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/vectorAddDrv/.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/vectorAddDrv/.vscode/extensions.json

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

cpp/0_Introduction/vectorAddDrv/CMakeLists.txt

@@ -0,0 +1,71 @@
+cmake_minimum_required(VERSION 3.20)
+
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/Modules")
+
+project(vectorAddDrv LANGUAGES C CXX CUDA)
+
+find_package(CUDAToolkit REQUIRED)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+set(CMAKE_CUDA_ARCHITECTURES 75 80 86 87 89 90 100 110 120)
+set(CMAKE_CUDA_FLAGS "${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 target for vectorAddDrv
+add_executable(vectorAddDrv vectorAddDrv.cpp)
+
+target_compile_options(vectorAddDrv PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>)
+
+target_compile_features(vectorAddDrv PRIVATE cxx_std_17 cuda_std_17)
+
+set_target_properties(vectorAddDrv PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
+target_include_directories(vectorAddDrv PRIVATE
+    ${CUDAToolkit_INCLUDE_DIRS}
+)
+
+target_link_libraries(vectorAddDrv PUBLIC
+    CUDA::cuda_driver
+)
+
+set(CUDA_FATBIN_FILE "${CMAKE_CURRENT_BINARY_DIR}/vectorAdd_kernel64.fatbin")
+set(CUDA_KERNEL_SOURCE "${CMAKE_CURRENT_SOURCE_DIR}/vectorAdd_kernel.cu")
+
+# Construct GENCODE_FLAGS explicitly from CUDA architectures
+set(GENCODE_FLAGS "")
+foreach(arch ${CMAKE_CUDA_ARCHITECTURES})
+    list(APPEND GENCODE_FLAGS "-gencode=arch=compute_${arch},code=sm_${arch}")
+endforeach()
+
+if(CMAKE_SYSTEM_NAME STREQUAL "QNX")
+    set(INCLUDES_LIST)
+    foreach(dir ${CUDAToolkit_INCLUDE_DIRS})
+        list(APPEND INCLUDES_LIST "-I${dir}")
+    endforeach()
+    string(JOIN " " INCLUDES "${INCLUDES_LIST}")
+endif()
+
+add_custom_command(
+    OUTPUT ${CUDA_FATBIN_FILE}
+    COMMAND ${CMAKE_CUDA_COMPILER} ${INCLUDES} ${ALL_CCFLAGS} -Wno-deprecated-gpu-targets  ${GENCODE_FLAGS} -o ${CUDA_FATBIN_FILE} -fatbin ${CUDA_KERNEL_SOURCE}
+    DEPENDS ${CUDA_KERNEL_SOURCE}
+    COMMENT "Building CUDA fatbin: ${CUDA_FATBIN_FILE}"
+)
+
+# Create a dummy target for fatbin generation
+add_custom_target(generate_fatbin_vectorAdd ALL DEPENDS ${CUDA_FATBIN_FILE})
+
+# Ensure matrixMulDrv depends on the fatbin
+add_dependencies(vectorAddDrv generate_fatbin_vectorAdd)
+
+# Include installation configuration
+include(${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/InstallSamples.cmake)
+setup_samples_install()

cpp/0_Introduction/vectorAddDrv/README.md

@@ -0,0 +1,32 @@
+# vectorAddDrv - Vector Addition Driver API
+
+## Description
+
+This Vector Addition sample is a basic sample that is implemented element by element.  It is the same as the sample illustrating Chapter 3 of the programming guide with some additions like error checking.   This sample also uses the new CUDA 4.0 kernel launch Driver API.
+
+## Key Concepts
+
+CUDA Driver API, Vector Addition
+
+## 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, armv7l
+
+## CUDA APIs involved
+
+### [CUDA Driver API](http://docs.nvidia.com/cuda/cuda-driver-api/index.html)
+cuMemcpyDtoH, cuLaunchKernel, cuMemcpyHtoD, cuModuleLoadData, cuCtxSynchronize, cuMemAlloc, cuMemFree, cuCtxDestroy, cuModuleGetFunction, cuCtxCreate, cuInit
+
+## Prerequisites
+
+Download and install the [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+
+## References (for more details)

cpp/0_Introduction/vectorAddDrv/vectorAddDrv.cpp

@@ -0,0 +1,225 @@
+/* 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 3
+ * of the programming guide with some additions like error checking.
+ *
+ */
+
+// Includes
+#include <cstring>
+#include <cuda.h>
+#include <iostream>
+#include <stdio.h>
+#include <string.h>
+
+// includes, project
+#include <helper_cuda_drvapi.h>
+#include <helper_functions.h>
+
+// includes, CUDA
+#include <builtin_types.h>
+
+using namespace std;
+
+// Variables
+CUdevice    cuDevice;
+CUcontext   cuContext;
+CUmodule    cuModule;
+CUfunction  vecAdd_kernel;
+float      *h_A;
+float      *h_B;
+float      *h_C;
+CUdeviceptr d_A;
+CUdeviceptr d_B;
+CUdeviceptr d_C;
+
+// Functions
+int  CleanupNoFailure();
+void RandomInit(float *, int);
+bool findModulePath(const char *, string &, char **, string &);
+
+// define input fatbin file
+#ifndef FATBIN_FILE
+#define FATBIN_FILE "vectorAdd_kernel64.fatbin"
+#endif
+
+// Host code
+int main(int argc, char **argv)
+{
+    printf("Vector Addition (Driver API)\n");
+    int               N = 50000, devID = 0;
+    size_t            size            = N * sizeof(float);
+    CUctxCreateParams ctxCreateParams = {};
+
+    // Initialize
+    checkCudaErrors(cuInit(0));
+
+    cuDevice = findCudaDeviceDRV(argc, (const char **)argv);
+    // Create context
+    checkCudaErrors(cuCtxCreate(&cuContext, &ctxCreateParams, 0, cuDevice));
+
+    // first search for the module path before we load the results
+    string module_path;
+
+    std::ostringstream fatbin;
+
+    if (!findFatbinPath(FATBIN_FILE, module_path, argv, fatbin)) {
+        exit(EXIT_FAILURE);
+    }
+    else {
+        printf("> initCUDA loading module: <%s>\n", module_path.c_str());
+    }
+
+    if (!fatbin.str().size()) {
+        printf("fatbin file empty. exiting..\n");
+        exit(EXIT_FAILURE);
+    }
+
+    // Create module from binary file (FATBIN)
+    checkCudaErrors(cuModuleLoadData(&cuModule, fatbin.str().c_str()));
+
+    // Get function handle from module
+    checkCudaErrors(cuModuleGetFunction(&vecAdd_kernel, cuModule, "VecAdd_kernel"));
+
+    // Allocate input vectors h_A and h_B in host memory
+    h_A = (float *)malloc(size);
+    h_B = (float *)malloc(size);
+    h_C = (float *)malloc(size);
+
+    // Initialize input vectors
+    RandomInit(h_A, N);
+    RandomInit(h_B, N);
+
+    // Allocate vectors in device memory
+    checkCudaErrors(cuMemAlloc(&d_A, size));
+
+    checkCudaErrors(cuMemAlloc(&d_B, size));
+
+    checkCudaErrors(cuMemAlloc(&d_C, size));
+
+    // Copy vectors from host memory to device memory
+    checkCudaErrors(cuMemcpyHtoD(d_A, h_A, size));
+
+    checkCudaErrors(cuMemcpyHtoD(d_B, h_B, size));
+
+    if (1) {
+        // This is the new CUDA 4.0 API for Kernel Parameter Passing and Kernel
+        // Launch (simpler method)
+
+        // Grid/Block configuration
+        int threadsPerBlock = 256;
+        int blocksPerGrid   = (N + threadsPerBlock - 1) / threadsPerBlock;
+
+        void *args[] = {&d_A, &d_B, &d_C, &N};
+
+        // Launch the CUDA kernel
+        checkCudaErrors(cuLaunchKernel(vecAdd_kernel, blocksPerGrid, 1, 1, threadsPerBlock, 1, 1, 0, NULL, args, NULL));
+    }
+    else {
+        // This is the new CUDA 4.0 API for Kernel Parameter Passing and Kernel
+        // Launch (advanced method)
+        int   offset = 0;
+        void *argBuffer[16];
+        *((CUdeviceptr *)&argBuffer[offset]) = d_A;
+        offset += sizeof(d_A);
+        *((CUdeviceptr *)&argBuffer[offset]) = d_B;
+        offset += sizeof(d_B);
+        *((CUdeviceptr *)&argBuffer[offset]) = d_C;
+        offset += sizeof(d_C);
+        *((int *)&argBuffer[offset]) = N;
+        offset += sizeof(N);
+
+        // Grid/Block configuration
+        int threadsPerBlock = 256;
+        int blocksPerGrid   = (N + threadsPerBlock - 1) / threadsPerBlock;
+
+        // Launch the CUDA kernel
+        checkCudaErrors(
+            cuLaunchKernel(vecAdd_kernel, blocksPerGrid, 1, 1, threadsPerBlock, 1, 1, 0, NULL, NULL, argBuffer));
+    }
+
+#ifdef _DEBUG
+    checkCudaErrors(cuCtxSynchronize());
+#endif
+
+    // Copy result from device memory to host memory
+    // h_C contains the result in host memory
+    checkCudaErrors(cuMemcpyDtoH(h_C, d_C, size));
+
+    // Verify result
+    int i;
+
+    for (i = 0; i < N; ++i) {
+        float sum = h_A[i] + h_B[i];
+
+        if (fabs(h_C[i] - sum) > 1e-7f) {
+            break;
+        }
+    }
+
+    CleanupNoFailure();
+    printf("%s\n", (i == N) ? "Result = PASS" : "Result = FAIL");
+
+    exit((i == N) ? EXIT_SUCCESS : EXIT_FAILURE);
+}
+
+int CleanupNoFailure()
+{
+    // Free device memory
+    checkCudaErrors(cuMemFree(d_A));
+    checkCudaErrors(cuMemFree(d_B));
+    checkCudaErrors(cuMemFree(d_C));
+
+    // Free host memory
+    if (h_A) {
+        free(h_A);
+    }
+
+    if (h_B) {
+        free(h_B);
+    }
+
+    if (h_C) {
+        free(h_C);
+    }
+
+    checkCudaErrors(cuModuleUnload(cuModule));
+    checkCudaErrors(cuCtxDestroy(cuContext));
+
+    return EXIT_SUCCESS;
+}
+// Allocates an array with random float entries.
+void RandomInit(float *data, int n)
+{
+    for (int i = 0; i < n; ++i) {
+        data[i] = rand() / (float)RAND_MAX;
+    }
+}

cpp/0_Introduction/vectorAddDrv/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.
+ */
+/* 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 3
+ * of the programming guide with some additions like error checking.
+ *
+ */
+
+// Device code
+extern "C" __global__ void VecAdd_kernel(const float *A, const float *B, float *C, int N)
+{
+    int i = blockDim.x * blockIdx.x + threadIdx.x;
+
+    if (i < N)
+        C[i] = A[i] + B[i];
+}