> as little memory latency as possible Should be "as much memory bandwidth as po... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

rfoo 11 months ago | parent | context | favorite | on: GPUs Go Brrr

> as little memory latency as possible

Should be "as much memory bandwidth as possible". GPUs are designed to be (relatively) more insensitive to memory latency than CPU.

muyuu 11 months ago [–]

yep that's true, although AI compute modules do get significant benefit from low latency cache as well

Join us for AI Startup School this June 16-17 in San Francisco!
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact