diff --git a/CHANGELOG.md b/CHANGELOG.md
index 1b3dc904..c18a8cc4 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,13 +1,15 @@
## Changelog
### CUDA 12.8
+* Updated build system across the repository to CMake. Removed Visual Studio project files and Makefiles.
* Removed the following outdated samples:
* `0_Introduction`
* `c++11_cuda` demonstrating CUDA and C++ 11 interoperability (reason: obsolete)
* `concurrentKernels` demonstrating the ability to run multiple kernels simultaneously (reason: obsolete)
* `cppIntegration` demonstrating calling between .cu and .cpp files (reason: obsolete)
* `cppOverload` demonstrating C++ function overloading (reason: obsolete)
-
+ * `simpleSeparateCompilation` demonstrating NVCC compilation to a static library (reason: trivial)
+ *
### CUDA 12.5
diff --git a/Samples/0_Introduction/CMakeLists.txt b/Samples/0_Introduction/CMakeLists.txt
index 29183940..4ba7efdd 100644
--- a/Samples/0_Introduction/CMakeLists.txt
+++ b/Samples/0_Introduction/CMakeLists.txt
@@ -30,7 +30,6 @@ add_subdirectory(simpleOccupancy)
add_subdirectory(simpleP2P)
add_subdirectory(simplePitchLinearTexture)
add_subdirectory(simplePrintf)
-#add_subdirectory(simpleSeparateCompilation)
add_subdirectory(simpleStreams)
add_subdirectory(simpleSurfaceWrite)
#add_subdirectory(simpleTemplates)
diff --git a/Samples/0_Introduction/simpleSeparateCompilation/.vscode/c_cpp_properties.json b/Samples/0_Introduction/simpleSeparateCompilation/.vscode/c_cpp_properties.json
deleted file mode 100644
index f0066b0f..00000000
--- a/Samples/0_Introduction/simpleSeparateCompilation/.vscode/c_cpp_properties.json
+++ /dev/null
@@ -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
-}
diff --git a/Samples/0_Introduction/simpleSeparateCompilation/.vscode/extensions.json b/Samples/0_Introduction/simpleSeparateCompilation/.vscode/extensions.json
deleted file mode 100644
index c7eb54dc..00000000
--- a/Samples/0_Introduction/simpleSeparateCompilation/.vscode/extensions.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
- "recommendations": [
- "nvidia.nsight-vscode-edition",
- "ms-vscode.cpptools",
- "ms-vscode.makefile-tools"
- ]
-}
diff --git a/Samples/0_Introduction/simpleSeparateCompilation/.vscode/launch.json b/Samples/0_Introduction/simpleSeparateCompilation/.vscode/launch.json
deleted file mode 100644
index 2fafa675..00000000
--- a/Samples/0_Introduction/simpleSeparateCompilation/.vscode/launch.json
+++ /dev/null
@@ -1,10 +0,0 @@
-{
- "configurations": [
- {
- "name": "CUDA C++: Launch",
- "type": "cuda-gdb",
- "request": "launch",
- "program": "${workspaceFolder}/simpleSeparateCompilation"
- }
- ]
-}
diff --git a/Samples/0_Introduction/simpleSeparateCompilation/.vscode/tasks.json b/Samples/0_Introduction/simpleSeparateCompilation/.vscode/tasks.json
deleted file mode 100644
index 4509aeb1..00000000
--- a/Samples/0_Introduction/simpleSeparateCompilation/.vscode/tasks.json
+++ /dev/null
@@ -1,15 +0,0 @@
-{
- "version": "2.0.0",
- "tasks": [
- {
- "label": "sample",
- "type": "shell",
- "command": "make dbg=1",
- "problemMatcher": ["$nvcc"],
- "group": {
- "kind": "build",
- "isDefault": true
- }
- }
- ]
-}
diff --git a/Samples/0_Introduction/simpleSeparateCompilation/Makefile b/Samples/0_Introduction/simpleSeparateCompilation/Makefile
deleted file mode 100644
index 7e16c0c0..00000000
--- a/Samples/0_Introduction/simpleSeparateCompilation/Makefile
+++ /dev/null
@@ -1,363 +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
- NVCCFLAGS += -arbin $(QNX_HOST)/usr/bin/aarch64-unknown-nto-qnx7.1.0-ar
- ifneq ($(TARGET_FS),)
- LDFLAGS += -L$(TARGET_FS)/usr/lib
- CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/lib"
- LDFLAGS += -L$(TARGET_FS)/usr/libnvidia
- CCFLAGS += "-Wl\,-rpath-link\,$(TARGET_FS)/usr/libnvidia"
- CCFLAGS += -I$(TARGET_FS)/../include
- endif
- endif
-endif
-
-ifdef TARGET_OVERRIDE # cuda toolkit targets override
- NVCCFLAGS += -target-dir $(TARGET_OVERRIDE)
-endif
-
-# Install directory of different arch
-CUDA_INSTALL_TARGET_DIR :=
-ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-linux)
- CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-gnueabihf/
-else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-linux)
- CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux/
-else ifeq ($(TARGET_ARCH)-$(TARGET_OS),sbsa-linux)
- CUDA_INSTALL_TARGET_DIR = targets/sbsa-linux/
-else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-android)
- CUDA_INSTALL_TARGET_DIR = targets/armv7-linux-androideabi/
-else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-android)
- CUDA_INSTALL_TARGET_DIR = targets/aarch64-linux-androideabi/
-else ifeq ($(TARGET_ARCH)-$(TARGET_OS),armv7l-qnx)
- CUDA_INSTALL_TARGET_DIR = targets/ARMv7-linux-QNX/
-else ifeq ($(TARGET_ARCH)-$(TARGET_OS),aarch64-qnx)
- CUDA_INSTALL_TARGET_DIR = targets/aarch64-qnx/
-else ifeq ($(TARGET_ARCH),ppc64le)
- CUDA_INSTALL_TARGET_DIR = targets/ppc64le-linux/
-endif
-
-# Debug build flags
-ifeq ($(dbg),1)
- NVCCFLAGS += -g -G
- BUILD_TYPE := debug
-else
- BUILD_TYPE := release
-endif
-
-ALL_CCFLAGS :=
-ALL_CCFLAGS += $(NVCCFLAGS)
-ALL_CCFLAGS += $(EXTRA_NVCCFLAGS)
-ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS))
-ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS))
-
-SAMPLE_ENABLED := 1
-
-ALL_LDFLAGS :=
-ALL_LDFLAGS += $(ALL_CCFLAGS)
-ALL_LDFLAGS += $(addprefix -Xlinker ,$(LDFLAGS))
-ALL_LDFLAGS += $(addprefix -Xlinker ,$(EXTRA_LDFLAGS))
-
-# Common includes and paths for CUDA
-INCLUDES := -I../../../Common
-LIBRARIES :=
-
-################################################################################
-
-# Gencode arguments
-ifeq ($(TARGET_ARCH),$(filter $(TARGET_ARCH),armv7l aarch64 sbsa))
-SMS ?= 53 61 70 72 75 80 86 87 90
-else
-SMS ?= 50 52 60 61 70 75 80 86 89 90
-endif
-
-ifeq ($(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 += -dc --threads 0 --std=c++11
-
-ifeq ($(SAMPLE_ENABLED),0)
-EXEC ?= @echo "[@]"
-endif
-
-################################################################################
-
-# Target rules
-all: build
-
-build: simpleSeparateCompilation
-
-check.deps:
-ifeq ($(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
-
-simpleDeviceLibrary.o:simpleDeviceLibrary.cu
- $(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
-
-simpleSeparateCompilation.o:simpleSeparateCompilation.cu
- $(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
-
-simpleDeviceLibrary.a:simpleDeviceLibrary.o
- $(EXEC) $(NVCC) $(ALL_LDFLAGS) -lib -o $@ $< $(LIBRARIES)
-
-simpleSeparateCompilation: simpleDeviceLibrary.a simpleSeparateCompilation.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
- $(EXEC) ./simpleSeparateCompilation
-
-testrun: build
-
-clean:
- rm -f simpleSeparateCompilation simpleDeviceLibrary.o simpleSeparateCompilation.o simpleDeviceLibrary.a
- rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/simpleSeparateCompilation
-
-clobber: clean
diff --git a/Samples/0_Introduction/simpleSeparateCompilation/NsightEclipse.xml b/Samples/0_Introduction/simpleSeparateCompilation/NsightEclipse.xml
deleted file mode 100644
index 28f1a483..00000000
--- a/Samples/0_Introduction/simpleSeparateCompilation/NsightEclipse.xml
+++ /dev/null
@@ -1,87 +0,0 @@
-
-
-
- simpleSeparateCompilation
-
- -dc
-
-
-
- simpleDeviceLibrary.o
- simpleDeviceLibrary.a
-
-
-
- cudaMemcpy
- cudaMemcpyFromSymbol
- cudaFree
- cudaGetLastError
- cudaMalloc
-
-
- separate
-
- settings.nvlink
-
-
- ./
- ../
- ../../../Common
-
-
- Separate Compilation
-
-
- GPGPU
-
-
-
-
-
- true
- simpleSeparateCompilation.cu
-
- 1:CUDA Basic Topics
-
- sm50
- sm52
- sm53
- sm60
- sm61
- sm70
- sm72
- sm75
- sm80
- sm86
- sm87
- sm89
- sm90
-
-
- x86_64
- linux
-
-
- windows7
-
-
- x86_64
- macosx
-
-
- arm
-
-
- sbsa
-
-
- ppc64le
- linux
-
-
-
- all
-
- Simple Static GPU Device Library
- exe
-
diff --git a/Samples/0_Introduction/simpleSeparateCompilation/README.md b/Samples/0_Introduction/simpleSeparateCompilation/README.md
deleted file mode 100644
index 0fc29062..00000000
--- a/Samples/0_Introduction/simpleSeparateCompilation/README.md
+++ /dev/null
@@ -1,70 +0,0 @@
-# simpleSeparateCompilation - Simple Static GPU Device Library
-
-## Description
-
-This sample demonstrates a CUDA 5.0 feature, the ability to create a GPU device static library and use it within another CUDA kernel. This example demonstrates how to pass in a GPU device function (from the GPU device static library) as a function pointer to be called. This sample requires devices with compute capability 2.0 or higher.
-
-## Key Concepts
-
-Separate Compilation
-
-## 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)
-cudaMemcpy, cudaMemcpyFromSymbol, cudaFree, cudaGetLastError, cudaMalloc
-
-## Prerequisites
-
-Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
-
-## Build and Run
-
-### Windows
-The Windows samples are built using the Visual Studio IDE. Solution files (.sln) are provided for each supported version of Visual Studio, using the format:
-```
-*_vs.sln - for Visual Studio
-```
-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
-$ make
-```
-The samples makefiles can take advantage of certain options:
-* **TARGET_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.
-`$ make TARGET_ARCH=x86_64`
`$ make TARGET_ARCH=ppc64le`
`$ make TARGET_ARCH=armv7l`
- 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=** - 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)
-
diff --git a/Samples/0_Introduction/simpleSeparateCompilation/simpleDeviceLibrary.cu b/Samples/0_Introduction/simpleSeparateCompilation/simpleDeviceLibrary.cu
deleted file mode 100644
index 5f9509ee..00000000
--- a/Samples/0_Introduction/simpleSeparateCompilation/simpleDeviceLibrary.cu
+++ /dev/null
@@ -1,30 +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.
- */
-
-__device__ float multiplyByTwo(float number) { return number * 2.0f; }
-
-__device__ float divideByTwo(float number) { return number * 0.5f; }
diff --git a/Samples/0_Introduction/simpleSeparateCompilation/simpleDeviceLibrary.cuh b/Samples/0_Introduction/simpleSeparateCompilation/simpleDeviceLibrary.cuh
deleted file mode 100644
index 0df50368..00000000
--- a/Samples/0_Introduction/simpleSeparateCompilation/simpleDeviceLibrary.cuh
+++ /dev/null
@@ -1,35 +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 SIMPLE_DEVICE_LIBRARY_CUH
-#define SIMPLE_DEVICE_LIBRARY_CUH
-
-extern __device__ float multiplyByTwo(float number);
-
-extern __device__ float divideByTwo(float number);
-
-#endif /* SIMPLE_DEVICE_LIBRARY_CUH */
diff --git a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation.cu b/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation.cu
deleted file mode 100644
index 128fa3ed..00000000
--- a/Samples/0_Introduction/simpleSeparateCompilation/simpleSeparateCompilation.cu
+++ /dev/null
@@ -1,162 +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.
- */
-
-// System includes.
-#include
-#include
-
-// STL.
-#include
-
-// CUDA runtime.
-#include
-
-// Helper functions and utilities to work with CUDA.
-#include
-#include
-
-// Device library includes.
-#include "simpleDeviceLibrary.cuh"
-
-using std::cout;
-using std::endl;
-
-using std::vector;
-
-#define EPS 1e-5
-
-typedef unsigned int uint;
-typedef float (*deviceFunc)(float);
-
-const char *sampleName = "simpleSeparateCompilation";
-
-////////////////////////////////////////////////////////////////////////////////
-// Auto-Verification Code
-bool testResult = true;
-
-////////////////////////////////////////////////////////////////////////////////
-// Static device pointers to __device__ functions.
-__device__ deviceFunc dMultiplyByTwoPtr = multiplyByTwo;
-__device__ deviceFunc dDivideByTwoPtr = divideByTwo;
-
-////////////////////////////////////////////////////////////////////////////////
-// Kernels
-////////////////////////////////////////////////////////////////////////////////
-//! Transforms vector.
-//! Applies the __device__ function "f" to each element of the vector "v".
-////////////////////////////////////////////////////////////////////////////////
-__global__ void transformVector(float *v, deviceFunc f, uint size) {
- uint tid = blockIdx.x * blockDim.x + threadIdx.x;
-
- if (tid < size) {
- v[tid] = (*f)(v[tid]);
- }
-}
-
-////////////////////////////////////////////////////////////////////////////////
-// Declaration, forward
-void runTest(int argc, const char **argv);
-
-////////////////////////////////////////////////////////////////////////////////
-// Program main
-////////////////////////////////////////////////////////////////////////////////
-int main(int argc, char **argv) {
- cout << sampleName << " starting..." << endl;
-
- runTest(argc, (const char **)argv);
-
- cout << sampleName << " completed, returned " << (testResult ? "OK" : "ERROR")
- << endl;
-
- exit(testResult ? EXIT_SUCCESS : EXIT_FAILURE);
-}
-
-void runTest(int argc, const char **argv) {
- try {
- // This will pick the best possible CUDA capable device.
- findCudaDevice(argc, (const char **)argv);
-
- // Create host vector.
- const uint kVectorSize = 1000;
-
- vector hVector(kVectorSize);
-
- for (uint i = 0; i < kVectorSize; ++i) {
- hVector[i] = rand() / static_cast(RAND_MAX);
- }
-
- // Create and populate device vector.
- float *dVector;
- checkCudaErrors(cudaMalloc(&dVector, kVectorSize * sizeof(float)));
-
- checkCudaErrors(cudaMemcpy(dVector, &hVector[0],
- kVectorSize * sizeof(float),
- cudaMemcpyHostToDevice));
-
- // Kernel configuration, where a one-dimensional
- // grid and one-dimensional blocks are configured.
- const int nThreads = 1024;
- const int nBlocks = 1;
-
- dim3 dimGrid(nBlocks);
- dim3 dimBlock(nThreads);
-
- // Test library functions.
- deviceFunc hFunctionPtr;
-
- cudaMemcpyFromSymbol(&hFunctionPtr, dMultiplyByTwoPtr, sizeof(deviceFunc));
- transformVector<<>>(dVector, hFunctionPtr, kVectorSize);
- checkCudaErrors(cudaGetLastError());
-
- cudaMemcpyFromSymbol(&hFunctionPtr, dDivideByTwoPtr, sizeof(deviceFunc));
- transformVector<<>>(dVector, hFunctionPtr, kVectorSize);
- checkCudaErrors(cudaGetLastError());
-
- // Download results.
- vector hResultVector(kVectorSize);
-
- checkCudaErrors(cudaMemcpy(&hResultVector[0], dVector,
- kVectorSize * sizeof(float),
- cudaMemcpyDeviceToHost));
-
- // Check results.
- for (int i = 0; i < kVectorSize; ++i) {
- if (fabs(hVector[i] - hResultVector[i]) > EPS) {
- cout << "Computations were incorrect..." << endl;
- testResult = false;
- break;
- }
- }
-
- // Free resources.
- if (dVector) checkCudaErrors(cudaFree(dVector));
- } catch (...) {
- cout << "Error occured, exiting..." << endl;
-
- exit(EXIT_FAILURE);
- }
-}