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/2_Concepts_and_Techniques/inlinePTX/.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/2_Concepts_and_Techniques/inlinePTX/.vscode/extensions.json

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

cpp/2_Concepts_and_Techniques/inlinePTX/CMakeLists.txt

@@ -0,0 +1,34 @@
+cmake_minimum_required(VERSION 3.20)
+
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/Modules")
+
+project(inlinePTX LANGUAGES C CXX CUDA)
+
+find_package(CUDAToolkit REQUIRED)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+set(CMAKE_CUDA_ARCHITECTURES 75 80 86 87 89 90 100 110 120)
+set(CMAKE_CUDA_FLAGS "${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 inlinePTX
+add_executable(inlinePTX inlinePTX.cu)
+
+target_compile_options(inlinePTX PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>)
+
+target_compile_features(inlinePTX PRIVATE cxx_std_17 cuda_std_17)
+
+set_target_properties(inlinePTX PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
+
+# Include installation configuration
+include(${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/InstallSamples.cmake)
+setup_samples_install()

cpp/2_Concepts_and_Techniques/inlinePTX/README.md

@@ -0,0 +1,32 @@
+# inlinePTX - Using Inline PTX
+
+## Description
+
+A simple test application that demonstrates a new CUDA 4.0 ability to embed PTX in a CUDA kernel.
+
+## Key Concepts
+
+Performance Strategies, PTX Assembly, CUDA Driver API
+
+## 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)
+cudaMemcpy, cudaFree, cudaMallocHost, cudaGetLastError, cudaGridSize, cudaBlockSize, cudaDeviceSynchronize, cudaFreeHost, cudaMalloc
+
+## Prerequisites
+
+Download and install the [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads) for your corresponding platform.
+
+## References (for more details)

cpp/2_Concepts_and_Techniques/inlinePTX/inlinePTX.cu

@@ -0,0 +1,108 @@
+/* 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.
+ */
+
+/*
+ * Demonstration of inline PTX (assembly language) usage in CUDA kernels
+ */
+
+// System includes
+#include <assert.h>
+#include <stdio.h>
+
+// CUDA runtime
+#include <cuda_runtime.h>
+
+// helper functions and utilities to work with CUDA
+#include <helper_cuda.h>
+#include <helper_functions.h>
+
+__global__ void sequence_gpu(int *d_ptr, int length)
+{
+    int elemID = blockIdx.x * blockDim.x + threadIdx.x;
+
+    if (elemID < length) {
+        unsigned int laneid;
+        // This command gets the lane ID within the current warp
+        asm("mov.u32 %0, %%laneid;" : "=r"(laneid));
+        d_ptr[elemID] = laneid;
+    }
+}
+
+
+void sequence_cpu(int *h_ptr, int length)
+{
+    for (int elemID = 0; elemID < length; elemID++) {
+        h_ptr[elemID] = elemID % 32;
+    }
+}
+
+int main(int argc, char **argv)
+{
+    printf("CUDA inline PTX assembler sample\n");
+
+    const int N = 1000;
+
+    int dev = findCudaDevice(argc, (const char **)argv);
+
+    if (dev == -1) {
+        return EXIT_FAILURE;
+    }
+
+    int *d_ptr;
+    checkCudaErrors(cudaMalloc(&d_ptr, N * sizeof(int)));
+
+    int *h_ptr;
+    checkCudaErrors(cudaMallocHost(&h_ptr, N * sizeof(int)));
+
+    dim3 cudaBlockSize(256, 1, 1);
+    dim3 cudaGridSize((N + cudaBlockSize.x - 1) / cudaBlockSize.x, 1, 1);
+    sequence_gpu<<<cudaGridSize, cudaBlockSize>>>(d_ptr, N);
+    checkCudaErrors(cudaGetLastError());
+    checkCudaErrors(cudaDeviceSynchronize());
+
+    sequence_cpu(h_ptr, N);
+
+    int *h_d_ptr;
+    checkCudaErrors(cudaMallocHost(&h_d_ptr, N * sizeof(int)));
+    checkCudaErrors(cudaMemcpy(h_d_ptr, d_ptr, N * sizeof(int), cudaMemcpyDeviceToHost));
+
+    bool bValid = true;
+
+    for (int i = 0; i < N && bValid; i++) {
+        if (h_ptr[i] != h_d_ptr[i]) {
+            bValid = false;
+        }
+    }
+
+    printf("Test %s.\n", bValid ? "Successful" : "Failed");
+
+    checkCudaErrors(cudaFree(d_ptr));
+    checkCudaErrors(cudaFreeHost(h_ptr));
+    checkCudaErrors(cudaFreeHost(h_d_ptr));
+
+    return bValid ? EXIT_SUCCESS : EXIT_FAILURE;
+}