crap, I hate it when I agree with @ErrataRob
https://blog.erratasec.com/2018/05/c-is-too-low-level.html …
-
Show this thread
-
Replying to @johnregehr @ErrataRob
I agree with the original ACM article more than I agree with Rob here. There is an obvious, extremely successful, counterexample to the “single threaded performance is king” meme and that’s GPUs.
5 replies 0 retweets 6 likes -
The vicious cycle of “processors optimize for popular languages” <-> “popular languages are bad at parallelism” is a real phenomenon. GPUs are evidence that if you have a model rooted in parallelism from the start then things can turn out differently.
5 replies 0 retweets 4 likes -
To what extent are GPUs actually massive parallelism rather than glorified SIMD?
1 reply 0 retweets 0 likes -
They’re basically SIMD, but they usually don’t do OoO and instead eagerly context switch away to other threads to hide stalls.
2 replies 0 retweets 0 likes
It seems to me that real independent branching/programs, rather than just doing the same thing on a bunch of data, is what you need to make the model interesting for general-purpose computing.
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.