Re:Apple’s M1 Positioning Mocks the Entire x86 Business Model
by rubatuga on Friday April 23, 2021 @04:46AM
(#26912517)
GPU schedulers are much, much more advanced than you give credit.
Re:Apple’s M1 Positioning Mocks the Entire x86 Business Model
by tobyhinloopen on Friday April 23, 2021 @04:54AM
(#26912565)
Well GPU data structures aren’t always a power of two, right? There’s more than textures. For a fact, I know vertex count (vertex shaders?) and screen sizes (fragment shaders?) will rarely be exactly a power of two.
Re:Apple’s M1 Positioning Mocks the Entire x86 Business Model
by Toutouxc on Friday April 23, 2021 @04:47AM
(#26912523)
Nope, AFAIK the actual performance impact is < 10 % for most workloads.
Re:Apple’s M1 Positioning Mocks the Entire x86 Business Model
by NavinF on Friday April 23, 2021 @05:46AM
(#26912868)
Isn't false sharing (as in all your addresses hashing onto the same cache lines) still an issue for power-of-two sizes? You'd have to mess with padding to figure out what's fastest for each chip regardless of core count.
When data structures are power-of-two sizes, having 7 cores instead of 8 could halve performance, since the work gets split into 4 pieces and 3 cores sit idle.