Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
rivetfasten
3 days ago
|
parent
|
context
|
favorite
| on:
Samsung's Processing-in-Memory (PIM)
The discussion about cpu caching challenges etc seems like it's missing the point. Wouldn't it be more likely to DMA the results to a GPU anyway?
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
