Hacker Timesnew | past | comments | ask | show | jobs | submitlogin

Computation happens in the registers. If you’re not moving data to registers you aren’t doing any compute.


Obviously yes but NVIDIA Ampere/Hopper architecture has 64k 32-bit registers per SM. A100 has 108 SMs and H100 has 132 SMs so go figure - registers aren't a bottleneck.




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

Search: