CUDA 13.2 samples update (#432)

- Added Python samples for CUDA Python 1.0 release
- Renamed top-level `Samples` directory to `cpp` to accommodate Python samples.

cpp/0_Introduction/vectorAdd_nvrtc/.vscode/c_cpp_properties.json

@@ -0,0 +1,18 @@
+{
+    "configurations": [
+        {
+            "name": "Linux",
+            "includePath": [
+                "${workspaceFolder}/**",
+                "${workspaceFolder}/../../../Common"
+            ],
+            "defines": [],
+            "compilerPath": "/usr/local/cuda/bin/nvcc",
+            "cStandard": "gnu17",
+            "cppStandard": "gnu++14",
+            "intelliSenseMode": "linux-gcc-x64",
+            "configurationProvider": "ms-vscode.makefile-tools"
+        }
+    ],
+    "version": 4
+}

cpp/0_Introduction/vectorAdd_nvrtc/.vscode/extensions.json

@@ -0,0 +1,7 @@
+{
+    "recommendations": [
+        "nvidia.nsight-vscode-edition",
+        "ms-vscode.cpptools",
+        "ms-vscode.makefile-tools"
+    ]
+}

cpp/0_Introduction/vectorAdd_nvrtc/CMakeLists.txt

@@ -0,0 +1,43 @@
+cmake_minimum_required(VERSION 3.20)
+
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/Modules")
+
+project(vectorAdd_nvrtc LANGUAGES C CXX CUDA)
+
+find_package(CUDAToolkit REQUIRED)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+set(CMAKE_CUDA_ARCHITECTURES 75 80 86 87 89 90 100 110 120)
+set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -Wno-deprecated-gpu-targets")
+if(ENABLE_CUDA_DEBUG)
+    set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -G")        # enable cuda-gdb (may significantly affect performance on some targets)
+else()
+    set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -lineinfo") # add line information to all builds for debug tools (exclusive to -G option)
+endif()
+
+# Include directories and libraries
+include_directories(../../../Common)
+
+# Source file
+# Add sample target executable
+add_executable(vectorAdd_nvrtc vectorAdd.cpp)
+
+target_compile_options(vectorAdd_nvrtc PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>)
+
+target_compile_features(vectorAdd_nvrtc PRIVATE cxx_std_17 cuda_std_17)
+
+target_link_libraries(vectorAdd_nvrtc PRIVATE
+    CUDA::nvrtc
+    CUDA::cuda_driver
+)
+
+# Copy vectorAdd_kernel.cu to the output directory
+add_custom_command(TARGET vectorAdd_nvrtc POST_BUILD
+    COMMAND ${CMAKE_COMMAND} -E copy_if_different
+    ${CMAKE_CURRENT_SOURCE_DIR}/vectorAdd_kernel.cu ${CMAKE_CURRENT_BINARY_DIR}
+)
+
+# Include installation configuration
+include(${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/InstallSamples.cmake)
+setup_samples_install()

cpp/0_Introduction/vectorAdd_nvrtc/README.md

@@ -0,0 +1,39 @@
+# vectorAdd_nvrtc - Vector Addition with libNVRTC
+
+## Description
+
+This CUDA Driver API sample uses NVRTC for runtime compilation of vector addition kernel. Vector addition kernel demonstrated is the same as the sample illustrating Chapter 3 of the programming guide.
+
+## Key Concepts
+
+CUDA Driver API, Vector Addition, Runtime 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, QNX
+
+## Supported CPU Architecture
+
+x86_64, aarch64
+
+## CUDA APIs involved
+
+### [CUDA Driver API](http://docs.nvidia.com/cuda/cuda-driver-api/index.html)
+cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuCtxSynchronize, cuMemAlloc, cuMemFree, cuModuleGetFunction
+
+### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
+cudaBlockSize, cudaGridSize
+
+## Dependencies needed to build/run
+[NVRTC](../../../README.md#nvrtc)
+
+## Prerequisites
+
+Download and install the [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+Make sure the dependencies mentioned in [Dependencies]() section above are installed.
+
+## References (for more details)

cpp/0_Introduction/vectorAdd_nvrtc/vectorAdd.cpp

@@ -0,0 +1,157 @@
+/* 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.
+ */
+
+/**
+ * Vector addition: C = A + B.
+ *
+ * This sample is a very basic sample that implements element by element
+ * vector addition. It is the same as the sample illustrating Chapter 2
+ * of the programming guide with some additions like error checking.
+ */
+
+#include <cmath>
+#include <stdio.h>
+
+// For the CUDA runtime routines (prefixed with "cuda_")
+#include <cuda.h>
+#include <cuda_runtime.h>
+
+// helper functions and utilities to work with CUDA
+#include <helper_functions.h>
+#include <nvrtc_helper.h>
+
+/**
+ * Host main routine
+ */
+int main(int argc, char **argv)
+{
+    char  *cubin, *kernel_file;
+    size_t cubinSize;
+    kernel_file = sdkFindFilePath("vectorAdd_kernel.cu", argv[0]);
+    compileFileToCUBIN(kernel_file, argc, argv, &cubin, &cubinSize, 0);
+    CUmodule module = loadCUBIN(cubin, argc, argv);
+
+    CUfunction kernel_addr;
+    checkCudaErrors(cuModuleGetFunction(&kernel_addr, module, "vectorAdd"));
+
+    // Print the vector length to be used, and compute its size
+    int    numElements = 50000;
+    size_t size        = numElements * sizeof(float);
+    printf("[Vector addition of %d elements]\n", numElements);
+
+    // Allocate the host input vector A
+    float *h_A = reinterpret_cast<float *>(malloc(size));
+
+    // Allocate the host input vector B
+    float *h_B = reinterpret_cast<float *>(malloc(size));
+
+    // Allocate the host output vector C
+    float *h_C = reinterpret_cast<float *>(malloc(size));
+
+    // Verify that allocations succeeded
+    if (h_A == NULL || h_B == NULL || h_C == NULL) {
+        fprintf(stderr, "Failed to allocate host vectors!\n");
+        exit(EXIT_FAILURE);
+    }
+
+    // Initialize the host input vectors
+    for (int i = 0; i < numElements; ++i) {
+        h_A[i] = rand() / static_cast<float>(RAND_MAX);
+        h_B[i] = rand() / static_cast<float>(RAND_MAX);
+    }
+
+    // Allocate the device input vector A
+    CUdeviceptr d_A;
+    checkCudaErrors(cuMemAlloc(&d_A, size));
+
+    // Allocate the device input vector B
+    CUdeviceptr d_B;
+    checkCudaErrors(cuMemAlloc(&d_B, size));
+
+    // Allocate the device output vector C
+    CUdeviceptr d_C;
+    checkCudaErrors(cuMemAlloc(&d_C, size));
+
+    // Copy the host input vectors A and B in host memory to the device input
+    // vectors in device memory
+    printf("Copy input data from the host memory to the CUDA device\n");
+    checkCudaErrors(cuMemcpyHtoD(d_A, h_A, size));
+    checkCudaErrors(cuMemcpyHtoD(d_B, h_B, size));
+
+    // Launch the Vector Add CUDA Kernel
+    int threadsPerBlock = 256;
+    int blocksPerGrid   = (numElements + threadsPerBlock - 1) / threadsPerBlock;
+    printf("CUDA kernel launch with %d blocks of %d threads\n", blocksPerGrid, threadsPerBlock);
+    dim3 cudaBlockSize(threadsPerBlock, 1, 1);
+    dim3 cudaGridSize(blocksPerGrid, 1, 1);
+
+    void *arr[] = {reinterpret_cast<void *>(&d_A),
+                   reinterpret_cast<void *>(&d_B),
+                   reinterpret_cast<void *>(&d_C),
+                   reinterpret_cast<void *>(&numElements)};
+    checkCudaErrors(cuLaunchKernel(kernel_addr,
+                                   cudaGridSize.x,
+                                   cudaGridSize.y,
+                                   cudaGridSize.z, /* grid dim */
+                                   cudaBlockSize.x,
+                                   cudaBlockSize.y,
+                                   cudaBlockSize.z, /* block dim */
+                                   0,
+                                   0,       /* shared mem, stream */
+                                   &arr[0], /* arguments */
+                                   0));
+    checkCudaErrors(cuCtxSynchronize());
+
+    // Copy the device result vector in device memory to the host result vector
+    // in host memory.
+    printf("Copy output data from the CUDA device to the host memory\n");
+    checkCudaErrors(cuMemcpyDtoH(h_C, d_C, size));
+
+    // Verify that the result vector is correct
+    for (int i = 0; i < numElements; ++i) {
+        if (fabs(h_A[i] + h_B[i] - h_C[i]) > 1e-5) {
+            fprintf(stderr, "Result verification failed at element %d!\n", i);
+            exit(EXIT_FAILURE);
+        }
+    }
+
+    printf("Test PASSED\n");
+
+    // Free device global memory
+    checkCudaErrors(cuMemFree(d_A));
+    checkCudaErrors(cuMemFree(d_B));
+    checkCudaErrors(cuMemFree(d_C));
+
+    // Free host memory
+    free(h_A);
+    free(h_B);
+    free(h_C);
+
+    printf("Done\n");
+
+    return 0;
+}

cpp/0_Introduction/vectorAdd_nvrtc/vectorAdd_kernel.cu

@@ -0,0 +1,42 @@
+/* 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.
+ */
+
+/**
+ * CUDA Kernel Device code
+ *
+ * Computes the vector addition of A and B into C. The 3 vectors have the same
+ * number of elements numElements.
+ */
+
+extern "C" __global__ void vectorAdd(const float *A, const float *B, float *C, int numElements)
+{
+    int i = blockDim.x * blockIdx.x + threadIdx.x;
+
+    if (i < numElements) {
+        C[i] = A[i] + B[i];
+    }
+}