Skip to content

resource.md

Latest commit

 

History

History
121 lines (110 loc) · 11.4 KB

resource.md

File metadata and controls

121 lines (110 loc) · 11.4 KB
Raw

GPU Learning PDF/PPT Resources

Collected on 2026-06-11. The 100 links below were deduplicated and checked with ranged HTTP requests.

GitHub Repositories to Remember

  • GPU Mode Lectures / clone URL: https://github.com/gpu-mode/lectures.git
    • Material for GPU Mode lectures，覆盖 CUDA、Triton、GPU kernels、性能优化等内容。
    • TODO: 后续网络稳定时可加入 submodule：git submodule add --depth 1 https://github.com/gpu-mode/lectures.git gpu-mode-lectures

NVIDIA Documentation and Training

  1. CUDA C++ Programming Guide
  2. CUDA Runtime API
  3. CUDA C++ Best Practices Guide
  4. CUDA Compiler Driver NVCC
  5. CUDA-GDB
  6. CUDA Math API
  7. cuBLAS Library
  8. cuFFT Library
  9. cuRAND Library
  10. cuSOLVER Library
  11. cuSPARSE Library
  12. PTX ISA 8.5
  13. Introduction to CUDA Platform PPTX
  14. Optimizing Parallel Reduction in CUDA
  15. CUDA Programming and Optimization

Oxford CUDA Course

  1. Pre-course Lectures
  2. Lecture 1
  3. Lecture 2
  4. Lecture 3
  5. Lecture 4
  6. Lecture 5
  7. Lecture 6
  8. Lecture 7
  9. Lecture 8
  10. Lecture 9
  11. NVIDIA Performance Debugging
  12. FlashAttention
  13. CUDA Workshop
  14. Code Generation
  15. OP2
  16. ARC Notes
  17. Nsight
  18. Practical 1
  19. Practical 2
  20. Practical 3
  21. Practical 4
  22. Practical 5
  23. Practical 6
  24. Practical 7
  25. Practical 8
  26. Practical 9
  27. Practical 10
  28. Practical 11
  29. Practical 12

Purdue NVIDIA GPU Teaching Toolkit

  1. Module 1: Overview
  2. Module 1: Heterogeneous Computing
  3. Module 1: Portability and Scalability
  4. Module 1 Intro
  5. Module 2
  6. Module 2: CUDA, Thrust, and Libraries
  7. Module 2: CUDA Data Allocation API
  8. Module 2: CUDA Parallelism and Threads
  9. Module 2: CUDA Toolkit
  10. Module 3
  11. Module 3: Kernel SPMD Parallelism
  12. Module 3: Kernel Multidimension
  13. Module 3: Color to Greyscale Image Processing Example
  14. Module 3: Blur Kernel
  15. Module 3: Transparent Scaling
  16. Module 4: CUDA Memories
  17. Module 4: Tiled Algorithms
  18. Module 4: Tiled Matrix Multiplication
  19. Module 4: Tiled Matrix Multiplication Kernel
  20. Module 4: Tile Boundary Condition
  21. Module 4
  22. Module 5: Warps and SIMD
  23. Module 5: Control Divergence
  24. Module 5: Warp Control Divergence
  25. Module 6: DRAM Bandwidth
  26. Module 6: Memory Coalescing
  27. Module 6: Coalescing
  28. Module 7: Histogram
  29. Module 9: Reductions
  30. Module 12: Floating Point
  31. Module 13: GPU Workload Performance Considerations
  32. Module 14: Data Transfer
  33. Module 20: Introduction to OpenCL
  34. Module 20: OpenCL
  35. Module 21: OpenACC

Caltech CS 179 GPU Programming

  1. CS 179 2026 Lecture 01
  2. CS 179 2026 Lecture 02
  3. CS 179 2026 Lecture 03
  4. CS 179 2026 Lecture 04
  5. CS 179 2026 Lecture 05
  6. CS 179 2026 Lecture 06
  7. CS 179 2026 Lecture 07
  8. CS 179 2026 Lecture 08
  9. CS 179 2026 Lecture 09
  10. CS 179 2026 Lecture 10
  11. CS 179 2026 Lecture 11
  12. CS 179 2026 Lecture 12
  13. CS 179 2026 Lecture 13
  14. CS 179 2026 Lecture 14
  15. CS 179 2026 Lecture 15
  16. CS 179 2026 Lecture 16
  17. CS 179 2024 Lecture 17 PPTX
  18. CS 179 2024 Lecture 17 PDF
  19. CUDA Tips PPTX
  20. CUDA Tips PDF
  21. NVIDIA RTX Blackwell GPU Architecture