- Making GPUs Actually Fast: A Deep Dive into Training Performance
Making GPUs Actually Fast: A Deep Dive into Training Performance is a Jane Street YouTube talk by Corwin and Sylvain on keeping GPUs busy while training neural nets in…
100% match
· <code><optimization><kernels><memory><nvidia><part><shared><tensor> - CUDA Tile IR
CUDA Tile IR is an NVIDIA open-source GitHub repository for an MLIR-based intermediate representation and compiler stack aimed at tile-based CUDA kernel optimization on NVIDIA…
100% match
· <code><optimization><advanced><core><kernel><kernels><memory><nvidia> - Inside NVIDIA GPUs: Anatomy of high performance matmul kernels
Inside NVIDIA GPUs: Anatomy of high performance matmul kernels is a long self-contained blog post by Aleksa Gordić that teaches how near-peak NVIDIA matrix-multiply kernels are…
100% match
· <code><optimization><advanced><blog><core><kernel><kernels><matmul> - Adventures in Neural Rendering part 2: Cooperative vectors
Technical blog post by Kostas Anagnostou on Interplay of Light, part 2 of Adventures in Neural Rendering, on Cooperative Vectors for MLP inference in shaders.
92% match
· <code><optimization><advanced><blog><core><light><mma><part> - How to Think About GPUs
How to Think About GPUs is a free online chapter from How To Scale Your Model by Jacob Austin, Swapnil Patil, Adam Paszke, and Reiner Pope.
92% match
· <code><optimization><advanced><blog><b200><kernel><memory><nvidia> - Basic facts about GPUs
Basic facts about GPUs is a single technical essay by Damek Davis on his personal site.
90% match
· <code><optimization><blog><kernels><matmul><memory><nvidia><shared> - The Graphics Pipeline and Rendering Types - Game Optimization - Episode 2
The Graphics Pipeline and Rendering Types - Game Optimization - Episode 2 is a YouTube fundamentals video by Ben Cloward that opens his Game Optimization series with pipeline…
69% match
· <code><light><memory><series><shared><walks> - Warp-Level Culling for Efficient Blending in 3D Gaussian Splatting
Conference talk by Kenneth Yang on speeding up alpha-over blending in 3D Gaussian Splatting without changing the rendered image.
65% match
· <code><optimization><advanced><measured><memory><nvidia><shared> - Optimizing RTX Mega Geometry with Nsight Graphics GPU Trace
Optimizing RTX Mega Geometry with Nsight Graphics GPU Trace is an NVIDIA Game Developer talk by Calvin Chu on profiling and speeding up the RTX Mega Geometry SDK sample.
It…
65% match
· <code><optimization><advanced><memory><nvidia><shared><throughput> - GPU Memory Fundamentals
GPU Memory Fundamentals is a markdown tutorial in the cverrier/tinygrad-tutos GitHub repository on how GPU memory movement limits performance, with tinygrad examples pinned to a…
62% match
· <code><optimization><kernels><memory><speed><tensor> - Introducing CUDA Rust: Two Tracks for Writing GPU Kernels
NVIDIA Technical Blog introducing CUDA Rust via cuda-oxide (SIMT kernels compiled to PTX) and cutile-rs (tile-based kernels on stable Rust).
60% match
· <code><advanced><blog><kernels><memory><nvidia><writing> - IBL Optimization Study III: Shared memory and Latency Hiding
IBL Optimization Study III: Shared memory and Latency Hiding is the third Technik blog post by Carmelo J Fernandez-Aguera Tortosa optimizing GGX specular prefiltering for…
60% match
· <optimization><advanced><blog><memory><naive><series><shared> - Focus on Your Algorithm—NVIDIA CUDA Tile Handles the Hardware
This is an NVIDIA developer blog by Jonathan Bentz and Tony Scudiero introducing CUDA Tile in CUDA 13.1 as a virtual instruction set for tile-based GPU programming that abstracts…
58% match
· <code><blog><core><kernels><nvidia><tensor> - Performance Profiling on AMD GPUs – Part 1: Foundations
This is Part 1 of a three-part ROCm Blogs series by Gina Sitaraman, Thomas Gibson, Luka Stanisic, Giacomo Capodaglio, Alessandro Fanfarillo, and Asitav Mishra on performance…
58% match
· <optimization><blog><kernel><kernels><part><series> - GPU Programming and Language Design with Chris Lattner
GPU Programming and Language Design with Chris Lattner is a Software Unscripted podcast episode hosted by Richard Feldman with guest Chris Lattner on Mojo and GPU-oriented…
58% match
· <code><advanced><kernel><kernels><memory><tensor> - The cuda-oxide Book
The cuda-oxide Book is the online documentation for cuda-oxide, an NVIDIA Labs open-source Rust-to-CUDA compiler project.
Online book for cuda-oxide, a Rust-to-CUDA compiler…
56% match
· <code><kernel><kernels><nvidia><writing> - GPU memory management in AnKi
AnKi 3D Engine blog post on how GPU memory management evolved from custom VkDeviceMemory suballocation through GPU-driven rendering and a render-graph to placed/committed…
54% match
· <code><optimization><advanced><blog><memory><nvidia><shared> - Writing to Compressed Textures in Metal
Writing to Compressed Textures in Metal is a technical blog article by Ignacio Castaño.
Technical post on emulating compressed-texture writes on Metal by placing a BC texture…
54% match
· <code><optimization><advanced><blog><kernels><swizzling><writing> - Runtime Mipmap Generation
Runtime Mipmap Generation is a February 2026 blog post by Ignacio Castano on generating mipmaps at runtime in spark.js instead of shipping precomputed chains with compressed…
54% match
· <code><optimization><advanced><blog><kernel><memory><shared> - ONNX and DirectML execution provider guide - part 1
This AMD GPUOpen technical article by Hui Zhang is part 1 of a guide to using the ONNX Runtime DirectML execution provider with a native DirectX 12 pipeline.
54% match
· <code><optimization><advanced><blog><naive><part><steps>