https://harisudarsan1.github.io/blog/tags/gpu/Recent content in Gpu on Hari's BlogHugoen-ushttps://harisudarsan1.github.io/blog/posts/2026-06-09-gpu-cuda-learning-path/Mon, 01 Jan 0001 00:00:00 +0000https://harisudarsan1.github.io/blog/posts/2026-06-09-gpu-cuda-learning-path/<h2 id="tier-1-gpu-architecture-deep-understanding">Tier 1: GPU Architecture (deep understanding)</h2> <h3 id="stanford-cs149-lecture-7--kayvon-fatahalian">Stanford CS149 Lecture 7 — Kayvon Fatahalian</h3> <p>The best lecture on SIMT execution model, warp scheduling, memory hierarchy, and occupancy. Start here. Videos on YouTube.</p> <p><strong>URL:</strong> <a href="https://cs149.stanford.edu">https://cs149.stanford.edu</a></p> <h3 id="programming-massively-parallel-processors--kirk-hwu-el-hajj-4th-ed">&ldquo;Programming Massively Parallel Processors&rdquo; — Kirk, Hwu, El Hajj (4th ed.)</h3> <p>The canonical textbook. Chapters 1-4 = architecture fundamentals. 4th edition covers tensor cores and Hopper.</p> <p><strong>URL:</strong> <a href="https://www.sciencedirect.com/book/9780124159921/programming-massively-parallel-processors">https://www.sciencedirect.com/book/9780124159921/programming-massively-parallel-processors</a></p> <h3 id="brendan-lynskey--nvidia-gpu-architectures-series">Brendan Lynskey — NVIDIA GPU Architectures Series</h3> <p>Deep dives on warp scheduling internals, SIMT vs SIMD nuance, memory latency per architecture, TMA on Hopper. Diagrams + assembly snippets.</p>