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/simpleMPI/.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/simpleMPI/.vscode/extensions.json

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

cpp/0_Introduction/simpleMPI/CMakeLists.txt

@@ -0,0 +1,50 @@
+cmake_minimum_required(VERSION 3.20)
+
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/Modules")
+
+project(simpleMPI LANGUAGES C CXX CUDA)
+
+find_package(CUDAToolkit REQUIRED)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+set(CMAKE_CUDA_ARCHITECTURES 75 80 86 87 89 90 100 110 120)
+set(CMAKE_CUDA_FLAGS "${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)
+
+find_package(MPI)
+
+# Source file
+if(${MPI_FOUND})
+    # Add target for simpleMPI
+    add_executable(simpleMPI simpleMPI.cpp simpleMPI.cu)
+
+target_compile_options(simpleMPI PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>)
+
+target_compile_features(simpleMPI PRIVATE cxx_std_17 cuda_std_17)
+
+    set_target_properties(simpleMPI PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
+
+    target_include_directories(simpleMPI PUBLIC
+        ${MPI_INCLUDE_PATH}
+    )
+
+    target_link_libraries(simpleMPI PUBLIC
+        ${MPI_C_LIBRARIES}
+        ${MPI_CXX_LIBRARIES}
+    )
+
+else()
+    message(STATUS "MPI not found - will not build sample 'simpleMPI'")
+endif()
+
+# Include installation configuration
+include(${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/InstallSamples.cmake)
+setup_samples_install()

cpp/0_Introduction/simpleMPI/README.md

@@ -0,0 +1,36 @@
+# simpleMPI - simpleMPI
+
+## Description
+
+Simple example demonstrating how to use MPI in combination with CUDA.
+
+## Key Concepts
+
+CUDA Systems Integration, MPI, Multithreading
+
+## 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, aarch64
+
+## CUDA APIs involved
+
+### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
+cudaMalloc, cudaGetLastError, cudaMemcpy, cudaFree
+
+## Dependencies needed to build/run
+[MPI](../../../README.md#message-passing-interface)
+
+## 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/simpleMPI/simpleMPI.cpp

@@ -0,0 +1,129 @@
+/* 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.
+ */
+
+/* Simple example demonstrating how to use MPI with CUDA
+ *
+ *  Generate some random numbers on one node.
+ *  Dispatch them to all nodes.
+ *  Compute their square root on each node's GPU.
+ *  Compute the average of the results using MPI.
+ *
+ *  simpleMPI.cpp: main program, compiled with mpicxx on linux/Mac platforms
+ *                 on Windows, please download the Microsoft HPC Pack SDK 2008
+ */
+
+// MPI include
+#include <mpi.h>
+
+// System includes
+#include <iostream>
+
+using std::cerr;
+using std::cout;
+using std::endl;
+
+// User include
+#include "simpleMPI.h"
+
+// Error handling macros
+#define MPI_CHECK(call)                              \
+    if ((call) != MPI_SUCCESS) {                     \
+        cerr << "MPI error calling \"" #call "\"\n"; \
+        my_abort(-1);                                \
+    }
+
+// Host code
+// No CUDA here, only MPI
+int main(int argc, char *argv[])
+{
+    // Dimensions of the dataset
+    int blockSize       = 256;
+    int gridSize        = 10000;
+    int dataSizePerNode = gridSize * blockSize;
+
+    // Initialize MPI state
+    MPI_CHECK(MPI_Init(&argc, &argv));
+
+    // Get our MPI node number and node count
+    int commSize, commRank;
+    MPI_CHECK(MPI_Comm_size(MPI_COMM_WORLD, &commSize));
+    MPI_CHECK(MPI_Comm_rank(MPI_COMM_WORLD, &commRank));
+
+    // Generate some random numbers on the root node (node 0)
+    int    dataSizeTotal = dataSizePerNode * commSize;
+    float *dataRoot      = NULL;
+
+    // Are we the root node?
+    if (commRank == 0) {
+        cout << "Running on " << commSize << " nodes" << endl;
+        dataRoot = new float[dataSizeTotal];
+        initData(dataRoot, dataSizeTotal);
+    }
+
+    // Allocate a buffer on each node
+    float *dataNode = new float[dataSizePerNode];
+
+    // Dispatch a portion of the input data to each node
+    MPI_CHECK(
+        MPI_Scatter(dataRoot, dataSizePerNode, MPI_FLOAT, dataNode, dataSizePerNode, MPI_FLOAT, 0, MPI_COMM_WORLD));
+
+    if (commRank == 0) {
+        // No need for root data any more
+        delete[] dataRoot;
+    }
+
+    // On each node, run computation on GPU
+    computeGPU(dataNode, blockSize, gridSize);
+
+    // Reduction to the root node, computing the sum of output elements
+    float sumNode = sum(dataNode, dataSizePerNode);
+    float sumRoot;
+
+    MPI_CHECK(MPI_Reduce(&sumNode, &sumRoot, 1, MPI_FLOAT, MPI_SUM, 0, MPI_COMM_WORLD));
+
+    if (commRank == 0) {
+        float average = sumRoot / dataSizeTotal;
+        cout << "Average of square roots is: " << average << endl;
+    }
+
+    // Cleanup
+    delete[] dataNode;
+    MPI_CHECK(MPI_Finalize());
+
+    if (commRank == 0) {
+        cout << "PASSED\n";
+    }
+
+    return 0;
+}
+
+// Shut down MPI cleanly if something goes wrong
+void my_abort(int err)
+{
+    cout << "Test FAILED\n";
+    MPI_Abort(MPI_COMM_WORLD, err);
+}

cpp/0_Introduction/simpleMPI/simpleMPI.cu

@@ -0,0 +1,104 @@
+/* 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.
+ */
+
+/* Simple example demonstrating how to use MPI with CUDA
+ *
+ *  Generate some random numbers on one node.
+ *  Dispatch them to all nodes.
+ *  Compute their square root on each node's GPU.
+ *  Compute the average of the results using MPI.
+ *
+ *  simpleMPI.cu: GPU part, compiled with nvcc
+ */
+
+#include <iostream>
+using std::cerr;
+using std::endl;
+
+#include "simpleMPI.h"
+
+// Error handling macro
+#define CUDA_CHECK(call)                                                     \
+    if ((call) != cudaSuccess) {                                             \
+        cudaError_t err = cudaGetLastError();                                \
+        cerr << "CUDA error calling \"" #call "\", code is " << err << endl; \
+        my_abort(err);                                                       \
+    }
+
+// Device code
+// Very simple GPU Kernel that computes square roots of input numbers
+__global__ void simpleMPIKernel(float *input, float *output)
+{
+    int tid     = blockIdx.x * blockDim.x + threadIdx.x;
+    output[tid] = sqrt(input[tid]);
+}
+
+// Initialize an array with random data (between 0 and 1)
+void initData(float *data, int dataSize)
+{
+    for (int i = 0; i < dataSize; i++) {
+        data[i] = (float)rand() / RAND_MAX;
+    }
+}
+
+// CUDA computation on each node
+// No MPI here, only CUDA
+void computeGPU(float *hostData, int blockSize, int gridSize)
+{
+    int dataSize = blockSize * gridSize;
+
+    // Allocate data on GPU memory
+    float *deviceInputData = NULL;
+    CUDA_CHECK(cudaMalloc((void **)&deviceInputData, dataSize * sizeof(float)));
+
+    float *deviceOutputData = NULL;
+    CUDA_CHECK(cudaMalloc((void **)&deviceOutputData, dataSize * sizeof(float)));
+
+    // Copy to GPU memory
+    CUDA_CHECK(cudaMemcpy(deviceInputData, hostData, dataSize * sizeof(float), cudaMemcpyHostToDevice));
+
+    // Run kernel
+    simpleMPIKernel<<<gridSize, blockSize>>>(deviceInputData, deviceOutputData);
+
+    // Copy data back to CPU memory
+    CUDA_CHECK(cudaMemcpy(hostData, deviceOutputData, dataSize * sizeof(float), cudaMemcpyDeviceToHost));
+
+    // Free GPU memory
+    CUDA_CHECK(cudaFree(deviceInputData));
+    CUDA_CHECK(cudaFree(deviceOutputData));
+}
+
+float sum(float *data, int size)
+{
+    float accum = 0.f;
+
+    for (int i = 0; i < size; i++) {
+        accum += data[i];
+    }
+
+    return accum;
+}

cpp/0_Introduction/simpleMPI/simpleMPI.h

@@ -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.
+ */
+
+/* Simple example demonstrating how to use MPI with CUDA
+ *
+ *  Generate some random numbers on one node.
+ *  Dispatch them to all nodes.
+ *  Compute their square root on each node's GPU.
+ *  Compute the average of the results using MPI.
+ *
+ *  simpleMPI.h: common header file
+ */
+
+// Forward declarations
+extern "C"
+{
+    void  initData(float *data, int dataSize);
+    void  computeGPU(float *hostData, int blockSize, int gridSize);
+    float sum(float *data, int size);
+    void  my_abort(int err);
+}