@vivekgalatage: Best structured reference I've found for GPU optimization - 450 papers, 14 years of research. Some techniques will have…
Summary
A tweet shares a structured reference of 450 papers on GPU optimization spanning 14 years, noting that while some techniques evolve, the mental models remain useful. It also references a lecture on GPU architectures by Onur Mutlu.
View Cached Full Text
Cached at: 05/21/26, 10:22 AM
Best structured reference I’ve found for GPU optimization - 450 papers, 14 years of research. Some techniques will have evolved, but the mental models hold up.
https://t.co/2kFfsEq31h https://t.co/0jmUz9OUsX
Vivek Galatage (@vivekgalatage): Yesterday’s lecture on GPU Architectures by @onurmutlu
Similar Articles
@chessMan786: Fundamentals of GPU Architecture
A tweet shares a link to an article about the fundamentals of GPU architecture.
@DanKornas: GPU engineering is too broad to learn from random tabs. Awesome GPU Engineering is a curated GitHub list of resources f…
A curated GitHub list of resources for learning GPU engineering, covering architecture, kernel programming, optimization, distributed systems, and AI acceleration with books, frameworks, profilers, and interview prep.
@vivekgalatage: GPU Programming Fundamentals https://youtu.be/Cl2B_hmg4gA William Brandon, a performance engineer at Anthropic, outline…
A summary of William Brandon's (performance engineer at Anthropic) GPU programming fundamentals lecture, emphasizing that understanding the streaming multiprocessor (SM) structure of GPU hardware is key to predicting performance, rather than starting solely from the software abstraction of thread blocks/threads.
@goyal__pramod: Software is evolving, so should you! These are the best blogs I read to understand GPUs and CUDA!
Tweet recommending a collection of blogs to understand GPUs and CUDA, encouraging developers to improve their skills.
@akshay_pachaar: https://x.com/akshay_pachaar/status/2087928032904523980
An educational thread explaining how GPUs work, focusing on the memory-compute asymmetry that dominates LLM serving performance, and demonstrating how techniques like quantization, speculative decoding, and continuous batching follow from that fundamental constraint.