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/1_Utilities/topologyQuery/.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/1_Utilities/topologyQuery/.vscode/extensions.json

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

cpp/1_Utilities/topologyQuery/CMakeLists.txt

@@ -0,0 +1,38 @@
+cmake_minimum_required(VERSION 3.20)
+
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/Modules")
+
+project(topologyQuery LANGUAGES C CXX CUDA)
+
+find_package(CUDAToolkit REQUIRED)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+set(CMAKE_CUDA_ARCHITECTURES 75 80 86 87 89 90 100 110 120)
+set(CMAKE_CUDA_FLAGS "${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)
+
+if(CMAKE_SYSTEM_PROCESSOR STREQUAL "aarch64")
+    message(STATUS "Will not build sample topologyQuery - not supported on aarch64")
+else()
+    # Source file
+    # Add target for topologyQuery
+    add_executable(topologyQuery topologyQuery.cu)
+
+    target_compile_options(topologyQuery PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>)
+
+    target_compile_features(topologyQuery PRIVATE cxx_std_17 cuda_std_17)
+
+    set_target_properties(topologyQuery PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
+endif()
+
+# Include installation configuration
+include(${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/InstallSamples.cmake)
+setup_samples_install()

cpp/1_Utilities/topologyQuery/README.md

@@ -0,0 +1,32 @@
+# topologyQuery - Topology Query
+
+## Description
+
+A simple exemple on how to query the topology of a system with multiple GPU
+
+## Key Concepts
+
+Performance Strategies, Multi-GPU
+
+## 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, ppc64le
+
+## CUDA APIs involved
+
+### [CUDA Runtime API](http://docs.nvidia.com/cuda/cuda-runtime-api/index.html)
+cudaGetDeviceCount, cudaDeviceGetAttribute
+
+## Prerequisites
+
+Download and install the [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+
+## References (for more details)

cpp/1_Utilities/topologyQuery/topologyQuery.cu

@@ -0,0 +1,78 @@
+/* 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 sample demonstrates how to use query information on the current system
+ * topology using a SDK 8.0 API.
+ */
+
+// includes CUDA
+#include <cuda_runtime.h>
+
+// includes, project
+#include <helper_cuda.h>
+#include <helper_functions.h> // helper for shared that are common to CUDA Samples
+
+int main(int argc, char **argv)
+{
+    int deviceCount = 0;
+    checkCudaErrors(cudaGetDeviceCount(&deviceCount));
+
+    // Enumerates Device <-> Device links
+    for (int device1 = 0; device1 < deviceCount; device1++) {
+        for (int device2 = 0; device2 < deviceCount; device2++) {
+            if (device1 == device2)
+                continue;
+
+            int perfRank        = 0;
+            int atomicSupported = 0;
+            int accessSupported = 0;
+
+            checkCudaErrors(
+                cudaDeviceGetP2PAttribute(&accessSupported, cudaDevP2PAttrAccessSupported, device1, device2));
+            checkCudaErrors(cudaDeviceGetP2PAttribute(&perfRank, cudaDevP2PAttrPerformanceRank, device1, device2));
+            checkCudaErrors(
+                cudaDeviceGetP2PAttribute(&atomicSupported, cudaDevP2PAttrNativeAtomicSupported, device1, device2));
+
+            if (accessSupported) {
+                std::cout << "GPU" << device1 << " <-> GPU" << device2 << ":" << std::endl;
+                std::cout << "  * Atomic Supported: " << (atomicSupported ? "yes" : "no") << std::endl;
+                std::cout << "  * Perf Rank: " << perfRank << std::endl;
+            }
+        }
+    }
+
+    // Enumerates Device <-> Host links
+    for (int device = 0; device < deviceCount; device++) {
+        int atomicSupported = 0;
+        checkCudaErrors(cudaDeviceGetAttribute(&atomicSupported, cudaDevAttrHostNativeAtomicSupported, device));
+        std::cout << "GPU" << device << " <-> CPU:" << std::endl;
+        std::cout << "  * Atomic Supported: " << (atomicSupported ? "yes" : "no") << std::endl;
+    }
+
+    return 0;
+}