Wrote lots of SIMD for only a 10% overall speedup. Curse you, Amdahl's Law! (I'm not despairing--the code in question parallelizes across cores beautifully--just mildly annoyed.) :)
-
-
Replying to @pcwalton
Need shorter sequential critical path if possible. What alg?
1 reply 0 retweets 0 likes -
Replying to @BrendanEich
SVG fill tiling. It’s inherently too branchy for SIMD. It can be made parallel but at the cost of a lot of work-efficiency: probably not worth it right now.
1 reply 0 retweets 2 likes -
Replying to @pcwalton
Right -- with a GPU predication layer, the inefficiency can be worth it, but SIMD not || enough.
1 reply 0 retweets 1 like -
Replying to @BrendanEich
It’s parallelizable across paths, which is sufficient to get 100% CPU utilization. I’m planning on trying GPU compute later. I suspect whether it’ll be a win over CPU will be hardware dependent. It’s really not an ideal problem for GPU either.
1 reply 0 retweets 2 likes
(Note that tiling is only one part of Pathfinder 3. The other parts run entirely on GPU.)
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.