@vitaut Is the clang code better on average or is it better for your benchmark? A branch is not necessarily bad, especially if it’s short and predictable. Your benchmark may be stressing the core in a way that makes the branch-based version underperform, while it might do better in a one-shot situation.
undefined
shac ron ₪
@shac@ioc.exchange
Posts
-
I gave up on trying to make gcc emit branchless code on amd64 and switched to inline asm. -
Forget about microoptimizations, we are now dealing with nanooptimizations.@vitaut This is when you discover your cores are not actually identical in performance in several dimensions (even the supposedly identical ones).
-
BREAKING: C++26 will introduce unsigned double@vitaut This implies unsigned nan
-
This post did not contain any content.This post did not contain any content. -
I still can’t believe they named the #rust compiler rustc when crust was right thereI still can’t believe they named the #rust compiler rustc when crust was right there