Lecture 117:Building a GPU Compiler from Scratch - YouTube
youtube.com · 6,999 words · saved by 1 readers
Follow along using the transcript. Follow along using the transcript.
Abstract: Dmitry Trifonov demystifies ML compilers by showing how PyTorch layers become efficient GPU kernels through progressive IR lowering. Perfect if you plan to participate in the upcoming riftstack.ai hackathon or want a gentle, hands-on introduction to modern GPU compiler technology. can hear us. Okay. >> Okay. >> Okay. Wait just one moment. I think Yeah, I think we're in good shape. So, okay. So, welcome everyone to like another episode of GP mode. Today, I'm really glad we have like Mitri Trifanov who's here to talk to us about um like co-designing like IRS and like kernels on top…
saved by
related reading
- Making Deep Learning go Brrrr From First Principleshorace.io
- Horace He: Building Machine Learning Systems for a Trillion Trillion Floating Point Operationsyoutube.com
- A friendly introduction to machine learning compilers and optimizershuyenchip.com
- Reiner Pope – The math behind how LLMs are trained and serveddwarkesh.com
- Inside NVIDIA GPUs: Anatomy of high performance matmul kernels - Aleksa Gordićaleksagordic.com
- How to Optimize a CUDA Matmul Kernel for cuBLAS-like Performance: a Worklogsiboehm.com
- Chip design from the bottom up – Reiner Popeyoutube.com
- ⭐️ Fast LLM Inference From Scratchandrewkchan.dev
- Let's build GPT: from scratch, in code, spelled out.youtube.com
- Turing Award Winner: TPU vs GPU vs CPU, Computer Architecture, RISC vs CISC | David Pattersonyoutube.com
- AI Chip Architecturesjacobpeake.com
- Modern GPU Programming For MLSys — Modern GPU Programming For MLSysmlc.ai