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

So I had to look up SIMT: http://yosefk.com/blog/simd-simt-smt-parallelism-in-nvidia-g...

Batches of execution units all run the same opcode (or skip it in if/else constructs) but each one has its own register set.

As opposed to SIMD's simple, single, massively-parallel vector instructions.




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: