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/template/.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/template/.vscode/extensions.json

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

cpp/0_Introduction/template/CMakeLists.txt

@@ -0,0 +1,35 @@
+cmake_minimum_required(VERSION 3.20)
+
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/Modules")
+
+project(template LANGUAGES C CXX CUDA)
+
+find_package(CUDAToolkit REQUIRED)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+set(CMAKE_CUDA_ARCHITECTURES 75 80 86 87 89 90 100 110 120)
+set(CMAKE_CUDA_FLAGS "${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 template
+add_executable(template template.cu template_cpu.cpp)
+
+target_compile_options(template PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>)
+
+target_compile_features(template PRIVATE cxx_std_17 cuda_std_17)
+
+set_target_properties(template PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
+
+# Include installation configuration
+include(${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/InstallSamples.cmake)
+setup_samples_install()

cpp/0_Introduction/template/README.md

@@ -0,0 +1,32 @@
+# template - Template
+
+## Description
+
+A trivial template project that can be used as a starting point to create new CUDA projects.
+
+## Key Concepts
+
+Device Memory Allocation
+
+## 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 Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
+cudaMalloc, cudaMemcpy, cudaFree
+
+## Prerequisites
+
+Download and install the [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+
+## References (for more details)

cpp/0_Introduction/template/template.cu

@@ -0,0 +1,165 @@
+/* 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.
+ */
+
+/* Template project which demonstrates the basics on how to setup a project
+ * example application.
+ * Host code.
+ */
+
+// includes, system
+#include <math.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+// includes CUDA
+#include <cuda_runtime.h>
+
+// includes, project
+#include <helper_cuda.h>
+#include <helper_functions.h> // helper functions for SDK examples
+
+////////////////////////////////////////////////////////////////////////////////
+// declaration, forward
+void runTest(int argc, char **argv);
+
+extern "C" void computeGold(float *reference, float *idata, const unsigned int len);
+
+////////////////////////////////////////////////////////////////////////////////
+//! Simple test kernel for device functionality
+//! @param g_idata  input data in global memory
+//! @param g_odata  output data in global memory
+////////////////////////////////////////////////////////////////////////////////
+__global__ void testKernel(float *g_idata, float *g_odata)
+{
+    // shared memory
+    // the size is determined by the host application
+    extern __shared__ float sdata[];
+
+    // access thread id
+    const unsigned int tid = threadIdx.x;
+    // access number of threads in this block
+    const unsigned int num_threads = blockDim.x;
+
+    // read in input data from global memory
+    sdata[tid] = g_idata[tid];
+    __syncthreads();
+
+    // perform some computations
+    sdata[tid] = (float)num_threads * sdata[tid];
+    __syncthreads();
+
+    // write data to global memory
+    g_odata[tid] = sdata[tid];
+}
+
+////////////////////////////////////////////////////////////////////////////////
+// Program main
+////////////////////////////////////////////////////////////////////////////////
+int main(int argc, char **argv) { runTest(argc, argv); }
+
+////////////////////////////////////////////////////////////////////////////////
+//! Run a simple test for CUDA
+////////////////////////////////////////////////////////////////////////////////
+void runTest(int argc, char **argv)
+{
+    bool bTestResult = true;
+
+    printf("%s Starting...\n\n", argv[0]);
+
+    // use command-line specified CUDA device, otherwise use device with highest
+    // Gflops/s
+    int devID = findCudaDevice(argc, (const char **)argv);
+
+    StopWatchInterface *timer = 0;
+    sdkCreateTimer(&timer);
+    sdkStartTimer(&timer);
+
+    unsigned int num_threads = 32;
+    unsigned int mem_size    = sizeof(float) * num_threads;
+
+    // allocate host memory
+    float *h_idata = (float *)malloc(mem_size);
+
+    // initalize the memory
+    for (unsigned int i = 0; i < num_threads; ++i) {
+        h_idata[i] = (float)i;
+    }
+
+    // allocate device memory
+    float *d_idata;
+    checkCudaErrors(cudaMalloc((void **)&d_idata, mem_size));
+    // copy host memory to device
+    checkCudaErrors(cudaMemcpy(d_idata, h_idata, mem_size, cudaMemcpyHostToDevice));
+
+    // allocate device memory for result
+    float *d_odata;
+    checkCudaErrors(cudaMalloc((void **)&d_odata, mem_size));
+
+    // setup execution parameters
+    dim3 grid(1, 1, 1);
+    dim3 threads(num_threads, 1, 1);
+
+    // execute the kernel
+    testKernel<<<grid, threads, mem_size>>>(d_idata, d_odata);
+
+    // check if kernel execution generated and error
+    getLastCudaError("Kernel execution failed");
+
+    // allocate mem for the result on host side
+    float *h_odata = (float *)malloc(mem_size);
+    // copy result from device to host
+    checkCudaErrors(cudaMemcpy(h_odata, d_odata, sizeof(float) * num_threads, cudaMemcpyDeviceToHost));
+
+    sdkStopTimer(&timer);
+    printf("Processing time: %f (ms)\n", sdkGetTimerValue(&timer));
+    sdkDeleteTimer(&timer);
+
+    // compute reference solution
+    float *reference = (float *)malloc(mem_size);
+    computeGold(reference, h_idata, num_threads);
+
+    // check result
+    if (checkCmdLineFlag(argc, (const char **)argv, "regression")) {
+        // write file for regression test
+        sdkWriteFile("./data/regression.dat", h_odata, num_threads, 0.0f, false);
+    }
+    else {
+        // custom output handling when no regression test running
+        // in this case check if the result is equivalent to the expected solution
+        bTestResult = compareData(reference, h_odata, num_threads, 0.0f, 0.0f);
+    }
+
+    // cleanup memory
+    free(h_idata);
+    free(h_odata);
+    free(reference);
+    checkCudaErrors(cudaFree(d_idata));
+    checkCudaErrors(cudaFree(d_odata));
+
+    exit(bTestResult ? EXIT_SUCCESS : EXIT_FAILURE);
+}

cpp/0_Introduction/template/template_cpu.cpp

@@ -0,0 +1,45 @@
+/* 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.
+ */
+
+// export C interface
+extern "C" void computeGold(float *reference, float *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(float *reference, float *idata, const unsigned int len)
+{
+    const float f_len = static_cast<float>(len);
+
+    for (unsigned int i = 0; i < len; ++i) {
+        reference[i] = idata[i] * f_len;
+    }
+}