mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2026-10-23 21:28:17 +08:00
add and update samples for CUDA 11.5
This commit is contained in:
Rutwik Choughule
18
Samples/oceanFFT/.vscode/c_cpp_properties.json
vendored
Normal file
18
Samples/oceanFFT/.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/oceanFFT/.vscode/extensions.json
vendored
Normal file
7
Samples/oceanFFT/.vscode/extensions.json
vendored
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"recommendations": [
|
||||
"nvidia.nsight-vscode-edition",
|
||||
"ms-vscode.cpptools",
|
||||
"ms-vscode.makefile-tools"
|
||||
]
|
||||
}
|
||||
10
Samples/oceanFFT/.vscode/launch.json
vendored
Normal file
10
Samples/oceanFFT/.vscode/launch.json
vendored
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"configurations": [
|
||||
{
|
||||
"name": "CUDA C++: Launch",
|
||||
"type": "cuda-gdb",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/oceanFFT"
|
||||
}
|
||||
]
|
||||
}
|
||||
15
Samples/oceanFFT/.vscode/tasks.json
vendored
Normal file
15
Samples/oceanFFT/.vscode/tasks.json
vendored
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"version": "2.0.0",
|
||||
"tasks": [
|
||||
{
|
||||
"label": "sample",
|
||||
"type": "shell",
|
||||
"command": "make dbg=1",
|
||||
"problemMatcher": ["$nvcc"],
|
||||
"group": {
|
||||
"kind": "build",
|
||||
"isDefault": true
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
387
Samples/oceanFFT/Makefile
Normal file
387
Samples/oceanFFT/Makefile
Normal file
@@ -0,0 +1,387 @@
|
||||
################################################################################
|
||||
# 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 - oceanFFT 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
|
||||
|
||||
LIBRARIES += -lcufft
|
||||
|
||||
ifeq ($(SAMPLE_ENABLED),0)
|
||||
EXEC ?= @echo "[@]"
|
||||
endif
|
||||
|
||||
################################################################################
|
||||
|
||||
# Target rules
|
||||
all: build
|
||||
|
||||
build: oceanFFT
|
||||
|
||||
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
|
||||
|
||||
oceanFFT.o:oceanFFT.cpp
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
oceanFFT_kernel.o:oceanFFT_kernel.cu
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
oceanFFT: oceanFFT.o oceanFFT_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) ./oceanFFT
|
||||
|
||||
clean:
|
||||
rm -f oceanFFT oceanFFT.o oceanFFT_kernel.o
|
||||
rm -rf ../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/oceanFFT
|
||||
|
||||
clobber: clean
|
||||
105
Samples/oceanFFT/NsightEclipse.xml
Normal file
105
Samples/oceanFFT/NsightEclipse.xml
Normal file
@@ -0,0 +1,105 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
||||
<entry>
|
||||
<name>oceanFFT</name>
|
||||
<cuda_api_list>
|
||||
<toolkit>cudaGraphicsMapResources</toolkit>
|
||||
<toolkit>cudaGraphicsUnmapResources</toolkit>
|
||||
<toolkit>cudaGraphicsResourceGetMappedPointer</toolkit>
|
||||
<toolkit>cudaGraphicsRegisterResource</toolkit>
|
||||
<toolkit>cudaGraphicsGLRegisterBuffer</toolkit>
|
||||
<toolkit>cudaGraphicsUnregisterResource</toolkit>
|
||||
<toolkit>cufftPlan2d</toolkit>
|
||||
<toolkit>cufftExecR2C</toolkit>
|
||||
<toolkit>cufftExecC2R</toolkit>
|
||||
<toolkit>cufftDestroy</toolkit>
|
||||
</cuda_api_list>
|
||||
<description><![CDATA[This sample simulates an Ocean height field using CUFFT Library and renders the result using OpenGL.]]></description>
|
||||
<devicecompilation>whole</devicecompilation>
|
||||
<files>
|
||||
<file>data\ocean.frag</file>
|
||||
<file>data\ocean.vert</file>
|
||||
<file>data\reference.ppm</file>
|
||||
<file>data\ref_slopeShading.bin</file>
|
||||
<file>data\ref_spatialDomain.bin</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">CUFFT Library</concept>
|
||||
</keyconcepts>
|
||||
<keywords>
|
||||
<keyword>CUDA</keyword>
|
||||
<keyword>CUFFT</keyword>
|
||||
<keyword>Ocean</keyword>
|
||||
<keyword>OpenGL</keyword>
|
||||
<keyword>Height Field</keyword>
|
||||
<keyword>openGL</keyword>
|
||||
</keywords>
|
||||
<libraries>
|
||||
<library>cufft</library>
|
||||
<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>oceanFFT.cpp</primary_file>
|
||||
<qatests>
|
||||
<qatest>-qatest</qatest>
|
||||
</qatests>
|
||||
<required_dependencies>
|
||||
<dependency>X11</dependency>
|
||||
<dependency>GL</dependency>
|
||||
<dependency>CUFFT</dependency>
|
||||
</required_dependencies>
|
||||
<scopes>
|
||||
<scope>1:CUDA Advanced Topics</scope>
|
||||
<scope>2:Graphics Interop</scope>
|
||||
<scope>3:Physically-Based Simulation</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>CUDA FFT Ocean Simulation</title>
|
||||
<type>exe</type>
|
||||
</entry>
|
||||
74
Samples/oceanFFT/README.md
Normal file
74
Samples/oceanFFT/README.md
Normal file
@@ -0,0 +1,74 @@
|
||||
# oceanFFT - CUDA FFT Ocean Simulation
|
||||
|
||||
## Description
|
||||
|
||||
This sample simulates an Ocean height field using CUFFT Library and renders the result using OpenGL.
|
||||
|
||||
## Key Concepts
|
||||
|
||||
Graphics Interop, Image Processing, CUFFT Library
|
||||
|
||||
## 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, cufftPlan2d, cufftExecR2C, cufftExecC2R, cufftDestroy
|
||||
|
||||
## Dependencies needed to build/run
|
||||
[X11](../../README.md#x11), [GL](../../README.md#gl), [CUFFT](../../README.md#cufft)
|
||||
|
||||
## 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)
|
||||
|
||||
30
Samples/oceanFFT/data/ocean.frag
Normal file
30
Samples/oceanFFT/data/ocean.frag
Normal file
@@ -0,0 +1,30 @@
|
||||
// GLSL fragment shader
|
||||
varying vec3 eyeSpacePos;
|
||||
varying vec3 worldSpaceNormal;
|
||||
varying vec3 eyeSpaceNormal;
|
||||
|
||||
uniform vec4 deepColor;
|
||||
uniform vec4 shallowColor;
|
||||
uniform vec4 skyColor;
|
||||
uniform vec3 lightDir;
|
||||
|
||||
void main()
|
||||
{
|
||||
vec3 eyeVector = normalize(eyeSpacePos);
|
||||
vec3 eyeSpaceNormalVector = normalize(eyeSpaceNormal);
|
||||
vec3 worldSpaceNormalVector = normalize(worldSpaceNormal);
|
||||
|
||||
float facing = max(0.0, dot(eyeSpaceNormalVector, -eyeVector));
|
||||
float fresnel = pow(1.0 - facing, 5.0); // Fresnel approximation
|
||||
float diffuse = max(0.0, dot(worldSpaceNormalVector, lightDir));
|
||||
|
||||
// vec4 waterColor = mix(shallowColor, deepColor, facing);
|
||||
vec4 waterColor = deepColor;
|
||||
|
||||
// gl_FragColor = gl_Color;
|
||||
// gl_FragColor = vec4(fresnel);
|
||||
// gl_FragColor = vec4(diffuse);
|
||||
// gl_FragColor = waterColor;
|
||||
// gl_FragColor = waterColor*diffuse;
|
||||
gl_FragColor = waterColor*diffuse + skyColor*fresnel;
|
||||
}
|
||||
24
Samples/oceanFFT/data/ocean.vert
Normal file
24
Samples/oceanFFT/data/ocean.vert
Normal file
@@ -0,0 +1,24 @@
|
||||
// GLSL vertex shader
|
||||
varying vec3 eyeSpacePos;
|
||||
varying vec3 worldSpaceNormal;
|
||||
varying vec3 eyeSpaceNormal;
|
||||
uniform float heightScale; // = 0.5;
|
||||
uniform float chopiness; // = 1.0;
|
||||
uniform vec2 size; // = vec2(256.0, 256.0);
|
||||
|
||||
void main()
|
||||
{
|
||||
float height = gl_MultiTexCoord0.x;
|
||||
vec2 slope = gl_MultiTexCoord1.xy;
|
||||
|
||||
// calculate surface normal from slope for shading
|
||||
vec3 normal = normalize(cross( vec3(0.0, slope.y*heightScale, 2.0 / size.x), vec3(2.0 / size.y, slope.x*heightScale, 0.0)));
|
||||
worldSpaceNormal = normal;
|
||||
|
||||
// calculate position and transform to homogeneous clip space
|
||||
vec4 pos = vec4(gl_Vertex.x, height * heightScale, gl_Vertex.z, 1.0);
|
||||
gl_Position = gl_ModelViewProjectionMatrix * pos;
|
||||
|
||||
eyeSpacePos = (gl_ModelViewMatrix * pos).xyz;
|
||||
eyeSpaceNormal = (gl_NormalMatrix * normal).xyz;
|
||||
}
|
||||
BIN
Samples/oceanFFT/data/ref_slopeShading.bin
Normal file
BIN
Samples/oceanFFT/data/ref_slopeShading.bin
Normal file
Binary file not shown.
BIN
Samples/oceanFFT/data/ref_spatialDomain.bin
Normal file
BIN
Samples/oceanFFT/data/ref_spatialDomain.bin
Normal file
Binary file not shown.
BIN
Samples/oceanFFT/data/reference.ppm
Normal file
BIN
Samples/oceanFFT/data/reference.ppm
Normal file
Binary file not shown.
BIN
Samples/oceanFFT/doc/sshot_lg.png
Normal file
BIN
Samples/oceanFFT/doc/sshot_lg.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 4.4 KiB |
BIN
Samples/oceanFFT/doc/sshot_md.png
Normal file
BIN
Samples/oceanFFT/doc/sshot_md.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.2 KiB |
BIN
Samples/oceanFFT/doc/sshot_sm.png
Normal file
BIN
Samples/oceanFFT/doc/sshot_sm.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.0 KiB |
145
Samples/oceanFFT/findgllib.mk
Normal file
145
Samples/oceanFFT/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
|
||||
|
||||
895
Samples/oceanFFT/oceanFFT.cpp
Normal file
895
Samples/oceanFFT/oceanFFT.cpp
Normal file
@@ -0,0 +1,895 @@
|
||||
/* 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.
|
||||
*/
|
||||
|
||||
/*
|
||||
FFT-based Ocean simulation
|
||||
based on original code by Yury Uralsky and Calvin Lin
|
||||
|
||||
This sample demonstrates how to use CUFFT to synthesize and
|
||||
render an ocean surface in real-time.
|
||||
|
||||
See Jerry Tessendorf's Siggraph course notes for more details:
|
||||
http://tessendorf.org/reports.html
|
||||
|
||||
It also serves as an example of how to generate multiple vertex
|
||||
buffer streams from CUDA and render them using GLSL shaders.
|
||||
*/
|
||||
|
||||
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
|
||||
#define WINDOWS_LEAN_AND_MEAN
|
||||
#define NOMINMAX
|
||||
#include <windows.h>
|
||||
#endif
|
||||
|
||||
// includes
|
||||
#include <stdlib.h>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <math.h>
|
||||
#include <helper_gl.h>
|
||||
|
||||
#include <cuda_runtime.h>
|
||||
#include <cuda_gl_interop.h>
|
||||
#include <cufft.h>
|
||||
|
||||
#include <helper_cuda.h>
|
||||
#include <helper_functions.h>
|
||||
#include <math_constants.h>
|
||||
|
||||
#if defined(__APPLE__) || defined(MACOSX)
|
||||
#pragma clang diagnostic ignored "-Wdeprecated-declarations"
|
||||
#include <GLUT/glut.h>
|
||||
#else
|
||||
#include <GL/freeglut.h>
|
||||
#endif
|
||||
|
||||
#include <rendercheck_gl.h>
|
||||
|
||||
const char *sSDKsample = "CUDA FFT Ocean Simulation";
|
||||
|
||||
#define MAX_EPSILON 0.10f
|
||||
#define THRESHOLD 0.15f
|
||||
#define REFRESH_DELAY 10 // ms
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// constants
|
||||
unsigned int windowW = 512, windowH = 512;
|
||||
|
||||
const unsigned int meshSize = 256;
|
||||
const unsigned int spectrumW = meshSize + 4;
|
||||
const unsigned int spectrumH = meshSize + 1;
|
||||
|
||||
const int frameCompare = 4;
|
||||
|
||||
// OpenGL vertex buffers
|
||||
GLuint posVertexBuffer;
|
||||
GLuint heightVertexBuffer, slopeVertexBuffer;
|
||||
struct cudaGraphicsResource *cuda_posVB_resource, *cuda_heightVB_resource,
|
||||
*cuda_slopeVB_resource; // handles OpenGL-CUDA exchange
|
||||
|
||||
GLuint indexBuffer;
|
||||
GLuint shaderProg;
|
||||
char *vertShaderPath = 0, *fragShaderPath = 0;
|
||||
|
||||
// mouse controls
|
||||
int mouseOldX, mouseOldY;
|
||||
int mouseButtons = 0;
|
||||
float rotateX = 20.0f, rotateY = 0.0f;
|
||||
float translateX = 0.0f, translateY = 0.0f, translateZ = -2.0f;
|
||||
|
||||
bool animate = true;
|
||||
bool drawPoints = false;
|
||||
bool wireFrame = false;
|
||||
bool g_hasDouble = false;
|
||||
|
||||
// FFT data
|
||||
cufftHandle fftPlan;
|
||||
float2 *d_h0 = 0; // heightfield at time 0
|
||||
float2 *h_h0 = 0;
|
||||
float2 *d_ht = 0; // heightfield at time t
|
||||
float2 *d_slope = 0;
|
||||
|
||||
// pointers to device object
|
||||
float *g_hptr = NULL;
|
||||
float2 *g_sptr = NULL;
|
||||
|
||||
// simulation parameters
|
||||
const float g = 9.81f; // gravitational constant
|
||||
const float A = 1e-7f; // wave scale factor
|
||||
const float patchSize = 100; // patch size
|
||||
float windSpeed = 100.0f;
|
||||
float windDir = CUDART_PI_F / 3.0f;
|
||||
float dirDepend = 0.07f;
|
||||
|
||||
StopWatchInterface *timer = NULL;
|
||||
float animTime = 0.0f;
|
||||
float prevTime = 0.0f;
|
||||
float animationRate = -0.001f;
|
||||
|
||||
// Auto-Verification Code
|
||||
const int frameCheckNumber = 4;
|
||||
int fpsCount = 0; // FPS count for averaging
|
||||
int fpsLimit = 1; // FPS limit for sampling
|
||||
unsigned int frameCount = 0;
|
||||
unsigned int g_TotalErrors = 0;
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// kernels
|
||||
//#include <oceanFFT_kernel.cu>
|
||||
|
||||
extern "C" void cudaGenerateSpectrumKernel(float2 *d_h0, float2 *d_ht,
|
||||
unsigned int in_width,
|
||||
unsigned int out_width,
|
||||
unsigned int out_height,
|
||||
float animTime, float patchSize);
|
||||
|
||||
extern "C" void cudaUpdateHeightmapKernel(float *d_heightMap, float2 *d_ht,
|
||||
unsigned int width,
|
||||
unsigned int height, bool autoTest);
|
||||
|
||||
extern "C" void cudaCalculateSlopeKernel(float *h, float2 *slopeOut,
|
||||
unsigned int width,
|
||||
unsigned int height);
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// forward declarations
|
||||
void runAutoTest(int argc, char **argv);
|
||||
void runGraphicsTest(int argc, char **argv);
|
||||
|
||||
// GL functionality
|
||||
bool initGL(int *argc, char **argv);
|
||||
void createVBO(GLuint *vbo, int size);
|
||||
void deleteVBO(GLuint *vbo);
|
||||
void createMeshIndexBuffer(GLuint *id, int w, int h);
|
||||
void createMeshPositionVBO(GLuint *id, int w, int h);
|
||||
GLuint loadGLSLProgram(const char *vertFileName, const char *fragFileName);
|
||||
|
||||
// rendering callbacks
|
||||
void display();
|
||||
void keyboard(unsigned char key, int x, int y);
|
||||
void mouse(int button, int state, int x, int y);
|
||||
void motion(int x, int y);
|
||||
void reshape(int w, int h);
|
||||
void timerEvent(int value);
|
||||
|
||||
// Cuda functionality
|
||||
void runCuda();
|
||||
void runCudaTest(char *exec_path);
|
||||
void generate_h0(float2 *h0);
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Program main
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
int main(int argc, char **argv) {
|
||||
printf(
|
||||
"NOTE: The CUDA Samples are not meant for performance measurements. "
|
||||
"Results may vary when GPU Boost is enabled.\n\n");
|
||||
|
||||
// check for command line arguments
|
||||
if (checkCmdLineFlag(argc, (const char **)argv, "qatest")) {
|
||||
animate = false;
|
||||
fpsLimit = frameCheckNumber;
|
||||
runAutoTest(argc, argv);
|
||||
} else {
|
||||
printf(
|
||||
"[%s]\n\n"
|
||||
"Left mouse button - rotate\n"
|
||||
"Middle mouse button - pan\n"
|
||||
"Right mouse button - zoom\n"
|
||||
"'w' key - toggle wireframe\n",
|
||||
sSDKsample);
|
||||
|
||||
runGraphicsTest(argc, argv);
|
||||
}
|
||||
|
||||
exit(EXIT_SUCCESS);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Run test
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void runAutoTest(int argc, char **argv) {
|
||||
printf("%s Starting...\n\n", argv[0]);
|
||||
|
||||
// Cuda init
|
||||
int dev = findCudaDevice(argc, (const char **)argv);
|
||||
|
||||
cudaDeviceProp deviceProp;
|
||||
checkCudaErrors(cudaGetDeviceProperties(&deviceProp, dev));
|
||||
printf("Compute capability %d.%d\n", deviceProp.major, deviceProp.minor);
|
||||
|
||||
// create FFT plan
|
||||
checkCudaErrors(cufftPlan2d(&fftPlan, meshSize, meshSize, CUFFT_C2C));
|
||||
|
||||
// allocate memory
|
||||
int spectrumSize = spectrumW * spectrumH * sizeof(float2);
|
||||
checkCudaErrors(cudaMalloc((void **)&d_h0, spectrumSize));
|
||||
h_h0 = (float2 *)malloc(spectrumSize);
|
||||
generate_h0(h_h0);
|
||||
checkCudaErrors(cudaMemcpy(d_h0, h_h0, spectrumSize, cudaMemcpyHostToDevice));
|
||||
|
||||
int outputSize = meshSize * meshSize * sizeof(float2);
|
||||
checkCudaErrors(cudaMalloc((void **)&d_ht, outputSize));
|
||||
checkCudaErrors(cudaMalloc((void **)&d_slope, outputSize));
|
||||
|
||||
sdkCreateTimer(&timer);
|
||||
sdkStartTimer(&timer);
|
||||
prevTime = sdkGetTimerValue(&timer);
|
||||
|
||||
runCudaTest(argv[0]);
|
||||
|
||||
checkCudaErrors(cudaFree(d_ht));
|
||||
checkCudaErrors(cudaFree(d_slope));
|
||||
checkCudaErrors(cudaFree(d_h0));
|
||||
checkCudaErrors(cufftDestroy(fftPlan));
|
||||
free(h_h0);
|
||||
|
||||
exit(g_TotalErrors == 0 ? EXIT_SUCCESS : EXIT_FAILURE);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Run test
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void runGraphicsTest(int argc, char **argv) {
|
||||
#if defined(__linux__)
|
||||
setenv("DISPLAY", ":0", 0);
|
||||
#endif
|
||||
|
||||
printf("[%s] ", sSDKsample);
|
||||
printf("\n");
|
||||
|
||||
if (checkCmdLineFlag(argc, (const char **)argv, "device")) {
|
||||
printf("[%s]\n", argv[0]);
|
||||
printf(" Does not explicitly support -device=n in OpenGL mode\n");
|
||||
printf(" To use -device=n, the sample must be running w/o OpenGL\n\n");
|
||||
printf(" > %s -device=n -qatest\n", argv[0]);
|
||||
printf("exiting...\n");
|
||||
|
||||
exit(EXIT_SUCCESS);
|
||||
}
|
||||
|
||||
// First initialize OpenGL context, so we can properly set the GL for CUDA.
|
||||
// This is necessary in order to achieve optimal performance with OpenGL/CUDA
|
||||
// interop.
|
||||
if (false == initGL(&argc, argv)) {
|
||||
return;
|
||||
}
|
||||
|
||||
findCudaDevice(argc, (const char **)argv);
|
||||
|
||||
// create FFT plan
|
||||
checkCudaErrors(cufftPlan2d(&fftPlan, meshSize, meshSize, CUFFT_C2C));
|
||||
|
||||
// allocate memory
|
||||
int spectrumSize = spectrumW * spectrumH * sizeof(float2);
|
||||
checkCudaErrors(cudaMalloc((void **)&d_h0, spectrumSize));
|
||||
h_h0 = (float2 *)malloc(spectrumSize);
|
||||
generate_h0(h_h0);
|
||||
checkCudaErrors(cudaMemcpy(d_h0, h_h0, spectrumSize, cudaMemcpyHostToDevice));
|
||||
|
||||
int outputSize = meshSize * meshSize * sizeof(float2);
|
||||
checkCudaErrors(cudaMalloc((void **)&d_ht, outputSize));
|
||||
checkCudaErrors(cudaMalloc((void **)&d_slope, outputSize));
|
||||
|
||||
sdkCreateTimer(&timer);
|
||||
sdkStartTimer(&timer);
|
||||
prevTime = sdkGetTimerValue(&timer);
|
||||
|
||||
// create vertex buffers and register with CUDA
|
||||
createVBO(&heightVertexBuffer, meshSize * meshSize * sizeof(float));
|
||||
checkCudaErrors(
|
||||
cudaGraphicsGLRegisterBuffer(&cuda_heightVB_resource, heightVertexBuffer,
|
||||
cudaGraphicsMapFlagsWriteDiscard));
|
||||
|
||||
createVBO(&slopeVertexBuffer, outputSize);
|
||||
checkCudaErrors(
|
||||
cudaGraphicsGLRegisterBuffer(&cuda_slopeVB_resource, slopeVertexBuffer,
|
||||
cudaGraphicsMapFlagsWriteDiscard));
|
||||
|
||||
// create vertex and index buffer for mesh
|
||||
createMeshPositionVBO(&posVertexBuffer, meshSize, meshSize);
|
||||
createMeshIndexBuffer(&indexBuffer, meshSize, meshSize);
|
||||
|
||||
runCuda();
|
||||
|
||||
// register callbacks
|
||||
glutDisplayFunc(display);
|
||||
glutKeyboardFunc(keyboard);
|
||||
glutMouseFunc(mouse);
|
||||
glutMotionFunc(motion);
|
||||
glutReshapeFunc(reshape);
|
||||
glutTimerFunc(REFRESH_DELAY, timerEvent, 0);
|
||||
|
||||
// start rendering mainloop
|
||||
glutMainLoop();
|
||||
}
|
||||
|
||||
float urand() { return rand() / (float)RAND_MAX; }
|
||||
|
||||
// Generates Gaussian random number with mean 0 and standard deviation 1.
|
||||
float gauss() {
|
||||
float u1 = urand();
|
||||
float u2 = urand();
|
||||
|
||||
if (u1 < 1e-6f) {
|
||||
u1 = 1e-6f;
|
||||
}
|
||||
|
||||
return sqrtf(-2 * logf(u1)) * cosf(2 * CUDART_PI_F * u2);
|
||||
}
|
||||
|
||||
// Phillips spectrum
|
||||
// (Kx, Ky) - normalized wave vector
|
||||
// Vdir - wind angle in radians
|
||||
// V - wind speed
|
||||
// A - constant
|
||||
float phillips(float Kx, float Ky, float Vdir, float V, float A,
|
||||
float dir_depend) {
|
||||
float k_squared = Kx * Kx + Ky * Ky;
|
||||
|
||||
if (k_squared == 0.0f) {
|
||||
return 0.0f;
|
||||
}
|
||||
|
||||
// largest possible wave from constant wind of velocity v
|
||||
float L = V * V / g;
|
||||
|
||||
float k_x = Kx / sqrtf(k_squared);
|
||||
float k_y = Ky / sqrtf(k_squared);
|
||||
float w_dot_k = k_x * cosf(Vdir) + k_y * sinf(Vdir);
|
||||
|
||||
float phillips = A * expf(-1.0f / (k_squared * L * L)) /
|
||||
(k_squared * k_squared) * w_dot_k * w_dot_k;
|
||||
|
||||
// filter out waves moving opposite to wind
|
||||
if (w_dot_k < 0.0f) {
|
||||
phillips *= dir_depend;
|
||||
}
|
||||
|
||||
// damp out waves with very small length w << l
|
||||
// float w = L / 10000;
|
||||
// phillips *= expf(-k_squared * w * w);
|
||||
|
||||
return phillips;
|
||||
}
|
||||
|
||||
// Generate base heightfield in frequency space
|
||||
void generate_h0(float2 *h0) {
|
||||
for (unsigned int y = 0; y <= meshSize; y++) {
|
||||
for (unsigned int x = 0; x <= meshSize; x++) {
|
||||
float kx = (-(int)meshSize / 2.0f + x) * (2.0f * CUDART_PI_F / patchSize);
|
||||
float ky = (-(int)meshSize / 2.0f + y) * (2.0f * CUDART_PI_F / patchSize);
|
||||
|
||||
float P = sqrtf(phillips(kx, ky, windDir, windSpeed, A, dirDepend));
|
||||
|
||||
if (kx == 0.0f && ky == 0.0f) {
|
||||
P = 0.0f;
|
||||
}
|
||||
|
||||
// float Er = urand()*2.0f-1.0f;
|
||||
// float Ei = urand()*2.0f-1.0f;
|
||||
float Er = gauss();
|
||||
float Ei = gauss();
|
||||
|
||||
float h0_re = Er * P * CUDART_SQRT_HALF_F;
|
||||
float h0_im = Ei * P * CUDART_SQRT_HALF_F;
|
||||
|
||||
int i = y * spectrumW + x;
|
||||
h0[i].x = h0_re;
|
||||
h0[i].y = h0_im;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Run the Cuda kernels
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void runCuda() {
|
||||
size_t num_bytes;
|
||||
|
||||
// generate wave spectrum in frequency domain
|
||||
cudaGenerateSpectrumKernel(d_h0, d_ht, spectrumW, meshSize, meshSize,
|
||||
animTime, patchSize);
|
||||
|
||||
// execute inverse FFT to convert to spatial domain
|
||||
checkCudaErrors(cufftExecC2C(fftPlan, d_ht, d_ht, CUFFT_INVERSE));
|
||||
|
||||
// update heightmap values in vertex buffer
|
||||
checkCudaErrors(cudaGraphicsMapResources(1, &cuda_heightVB_resource, 0));
|
||||
checkCudaErrors(cudaGraphicsResourceGetMappedPointer(
|
||||
(void **)&g_hptr, &num_bytes, cuda_heightVB_resource));
|
||||
|
||||
cudaUpdateHeightmapKernel(g_hptr, d_ht, meshSize, meshSize, false);
|
||||
|
||||
// calculate slope for shading
|
||||
checkCudaErrors(cudaGraphicsMapResources(1, &cuda_slopeVB_resource, 0));
|
||||
checkCudaErrors(cudaGraphicsResourceGetMappedPointer(
|
||||
(void **)&g_sptr, &num_bytes, cuda_slopeVB_resource));
|
||||
|
||||
cudaCalculateSlopeKernel(g_hptr, g_sptr, meshSize, meshSize);
|
||||
|
||||
checkCudaErrors(cudaGraphicsUnmapResources(1, &cuda_heightVB_resource, 0));
|
||||
checkCudaErrors(cudaGraphicsUnmapResources(1, &cuda_slopeVB_resource, 0));
|
||||
}
|
||||
|
||||
void runCudaTest(char *exec_path) {
|
||||
checkCudaErrors(
|
||||
cudaMalloc((void **)&g_hptr, meshSize * meshSize * sizeof(float)));
|
||||
checkCudaErrors(
|
||||
cudaMalloc((void **)&g_sptr, meshSize * meshSize * sizeof(float2)));
|
||||
|
||||
// generate wave spectrum in frequency domain
|
||||
cudaGenerateSpectrumKernel(d_h0, d_ht, spectrumW, meshSize, meshSize,
|
||||
animTime, patchSize);
|
||||
|
||||
// execute inverse FFT to convert to spatial domain
|
||||
checkCudaErrors(cufftExecC2C(fftPlan, d_ht, d_ht, CUFFT_INVERSE));
|
||||
|
||||
// update heightmap values
|
||||
cudaUpdateHeightmapKernel(g_hptr, d_ht, meshSize, meshSize, true);
|
||||
|
||||
{
|
||||
float *hptr = (float *)malloc(meshSize * meshSize * sizeof(float));
|
||||
cudaMemcpy((void *)hptr, (void *)g_hptr,
|
||||
meshSize * meshSize * sizeof(float), cudaMemcpyDeviceToHost);
|
||||
sdkDumpBin((void *)hptr, meshSize * meshSize * sizeof(float),
|
||||
"spatialDomain.bin");
|
||||
|
||||
if (!sdkCompareBin2BinFloat("spatialDomain.bin", "ref_spatialDomain.bin",
|
||||
meshSize * meshSize, MAX_EPSILON, THRESHOLD,
|
||||
exec_path)) {
|
||||
g_TotalErrors++;
|
||||
}
|
||||
|
||||
free(hptr);
|
||||
}
|
||||
|
||||
// calculate slope for shading
|
||||
cudaCalculateSlopeKernel(g_hptr, g_sptr, meshSize, meshSize);
|
||||
|
||||
{
|
||||
float2 *sptr = (float2 *)malloc(meshSize * meshSize * sizeof(float2));
|
||||
cudaMemcpy((void *)sptr, (void *)g_sptr,
|
||||
meshSize * meshSize * sizeof(float2), cudaMemcpyDeviceToHost);
|
||||
sdkDumpBin(sptr, meshSize * meshSize * sizeof(float2), "slopeShading.bin");
|
||||
|
||||
if (!sdkCompareBin2BinFloat("slopeShading.bin", "ref_slopeShading.bin",
|
||||
meshSize * meshSize * 2, MAX_EPSILON, THRESHOLD,
|
||||
exec_path)) {
|
||||
g_TotalErrors++;
|
||||
}
|
||||
|
||||
free(sptr);
|
||||
}
|
||||
|
||||
checkCudaErrors(cudaFree(g_hptr));
|
||||
checkCudaErrors(cudaFree(g_sptr));
|
||||
}
|
||||
|
||||
// void computeFPS()
|
||||
//{
|
||||
// frameCount++;
|
||||
// fpsCount++;
|
||||
//
|
||||
// if (fpsCount == fpsLimit) {
|
||||
// fpsCount = 0;
|
||||
// }
|
||||
//}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Display callback
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void display() {
|
||||
// run CUDA kernel to generate vertex positions
|
||||
if (animate) {
|
||||
runCuda();
|
||||
}
|
||||
|
||||
glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
|
||||
|
||||
// set view matrix
|
||||
glMatrixMode(GL_MODELVIEW);
|
||||
glLoadIdentity();
|
||||
glTranslatef(translateX, translateY, translateZ);
|
||||
glRotatef(rotateX, 1.0, 0.0, 0.0);
|
||||
glRotatef(rotateY, 0.0, 1.0, 0.0);
|
||||
|
||||
// render from the vbo
|
||||
glBindBuffer(GL_ARRAY_BUFFER, posVertexBuffer);
|
||||
glVertexPointer(4, GL_FLOAT, 0, 0);
|
||||
glEnableClientState(GL_VERTEX_ARRAY);
|
||||
|
||||
glBindBuffer(GL_ARRAY_BUFFER, heightVertexBuffer);
|
||||
glClientActiveTexture(GL_TEXTURE0);
|
||||
glTexCoordPointer(1, GL_FLOAT, 0, 0);
|
||||
glEnableClientState(GL_TEXTURE_COORD_ARRAY);
|
||||
|
||||
glBindBuffer(GL_ARRAY_BUFFER, slopeVertexBuffer);
|
||||
glClientActiveTexture(GL_TEXTURE1);
|
||||
glTexCoordPointer(2, GL_FLOAT, 0, 0);
|
||||
glEnableClientState(GL_TEXTURE_COORD_ARRAY);
|
||||
|
||||
glUseProgram(shaderProg);
|
||||
|
||||
// Set default uniform variables parameters for the vertex shader
|
||||
GLuint uniHeightScale, uniChopiness, uniSize;
|
||||
|
||||
uniHeightScale = glGetUniformLocation(shaderProg, "heightScale");
|
||||
glUniform1f(uniHeightScale, 0.5f);
|
||||
|
||||
uniChopiness = glGetUniformLocation(shaderProg, "chopiness");
|
||||
glUniform1f(uniChopiness, 1.0f);
|
||||
|
||||
uniSize = glGetUniformLocation(shaderProg, "size");
|
||||
glUniform2f(uniSize, (float)meshSize, (float)meshSize);
|
||||
|
||||
// Set default uniform variables parameters for the pixel shader
|
||||
GLuint uniDeepColor, uniShallowColor, uniSkyColor, uniLightDir;
|
||||
|
||||
uniDeepColor = glGetUniformLocation(shaderProg, "deepColor");
|
||||
glUniform4f(uniDeepColor, 0.0f, 0.1f, 0.4f, 1.0f);
|
||||
|
||||
uniShallowColor = glGetUniformLocation(shaderProg, "shallowColor");
|
||||
glUniform4f(uniShallowColor, 0.1f, 0.3f, 0.3f, 1.0f);
|
||||
|
||||
uniSkyColor = glGetUniformLocation(shaderProg, "skyColor");
|
||||
glUniform4f(uniSkyColor, 1.0f, 1.0f, 1.0f, 1.0f);
|
||||
|
||||
uniLightDir = glGetUniformLocation(shaderProg, "lightDir");
|
||||
glUniform3f(uniLightDir, 0.0f, 1.0f, 0.0f);
|
||||
// end of uniform settings
|
||||
|
||||
glColor3f(1.0, 1.0, 1.0);
|
||||
|
||||
if (drawPoints) {
|
||||
glDrawArrays(GL_POINTS, 0, meshSize * meshSize);
|
||||
} else {
|
||||
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, indexBuffer);
|
||||
|
||||
glPolygonMode(GL_FRONT_AND_BACK, wireFrame ? GL_LINE : GL_FILL);
|
||||
glDrawElements(GL_TRIANGLE_STRIP, ((meshSize * 2) + 2) * (meshSize - 1),
|
||||
GL_UNSIGNED_INT, 0);
|
||||
glPolygonMode(GL_FRONT_AND_BACK, GL_FILL);
|
||||
|
||||
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, 0);
|
||||
}
|
||||
|
||||
glDisableClientState(GL_VERTEX_ARRAY);
|
||||
glClientActiveTexture(GL_TEXTURE0);
|
||||
glDisableClientState(GL_TEXTURE_COORD_ARRAY);
|
||||
glClientActiveTexture(GL_TEXTURE1);
|
||||
glDisableClientState(GL_TEXTURE_COORD_ARRAY);
|
||||
|
||||
glUseProgram(0);
|
||||
|
||||
glutSwapBuffers();
|
||||
|
||||
// computeFPS();
|
||||
}
|
||||
|
||||
void timerEvent(int value) {
|
||||
float time = sdkGetTimerValue(&timer);
|
||||
|
||||
if (animate) {
|
||||
animTime += (time - prevTime) * animationRate;
|
||||
}
|
||||
|
||||
glutPostRedisplay();
|
||||
prevTime = time;
|
||||
|
||||
glutTimerFunc(REFRESH_DELAY, timerEvent, 0);
|
||||
}
|
||||
|
||||
void cleanup() {
|
||||
sdkDeleteTimer(&timer);
|
||||
checkCudaErrors(cudaGraphicsUnregisterResource(cuda_heightVB_resource));
|
||||
checkCudaErrors(cudaGraphicsUnregisterResource(cuda_slopeVB_resource));
|
||||
|
||||
deleteVBO(&posVertexBuffer);
|
||||
deleteVBO(&heightVertexBuffer);
|
||||
deleteVBO(&slopeVertexBuffer);
|
||||
|
||||
checkCudaErrors(cudaFree(d_h0));
|
||||
checkCudaErrors(cudaFree(d_slope));
|
||||
checkCudaErrors(cudaFree(d_ht));
|
||||
free(h_h0);
|
||||
cufftDestroy(fftPlan);
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Keyboard events handler
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void keyboard(unsigned char key, int /*x*/, int /*y*/) {
|
||||
switch (key) {
|
||||
case (27):
|
||||
cleanup();
|
||||
exit(EXIT_SUCCESS);
|
||||
|
||||
case 'w':
|
||||
wireFrame = !wireFrame;
|
||||
break;
|
||||
|
||||
case 'p':
|
||||
drawPoints = !drawPoints;
|
||||
break;
|
||||
|
||||
case ' ':
|
||||
animate = !animate;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Mouse event handlers
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void mouse(int button, int state, int x, int y) {
|
||||
if (state == GLUT_DOWN) {
|
||||
mouseButtons |= 1 << button;
|
||||
} else if (state == GLUT_UP) {
|
||||
mouseButtons = 0;
|
||||
}
|
||||
|
||||
mouseOldX = x;
|
||||
mouseOldY = y;
|
||||
glutPostRedisplay();
|
||||
}
|
||||
|
||||
void motion(int x, int y) {
|
||||
float dx, dy;
|
||||
dx = (float)(x - mouseOldX);
|
||||
dy = (float)(y - mouseOldY);
|
||||
|
||||
if (mouseButtons == 1) {
|
||||
rotateX += dy * 0.2f;
|
||||
rotateY += dx * 0.2f;
|
||||
} else if (mouseButtons == 2) {
|
||||
translateX += dx * 0.01f;
|
||||
translateY -= dy * 0.01f;
|
||||
} else if (mouseButtons == 4) {
|
||||
translateZ += dy * 0.01f;
|
||||
}
|
||||
|
||||
mouseOldX = x;
|
||||
mouseOldY = y;
|
||||
}
|
||||
|
||||
void reshape(int w, int h) {
|
||||
glViewport(0, 0, w, h);
|
||||
|
||||
glMatrixMode(GL_PROJECTION);
|
||||
glLoadIdentity();
|
||||
gluPerspective(60.0, (double)w / (double)h, 0.1, 10.0);
|
||||
|
||||
windowW = w;
|
||||
windowH = h;
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Initialize GL
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
bool initGL(int *argc, char **argv) {
|
||||
// Create GL context
|
||||
glutInit(argc, argv);
|
||||
glutInitDisplayMode(GLUT_RGBA | GLUT_DOUBLE | GLUT_DEPTH);
|
||||
glutInitWindowSize(windowW, windowH);
|
||||
glutCreateWindow("CUDA FFT Ocean Simulation");
|
||||
|
||||
vertShaderPath = sdkFindFilePath("ocean.vert", argv[0]);
|
||||
fragShaderPath = sdkFindFilePath("ocean.frag", argv[0]);
|
||||
|
||||
if (vertShaderPath == NULL || fragShaderPath == NULL) {
|
||||
fprintf(stderr, "Error unable to find GLSL vertex and fragment shaders!\n");
|
||||
exit(EXIT_FAILURE);
|
||||
}
|
||||
|
||||
// initialize necessary OpenGL extensions
|
||||
|
||||
if (!isGLVersionSupported(2, 0)) {
|
||||
fprintf(stderr, "ERROR: Support for necessary OpenGL extensions missing.");
|
||||
fflush(stderr);
|
||||
return false;
|
||||
}
|
||||
|
||||
if (!areGLExtensionsSupported(
|
||||
"GL_ARB_vertex_buffer_object GL_ARB_pixel_buffer_object")) {
|
||||
fprintf(stderr, "Error: failed to get minimal extensions for demo\n");
|
||||
fprintf(stderr, "This sample requires:\n");
|
||||
fprintf(stderr, " OpenGL version 1.5\n");
|
||||
fprintf(stderr, " GL_ARB_vertex_buffer_object\n");
|
||||
fprintf(stderr, " GL_ARB_pixel_buffer_object\n");
|
||||
cleanup();
|
||||
exit(EXIT_FAILURE);
|
||||
}
|
||||
|
||||
// default initialization
|
||||
glClearColor(0.0, 0.0, 0.0, 1.0);
|
||||
glEnable(GL_DEPTH_TEST);
|
||||
|
||||
// load shader
|
||||
shaderProg = loadGLSLProgram(vertShaderPath, fragShaderPath);
|
||||
|
||||
SDK_CHECK_ERROR_GL();
|
||||
return true;
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Create VBO
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void createVBO(GLuint *vbo, int size) {
|
||||
// create buffer object
|
||||
glGenBuffers(1, vbo);
|
||||
glBindBuffer(GL_ARRAY_BUFFER, *vbo);
|
||||
glBufferData(GL_ARRAY_BUFFER, size, 0, GL_DYNAMIC_DRAW);
|
||||
glBindBuffer(GL_ARRAY_BUFFER, 0);
|
||||
|
||||
SDK_CHECK_ERROR_GL();
|
||||
}
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
//! Delete VBO
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
void deleteVBO(GLuint *vbo) {
|
||||
glDeleteBuffers(1, vbo);
|
||||
*vbo = 0;
|
||||
}
|
||||
|
||||
// create index buffer for rendering quad mesh
|
||||
void createMeshIndexBuffer(GLuint *id, int w, int h) {
|
||||
int size = ((w * 2) + 2) * (h - 1) * sizeof(GLuint);
|
||||
|
||||
// create index buffer
|
||||
glGenBuffers(1, id);
|
||||
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, *id);
|
||||
glBufferData(GL_ELEMENT_ARRAY_BUFFER, size, 0, GL_STATIC_DRAW);
|
||||
|
||||
// fill with indices for rendering mesh as triangle strips
|
||||
GLuint *indices =
|
||||
(GLuint *)glMapBuffer(GL_ELEMENT_ARRAY_BUFFER, GL_WRITE_ONLY);
|
||||
|
||||
if (!indices) {
|
||||
return;
|
||||
}
|
||||
|
||||
for (int y = 0; y < h - 1; y++) {
|
||||
for (int x = 0; x < w; x++) {
|
||||
*indices++ = y * w + x;
|
||||
*indices++ = (y + 1) * w + x;
|
||||
}
|
||||
|
||||
// start new strip with degenerate triangle
|
||||
*indices++ = (y + 1) * w + (w - 1);
|
||||
*indices++ = (y + 1) * w;
|
||||
}
|
||||
|
||||
glUnmapBuffer(GL_ELEMENT_ARRAY_BUFFER);
|
||||
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, 0);
|
||||
}
|
||||
|
||||
// create fixed vertex buffer to store mesh vertices
|
||||
void createMeshPositionVBO(GLuint *id, int w, int h) {
|
||||
createVBO(id, w * h * 4 * sizeof(float));
|
||||
|
||||
glBindBuffer(GL_ARRAY_BUFFER, *id);
|
||||
float *pos = (float *)glMapBuffer(GL_ARRAY_BUFFER, GL_WRITE_ONLY);
|
||||
|
||||
if (!pos) {
|
||||
return;
|
||||
}
|
||||
|
||||
for (int y = 0; y < h; y++) {
|
||||
for (int x = 0; x < w; x++) {
|
||||
float u = x / (float)(w - 1);
|
||||
float v = y / (float)(h - 1);
|
||||
*pos++ = u * 2.0f - 1.0f;
|
||||
*pos++ = 0.0f;
|
||||
*pos++ = v * 2.0f - 1.0f;
|
||||
*pos++ = 1.0f;
|
||||
}
|
||||
}
|
||||
|
||||
glUnmapBuffer(GL_ARRAY_BUFFER);
|
||||
glBindBuffer(GL_ARRAY_BUFFER, 0);
|
||||
}
|
||||
|
||||
// Attach shader to a program
|
||||
int attachShader(GLuint prg, GLenum type, const char *name) {
|
||||
GLuint shader;
|
||||
FILE *fp;
|
||||
int size, compiled;
|
||||
char *src;
|
||||
|
||||
fp = fopen(name, "rb");
|
||||
|
||||
if (!fp) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
fseek(fp, 0, SEEK_END);
|
||||
size = ftell(fp);
|
||||
src = (char *)malloc(size);
|
||||
|
||||
fseek(fp, 0, SEEK_SET);
|
||||
fread(src, sizeof(char), size, fp);
|
||||
fclose(fp);
|
||||
|
||||
shader = glCreateShader(type);
|
||||
glShaderSource(shader, 1, (const char **)&src, (const GLint *)&size);
|
||||
glCompileShader(shader);
|
||||
glGetShaderiv(shader, GL_COMPILE_STATUS, (GLint *)&compiled);
|
||||
|
||||
if (!compiled) {
|
||||
char log[2048];
|
||||
int len;
|
||||
|
||||
glGetShaderInfoLog(shader, 2048, (GLsizei *)&len, log);
|
||||
printf("Info log: %s\n", log);
|
||||
glDeleteShader(shader);
|
||||
return 0;
|
||||
}
|
||||
|
||||
free(src);
|
||||
|
||||
glAttachShader(prg, shader);
|
||||
glDeleteShader(shader);
|
||||
|
||||
return 1;
|
||||
}
|
||||
|
||||
// Create shader program from vertex shader and fragment shader files
|
||||
GLuint loadGLSLProgram(const char *vertFileName, const char *fragFileName) {
|
||||
GLint linked;
|
||||
GLuint program;
|
||||
|
||||
program = glCreateProgram();
|
||||
|
||||
if (!attachShader(program, GL_VERTEX_SHADER, vertFileName)) {
|
||||
glDeleteProgram(program);
|
||||
fprintf(stderr, "Couldn't attach vertex shader from file %s\n",
|
||||
vertFileName);
|
||||
return 0;
|
||||
}
|
||||
|
||||
if (!attachShader(program, GL_FRAGMENT_SHADER, fragFileName)) {
|
||||
glDeleteProgram(program);
|
||||
fprintf(stderr, "Couldn't attach fragment shader from file %s\n",
|
||||
fragFileName);
|
||||
return 0;
|
||||
}
|
||||
|
||||
glLinkProgram(program);
|
||||
glGetProgramiv(program, GL_LINK_STATUS, &linked);
|
||||
|
||||
if (!linked) {
|
||||
glDeleteProgram(program);
|
||||
char temp[256];
|
||||
glGetProgramInfoLog(program, 256, 0, temp);
|
||||
fprintf(stderr, "Failed to link program: %s\n", temp);
|
||||
return 0;
|
||||
}
|
||||
|
||||
return program;
|
||||
}
|
||||
159
Samples/oceanFFT/oceanFFT_kernel.cu
Normal file
159
Samples/oceanFFT/oceanFFT_kernel.cu
Normal file
@@ -0,0 +1,159 @@
|
||||
/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
* * Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* * Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in the
|
||||
* documentation and/or other materials provided with the distribution.
|
||||
* * Neither the name of NVIDIA CORPORATION nor the names of its
|
||||
* contributors may be used to endorse or promote products derived
|
||||
* from this software without specific prior written permission.
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
|
||||
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
||||
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
||||
* OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
*/
|
||||
|
||||
///////////////////////////////////////////////////////////////////////////////
|
||||
#include <cufft.h>
|
||||
#include <math_constants.h>
|
||||
|
||||
// Round a / b to nearest higher integer value
|
||||
int cuda_iDivUp(int a, int b) { return (a + (b - 1)) / b; }
|
||||
|
||||
// complex math functions
|
||||
__device__ float2 conjugate(float2 arg) { return make_float2(arg.x, -arg.y); }
|
||||
|
||||
__device__ float2 complex_exp(float arg) {
|
||||
return make_float2(cosf(arg), sinf(arg));
|
||||
}
|
||||
|
||||
__device__ float2 complex_add(float2 a, float2 b) {
|
||||
return make_float2(a.x + b.x, a.y + b.y);
|
||||
}
|
||||
|
||||
__device__ float2 complex_mult(float2 ab, float2 cd) {
|
||||
return make_float2(ab.x * cd.x - ab.y * cd.y, ab.x * cd.y + ab.y * cd.x);
|
||||
}
|
||||
|
||||
// generate wave heightfield at time t based on initial heightfield and
|
||||
// dispersion relationship
|
||||
__global__ void generateSpectrumKernel(float2 *h0, float2 *ht,
|
||||
unsigned int in_width,
|
||||
unsigned int out_width,
|
||||
unsigned int out_height, float t,
|
||||
float patchSize) {
|
||||
unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
|
||||
unsigned int y = blockIdx.y * blockDim.y + threadIdx.y;
|
||||
unsigned int in_index = y * in_width + x;
|
||||
unsigned int in_mindex =
|
||||
(out_height - y) * in_width + (out_width - x); // mirrored
|
||||
unsigned int out_index = y * out_width + x;
|
||||
|
||||
// calculate wave vector
|
||||
float2 k;
|
||||
k.x = (-(int)out_width / 2.0f + x) * (2.0f * CUDART_PI_F / patchSize);
|
||||
k.y = (-(int)out_width / 2.0f + y) * (2.0f * CUDART_PI_F / patchSize);
|
||||
|
||||
// calculate dispersion w(k)
|
||||
float k_len = sqrtf(k.x * k.x + k.y * k.y);
|
||||
float w = sqrtf(9.81f * k_len);
|
||||
|
||||
if ((x < out_width) && (y < out_height)) {
|
||||
float2 h0_k = h0[in_index];
|
||||
float2 h0_mk = h0[in_mindex];
|
||||
|
||||
// output frequency-space complex values
|
||||
ht[out_index] =
|
||||
complex_add(complex_mult(h0_k, complex_exp(w * t)),
|
||||
complex_mult(conjugate(h0_mk), complex_exp(-w * t)));
|
||||
// ht[out_index] = h0_k;
|
||||
}
|
||||
}
|
||||
|
||||
// update height map values based on output of FFT
|
||||
__global__ void updateHeightmapKernel(float *heightMap, float2 *ht,
|
||||
unsigned int width) {
|
||||
unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
|
||||
unsigned int y = blockIdx.y * blockDim.y + threadIdx.y;
|
||||
unsigned int i = y * width + x;
|
||||
|
||||
// cos(pi * (m1 + m2))
|
||||
float sign_correction = ((x + y) & 0x01) ? -1.0f : 1.0f;
|
||||
|
||||
heightMap[i] = ht[i].x * sign_correction;
|
||||
}
|
||||
|
||||
// update height map values based on output of FFT
|
||||
__global__ void updateHeightmapKernel_y(float *heightMap, float2 *ht,
|
||||
unsigned int width) {
|
||||
unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
|
||||
unsigned int y = blockIdx.y * blockDim.y + threadIdx.y;
|
||||
unsigned int i = y * width + x;
|
||||
|
||||
// cos(pi * (m1 + m2))
|
||||
float sign_correction = ((x + y) & 0x01) ? -1.0f : 1.0f;
|
||||
|
||||
heightMap[i] = ht[i].y * sign_correction;
|
||||
}
|
||||
|
||||
// generate slope by partial differences in spatial domain
|
||||
__global__ void calculateSlopeKernel(float *h, float2 *slopeOut,
|
||||
unsigned int width, unsigned int height) {
|
||||
unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
|
||||
unsigned int y = blockIdx.y * blockDim.y + threadIdx.y;
|
||||
unsigned int i = y * width + x;
|
||||
|
||||
float2 slope = make_float2(0.0f, 0.0f);
|
||||
|
||||
if ((x > 0) && (y > 0) && (x < width - 1) && (y < height - 1)) {
|
||||
slope.x = h[i + 1] - h[i - 1];
|
||||
slope.y = h[i + width] - h[i - width];
|
||||
}
|
||||
|
||||
slopeOut[i] = slope;
|
||||
}
|
||||
|
||||
// wrapper functions
|
||||
extern "C" void cudaGenerateSpectrumKernel(float2 *d_h0, float2 *d_ht,
|
||||
unsigned int in_width,
|
||||
unsigned int out_width,
|
||||
unsigned int out_height,
|
||||
float animTime, float patchSize) {
|
||||
dim3 block(8, 8, 1);
|
||||
dim3 grid(cuda_iDivUp(out_width, block.x), cuda_iDivUp(out_height, block.y),
|
||||
1);
|
||||
generateSpectrumKernel<<<grid, block>>>(d_h0, d_ht, in_width, out_width,
|
||||
out_height, animTime, patchSize);
|
||||
}
|
||||
|
||||
extern "C" void cudaUpdateHeightmapKernel(float *d_heightMap, float2 *d_ht,
|
||||
unsigned int width,
|
||||
unsigned int height, bool autoTest) {
|
||||
dim3 block(8, 8, 1);
|
||||
dim3 grid(cuda_iDivUp(width, block.x), cuda_iDivUp(height, block.y), 1);
|
||||
if (autoTest) {
|
||||
updateHeightmapKernel_y<<<grid, block>>>(d_heightMap, d_ht, width);
|
||||
} else {
|
||||
updateHeightmapKernel<<<grid, block>>>(d_heightMap, d_ht, width);
|
||||
}
|
||||
}
|
||||
|
||||
extern "C" void cudaCalculateSlopeKernel(float *hptr, float2 *slopeOut,
|
||||
unsigned int width,
|
||||
unsigned int height) {
|
||||
dim3 block(8, 8, 1);
|
||||
dim3 grid2(cuda_iDivUp(width, block.x), cuda_iDivUp(height, block.y), 1);
|
||||
calculateSlopeKernel<<<grid2, block>>>(hptr, slopeOut, width, height);
|
||||
}
|
||||
20
Samples/oceanFFT/oceanFFT_vs2017.sln
Normal file
20
Samples/oceanFFT/oceanFFT_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}") = "oceanFFT", "oceanFFT_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
|
||||
124
Samples/oceanFFT/oceanFFT_vs2017.vcxproj
Normal file
124
Samples/oceanFFT/oceanFFT_vs2017.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)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||
</PropertyGroup>
|
||||
<ItemGroup Label="ProjectConfigurations">
|
||||
<ProjectConfiguration Include="Debug|x64">
|
||||
<Configuration>Debug</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
<ProjectConfiguration Include="Release|x64">
|
||||
<Configuration>Release</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
</ItemGroup>
|
||||
<PropertyGroup Label="Globals">
|
||||
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||
<RootNamespace>oceanFFT_vs2017</RootNamespace>
|
||||
<ProjectName>oceanFFT</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(WindowsTargetPlatformVersion)'==''">
|
||||
<LatestTargetPlatformVersion>$([Microsoft.Build.Utilities.ToolLocationHelper]::GetLatestSDKTargetPlatformVersion('Windows', '10.0'))</LatestTargetPlatformVersion>
|
||||
<WindowsTargetPlatformVersion Condition="'$(WindowsTargetPlatformVersion)' == ''">$(LatestTargetPlatformVersion)</WindowsTargetPlatformVersion>
|
||||
<TargetPlatformVersion>$(WindowsTargetPlatformVersion)</TargetPlatformVersion>
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup>
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v141</PlatformToolset>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
|
||||
<UseDebugLibraries>true</UseDebugLibraries>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Release'">
|
||||
<WholeProgramOptimization>true</WholeProgramOptimization>
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
|
||||
<ImportGroup Label="ExtensionSettings">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.5.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
|
||||
</ImportGroup>
|
||||
<PropertyGroup Label="UserMacros" />
|
||||
<PropertyGroup>
|
||||
<IntDir>$(Platform)/$(Configuration)/</IntDir>
|
||||
<IncludePath>$(IncludePath)</IncludePath>
|
||||
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
|
||||
<CodeAnalysisRules />
|
||||
<CodeAnalysisRuleAssemblies />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Platform)'=='x64'">
|
||||
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
|
||||
</PropertyGroup>
|
||||
<ItemDefinitionGroup>
|
||||
<ClCompile>
|
||||
<WarningLevel>Level3</WarningLevel>
|
||||
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
|
||||
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cufft.lib;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>$(OutDir)/oceanFFT.exe</OutputFile>
|
||||
</Link>
|
||||
<CudaCompile>
|
||||
<CodeGeneration>compute_35,sm_35;compute_37,sm_37;compute_50,sm_50;compute_52,sm_52;compute_60,sm_60;compute_61,sm_61;compute_70,sm_70;compute_75,sm_75;compute_80,sm_80;compute_86,sm_86;</CodeGeneration>
|
||||
<AdditionalOptions>-Xcompiler "/wd 4819" %(AdditionalOptions)</AdditionalOptions>
|
||||
<Include>./;../../Common</Include>
|
||||
<Defines>WIN32</Defines>
|
||||
<AdditionalOptions>--threads 0</AdditionalOptions>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(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="'$(Platform)'=='x64'">
|
||||
<Link>
|
||||
<AdditionalDependencies>glew64.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
</Link>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="oceanFFT.cpp" />
|
||||
<CudaCompile Include="oceanFFT_kernel.cu" />
|
||||
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
20
Samples/oceanFFT/oceanFFT_vs2019.sln
Normal file
20
Samples/oceanFFT/oceanFFT_vs2019.sln
Normal file
@@ -0,0 +1,20 @@
|
||||
|
||||
Microsoft Visual Studio Solution File, Format Version 12.00
|
||||
# Visual Studio 2019
|
||||
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "oceanFFT", "oceanFFT_vs2019.vcxproj", "{997E0757-EA74-4A4E-A0FC-47D8C8831A15}"
|
||||
EndProject
|
||||
Global
|
||||
GlobalSection(SolutionConfigurationPlatforms) = preSolution
|
||||
Debug|x64 = Debug|x64
|
||||
Release|x64 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(ProjectConfigurationPlatforms) = postSolution
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.ActiveCfg = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Debug|x64.Build.0 = Debug|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.ActiveCfg = Release|x64
|
||||
{997E0757-EA74-4A4E-A0FC-47D8C8831A15}.Release|x64.Build.0 = Release|x64
|
||||
EndGlobalSection
|
||||
GlobalSection(SolutionProperties) = preSolution
|
||||
HideSolutionNode = FALSE
|
||||
EndGlobalSection
|
||||
EndGlobal
|
||||
120
Samples/oceanFFT/oceanFFT_vs2019.vcxproj
Normal file
120
Samples/oceanFFT/oceanFFT_vs2019.vcxproj
Normal file
@@ -0,0 +1,120 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
|
||||
<PropertyGroup>
|
||||
<CUDAPropsPath Condition="'$(CUDAPropsPath)'==''">$(VCTargetsPath)\BuildCustomizations</CUDAPropsPath>
|
||||
</PropertyGroup>
|
||||
<ItemGroup Label="ProjectConfigurations">
|
||||
<ProjectConfiguration Include="Debug|x64">
|
||||
<Configuration>Debug</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
<ProjectConfiguration Include="Release|x64">
|
||||
<Configuration>Release</Configuration>
|
||||
<Platform>x64</Platform>
|
||||
</ProjectConfiguration>
|
||||
</ItemGroup>
|
||||
<PropertyGroup Label="Globals">
|
||||
<ProjectGuid>{997E0757-EA74-4A4E-A0FC-47D8C8831A15}</ProjectGuid>
|
||||
<RootNamespace>oceanFFT_vs2019</RootNamespace>
|
||||
<ProjectName>oceanFFT</ProjectName>
|
||||
<CudaToolkitCustomDir />
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup>
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v142</PlatformToolset>
|
||||
<WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Debug'">
|
||||
<UseDebugLibraries>true</UseDebugLibraries>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Release'">
|
||||
<WholeProgramOptimization>true</WholeProgramOptimization>
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
|
||||
<ImportGroup Label="ExtensionSettings">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.5.props" />
|
||||
</ImportGroup>
|
||||
<ImportGroup Label="PropertySheets">
|
||||
<Import Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" />
|
||||
</ImportGroup>
|
||||
<PropertyGroup Label="UserMacros" />
|
||||
<PropertyGroup>
|
||||
<IntDir>$(Platform)/$(Configuration)/</IntDir>
|
||||
<IncludePath>$(IncludePath)</IncludePath>
|
||||
<CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
|
||||
<CodeAnalysisRules />
|
||||
<CodeAnalysisRuleAssemblies />
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Platform)'=='x64'">
|
||||
<OutDir>../../bin/win64/$(Configuration)/</OutDir>
|
||||
</PropertyGroup>
|
||||
<ItemDefinitionGroup>
|
||||
<ClCompile>
|
||||
<WarningLevel>Level3</WarningLevel>
|
||||
<PreprocessorDefinitions>WIN32;_MBCS;%(PreprocessorDefinitions)</PreprocessorDefinitions>
|
||||
<AdditionalIncludeDirectories>./;$(CudaToolkitDir)/include;../../Common;$(CudaToolkitIncludeDir);</AdditionalIncludeDirectories>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<SubSystem>Console</SubSystem>
|
||||
<AdditionalDependencies>cufft.lib;cudart_static.lib;freeglut.lib;kernel32.lib;user32.lib;gdi32.lib;winspool.lib;comdlg32.lib;advapi32.lib;shell32.lib;ole32.lib;oleaut32.lib;uuid.lib;odbc32.lib;odbccp32.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
||||
<AdditionalLibraryDirectories>$(CudaToolkitLibDir);../../Common/lib/$(PlatformName);</AdditionalLibraryDirectories>
|
||||
<OutputFile>$(OutDir)/oceanFFT.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="oceanFFT.cpp" />
|
||||
<CudaCompile Include="oceanFFT_kernel.cu" />
|
||||
|
||||
</ItemGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
||||
<ImportGroup Label="ExtensionTargets">
|
||||
<Import Project="$(CUDAPropsPath)\CUDA 11.5.targets" />
|
||||
</ImportGroup>
|
||||
</Project>
|
||||
Reference in New Issue
Block a user