It would be interesting to bridge the gap between language-level async features and the async execution of out-of-order CPUs.
Yes! I think this could be automated based on timing: tasks start on-core but later flush to main memory futures, like caches.
-
-
Hmm like drive the task/threading system straight from the cache manager based on distance-to-memory?
-
I mean in a way GPU's 'suspend' their warps when they wait for a texture read, so something similar?
- 4 more replies
New conversation -
-
-
Ah wait i think i know what you are saying, super lightweight task-threads that can be spawned with a single instruction
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Cool idea, might actually drive the CPU cores to become more GPU like, a cpu where the microthreads execute gpu like
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Instead of relying on OO to do it you take that idea and stack up bigtime on the OO exec units but make it explicitly av.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.