[zanussbaum]

at least on my m2, the compiled kernel ends up using fast math anyways so using WGSL's fma didn't change anything about the actual kernel that gets run

[hedgehog]

inglor is probably referring to Strassen or Coppersmith–Winograd.

[wbl]

Last I checked the extra mems really hurt on a lot of cases especially for the more complex ones, but I'm no expert.

[zanussbaum]

oh in that case it was because i didn't know about them :) something to try next!