mirror of
https://github.com/NVIDIA/cuda-samples.git
synced 2025-04-10 18:22:11 +01:00
Add basic CMake framework
This commit is contained in:
Rob Armstrong
parent
82bcada84c
commit
912f37963a
2
.gitignore
vendored
2
.gitignore
vendored
@ -1 +1 @@
|
||||
.vscode/*
|
||||
build
|
||||
|
||||
18
CMakeLists.txt
Normal file
18
CMakeLists.txt
Normal file
@ -0,0 +1,18 @@
|
||||
cmake_minimum_required(VERSION 3.20)
|
||||
|
||||
project(cuda-samples LANGUAGES CXX CUDA)
|
||||
|
||||
set(CMAKE_CXX_STANDARD 17)
|
||||
set(CMAKE_CXX_STANDARD_REQUIRED ON)
|
||||
|
||||
set(CMAKE_CUDA_STANDARD 17)
|
||||
set(CMAKE_CUDA_STANDARD_REQUIRED ON)
|
||||
|
||||
set(CMAKE_CUDA_ARCHITECTURES "native")
|
||||
if(CMAKE_BUILD_TYPE STREQUAL "Debug")
|
||||
# set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -G") # enable cuda-gdb (expensive)
|
||||
endif()
|
||||
|
||||
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --extended-lambda")
|
||||
|
||||
add_subdirectory(Samples)
|
||||
53
Samples/0_Introduction/CMakeLists.txt
Normal file
53
Samples/0_Introduction/CMakeLists.txt
Normal file
@ -0,0 +1,53 @@
|
||||
#add_subdirectory(UnifiedMemoryStreams)
|
||||
add_subdirectory(asyncAPI)
|
||||
#add_subdirectory(c++11_cuda)
|
||||
#add_subdirectory(clock)
|
||||
#add_subdirectory(clock_nvrtc)
|
||||
#add_subdirectory(concurrentKernels)
|
||||
#add_subdirectory(cppIntegration)
|
||||
#add_subdirectory(cppOverload)
|
||||
#add_subdirectory(cudaOpenMP)
|
||||
#add_subdirectory(fp16ScalarProduct)
|
||||
#add_subdirectory(matrixMul)
|
||||
#add_subdirectory(matrixMulDrv)
|
||||
#add_subdirectory(matrixMulDynlinkJIT)
|
||||
#add_subdirectory(matrixMul_nvrtc)
|
||||
#add_subdirectory(mergeSort)
|
||||
#add_subdirectory(simpleAWBarrier)
|
||||
#add_subdirectory(simpleAssert)
|
||||
#add_subdirectory(simpleAssert_nvrtc)
|
||||
#add_subdirectory(simpleAtomicIntrinsics)
|
||||
#add_subdirectory(simpleAtomicIntrinsics_nvrtc)
|
||||
#add_subdirectory(simpleAttributes)
|
||||
#add_subdirectory(simpleCUDA2GL)
|
||||
#add_subdirectory(simpleCallback)
|
||||
#add_subdirectory(simpleCooperativeGroups)
|
||||
#add_subdirectory(simpleCubemapTexture)
|
||||
#add_subdirectory(simpleDrvRuntime)
|
||||
#add_subdirectory(simpleHyperQ)
|
||||
#add_subdirectory(simpleIPC)
|
||||
#add_subdirectory(simpleLayeredTexture)
|
||||
#add_subdirectory(simpleMPI)
|
||||
#add_subdirectory(simpleMultiCopy)
|
||||
#add_subdirectory(simpleMultiGPU)
|
||||
#add_subdirectory(simpleOccupancy)
|
||||
#add_subdirectory(simpleP2P)
|
||||
#add_subdirectory(simplePitchLinearTexture)
|
||||
#add_subdirectory(simplePrintf)
|
||||
#add_subdirectory(simpleSeparateCompilation)
|
||||
#add_subdirectory(simpleStreams)
|
||||
#add_subdirectory(simpleSurfaceWrite)
|
||||
#add_subdirectory(simpleTemplates)
|
||||
#add_subdirectory(simpleTemplates_nvrtc)
|
||||
#add_subdirectory(simpleTexture)
|
||||
#add_subdirectory(simpleTexture3D)
|
||||
#add_subdirectory(simpleTextureDrv)
|
||||
#add_subdirectory(simpleVoteIntrinsics)
|
||||
#add_subdirectory(simpleVoteIntrinsics_nvrtc)
|
||||
#add_subdirectory(simpleZeroCopy)
|
||||
#add_subdirectory(systemWideAtomics)
|
||||
#add_subdirectory(template)
|
||||
#add_subdirectory(vectorAdd)
|
||||
#add_subdirectory(vectorAddDrv)
|
||||
#add_subdirectory(vectorAddMMAP)
|
||||
#add_subdirectory(vectorAdd_nvrtc)
|
||||
11
Samples/0_Introduction/asyncAPI/CMakeLists.txt
Normal file
11
Samples/0_Introduction/asyncAPI/CMakeLists.txt
Normal file
@ -0,0 +1,11 @@
|
||||
# Include directories and libraries
|
||||
include_directories(../../../Common)
|
||||
|
||||
# Source file
|
||||
set(SRC_FILES
|
||||
asyncAPI.cu
|
||||
)
|
||||
|
||||
# Add target for asyncAPI
|
||||
add_executable(asyncAPI ${SRC_FILES})
|
||||
set_target_properties(asyncAPI PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
|
||||
@ -1,18 +0,0 @@
|
||||
{
|
||||
"configurations": [
|
||||
{
|
||||
"name": "Linux",
|
||||
"includePath": [
|
||||
"${workspaceFolder}/**",
|
||||
"${workspaceFolder}/../../../Common"
|
||||
],
|
||||
"defines": [],
|
||||
"compilerPath": "/usr/local/cuda/bin/nvcc",
|
||||
"cStandard": "gnu17",
|
||||
"cppStandard": "gnu++14",
|
||||
"intelliSenseMode": "linux-gcc-x64",
|
||||
"configurationProvider": "ms-vscode.makefile-tools"
|
||||
}
|
||||
],
|
||||
"version": 4
|
||||
}
|
||||
@ -1,7 +0,0 @@
|
||||
{
|
||||
"recommendations": [
|
||||
"nvidia.nsight-vscode-edition",
|
||||
"ms-vscode.cpptools",
|
||||
"ms-vscode.makefile-tools"
|
||||
]
|
||||
}
|
||||
@ -1,10 +0,0 @@
|
||||
{
|
||||
"configurations": [
|
||||
{
|
||||
"name": "CUDA C++: Launch",
|
||||
"type": "cuda-gdb",
|
||||
"request": "launch",
|
||||
"program": "${workspaceFolder}/c++11_cuda"
|
||||
}
|
||||
]
|
||||
}
|
||||
@ -1,15 +0,0 @@
|
||||
{
|
||||
"version": "2.0.0",
|
||||
"tasks": [
|
||||
{
|
||||
"label": "sample",
|
||||
"type": "shell",
|
||||
"command": "make dbg=1",
|
||||
"problemMatcher": ["$nvcc"],
|
||||
"group": {
|
||||
"kind": "build",
|
||||
"isDefault": true
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@ -1,391 +0,0 @@
|
||||
################################################################################
|
||||
# Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved.
|
||||
#
|
||||
# Redistribution and use in source and binary forms, with or without
|
||||
# modification, are permitted provided that the following conditions
|
||||
# are met:
|
||||
# * Redistributions of source code must retain the above copyright
|
||||
# notice, this list of conditions and the following disclaimer.
|
||||
# * Redistributions in binary form must reproduce the above copyright
|
||||
# notice, this list of conditions and the following disclaimer in the
|
||||
# documentation and/or other materials provided with the distribution.
|
||||
# * Neither the name of NVIDIA CORPORATION nor the names of its
|
||||
# contributors may be used to endorse or promote products derived
|
||||
# from this software without specific prior written permission.
|
||||
#
|
||||
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
|
||||
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
||||
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
||||
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
#
|
||||
################################################################################
|
||||
#
|
||||
# Makefile project only supported on Mac OS X and Linux Platforms)
|
||||
#
|
||||
################################################################################
|
||||
|
||||
# Location of the CUDA Toolkit
|
||||
CUDA_PATH ?= /usr/local/cuda
|
||||
|
||||
##############################
|
||||
# start deprecated interface #
|
||||
##############################
|
||||
ifeq ($(x86_64),1)
|
||||
$(info WARNING - x86_64 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=x86_64 instead)
|
||||
TARGET_ARCH ?= x86_64
|
||||
endif
|
||||
ifeq ($(ARMv7),1)
|
||||
$(info WARNING - ARMv7 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=armv7l instead)
|
||||
TARGET_ARCH ?= armv7l
|
||||
endif
|
||||
ifeq ($(aarch64),1)
|
||||
$(info WARNING - aarch64 variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=aarch64 instead)
|
||||
TARGET_ARCH ?= aarch64
|
||||
endif
|
||||
ifeq ($(ppc64le),1)
|
||||
$(info WARNING - ppc64le variable has been deprecated)
|
||||
$(info WARNING - please use TARGET_ARCH=ppc64le instead)
|
||||
TARGET_ARCH ?= ppc64le
|
||||
endif
|
||||
ifneq ($(GCC),)
|
||||
$(info WARNING - GCC variable has been deprecated)
|
||||
$(info WARNING - please use HOST_COMPILER=$(GCC) instead)
|
||||
HOST_COMPILER ?= $(GCC)
|
||||
endif
|
||||
ifneq ($(abi),)
|
||||
$(error ERROR - abi variable has been removed)
|
||||
endif
|
||||
############################
|
||||
# end deprecated interface #
|
||||
############################
|
||||
|
||||
# architecture
|
||||
HOST_ARCH := $(shell uname -m)
|
||||
TARGET_ARCH ?= $(HOST_ARCH)
|
||||
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le armv7l))
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifneq (,$(filter $(TARGET_ARCH),x86_64 aarch64 sbsa ppc64le))
|
||||
TARGET_SIZE := 64
|
||||
else ifneq (,$(filter $(TARGET_ARCH),armv7l))
|
||||
TARGET_SIZE := 32
|
||||
endif
|
||||
else
|
||||
TARGET_SIZE := $(shell getconf LONG_BIT)
|
||||
endif
|
||||
else
|
||||
$(error ERROR - unsupported value $(TARGET_ARCH) for TARGET_ARCH!)
|
||||
endif
|
||||
|
||||
# sbsa and aarch64 systems look similar. Need to differentiate them at host level for now.
|
||||
ifeq ($(HOST_ARCH),aarch64)
|
||||
ifeq ($(CUDA_PATH)/targets/sbsa-linux,$(shell ls -1d $(CUDA_PATH)/targets/sbsa-linux 2>/dev/null))
|
||||
HOST_ARCH := sbsa
|
||||
TARGET_ARCH := sbsa
|
||||
endif
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq (,$(filter $(HOST_ARCH)-$(TARGET_ARCH),aarch64-armv7l x86_64-armv7l x86_64-aarch64 x86_64-sbsa x86_64-ppc64le))
|
||||
$(error ERROR - cross compiling from $(HOST_ARCH) to $(TARGET_ARCH) is not supported!)
|
||||
endif
|
||||
endif
|
||||
|
||||
# When on native aarch64 system with userspace of 32-bit, change TARGET_ARCH to armv7l
|
||||
ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_SIZE),aarch64-aarch64-32)
|
||||
TARGET_ARCH = armv7l
|
||||
endif
|
||||
|
||||
# operating system
|
||||
HOST_OS := $(shell uname -s 2>/dev/null | tr "[:upper:]" "[:lower:]")
|
||||
TARGET_OS ?= $(HOST_OS)
|
||||
ifeq (,$(filter $(TARGET_OS),linux darwin qnx android))
|
||||
$(error ERROR - unsupported value $(TARGET_OS) for TARGET_OS!)
|
||||
endif
|
||||
|
||||
# host compiler
|
||||
ifdef HOST_COMPILER
|
||||
CUSTOM_HOST_COMPILER = 1
|
||||
endif
|
||||
|
||||
ifeq ($(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
|
||||
|
||||
# Link flag for customized HOST_COMPILER with gcc realpath
|
||||
GCC_PATH := $(shell which gcc)
|
||||
ifeq ($(CUSTOM_HOST_COMPILER),1)
|
||||
ifneq ($(filter /%,$(HOST_COMPILER)),)
|
||||
ifneq ($(findstring gcc,$(HOST_COMPILER)),)
|
||||
ifneq ($(GCC_PATH),$(HOST_COMPILER))
|
||||
LDFLAGS += -lstdc++
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
ifeq ($(TARGET_OS),darwin)
|
||||
LDFLAGS += -rpath $(CUDA_PATH)/lib
|
||||
CCFLAGS += -arch $(HOST_ARCH)
|
||||
else ifeq ($(HOST_ARCH)-$(TARGET_ARCH)-$(TARGET_OS),x86_64-armv7l-linux)
|
||||
LDFLAGS += --dynamic-linker=/lib/ld-linux-armhf.so.3
|
||||
CCFLAGS += -mfloat-abi=hard
|
||||
else ifeq ($(TARGET_OS),android)
|
||||
LDFLAGS += -pie
|
||||
CCFLAGS += -fpie -fpic -fexceptions
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_ARCH),$(HOST_ARCH))
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
|
||||
ifneq ($(TARGET_FS),)
|
||||
GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
|
||||
ifeq ($(GCCVERSIONLTEQ46),1)
|
||||
CCFLAGS += --sysroot=$(TARGET_FS)
|
||||
endif
|
||||
LDFLAGS += --sysroot=$(TARGET_FS)
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/arm-linux-gnueabihf
|
||||
endif
|
||||
endif
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
|
||||
ifneq ($(TARGET_FS),)
|
||||
GCCVERSIONLTEQ46 := $(shell expr `$(HOST_COMPILER) -dumpversion` \<= 4.6)
|
||||
ifeq ($(GCCVERSIONLTEQ46),1)
|
||||
CCFLAGS += --sysroot=$(TARGET_FS)
|
||||
endif
|
||||
LDFLAGS += --sysroot=$(TARGET_FS)
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib -L$(TARGET_FS)/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/lib/aarch64-linux-gnu -L$(TARGET_FS)/lib/aarch64-linux-gnu
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib -L$(TARGET_FS)/usr/lib
|
||||
LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/aarch64-linux-gnu -L$(TARGET_FS)/usr/lib/aarch64-linux-gnu
|
||||
LDFLAGS += --unresolved-symbols=ignore-in-shared-libs
|
||||
CCFLAGS += -isystem=$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include -I$(TARGET_FS)/usr/include/libdrm
|
||||
CCFLAGS += -isystem=$(TARGET_FS)/usr/include/aarch64-linux-gnu -I$(TARGET_FS)/usr/include/aarch64-linux-gnu
|
||||
endif
|
||||
endif
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
|
||||
NVCCFLAGS += -D_QNX_SOURCE
|
||||
NVCCFLAGS += --qpp-config 8.3.0,gcc_ntoaarch64le
|
||||
CCFLAGS += -DWIN_INTERFACE_CUSTOM -I/usr/include/aarch64-qnx-gnu
|
||||
LDFLAGS += -lsocket
|
||||
LDFLAGS += -L/usr/lib/aarch64-qnx-gnu
|
||||
CCFLAGS += "-Wl\,-rpath-link\,/usr/lib/aarch64-qnx-gnu"
|
||||
ifdef TARGET_OVERRIDE
|
||||
LDFLAGS += -lslog2
|
||||
endif
|
||||
|
||||
ifneq ($(TARGET_FS),)
|
||||
LDFLAGS += -L$(TARGET_FS)/usr/lib
|
||||
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
|
||||
LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
|
||||
CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
|
||||
CCFLAGS += -I$(TARGET_FS)/../include
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
ifdef TARGET_OVERRIDE # cuda toolkit targets override
|
||||
NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
|
||||
endif
|
||||
|
||||
# Install directory of different arch
|
||||
CUDA_INSTALL_TARGET_DIR :=
|
||||
ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-gnueabihf/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),sbsa-linux)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/sbsa-linux/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-android)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-androideabi/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-android)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux-androideabi/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-qnx)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/ARMv7-linux-QNX/
|
||||
else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/aarch64-qnx/
|
||||
else ifeq ($(TARGET_ARCH),ppc64le)
|
||||
CUDA_INSTALL_TARGET_DIR = targets/ppc64le-linux/
|
||||
endif
|
||||
|
||||
# Debug build flags
|
||||
ifeq ($(dbg),1)
|
||||
NVCCFLAGS += -g -G
|
||||
BUILD_TYPE := debug
|
||||
else
|
||||
BUILD_TYPE := release
|
||||
endif
|
||||
|
||||
ALL_CCFLAGS :=
|
||||
ALL_CCFLAGS += $(NVCCFLAGS)
|
||||
ALL_CCFLAGS += $(EXTRA_NVCCFLAGS)
|
||||
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS))
|
||||
ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS))
|
||||
|
||||
SAMPLE_ENABLED := 1
|
||||
|
||||
# This sample is not supported on QNX
|
||||
ifeq ($(TARGET_OS),qnx)
|
||||
$(info >>> WARNING - c++11_cuda 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 :=
|
||||
|
||||
################################################################################
|
||||
|
||||
#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 $(GCCVERSION)` \>= 47000)
|
||||
ifneq ($(CUSTOM_HOST_COMPILER), 1)
|
||||
ifeq ($(IS_MIN_VERSION), 1)
|
||||
$(info >>> GCC Version is greater or equal to 4.7.0 <<<)
|
||||
else
|
||||
$(info >>> Waiving build. Minimum GCC version required is 4.7.0<<<)
|
||||
SAMPLE_ENABLED := 0
|
||||
endif
|
||||
else
|
||||
$(warning >>> Custom HOST_COMPILER set; skipping GCC version check. This may lead to unintended behavior. Please note the minimum equivalent GCC version is 4.7.0 <<<)
|
||||
endif
|
||||
endif
|
||||
|
||||
# Gencode arguments
|
||||
ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
|
||||
SMS ?= 53 61 70 72 75 80 86 87 90
|
||||
else
|
||||
SMS ?= 50 52 60 61 70 75 80 86 89 90
|
||||
endif
|
||||
|
||||
ifeq ($(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 += --std=c++11 --threads 0
|
||||
|
||||
ifeq ($(SAMPLE_ENABLED),0)
|
||||
EXEC ?= @echo "[@]"
|
||||
endif
|
||||
|
||||
################################################################################
|
||||
|
||||
# Target rules
|
||||
all: build
|
||||
|
||||
build: c++11_cuda
|
||||
|
||||
check.deps:
|
||||
ifeq ($(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
|
||||
|
||||
c++11_cuda.o:c++11_cuda.cu
|
||||
$(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
|
||||
|
||||
c++11_cuda: c++11_cuda.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
|
||||
$(EXEC) ./c++11_cuda
|
||||
|
||||
testrun: build
|
||||
|
||||
clean:
|
||||
rm -f c++11_cuda c++11_cuda.o
|
||||
rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/c++11_cuda
|
||||
|
||||
clobber: clean
|
||||
@ -1,82 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE entry SYSTEM "SamplesInfo.dtd">
|
||||
<entry>
|
||||
<name>c++11_cuda</name>
|
||||
<cflags>
|
||||
<flag>--std=c++11</flag>
|
||||
</cflags>
|
||||
<cuda_api_list>
|
||||
<toolkit>cudaMalloc</toolkit>
|
||||
<toolkit>cudaMemcpy</toolkit>
|
||||
<toolkit>cudaMemset</toolkit>
|
||||
<toolkit>cudaFree</toolkit>
|
||||
</cuda_api_list>
|
||||
<description><![CDATA[This sample demonstrates C++11 feature support in CUDA. It scans a input text file and prints no. of occurrences of x, y, z, w characters. ]]></description>
|
||||
<devicecompilation>whole</devicecompilation>
|
||||
<includepaths>
|
||||
<path>./</path>
|
||||
<path>../</path>
|
||||
<path>../../../Common</path>
|
||||
</includepaths>
|
||||
<keyconcepts>
|
||||
<concept level="advanced">CPP11 CUDA</concept>
|
||||
</keyconcepts>
|
||||
<keywords>
|
||||
<keyword>GPGPU</keyword>
|
||||
<keyword>CPP11</keyword>
|
||||
</keywords>
|
||||
<libraries>
|
||||
</libraries>
|
||||
<librarypaths>
|
||||
</librarypaths>
|
||||
<nsight_eclipse>true</nsight_eclipse>
|
||||
<primary_file>c++11_cuda.cu</primary_file>
|
||||
<required_dependencies>
|
||||
<dependency>CPP11</dependency>
|
||||
</required_dependencies>
|
||||
<scopes>
|
||||
<scope>1:CUDA Advanced Topics</scope>
|
||||
<scope>1:C++11 CUDA</scope>
|
||||
</scopes>
|
||||
<sm-arch>sm50</sm-arch>
|
||||
<sm-arch>sm52</sm-arch>
|
||||
<sm-arch>sm53</sm-arch>
|
||||
<sm-arch>sm60</sm-arch>
|
||||
<sm-arch>sm61</sm-arch>
|
||||
<sm-arch>sm70</sm-arch>
|
||||
<sm-arch>sm72</sm-arch>
|
||||
<sm-arch>sm75</sm-arch>
|
||||
<sm-arch>sm80</sm-arch>
|
||||
<sm-arch>sm86</sm-arch>
|
||||
<sm-arch>sm87</sm-arch>
|
||||
<sm-arch>sm89</sm-arch>
|
||||
<sm-arch>sm90</sm-arch>
|
||||
<supported_envs>
|
||||
<env>
|
||||
<arch>x86_64</arch>
|
||||
<platform>linux</platform>
|
||||
</env>
|
||||
<env>
|
||||
<arch>x86_64</arch>
|
||||
<platform>macosx</platform>
|
||||
</env>
|
||||
<env>
|
||||
<arch>arm</arch>
|
||||
</env>
|
||||
<env>
|
||||
<arch>sbsa</arch>
|
||||
</env>
|
||||
<env>
|
||||
<arch>ppc64le</arch>
|
||||
<platform>linux</platform>
|
||||
</env>
|
||||
<env>
|
||||
<platform>windows7</platform>
|
||||
</env>
|
||||
</supported_envs>
|
||||
<supported_sm_architectures>
|
||||
<include>all</include>
|
||||
</supported_sm_architectures>
|
||||
<title>C++11 CUDA</title>
|
||||
<type>exe</type>
|
||||
</entry>
|
||||
@ -1,74 +0,0 @@
|
||||
# c++11_cuda - C++11 CUDA
|
||||
|
||||
## Description
|
||||
|
||||
This sample demonstrates C++11 feature support in CUDA. It scans a input text file and prints no. of occurrences of x, y, z, w characters.
|
||||
|
||||
## Key Concepts
|
||||
|
||||
CPP11 CUDA
|
||||
|
||||
## Supported SM Architectures
|
||||
|
||||
[SM 5.0 ](https://developer.nvidia.com/cuda-gpus) [SM 5.2 ](https://developer.nvidia.com/cuda-gpus) [SM 5.3 ](https://developer.nvidia.com/cuda-gpus) [SM 6.0 ](https://developer.nvidia.com/cuda-gpus) [SM 6.1 ](https://developer.nvidia.com/cuda-gpus) [SM 7.0 ](https://developer.nvidia.com/cuda-gpus) [SM 7.2 ](https://developer.nvidia.com/cuda-gpus) [SM 7.5 ](https://developer.nvidia.com/cuda-gpus) [SM 8.0 ](https://developer.nvidia.com/cuda-gpus) [SM 8.6 ](https://developer.nvidia.com/cuda-gpus) [SM 8.7 ](https://developer.nvidia.com/cuda-gpus) [SM 8.9 ](https://developer.nvidia.com/cuda-gpus) [SM 9.0 ](https://developer.nvidia.com/cuda-gpus)
|
||||
|
||||
## Supported OSes
|
||||
|
||||
Linux, Windows
|
||||
|
||||
## Supported CPU Architecture
|
||||
|
||||
x86_64, ppc64le, armv7l
|
||||
|
||||
## CUDA APIs involved
|
||||
|
||||
### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
|
||||
cudaMalloc, cudaMemcpy, cudaMemset, cudaFree
|
||||
|
||||
## Dependencies needed to build/run
|
||||
[CPP11](../../../README.md#cpp11)
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
|
||||
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
|
||||
|
||||
## Build and Run
|
||||
|
||||
### Windows
|
||||
The Windows samples are built using the Visual Studio IDE. Solution files (.sln) are provided for each supported version of Visual Studio, using the format:
|
||||
```
|
||||
*_vs<version>.sln - for Visual Studio <version>
|
||||
```
|
||||
Each individual sample has its own set of solution files in its directory:
|
||||
|
||||
To build/examine all the samples at once, the complete solution files should be used. To build/examine a single sample, the individual sample solution files should be used.
|
||||
> **Note:** Some samples require that the Microsoft DirectX SDK (June 2010 or newer) be installed and that the VC++ directory paths are properly set up (**Tools > Options...**). Check DirectX Dependencies section for details."
|
||||
|
||||
### Linux
|
||||
The Linux samples are built using makefiles. To use the makefiles, change the current directory to the sample directory you wish to build, and run make:
|
||||
```
|
||||
$ cd <sample_dir>
|
||||
$ make
|
||||
```
|
||||
The samples makefiles can take advantage of certain options:
|
||||
* **TARGET_ARCH=<arch>** - cross-compile targeting a specific architecture. Allowed architectures are x86_64, ppc64le, armv7l.
|
||||
By default, TARGET_ARCH is set to HOST_ARCH. On a x86_64 machine, not setting TARGET_ARCH is the equivalent of setting TARGET_ARCH=x86_64.<br/>
|
||||
`$ make TARGET_ARCH=x86_64` <br/> `$ make TARGET_ARCH=ppc64le` <br/> `$ make TARGET_ARCH=armv7l` <br/>
|
||||
See [here](http://docs.nvidia.com/cuda/cuda-samples/index.html#cross-samples) for more details.
|
||||
* **dbg=1** - build with debug symbols
|
||||
```
|
||||
$ make dbg=1
|
||||
```
|
||||
* **SMS="A B ..."** - override the SM architectures for which the sample will be built, where `"A B ..."` is a space-delimited list of SM architectures. For example, to generate SASS for SM 50 and SM 60, use `SMS="50 60"`.
|
||||
```
|
||||
$ make SMS="50 60"
|
||||
```
|
||||
|
||||
* **HOST_COMPILER=<host_compiler>** - override the default g++ host compiler. See the [Linux Installation Guide](http://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#system-requirements) for a list of supported host compilers.
|
||||
```
|
||||
$ make HOST_COMPILER=g++
|
||||
```
|
||||
|
||||
## References (for more details)
|
||||
|
||||
@ -1,140 +0,0 @@
|
||||
/* Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
* * Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* * Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in the
|
||||
* documentation and/or other materials provided with the distribution.
|
||||
* * Neither the name of NVIDIA CORPORATION nor the names of its
|
||||
* contributors may be used to endorse or promote products derived
|
||||
* from this software without specific prior written permission.
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
|
||||
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
||||
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
||||
* OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
*/
|
||||
|
||||
#include <thrust/device_ptr.h>
|
||||
#include <thrust/count.h>
|
||||
#include <thrust/execution_policy.h>
|
||||
|
||||
#include <iostream>
|
||||
#include <helper_cuda.h>
|
||||
|
||||
/////////////////////////////////////////////////////////////////
|
||||
// Some utility code to define grid_stride_range
|
||||
// Normally this would be in a header but it's here
|
||||
// for didactic purposes. Uses
|
||||
#include "range.hpp"
|
||||
using namespace util::lang;
|
||||
|
||||
// type alias to simplify typing...
|
||||
template <typename T>
|
||||
using step_range = typename range_proxy<T>::step_range_proxy;
|
||||
|
||||
template <typename T>
|
||||
__device__ step_range<T> grid_stride_range(T begin, T end) {
|
||||
begin += blockDim.x * blockIdx.x + threadIdx.x;
|
||||
return range(begin, end).step(gridDim.x * blockDim.x);
|
||||
}
|
||||
/////////////////////////////////////////////////////////////////
|
||||
|
||||
template <typename T, typename Predicate>
|
||||
__device__ void count_if(int *count, T *data, int n, Predicate p) {
|
||||
for (auto i : grid_stride_range(0, n)) {
|
||||
if (p(data[i])) atomicAdd(count, 1);
|
||||
}
|
||||
}
|
||||
|
||||
// Use count_if with a lambda function that searches for x, y, z or w
|
||||
// Note the use of range-based for loop and initializer_list inside the functor
|
||||
// We use auto so we don't have to know the type of the functor or array
|
||||
__global__ void xyzw_frequency(int *count, char *text, int n) {
|
||||
const char letters[]{'x', 'y', 'z', 'w'};
|
||||
|
||||
count_if(count, text, n, [&](char c) {
|
||||
for (const auto x : letters)
|
||||
if (c == x) return true;
|
||||
return false;
|
||||
});
|
||||
}
|
||||
|
||||
__global__ void xyzw_frequency_thrust_device(int *count, char *text, int n) {
|
||||
const char letters[]{'x', 'y', 'z', 'w'};
|
||||
*count = thrust::count_if(thrust::device, text, text + n, [=](char c) {
|
||||
for (const auto x : letters)
|
||||
if (c == x) return true;
|
||||
return false;
|
||||
});
|
||||
}
|
||||
|
||||
// a bug in Thrust 1.8 causes warnings when this is uncommented
|
||||
// so commented out by default -- fixed in Thrust master branch
|
||||
#if 0
|
||||
void xyzw_frequency_thrust_host(int *count, char *text, int n)
|
||||
{
|
||||
const char letters[] { 'x','y','z','w' };
|
||||
*count = thrust::count_if(thrust::host, text, text+n, [&](char c) {
|
||||
for (const auto x : letters)
|
||||
if (c == x) return true;
|
||||
return false;
|
||||
});
|
||||
}
|
||||
#endif
|
||||
|
||||
int main(int argc, char **argv) {
|
||||
const char *filename = sdkFindFilePath("warandpeace.txt", argv[0]);
|
||||
|
||||
int numBytes = 16 * 1048576;
|
||||
char *h_text = (char *)malloc(numBytes);
|
||||
|
||||
// find first CUDA device
|
||||
int devID = findCudaDevice(argc, (const char **)argv);
|
||||
|
||||
char *d_text;
|
||||
checkCudaErrors(cudaMalloc((void **)&d_text, numBytes));
|
||||
|
||||
FILE *fp = fopen(filename, "r");
|
||||
if (fp == NULL) {
|
||||
printf("Cannot find the input text file\n. Exiting..\n");
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
int len = (int)fread(h_text, sizeof(char), numBytes, fp);
|
||||
fclose(fp);
|
||||
std::cout << "Read " << len << " byte corpus from " << filename << std::endl;
|
||||
|
||||
checkCudaErrors(cudaMemcpy(d_text, h_text, len, cudaMemcpyHostToDevice));
|
||||
|
||||
int count = 0;
|
||||
int *d_count;
|
||||
checkCudaErrors(cudaMalloc(&d_count, sizeof(int)));
|
||||
checkCudaErrors(cudaMemset(d_count, 0, sizeof(int)));
|
||||
|
||||
// Try uncommenting one kernel call at a time
|
||||
xyzw_frequency<<<8, 256>>>(d_count, d_text, len);
|
||||
xyzw_frequency_thrust_device<<<1, 1>>>(d_count, d_text, len);
|
||||
checkCudaErrors(
|
||||
cudaMemcpy(&count, d_count, sizeof(int), cudaMemcpyDeviceToHost));
|
||||
|
||||
// xyzw_frequency_thrust_host(&count, h_text, len);
|
||||
|
||||
std::cout << "counted " << count
|
||||
<< " instances of 'x', 'y', 'z', or 'w' in \"" << filename << "\""
|
||||
<< std::endl;
|
||||
|
||||
checkCudaErrors(cudaFree(d_count));
|
||||
checkCudaErrors(cudaFree(d_text));
|
||||
|
||||
return EXIT_SUCCESS;
|
||||
}
|
||||
@ -1,279 +0,0 @@
|
||||
/* Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
* * Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* * Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in the
|
||||
* documentation and/or other materials provided with the distribution.
|
||||
* * Neither the name of NVIDIA CORPORATION nor the names of its
|
||||
* contributors may be used to endorse or promote products derived
|
||||
* from this software without specific prior written permission.
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
|
||||
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
||||
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
||||
* OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
*/
|
||||
|
||||
#ifndef UTIL_LANG_RANGE_HPP
|
||||
#define UTIL_LANG_RANGE_HPP
|
||||
|
||||
#include <iterator>
|
||||
#include <type_traits>
|
||||
|
||||
// Make these ranges usable inside CUDA C++ device code
|
||||
#ifdef __CUDACC__
|
||||
#define DEVICE_CALLABLE __host__ __device__
|
||||
#else
|
||||
#define DEVICE_CALLABLE
|
||||
#endif
|
||||
|
||||
namespace util {
|
||||
namespace lang {
|
||||
|
||||
namespace detail {
|
||||
|
||||
template <typename T>
|
||||
struct range_iter_base : std::iterator<std::input_iterator_tag, T> {
|
||||
DEVICE_CALLABLE
|
||||
range_iter_base(T current) : current(current) {}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
T operator*() const { return current; }
|
||||
|
||||
DEVICE_CALLABLE
|
||||
T const* operator->() const { return ¤t; }
|
||||
|
||||
DEVICE_CALLABLE
|
||||
range_iter_base& operator++() {
|
||||
++current;
|
||||
return *this;
|
||||
}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
range_iter_base operator++(int) {
|
||||
auto copy = *this;
|
||||
++*this;
|
||||
return copy;
|
||||
}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
bool operator==(range_iter_base const& other) const {
|
||||
return current == other.current;
|
||||
}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
bool operator!=(range_iter_base const& other) const {
|
||||
return not(*this == other);
|
||||
}
|
||||
|
||||
protected:
|
||||
T current;
|
||||
};
|
||||
|
||||
} // namespace detail
|
||||
|
||||
template <typename T>
|
||||
struct range_proxy {
|
||||
struct iter : detail::range_iter_base<T> {
|
||||
DEVICE_CALLABLE
|
||||
iter(T current) : detail::range_iter_base<T>(current) {}
|
||||
};
|
||||
|
||||
struct step_range_proxy {
|
||||
struct iter : detail::range_iter_base<T> {
|
||||
DEVICE_CALLABLE
|
||||
iter(T current, T step)
|
||||
: detail::range_iter_base<T>(current), step(step) {}
|
||||
|
||||
using detail::range_iter_base<T>::current;
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter& operator++() {
|
||||
current += step;
|
||||
return *this;
|
||||
}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter operator++(int) {
|
||||
auto copy = *this;
|
||||
++*this;
|
||||
return copy;
|
||||
}
|
||||
|
||||
// Loses commutativity. Iterator-based ranges are simply broken. :-(
|
||||
DEVICE_CALLABLE
|
||||
bool operator==(iter const& other) const {
|
||||
return step > 0 ? current >= other.current : current < other.current;
|
||||
}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
bool operator!=(iter const& other) const { return !(*this == other); }
|
||||
|
||||
private:
|
||||
T step;
|
||||
};
|
||||
|
||||
DEVICE_CALLABLE
|
||||
step_range_proxy(T begin, T end, T step)
|
||||
: begin_(begin, step), end_(end, step) {}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter begin() const { return begin_; }
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter end() const { return end_; }
|
||||
|
||||
private:
|
||||
iter begin_;
|
||||
iter end_;
|
||||
};
|
||||
|
||||
DEVICE_CALLABLE
|
||||
range_proxy(T begin, T end) : begin_(begin), end_(end) {}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
step_range_proxy step(T step) { return {*begin_, *end_, step}; }
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter begin() const { return begin_; }
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter end() const { return end_; }
|
||||
|
||||
private:
|
||||
iter begin_;
|
||||
iter end_;
|
||||
};
|
||||
|
||||
template <typename T>
|
||||
struct infinite_range_proxy {
|
||||
struct iter : detail::range_iter_base<T> {
|
||||
DEVICE_CALLABLE
|
||||
iter(T current = T()) : detail::range_iter_base<T>(current) {}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
bool operator==(iter const&) const { return false; }
|
||||
|
||||
DEVICE_CALLABLE
|
||||
bool operator!=(iter const&) const { return true; }
|
||||
};
|
||||
|
||||
struct step_range_proxy {
|
||||
struct iter : detail::range_iter_base<T> {
|
||||
DEVICE_CALLABLE
|
||||
iter(T current = T(), T step = T())
|
||||
: detail::range_iter_base<T>(current), step(step) {}
|
||||
|
||||
using detail::range_iter_base<T>::current;
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter& operator++() {
|
||||
current += step;
|
||||
return *this;
|
||||
}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter operator++(int) {
|
||||
auto copy = *this;
|
||||
++*this;
|
||||
return copy;
|
||||
}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
bool operator==(iter const&) const { return false; }
|
||||
|
||||
DEVICE_CALLABLE
|
||||
bool operator!=(iter const&) const { return true; }
|
||||
|
||||
private:
|
||||
T step;
|
||||
};
|
||||
|
||||
DEVICE_CALLABLE
|
||||
step_range_proxy(T begin, T step) : begin_(begin, step) {}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter begin() const { return begin_; }
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter end() const { return iter(); }
|
||||
|
||||
private:
|
||||
iter begin_;
|
||||
};
|
||||
|
||||
DEVICE_CALLABLE
|
||||
infinite_range_proxy(T begin) : begin_(begin) {}
|
||||
|
||||
DEVICE_CALLABLE
|
||||
step_range_proxy step(T step) { return step_range_proxy(*begin_, step); }
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter begin() const { return begin_; }
|
||||
|
||||
DEVICE_CALLABLE
|
||||
iter end() const { return iter(); }
|
||||
|
||||
private:
|
||||
iter begin_;
|
||||
};
|
||||
|
||||
template <typename T>
|
||||
DEVICE_CALLABLE range_proxy<T> range(T begin, T end) {
|
||||
return {begin, end};
|
||||
}
|
||||
|
||||
template <typename T>
|
||||
DEVICE_CALLABLE infinite_range_proxy<T> range(T begin) {
|
||||
return {begin};
|
||||
}
|
||||
|
||||
namespace traits {
|
||||
|
||||
template <typename C>
|
||||
struct has_size {
|
||||
template <typename T>
|
||||
static constexpr auto check(T*) ->
|
||||
typename std::is_integral<decltype(std::declval<T const>().size())>::type;
|
||||
|
||||
template <typename>
|
||||
static constexpr auto check(...) -> std::false_type;
|
||||
|
||||
using type = decltype(check<C>(0));
|
||||
static constexpr bool value = type::value;
|
||||
};
|
||||
|
||||
} // namespace traits
|
||||
|
||||
template <typename C,
|
||||
typename = typename std::enable_if<traits::has_size<C>::value>>
|
||||
DEVICE_CALLABLE auto indices(C const& cont)
|
||||
-> range_proxy<decltype(cont.size())> {
|
||||
return {0, cont.size()};
|
||||
}
|
||||
|
||||
template <typename T, std::size_t N>
|
||||
DEVICE_CALLABLE range_proxy<std::size_t> indices(T(&)[N]) {
|
||||
return {0, N};
|
||||
}
|
||||
|
||||
template <typename T>
|
||||
range_proxy<typename std::initializer_list<T>::size_type> DEVICE_CALLABLE
|
||||
indices(std::initializer_list<T>&& cont) {
|
||||
return {0, cont.size()};
|
||||
}
|
||||
}
|
||||
} // namespace util::lang
|
||||
|
||||
#endif // ndef UTIL_LANG_RANGE_HPP
|
||||
File diff suppressed because it is too large
Load Diff
1
Samples/CMakeLists.txt
Normal file
1
Samples/CMakeLists.txt
Normal file
@ -0,0 +1 @@
|
||||
add_subdirectory(0_Introduction)
|
||||
Loading…
x
Reference in New Issue
Block a user