@aphyr Can we really do better than work-stealing (Intel TBB, Cilk, Haskell RTS)?
-
-
Replying to @markpapadakis
@markpapadakis@aphyr per-processor work-stealing deques? Maybe try something like http://chargueraud.org/research/2013/ppopp/full.pdf … with private deques and messaging?2 replies 0 retweets 0 likes -
Replying to @markpapadakis
@markpapadakis@aphyr At least it's a hot bed for researchers these days so lots of new stuff to try :D2 replies 0 retweets 0 likes -
Replying to @markpapadakis
@markpapadakis@aphyr something something caching.1 reply 0 retweets 0 likes -
Replying to @ReinH
@markpapadakis@aphyr It's always something something caching ;)3 replies 0 retweets 0 likes -
Replying to @markpapadakis
@markpapadakis@aphyr Haskell's RTS seems to be among the more efficient work stealing schedulers.3 replies 0 retweets 0 likes
@ReinH not sure how much you're following Rust, but here was a talk on its work-stealing runtime: https://air.mozilla.org/2013-intern-todd/ …
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.