
||||
// Values and pseudoprobabilities of upward and downward moves
|
||||
const real u = exp(vDt);
|
||||
const real d = exp(-vDt);
|
||||
const real pu = (If - d) / (u - d);
|
||||
const real pd = (real)1.0 - pu;
|
||||
const real puByDf = pu * Df;
|
||||
const real pdByDf = pd * Df;
|
||||
|
||||
h_OptionData[i].S = (real)optionData[i].S;
|
||||
h_OptionData[i].X = (real)optionData[i].X;
|
||||
h_OptionData[i].vDt = (real)vDt;
|
||||
h_OptionData[i].puByDf = (real)puByDf;
|
||||
h_OptionData[i].pdByDf = (real)pdByDf;
|
||||
}
|
||||
|
||||
CUfunction kernel_addr;
|
||||
checkCudaErrors(
|
||||
cuModuleGetFunction(&kernel_addr, module, "binomialOptionsKernel"));
|
||||
|
||||
CUdeviceptr d_OptionData;
|
||||
checkCudaErrors(
|
||||
cuModuleGetGlobal(&d_OptionData, NULL, module, "d_OptionData"));
|
||||
checkCudaErrors(
|
||||
cuMemcpyHtoD(d_OptionData, h_OptionData, optN * sizeof(__TOptionData)));
|
||||
|
||||
dim3 cudaBlockSize(128, 1, 1);
|
||||
dim3 cudaGridSize(optN, 1, 1);
|
||||
|
||||
checkCudaErrors(cuLaunchKernel(kernel_addr, cudaGridSize.x, cudaGridSize.y,
|
||||
cudaGridSize.z, /* grid dim */
|
||||
cudaBlockSize.x, cudaBlockSize.y,
|
||||
cudaBlockSize.z, /* block dim */
|
||||
0, 0, /* shared mem, stream */
|
||||
NULL, /* arguments */
|
||||
0));
|
||||
|
||||
checkCudaErrors(cuCtxSynchronize());
|
||||
|
||||
CUdeviceptr d_CallValue;
|
||||
checkCudaErrors(cuModuleGetGlobal(&d_CallValue, NULL, module, "d_CallValue"));
|
||||
checkCudaErrors(cuMemcpyDtoH(callValue, d_CallValue, optN * sizeof(real)));
|
||||
}
|
||||
107
Samples/binomialOptions_nvrtc/binomialOptions_kernel.cu
Normal file
107
Samples/binomialOptions_nvrtc/binomialOptions_kernel.cu
Normal file
@@ -0,0 +1,107 @@
|
||||
/* Copyright (c) 2021, 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 "common_gpu_header.h"
|
||||
#include "binomialOptions_common.h"
|
||||
#include "realtype.h"
|
||||
|
||||
// Preprocessed input option data
|
||||
typedef struct {
|
||||
real S;
|
||||
real X;
|
||||
real vDt;
|
||||
real puByDf;
|
||||
real pdByDf;
|
||||
} __TOptionData;
|
||||
static __constant__ __TOptionData d_OptionData[MAX_OPTIONS];
|
||||
__device__ real d_CallValue[MAX_OPTIONS];
|
||||
|
||||
#define THREADBLOCK_SIZE 128
|
||||
#define ELEMS_PER_THREAD (NUM_STEPS / THREADBLOCK_SIZE)
|
||||
#if NUM_STEPS % THREADBLOCK_SIZE
|
||||
#error Bad constants
|
||||
#endif
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Overloaded shortcut functions for different precision modes
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
#ifndef DOUBLE_PRECISION
|
||||
__device__ inline float expiryCallValue(float S, float X, float vDt, int i) {
|
||||
float d = S * __expf(vDt * (2.0f * i - NUM_STEPS)) - X;
|
||||
return (d > 0.0F) ? d : 0.0F;
|
||||
}
|
||||
|
||||
#else
|
||||
__device__ inline double expiryCallValue(double S, double X, double vDt,
|
||||
int i) {
|
||||
double d = S * exp(vDt * (2.0 * i - NUM_STEPS)) - X;
|
||||
return (d > 0.0) ? d : 0.0;
|
||||
}
|
||||
#endif
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// GPU kernel
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
extern "C" __global__ void binomialOptionsKernel() {
|
||||
__shared__ real call_exchange[THREADBLOCK_SIZE + 1];
|
||||
|
||||
const int tid = threadIdx.x;
|
||||
const real S = d_OptionData[blockIdx.x].S;
|
||||
const real X = d_OptionData[blockIdx.x].X;
|
||||
const real vDt = d_OptionData[blockIdx.x].vDt;
|
||||
const real puByDf = d_OptionData[blockIdx.x].puByDf;
|
||||
const real pdByDf = d_OptionData[blockIdx.x].pdByDf;
|
||||
|
||||
real call[ELEMS_PER_THREAD + 1];
|
||||
#pragma unroll
|
||||
for (int i = 0; i < ELEMS_PER_THREAD; ++i)
|
||||
call[i] = expiryCallValue(S, X, vDt, tid * ELEMS_PER_THREAD + i);
|
||||
|
||||
if (tid == 0)
|
||||
call_exchange[THREADBLOCK_SIZE] = expiryCallValue(S, X, vDt, NUM_STEPS);
|
||||
|
||||
int final_it = max(0, tid * ELEMS_PER_THREAD - 1);
|
||||
|
||||
#pragma unroll 16
|
||||
for (int i = NUM_STEPS; i > 0; --i) {
|
||||
call_exchange[tid] = call[0];
|
||||
__syncthreads();
|
||||
call[ELEMS_PER_THREAD] = call_exchange[tid + 1];
|
||||
__syncthreads();
|
||||
|
||||
if (i > final_it) {
|
||||
#pragma unroll
|
||||
for (int j = 0; j < ELEMS_PER_THREAD; ++j)
|
||||
call[j] = puByDf * call[j + 1] + pdByDf * call[j];
|
||||
}
|
||||
}
|
||||
|
||||
if (tid == 0) {
|
||||
d_CallValue[blockIdx.x] = call[0];
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2017
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "binomialOptions_nvrtc", "binomialOptions_nvrtc_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 +1,118 @@
|
||||
<?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>binomialOptions_nvrtc_vs2017</RootNamespace>
|
||||
<ProjectName>binomialOptions_nvrtc</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 11.5.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
|
||||
</ImportGroup>
|
||||
<PropertyGroup Label="UserMacros" />
|
||||
<PropertyGroup>
|
||||
<IntDir>$(Platform)/$(Configuration)/</IntDir>
|
||||
<IncludePath>$(IncludePath)</IncludePath>
|
||||
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
|
||||
<CodeAnalysisRules />
|
||||
<CodeAnalysisRuleAssemblies />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Platform)'=='x64'">
|
||||
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
|
||||
</PropertyGroup>
|
||||
<ItemDefinitionGroup>
|
||||
<ClCompile>
|
||||
<WarningLevel>Level3</WarningLevel>
|
||||
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
|
||||
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);$(CUDA_PATH)/include;</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cuda.lib;nvrtc.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)/binomialOptions_nvrtc.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration></CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
|
||||
<Include>./;../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
<AdditionalOptions>--threads 0</AdditionalOptions>
|
||||
</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="binomialOptions.cpp" />
|
||||
<ClCompile Include="binomialOptions_gold.cpp" />
|
||||
<ClCompile Include="binomialOptions_gpu.cpp" />
|
||||
<ClInclude Include="binomialOptions_common.h" />
|
||||
<ClInclude Include="common_gpu_header.h" />
|
||||
<ClInclude Include="realtype.h" />
|
||||
<None Include="binomialOptions_kernel.cu" />
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.5.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}") = "binomialOptions_nvrtc", "binomialOptions_nvrtc_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 +1,114 @@
|
||||
<?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>binomialOptions_nvrtc_vs2019</RootNamespace>
|
||||
<ProjectName>binomialOptions_nvrtc</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="$(CUDAPropsPath)\CUDA 11.5.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
|
||||
</ImportGroup>
|
||||
<PropertyGroup Label="UserMacros" />
|
||||
<PropertyGroup>
|
||||
<IntDir>$(Platform)/$(Configuration)/</IntDir>
|
||||
<IncludePath>$(IncludePath)</IncludePath>
|
||||
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
|
||||
<CodeAnalysisRules />
|
||||
<CodeAnalysisRuleAssemblies />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Platform)'=='x64'">
|
||||
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
|
||||
</PropertyGroup>
|
||||
<ItemDefinitionGroup>
|
||||
<ClCompile>
|
||||
<WarningLevel>Level3</WarningLevel>
|
||||
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
|
||||
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);$(CUDA_PATH)/include;</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cuda.lib;nvrtc.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);</AdditionalLibraryDirectories>
|
||||
<OutputFile>$(OutDir)/binomialOptions_nvrtc.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration></CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
|
||||
<Include>./;../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
<AdditionalOptions>--threads 0</AdditionalOptions>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(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="'$(Configuration)'=='Release'">
|
||||
<ClCompile>
|
||||
<Optimization>MaxSpeed</Optimization>
|
||||
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>false</GenerateDebugInformation>
|
||||
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<Runtime>MT</Runtime>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="binomialOptions.cpp" />
|
||||
<ClCompile Include="binomialOptions_gold.cpp" />
|
||||
<ClCompile Include="binomialOptions_gpu.cpp" />
|
||||
<ClInclude Include="binomialOptions_common.h" />
|
||||
<ClInclude Include="common_gpu_header.h" />
|
||||
<ClInclude Include="realtype.h" />
|
||||
<None Include="binomialOptions_kernel.cu" />
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
31
Samples/binomialOptions_nvrtc/common_gpu_header.h
Normal file
31
Samples/binomialOptions_nvrtc/common_gpu_header.h
Normal file
@@ -0,0 +1,31 @@
|
||||
/*
|
||||
* Copyright 1993-2015 NVIDIA Corporation. All rights reserved.
|
||||
*
|
||||
* Please refer to the NVIDIA end user license agreement (EULA) associated
|
||||
* with this source code for terms and conditions that govern your use of
|
||||
* this software. Any use, reproduction, disclosure, or distribution of
|
||||
* this software and related documentation outside the terms of the EULA
|
||||
* is strictly prohibited.
|
||||
*
|
||||
*/
|
||||
|
||||
#if !defined(__COMMON_GPU_HEADER_H)
|
||||
#define __COMMON_GPU_HEADER_H
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Internal GPU-side constants and data structures
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
#define TIME_STEPS 16
|
||||
|
||||
#define CACHE_DELTA (2 * TIME_STEPS)
|
||||
|
||||
#define CACHE_SIZE (256)
|
||||
|
||||
#define CACHE_STEP (CACHE_SIZE - CACHE_DELTA)
|
||||
|
||||
#if NUM_STEPS % CACHE_DELTA
|
||||
#error Bad constants
|
||||
#endif
|
||||
|
||||
#endif
|
||||
41
Samples/binomialOptions_nvrtc/realtype.h
Normal file
41
Samples/binomialOptions_nvrtc/realtype.h
Normal file
@@ -0,0 +1,41 @@
|
||||
/* Copyright (c) 2021, 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 REALTYPE_H
|
||||
#define REALTYPE_H
|
||||
|
||||
// To use double precision uncomment the macro DOUBLE_PRECISION below, default
|
||||
// is single precision.
|
||||
//#define DOUBLE_PRECISION
|
||||
|
||||
#ifndef DOUBLE_PRECISION
|
||||
typedef float real;
|
||||
#else
|
||||
typedef double real;
|
||||
#endif
|
||||
|
||||
#endif
|
||||
Reference in New Issue
Block a user