2. Getting Started
3. 🔥 Introduction
4. 🧭 Puzzles Usage Guide
5. 🏆 Claim Your Rewards
7. Part I: GPU Fundamentals
8. Puzzle 1: Map
9. 1. 🔰 Raw Memory Approach
   2. 💡 Preview: Modern Approach with LayoutTensor
10. Puzzle 2: Zip
11. Puzzle 3: Guards
12. Puzzle 4: 2D Map
13. 1. 🔰 Raw Memory Approach
    2. 📚 Learn about LayoutTensor
    3. 🚀 Modern 2D Operations
14. Puzzle 5: Broadcast
15. 1. 🔰 Raw Memory Approach
    2. 📐 LayoutTensor Version
16. Puzzle 6: Blocks
17. Puzzle 7: 2D Blocks
18. 1. 🔰 Raw Memory Approach
    2. 📐 LayoutTensor Version
19. Puzzle 8: Shared Memory
20. 1. 🔰 Raw Memory Approach
    2. 📐 LayoutTensor Version
22. Part II: 🐞 Debugging GPU Programs
23. Puzzle 9: GPU Debugging Workflow
24. 1. 📚 Mojo GPU Debugging Essentials
    2. 🧐 Detective Work: First Case
    3. 🔍 Detective Work: Second Case
    4. 🕵 Detective Work: Third Case
25. Puzzle 10: Memory Error Detection & Race Conditions with Sanitizers
26. 1. 👮🏼‍♂️ Detect Memory Violation
    2. 🏁 Debug Race Condition
28. Part III: 🧮 GPU Algorithms
29. Puzzle 11: Pooling
30. 1. 🔰 Raw Memory Approach
    2. 📐 LayoutTensor Version
31. Puzzle 12: Dot Product
32. 1. 🔰 Raw Memory Approach
    2. 📐 LayoutTensor Version
33. Puzzle 13: 1D Convolution
34. 1. 🔰 Simple Version
    2. ⭐ Block Boundary Version
35. Puzzle 14: Prefix Sum
36. 1. 🔰 Simple Version
    2. ⭐ Complete Version
37. Puzzle 15: Axis Sum
38. Puzzle 16: Matrix Multiplication (MatMul)
39. 1. 🔰 Naïve Version with Global Memory
    2. 📚 Learn about Roofline Model
    3. 🤝 Shared Memory Version
    4. 📐 Tiled Version
41. Part IV: 🐍 Interfacing with Python via MAX Graph Custom Ops
42. Puzzle 17: 1D Convolution Op
43. Puzzle 18: Softmax Op
44. Puzzle 19: Attention Op
45. 🎯 Bonus Challenges
47. Part V: 🔥 PyTorch Custom Ops Integration
48. Puzzle 20: 1D Convolution Op
49. Puzzle 21: Embedding Op
50. 1. 🔰 Coaleasced vs non-Coaleasced Kernel
    2. 📊 Performance Comparison
51. Puzzle 22: Kernel Fusion and Custom Backward Pass
52. 1. ⚛️ Fused vs Unfused Kernels
    2. ⛓️ Autograd Integration & Backward Pass
54. Part VI: 🌊 Mojo Functional Patterns and Benchmarking
55. Puzzle 23: GPU Functional Programming Patterns
56. 1. elementwise - Basic GPU Functional Operations
    2. tile - Memory-Efficient Tiled Processing
    3. vectorize - SIMD Control
    4. 🧠 GPU Threading vs SIMD Concepts
    5. 📊 Benchmarking in Mojo
58. Part VII: ⚡ Warp-Level Programming
59. Puzzle 24: Warp Fundamentals
60. 1. 🧠 Warp lanes & SIMT execution
    2. 🔰 warp.sum() Essentials
    3. 🤔 When to Use Warp Programming
61. Puzzle 25: Warp Communication
62. 1. ⬇️ warp.shuffle_down()
    2. 📢 warp.broadcast()
63. Puzzle 26: Advanced Warp Patterns
64. 1. 🦋 warp.shuffle_xor() Butterfly Networks
    2. 🔢 warp.prefix_sum() Scan Operations
66. Part VIII: 🧱 Block-Level Programming
67. Puzzle 27: Block-Wide Patterns
68. 1. 🔰 block.sum() Essentials
    2. 📈 block.prefix_sum() Parallel Histogram Binning
    3. 📡 block.broadcast() Vector Normalization
70. Part IX: 🧠 Advanced Memory Systems
71. Puzzle 28: Async Memory Operations & Copy Overlap
72. Puzzle 29: GPU Synchronization Primitives
73. 1. 📶 Multi-Stage Pipeline Coordination
    2. Double-Buffered Stencil Computation
75. Part X: 📊 Performance Analysis & Optimization
76. Puzzle 30: GPU Profiling
77. 1. 📚 NVIDIA Profiling Basics
    2. 🕵 The Cache Hit Paradox
78. Puzzle 31: Occupancy Optimization
79. Puzzle 32: Bank Conflicts
80. 1. 📚 Understanding Shared Memory Banks
    2. Conflict-Free Patterns
82. Part XI: 🚀 Advanced GPU Features
83. Puzzle 33: Tensor Core Operations
84. 1. 🎯 Performance Bonus Challenge
85. Puzzle 34: GPU Cluster Programming (SM90+)
86. 1. 🔰 Multi-Block Coordination Basics
    2. ☸️ Cluster-Wide Collective Operations
    3. 🧠 Advanced Cluster Algorithms