https://sankethbk.github.io/blog/tags/computer-architecture/Recent content in Computer-Architecture on Sanketh's BlogHugo -- 0.166.0en-usSat, 29 Aug 2026 00:00:00 +0000https://sankethbk.github.io/blog/posts/gpu/2026-08-29-anatomy-of-a-gpu/Sat, 29 Aug 2026 00:00:00 +0000https://sankethbk.github.io/blog/posts/gpu/2026-08-29-anatomy-of-a-gpu/<h1 id="anatomy-of-a-gpu-hardware-components">Anatomy of a GPU: Hardware Components</h1> <p>The <a href="https://sankethbk.github.io/blog/gpu/2026-08-29-cpu-vs-gpu">previous note</a> covered <em>why</em> GPUs look the way they do — throughput over latency, thousands of simple cores instead of a few smart ones. This note zooms into the actual silicon: what physically sits on a GPU die, what each piece is called, and what job it does. The goal is to have concrete hardware nouns (SM, warp scheduler, register file, L2, &hellip;) in hand before those same nouns start showing up as CUDA concepts (<code>threadIdx</code>, <code>__shared__</code>, occupancy, &hellip;).</p>