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/4_CUDA_Libraries/simpleCUBLAS/.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/4_CUDA_Libraries/simpleCUBLAS/.vscode/extensions.json

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

cpp/4_CUDA_Libraries/simpleCUBLAS/CMakeLists.txt

@@ -0,0 +1,43 @@
+cmake_minimum_required(VERSION 3.20)
+
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/Modules")
+
+project(simpleCUBLAS LANGUAGES CXX)
+
+find_package(CUDAToolkit REQUIRED)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+set(CMAKE_CUDA_ARCHITECTURES 75 80 86 87 89 90 100 110 120)
+set(CMAKE_CUDA_FLAGS "${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 simpleCUBLAS
+add_executable(simpleCUBLAS simpleCUBLAS.cpp)
+
+target_compile_options(simpleCUBLAS PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>)
+
+target_compile_features(simpleCUBLAS PRIVATE cxx_std_17 cuda_std_17)
+
+set_target_properties(simpleCUBLAS PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
+
+target_include_directories(simpleCUBLAS PRIVATE
+    ${CUDAToolkit_INCLUDE_DIRS}
+)
+
+target_link_libraries(simpleCUBLAS PRIVATE
+    CUDA::cudart
+    CUDA::cublas
+)
+
+# Include installation configuration
+include(${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/InstallSamples.cmake)
+setup_samples_install()

cpp/4_CUDA_Libraries/simpleCUBLAS/README.md

@@ -0,0 +1,36 @@
+# simpleCUBLAS - Simple CUBLAS
+
+## Description
+
+Example of using CUBLAS API interface to perform GEMM operations.
+
+## Key Concepts
+
+Image Processing, CUBLAS Library
+
+## 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, aarch64
+
+## CUDA APIs involved
+
+### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
+cudaMalloc, cudaFree
+
+## Dependencies needed to build/run
+[CUBLAS](../../../README.md#cublas)
+
+## 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/4_CUDA_Libraries/simpleCUBLAS/simpleCUBLAS.cpp

@@ -0,0 +1,253 @@
+/* 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.
+ */
+
+/* This example demonstrates how to use the CUBLAS library
+ * by scaling an array of floating-point values on the device
+ * and comparing the result to the same operation performed
+ * on the host.
+ */
+
+/* Includes, system */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+/* Includes, cuda */
+#include <cublas_v2.h>
+#include <cuda_runtime.h>
+#include <helper_cuda.h>
+
+/* Matrix size */
+#define N (275)
+
+/* Host implementation of a simple version of sgemm */
+static void simple_sgemm(int n, float alpha, const float *A, const float *B, float beta, float *C)
+{
+    int i;
+    int j;
+    int k;
+
+    for (i = 0; i < n; ++i) {
+        for (j = 0; j < n; ++j) {
+            float prod = 0;
+
+            for (k = 0; k < n; ++k) {
+                prod += A[k * n + i] * B[j * n + k];
+            }
+
+            C[j * n + i] = alpha * prod + beta * C[j * n + i];
+        }
+    }
+}
+
+/* Main */
+int main(int argc, char **argv)
+{
+    cublasStatus_t status;
+    float         *h_A;
+    float         *h_B;
+    float         *h_C;
+    float         *h_C_ref;
+    float         *d_A   = 0;
+    float         *d_B   = 0;
+    float         *d_C   = 0;
+    float          alpha = 1.0f;
+    float          beta  = 0.0f;
+    int            n2    = N * N;
+    int            i;
+    float          error_norm;
+    float          ref_norm;
+    float          diff;
+    cublasHandle_t handle;
+
+    int dev = findCudaDevice(argc, (const char **)argv);
+
+    if (dev == -1) {
+        return EXIT_FAILURE;
+    }
+
+    /* Initialize CUBLAS */
+    printf("simpleCUBLAS test running..\n");
+
+    status = cublasCreate(&handle);
+
+    if (status != CUBLAS_STATUS_SUCCESS) {
+        fprintf(stderr, "!!!! CUBLAS initialization error\n");
+        return EXIT_FAILURE;
+    }
+
+    /* Allocate host memory for the matrices */
+    h_A = reinterpret_cast<float *>(malloc(n2 * sizeof(h_A[0])));
+
+    if (h_A == 0) {
+        fprintf(stderr, "!!!! host memory allocation error (A)\n");
+        return EXIT_FAILURE;
+    }
+
+    h_B = reinterpret_cast<float *>(malloc(n2 * sizeof(h_B[0])));
+
+    if (h_B == 0) {
+        fprintf(stderr, "!!!! host memory allocation error (B)\n");
+        return EXIT_FAILURE;
+    }
+
+    h_C = reinterpret_cast<float *>(malloc(n2 * sizeof(h_C[0])));
+
+    if (h_C == 0) {
+        fprintf(stderr, "!!!! host memory allocation error (C)\n");
+        return EXIT_FAILURE;
+    }
+
+    /* Fill the matrices with test data */
+    for (i = 0; i < n2; i++) {
+        h_A[i] = rand() / static_cast<float>(RAND_MAX);
+        h_B[i] = rand() / static_cast<float>(RAND_MAX);
+        h_C[i] = rand() / static_cast<float>(RAND_MAX);
+    }
+
+    /* Allocate device memory for the matrices */
+    if (cudaMalloc(reinterpret_cast<void **>(&d_A), n2 * sizeof(d_A[0])) != cudaSuccess) {
+        fprintf(stderr, "!!!! device memory allocation error (allocate A)\n");
+        return EXIT_FAILURE;
+    }
+
+    if (cudaMalloc(reinterpret_cast<void **>(&d_B), n2 * sizeof(d_B[0])) != cudaSuccess) {
+        fprintf(stderr, "!!!! device memory allocation error (allocate B)\n");
+        return EXIT_FAILURE;
+    }
+
+    if (cudaMalloc(reinterpret_cast<void **>(&d_C), n2 * sizeof(d_C[0])) != cudaSuccess) {
+        fprintf(stderr, "!!!! device memory allocation error (allocate C)\n");
+        return EXIT_FAILURE;
+    }
+
+    /* Initialize the device matrices with the host matrices */
+    status = cublasSetVector(n2, sizeof(h_A[0]), h_A, 1, d_A, 1);
+
+    if (status != CUBLAS_STATUS_SUCCESS) {
+        fprintf(stderr, "!!!! device access error (write A)\n");
+        return EXIT_FAILURE;
+    }
+
+    status = cublasSetVector(n2, sizeof(h_B[0]), h_B, 1, d_B, 1);
+
+    if (status != CUBLAS_STATUS_SUCCESS) {
+        fprintf(stderr, "!!!! device access error (write B)\n");
+        return EXIT_FAILURE;
+    }
+
+    status = cublasSetVector(n2, sizeof(h_C[0]), h_C, 1, d_C, 1);
+
+    if (status != CUBLAS_STATUS_SUCCESS) {
+        fprintf(stderr, "!!!! device access error (write C)\n");
+        return EXIT_FAILURE;
+    }
+
+    /* Performs operation using plain C code */
+    simple_sgemm(N, alpha, h_A, h_B, beta, h_C);
+    h_C_ref = h_C;
+
+    /* Performs operation using cublas */
+    status = cublasSgemm(handle, CUBLAS_OP_N, CUBLAS_OP_N, N, N, N, &alpha, d_A, N, d_B, N, &beta, d_C, N);
+
+    if (status != CUBLAS_STATUS_SUCCESS) {
+        fprintf(stderr, "!!!! kernel execution error.\n");
+        return EXIT_FAILURE;
+    }
+
+    /* Allocate host memory for reading back the result from device memory */
+    h_C = reinterpret_cast<float *>(malloc(n2 * sizeof(h_C[0])));
+
+    if (h_C == 0) {
+        fprintf(stderr, "!!!! host memory allocation error (C)\n");
+        return EXIT_FAILURE;
+    }
+
+    /* Read the result back */
+    status = cublasGetVector(n2, sizeof(h_C[0]), d_C, 1, h_C, 1);
+
+    if (status != CUBLAS_STATUS_SUCCESS) {
+        fprintf(stderr, "!!!! device access error (read C)\n");
+        return EXIT_FAILURE;
+    }
+
+    /* Check result against reference */
+    error_norm = 0;
+    ref_norm   = 0;
+
+    for (i = 0; i < n2; ++i) {
+        diff = h_C_ref[i] - h_C[i];
+        error_norm += diff * diff;
+        ref_norm += h_C_ref[i] * h_C_ref[i];
+    }
+
+    error_norm = static_cast<float>(sqrt(static_cast<double>(error_norm)));
+    ref_norm   = static_cast<float>(sqrt(static_cast<double>(ref_norm)));
+
+    if (fabs(ref_norm) < 1e-7) {
+        fprintf(stderr, "!!!! reference norm is 0\n");
+        return EXIT_FAILURE;
+    }
+
+    /* Memory clean up */
+    free(h_A);
+    free(h_B);
+    free(h_C);
+    free(h_C_ref);
+
+    if (cudaFree(d_A) != cudaSuccess) {
+        fprintf(stderr, "!!!! memory free error (A)\n");
+        return EXIT_FAILURE;
+    }
+
+    if (cudaFree(d_B) != cudaSuccess) {
+        fprintf(stderr, "!!!! memory free error (B)\n");
+        return EXIT_FAILURE;
+    }
+
+    if (cudaFree(d_C) != cudaSuccess) {
+        fprintf(stderr, "!!!! memory free error (C)\n");
+        return EXIT_FAILURE;
+    }
+
+    /* Shutdown */
+    status = cublasDestroy(handle);
+
+    if (status != CUBLAS_STATUS_SUCCESS) {
+        fprintf(stderr, "!!!! shutdown error (A)\n");
+        return EXIT_FAILURE;
+    }
+
+    if (error_norm / ref_norm < 1e-6f) {
+        printf("simpleCUBLAS test passed.\n");
+        exit(EXIT_SUCCESS);
+    }
+    else {
+        printf("simpleCUBLAS test failed.\n");
+        exit(EXIT_FAILURE);
+    }
+}