Skip to content
CUDA From First Principles — Under Development
B. Practice Quiz
Initializing search
CUDA From First Principles — Under Development
Home
Getting Started
Part 0 — CUDA Foundations
Part 0 — CUDA Foundations
1. Variables and Types
2. Struct Design Patterns
3. Memory Layout Strategies
4. GPU Programming Introduction
5. SIMD and Vectorization
Part 1 — Core Tensor Infrastructure
Part 1 — Core Tensor Infrastructure
6. The Tensor
7. Memory Layout Design
8. Tensor Creation Functions
9. Specialized Tensor Types
10. Device Abstraction Layer
11. Memory Management System
Part 2 — Basic Tensor Operations
Part 2 — Basic Tensor Operations
12. Element-wise Operations
13. Matrix Operations
14. Reduction Operations
Part 3 — Computational Graph Foundation
Part 3 — Computational Graph Foundation
15. Graph Node Architecture
Part 4 — Automatic Differentiation Engine
Part 4 — Automatic Differentiation Engine
16. Backward Function Implementation
17. Gradient Computation Engine
Part 5 — GPU Acceleration and Performance
Part 5 — GPU Acceleration and Performance
18. GPU Kernel Implementation
19. Performance Optimization Techniques
Part 6 — Neural Network Building Blocks
Part 6 — Neural Network Building Blocks
20. Neural Network Layers
21. Advanced Features
Part 7 — Financial Computing Applications
Part 7 — Financial Computing Applications
22. Quantitative Finance Examples
Appendix
Appendix
A. Installation & Setup
B. Practice Quiz
C. CUDA Memory Architecture
D. C++ Functional and Lambda Programming
E. The SM as a Pipeline and the Tiling Payoff
F. C++ Lambda Functions, From First Principles
G. The Rule of Five, and a Risk Engine to Exercise It
H. Tensor Contractions, From First Principles (CPU)
I. Tensor Contractions, From First Principles (GPU)
J. Heap versus Stack, and Pinned versus Pageable Memory
K. Matrix Traversal, Grids, and Boundary Checks
Appendix B: Practice Quiz
¶
Not yet written.
Back to top