gpu architecture

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.

Dragan Djuric presents Clojure libraries for GPU and numerical computing, including ClojureCL, ClojureCUDA and Neanderthal. He shows how a dynamic REPL workflow can be combined with low-level hardware acceleration for machine learning and data science.

Linus Tech Tips looks at whether buying a used GPU that was previously used for crypto mining is a good idea, as miners prepare to sell off cards. The video discusses how mining affects wear on cards and what to watch for.

David Patterson's talk on the history of computer architecture, from RISC and superscalar designs to the end of Dennard scaling and Moore's Law. It argues that domain-specific architectures and open instruction sets open a new golden age.

SpaceX engineers present at NVIDIA's GPU Technology Conference on a multi-physics code that simulates the full-scale Raptor methane engine. It covers GPU-based turbulent combustion modeling with adaptive grids and wavelet compression.

The second talk in the Mill CPU series by Mill Computing, covering the Belt, the Mill's operand-passing model that replaces general registers. It explains the cost of register renaming in conventional wide CPUs and how the Belt reaches high instruction-level parallelism.

Level1Techs' Wendell shows Intel's Flex 170 GPU providing GPU-accelerated virtual desktops on Proxmox 8.1 without subscription licensing, using SR-IOV, and demonstrates many desktop instances running at once.

Robert C. Martin's Ruby Midwest 2011 keynote argues that software architecture should express the application's intent rather than its framework. He covers separating entities, interactors and boundaries so the web, database and framework are details.

James Howard Kunstler's TED talk argues that American public spaces and architecture have become unworthy of care, damaging civic life. He presents suburban sprawl and car-first design as failures of the common good.

Simon Brown's Agile on the Beach 2019 talk presents the C4 model, a lightweight approach to diagramming software architecture with a shared vocabulary and simple notation.

Robert C. Martin (Uncle Bob) talks about clean architecture and design, including keeping the database and frameworks out of the center of an application. It is an hour-long conference talk.

Robert C. Martin (Uncle Bob) presents the principles of Clean Architecture, covering dependency direction, boundaries, and why frameworks and databases should be details rather than the center of an application.

Linus Tech Tips tests a Chinese mining-only Nvidia card, hacked with a modified driver so it can render games and output video through an integrated GPU.

Gamers Nexus benchmarks GPU gaming performance on Linux using the Bazzite OS, an exploratory first step toward establishing a Linux testing methodology. It compares results against Windows and notes where Linux still falls short.

Mark Seemann argues that functional programming naturally yields many of the best practices object-oriented developers learn painfully. He shows how functional architecture leads to a pit of success, with a pure core and impure shell.

Brandon Rhodes' PyOhio 2014 talk on applying the Clean Architecture in Python. He shows how this high-level design pattern fits Python's features and addresses maintainability problems in large applications.

Christopher Alexander's keynote at OOPSLA 1996 on patterns in architecture, addressed to the software community. He moves beyond patterns toward deeper ideas of wholeness and living structure.

Nicholas Zakas of Yahoo discusses architecture for large, modular JavaScript web applications. He lays out the theory behind building front ends that scale in complexity.

Martin Fowler's GOTO Chicago 2017 talk on the different things people mean by event-driven architecture. He identifies four patterns, including event notification and event-carried state transfer.

Sandy Munro sits down with engineers from 3IS to compare the electrical architectures of the Tesla Model Y, Ford Mach-E and VW ID.4. They discuss ECU counts, bus architectures and what the differences mean for cost and integration.

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.

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.

Ian Cutress interviews Mike Clark, AMD's chief architect of Zen, about his career since the K5, how Zen began and how CPUs are designed. It also covers the future of AMD.

A long Mill Computing lecture on the Mill CPU's compiler toolchain, covering the specializer that targets family members, scheduling and latency passes, and the belt. It explains how the compiler handles a wide-issue, exposed-pipeline design.

Jack Moffitt presents the architecture of Servo, Mozilla's experimental browser engine written in Rust, focusing on parallelism across cores, GPUs and SIMD and the safety properties gained from Rust.

Bob Nystrom, author of Game Programming Patterns, gives a Roguelike Celebration 2018 talk questioning whether entity component systems are the only way to structure a game. He walks through alternative architectures drawn from roguelike development.

An excerpt from a Bay Area Rust meetup on Servo's WebRender, which renders CSS display lists on the GPU at very high frame rates. It explains the approach and demos rendering at around 500 FPS.

A Remedy engineer explains how Alan Wake 2 moved to a GPU-driven rendering pipeline built on mesh shaders, culling and rendering meshlets for dense vegetation on PS5 and Xbox Series consoles.

A GDC 2015 talk in which Natalya Tatarchuk describes the multithreaded renderer Bungie built for Destiny. It covers the low-latency architecture across platforms, its successes and its challenges.

PS5 lead system architect Mark Cerny gives a deep dive into the PS5's architecture, covering its SSD, I/O, audio and design goals. He explains how removing bottlenecks shapes future games.

A showcase of the author's fifth-generation quad-core computer built entirely from Minecraft redstone, after two years of development. It features cache, a hardware stack, a GPU driving a 15x15 display, and serial I/O ports.

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.

Blizzard's Timothy Ford explains in this 2017 GDC session how Overwatch uses an Entity Component System architecture for layered gameplay. He also covers its server-authoritative netcode with client-side prediction and how they keep the game responsive and fair.

Jacob Geller's video essay examines how architecture in schools and in video games, such as cover shooters, is shaped by violence. It touches on brutalism, campus policing and protests.

Louis Rossmann argues that reballing flip-chip GPUs is not a real fix for dead laptop GPUs. He explains why such repairs and oven reflow tricks fail and what is actually happening with failing hardware.

Louis Rossmann examines a 2012 MacBook Pro logic board that Apple refurbished for GPU failures and that failed again. He criticizes the quality of Apple's authorized repair work and argues for right to repair.

A demo excerpt from a 2016 Bay Area Rust meetup showing Servo's WebRender drawing CSS on the GPU at very high frame rates. It presents the promise of GPU-based browser rendering.

R. Stanley Williams of HP Labs gives a keynote on the memristor, covering the physics, crossbar computation, and potential for memory and new computer architectures.

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.