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/8_Platform_Specific/Tegra/cuDLALayerwiseStatsStandalone/.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/8_Platform_Specific/Tegra/cuDLALayerwiseStatsStandalone/.vscode/extensions.json

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

cpp/8_Platform_Specific/Tegra/cuDLALayerwiseStatsStandalone/CMakeLists.txt

@@ -0,0 +1,60 @@
+cmake_minimum_required(VERSION 3.20)
+
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../../../../cmake/Modules")
+
+project(cuDLALayerwiseStatsStandalone LANGUAGES C CXX CUDA)
+
+find_package(CUDAToolkit REQUIRED)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+set(CMAKE_CUDA_ARCHITECTURES 87 110)
+set(CMAKE_CUDA_FLAGS "${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(NVSCI)
+find_library(CUDLA_LIB cudla PATHS ${CUDAToolkit_LIBRARY_DIR} ${CMAKE_LIBRARY_PATH})
+
+if(CMAKE_SYSTEM_NAME STREQUAL "Linux")
+    if(CUDLA_LIB)
+        if(NVSCI_FOUND)
+            # Source file
+            # Add target for cuDLALayerwiseStatsStandalone
+            add_executable(cuDLALayerwiseStatsStandalone main.cpp)
+
+            target_compile_options(cuDLALayerwiseStatsStandalone PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>)
+
+            target_compile_features(cuDLALayerwiseStatsStandalone PRIVATE cxx_std_17 cuda_std_17)
+
+            set_target_properties(cuDLALayerwiseStatsStandalone PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
+
+            target_include_directories(cuDLALayerwiseStatsStandalone PUBLIC
+                ${CUDAToolkit_INCLUDE_DIRS}
+                ${NVSCI_INCLUDE_DIRS}
+            )
+
+            target_link_libraries(cuDLALayerwiseStatsStandalone
+                ${CUDLA_LIB}
+                ${NVSCI_LIBRARIES}
+            )
+        else()
+            message(STATUS "NvSCI not found - will not build sample 'cuDLALayerwiseStatsStandalone'")
+        endif()
+    else()
+        message(STATUS "CUDLA not found - will not build sample 'cuDLALayerwiseStatsStandalone'")
+    endif()
+else()
+    message(STATUS "Will not build sample cuDLALayerwiseStatsStandalone - requires Linux OS")
+endif()
+
+# Include installation configuration
+include(${CMAKE_CURRENT_SOURCE_DIR}/../../../../cmake/InstallSamples.cmake)
+setup_samples_install()

cpp/8_Platform_Specific/Tegra/cuDLALayerwiseStatsStandalone/README.md

@@ -0,0 +1,33 @@
+# cuDLALayerwiseStatsStandalone - cuDLA Layerwise Statistics Standalone Mode
+
+## Description
+
+This sample is used to provide layerwise statistics to the application in cuDLA standalone mode where DLA is programmed without using CUDA.
+
+## Key Concepts
+
+cuDLA, Data Parallel Algorithms, Image Processing
+
+## Supported SM Architectures
+
+[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, QNX
+
+## Supported CPU Architecture
+
+aarch64
+
+## CUDA APIs involved
+
+## Dependencies needed to build/run
+[NVSCI](../../../README.md#nvsci)
+
+## 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)