NASP/cuda-samples
84
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-10-13 00:08:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

CUDA 13.4 samples update - v13.4-public

Browse Source 
Release 13.4 of the CUDA Samples supported by CUDA Toolkit 13.4.
See Changelog for more information.
This commit is contained in:
Dheemanth
2026-09-09 15:07:08 -07:00
committed by GitHub
parent b7c5481c55
commit 5443602d89
871 changed files with 6843 additions and 321849 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
cpp/0_Introduction/matrixMul/.vscode/c_cpp_properties.json vendored
View File

@@ -1,18 +0,0 @@
{
"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
}

7
cpp/0_Introduction/matrixMul/.vscode/extensions.json vendored
View File

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

27
cpp/0_Introduction/matrixMul/CMakeLists.txt
View File

@@ -1,34 +1,25 @@
cmake_minimum_required(VERSION 3.20)
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/Modules")
include("${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/DetectCudaArch.cmake")
if(SAMPLE_SKIP_BUILD)
return()
endif()
project(matrixMul LANGUAGES C CXX CUDA)
include("${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/CudaSampleCommon.cmake")
find_package(CUDAToolkit REQUIRED)
set(CMAKE_POSITION_INDEPENDENT_CODE ON)
set(CMAKE_CUDA_ARCHITECTURES 75 80 86 87 89 90 100 110 120)
set(CMAKE_CUDA_FLAGS "${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 asyncAPI
add_executable(matrixMul matrixMul.cu)
target_compile_options(matrixMul PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>)
target_compile_features(matrixMul PRIVATE cxx_std_17 cuda_std_17)
set_target_properties(matrixMul PROPERTIES CUDA_SEPARABLE_COMPILATION ON)
# Include installation configuration
include(${CMAKE_CURRENT_SOURCE_DIR}/../../../cmake/InstallSamples.cmake)
include(InstallSamples)
setup_samples_install()

4
cpp/0_Introduction/matrixMul/README.md
View File

@@ -2,7 +2,7 @@
## Description
This sample implements matrix multiplication and is exactly the same as the second example of the [Shared Memory](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#shared-memory) section of the programming guide. It has been written for clarity of exposition to illustrate various CUDA programming principles, not with the goal of providing the most performant generic kernel for matrix multiplication. To illustrate GPU performance for matrix multiply, this sample also shows how to use the CUDA 4.0+ interface for cuBLAS to demonstrate high-performance performance for matrix multiplication.
This sample implements matrix multiplication. It has been written for clarity of exposition to illustrate various CUDA programming principles, not with the goal of providing the most performant generic kernel for matrix multiplication. To illustrate GPU performance for matrix multiply, this sample also shows how to use the CUDA 4.0+ interface for cuBLAS to demonstrate high-performance matrix multiplication.
## Key Concepts
@@ -14,7 +14,7 @@ CUDA Runtime API, Linear Algebra
## Supported OSes
Linux, Windows
Linux, Windows, QNX (QNX Safety cross-build with CUDA Safe toolkit)
## Supported CPU Architecture

16
cpp/0_Introduction/matrixMul/matrixMul.cu
View File

@@ -44,8 +44,12 @@
#include <stdio.h>
// CUDA runtime
#include <cuda_profiler_api.h>
#include <cuda_runtime.h>
// The CUDA Safe runtime does not ship the profiler API; gate it on header availability.
#if defined(__has_include) && __has_include(<cuda_profiler_api.h>)
#include <cuda_profiler_api.h>
#define HAVE_CUDA_PROFILER_API 1
#endif
// Helper functions and utilities to work with CUDA
#include <helper_cuda.h>
@@ -141,11 +145,11 @@ int MatrixMultiply(int argc, char **argv, int block_size, const dim3 &dimsA, con
unsigned int size_A = dimsA.x * dimsA.y;
unsigned int mem_size_A = sizeof(float) * size_A;
float *h_A;
checkCudaErrors(cudaMallocHost(&h_A, mem_size_A));
checkCudaErrors(cudaMallocHost(&h_A, mem_size_A, 0));
unsigned int size_B = dimsB.x * dimsB.y;
unsigned int mem_size_B = sizeof(float) * size_B;
float *h_B;
checkCudaErrors(cudaMallocHost(&h_B, mem_size_B));
checkCudaErrors(cudaMallocHost(&h_B, mem_size_B, 0));
cudaStream_t stream;
// Initialize host memory
@@ -160,7 +164,7 @@ int MatrixMultiply(int argc, char **argv, int block_size, const dim3 &dimsA, con
dim3 dimsC(dimsB.x, dimsA.y, 1);
unsigned int mem_size_C = dimsC.x * dimsC.y * sizeof(float);
float *h_C;
checkCudaErrors(cudaMallocHost(&h_C, mem_size_C));
checkCudaErrors(cudaMallocHost(&h_C, mem_size_C, 0));
if (h_C == NULL) {
fprintf(stderr, "Failed to allocate host matrix C!\n");
@@ -334,9 +338,13 @@ int main(int argc, char **argv)
printf("MatrixA(%d,%d), MatrixB(%d,%d)\n", dimsA.x, dimsA.y, dimsB.x, dimsB.y);
#ifdef HAVE_CUDA_PROFILER_API
checkCudaErrors(cudaProfilerStart());
#endif
int matrix_result = MatrixMultiply(argc, argv, block_size, dimsA, dimsB);
#ifdef HAVE_CUDA_PROFILER_API
checkCudaErrors(cudaProfilerStop());
#endif
exit(matrix_result);
}