mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2026-10-23 13:18:16 +08:00
add and update samples for CUDA 11.5
This commit is contained in:
Rutwik Choughule
18
Samples/volumeFiltering/.vscode/c_cpp_properties.json
vendored
Normal file
18
Samples/volumeFiltering/.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/volumeFiltering/.vscode/extensions.json
vendored
Normal file
7
Samples/volumeFiltering/.vscode/extensions.json
vendored
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"recommendations": [
|
||||
"nvidia.nsight-vscode-edition",
|
||||
"ms-vscode.cpptools",
|
||||
"ms-vscode.makefile-tools"
|
||||
]
|
||||
}
|
||||
10
Samples/volumeFiltering/.vscode/launch.json
vendored
Normal file
10
Samples/volumeFiltering/.vscode/launch.json
vendored
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"configurations": [
|
||||
{
|
||||
"name": "CUDA C++: Launch",
|
||||
"type": "cuda-gdb",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/volumeFiltering"
|
||||
}
|
||||
]
|
||||
}
|
||||
15
Samples/volumeFiltering/.vscode/tasks.json
vendored
Normal file
15
Samples/volumeFiltering/.vscode/tasks.json
vendored
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"version": "2.0.0",
|
||||
"tasks": [
|
||||
{
|
||||
"label": "sample",
|
||||
"type": "shell",
|
||||
"command": "make dbg=1",
|
||||
"problemMatcher": ["$nvcc"],
|
||||
"group": {
|
||||
"kind": "build",
|
||||
"isDefault": true
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
391
Samples/volumeFiltering/Makefile
Normal file
391
Samples/volumeFiltering/Makefile
Normal file
@@ -0,0 +1,391 @@
|
||||
################################################################################
|
||||
# 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)
|
||||
NVCCFLAGS += -g -G
|
||||
BUILD_TYPE := debug
|
||||
else
|
||||
BUILD_TYPE := release
|
||||
endif
|
||||
|
||||
ALL_CCFLAGS :=
|
||||
ALL_CCFLAGS += $(NVCCFLAGS)
|
||||
ALL_CCFLAGS += $(EXTRA_NVCCFLAGS)
|
||||
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS))
|
||||
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS))
|
||||
|
||||
SAMPLE_ENABLED := 1
|
||||
|
||||
# This sample is not supported on QNX
|
||||
ifeq ($(TARGET_OS),qnx)
|
||||
$(info >>> WARNING - volumeFiltering 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 :=
|
||||
|
||||
################################################################################
|
||||
|
||||
# Makefile include to help find GL Libraries
|
||||
include ./findgllib.mk
|
||||
|
||||
# OpenGL specific libraries
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
# Mac OSX specific libraries and paths to include
|
||||
LIBRARIES += -L/System/Library/Frameworks/OpenGL.framework/Libraries
|
||||
LIBRARIES += -lGL -lGLU
|
||||
ALL_LDFLAGS += -Xlinker -framework -Xlinker GLUT
|
||||
else
|
||||
LIBRARIES += $(GLLINK)
|
||||
LIBRARIES += -lGL -lGLU -lglut
|
||||
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
|
||||
|
||||
# Gencode arguments
|
||||
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64))
|
||||
SMS ?= 35 37 50 52 60 61 70 72 75 80 86
|
||||
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: volumeFiltering
|
||||
|
||||
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
|
||||
|
||||
volume.o:volume.cpp
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
volumeFilter_kernel.o:volumeFilter_kernel.cu
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
volumeFiltering.o:volumeFiltering.cpp
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
volumeRender_kernel.o:volumeRender_kernel.cu
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
volumeFiltering: volume.o volumeFilter_kernel.o volumeFiltering.o volumeRender_kernel.o
|
||||
$(EXEC) $(NVCC) $(ALL_LDFLAGS) $(GENCODE_FLAGS) -o $@ $+ $(LIBRARIES)
|
||||
$(EXEC) mkdir -p ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
|
||||
$(EXEC) cp $@ ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)
|
||||
|
||||
run: build
|
||||
$(EXEC) ./volumeFiltering
|
||||
|
||||
clean:
|
||||
rm -f volumeFiltering volume.o volumeFilter_kernel.o volumeFiltering.o volumeRender_kernel.o
|
||||
rm -rf ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/volumeFiltering
|
||||
|
||||
clobber: clean
|
||||
95
Samples/volumeFiltering/NsightEclipse.xml
Normal file
95
Samples/volumeFiltering/NsightEclipse.xml
Normal file
@@ -0,0 +1,95 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
||||
<entry>
|
||||
<name>volumeFiltering</name>
|
||||
<cuda_api_list>
|
||||
<toolkit>cudaGraphicsMapResources</toolkit>
|
||||
<toolkit>cudaGraphicsUnmapResources</toolkit>
|
||||
<toolkit>cudaGraphicsResourceGetMappedPointer</toolkit>
|
||||
<toolkit>cudaGraphicsRegisterResource</toolkit>
|
||||
<toolkit>cudaGraphicsGLRegisterBuffer</toolkit>
|
||||
<toolkit>cudaGraphicsUnregisterResource</toolkit>
|
||||
</cuda_api_list>
|
||||
<description><![CDATA[This sample demonstrates 3D Volumetric Filtering using 3D Textures and 3D Surface Writes.]]></description>
|
||||
<devicecompilation>whole</devicecompilation>
|
||||
<files>
|
||||
<file>data\Bucky.raw</file>
|
||||
<file>data\ref_volumefilter.ppm</file>
|
||||
</files>
|
||||
<includepaths>
|
||||
<path>./</path>
|
||||
<path>../</path>
|
||||
<path>../../Common</path>
|
||||
</includepaths>
|
||||
<keyconcepts>
|
||||
<concept level="advanced">Graphics Interop</concept>
|
||||
<concept level="advanced">Image Processing</concept>
|
||||
<concept level="advanced">3D Textures</concept>
|
||||
<concept level="advanced">Surface Writes</concept>
|
||||
</keyconcepts>
|
||||
<keywords>
|
||||
<keyword>CUDA 3D Volume Filtering</keyword>
|
||||
<keyword>openGL</keyword>
|
||||
</keywords>
|
||||
<libraries>
|
||||
<library>GLU</library>
|
||||
<library>GL</library>
|
||||
<library framework="true" os="macosx">GLUT</library>
|
||||
<library os="linux">GLEW</library>
|
||||
<library os="linux">glut</library>
|
||||
<library os="linux">X11</library>
|
||||
</libraries>
|
||||
<librarypaths>
|
||||
<path arch="x86_64" os="linux">../../common/lib/linux/x86_64</path>
|
||||
<path arch="armv7l" os="linux">../../common/lib/linux/armv7l</path>
|
||||
<path os="macosx">../../common/lib/darwin</path>
|
||||
</librarypaths>
|
||||
<nsight_eclipse>true</nsight_eclipse>
|
||||
<primary_file>volumeFiltering.cpp</primary_file>
|
||||
<qatests>
|
||||
<qatest>-file=ref_volumefilter.ppm</qatest>
|
||||
</qatests>
|
||||
<required_dependencies>
|
||||
<dependency>X11</dependency>
|
||||
<dependency>GL</dependency>
|
||||
</required_dependencies>
|
||||
<scopes>
|
||||
<scope>1:CUDA Basic Topics</scope>
|
||||
<scope>2:Texture</scope>
|
||||
<scope>2:Graphics Interop</scope>
|
||||
<scope>2:Image Processing</scope>
|
||||
<scope>3:Volume 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>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>
|
||||
<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>
|
||||
</supported_envs>
|
||||
<supported_sm_architectures>
|
||||
<include>all</include>
|
||||
</supported_sm_architectures>
|
||||
<title>Volumetric Filtering with 3D Textures and Surface Writes</title>
|
||||
<type>exe</type>
|
||||
</entry>
|
||||
74
Samples/volumeFiltering/README.md
Normal file
74
Samples/volumeFiltering/README.md
Normal file
@@ -0,0 +1,74 @@
|
||||
# volumeFiltering - Volumetric Filtering with 3D Textures and Surface Writes
|
||||
|
||||
## Description
|
||||
|
||||
This sample demonstrates 3D Volumetric Filtering using 3D Textures and 3D Surface Writes.
|
||||
|
||||
## Key Concepts
|
||||
|
||||
Graphics Interop, Image Processing, 3D Textures, Surface Writes
|
||||
|
||||
## 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, armv7l
|
||||
|
||||
## CUDA APIs involved
|
||||
|
||||
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
|
||||
cudaGraphicsMapResources, cudaGraphicsUnmapResources, cudaGraphicsResourceGetMappedPointer, cudaGraphicsRegisterResource, cudaGraphicsGLRegisterBuffer, cudaGraphicsUnregisterResource
|
||||
|
||||
## Dependencies needed to build/run
|
||||
[X11](../../README.md#x11), [GL](../../README.md#gl)
|
||||
|
||||
## 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, 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=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)
|
||||
|
||||
BIN
Samples/volumeFiltering/data/Bucky.raw
Normal file
BIN
Samples/volumeFiltering/data/Bucky.raw
Normal file
Binary file not shown.
BIN
Samples/volumeFiltering/data/ref_volumefilter.ppm
Normal file
BIN
Samples/volumeFiltering/data/ref_volumefilter.ppm
Normal file
Binary file not shown.
BIN
Samples/volumeFiltering/doc/sshot_lg.JPG
Normal file
BIN
Samples/volumeFiltering/doc/sshot_lg.JPG
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 24 KiB |
BIN
Samples/volumeFiltering/doc/sshot_md.JPG
Normal file
BIN
Samples/volumeFiltering/doc/sshot_md.JPG
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 9.3 KiB |
BIN
Samples/volumeFiltering/doc/sshot_sm.JPG
Normal file
BIN
Samples/volumeFiltering/doc/sshot_sm.JPG
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 3.8 KiB |
145
Samples/volumeFiltering/findgllib.mk
Normal file
145
Samples/volumeFiltering/findgllib.mk
Normal file
@@ -0,0 +1,145 @@
|
||||
################################################################################
|
||||
# Copyright (c) 2020, 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.
|
||||
#
|
||||
################################################################################
|
||||
#
|
||||
# findgllib.mk is used to find the necessary GL Libraries for specific distributions
|
||||
# this is supported on Mac OSX and Linux Platforms
|
||||
#
|
||||
################################################################################
|
||||
|
||||
# Determine OS platform and unix distribution
|
||||
ifeq ("$(TARGET_OS)","linux")
|
||||
# first search lsb_release
|
||||
DISTRO := $(shell lsb_release -i -s 2>/dev/null | tr "[:upper:]" "[:lower:]")
|
||||
ifeq ("$(DISTRO)","")
|
||||
# second search and parse /etc/issue
|
||||
DISTRO := $(shell awk '{print $$1}' /etc/issue | tr -d "[:space:]" | sed -e "/^$$/d" | tr "[:upper:]" "[:lower:]")
|
||||
# ensure data from /etc/issue is valid
|
||||
ifeq (,$(filter $(DISTRO),ubuntu fedora red rhel centos suse))
|
||||
DISTRO :=
|
||||
endif
|
||||
ifeq ("$(DISTRO)","")
|
||||
# third, we can search in /etc/os-release or /etc/{distro}-release
|
||||
DISTRO := $(shell awk '/ID/' /etc/*-release | sed 's/ID=//' | grep -v "VERSION" | grep -v "ID" | grep -v "DISTRIB")
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
ifeq ("$(TARGET_OS)","linux")
|
||||
# $(info) >> findgllib.mk -> LINUX path <<<)
|
||||
# Each set of Linux Distros have different paths for where to find their OpenGL libraries reside
|
||||
UBUNTU = $(shell echo $(DISTRO) | grep -i ubuntu >/dev/null 2>&1; echo $$?)
|
||||
FEDORA = $(shell echo $(DISTRO) | grep -i fedora >/dev/null 2>&1; echo $$?)
|
||||
RHEL = $(shell echo $(DISTRO) | grep -i 'red\|rhel' >/dev/null 2>&1; echo $$?)
|
||||
CENTOS = $(shell echo $(DISTRO) | grep -i centos >/dev/null 2>&1; echo $$?)
|
||||
SUSE = $(shell echo $(DISTRO) | grep -i 'suse\|sles' >/dev/null 2>&1; echo $$?)
|
||||
ifeq ("$(UBUNTU)","0")
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-armv7l)
|
||||
GLPATH := /usr/arm-linux-gnueabihf/lib
|
||||
GLLINK := -L/usr/arm-linux-gnueabihf/lib
|
||||
ifneq ($(TARGET_FS),)
|
||||
GLPATH += $(TARGET_FS)/usr/lib/arm-linux-gnueabihf
|
||||
GLLINK += -L$(TARGET_FS)/usr/lib/arm-linux-gnueabihf
|
||||
endif
|
||||
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-aarch64)
|
||||
GLPATH := /usr/aarch64-linux-gnu/lib
|
||||
GLLINK := -L/usr/aarch64-linux-gnu/lib
|
||||
ifneq ($(TARGET_FS),)
|
||||
GLPATH += $(TARGET_FS)/usr/lib
|
||||
GLPATH += $(TARGET_FS)/usr/lib/aarch64-linux-gnu
|
||||
GLLINK += -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
|
||||
endif
|
||||
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH),x86_64-ppc64le)
|
||||
GLPATH := /usr/powerpc64le-linux-gnu/lib
|
||||
GLLINK := -L/usr/powerpc64le-linux-gnu/lib
|
||||
else
|
||||
UBUNTU_PKG_NAME = $(shell which dpkg >/dev/null 2>&1 && dpkg -l 'nvidia-*' | grep '^ii' | awk '{print $$2}' | head -1)
|
||||
ifneq ("$(UBUNTU_PKG_NAME)","")
|
||||
GLPATH ?= /usr/lib/$(UBUNTU_PKG_NAME)
|
||||
GLLINK ?= -L/usr/lib/$(UBUNTU_PKG_NAME)
|
||||
endif
|
||||
|
||||
DFLT_PATH ?= /usr/lib
|
||||
endif
|
||||
endif
|
||||
ifeq ("$(SUSE)","0")
|
||||
GLPATH ?= /usr/X11R6/lib64
|
||||
GLLINK ?= -L/usr/X11R6/lib64
|
||||
DFLT_PATH ?= /usr/lib64
|
||||
endif
|
||||
ifeq ("$(FEDORA)","0")
|
||||
GLPATH ?= /usr/lib64/nvidia
|
||||
GLLINK ?= -L/usr/lib64/nvidia
|
||||
DFLT_PATH ?= /usr/lib64
|
||||
endif
|
||||
ifeq ("$(RHEL)","0")
|
||||
GLPATH ?= /usr/lib64/nvidia
|
||||
GLLINK ?= -L/usr/lib64/nvidia
|
||||
DFLT_PATH ?= /usr/lib64
|
||||
endif
|
||||
ifeq ("$(CENTOS)","0")
|
||||
GLPATH ?= /usr/lib64/nvidia
|
||||
GLLINK ?= -L/usr/lib64/nvidia
|
||||
DFLT_PATH ?= /usr/lib64
|
||||
endif
|
||||
|
||||
# find libGL, libGLU
|
||||
GLLIB := $(shell find -L $(GLPATH) $(DFLT_PATH) -name libGL.so -print 2>/dev/null)
|
||||
GLULIB := $(shell find -L $(GLPATH) $(DFLT_PATH) -name libGLU.so -print 2>/dev/null)
|
||||
|
||||
ifeq ("$(GLLIB)","")
|
||||
$(info >>> WARNING - libGL.so not found, refer to CUDA Getting Started Guide for how to find and install them. <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
ifeq ("$(GLULIB)","")
|
||||
$(info >>> WARNING - libGLU.so not found, refer to CUDA Getting Started Guide for how to find and install them. <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
|
||||
HEADER_SEARCH_PATH ?= $(TARGET_FS)/usr/include
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-armv7l-linux)
|
||||
HEADER_SEARCH_PATH += /usr/arm-linux-gnueabihf/include
|
||||
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-aarch64-linux)
|
||||
HEADER_SEARCH_PATH += /usr/aarch64-linux-gnu/include
|
||||
endif
|
||||
|
||||
GLHEADER := $(shell find -L $(HEADER_SEARCH_PATH) -name gl.h -print 2>/dev/null)
|
||||
GLUHEADER := $(shell find -L $(HEADER_SEARCH_PATH) -name glu.h -print 2>/dev/null)
|
||||
|
||||
ifeq ("$(GLHEADER)","")
|
||||
$(info >>> WARNING - gl.h not found, refer to CUDA Getting Started Guide for how to find and install them. <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
ifeq ("$(GLUHEADER)","")
|
||||
$(info >>> WARNING - glu.h not found, refer to CUDA Getting Started Guide for how to find and install them. <<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
else
|
||||
# This would be the Mac OS X path if we had to do anything special
|
||||
endif
|
||||
|
||||
92
Samples/volumeFiltering/volume.cpp
Normal file
92
Samples/volumeFiltering/volume.cpp
Normal file
@@ -0,0 +1,92 @@
|
||||
/* 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.
|
||||
*/
|
||||
|
||||
// CUDA Runtime
|
||||
#include <cuda_runtime.h>
|
||||
|
||||
// Helper functions
|
||||
#include <helper_cuda.h>
|
||||
#include <helper_math.h>
|
||||
#include "volume.h"
|
||||
|
||||
void Volume_init(Volume *vol, cudaExtent dataSize, void *h_data,
|
||||
int allowStore) {
|
||||
// create 3D array
|
||||
vol->channelDesc = cudaCreateChannelDesc<VolumeType>();
|
||||
checkCudaErrors(
|
||||
cudaMalloc3DArray(&vol->content, &vol->channelDesc, dataSize,
|
||||
allowStore ? cudaArraySurfaceLoadStore : 0));
|
||||
vol->size = dataSize;
|
||||
|
||||
if (h_data) {
|
||||
// copy data to 3D array
|
||||
cudaMemcpy3DParms copyParams = {0};
|
||||
copyParams.srcPtr =
|
||||
make_cudaPitchedPtr(h_data, dataSize.width * sizeof(VolumeType),
|
||||
dataSize.width, dataSize.height);
|
||||
copyParams.dstArray = vol->content;
|
||||
copyParams.extent = dataSize;
|
||||
copyParams.kind = cudaMemcpyHostToDevice;
|
||||
checkCudaErrors(cudaMemcpy3D(©Params));
|
||||
}
|
||||
|
||||
if (allowStore) {
|
||||
cudaResourceDesc surfRes;
|
||||
memset(&surfRes, 0, sizeof(cudaResourceDesc));
|
||||
surfRes.resType = cudaResourceTypeArray;
|
||||
surfRes.res.array.array = vol->content;
|
||||
|
||||
checkCudaErrors(cudaCreateSurfaceObject(&vol->volumeSurf, &surfRes));
|
||||
}
|
||||
|
||||
cudaResourceDesc texRes;
|
||||
memset(&texRes, 0, sizeof(cudaResourceDesc));
|
||||
|
||||
texRes.resType = cudaResourceTypeArray;
|
||||
texRes.res.array.array = vol->content;
|
||||
|
||||
cudaTextureDesc texDescr;
|
||||
memset(&texDescr, 0, sizeof(cudaTextureDesc));
|
||||
|
||||
texDescr.normalizedCoords = true;
|
||||
texDescr.filterMode = cudaFilterModeLinear;
|
||||
texDescr.addressMode[0] = cudaAddressModeWrap;
|
||||
texDescr.addressMode[1] = cudaAddressModeWrap;
|
||||
texDescr.addressMode[2] = cudaAddressModeWrap;
|
||||
texDescr.readMode =
|
||||
cudaReadModeNormalizedFloat; // VolumeTypeInfo<VolumeType>::readMode;
|
||||
|
||||
checkCudaErrors(
|
||||
cudaCreateTextureObject(&vol->volumeTex, &texRes, &texDescr, NULL));
|
||||
}
|
||||
|
||||
void Volume_deinit(Volume *vol) {
|
||||
checkCudaErrors(cudaDestroyTextureObject(vol->volumeTex));
|
||||
checkCudaErrors(cudaDestroySurfaceObject(vol->volumeSurf));
|
||||
checkCudaErrors(cudaFreeArray(vol->content));
|
||||
vol->content = 0;
|
||||
}
|
||||
83
Samples/volumeFiltering/volume.h
Normal file
83
Samples/volumeFiltering/volume.h
Normal file
@@ -0,0 +1,83 @@
|
||||
/* 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 _VOLUME_H_
|
||||
#define _VOLUME_H_
|
||||
|
||||
#include <cuda_runtime.h>
|
||||
|
||||
typedef unsigned char VolumeType;
|
||||
|
||||
extern "C" {
|
||||
|
||||
struct Volume {
|
||||
cudaArray *content;
|
||||
cudaExtent size;
|
||||
cudaChannelFormatDesc channelDesc;
|
||||
cudaTextureObject_t volumeTex;
|
||||
cudaSurfaceObject_t volumeSurf;
|
||||
};
|
||||
|
||||
void Volume_init(Volume *vol, cudaExtent size, void *data, int allowStore);
|
||||
void Volume_deinit(Volume *vol);
|
||||
};
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
|
||||
#ifdef __CUDACC__
|
||||
|
||||
/* Helper class to do popular integer storage to float conversions if required
|
||||
*/
|
||||
|
||||
template <typename T>
|
||||
struct VolumeTypeInfo {};
|
||||
|
||||
template <>
|
||||
struct VolumeTypeInfo<unsigned char> {
|
||||
static const cudaTextureReadMode readMode = cudaReadModeNormalizedFloat;
|
||||
static __inline__ __device__ unsigned char convert(float sampled) {
|
||||
return (unsigned char)(saturate(sampled) * 255.0);
|
||||
}
|
||||
};
|
||||
|
||||
template <>
|
||||
struct VolumeTypeInfo<unsigned short> {
|
||||
static const cudaTextureReadMode readMode = cudaReadModeNormalizedFloat;
|
||||
static __inline__ __device__ unsigned short convert(float sampled) {
|
||||
return (unsigned short)(saturate(sampled) * 65535.0);
|
||||
}
|
||||
};
|
||||
|
||||
template <>
|
||||
struct VolumeTypeInfo<float> {
|
||||
static const cudaTextureReadMode readMode = cudaReadModeElementType;
|
||||
static __inline__ __device__ float convert(float sampled) { return sampled; }
|
||||
};
|
||||
|
||||
#endif
|
||||
|
||||
#endif
|
||||
42
Samples/volumeFiltering/volumeFilter.h
Normal file
42
Samples/volumeFiltering/volumeFilter.h
Normal file
@@ -0,0 +1,42 @@
|
||||
/* 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 _VOLUMEFILTER_KERNEL_H_
|
||||
#define _VOLUMEFILTER_KERNEL_H_
|
||||
|
||||
#define VOLUMEFILTER_MAXWEIGHTS 125
|
||||
|
||||
#include <cuda_runtime.h>
|
||||
#include "volume.h"
|
||||
|
||||
extern "C" {
|
||||
Volume *VolumeFilter_runFilter(Volume *input, Volume *output0, Volume *output1,
|
||||
int iterations, int numWeights, float4 *weights,
|
||||
float postWeightOffset);
|
||||
};
|
||||
|
||||
#endif
|
||||
115
Samples/volumeFiltering/volumeFilter_kernel.cu
Normal file
115
Samples/volumeFiltering/volumeFilter_kernel.cu
Normal file
@@ -0,0 +1,115 @@
|
||||
/* 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 _VOLUMEFILTER_KERNEL_CU_
|
||||
#define _VOLUMEFILTER_KERNEL_CU_
|
||||
|
||||
#include <helper_cuda.h>
|
||||
#include <helper_math.h>
|
||||
#include "volumeFilter.h"
|
||||
|
||||
typedef unsigned int uint;
|
||||
typedef unsigned char uchar;
|
||||
typedef unsigned short ushort;
|
||||
|
||||
__constant__ float4 c_filterData[VOLUMEFILTER_MAXWEIGHTS];
|
||||
|
||||
__global__ void d_filter_surface3d(int filterSize, float filter_offset,
|
||||
cudaExtent volumeSize,
|
||||
cudaTextureObject_t volumeTexIn,
|
||||
cudaSurfaceObject_t volumeTexOut) {
|
||||
int x = blockIdx.x * blockDim.x + threadIdx.x;
|
||||
int y = blockIdx.y * blockDim.y + threadIdx.y;
|
||||
int z = blockIdx.z * blockDim.z + threadIdx.z;
|
||||
|
||||
if (x >= volumeSize.width || y >= volumeSize.height ||
|
||||
z >= volumeSize.depth) {
|
||||
return;
|
||||
}
|
||||
|
||||
float filtered = 0;
|
||||
float4 basecoord = make_float4(x, y, z, 0);
|
||||
|
||||
for (int i = 0; i < filterSize; i++) {
|
||||
float4 coord = basecoord + c_filterData[i];
|
||||
filtered += tex3D<float>(volumeTexIn, coord.x, coord.y, coord.z) *
|
||||
c_filterData[i].w;
|
||||
}
|
||||
|
||||
filtered += filter_offset;
|
||||
|
||||
VolumeType output = VolumeTypeInfo<VolumeType>::convert(filtered);
|
||||
|
||||
// surface writes need byte offsets for x!
|
||||
surf3Dwrite(output, volumeTexOut, x * sizeof(VolumeType), y, z);
|
||||
}
|
||||
|
||||
static unsigned int iDivUp(size_t a, size_t b) {
|
||||
size_t val = (a % b != 0) ? (a / b + 1) : (a / b);
|
||||
if (val > UINT_MAX) {
|
||||
fprintf(stderr, "\nUINT_MAX limit exceeded in iDivUp() exiting.....\n");
|
||||
exit(EXIT_FAILURE); // val exceeds limit
|
||||
}
|
||||
|
||||
return static_cast<unsigned int>(val);
|
||||
}
|
||||
|
||||
extern "C" Volume *VolumeFilter_runFilter(Volume *input, Volume *output0,
|
||||
Volume *output1, int iterations,
|
||||
int numWeights, float4 *weights,
|
||||
float postWeightOffset) {
|
||||
Volume *swap = 0;
|
||||
cudaExtent size = input->size;
|
||||
unsigned int dim = 32 / sizeof(VolumeType);
|
||||
dim3 blockSize(dim, dim, 1);
|
||||
dim3 gridSize(iDivUp(size.width, blockSize.x),
|
||||
iDivUp(size.height, blockSize.y),
|
||||
iDivUp(size.depth, blockSize.z));
|
||||
|
||||
// set weights
|
||||
checkCudaErrors(
|
||||
cudaMemcpyToSymbol(c_filterData, weights, sizeof(float4) * numWeights));
|
||||
|
||||
for (int i = 0; i < iterations; i++) {
|
||||
d_filter_surface3d<<<gridSize, blockSize>>>(numWeights, postWeightOffset,
|
||||
size, input->volumeTex,
|
||||
output0->volumeSurf);
|
||||
|
||||
getLastCudaError("filter kernel failed");
|
||||
|
||||
swap = input;
|
||||
input = output0;
|
||||
output0 = swap;
|
||||
|
||||
if (i == 0) {
|
||||
output0 = output1;
|
||||
}
|
||||
}
|
||||
|
||||
return input;
|
||||
}
|
||||
#endif
|
||||
823
Samples/volumeFiltering/volumeFiltering.cpp
Normal file
823
Samples/volumeFiltering/volumeFiltering.cpp
Normal file
@@ -0,0 +1,823 @@
|
||||
/**
|
||||
* 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.
|
||||
*
|
||||
*/
|
||||
|
||||
/**
|
||||
* CUDA 3D Volume Filtering sample
|
||||
*
|
||||
* This sample loads a 3D volume from disk and displays it using
|
||||
* ray marching and 3D textures.
|
||||
*
|
||||
* Note - this is intended to be an example of using 3D textures
|
||||
* in CUDA, not an optimized volume renderer.
|
||||
*
|
||||
* Changes
|
||||
* sgg 22/3/2010
|
||||
* - updated to use texture for display instead of glDrawPixels.
|
||||
* - changed to render from front-to-back rather than back-to-front.
|
||||
*/
|
||||
|
||||
// OpenGL Graphics includes
|
||||
#include <helper_gl.h>
|
||||
#if defined (__APPLE__) || defined(MACOSX)
|
||||
#pragma clang diagnostic ignored "-Wdeprecated-declarations"
|
||||
#include <GLUT/glut.h>
|
||||
#ifndef glutCloseFunc
|
||||
#define glutCloseFunc glutWMCloseFunc
|
||||
#endif
|
||||
#else
|
||||
#include <GL/freeglut.h>
|
||||
#endif
|
||||
|
||||
// CUDA Runtime and Interop
|
||||
#include <cuda_runtime.h>
|
||||
#include <cuda_gl_interop.h>
|
||||
|
||||
// Helper functions
|
||||
#include <helper_functions.h>
|
||||
#include <helper_timer.h>
|
||||
|
||||
// CUDA utilities and system includes
|
||||
#include <helper_cuda.h>
|
||||
|
||||
typedef unsigned int uint;
|
||||
typedef unsigned char uchar;
|
||||
|
||||
#define MAX_EPSILON_ERROR 5.00f
|
||||
#define THRESHOLD 0.30f
|
||||
|
||||
const char *sSDKsample = "CUDA 3D Volume Filtering";
|
||||
|
||||
|
||||
#include "volume.h"
|
||||
#include "volumeFilter.h"
|
||||
#include "volumeRender.h"
|
||||
|
||||
const char *volumeFilename = "Bucky.raw";
|
||||
cudaExtent volumeSize = make_cudaExtent(32, 32, 32);
|
||||
|
||||
uint width = 512, height = 512;
|
||||
dim3 blockSize(16, 16);
|
||||
dim3 gridSize;
|
||||
|
||||
float3 viewRotation;
|
||||
float3 viewTranslation = make_float3(0.0, 0.0, -4.0f);
|
||||
float invViewMatrix[12];
|
||||
|
||||
float density = 0.05f;
|
||||
float brightness = 1.0f;
|
||||
float transferOffset = 0.0f;
|
||||
float transferScale = 1.0f;
|
||||
bool linearFiltering = true;
|
||||
bool preIntegrated = true;
|
||||
StopWatchInterface *animationTimer = NULL;
|
||||
|
||||
float filterFactor = 0.0f;
|
||||
bool filterAnimation = true;
|
||||
int filterIterations = 2;
|
||||
float filterTimeScale = 0.001f;
|
||||
float filterBias = 0.0f;
|
||||
float4 filterWeights[3*3*3];
|
||||
|
||||
Volume volumeOriginal;
|
||||
Volume volumeFilter0;
|
||||
Volume volumeFilter1;
|
||||
|
||||
GLuint pbo = 0; // OpenGL pixel buffer object
|
||||
GLuint volumeTex = 0; // OpenGL texture object
|
||||
struct cudaGraphicsResource *cuda_pbo_resource; // CUDA Graphics Resource (to transfer PBO)
|
||||
|
||||
StopWatchInterface *timer = 0;
|
||||
|
||||
// Auto-Verification Code
|
||||
const int frameCheckNumber = 2;
|
||||
int fpsCount = 0; // FPS count for averaging
|
||||
int fpsLimit = 1; // FPS limit for sampling
|
||||
int g_Index = 0;
|
||||
unsigned int frameCount = 0;
|
||||
unsigned int g_TotalErrors = 0;
|
||||
|
||||
int *pArgc;
|
||||
char **pArgv;
|
||||
|
||||
#define MAX(a,b) ((a > b) ? a : b)
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
// QA RELATED
|
||||
|
||||
void computeFPS()
|
||||
{
|
||||
frameCount++;
|
||||
fpsCount++;
|
||||
|
||||
if (fpsCount == fpsLimit)
|
||||
{
|
||||
char fps[256];
|
||||
float ifps = 1.f / (sdkGetAverageTimerValue(&timer) / 1000.f);
|
||||
sprintf(fps, "CUDA 3D Volume Filtering: %3.1f fps", ifps);
|
||||
|
||||
glutSetWindowTitle(fps);
|
||||
fpsCount = 0;
|
||||
|
||||
fpsLimit = ftoi(MAX(1.f, ifps));
|
||||
sdkResetTimer(&timer);
|
||||
}
|
||||
}
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
// 3D FILTER
|
||||
|
||||
static float filteroffsets[3*3*3][3] =
|
||||
{
|
||||
{-1,-1,-1},{ 0,-1,-1},{ 1,-1,-1},
|
||||
{-1, 0,-1},{ 0, 0,-1},{ 1, 0,-1},
|
||||
{-1, 1,-1},{ 0, 1,-1},{ 1, 1,-1},
|
||||
|
||||
{-1,-1, 0},{ 0,-1, 0},{ 1,-1, 0},
|
||||
{-1, 0, 0},{ 0, 0, 0},{ 1, 0, 0},
|
||||
{-1, 1, 0},{ 0, 1, 0},{ 1, 1, 0},
|
||||
|
||||
{-1,-1, 1},{ 0,-1, 1},{ 1,-1, 1},
|
||||
{-1, 0, 1},{ 0, 0, 1},{ 1, 0, 1},
|
||||
{-1, 1, 1},{ 0, 1, 1},{ 1, 1, 1},
|
||||
};
|
||||
|
||||
static float filterblur[3*3*3] =
|
||||
{
|
||||
0,1,0,
|
||||
1,2,1,
|
||||
0,1,0,
|
||||
|
||||
1,2,1,
|
||||
2,4,2,
|
||||
1,2,1,
|
||||
|
||||
0,1,0,
|
||||
1,2,1,
|
||||
0,1,0,
|
||||
};
|
||||
static float filtersharpen[3*3*3] =
|
||||
{
|
||||
0,0,0,
|
||||
0,-2,0,
|
||||
0,0,0,
|
||||
|
||||
0,-2,0,
|
||||
-2,15,-2,
|
||||
0,-2,0,
|
||||
|
||||
0,0,0,
|
||||
0,-2,0,
|
||||
0,0,0,
|
||||
};
|
||||
|
||||
static float filterpassthru[3*3*3] =
|
||||
{
|
||||
0,0,0,
|
||||
0,0,0,
|
||||
0,0,0,
|
||||
|
||||
0,0,0,
|
||||
0,1,0,
|
||||
0,0,0,
|
||||
|
||||
0,0,0,
|
||||
0,0,0,
|
||||
0,0,0,
|
||||
};
|
||||
|
||||
void FilterKernel_init()
|
||||
{
|
||||
float sumblur = 0.0f;
|
||||
float sumsharpen = 0.0f;
|
||||
|
||||
for (int i = 0; i < 3*3*3; i++)
|
||||
{
|
||||
sumblur += filterblur[i];
|
||||
sumsharpen += filtersharpen[i];
|
||||
}
|
||||
|
||||
for (int i = 0; i < 3*3*3; i++)
|
||||
{
|
||||
filterblur[i] /= sumblur;
|
||||
filtersharpen[i] /= sumsharpen;
|
||||
|
||||
filterWeights[i].x = filteroffsets[i][0];
|
||||
filterWeights[i].y = filteroffsets[i][1];
|
||||
filterWeights[i].z = filteroffsets[i][2];
|
||||
}
|
||||
}
|
||||
|
||||
void FilterKernel_update(float blurfactor)
|
||||
{
|
||||
if (blurfactor > 0.0f)
|
||||
{
|
||||
for (int i = 0; i < 3*3*3; i++)
|
||||
{
|
||||
filterWeights[i].w = filterblur[i] * blurfactor + filterpassthru[i] * (1.0f - blurfactor);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
blurfactor = -blurfactor;
|
||||
|
||||
for (int i = 0; i < 3*3*3; i++)
|
||||
{
|
||||
filterWeights[i].w = filtersharpen[i] * blurfactor + filterpassthru[i] * (1.0f - blurfactor);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
void filter()
|
||||
{
|
||||
if (filterAnimation)
|
||||
{
|
||||
filterFactor = cosf(sdkGetTimerValue(&animationTimer) * filterTimeScale);
|
||||
}
|
||||
|
||||
FilterKernel_update(filterFactor);
|
||||
|
||||
Volume *volumeRender = VolumeFilter_runFilter(&volumeOriginal,&volumeFilter0,&volumeFilter1,
|
||||
filterIterations, 3*3*3,filterWeights,filterBias);
|
||||
|
||||
}
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
// RENDERING
|
||||
|
||||
// render image using CUDA
|
||||
void render()
|
||||
{
|
||||
|
||||
VolumeRender_copyInvViewMatrix(invViewMatrix, sizeof(float4)*3);
|
||||
|
||||
// map PBO to get CUDA device pointer
|
||||
uint *d_output;
|
||||
// map PBO to get CUDA device pointer
|
||||
checkCudaErrors(cudaGraphicsMapResources(1, &cuda_pbo_resource, 0));
|
||||
size_t num_bytes;
|
||||
checkCudaErrors(cudaGraphicsResourceGetMappedPointer((void **)&d_output, &num_bytes,
|
||||
cuda_pbo_resource));
|
||||
//printf("CUDA mapped PBO: May access %ld bytes\n", num_bytes);
|
||||
|
||||
// clear image
|
||||
checkCudaErrors(cudaMemset(d_output, 0, width*height*4));
|
||||
|
||||
// call CUDA kernel, writing results to PBO
|
||||
VolumeRender_render(gridSize, blockSize, d_output, width, height, density, brightness, transferOffset, transferScale, volumeOriginal.volumeTex);
|
||||
|
||||
getLastCudaError("render kernel failed");
|
||||
|
||||
checkCudaErrors(cudaGraphicsUnmapResources(1, &cuda_pbo_resource, 0));
|
||||
}
|
||||
|
||||
// display results using OpenGL (called by GLUT)
|
||||
void display()
|
||||
{
|
||||
sdkStartTimer(&timer);
|
||||
|
||||
// use OpenGL to build view matrix
|
||||
GLfloat modelView[16];
|
||||
glMatrixMode(GL_MODELVIEW);
|
||||
glPushMatrix();
|
||||
glLoadIdentity();
|
||||
glRotatef(-viewRotation.x, 1.0, 0.0, 0.0);
|
||||
glRotatef(-viewRotation.y, 0.0, 1.0, 0.0);
|
||||
glTranslatef(-viewTranslation.x, -viewTranslation.y, -viewTranslation.z);
|
||||
glGetFloatv(GL_MODELVIEW_MATRIX, modelView);
|
||||
glPopMatrix();
|
||||
|
||||
invViewMatrix[0] = modelView[0];
|
||||
invViewMatrix[1] = modelView[4];
|
||||
invViewMatrix[2] = modelView[8];
|
||||
invViewMatrix[3] = modelView[12];
|
||||
invViewMatrix[4] = modelView[1];
|
||||
invViewMatrix[5] = modelView[5];
|
||||
invViewMatrix[6] = modelView[9];
|
||||
invViewMatrix[7] = modelView[13];
|
||||
invViewMatrix[8] = modelView[2];
|
||||
invViewMatrix[9] = modelView[6];
|
||||
invViewMatrix[10] = modelView[10];
|
||||
invViewMatrix[11] = modelView[14];
|
||||
|
||||
filter();
|
||||
render();
|
||||
|
||||
// display results
|
||||
glClear(GL_COLOR_BUFFER_BIT);
|
||||
|
||||
// draw image from PBO
|
||||
glDisable(GL_DEPTH_TEST);
|
||||
|
||||
glPixelStorei(GL_UNPACK_ALIGNMENT, 1);
|
||||
// draw using texture
|
||||
// copy from pbo to texture
|
||||
glBindBuffer(GL_PIXEL_UNPACK_BUFFER_ARB, pbo);
|
||||
glBindTexture(GL_TEXTURE_2D, volumeTex);
|
||||
glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, width, height, GL_RGBA, GL_UNSIGNED_BYTE, 0);
|
||||
glBindBuffer(GL_PIXEL_UNPACK_BUFFER_ARB, 0);
|
||||
|
||||
// draw textured quad
|
||||
glEnable(GL_TEXTURE_2D);
|
||||
glBegin(GL_QUADS);
|
||||
glTexCoord2f(0, 0);
|
||||
glVertex2f(0, 0);
|
||||
glTexCoord2f(1, 0);
|
||||
glVertex2f(1, 0);
|
||||
glTexCoord2f(1, 1);
|
||||
glVertex2f(1, 1);
|
||||
glTexCoord2f(0, 1);
|
||||
glVertex2f(0, 1);
|
||||
glEnd();
|
||||
|
||||
glDisable(GL_TEXTURE_2D);
|
||||
glBindTexture(GL_TEXTURE_2D, 0);
|
||||
|
||||
glutSwapBuffers();
|
||||
glutReportErrors();
|
||||
|
||||
sdkStopTimer(&timer);
|
||||
|
||||
computeFPS();
|
||||
}
|
||||
|
||||
void idle()
|
||||
{
|
||||
glutPostRedisplay();
|
||||
}
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
// LOGIC
|
||||
|
||||
void keyboard(unsigned char key, int x, int y)
|
||||
{
|
||||
switch (key)
|
||||
{
|
||||
case 27:
|
||||
#if defined (__APPLE__) || defined(MACOSX)
|
||||
exit(EXIT_SUCCESS);
|
||||
#else
|
||||
glutDestroyWindow(glutGetWindow());
|
||||
return;
|
||||
#endif
|
||||
break;
|
||||
|
||||
case ' ':
|
||||
filterAnimation = !filterAnimation;
|
||||
|
||||
if (!filterAnimation)
|
||||
{
|
||||
sdkStopTimer(&animationTimer);
|
||||
}
|
||||
else
|
||||
{
|
||||
sdkStartTimer(&animationTimer);
|
||||
}
|
||||
|
||||
break;
|
||||
|
||||
case 'f':
|
||||
linearFiltering = !linearFiltering;
|
||||
VolumeRender_setTextureFilterMode(linearFiltering, &volumeOriginal);
|
||||
break;
|
||||
|
||||
case 'p':
|
||||
preIntegrated = !preIntegrated;
|
||||
VolumeRender_setPreIntegrated(preIntegrated);
|
||||
break;
|
||||
|
||||
case '+':
|
||||
density += 0.01f;
|
||||
break;
|
||||
|
||||
case '-':
|
||||
density -= 0.01f;
|
||||
break;
|
||||
|
||||
case ']':
|
||||
brightness += 0.1f;
|
||||
break;
|
||||
|
||||
case '[':
|
||||
brightness -= 0.1f;
|
||||
break;
|
||||
|
||||
case ';':
|
||||
transferOffset += 0.01f;
|
||||
break;
|
||||
|
||||
case '\'':
|
||||
transferOffset -= 0.01f;
|
||||
break;
|
||||
|
||||
case '.':
|
||||
transferScale += 0.01f;
|
||||
break;
|
||||
|
||||
case ',':
|
||||
transferScale -= 0.01f;
|
||||
break;
|
||||
|
||||
default:
|
||||
break;
|
||||
}
|
||||
|
||||
printf("density = %.2f, brightness = %.2f, transferOffset = %.2f, transferScale = %.2f\n", density, brightness, transferOffset, transferScale);
|
||||
glutPostRedisplay();
|
||||
}
|
||||
|
||||
int ox, oy;
|
||||
int buttonState = 0;
|
||||
|
||||
void mouse(int button, int state, int x, int y)
|
||||
{
|
||||
if (state == GLUT_DOWN)
|
||||
{
|
||||
buttonState |= 1<<button;
|
||||
}
|
||||
else if (state == GLUT_UP)
|
||||
{
|
||||
buttonState = 0;
|
||||
}
|
||||
|
||||
ox = x;
|
||||
oy = y;
|
||||
glutPostRedisplay();
|
||||
}
|
||||
|
||||
void motion(int x, int y)
|
||||
{
|
||||
float dx, dy;
|
||||
dx = (float)(x - ox);
|
||||
dy = (float)(y - oy);
|
||||
|
||||
if (buttonState == 4)
|
||||
{
|
||||
// right = zoom
|
||||
viewTranslation.z += dy / 100.0f;
|
||||
}
|
||||
else if (buttonState == 2)
|
||||
{
|
||||
// middle = translate
|
||||
viewTranslation.x += dx / 100.0f;
|
||||
viewTranslation.y -= dy / 100.0f;
|
||||
}
|
||||
else if (buttonState == 1)
|
||||
{
|
||||
// left = rotate
|
||||
viewRotation.x += dy / 5.0f;
|
||||
viewRotation.y += dx / 5.0f;
|
||||
}
|
||||
|
||||
ox = x;
|
||||
oy = y;
|
||||
glutPostRedisplay();
|
||||
}
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
// SAMPLE INIT/DEINIT
|
||||
|
||||
static int iDivUp(int a, int b)
|
||||
{
|
||||
return (a % b != 0) ? (a / b + 1) : (a / b);
|
||||
}
|
||||
void initPixelBuffer();
|
||||
void reshape(int w, int h)
|
||||
{
|
||||
width = w;
|
||||
height = h;
|
||||
initPixelBuffer();
|
||||
|
||||
// calculate new grid size
|
||||
gridSize = dim3(iDivUp(width, blockSize.x), iDivUp(height, blockSize.y));
|
||||
|
||||
glViewport(0, 0, w, h);
|
||||
|
||||
glMatrixMode(GL_MODELVIEW);
|
||||
glLoadIdentity();
|
||||
|
||||
glMatrixMode(GL_PROJECTION);
|
||||
glLoadIdentity();
|
||||
glOrtho(0.0, 1.0, 0.0, 1.0, 0.0, 1.0);
|
||||
}
|
||||
|
||||
|
||||
void initGL(int *argc, char **argv)
|
||||
{
|
||||
// initialize GLUT callback functions
|
||||
glutInit(argc, argv);
|
||||
glutInitDisplayMode(GLUT_RGB | GLUT_DOUBLE);
|
||||
glutInitWindowSize(width, height);
|
||||
glutCreateWindow("CUDA 3D Volume Filtering");
|
||||
|
||||
if (!isGLVersionSupported(2,0) ||
|
||||
!areGLExtensionsSupported("GL_ARB_pixel_buffer_object"))
|
||||
{
|
||||
printf("Required OpenGL extensions are missing.");
|
||||
exit(EXIT_SUCCESS);
|
||||
}
|
||||
}
|
||||
|
||||
void initPixelBuffer()
|
||||
{
|
||||
if (pbo)
|
||||
{
|
||||
// unregister this buffer object from CUDA C
|
||||
checkCudaErrors(cudaGraphicsUnregisterResource(cuda_pbo_resource));
|
||||
|
||||
// delete old buffer
|
||||
glDeleteBuffers(1, &pbo);
|
||||
glDeleteTextures(1, &volumeTex);
|
||||
}
|
||||
|
||||
// create pixel buffer object for display
|
||||
glGenBuffers(1, &pbo);
|
||||
glBindBuffer(GL_PIXEL_UNPACK_BUFFER_ARB, pbo);
|
||||
glBufferData(GL_PIXEL_UNPACK_BUFFER_ARB, width*height*sizeof(GLubyte)*4, 0, GL_STREAM_DRAW_ARB);
|
||||
glBindBuffer(GL_PIXEL_UNPACK_BUFFER_ARB, 0);
|
||||
|
||||
// register this buffer object with CUDA
|
||||
checkCudaErrors(cudaGraphicsGLRegisterBuffer(&cuda_pbo_resource, pbo, cudaGraphicsMapFlagsWriteDiscard));
|
||||
|
||||
// create texture for display
|
||||
glGenTextures(1, &volumeTex);
|
||||
glBindTexture(GL_TEXTURE_2D, volumeTex);
|
||||
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA8, width, height, 0, GL_RGBA, GL_UNSIGNED_BYTE, NULL);
|
||||
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
|
||||
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
|
||||
glBindTexture(GL_TEXTURE_2D, 0);
|
||||
}
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
|
||||
void cleanup()
|
||||
{
|
||||
sdkDeleteTimer(&timer);
|
||||
sdkDeleteTimer(&animationTimer);
|
||||
|
||||
Volume_deinit(&volumeOriginal);
|
||||
Volume_deinit(&volumeFilter0);
|
||||
Volume_deinit(&volumeFilter1);
|
||||
VolumeRender_deinit();
|
||||
|
||||
if (pbo)
|
||||
{
|
||||
cudaGraphicsUnregisterResource(cuda_pbo_resource);
|
||||
glDeleteBuffers(1, &pbo);
|
||||
glDeleteTextures(1, &volumeTex);
|
||||
}
|
||||
}
|
||||
|
||||
// Load raw data from disk
|
||||
void *loadRawFile(char *filename, size_t size)
|
||||
{
|
||||
FILE *fp = fopen(filename, "rb");
|
||||
|
||||
if (!fp)
|
||||
{
|
||||
fprintf(stderr, "Error opening file '%s'\n", filename);
|
||||
return 0;
|
||||
}
|
||||
|
||||
void *data = malloc(size);
|
||||
size_t read = fread(data, 1, size, fp);
|
||||
fclose(fp);
|
||||
|
||||
printf("Read '%s', %d bytes\n", filename, (int)read);
|
||||
|
||||
return data;
|
||||
}
|
||||
|
||||
void initData(int argc, char **argv)
|
||||
{
|
||||
// parse arguments
|
||||
char *filename;
|
||||
|
||||
if (getCmdLineArgumentString(argc, (const char **) argv, "file", &filename))
|
||||
{
|
||||
volumeFilename = filename;
|
||||
}
|
||||
|
||||
int n;
|
||||
|
||||
if (checkCmdLineFlag(argc, (const char **) argv, "size"))
|
||||
{
|
||||
n = getCmdLineArgumentInt(argc, (const char **) argv, "size");
|
||||
volumeSize.width = volumeSize.height = volumeSize.depth = n;
|
||||
}
|
||||
|
||||
if (checkCmdLineFlag(argc, (const char **) argv, "xsize"))
|
||||
{
|
||||
n = getCmdLineArgumentInt(argc, (const char **) argv, "xsize");
|
||||
volumeSize.width = n;
|
||||
}
|
||||
|
||||
if (checkCmdLineFlag(argc, (const char **) argv, "ysize"))
|
||||
{
|
||||
n = getCmdLineArgumentInt(argc, (const char **) argv, "ysize");
|
||||
volumeSize.height = n;
|
||||
}
|
||||
|
||||
if (checkCmdLineFlag(argc, (const char **) argv, "zsize"))
|
||||
{
|
||||
n = getCmdLineArgumentInt(argc, (const char **) argv, "zsize");
|
||||
volumeSize.depth = n;
|
||||
}
|
||||
|
||||
char *path = sdkFindFilePath(volumeFilename, argv[0]);
|
||||
|
||||
if (path == 0)
|
||||
{
|
||||
printf("Error finding file '%s'\n", volumeFilename);
|
||||
exit(EXIT_FAILURE);
|
||||
}
|
||||
|
||||
size_t size = volumeSize.width*volumeSize.height*volumeSize.depth*sizeof(VolumeType);
|
||||
void *h_volume = loadRawFile(path, size);
|
||||
|
||||
FilterKernel_init();
|
||||
Volume_init(&volumeOriginal,volumeSize, h_volume, 0);
|
||||
free(h_volume);
|
||||
Volume_init(&volumeFilter0, volumeSize, NULL, 1);
|
||||
Volume_init(&volumeFilter1, volumeSize, NULL, 1);
|
||||
VolumeRender_init();
|
||||
VolumeRender_setPreIntegrated(preIntegrated);
|
||||
|
||||
sdkCreateTimer(&timer);
|
||||
sdkCreateTimer(&animationTimer);
|
||||
sdkStartTimer(&animationTimer);
|
||||
|
||||
// calculate new grid size
|
||||
gridSize = dim3(iDivUp(width, blockSize.x), iDivUp(height, blockSize.y));
|
||||
}
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
// AUTOMATIC TESTING
|
||||
void runSingleTest(const char *ref_file, const char *exec_path)
|
||||
{
|
||||
uint *d_output;
|
||||
checkCudaErrors(cudaMalloc((void **)&d_output, width*height*sizeof(uint)));
|
||||
checkCudaErrors(cudaMemset(d_output, 0, width*height*sizeof(uint)));
|
||||
|
||||
float modelView[16] =
|
||||
{
|
||||
1.0f, 0.0f, 0.0f, 0.0f,
|
||||
0.0f, 1.0f, 0.0f, 0.0f,
|
||||
0.0f, 0.0f, 1.0f, 0.0f,
|
||||
0.0f, 0.0f, 4.0f, 1.0f
|
||||
};
|
||||
|
||||
invViewMatrix[0] = modelView[0];
|
||||
invViewMatrix[1] = modelView[4];
|
||||
invViewMatrix[2] = modelView[8];
|
||||
invViewMatrix[3] = modelView[12];
|
||||
invViewMatrix[4] = modelView[1];
|
||||
invViewMatrix[5] = modelView[5];
|
||||
invViewMatrix[6] = modelView[9];
|
||||
invViewMatrix[7] = modelView[13];
|
||||
invViewMatrix[8] = modelView[2];
|
||||
invViewMatrix[9] = modelView[6];
|
||||
invViewMatrix[10] = modelView[10];
|
||||
invViewMatrix[11] = modelView[14];
|
||||
|
||||
// call CUDA kernel, writing results to PBO
|
||||
VolumeRender_copyInvViewMatrix(invViewMatrix, sizeof(float4)*3);
|
||||
filterAnimation = false;
|
||||
|
||||
// Start timer 0 and process n loops on the GPU
|
||||
int nIter = 10;
|
||||
float scale = 2.0f/float(nIter-1);
|
||||
|
||||
for (int i = -1; i < nIter; i++)
|
||||
{
|
||||
if (i == 0)
|
||||
{
|
||||
cudaDeviceSynchronize();
|
||||
sdkStartTimer(&timer);
|
||||
}
|
||||
|
||||
filterFactor = (float(i) * scale) - 1.0f;
|
||||
filterFactor = -filterFactor;
|
||||
filter();
|
||||
VolumeRender_render(gridSize, blockSize, d_output, width, height, density, brightness, transferOffset, transferScale, volumeOriginal.volumeTex);
|
||||
}
|
||||
|
||||
cudaDeviceSynchronize();
|
||||
sdkStopTimer(&timer);
|
||||
// Get elapsed time and throughput, then log to sample and master logs
|
||||
double dAvgTime = sdkGetTimerValue(&timer)/(nIter * 1000.0);
|
||||
printf("volumeFiltering, Throughput = %.4f MTexels/s, Time = %.5f s, Size = %u Texels, NumDevsUsed = %u, Workgroup = %u\n",
|
||||
(1.0e-6 * width * height)/dAvgTime, dAvgTime, (width * height), 1, blockSize.x * blockSize.y);
|
||||
|
||||
|
||||
getLastCudaError("Error: kernel execution FAILED");
|
||||
checkCudaErrors(cudaDeviceSynchronize());
|
||||
|
||||
unsigned char *h_output = (unsigned char *)malloc(width*height*4);
|
||||
checkCudaErrors(cudaMemcpy(h_output, d_output, width*height*4, cudaMemcpyDeviceToHost));
|
||||
|
||||
sdkSavePPM4ub("volumefilter.ppm", h_output, width, height);
|
||||
bool bTestResult = sdkComparePPM("volumefilter.ppm", sdkFindFilePath(ref_file, exec_path),
|
||||
MAX_EPSILON_ERROR, THRESHOLD, true);
|
||||
|
||||
checkCudaErrors(cudaFree(d_output));
|
||||
free(h_output);
|
||||
cleanup();
|
||||
|
||||
exit(bTestResult ? EXIT_SUCCESS : EXIT_FAILURE);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Program main
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
void printHelp()
|
||||
{
|
||||
printf("\nUsage: volumeFiltering <options>\n");
|
||||
printf("\t\t-file = filename.raw (volume file for input)\n\n");
|
||||
printf("\t\t-size = 64 (volume size, isotropic)\n\n");
|
||||
printf("\t\t-xsize = 128 (volume size, anisotropic)\n\n");
|
||||
printf("\t\t-ysize = 128 (volume size, anisotropic)\n\n");
|
||||
printf("\t\t-zsize = 32 (volume size, anisotropic)\n\n");
|
||||
}
|
||||
|
||||
int
|
||||
main(int argc, char **argv)
|
||||
{
|
||||
pArgc = &argc;
|
||||
pArgv = argv;
|
||||
|
||||
char *ref_file = NULL;
|
||||
|
||||
#if defined(__linux__)
|
||||
setenv ("DISPLAY", ":0", 0);
|
||||
#endif
|
||||
|
||||
printf("%s Starting...\n\n", sSDKsample);
|
||||
|
||||
//start logs
|
||||
|
||||
if (checkCmdLineFlag(argc, (const char **)argv, "help"))
|
||||
{
|
||||
printHelp();
|
||||
exit(EXIT_SUCCESS);
|
||||
}
|
||||
|
||||
if (checkCmdLineFlag(argc, (const char **)argv, "file"))
|
||||
{
|
||||
fpsLimit = frameCheckNumber;
|
||||
getCmdLineArgumentString(argc, (const char **)argv, "file", &ref_file);
|
||||
}
|
||||
|
||||
int device = findCudaDevice(argc, (const char **)argv);
|
||||
|
||||
if (!ref_file)
|
||||
{
|
||||
initGL(&argc, argv);
|
||||
}
|
||||
|
||||
// load volume data
|
||||
initData(argc, argv);
|
||||
|
||||
printf(
|
||||
"Press \n"
|
||||
" 'SPACE' to toggle animation\n"
|
||||
" 'p' to toggle pre-integrated transfer function\n"
|
||||
" '+' and '-' to change density (0.01 increments)\n"
|
||||
" ']' and '[' to change brightness\n"
|
||||
" ';' and ''' to modify transfer function offset\n"
|
||||
" '.' and ',' to modify transfer function scale\n\n");
|
||||
|
||||
if (ref_file)
|
||||
{
|
||||
runSingleTest(ref_file, argv[0]);
|
||||
}
|
||||
else
|
||||
{
|
||||
// This is the normal rendering path for VolumeRender
|
||||
glutDisplayFunc(display);
|
||||
glutKeyboardFunc(keyboard);
|
||||
glutMouseFunc(mouse);
|
||||
glutMotionFunc(motion);
|
||||
glutReshapeFunc(reshape);
|
||||
glutIdleFunc(idle);
|
||||
|
||||
initPixelBuffer();
|
||||
|
||||
#if defined (__APPLE__) || defined(MACOSX)
|
||||
atexit(cleanup);
|
||||
#else
|
||||
glutCloseFunc(cleanup);
|
||||
#endif
|
||||
|
||||
glutMainLoop();
|
||||
}
|
||||
}
|
||||
20
Samples/volumeFiltering/volumeFiltering_vs2017.sln
Normal file
20
Samples/volumeFiltering/volumeFiltering_vs2017.sln
Normal file
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2017
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "volumeFiltering", "volumeFiltering_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
|
||||
128
Samples/volumeFiltering/volumeFiltering_vs2017.vcxproj
Normal file
128
Samples/volumeFiltering/volumeFiltering_vs2017.vcxproj
Normal file
@@ -0,0 +1,128 @@
|
||||
<?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)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||
</PropertyGroup>
|
||||
<ItemGroup Label="ProjectConfigurations">
|
||||
<ProjectConfiguration Include="Debug|x64">
|
||||
<Configuration>Debug</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
<ProjectConfiguration Include="Release|x64">
|
||||
<Configuration>Release</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
</ItemGroup>
|
||||
<PropertyGroup Label="Globals">
|
||||
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||
<RootNamespace>volumeFiltering_vs2017</RootNamespace>
|
||||
<ProjectName>volumeFiltering</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(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>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cudart_static.lib;freeglut.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/lib/$(PlatformName);</AdditionalLibraryDirectories>
|
||||
<OutputFile>$(OutDir)/volumeFiltering.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" %(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>
|
||||
<ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
|
||||
<Link>
|
||||
|
||||
</Link>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
|
||||
<Link>
|
||||
<AdditionalDependencies>glew64.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
</Link>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="volume.cpp" />
|
||||
<CudaCompile Include="volumeFilter_kernel.cu" />
|
||||
<ClCompile Include="volumeFiltering.cpp" />
|
||||
<CudaCompile Include="volumeRender_kernel.cu" />
|
||||
<ClInclude Include="volume.h" />
|
||||
<ClInclude Include="volumeFilter.h" />
|
||||
<ClInclude Include="volumeRender.h" />
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
20
Samples/volumeFiltering/volumeFiltering_vs2019.sln
Normal file
20
Samples/volumeFiltering/volumeFiltering_vs2019.sln
Normal file
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2019
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "volumeFiltering", "volumeFiltering_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
|
||||
124
Samples/volumeFiltering/volumeFiltering_vs2019.vcxproj
Normal file
124
Samples/volumeFiltering/volumeFiltering_vs2019.vcxproj
Normal file
@@ -0,0 +1,124 @@
|
||||
<?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>volumeFiltering_vs2019</RootNamespace>
|
||||
<ProjectName>volumeFiltering</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>./;$(CudaToolkitDir)/include;../../Common;</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cudart_static.lib;freeglut.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/lib/$(PlatformName);</AdditionalLibraryDirectories>
|
||||
<OutputFile>$(OutDir)/volumeFiltering.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" %(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>
|
||||
<ItemDefinitionGroup Condition="'$(Platform)'=='Win32'">
|
||||
<Link>
|
||||
|
||||
</Link>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Platform)'=='x64'">
|
||||
<Link>
|
||||
<AdditionalDependencies>glew64.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
</Link>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="volume.cpp" />
|
||||
<CudaCompile Include="volumeFilter_kernel.cu" />
|
||||
<ClCompile Include="volumeFiltering.cpp" />
|
||||
<CudaCompile Include="volumeRender_kernel.cu" />
|
||||
<ClInclude Include="volume.h" />
|
||||
<ClInclude Include="volumeFilter.h" />
|
||||
<ClInclude Include="volumeRender.h" />
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
47
Samples/volumeFiltering/volumeRender.h
Normal file
47
Samples/volumeFiltering/volumeRender.h
Normal file
@@ -0,0 +1,47 @@
|
||||
/* 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 _VOLUMERENDER__H_
|
||||
#define _VOLUMERENDER__H_
|
||||
|
||||
#include <cuda_runtime.h>
|
||||
#include "volume.h"
|
||||
|
||||
extern "C" {
|
||||
void VolumeRender_init();
|
||||
void VolumeRender_deinit();
|
||||
|
||||
void VolumeRender_setPreIntegrated(int state);
|
||||
void VolumeRender_setTextureFilterMode(bool bLinearFilter, Volume *volume);
|
||||
void VolumeRender_render(dim3 gridSize, dim3 blockSize, uint *d_output,
|
||||
uint imageW, uint imageH, float density,
|
||||
float brightness, float transferOffset,
|
||||
float transferScale, cudaTextureObject_t tex);
|
||||
void VolumeRender_copyInvViewMatrix(float *invViewMatrix, size_t sizeofMatrix);
|
||||
};
|
||||
|
||||
#endif
|
||||
569
Samples/volumeFiltering/volumeRender_kernel.cu
Normal file
569
Samples/volumeFiltering/volumeRender_kernel.cu
Normal file
@@ -0,0 +1,569 @@
|
||||
/* 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.
|
||||
*/
|
||||
|
||||
// Simple 3D volume renderer
|
||||
|
||||
#ifndef _VOLUMERENDER_KERNEL_CU_
|
||||
#define _VOLUMERENDER_KERNEL_CU_
|
||||
|
||||
#include <helper_cuda.h>
|
||||
#include <helper_math.h>
|
||||
#include "volumeRender.h"
|
||||
|
||||
#define VOLUMERENDER_TFS 2
|
||||
#define VOLUMERENDER_TF_PREINTSIZE 1024
|
||||
#define VOLUMERENDER_TF_PREINTSTEPS 1024
|
||||
#define VOLUMERENDER_TF_PREINTRAY 4
|
||||
|
||||
enum TFMode {
|
||||
TF_SINGLE_1D = 0, // single 1D TF for everything
|
||||
TF_LAYERED_2D_PREINT = 1, // layered 2D TF uses pre-integration
|
||||
TF_LAYERED_2D = 2, // layered 2D TF without pre-integration behavior
|
||||
};
|
||||
|
||||
typedef unsigned int uint;
|
||||
typedef unsigned char uchar;
|
||||
|
||||
static bool usePreInt = true;
|
||||
static cudaArray *d_transferIntegrate = 0;
|
||||
static cudaArray *d_transferFunc = 0;
|
||||
static cudaArray *d_transferArray = 0;
|
||||
|
||||
// 1D transfer function texture
|
||||
cudaTextureObject_t transferTex;
|
||||
// 1D transfer integration texture
|
||||
cudaTextureObject_t transferIntegrateTex;
|
||||
cudaSurfaceObject_t transferIntegrateSurf;
|
||||
// 2D layered preintegrated transfer function texture
|
||||
cudaTextureObject_t transferLayerPreintTex;
|
||||
cudaSurfaceObject_t transferLayerPreintSurf;
|
||||
|
||||
typedef struct { float4 m[3]; } float3x4;
|
||||
|
||||
__constant__ float3x4 c_invViewMatrix; // inverse view matrix
|
||||
|
||||
struct Ray {
|
||||
float3 o; // origin
|
||||
float3 d; // direction
|
||||
};
|
||||
|
||||
// intersect ray with a box
|
||||
// http://www.siggraph.org/education/materials/HyperGraph/raytrace/rtinter3.htm
|
||||
|
||||
__device__ int intersectBox(Ray r, float3 boxmin, float3 boxmax, float *tnear,
|
||||
float *tfar) {
|
||||
// compute intersection of ray with all six bbox planes
|
||||
float3 invR = make_float3(1.0f) / r.d;
|
||||
float3 tbot = invR * (boxmin - r.o);
|
||||
float3 ttop = invR * (boxmax - r.o);
|
||||
|
||||
// re-order intersections to find smallest and largest on each axis
|
||||
float3 tmin = fminf(ttop, tbot);
|
||||
float3 tmax = fmaxf(ttop, tbot);
|
||||
|
||||
// find the largest tmin and the smallest tmax
|
||||
float largest_tmin = fmaxf(fmaxf(tmin.x, tmin.y), fmaxf(tmin.x, tmin.z));
|
||||
float smallest_tmax = fminf(fminf(tmax.x, tmax.y), fminf(tmax.x, tmax.z));
|
||||
|
||||
*tnear = largest_tmin;
|
||||
*tfar = smallest_tmax;
|
||||
|
||||
return smallest_tmax > largest_tmin;
|
||||
}
|
||||
|
||||
// transform vector by matrix (no translation)
|
||||
__device__ float3 mul(const float3x4 &M, const float3 &v) {
|
||||
float3 r;
|
||||
r.x = dot(v, make_float3(M.m[0]));
|
||||
r.y = dot(v, make_float3(M.m[1]));
|
||||
r.z = dot(v, make_float3(M.m[2]));
|
||||
return r;
|
||||
}
|
||||
|
||||
// transform vector by matrix with translation
|
||||
__device__ float4 mul(const float3x4 &M, const float4 &v) {
|
||||
float4 r;
|
||||
r.x = dot(v, M.m[0]);
|
||||
r.y = dot(v, M.m[1]);
|
||||
r.z = dot(v, M.m[2]);
|
||||
r.w = 1.0f;
|
||||
return r;
|
||||
}
|
||||
|
||||
__device__ uint rgbaFloatToInt(float4 rgba) {
|
||||
rgba.x = __saturatef(rgba.x); // clamp to [0.0, 1.0]
|
||||
rgba.y = __saturatef(rgba.y);
|
||||
rgba.z = __saturatef(rgba.z);
|
||||
rgba.w = __saturatef(rgba.w);
|
||||
return (uint(rgba.w * 255) << 24) | (uint(rgba.z * 255) << 16) |
|
||||
(uint(rgba.y * 255) << 8) | uint(rgba.x * 255);
|
||||
}
|
||||
|
||||
template <int TFMODE>
|
||||
__device__ void d_render(uint *d_output, uint imageW, uint imageH,
|
||||
float density, float brightness, float transferOffset,
|
||||
float transferScale, cudaTextureObject_t volumeTex,
|
||||
cudaTextureObject_t transferTex,
|
||||
cudaTextureObject_t transferLayerPreintTex,
|
||||
float transferWeight = 0.0f) {
|
||||
const float rayscale =
|
||||
float(TFMODE != TF_SINGLE_1D ? VOLUMERENDER_TF_PREINTRAY : 1);
|
||||
const int maxSteps = 512;
|
||||
const float tstep = 0.01f * rayscale;
|
||||
const float opacityThreshold = 0.95f;
|
||||
const float3 boxMin = make_float3(-1.0f, -1.0f, -1.0f);
|
||||
const float3 boxMax = make_float3(1.0f, 1.0f, 1.0f);
|
||||
|
||||
density *= rayscale;
|
||||
|
||||
uint x = blockIdx.x * blockDim.x + threadIdx.x;
|
||||
uint y = blockIdx.y * blockDim.y + threadIdx.y;
|
||||
|
||||
if ((x >= imageW) || (y >= imageH)) return;
|
||||
|
||||
float u = (x / (float)imageW) * 2.0f - 1.0f;
|
||||
float v = (y / (float)imageH) * 2.0f - 1.0f;
|
||||
|
||||
// calculate eye ray in world space
|
||||
Ray eyeRay;
|
||||
eyeRay.o =
|
||||
make_float3(mul(c_invViewMatrix, make_float4(0.0f, 0.0f, 0.0f, 1.0f)));
|
||||
eyeRay.d = normalize(make_float3(u, v, -2.0f));
|
||||
eyeRay.d = mul(c_invViewMatrix, eyeRay.d);
|
||||
|
||||
// find intersection with box
|
||||
float tnear, tfar;
|
||||
int hit = intersectBox(eyeRay, boxMin, boxMax, &tnear, &tfar);
|
||||
|
||||
if (!hit) return;
|
||||
|
||||
if (tnear < 0.0f) tnear = 0.0f; // clamp to near plane
|
||||
|
||||
// march along ray from front to back, accumulating color
|
||||
float4 sum = make_float4(0.0f);
|
||||
float t = tnear;
|
||||
float3 pos = eyeRay.o + eyeRay.d * tnear;
|
||||
float3 step = eyeRay.d * tstep;
|
||||
|
||||
float lastsample = 0;
|
||||
|
||||
// lastsample = (lastsample-transferOffset)*transferScale;
|
||||
for (int i = 0; i < maxSteps; i++) {
|
||||
// read from 3D texture
|
||||
// remap position to [0, 1] coordinates
|
||||
float3 coord = make_float3(pos.x * 0.5f + 0.5f, pos.y * 0.5f + 0.5f,
|
||||
pos.z * 0.5f + 0.5f);
|
||||
float sample = tex3D<float>(volumeTex, coord.x, coord.y, coord.z);
|
||||
// sample = (sample-transferOffset)*transferScale;
|
||||
// sample *= 64.0f; // scale for 10-bit data
|
||||
|
||||
// lookup in transfer function texture
|
||||
float4 col;
|
||||
int tfid = (pos.x < 0);
|
||||
|
||||
if (TFMODE != TF_SINGLE_1D) {
|
||||
col = tex2DLayered<float4>(transferLayerPreintTex, sample,
|
||||
TFMODE == TF_LAYERED_2D ? sample : lastsample,
|
||||
tfid);
|
||||
col.w *= density;
|
||||
lastsample = sample;
|
||||
} else {
|
||||
col = tex1D<float4>(transferTex, sample);
|
||||
col.w *= 0;
|
||||
}
|
||||
|
||||
// "under" operator for back-to-front blending
|
||||
// sum = lerp(sum, col, col.w);
|
||||
|
||||
// pre-multiply alpha
|
||||
col.x *= col.w;
|
||||
col.y *= col.w;
|
||||
col.z *= col.w;
|
||||
// "over" operator for front-to-back blending
|
||||
sum = sum + col * (1.0f - sum.w);
|
||||
|
||||
// exit early if opaque
|
||||
if (sum.w > opacityThreshold) break;
|
||||
|
||||
t += tstep;
|
||||
|
||||
if (t > tfar) break;
|
||||
|
||||
pos += step;
|
||||
}
|
||||
|
||||
sum *= brightness;
|
||||
|
||||
// write output color
|
||||
d_output[y * imageW + x] = rgbaFloatToInt(sum);
|
||||
}
|
||||
|
||||
__global__ void d_render_regular(uint *d_output, uint imageW, uint imageH,
|
||||
float density, float brightness,
|
||||
float transferOffset, float transferScale,
|
||||
cudaTextureObject_t volumeTex,
|
||||
cudaTextureObject_t transferTex,
|
||||
cudaTextureObject_t transferLayerPreintTex,
|
||||
float transferWeight = 0.0f) {
|
||||
d_render<TF_SINGLE_1D>(d_output, imageW, imageH, density, brightness,
|
||||
transferOffset, transferScale, volumeTex, transferTex,
|
||||
transferLayerPreintTex, transferWeight);
|
||||
}
|
||||
|
||||
__global__ void d_render_preint(uint *d_output, uint imageW, uint imageH,
|
||||
float density, float brightness,
|
||||
float transferOffset, float transferScale,
|
||||
cudaTextureObject_t volumeTex,
|
||||
cudaTextureObject_t transferTex,
|
||||
cudaTextureObject_t transferLayerPreintTex,
|
||||
float transferWeight = 0.0f) {
|
||||
d_render<TF_LAYERED_2D_PREINT>(d_output, imageW, imageH, density, brightness,
|
||||
transferOffset, transferScale, volumeTex,
|
||||
transferTex, transferLayerPreintTex,
|
||||
transferWeight);
|
||||
}
|
||||
|
||||
__global__ void d_render_preint_off(uint *d_output, uint imageW, uint imageH,
|
||||
float density, float brightness,
|
||||
float transferOffset, float transferScale,
|
||||
cudaTextureObject_t volumeTex,
|
||||
cudaTextureObject_t transferTex,
|
||||
cudaTextureObject_t transferLayerPreintTex,
|
||||
float transferWeight = 0.0f) {
|
||||
d_render<TF_LAYERED_2D>(d_output, imageW, imageH, density, brightness,
|
||||
transferOffset, transferScale, volumeTex, transferTex,
|
||||
transferLayerPreintTex, transferWeight);
|
||||
}
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
|
||||
__global__ void d_integrate_trapezoidal(
|
||||
cudaExtent extent, cudaTextureObject_t transferTex,
|
||||
cudaSurfaceObject_t transferIntegrateSurf) {
|
||||
uint x = blockIdx.x * blockDim.x + threadIdx.x;
|
||||
|
||||
// for higher speed could use hierarchical approach for sum
|
||||
if (x >= extent.width) {
|
||||
return;
|
||||
}
|
||||
|
||||
float stepsize = 1.0 / float(extent.width - 1);
|
||||
float to = float(x) * stepsize;
|
||||
|
||||
float4 outclr = make_float4(0, 0, 0, 0);
|
||||
float incr = stepsize;
|
||||
|
||||
float4 lastval = tex1D<float4>(transferTex, 0);
|
||||
|
||||
float cur = incr;
|
||||
|
||||
while (cur < to + incr * 0.5) {
|
||||
float4 val = tex1D<float4>(transferTex, cur);
|
||||
float4 trapezoid = (lastval + val) / 2.0f;
|
||||
lastval = val;
|
||||
|
||||
outclr += trapezoid;
|
||||
cur += incr;
|
||||
}
|
||||
|
||||
// surface writes need byte offsets for x!
|
||||
surf1Dwrite(outclr, transferIntegrateSurf, x * sizeof(float4));
|
||||
}
|
||||
|
||||
__global__ void d_preintegrate(int layer, float steps, cudaExtent extent,
|
||||
cudaTextureObject_t transferTex,
|
||||
cudaTextureObject_t transferIntegrateTex,
|
||||
cudaSurfaceObject_t transferLayerPreintSurf) {
|
||||
uint x = blockIdx.x * blockDim.x + threadIdx.x;
|
||||
uint y = blockIdx.y * blockDim.y + threadIdx.y;
|
||||
|
||||
if (x >= extent.width || y >= extent.height) {
|
||||
return;
|
||||
}
|
||||
|
||||
float sx = float(x) / float(extent.width);
|
||||
float sy = float(y) / float(extent.height);
|
||||
|
||||
float smax = max(sx, sy);
|
||||
float smin = min(sx, sy);
|
||||
|
||||
float4 iv;
|
||||
|
||||
if (x != y) {
|
||||
// assumes square textures!
|
||||
float fracc = smax - smin;
|
||||
fracc = 1.0 / (fracc * steps);
|
||||
|
||||
float4 intmax = tex1D<float4>(transferIntegrateTex, smax);
|
||||
float4 intmin = tex1D<float4>(transferIntegrateTex, smin);
|
||||
iv.x = (intmax.x - intmin.x) * fracc;
|
||||
iv.y = (intmax.y - intmin.y) * fracc;
|
||||
iv.z = (intmax.z - intmin.z) * fracc;
|
||||
// iv.w = (intmax.w - intmin.w)*fracc;
|
||||
iv.w = (1.0 - exp(-(intmax.w - intmin.w) * fracc));
|
||||
} else {
|
||||
float4 sample = tex1D<float4>(transferTex, smin);
|
||||
iv.x = sample.x;
|
||||
iv.y = sample.y;
|
||||
iv.z = sample.z;
|
||||
// iv.w = sample.w;
|
||||
iv.w = (1.0 - exp(-sample.w));
|
||||
}
|
||||
|
||||
iv.x = __saturatef(iv.x);
|
||||
iv.y = __saturatef(iv.y);
|
||||
iv.z = __saturatef(iv.z);
|
||||
iv.w = __saturatef(iv.w);
|
||||
|
||||
// surface writes need byte offsets for x!
|
||||
surf2DLayeredwrite(iv, transferLayerPreintSurf, x * sizeof(float4), y, layer);
|
||||
}
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
|
||||
void VolumeRender_setTextureFilterMode(bool bLinearFilter, Volume *vol) {
|
||||
if (vol->volumeTex) {
|
||||
checkCudaErrors(cudaDestroyTextureObject(vol->volumeTex));
|
||||
}
|
||||
cudaResourceDesc texRes;
|
||||
memset(&texRes, 0, sizeof(cudaResourceDesc));
|
||||
|
||||
texRes.resType = cudaResourceTypeArray;
|
||||
texRes.res.array.array = vol->content;
|
||||
|
||||
cudaTextureDesc texDescr;
|
||||
memset(&texDescr, 0, sizeof(cudaTextureDesc));
|
||||
|
||||
texDescr.normalizedCoords = true;
|
||||
texDescr.filterMode =
|
||||
bLinearFilter ? cudaFilterModeLinear : cudaFilterModePoint;
|
||||
|
||||
texDescr.addressMode[0] = cudaAddressModeWrap;
|
||||
texDescr.addressMode[1] = cudaAddressModeWrap;
|
||||
texDescr.addressMode[2] = cudaAddressModeWrap;
|
||||
|
||||
texDescr.readMode = VolumeTypeInfo<VolumeType>::readMode;
|
||||
|
||||
checkCudaErrors(
|
||||
cudaCreateTextureObject(&vol->volumeTex, &texRes, &texDescr, NULL));
|
||||
}
|
||||
|
||||
static unsigned int iDivUp(size_t a, size_t b) {
|
||||
size_t val = (a % b != 0) ? (a / b + 1) : (a / b);
|
||||
if (val > UINT_MAX) {
|
||||
fprintf(stderr, "\nUINT_MAX limit exceeded in iDivUp() exiting.....\n");
|
||||
exit(EXIT_FAILURE); // val exceeds limit
|
||||
}
|
||||
|
||||
return static_cast<unsigned int>(val);
|
||||
}
|
||||
|
||||
void VolumeRender_updateTF(int tfIdx, int numColors, float4 *colors) {
|
||||
if (d_transferFunc) {
|
||||
checkCudaErrors(cudaFreeArray(d_transferFunc));
|
||||
d_transferFunc = 0;
|
||||
}
|
||||
|
||||
cudaChannelFormatDesc channelFloat4 = cudaCreateChannelDesc<float4>();
|
||||
checkCudaErrors(
|
||||
cudaMallocArray(&d_transferFunc, &channelFloat4, numColors, 1));
|
||||
checkCudaErrors(cudaMemcpy2DToArray(d_transferFunc, 0, 0, colors, 0,
|
||||
sizeof(float4) * numColors, 1,
|
||||
cudaMemcpyHostToDevice));
|
||||
|
||||
cudaResourceDesc texRes;
|
||||
memset(&texRes, 0, sizeof(cudaResourceDesc));
|
||||
|
||||
texRes.resType = cudaResourceTypeArray;
|
||||
texRes.res.array.array = d_transferFunc;
|
||||
|
||||
cudaTextureDesc texDescr;
|
||||
memset(&texDescr, 0, sizeof(cudaTextureDesc));
|
||||
|
||||
texDescr.normalizedCoords = true;
|
||||
texDescr.filterMode = cudaFilterModeLinear;
|
||||
texDescr.addressMode[0] = cudaAddressModeClamp;
|
||||
texDescr.readMode = cudaReadModeElementType;
|
||||
|
||||
checkCudaErrors(
|
||||
cudaCreateTextureObject(&transferTex, &texRes, &texDescr, NULL));
|
||||
|
||||
if (tfIdx < 0 || tfIdx >= VOLUMERENDER_TFS) {
|
||||
return;
|
||||
}
|
||||
|
||||
{
|
||||
cudaExtent extent = {VOLUMERENDER_TF_PREINTSTEPS, 0, 0};
|
||||
dim3 blockSize(32, 1, 1);
|
||||
dim3 gridSize(iDivUp(extent.width, blockSize.x), 1, 1);
|
||||
d_integrate_trapezoidal<<<gridSize, blockSize>>>(extent, transferTex,
|
||||
transferIntegrateSurf);
|
||||
}
|
||||
|
||||
{
|
||||
cudaExtent extent = {VOLUMERENDER_TF_PREINTSIZE, VOLUMERENDER_TF_PREINTSIZE,
|
||||
VOLUMERENDER_TFS};
|
||||
dim3 blockSize(16, 16, 1);
|
||||
dim3 gridSize(iDivUp(extent.width, blockSize.x),
|
||||
iDivUp(extent.height, blockSize.y), 1);
|
||||
d_preintegrate<<<gridSize, blockSize>>>(
|
||||
tfIdx, float(VOLUMERENDER_TF_PREINTSTEPS), extent, transferTex,
|
||||
transferIntegrateTex, transferLayerPreintSurf);
|
||||
}
|
||||
}
|
||||
|
||||
void VolumeRender_init() {
|
||||
cudaResourceDesc texRes;
|
||||
cudaTextureDesc texDescr;
|
||||
|
||||
cudaChannelFormatDesc channelFloat4 = cudaCreateChannelDesc<float4>();
|
||||
cudaExtent extent = {VOLUMERENDER_TF_PREINTSIZE, VOLUMERENDER_TF_PREINTSIZE,
|
||||
VOLUMERENDER_TFS};
|
||||
checkCudaErrors(
|
||||
cudaMalloc3DArray(&d_transferArray, &channelFloat4, extent,
|
||||
cudaArrayLayered | cudaArraySurfaceLoadStore));
|
||||
|
||||
memset(&texRes, 0, sizeof(cudaResourceDesc));
|
||||
|
||||
texRes.resType = cudaResourceTypeArray;
|
||||
texRes.res.array.array = d_transferArray;
|
||||
|
||||
memset(&texDescr, 0, sizeof(cudaTextureDesc));
|
||||
|
||||
texDescr.normalizedCoords = true;
|
||||
texDescr.filterMode = cudaFilterModeLinear;
|
||||
texDescr.addressMode[0] = cudaAddressModeClamp;
|
||||
texDescr.addressMode[1] = cudaAddressModeClamp;
|
||||
texDescr.readMode = cudaReadModeElementType;
|
||||
|
||||
checkCudaErrors(cudaCreateTextureObject(&transferLayerPreintTex, &texRes,
|
||||
&texDescr, NULL));
|
||||
|
||||
cudaResourceDesc surfRes;
|
||||
memset(&surfRes, 0, sizeof(cudaResourceDesc));
|
||||
surfRes.resType = cudaResourceTypeArray;
|
||||
surfRes.res.array.array = d_transferArray;
|
||||
|
||||
checkCudaErrors(cudaCreateSurfaceObject(&transferLayerPreintSurf, &surfRes));
|
||||
|
||||
checkCudaErrors(cudaMallocArray(&d_transferIntegrate, &channelFloat4,
|
||||
VOLUMERENDER_TF_PREINTSTEPS, 0,
|
||||
cudaArraySurfaceLoadStore));
|
||||
|
||||
memset(&texRes, 0, sizeof(cudaResourceDesc));
|
||||
|
||||
texRes.resType = cudaResourceTypeArray;
|
||||
texRes.res.array.array = d_transferIntegrate;
|
||||
|
||||
memset(&texDescr, 0, sizeof(cudaTextureDesc));
|
||||
|
||||
texDescr.normalizedCoords = true;
|
||||
texDescr.filterMode = cudaFilterModeLinear;
|
||||
|
||||
texDescr.addressMode[0] = cudaAddressModeClamp;
|
||||
texDescr.addressMode[1] = cudaAddressModeClamp;
|
||||
texDescr.addressMode[2] = cudaAddressModeClamp;
|
||||
|
||||
texDescr.readMode = cudaReadModeElementType;
|
||||
|
||||
checkCudaErrors(
|
||||
cudaCreateTextureObject(&transferIntegrateTex, &texRes, &texDescr, NULL));
|
||||
|
||||
memset(&surfRes, 0, sizeof(cudaResourceDesc));
|
||||
surfRes.resType = cudaResourceTypeArray;
|
||||
surfRes.res.array.array = d_transferIntegrate;
|
||||
|
||||
checkCudaErrors(cudaCreateSurfaceObject(&transferIntegrateSurf, &surfRes));
|
||||
|
||||
// create transfer function texture
|
||||
float4 transferFunc0[] = {
|
||||
{ 0.0, 0.0, 0.0, 0.0, },
|
||||
{ 1.0, 0.0, 0.0, 1.0, },
|
||||
{ 1.0, 0.5, 0.0, 1.0, },
|
||||
{ 1.0, 1.0, 0.0, 1.0, },
|
||||
{ 0.0, 1.0, 0.0, 1.0, },
|
||||
{ 0.0, 1.0, 1.0, 1.0, },
|
||||
{ 0.0, 0.0, 1.0, 1.0, },
|
||||
{ 1.0, 0.0, 1.0, 1.0, },
|
||||
{ 0.0, 0.0, 0.0, 0.0, },
|
||||
};
|
||||
|
||||
float4 transferFunc1[] = {
|
||||
{ 0.0, 0.0, 0.0, 0.0, },
|
||||
{ 0.0, 1.0, 0.0, 0.125, },
|
||||
{ 0.0, 0.5, 1.0, 0.125, },
|
||||
{ 0.0, 1.0, 1.0, 0.125, },
|
||||
{ 0.0, 1.0, 0.0, 0.125, },
|
||||
{ 0.25, 0.75, 0.0, 1.0, },
|
||||
{ 0.75, 0.25, 0.0, 0.125, },
|
||||
{ 1.0, 0.75, 0.0, 0.125, },
|
||||
{ 0.0, 0.0, 0.0, 0.0, },
|
||||
};
|
||||
|
||||
VolumeRender_updateTF(1, sizeof(transferFunc1) / sizeof(float4),
|
||||
transferFunc1);
|
||||
VolumeRender_updateTF(0, sizeof(transferFunc0) / sizeof(float4),
|
||||
transferFunc0);
|
||||
}
|
||||
|
||||
void VolumeRender_deinit() {
|
||||
checkCudaErrors(cudaDestroyTextureObject(transferTex));
|
||||
checkCudaErrors(cudaDestroyTextureObject(transferIntegrateTex));
|
||||
checkCudaErrors(cudaDestroySurfaceObject(transferIntegrateSurf));
|
||||
checkCudaErrors(cudaDestroyTextureObject(transferLayerPreintTex));
|
||||
checkCudaErrors(cudaDestroySurfaceObject(transferLayerPreintSurf));
|
||||
checkCudaErrors(cudaFreeArray(d_transferFunc));
|
||||
checkCudaErrors(cudaFreeArray(d_transferArray));
|
||||
checkCudaErrors(cudaFreeArray(d_transferIntegrate));
|
||||
d_transferArray = 0;
|
||||
d_transferFunc = 0;
|
||||
d_transferIntegrate = 0;
|
||||
}
|
||||
|
||||
void VolumeRender_setPreIntegrated(int state) { usePreInt = !!state; }
|
||||
|
||||
void VolumeRender_render(dim3 gridSize, dim3 blockSize, uint *d_output,
|
||||
uint imageW, uint imageH, float density,
|
||||
float brightness, float transferOffset,
|
||||
float transferScale, cudaTextureObject_t volumeTex) {
|
||||
if (usePreInt) {
|
||||
d_render_preint<<<gridSize, blockSize>>>(
|
||||
d_output, imageW, imageH, density, brightness, transferOffset,
|
||||
transferScale, volumeTex, transferTex, transferLayerPreintTex);
|
||||
} else {
|
||||
d_render_preint_off<<<gridSize, blockSize>>>(
|
||||
d_output, imageW, imageH, density, brightness, transferOffset,
|
||||
transferScale, volumeTex, transferTex, transferLayerPreintTex);
|
||||
}
|
||||
}
|
||||
|
||||
void VolumeRender_copyInvViewMatrix(float *invViewMatrix, size_t sizeofMatrix) {
|
||||
checkCudaErrors(
|
||||
cudaMemcpyToSymbol(c_invViewMatrix, invViewMatrix, sizeofMatrix));
|
||||
}
|
||||
|
||||
#endif // #ifndef _VOLUMERENDER_KERNEL_CU_
|
||||
Reference in New Issue
Block a user