Committed new x86[_64] memset asm to @musllibc based on work by Denys Vlasenko and myself. http://git.musl-libc.org/cgit/musl/commit/?id=e346ff86c8faee901a7c2d502b5beb983b99f972 … http://git.musl-libc.org/cgit/musl/commit/?id=69858fa93107aa7485b143c54137e745a7b7ad72 …
Large gains in some misaligned cases where "rep stos" is pathologically bad. Also significant for tiny sizes where overhead dominates.
-
-
There are a number of cases where new memset is 1.5x faster, and some misaligned cases where it's 4x faster or more on some cpu models.
-
And thanks to new expanded libc-test coverage by Szabolcs Nagy, alignment combinations have all been tested. http://nsz.repo.hu/git/?p=libc-test;a=commit;h=0b6bb43211b258c0d24931b5425d4c58b94ea336 …
End of conversation
New conversation -
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.