Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ummonk
on April 9, 2021
|
parent
|
context
|
favorite
| on:
CPU-based algorithm trains deep neural nets up to ...
Yeah I disagree with the comparison of GPGPUs to specialized hardware. It’s more a distinction between hardware optimized for throughout of general highly parallel computations and hardware optimized for latency of highly serial computations.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: