Twitter | Pretraživanje | |
Raph Levien
GPU twitter: on Metal, Iris Plus 640, I'm seeing roughly 4x bandwidth for fragment shader writes to render target (~10Gpix/s) vs texure2d.write(~2.5Gpix/s). Is there a good explanation for this?
Reply Retweet Označi sa "sviđa mi se" More
Rik Arends 14. sij
Odgovor korisniku/ci @raphlinus
Random guess: maybe related that a fragment shader runs in blocks of 2x2 pixels for its derivatives? Maybe some kind of special datapath there?
Reply Retweet Označi sa "sviđa mi se"
Raph Levien 14. sij
Odgovor korisniku/ci @rikarends
I doubt it; my compute shader is running with full SIMD utilization (I checked). I also tried byte writes (doing unorm conversion in ALU), same bandwidth.
Reply Retweet Označi sa "sviđa mi se"