gpu

A Gamers Nexus investigative documentary on the black market for Nvidia AI GPUs, following smugglers, middlemen, and buyers, including reporting from China. It examines how export-restricted chips reach their users.

A long George Hotz live-stream from June 2023 in which he works on tinygrad and rants about AMD's drivers, ultimately declaring he is giving up on AMD. It also touches on hardware and compiler topics.

Olivier Giroux's CppCon 2019 talk recounts the roughly ten-year effort to bring std::atomic and the C++ memory model to CUDA GPUs, through ten stories from that work.

Bill Dally of NVIDIA gives a Hot Chips 2023 keynote on the challenges of building hardware for deep learning. He traces how GPUs have been adapted for machine learning, especially training.

Brian Karis's SIGGRAPH 2021 talk explains how Unreal Engine 5's Nanite virtualized geometry works. It covers mesh import, the data structures, streaming, decompression, culling, software and hardware rasterization, and shading.

A Computer History Museum oral history panel with four 3dfx founders on the company's rise with Voodoo Graphics and Glide, and its fall into bankruptcy. It runs about two and a half hours.

Bill Dally of NVIDIA gives a University of Washington lecture on trends in deep learning hardware. It covers numeric formats, specialized instructions, energy per operation and co-design of hardware and software.

John Carmack's keynote at Oculus Connect 2014 about the Gear VR and development stories from building it. He discusses mobile GPU optimization, latency, and display ideas like programmable interlacing.

Freya Holmer's 74-minute video essay on splines, covering Bezier curves, B-splines, derivatives and the different levels of continuity (C0, C1, C2), built with custom animation tools. She notes she did not cover non-uniform splines.

Robert Wills of TNMoC explains the Apollo Guidance Computer hardware and software, then walks through the Apollo 11 landing procedure step by step, including the 1202 alarms.

Casey Muratori's long talk arguing that modern software has ballooned to tens of millions of lines because of hardware and OS diversity. He proposes a stable ISA for entire system-on-a-chip packages and recalls when games shipped with their own boot disk.

Michael Steil's 33c3 talk explains essentially everything about the Game Boy: CPU, video hardware, peripherals, and the tricks used by games and demos. It revives the era of counting clock cycles around hardware limits.

A SIGGRAPH 2019 course on geometric algebra. Charles Gunn gives an intro, then Steven De Keninck gives a programmer-focused course with live examples in ganja.js.

Timothy Roscoe of ETH Zurich delivers the joint USENIX ATC/OSDI 2021 keynote arguing that operating systems must reckon with modern hardware, which is a heterogeneous collection of processors, firmware and coprocessors rather than a simple machine. It shows how much runs below and beside Linux.

Lex Fridman interviews legendary chip architect Jim Keller about Moore's Law, microprocessor design, and first-principles thinking. Keller draws on his work at AMD, Apple, Tesla and Intel, discussing instruction sets, transistor budgets, and self-driving.

Michael Steil and Christian Hessmann's 34C3 talk explaining the Apollo Guidance Computer end to end: hardware design, operating system, and mission software.

Jim Keller gives a UC Berkeley EECS colloquium arguing that Moore's Law is not dead. He surveys upcoming technologies and the multiple innovation curves that can keep transistor density and performance scaling.

A lecture by Richard Feynman on how computers work, using the analogy of a filing clerk that becomes progressively dumber and faster. It also covers heuristics and how computers handle data and solve problems in finite time.

Casey Muratori's University of Twente guest lecture is a case study in how straightforward code can cut thousands of lines and tens of seconds of runtime down to a few dozen lines running in under a second. It uses concrete examples to show why software is often an order of magnitude slower than it should be.

Herb Sutter's deep C++ and Beyond 2012 talk on atomics and the C++ memory model, covering why programmers chasing top performance need to understand hardware ordering. This is part one of two.

Bryan Cantrill of Oxide Computer Company gives a Stanford EE380 talk on rethinking the server. He argues that hyperscaler-style rack-scale machines with open firmware, RISC-V and Rust should be available to everyone, not just the giants.

Cliff Click of Azul Systems gives a Google Tech Talk on running Java business applications on a machine with about a thousand cores. He covers hardware and software codesign, including garbage collection hardware and the JIT.

Simon Peyton Jones explains nested data parallelism and Data Parallel Haskell, an approach to exploiting multicore and distributed hardware while keeping a simple single-control-flow programming model.

The first lecture in an 18-part series on digital photography from Marc Levoy's Stanford CS 178 course, recorded at Google in 2016. The series covers how digital cameras work and computational photography, with slides and assignments available on the course site.

Chandler Carruth shows how to squeeze more performance out of already-optimized C++ code, covering how the CPU executes it. The talk goes into pipelining, branch prediction and speculative execution using benchmarks.

Hennessy and Patterson's 2018 Turing Award lecture at ISCA, A New Golden Age for Computer Architecture. It covers domain-specific hardware, security, open instruction sets and agile chip development.

GDC 2019 session where Insomniac's David Santiago describes the procedural systems used to build Manhattan for Marvel's Spider-Man. It covers the open-world pipeline and how each system was designed to support iteration and dependencies.

Ian Cutress interviews chip architect Jim Keller about his time at AMD, Intel and elsewhere, management advice, design approach, Moore's Law and x86 versus Arm.

Scott Meyers explains how CPU caches work and why they matter for performance, covering cache levels, access speeds, associativity, and effects in multithreaded code. The focus is C++ and cache-aware, data-oriented programming.

Fedor Pikus's CppCon 2017 talk on C++ atomics, looking at what they let the programmer express and what the hardware actually does. It covers memory ordering and lock-free programming from basic to advanced.

Michael Steil's 25C3 talk covers the Commodore 64's architecture, quirks and demoscene tricks in about an hour. It aims to convey everything about the machine in a compact, nostalgic tour.

Lex Fridman interviews chip architect Jim Keller about the future of computing, AI, life and consciousness. Topics include CPU design, branch prediction and why imperfect designs often win.

Ubisoft procedural technical artist Etienne Carrier explains the Houdini-based tools used to build Far Cry 5's roughly 100 square km open world. It covers generating biomes, texturing terrain, freshwater networks, cliff rocks and vegetation placement.

Cathode Ray Dude's hour-long retrospective on the ABIT BP6, the dual-Celeron motherboard. He covers early multiprocessing, its legend, a build, running NT 4, benchmarks and the pros and cons of early SMP.

John Gustafson presents posits, a proposed drop-in replacement for IEEE 754 floats that is simpler in hardware and more flexible in precision. The seminar includes a live demo and machine learning results.

The first part of Freya Holmer's three-part, nearly four-hour lecture on shader coding for game devs in Unity. It covers what shaders are, vertex and fragment shaders, interpolators, data types, blending and textures.

Part two of Herb Sutter's C++ and Beyond 2012 session on atomic weapons, a deep dive into the C++ memory model, atomics, memory ordering, and hardware behavior. It ends with the modern meaning of volatile.

A full-day recording of the University of Utah computer science department's 50th anniversary event with panels, keynotes and talks by alumni and pioneers. It includes Ivan Sutherland's presentation on single flux quantum electronics.

Inigo Quilez live-codes the "Happy Jumping" animated scene in a Shadertoy GLSL shader over about six hours. He builds the raymarched character step by step, explaining the math and procedural techniques, with checkpoints linked for each stage.

A Stanford EE380 seminar by Michael P. Frank of Sandia National Laboratories on generalized reversible computing. It surveys unconventional computing approaches as transistor scaling nears its limits and energy efficiency stops improving.