this is how i wish i learned GPU fundamentals
not a lengthy textbook. not a static image. every concept is an interactive visualization.
covering the SM architecture, memory coalescing, synchronization, and more.
what concepts do you want to see next?
https://t.co/D7lq9xwXyk
Nobody gets more fast tokens out of a megawatt than us. Nobody.
· Bit-accurate log math is locked in.
· Chip is taped out with Broadcom and in wafer fab on TSMC 3nm.
· System bring-up of compute tray with HPE Juniper scale-up fabric is ahead of schedule.
Today we're publishing our whitepaper on how we solved for what really matters in AI inference.
I became an AI Research Scientist as a college freshman.
The job required a master’s degree.
I had:
• a high school diploma
• 0 publications
• 0 AI research experience
Here’s exactly how I did it (thread):
the fastest optimization you can make to a memory-bound kernel:
make the numbers smaller by going from fp32 to bf16
this is precision
learn about it @ https://t.co/1ni1pr6wA0
I'm on vacation in Hong Kong and just shipped BrrrViz Chapter 11: Tiling from my hotel room. It's 6 interactive visuals that will help you grasp the concept. It's 1:43am. I'm tired. Hope it helps and go check it out :)
https://t.co/D7lq9xxvnS