interactive GPU from scratch

MVIDIA FROM TRANSISTORS TO TERAFLOPS MEMO FROM: THE CEO Welcome to Mvidia! I know your resume said “software engineer” but honestly we need someone on the hardware side. Don’t worry, you’ll pick it up. Start with the basics — we ordered a shipment of transistors. START ← jaso1024 v0.1.0 ← BACK ACT 1: YOUR FIRST DAY Transistors → Logic Gates 1/10 COMPLETED ▶ INTRO: From Sand to Switch 0/7 Optional background on how transistors are made 1.1 The Switch NMOS as a switch "Flip it on, flip it off. How hard can it be?" ✓ 1.2 The Other Switch PMOS as a switch "Apparently there's a second kind. Who knew." 44s 1.3 Two Halves Requires: The Switch 1.4 NAND It Requires: Two Halves 1.5 The Dual Requires: NAND It 1.6 Truth Tables Requires: The Dual 1.7 AND Gate Requires: The Dual 1.8 OR Gate Requires: The Dual 1.9 XOR Gate Requires: The Dual 1.10 Choose Wisely Requires: AND Gate, OR Gate, XOR Gate UNLOCKS ACT 2 ▼ ACT 2: THE CORE Gates → ALU → Processor 0/38 COMPLETED 2.1 Half Adder Requires: Choose W

Before we wire a single transistor, I need to know you understand what electricity actually is. Not just "it powers things" — I mean electrons, voltage, current. The real stuff. Go. Here is the weird part. In a semiconductor, current is not carried only by free electrons. When an electron escapes its bond, it leaves a gap — and that gap moves. We call it a hole. It acts like a positive charge moving in the opposite direction. You need to understand this before we go any further. Before you wire anything, you need to understand the material. Silicon is a semiconductor -- it barely conducts on i

saved by

• Denys

related reading

• Computing with Transistors - Andrew Gibianskyandrew.gibiansky.com
• Could a Neuroscientist Understand a Microprocessor? | PLOS Computational Biologyjournals.plos.org
• Dwarkesh Patel on X: "New blackboard lecture w @reinerpope How do chips actually work – starting with basic logic gates, and working up to why GPUs, TPUs, FPGAs, and the human brain each look the way they do. 0:00:00 – Building a multiply-ax.com
• Inside NVIDIA GPUs: Anatomy of high performance matmul kernels - Aleksa Gordićaleksagordic.com
• Tiny TPUtinytpu.com
• The Tinkerings of Robert Noyceweb.stanford.edu
• What Every Programmer Should Know About Memorypeople.freebsd.org
• GitHub - adam-maj/tiny-gpu: A minimal GPU design in Verilog to learn how GPUs work from the ground up · GitHubgithub.com
• Lab 3: State and Registers | Computer Architecturecomp.anu.edu.au
• MoNETA: A Mind Made from Memristors - IEEE Spectrumspectrum.ieee.org
• Demystifying GPU Compute Architectures - by Babbagethechipletter.substack.com
• INTELLIGENCEstacks.stanford.edu