diff --git a/CHANGELOG.md b/CHANGELOG.md
index e54171cd..c3a12dba 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,7 +4,9 @@
* Removed the following outdated samples:
* `0_Introduction`
* `c++11_cuda` demonstrating CUDA and C++ 11 interoperability (reason: obsolete)
- * `concurrentKernels.cu` demonstrating the ability to run multiple kernels simultaneously (reason: obsolete)
+ * `concurrentKernels` demonstrating the ability to run multiple kernels simultaneously (reason: obsolete)
+ * `cppIntegration` demonstrating calling between .cu and .cpp files (reason: obsolete)
+
### CUDA 12.5
diff --git a/Samples/0_Introduction/cppIntegration/.vscode/c_cpp_properties.json b/Samples/0_Introduction/cppIntegration/.vscode/c_cpp_properties.json
deleted file mode 100644
index f0066b0f..00000000
--- a/Samples/0_Introduction/cppIntegration/.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/cppIntegration/.vscode/extensions.json b/Samples/0_Introduction/cppIntegration/.vscode/extensions.json
deleted file mode 100644
index c7eb54dc..00000000
--- a/Samples/0_Introduction/cppIntegration/.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/cppIntegration/.vscode/launch.json b/Samples/0_Introduction/cppIntegration/.vscode/launch.json
deleted file mode 100644
index 7fee3d07..00000000
--- a/Samples/0_Introduction/cppIntegration/.vscode/launch.json
+++ /dev/null
@@ -1,10 +0,0 @@
-{
- "configurations": [
- {
- "name": "CUDA C++: Launch",
- "type": "cuda-gdb",
- "request": "launch",
- "program": "${workspaceFolder}/cppIntegration"
- }
- ]
-}
diff --git a/Samples/0_Introduction/cppIntegration/.vscode/tasks.json b/Samples/0_Introduction/cppIntegration/.vscode/tasks.json
deleted file mode 100644
index 4509aeb1..00000000
--- a/Samples/0_Introduction/cppIntegration/.vscode/tasks.json
+++ /dev/null
@@ -1,15 +0,0 @@
-{
- "version": "2.0.0",
- "tasks": [
- {
- "label": "sample",
- "type": "shell",
- "command": "make dbg=1",
- "problemMatcher": ["$nvcc"],
- "group": {
- "kind": "build",
- "isDefault": true
- }
- }
- ]
-}
diff --git a/Samples/0_Introduction/cppIntegration/Makefile b/Samples/0_Introduction/cppIntegration/Makefile
deleted file mode 100644
index 05856802..00000000
--- a/Samples/0_Introduction/cppIntegration/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
-
- 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 += --threads 0 --std=c++11
-
-ifeq ($(SAMPLE_ENABLED),0)
-EXEC ?= @echo "[@]"
-endif
-
-################################################################################
-
-# Target rules
-all: build
-
-build: cppIntegration
-
-check.deps:
-ifeq ($(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
-
-cppIntegration.o:cppIntegration.cu
- $(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
-
-cppIntegration_gold.o:cppIntegration_gold.cpp
- $(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
-
-main.o:main.cpp
- $(EXEC) $(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
-
-cppIntegration: cppIntegration.o cppIntegration_gold.o main.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
- $(EXEC) ./cppIntegration
-
-testrun: build
-
-clean:
- rm -f cppIntegration cppIntegration.o cppIntegration_gold.o main.o
- rm -rf ../../../bin/$(TARGET_ARCH)/$(TARGET_OS)/$(BUILD_TYPE)/cppIntegration
-
-clobber: clean
diff --git a/Samples/0_Introduction/cppIntegration/NsightEclipse.xml b/Samples/0_Introduction/cppIntegration/NsightEclipse.xml
deleted file mode 100644
index 060b5b4b..00000000
--- a/Samples/0_Introduction/cppIntegration/NsightEclipse.xml
+++ /dev/null
@@ -1,72 +0,0 @@
-
-
-
- cppIntegration
-
- cudaMalloc
- cudaMemcpy
- cudaFree
-
-
- whole
-
- ./
- ../
- ../../../Common
-
-
- CPP-CUDA Integration
-
-
-
-
-
-
-
- true
- cppIntegration.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
-
- C++ Integration
- exe
-
diff --git a/Samples/0_Introduction/cppIntegration/README.md b/Samples/0_Introduction/cppIntegration/README.md
deleted file mode 100644
index 9aad8ada..00000000
--- a/Samples/0_Introduction/cppIntegration/README.md
+++ /dev/null
@@ -1,70 +0,0 @@
-# cppIntegration - C++ Integration
-
-## Description
-
-This example demonstrates how to integrate CUDA into an existing C++ application, i.e. the CUDA entry point on host side is only a function which is called from C++ code and only the file containing this function is compiled with nvcc. It also demonstrates that vector types can be used from cpp.
-
-## Key Concepts
-
-CPP-CUDA Integration
-
-## 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, cudaFree
-
-## 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/cppIntegration/cppIntegration.cu b/Samples/0_Introduction/cppIntegration/cppIntegration.cu
deleted file mode 100644
index 620110b1..00000000
--- a/Samples/0_Introduction/cppIntegration/cppIntegration.cu
+++ /dev/null
@@ -1,172 +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.
- */
-
-/*
- * Example of integrating CUDA functions into an existing
- * application / framework.
- * Host part of the device code.
- * Compiled with Cuda compiler.
- */
-
-// System includes
-#include
-#include
-#include
-#include
-#include
-
-// CUDA runtime
-#include
-
-// helper functions and utilities to work with CUDA
-#include
-#include
-
-#ifndef MAX
-#define MAX(a, b) (a > b ? a : b)
-#endif
-
-////////////////////////////////////////////////////////////////////////////////
-// declaration, forward
-
-extern "C" void computeGold(char *reference, char *idata,
- const unsigned int len);
-extern "C" void computeGold2(int2 *reference, int2 *idata,
- const unsigned int len);
-
-///////////////////////////////////////////////////////////////////////////////
-//! Simple test kernel for device functionality
-//! @param g_odata memory to process (in and out)
-///////////////////////////////////////////////////////////////////////////////
-__global__ void kernel(int *g_data) {
- // write data to global memory
- const unsigned int tid = threadIdx.x;
- int data = g_data[tid];
-
- // use integer arithmetic to process all four bytes with one thread
- // this serializes the execution, but is the simplest solutions to avoid
- // bank conflicts for this very low number of threads
- // in general it is more efficient to process each byte by a separate thread,
- // to avoid bank conflicts the access pattern should be
- // g_data[4 * wtid + wid], where wtid is the thread id within the half warp
- // and wid is the warp id
- // see also the programming guide for a more in depth discussion.
- g_data[tid] =
- ((((data << 0) >> 24) - 10) << 24) | ((((data << 8) >> 24) - 10) << 16) |
- ((((data << 16) >> 24) - 10) << 8) | ((((data << 24) >> 24) - 10) << 0);
-}
-
-///////////////////////////////////////////////////////////////////////////////
-//! Demonstration that int2 data can be used in the cpp code
-//! @param g_odata memory to process (in and out)
-///////////////////////////////////////////////////////////////////////////////
-__global__ void kernel2(int2 *g_data) {
- // write data to global memory
- const unsigned int tid = threadIdx.x;
- int2 data = g_data[tid];
-
- // use integer arithmetic to process all four bytes with one thread
- // this serializes the execution, but is the simplest solutions to avoid
- // bank conflicts for this very low number of threads
- // in general it is more efficient to process each byte by a separate thread,
- // to avoid bank conflicts the access pattern should be
- // g_data[4 * wtid + wid], where wtid is the thread id within the half warp
- // and wid is the warp id
- // see also the programming guide for a more in depth discussion.
- g_data[tid].x = data.x - data.y;
-}
-
-////////////////////////////////////////////////////////////////////////////////
-//! Entry point for Cuda functionality on host side
-//! @param argc command line argument count
-//! @param argv command line arguments
-//! @param data data to process on the device
-//! @param len len of \a data
-////////////////////////////////////////////////////////////////////////////////
-extern "C" bool runTest(const int argc, const char **argv, char *data,
- int2 *data_int2, unsigned int len) {
- // use command-line specified CUDA device, otherwise use device with highest
- // Gflops/s
- findCudaDevice(argc, (const char **)argv);
-
- const unsigned int num_threads = len / 4;
- assert(0 == (len % 4));
- const unsigned int mem_size = sizeof(char) * len;
- const unsigned int mem_size_int2 = sizeof(int2) * len;
-
- // allocate device memory
- char *d_data;
- checkCudaErrors(cudaMalloc((void **)&d_data, mem_size));
- // copy host memory to device
- checkCudaErrors(cudaMemcpy(d_data, data, mem_size, cudaMemcpyHostToDevice));
- // allocate device memory for int2 version
- int2 *d_data_int2;
- checkCudaErrors(cudaMalloc((void **)&d_data_int2, mem_size_int2));
- // copy host memory to device
- checkCudaErrors(cudaMemcpy(d_data_int2, data_int2, mem_size_int2,
- cudaMemcpyHostToDevice));
-
- // setup execution parameters
- dim3 grid(1, 1, 1);
- dim3 threads(num_threads, 1, 1);
- dim3 threads2(len, 1, 1); // more threads needed fir separate int2 version
- // execute the kernel
- kernel<<>>((int *)d_data);
- kernel2<<>>(d_data_int2);
-
- // check if kernel execution generated and error
- getLastCudaError("Kernel execution failed");
-
- // compute reference solutions
- char *reference = (char *)malloc(mem_size);
- computeGold(reference, data, len);
- int2 *reference2 = (int2 *)malloc(mem_size_int2);
- computeGold2(reference2, data_int2, len);
-
- // copy results from device to host
- checkCudaErrors(cudaMemcpy(data, d_data, mem_size, cudaMemcpyDeviceToHost));
- checkCudaErrors(cudaMemcpy(data_int2, d_data_int2, mem_size_int2,
- cudaMemcpyDeviceToHost));
-
- // check result
- bool success = true;
-
- for (unsigned int i = 0; i < len; i++) {
- if (reference[i] != data[i] || reference2[i].x != data_int2[i].x ||
- reference2[i].y != data_int2[i].y) {
- success = false;
- }
- }
-
- // cleanup memory
- checkCudaErrors(cudaFree(d_data));
- checkCudaErrors(cudaFree(d_data_int2));
- free(reference);
- free(reference2);
-
- return success;
-}
diff --git a/Samples/0_Introduction/cppIntegration/cppIntegration_gold.cpp b/Samples/0_Introduction/cppIntegration/cppIntegration_gold.cpp
deleted file mode 100644
index a7e16537..00000000
--- a/Samples/0_Introduction/cppIntegration/cppIntegration_gold.cpp
+++ /dev/null
@@ -1,67 +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.
- */
-
-/*
- * Example of integrating CUDA functions into an existing
- * application / framework.
- * Reference solution computation.
- */
-
-// Required header to support CUDA vector types
-#include
-
-////////////////////////////////////////////////////////////////////////////////
-// export C interface
-extern "C" void computeGold(char *reference, char *idata,
- const unsigned int len);
-extern "C" void computeGold2(int2 *reference, int2 *idata,
- const unsigned int len);
-
-////////////////////////////////////////////////////////////////////////////////
-//! Compute reference data set
-//! Each element is multiplied with the number of threads / array length
-//! @param reference reference data, computed but preallocated
-//! @param idata input data as provided to device
-//! @param len number of elements in reference / idata
-////////////////////////////////////////////////////////////////////////////////
-void computeGold(char *reference, char *idata, const unsigned int len) {
- for (unsigned int i = 0; i < len; ++i) reference[i] = idata[i] - 10;
-}
-
-////////////////////////////////////////////////////////////////////////////////
-//! Compute reference data set for int2 version
-//! Each element is multiplied with the number of threads / array length
-//! @param reference reference data, computed but preallocated
-//! @param idata input data as provided to device
-//! @param len number of elements in reference / idata
-////////////////////////////////////////////////////////////////////////////////
-void computeGold2(int2 *reference, int2 *idata, const unsigned int len) {
- for (unsigned int i = 0; i < len; ++i) {
- reference[i].x = idata[i].x - idata[i].y;
- reference[i].y = idata[i].y;
- }
-}
diff --git a/Samples/0_Introduction/cppIntegration/main.cpp b/Samples/0_Introduction/cppIntegration/main.cpp
deleted file mode 100644
index ef8ef9cf..00000000
--- a/Samples/0_Introduction/cppIntegration/main.cpp
+++ /dev/null
@@ -1,86 +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.
- */
-
-/*
- * Example of integrating CUDA functions into an existing
- * application / framework.
- * CPP code representing the existing application / framework.
- * Compiled with default CPP compiler.
- */
-
-// includes, system
-#include
-#include
-
-// Required to include CUDA vector types
-#include
-#include
-#include
-
-////////////////////////////////////////////////////////////////////////////////
-// declaration, forward
-extern "C" bool runTest(const int argc, const char **argv, char *data,
- int2 *data_int2, unsigned int len);
-
-////////////////////////////////////////////////////////////////////////////////
-// Program main
-////////////////////////////////////////////////////////////////////////////////
-int main(int argc, char **argv) {
- // input data
- int len = 16;
- // the data has some zero padding at the end so that the size is a multiple of
- // four, this simplifies the processing as each thread can process four
- // elements (which is necessary to avoid bank conflicts) but no branching is
- // necessary to avoid out of bounds reads
- char str[] = {82, 111, 118, 118, 121, 42, 97, 121,
- 124, 118, 110, 56, 10, 10, 10, 10};
-
- // Use int2 showing that CUDA vector types can be used in cpp code
- int2 i2[16];
-
- for (int i = 0; i < len; i++) {
- i2[i].x = str[i];
- i2[i].y = 10;
- }
-
- bool bTestResult;
-
- // run the device part of the program
- bTestResult = runTest(argc, (const char **)argv, str, i2, len);
-
- std::cout << str << std::endl;
-
- char str_device[16];
-
- for (int i = 0; i < len; i++) {
- str_device[i] = (char)(i2[i].x);
- }
-
- std::cout << str_device << std::endl;
-
- exit(bTestResult ? EXIT_SUCCESS : EXIT_FAILURE);
-}