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/stereoDisparity/.vscode/c_cpp_properties.json
vendored
Normal file
18
Samples/5_Domain_Specific/stereoDisparity/.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/stereoDisparity/.vscode/extensions.json
vendored
Normal file
7
Samples/5_Domain_Specific/stereoDisparity/.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/stereoDisparity/.vscode/launch.json
vendored
Normal file
10
Samples/5_Domain_Specific/stereoDisparity/.vscode/launch.json
vendored
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"configurations": [
|
||||
{
|
||||
"name": "CUDA C++: Launch",
|
||||
"type": "cuda-gdb",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/stereoDisparity"
|
||||
}
|
||||
]
|
||||
}
|
||||
15
Samples/5_Domain_Specific/stereoDisparity/.vscode/tasks.json
vendored
Normal file
15
Samples/5_Domain_Specific/stereoDisparity/.vscode/tasks.json
vendored
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"version": "2.0.0",
|
||||
"tasks": [
|
||||
{
|
||||
"label": "sample",
|
||||
"type": "shell",
|
||||
"command": "make dbg=1",
|
||||
"problemMatcher": ["$nvcc"],
|
||||
"group": {
|
||||
"kind": "build",
|
||||
"isDefault": true
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
340
Samples/5_Domain_Specific/stereoDisparity/Makefile
Normal file
340
Samples/5_Domain_Specific/stereoDisparity/Makefile
Normal file
@@ -0,0 +1,340 @@
|
||||
################################################################################
|
||||
# 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 ($(SAMPLE_ENABLED),0)
|
||||
EXEC ?= @echo "[@]"
|
||||
endif
|
||||
|
||||
################################################################################
|
||||
|
||||
# Target rules
|
||||
all: build
|
||||
|
||||
build: stereoDisparity
|
||||
|
||||
check.deps:
|
||||
ifeq ($(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
|
||||
|
||||
stereoDisparity.o:stereoDisparity.cu
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
stereoDisparity: stereoDisparity.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
|
||||
$(EXEC) ./stereoDisparity
|
||||
|
||||
testrun: build
|
||||
|
||||
clean:
|
||||
rm -f stereoDisparity stereoDisparity.o *.pgm
|
||||
rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/stereoDisparity
|
||||
|
||||
clobber: clean
|
||||
92
Samples/5_Domain_Specific/stereoDisparity/NsightEclipse.xml
Normal file
92
Samples/5_Domain_Specific/stereoDisparity/NsightEclipse.xml
Normal file
@@ -0,0 +1,92 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
||||
<entry>
|
||||
<name>stereoDisparity</name>
|
||||
<cleanextras>
|
||||
<clean>*.pgm</clean>
|
||||
</cleanextras>
|
||||
<cuda_api_list>
|
||||
<toolkit>cudaFree</toolkit>
|
||||
<toolkit>cudaEventRecord</toolkit>
|
||||
<toolkit>cudaEventCreate</toolkit>
|
||||
<toolkit>cudaEventElapsedTime</toolkit>
|
||||
<toolkit>cudaDeviceSynchronize</toolkit>
|
||||
<toolkit>cudaEventSynchronize</toolkit>
|
||||
<toolkit>cudaCreateTextureObject</toolkit>
|
||||
<toolkit>cudaMalloc</toolkit>
|
||||
<toolkit>cudaMemcpy</toolkit>
|
||||
<toolkit>cudaGetDeviceProperties</toolkit>
|
||||
</cuda_api_list>
|
||||
<description><![CDATA[A CUDA program that demonstrates how to compute a stereo disparity map using SIMD SAD (Sum of Absolute Difference) intrinsics. Requires Compute Capability 2.0 or higher.]]></description>
|
||||
<devicecompilation>whole</devicecompilation>
|
||||
<files>
|
||||
<file>data\stereo.im0.640x533.ppm</file>
|
||||
<file>data\stereo.im1.640x533.ppm</file>
|
||||
</files>
|
||||
<includepaths>
|
||||
<path>./</path>
|
||||
<path>../</path>
|
||||
<path>../../../Common</path>
|
||||
</includepaths>
|
||||
<keyconcepts>
|
||||
<concept level="advanced">Image Processing</concept>
|
||||
<concept level="advanced">Video Intrinsics</concept>
|
||||
</keyconcepts>
|
||||
<keywords>
|
||||
<keyword>CUDA</keyword>
|
||||
<keyword>GPGPU</keyword>
|
||||
<keyword>atomic</keyword>
|
||||
</keywords>
|
||||
<libraries>
|
||||
</libraries>
|
||||
<librarypaths>
|
||||
</librarypaths>
|
||||
<nsight_eclipse>true</nsight_eclipse>
|
||||
<primary_file>stereoDisparity.cu</primary_file>
|
||||
<scopes>
|
||||
<scope>2:Graphics Interop</scope>
|
||||
<scope>1:CUDA Advanced Topics</scope>
|
||||
<scope>2:Image Processing</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>Stereo Disparity Computation (SAD SIMD Intrinsics)</title>
|
||||
<type>exe</type>
|
||||
</entry>
|
||||
70
Samples/5_Domain_Specific/stereoDisparity/README.md
Normal file
70
Samples/5_Domain_Specific/stereoDisparity/README.md
Normal file
@@ -0,0 +1,70 @@
|
||||
# stereoDisparity - Stereo Disparity Computation (SAD SIMD Intrinsics)
|
||||
|
||||
## Description
|
||||
|
||||
A CUDA program that demonstrates how to compute a stereo disparity map using SIMD SAD (Sum of Absolute Difference) intrinsics. Requires Compute Capability 2.0 or higher.
|
||||
|
||||
## Key Concepts
|
||||
|
||||
Image Processing, Video Intrinsics
|
||||
|
||||
## 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)
|
||||
cudaFree, cudaEventRecord, cudaEventCreate, cudaEventElapsedTime, cudaDeviceSynchronize, cudaEventSynchronize, cudaCreateTextureObject, cudaMalloc, cudaMemcpy, cudaGetDeviceProperties
|
||||
|
||||
## 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)
|
||||
|
||||
Binary file not shown.
Binary file not shown.
282
Samples/5_Domain_Specific/stereoDisparity/stereoDisparity.cu
Normal file
282
Samples/5_Domain_Specific/stereoDisparity/stereoDisparity.cu
Normal file
@@ -0,0 +1,282 @@
|
||||
/* 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.
|
||||
*/
|
||||
|
||||
/* A CUDA program that demonstrates how to compute a stereo disparity map using
|
||||
* SIMD SAD (Sum of Absolute Difference) intrinsics
|
||||
*/
|
||||
|
||||
// includes, system
|
||||
#include <stdlib.h>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <math.h>
|
||||
|
||||
// includes, kernels
|
||||
#include <cuda_runtime.h>
|
||||
#include "stereoDisparity_kernel.cuh"
|
||||
|
||||
// includes, project
|
||||
#include <helper_functions.h> // helper for shared that are common to CUDA Samples
|
||||
#include <helper_cuda.h> // helper for checking cuda initialization and error checking
|
||||
#include <helper_string.h> // helper functions for string parsing
|
||||
|
||||
static const char *sSDKsample = "[stereoDisparity]\0";
|
||||
|
||||
int iDivUp(int a, int b) { return ((a % b) != 0) ? (a / b + 1) : (a / b); }
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// declaration, forward
|
||||
void runTest(int argc, char **argv);
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Program main
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
int main(int argc, char **argv) {
|
||||
printf("%s Starting...\n\n", sSDKsample);
|
||||
runTest(argc, argv);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! CUDA Sample for calculating depth maps
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void runTest(int argc, char **argv) {
|
||||
cudaDeviceProp deviceProp;
|
||||
deviceProp.major = 0;
|
||||
deviceProp.minor = 0;
|
||||
int dev = 0;
|
||||
|
||||
// This will pick the best possible CUDA capable device
|
||||
dev = findCudaDevice(argc, (const char **)argv);
|
||||
|
||||
checkCudaErrors(cudaGetDeviceProperties(&deviceProp, dev));
|
||||
|
||||
// Statistics about the GPU device
|
||||
printf(
|
||||
"> GPU device has %d Multi-Processors, SM %d.%d compute capabilities\n\n",
|
||||
deviceProp.multiProcessorCount, deviceProp.major, deviceProp.minor);
|
||||
|
||||
StopWatchInterface *timer;
|
||||
sdkCreateTimer(&timer);
|
||||
|
||||
// Search parameters
|
||||
int minDisp = -16;
|
||||
int maxDisp = 0;
|
||||
|
||||
// Load image data
|
||||
// allocate mem for the images on host side
|
||||
// initialize pointers to NULL to request lib call to allocate as needed
|
||||
// PPM images are loaded into 4 byte/pixel memory (RGBX)
|
||||
unsigned char *h_img0 = NULL;
|
||||
unsigned char *h_img1 = NULL;
|
||||
unsigned int w, h;
|
||||
char *fname0 = sdkFindFilePath("stereo.im0.640x533.ppm", argv[0]);
|
||||
char *fname1 = sdkFindFilePath("stereo.im1.640x533.ppm", argv[0]);
|
||||
|
||||
printf("Loaded <%s> as image 0\n", fname0);
|
||||
|
||||
if (!sdkLoadPPM4ub(fname0, &h_img0, &w, &h)) {
|
||||
fprintf(stderr, "Failed to load <%s>\n", fname0);
|
||||
}
|
||||
|
||||
printf("Loaded <%s> as image 1\n", fname1);
|
||||
|
||||
if (!sdkLoadPPM4ub(fname1, &h_img1, &w, &h)) {
|
||||
fprintf(stderr, "Failed to load <%s>\n", fname1);
|
||||
}
|
||||
|
||||
dim3 numThreads = dim3(blockSize_x, blockSize_y, 1);
|
||||
dim3 numBlocks = dim3(iDivUp(w, numThreads.x), iDivUp(h, numThreads.y));
|
||||
unsigned int numData = w * h;
|
||||
unsigned int memSize = sizeof(int) * numData;
|
||||
|
||||
// allocate mem for the result on host side
|
||||
unsigned int *h_odata = (unsigned int *)malloc(memSize);
|
||||
|
||||
// initialize the memory
|
||||
for (unsigned int i = 0; i < numData; i++) h_odata[i] = 0;
|
||||
|
||||
// allocate device memory for result
|
||||
unsigned int *d_odata, *d_img0, *d_img1;
|
||||
|
||||
checkCudaErrors(cudaMalloc((void **)&d_odata, memSize));
|
||||
checkCudaErrors(cudaMalloc((void **)&d_img0, memSize));
|
||||
checkCudaErrors(cudaMalloc((void **)&d_img1, memSize));
|
||||
|
||||
// copy host memory to device to initialize to zeros
|
||||
checkCudaErrors(cudaMemcpy(d_img0, h_img0, memSize, cudaMemcpyHostToDevice));
|
||||
checkCudaErrors(cudaMemcpy(d_img1, h_img1, memSize, cudaMemcpyHostToDevice));
|
||||
checkCudaErrors(
|
||||
cudaMemcpy(d_odata, h_odata, memSize, cudaMemcpyHostToDevice));
|
||||
|
||||
cudaChannelFormatDesc ca_desc0 = cudaCreateChannelDesc<unsigned int>();
|
||||
cudaChannelFormatDesc ca_desc1 = cudaCreateChannelDesc<unsigned int>();
|
||||
|
||||
cudaTextureObject_t tex2Dleft, tex2Dright;
|
||||
cudaResourceDesc texRes;
|
||||
memset(&texRes, 0, sizeof(cudaResourceDesc));
|
||||
|
||||
texRes.resType = cudaResourceTypePitch2D;
|
||||
texRes.res.pitch2D.devPtr = d_img0;
|
||||
texRes.res.pitch2D.desc = ca_desc0;
|
||||
texRes.res.pitch2D.width = w;
|
||||
texRes.res.pitch2D.height = h;
|
||||
texRes.res.pitch2D.pitchInBytes = w * 4;
|
||||
|
||||
cudaTextureDesc texDescr;
|
||||
memset(&texDescr, 0, sizeof(cudaTextureDesc));
|
||||
|
||||
texDescr.normalizedCoords = false;
|
||||
texDescr.filterMode = cudaFilterModePoint;
|
||||
texDescr.addressMode[0] = cudaAddressModeClamp;
|
||||
texDescr.addressMode[1] = cudaAddressModeClamp;
|
||||
texDescr.readMode = cudaReadModeElementType;
|
||||
|
||||
checkCudaErrors(
|
||||
cudaCreateTextureObject(&tex2Dleft, &texRes, &texDescr, NULL));
|
||||
|
||||
memset(&texRes, 0, sizeof(cudaResourceDesc));
|
||||
|
||||
texRes.resType = cudaResourceTypePitch2D;
|
||||
texRes.res.pitch2D.devPtr = d_img1;
|
||||
texRes.res.pitch2D.desc = ca_desc1;
|
||||
texRes.res.pitch2D.width = w;
|
||||
texRes.res.pitch2D.height = h;
|
||||
texRes.res.pitch2D.pitchInBytes = w * 4;
|
||||
|
||||
memset(&texDescr, 0, sizeof(cudaTextureDesc));
|
||||
|
||||
texDescr.normalizedCoords = false;
|
||||
texDescr.filterMode = cudaFilterModePoint;
|
||||
texDescr.addressMode[0] = cudaAddressModeClamp;
|
||||
texDescr.addressMode[1] = cudaAddressModeClamp;
|
||||
texDescr.readMode = cudaReadModeElementType;
|
||||
|
||||
checkCudaErrors(
|
||||
cudaCreateTextureObject(&tex2Dright, &texRes, &texDescr, NULL));
|
||||
|
||||
// First run the warmup kernel (which we'll use to get the GPU in the correct
|
||||
// max power state
|
||||
stereoDisparityKernel<<<numBlocks, numThreads>>>(
|
||||
d_img0, d_img1, d_odata, w, h, minDisp, maxDisp, tex2Dleft, tex2Dright);
|
||||
cudaDeviceSynchronize();
|
||||
|
||||
// Allocate CUDA events that we'll use for timing
|
||||
cudaEvent_t start, stop;
|
||||
checkCudaErrors(cudaEventCreate(&start));
|
||||
checkCudaErrors(cudaEventCreate(&stop));
|
||||
|
||||
printf("Launching CUDA stereoDisparityKernel()\n");
|
||||
|
||||
// Record the start event
|
||||
checkCudaErrors(cudaEventRecord(start, NULL));
|
||||
|
||||
// launch the stereoDisparity kernel
|
||||
stereoDisparityKernel<<<numBlocks, numThreads>>>(
|
||||
d_img0, d_img1, d_odata, w, h, minDisp, maxDisp, tex2Dleft, tex2Dright);
|
||||
|
||||
// Record the stop event
|
||||
checkCudaErrors(cudaEventRecord(stop, NULL));
|
||||
|
||||
// Wait for the stop event to complete
|
||||
checkCudaErrors(cudaEventSynchronize(stop));
|
||||
|
||||
// Check to make sure the kernel didn't fail
|
||||
getLastCudaError("Kernel execution failed");
|
||||
|
||||
float msecTotal = 0.0f;
|
||||
checkCudaErrors(cudaEventElapsedTime(&msecTotal, start, stop));
|
||||
|
||||
// Copy result from device to host for verification
|
||||
checkCudaErrors(
|
||||
cudaMemcpy(h_odata, d_odata, memSize, cudaMemcpyDeviceToHost));
|
||||
|
||||
printf("Input Size [%dx%d], ", w, h);
|
||||
printf("Kernel size [%dx%d], ", (2 * RAD + 1), (2 * RAD + 1));
|
||||
printf("Disparities [%d:%d]\n", minDisp, maxDisp);
|
||||
|
||||
printf("GPU processing time : %.4f (ms)\n", msecTotal);
|
||||
printf("Pixel throughput : %.3f Mpixels/sec\n",
|
||||
((float)(w * h * 1000.f) / msecTotal) / 1000000);
|
||||
|
||||
// calculate sum of resultant GPU image
|
||||
unsigned int checkSum = 0;
|
||||
|
||||
for (unsigned int i = 0; i < w * h; i++) {
|
||||
checkSum += h_odata[i];
|
||||
}
|
||||
|
||||
printf("GPU Checksum = %u, ", checkSum);
|
||||
|
||||
// write out the resulting disparity image.
|
||||
unsigned char *dispOut = (unsigned char *)malloc(numData);
|
||||
int mult = 20;
|
||||
const char *fnameOut = "output_GPU.pgm";
|
||||
|
||||
for (unsigned int i = 0; i < numData; i++) {
|
||||
dispOut[i] = (int)h_odata[i] * mult;
|
||||
}
|
||||
|
||||
printf("GPU image: <%s>\n", fnameOut);
|
||||
sdkSavePGM(fnameOut, dispOut, w, h);
|
||||
|
||||
// compute reference solution
|
||||
printf("Computing CPU reference...\n");
|
||||
cpu_gold_stereo((unsigned int *)h_img0, (unsigned int *)h_img1,
|
||||
(unsigned int *)h_odata, w, h, minDisp, maxDisp);
|
||||
unsigned int cpuCheckSum = 0;
|
||||
|
||||
for (unsigned int i = 0; i < w * h; i++) {
|
||||
cpuCheckSum += h_odata[i];
|
||||
}
|
||||
|
||||
printf("CPU Checksum = %u, ", cpuCheckSum);
|
||||
const char *cpuFnameOut = "output_CPU.pgm";
|
||||
|
||||
for (unsigned int i = 0; i < numData; i++) {
|
||||
dispOut[i] = (int)h_odata[i] * mult;
|
||||
}
|
||||
|
||||
printf("CPU image: <%s>\n", cpuFnameOut);
|
||||
sdkSavePGM(cpuFnameOut, dispOut, w, h);
|
||||
|
||||
// cleanup memory
|
||||
checkCudaErrors(cudaFree(d_odata));
|
||||
checkCudaErrors(cudaFree(d_img0));
|
||||
checkCudaErrors(cudaFree(d_img1));
|
||||
|
||||
if (h_odata != NULL) free(h_odata);
|
||||
|
||||
if (h_img0 != NULL) free(h_img0);
|
||||
|
||||
if (h_img1 != NULL) free(h_img1);
|
||||
|
||||
if (dispOut != NULL) free(dispOut);
|
||||
|
||||
sdkDeleteTimer(&timer);
|
||||
|
||||
exit((checkSum == cpuCheckSum) ? EXIT_SUCCESS : EXIT_FAILURE);
|
||||
}
|
||||
@@ -0,0 +1,252 @@
|
||||
/* 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.
|
||||
*/
|
||||
|
||||
/* Simple kernel computes a Stereo Disparity using CUDA SIMD SAD intrinsics. */
|
||||
|
||||
#ifndef _STEREODISPARITY_KERNEL_H_
|
||||
#define _STEREODISPARITY_KERNEL_H_
|
||||
|
||||
#define blockSize_x 32
|
||||
#define blockSize_y 8
|
||||
|
||||
// RAD is the radius of the region of support for the search
|
||||
#define RAD 8
|
||||
// STEPS is the number of loads we must perform to initialize the shared memory
|
||||
// area (see convolution CUDA Sample for example)
|
||||
#define STEPS 3
|
||||
|
||||
#include <cooperative_groups.h>
|
||||
|
||||
namespace cg = cooperative_groups;
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// This function applies the video intrinsic operations to compute a
|
||||
// sum of absolute differences. The absolute differences are computed
|
||||
// and the optional .add instruction is used to sum the lanes.
|
||||
//
|
||||
// For more information, see also the documents:
|
||||
// "Using_Inline_PTX_Assembly_In_CUDA.pdf"
|
||||
// and also the PTX ISA documentation for the architecture in question, e.g.:
|
||||
// "ptx_isa_3.0K.pdf"
|
||||
// included in the NVIDIA GPU Computing Toolkit
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
__device__ unsigned int __usad4(unsigned int A, unsigned int B,
|
||||
unsigned int C = 0) {
|
||||
unsigned int result;
|
||||
|
||||
// Kepler (SM 3.x) and higher supports a 4 vector SAD SIMD
|
||||
asm(
|
||||
"vabsdiff4.u32.u32.u32.add"
|
||||
" %0, %1, %2, %3;"
|
||||
: "=r"(result)
|
||||
: "r"(A), "r"(B), "r"(C));
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Simple stereo disparity kernel to test atomic instructions
|
||||
//! Algorithm Explanation:
|
||||
//! For stereo disparity this performs a basic block matching scheme.
|
||||
//! The sum of abs. diffs between and area of the candidate pixel in the left
|
||||
//! images
|
||||
//! is computed against different horizontal shifts of areas from the right.
|
||||
//! The shift at which the difference is minimum is taken as how far that pixel
|
||||
//! moved between left/right image pairs. The recovered motion is the
|
||||
//! disparity map
|
||||
//! More motion indicates more parallax indicates a closer object.
|
||||
//! @param g_img1 image 1 in global memory, RGBA, 4 bytes/pixel
|
||||
//! @param g_img2 image 2 in global memory
|
||||
//! @param g_odata disparity map output in global memory, unsigned int
|
||||
//! output/pixel
|
||||
//! @param w image width in pixels
|
||||
//! @param h image height in pixels
|
||||
//! @param minDisparity leftmost search range
|
||||
//! @param maxDisparity rightmost search range
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
__global__ void stereoDisparityKernel(unsigned int *g_img0,
|
||||
unsigned int *g_img1,
|
||||
unsigned int *g_odata, int w, int h,
|
||||
int minDisparity, int maxDisparity,
|
||||
cudaTextureObject_t tex2Dleft,
|
||||
cudaTextureObject_t tex2Dright) {
|
||||
// Handle to thread block group
|
||||
cg::thread_block cta = cg::this_thread_block();
|
||||
// access thread id
|
||||
const int tidx = blockDim.x * blockIdx.x + threadIdx.x;
|
||||
const int tidy = blockDim.y * blockIdx.y + threadIdx.y;
|
||||
const unsigned int sidx = threadIdx.x + RAD;
|
||||
const unsigned int sidy = threadIdx.y + RAD;
|
||||
|
||||
unsigned int imLeft;
|
||||
unsigned int imRight;
|
||||
unsigned int cost;
|
||||
unsigned int bestCost = 9999999;
|
||||
unsigned int bestDisparity = 0;
|
||||
__shared__ unsigned int diff[blockSize_y + 2 * RAD][blockSize_x + 2 * RAD];
|
||||
|
||||
// store needed values for left image into registers (constant indexed local
|
||||
// vars)
|
||||
unsigned int imLeftA[STEPS];
|
||||
unsigned int imLeftB[STEPS];
|
||||
|
||||
for (int i = 0; i < STEPS; i++) {
|
||||
int offset = -RAD + i * RAD;
|
||||
imLeftA[i] = tex2D<unsigned int>(tex2Dleft, tidx - RAD, tidy + offset);
|
||||
imLeftB[i] =
|
||||
tex2D<unsigned int>(tex2Dleft, tidx - RAD + blockSize_x, tidy + offset);
|
||||
}
|
||||
|
||||
// for a fixed camera system this could be hardcoded and loop unrolled
|
||||
for (int d = minDisparity; d <= maxDisparity; d++) {
|
||||
// LEFT
|
||||
#pragma unroll
|
||||
for (int i = 0; i < STEPS; i++) {
|
||||
int offset = -RAD + i * RAD;
|
||||
// imLeft = tex2D( tex2Dleft, tidx-RAD, tidy+offset );
|
||||
imLeft = imLeftA[i];
|
||||
imRight = tex2D<unsigned int>(tex2Dright, tidx - RAD + d, tidy + offset);
|
||||
cost = __usad4(imLeft, imRight);
|
||||
diff[sidy + offset][sidx - RAD] = cost;
|
||||
}
|
||||
|
||||
// RIGHT
|
||||
#pragma unroll
|
||||
|
||||
for (int i = 0; i < STEPS; i++) {
|
||||
int offset = -RAD + i * RAD;
|
||||
|
||||
if (threadIdx.x < 2 * RAD) {
|
||||
// imLeft = tex2D( tex2Dleft, tidx-RAD+blockSize_x, tidy+offset );
|
||||
imLeft = imLeftB[i];
|
||||
imRight = tex2D<unsigned int>(tex2Dright, tidx - RAD + blockSize_x + d,
|
||||
tidy + offset);
|
||||
cost = __usad4(imLeft, imRight);
|
||||
diff[sidy + offset][sidx - RAD + blockSize_x] = cost;
|
||||
}
|
||||
}
|
||||
|
||||
cg::sync(cta);
|
||||
|
||||
// sum cost horizontally
|
||||
#pragma unroll
|
||||
|
||||
for (int j = 0; j < STEPS; j++) {
|
||||
int offset = -RAD + j * RAD;
|
||||
cost = 0;
|
||||
#pragma unroll
|
||||
|
||||
for (int i = -RAD; i <= RAD; i++) {
|
||||
cost += diff[sidy + offset][sidx + i];
|
||||
}
|
||||
|
||||
cg::sync(cta);
|
||||
diff[sidy + offset][sidx] = cost;
|
||||
cg::sync(cta);
|
||||
}
|
||||
|
||||
// sum cost vertically
|
||||
cost = 0;
|
||||
#pragma unroll
|
||||
|
||||
for (int i = -RAD; i <= RAD; i++) {
|
||||
cost += diff[sidy + i][sidx];
|
||||
}
|
||||
|
||||
// see if it is better or not
|
||||
if (cost < bestCost) {
|
||||
bestCost = cost;
|
||||
bestDisparity = d + 8;
|
||||
}
|
||||
|
||||
cg::sync(cta);
|
||||
}
|
||||
|
||||
if (tidy < h && tidx < w) {
|
||||
g_odata[tidy * w + tidx] = bestDisparity;
|
||||
}
|
||||
}
|
||||
|
||||
void cpu_gold_stereo(unsigned int *img0, unsigned int *img1,
|
||||
unsigned int *odata, int w, int h, int minDisparity,
|
||||
int maxDisparity) {
|
||||
for (int y = 0; y < h; y++) {
|
||||
for (int x = 0; x < w; x++) {
|
||||
unsigned int bestCost = 9999999;
|
||||
unsigned int bestDisparity = 0;
|
||||
|
||||
for (int d = minDisparity; d <= maxDisparity; d++) {
|
||||
unsigned int cost = 0;
|
||||
|
||||
for (int i = -RAD; i <= RAD; i++) {
|
||||
for (int j = -RAD; j <= RAD; j++) {
|
||||
// border clamping
|
||||
int yy, xx, xxd;
|
||||
yy = y + i;
|
||||
|
||||
if (yy < 0) yy = 0;
|
||||
|
||||
if (yy >= h) yy = h - 1;
|
||||
|
||||
xx = x + j;
|
||||
|
||||
if (xx < 0) xx = 0;
|
||||
|
||||
if (xx >= w) xx = w - 1;
|
||||
|
||||
xxd = x + j + d;
|
||||
|
||||
if (xxd < 0) xxd = 0;
|
||||
|
||||
if (xxd >= w) xxd = w - 1;
|
||||
|
||||
// sum abs diff across components
|
||||
unsigned char *A = (unsigned char *)&img0[yy * w + xx];
|
||||
unsigned char *B = (unsigned char *)&img1[yy * w + xxd];
|
||||
unsigned int absdiff = 0;
|
||||
|
||||
for (int k = 0; k < 4; k++) {
|
||||
absdiff += abs((int)(A[k] - B[k]));
|
||||
}
|
||||
|
||||
cost += absdiff;
|
||||
}
|
||||
}
|
||||
|
||||
if (cost < bestCost) {
|
||||
bestCost = cost;
|
||||
bestDisparity = d + 8;
|
||||
}
|
||||
|
||||
} // end for disparities
|
||||
|
||||
// store to best disparity
|
||||
odata[y * w + x] = bestDisparity;
|
||||
}
|
||||
}
|
||||
}
|
||||
#endif // #ifndef _STEREODISPARITY_KERNEL_H_
|
||||
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2017
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "stereoDisparity", "stereoDisparity_vs2017.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
|
||||
EndProject
|
||||
Global
|
||||
GlobalSection(SolutionConfigurationPlatforms) = preSolution
|
||||
Debug|x64 = Debug|x64
|
||||
Release|x64 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(ProjectConfigurationPlatforms) = postSolution
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(SolutionProperties) = preSolution
|
||||
HideSolutionNode = FALSE
|
||||
EndGlobalSection
|
||||
EndGlobal
|
||||
@@ -0,0 +1,112 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
|
||||
<PropertyGroup>
|
||||
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||
</PropertyGroup>
|
||||
<ItemGroup Label="ProjectConfigurations">
|
||||
<ProjectConfiguration Include="Debug|x64">
|
||||
<Configuration>Debug</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
<ProjectConfiguration Include="Release|x64">
|
||||
<Configuration>Release</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
</ItemGroup>
|
||||
<PropertyGroup Label="Globals">
|
||||
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||
<RootNamespace>stereoDisparity_vs2017</RootNamespace>
|
||||
<ProjectName>stereoDisparity</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)/stereoDisparity.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>
|
||||
<CudaCompile Include="stereoDisparity.cu" />
|
||||
<None Include="stereoDisparity_kernel.cuh" />
|
||||
</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}") = "stereoDisparity", "stereoDisparity_vs2019.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
|
||||
EndProject
|
||||
Global
|
||||
GlobalSection(SolutionConfigurationPlatforms) = preSolution
|
||||
Debug|x64 = Debug|x64
|
||||
Release|x64 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(ProjectConfigurationPlatforms) = postSolution
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(SolutionProperties) = preSolution
|
||||
HideSolutionNode = FALSE
|
||||
EndGlobalSection
|
||||
EndGlobal
|
||||
@@ -0,0 +1,108 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
|
||||
<PropertyGroup>
|
||||
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||
</PropertyGroup>
|
||||
<ItemGroup Label="ProjectConfigurations">
|
||||
<ProjectConfiguration Include="Debug|x64">
|
||||
<Configuration>Debug</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
<ProjectConfiguration Include="Release|x64">
|
||||
<Configuration>Release</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
</ItemGroup>
|
||||
<PropertyGroup Label="Globals">
|
||||
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||
<RootNamespace>stereoDisparity_vs2019</RootNamespace>
|
||||
<ProjectName>stereoDisparity</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>$(OutDir)/stereoDisparity.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" --threads 0 </AdditionalOptions>
|
||||
<Include>./;../../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(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="'$(Configuration)'=='Release'">
|
||||
<ClCompile>
|
||||
<Optimization>MaxSpeed</Optimization>
|
||||
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>false</GenerateDebugInformation>
|
||||
<LinkTimeCodeGeneration>UseLinkTimeCodeGeneration</LinkTimeCodeGeneration>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<Runtime>MT</Runtime>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<CudaCompile Include="stereoDisparity.cu" />
|
||||
<None Include="stereoDisparity_kernel.cuh" />
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.6.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2022
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "stereoDisparity", "stereoDisparity_vs2022.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
|
||||
EndProject
|
||||
Global
|
||||
GlobalSection(SolutionConfigurationPlatforms) = preSolution
|
||||
Debug|x64 = Debug|x64
|
||||
Release|x64 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(ProjectConfigurationPlatforms) = postSolution
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(SolutionProperties) = preSolution
|
||||
HideSolutionNode = FALSE
|
||||
EndGlobalSection
|
||||
EndGlobal
|
||||
@@ -0,0 +1,108 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
|
||||
<PropertyGroup>
|
||||
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||
</PropertyGroup>
|
||||
<ItemGroup Label="ProjectConfigurations">
|
||||
<ProjectConfiguration Include="Debug|x64">
|
||||
<Configuration>Debug</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
<ProjectConfiguration Include="Release|x64">
|
||||
<Configuration>Release</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
</ItemGroup>
|
||||
<PropertyGroup Label="Globals">
|
||||
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||
<RootNamespace>stereoDisparity_vs2022</RootNamespace>
|
||||
<ProjectName>stereoDisparity</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<Import Project="$(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)/stereoDisparity.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>
|
||||
<CudaCompile Include="stereoDisparity.cu" />
|
||||
<None Include="stereoDisparity_kernel.cuh" />
|
||||
</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