Skip to content

Commit 8f52871

Browse files
coderonioncoderonion
committed
update
0 parents  commit 8f52871

File tree

5 files changed

+178
-0
lines changed

5 files changed

+178
-0
lines changed

‎.editorconfig

+12
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
# EditorConfig is awesome: https://EditorConfig.org
2+
3+
# top-most EditorConfig file
4+
root = true
5+
6+
[*]
7+
indent_style = space
8+
indent_size = 4
9+
end_of_line = lf
10+
charset = utf-8
11+
trim_trailing_whitespace = true
12+
insert_final_newline = false

‎.gitignore

+24
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
# macOS
2+
.DS_Store
3+
4+
# editor
5+
.vs/
6+
.vscode/
7+
.idea/
8+
9+
# build
10+
cmake*/
11+
build/
12+
target/
13+
14+
# files
15+
*.o
16+
*.a
17+
*.out
18+
*.dll
19+
*.lib
20+
*.obj
21+
*.exe
22+
*.lock
23+
.mdnice/
24+
*/*.md

‎README.md

+90
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,90 @@
1+
# CUDA-Beginner-Course-CPP-Version
2+
# CUDA 12.1 并行编程入门(C++语言版)
3+
4+
5+
6+
***Note that this repository is under active development.***
7+
8+
9+
10+
## Progress
11+
| Section | Videos | Codes |
12+
| :------ | :----------------------------------------------------------- | :-------------------------------------------- |
13+
| 01 | [第1集 NVIDIA CUDA介绍及Windows开发环境安装](https://www.bilibili.com/video/BV1Sj411H7Qq/) | 无 |
14+
| 02 | [第2集 Ubuntu系统下安装CUDA开发环境](https://www.bilibili.com/video/BV1je411U7yX/) | 无 |
15+
| 03 | [第3集 CUDA设备信息查看及跨平台编译第一个CUDA程序](https://www.bilibili.com/video/BV1oc411x7Gt/) | [course01_hello_cuda](./course01_hello_cuda/) |
16+
| | | |
17+
18+
19+
20+
21+
## Todo
22+
23+
- [ ] ...
24+
- [ ] ...
25+
26+
27+
28+
## Acknowledgements
29+
30+
Thanks you for the following excellent public learning resources.
31+
32+
- [codingonion/awesome-cuda-rocm-fpga](https://github.com/codingonion/awesome-cuda-rocm-fpga) <img src="https://img.shields.io/github/stars/codingonion/awesome-cuda-rocm-fpga?style=social"/> : A collection of some awesome public NVIDIA CUDA, CUDNN, TensorRT, AMD ROCm and FPGA projects.
33+
34+
- [codingonion/cuda-beginner-course-cpp-version](https://github.com/codingonion/cuda-beginner-course-cpp-version) <img src="https://img.shields.io/github/stars/codingonion/cuda-beginner-course-cpp-version?style=social"/> : bilibili视频【CUDA 12.1 并行编程入门(C++语言版)】配套代码。
35+
36+
- [codingonion/cuda-beginner-course-rust-version](https://github.com/codingonion/cuda-beginner-course-rust-version) <img src="https://img.shields.io/github/stars/codingonion/cuda-beginner-course-rust-version?style=social"/> : bilibili视频【CUDA 12.1 并行编程入门(Rust语言版)】配套代码。
37+
38+
- [codingonion/cuda-beginner-course-python-version](https://github.com/codingonion/cuda-beginner-course-python-version) <img src="https://img.shields.io/github/stars/codingonion/cuda-beginner-course-python-version?style=social"/> : bilibili视频【CUDA 12.1 并行编程入门(Python语言版)】配套代码。
39+
40+
- [NVIDIA CUDA Docs](https://docs.nvidia.com/cuda/) : CUDA Toolkit Documentation.
41+
42+
- [NVIDIA/cuda-samples](https://github.com/NVIDIA/cuda-samples) <img src="https://img.shields.io/github/stars/NVIDIA/cuda-samples?style=social"/> : Samples for CUDA Developers which demonstrates features in CUDA Toolkit.
43+
44+
- [NVIDIA/CUDALibrarySamples](https://github.com/NVIDIA/CUDALibrarySamples) <img src="https://img.shields.io/github/stars/NVIDIA/CUDALibrarySamples?style=social"/> : CUDA Library Samples.
45+
46+
- [HeKun-NVIDIA/CUDA-Programming-Guide-in-Chinese](https://github.com/HeKun-NVIDIA/CUDA-Programming-Guide-in-Chinese) <img src="https://img.shields.io/github/stars/HeKun-NVIDIA/CUDA-Programming-Guide-in-Chinese?style=social"/> : This is a Chinese translation of the CUDA programming guide. 本项目为 CUDA C Programming Guide 的中文翻译版。
47+
48+
- [brucefan1983/CUDA-Programming](https://github.com/brucefan1983/CUDA-Programming) <img src="https://img.shields.io/github/stars/brucefan1983/CUDA-Programming?style=social"/> : Sample codes for my CUDA programming book.
49+
50+
- [YouQixiaowu/CUDA-Programming-with-Python](https://github.com/YouQixiaowu/CUDA-Programming-with-Python) <img src="https://img.shields.io/github/stars/YouQixiaowu/CUDA-Programming-with-Python?style=social"/> : 关于书籍CUDA Programming使用了pycuda模块的Python版本的示例代码。
51+
52+
- [QINZHAOYU/CudaSteps](https://github.com/QINZHAOYU/CudaSteps) <img src="https://img.shields.io/github/stars/QINZHAOYU/CudaSteps?style=social"/> : 基于《cuda编程-基础与实践》（樊哲勇 著）的cuda学习之路。
53+
54+
- [sangyc10/CUDA-code](https://github.com/sangyc10/CUDA-code) <img src="https://img.shields.io/github/stars/sangyc10/CUDA-code?style=social"/> : B站视频教程【CUDA编程基础入门系列（持续更新）】配套代码。
55+
56+
- [RussWong/CUDATutorial](https://github.com/RussWong/CUDATutorial) <img src="https://img.shields.io/github/stars/RussWong/CUDATutorial?style=social"/> : A CUDA tutorial to make people learn CUDA program from 0.
57+
58+
- [DefTruth/cuda-learn-note](https://github.com/DefTruth/cuda-learn-note) <img src="https://img.shields.io/github/stars/DefTruth/cuda-learn-note?style=social"/> : 🎉CUDA 笔记 / 高频面试题汇总 / C++笔记，个人笔记，更新随缘: sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
59+
60+
- [Liu-xiandong/How_to_optimize_in_GPU](https://github.com/Liu-xiandong/How_to_optimize_in_GPU) <img src="https://img.shields.io/github/stars/Liu-xiandong/How_to_optimize_in_GPU?style=social"/> : This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.
61+
62+
- [enp1s0/ozIMMU](https://github.com/enp1s0/ozIMMU) <img src="https://img.shields.io/github/stars/enp1s0/ozIMMU?style=social"/> : FP64 equivalent GEMM via Int8 Tensor Cores using the Ozaki scheme. [arxiv.org/abs/2306.11975](https://arxiv.org/abs/2306.11975)
63+
64+
- [Bruce-Lee-LY/matrix_multiply](https://github.com/Bruce-Lee-LY/matrix_multiply) <img src="https://img.shields.io/github/stars/Bruce-Lee-LY/matrix_multiply?style=social"/> : Several common methods of matrix multiplication are implemented on CPU and Nvidia GPU using C++11 and CUDA.
65+
66+
- [Bruce-Lee-LY/cuda_hgemm](https://github.com/Bruce-Lee-LY/cuda_hgemm) <img src="https://img.shields.io/github/stars/Bruce-Lee-LY/cuda_hgemm?style=social"/> : Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.
67+
68+
- [Bruce-Lee-LY/cuda_hgemv](https://github.com/Bruce-Lee-LY/cuda_hgemv) <img src="https://img.shields.io/github/stars/Bruce-Lee-LY/cuda_hgemv?style=social"/> : Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
69+
70+
- [Cjkkkk/CUDA_gemm](https://github.com/Cjkkkk/CUDA_gemm) <img src="https://img.shields.io/github/stars/Cjkkkk/CUDA_gemm?style=social"/> : A simple high performance CUDA GEMM implementation.
71+
72+
- [AyakaGEMM/Hands-on-GEMM](https://github.com/AyakaGEMM/Hands-on-GEMM) <img src="https://img.shields.io/github/stars/AyakaGEMM/Hands-on-GEMM?style=social"/> : A GEMM tutorial.
73+
74+
- [zpzim/MSplitGEMM](https://github.com/zpzim/MSplitGEMM) <img src="https://img.shields.io/github/stars/zpzim/MSplitGEMM?style=social"/> : Large matrix multiplication in CUDA.
75+
76+
- [jundaf2/CUDA-INT8-GEMM](https://github.com/jundaf2/CUDA-INT8-GEMM) <img src="https://img.shields.io/github/stars/jundaf2/CUDA-INT8-GEMM?style=social"/> : CUDA 8-bit Tensor Core Matrix Multiplication based on m16n16k16 WMMA API.
77+
78+
- [chanzhennan/cuda_gemm_benchmark](https://github.com/chanzhennan/cuda_gemm_benchmark) <img src="https://img.shields.io/github/stars/chanzhennan/cuda_gemm_benchmark?style=social"/> : Base on gtest/benchmark, refer to [https://github.com/Liu-xiandong/How_to_optimize_in_GPU](https://github.com/Liu-xiandong/How_to_optimize_in_GPU).
79+
80+
- [YuxueYang1204/CudaDemo](https://github.com/YuxueYang1204/CudaDemo) <img src="https://img.shields.io/github/stars/YuxueYang1204/CudaDemo?style=social"/> : Implement custom operators in PyTorch with cuda/c++.
81+
82+
- [CoffeeBeforeArch/cuda_programming](https://github.com/CoffeeBeforeArch/cuda_programming) <img src="https://img.shields.io/github/stars/CoffeeBeforeArch/cuda_programming?style=social"/> : Code from the "CUDA Crash Course" YouTube series by CoffeeBeforeArch.
83+
84+
- [rbaygildin/learn-gpgpu](https://github.com/rbaygildin/learn-gpgpu) <img src="https://img.shields.io/github/stars/rbaygildin/learn-gpgpu?style=social"/> : Algorithms implemented in CUDA + resources about GPGPU.
85+
86+
- [PacktPublishing/Learn-CUDA-Programming](https://github.com/PacktPublishing/Learn-CUDA-Programming) <img src="https://img.shields.io/github/stars/PacktPublishing/Learn-CUDA-Programming?style=social"/> : Learn CUDA Programming, published by Packt.
87+
88+
- [PacktPublishing/Hands-On-GPU-Accelerated-Computer-Vision-with-OpenCV-and-CUDA](https://github.com/PacktPublishing/Hands-On-GPU-Accelerated-Computer-Vision-with-OpenCV-and-CUDA) <img src="https://img.shields.io/github/stars/PacktPublishing/Hands-On-GPU-Accelerated-Computer-Vision-with-OpenCV-and-CUDA?style=social"/> : Hands-On GPU Accelerated Computer Vision with OpenCV and CUDA, published by Packt.
89+
90+
- [PacktPublishing/Hands-On-GPU-Programming-with-Python-and-CUDA](https://github.com/PacktPublishing/Hands-On-GPU-Programming-with-Python-and-CUDA) <img src="https://img.shields.io/github/stars/PacktPublishing/Hands-On-GPU-Programming-with-Python-and-CUDA?style=social"/> : Hands-On GPU Programming with Python and CUDA, published by Packt.

‎course01_hello_cuda/CMakeLists.txt

+21
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,21 @@
1+
cmake_minimum_required(VERSION 3.22)
2+
project(course01_hello_cuda)
3+
4+
add_definitions(-arch=sm_86)
5+
if(CMAKE_SYSTEM_NAME MATCHES "Linux")
6+
set(CMAKE_CUDA_COMPILER /usr/local/cuda/bin/nvcc)
7+
endif()
8+
enable_language(CUDA)
9+
10+
set(CMAKE_CXX_STANDARD 17)
11+
set(CMAKE_CXX_STANDARD_REQUIRED ON)
12+
if(NOT CMAKE_BUILD_TYPE)
13+
set(CMAKE_BUILD_TYPE Release)
14+
endif()
15+
set(CMAKE_CXX_FLAGS "-Wall -Wextra")
16+
set(CMAKE_CXX_FLAGS_DEBUG "-g")
17+
set(CMAKE_CXX_FLAGS_RELEASE "-O3")
18+
19+
add_executable(course01_hello_cuda course01_hello_cuda.cu)
20+
set_target_properties(course01_hello_cuda PROPERTIES
21+
CUDA_SEPARABLE_COMPILATION ON)

‎course01_hello_cuda/course01_hello_cuda.cu

+31
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,31 @@
1+
#include <cstdio>
2+
3+
// CUDA核函数（CPU主机端调用，GPU设备端执行）
4+
// CUDA核函数标识符：__global__
5+
__global__ void hello_cuda_from_gpu() {
6+
printf("GPU: 你好, CUDA! (C++版)\n");
7+
}
8+
9+
// 普通函数（CPU主机端调用和执行）
10+
void hello_cuda_from_cpu() {
11+
printf("CPU: 你好, CUDA! (C++版)\n");
12+
}
13+
14+
int main() {
15+
// GPU: 你好, CUDA! (C++版)
16+
{
17+
const int GRID_DIM = 2; // grid网格大小（线程块数量）
18+
const int BLOCK_DIM = 8; // block线程块大小（每个线程块中的线程数量）
19+
// CUDA核函数调用, 核函数配置参数<<<...>>>, 核函数总线程数为2*8=16
20+
hello_cuda_from_gpu<<<GRID_DIM, BLOCK_DIM>>>(); // CUDA核函数调用
21+
cudaDeviceSynchronize(); // 同步CPU主机端和GPU设备端
22+
}
23+
printf("\n");
24+
// CPU: 你好, CUDA! (C++版)
25+
{
26+
for(int i = 0; i < 16; ++i) {
27+
hello_cuda_from_cpu();
28+
}
29+
}
30+
return 0;
31+
}

0 commit comments

Comments
 (0)