2. Getting Started
  3. 🔥 Introduction
  4. 🧭 Puzzles Usage Guide
  6. Part I: GPU Fundamentals
  7. Puzzle 1: Map
    1. 🔰 Raw Memory Approach
    2. 💡 Preview: Modern Approach with LayoutTensor
  9. Puzzle 2: Zip
  10. Puzzle 3: Guards
  11. Puzzle 4: 2D Map
    1. 🔰 Raw Memory Approach
    2. 📚 Learn about LayoutTensor
    3. 🚀 Modern 2D Operations
  13. Puzzle 5: Broadcast
    1. 🔰 Raw Memory Approach
    2. 📐 LayoutTensor Version
  15. Puzzle 6: Blocks
  16. Puzzle 7: 2D Blocks
    1. 🔰 Raw Memory Approach
    2. 📐 LayoutTensor Version
  18. Puzzle 8: Shared Memory
    1. 🔰 Raw Memory Approach
    2. 📐 LayoutTensor Version
  21. Part II: 🧮 GPU Algorithms
  22. Puzzle 9: Pooling
    1. 🔰 Raw Memory Approach
    2. 📐 LayoutTensor Version
  24. Puzzle 10: Dot Product
    1. 🔰 Raw Memory Approach
    2. 📐 LayoutTensor Version
  26. Puzzle 11: 1D Convolution
    1. 🔰 Simple Version
    2. ⭐ Block Boundary Version
  28. Puzzle 12: Prefix Sum
    1. 🔰 Simple Version
    2. ⭐ Complete Version
  30. Puzzle 13: Axis Sum
  31. Puzzle 14: Matrix Multiplication (MatMul)
    1. 🔰 Naïve Version with Global Memory
    2. 📚 Learn about Roofline Model
    3. 🤝 Shared Memory Version
    4. 📐 Tiled Version
  34. Part III: 🐍 Interfacing with Python via MAX Graph Custom Ops
  35. Puzzle 15: 1D Convolution Op
  36. Puzzle 16: Softmax Op
  37. Puzzle 17: Attention Op
  38. 🎯 Bonus Challenges
  40. Part IV: 🔥 PyTorch Custom Ops Integration
  41. Puzzle 18: 1D Convolution Op
  42. Puzzle 19: Embedding Op
    1. 🔰 Coaleasced vs non-Coaleasced Kernel
    2. 📊 Performance Comparison
  44. Puzzle 20: Kernel Fusion and Custom Backward Pass
    1. ⚛️ Fused vs Unfused Kernels
    2. ⛓️ Autograd Integration & Backward Pass
  47. Part V: 🌊 Mojo Functional Patterns and Benchmarking
  48. Puzzle 21: GPU Functional Programming Patterns
    1. elementwise - Basic GPU Functional Operations
    2. tile - Memory-Efficient Tiled Processing
    3. Vectorization - SIMD Control
    4. 🧠 GPU Threading vs SIMD Concepts
    5. 📊 Benchmarking in Mojo
  51. Part VI: ⚡ Warp-Level Programming
  52. Puzzle 22: Warp Fundamentals
    1. 🧠 Warp lanes & SIMT execution
    2. 🔰 warp.sum() Essentials
    3. 📊 When to Use Warp Programming
  54. Puzzle 23: Warp Communication
    1. ⬇️ warp.shuffle_down()
    2. 📢 warp.broadcast()
  56. Puzzle 24: Advanced Warp Patterns
    1. 🦋 warp.shuffle_xor() Butterfly Networks
    2. 🔢 warp.prefix_sum() Scan Operations
  59. Part VII: Advanced Memory Operations
  60. Puzzle 25: Memory Coalescing
    1. 📚 Understanding Coalesced Access
    2. Optimized Access Patterns
    3. 🔧 Troubleshooting Memory Issues
  62. Puzzle 26: Async Memory Operations
  63. Puzzle 27: Memory Fences & Atomics
  64. Puzzle 28: Prefetching & Caching
  66. Part VIII: 📊 Performance Analysis & Optimization
  67. Puzzle 29: GPU Profiling Basics
  68. Puzzle 30: Occupancy Optimization
  69. Puzzle 31: Bank Conflicts
    1. 📚 Understanding Shared Memory Banks
    2. Conflict-Free Patterns
  72. Part IX: 🚀 Advanced GPU Features
  73. Puzzle 32: Tensor Core Operations
  74. Puzzle 33: Random Number Generation
  75. Puzzle 34: Advanced Synchronization
  77. Part X: 🌐 Multi-GPU & Advanced Applications
  78. Puzzle 35: Multi-Stream Programming
  79. Puzzle 36: Multi-GPU Basics
  80. Puzzle 37: End-to-End Optimization Case Study
  81. 🎯 Advanced Bonus Challenges