Turns out it's a lot harder to find an implementation of qsort() with no licensing restrictions than you'd think.
-
-
@icculus @r_c_muschong I'm told llvm actually knows how to optimize the De Bruijn ctz into a native ctz instruction on targets that have one -
@RichFelker @r_c_muschong I had a suspicion that might be true, but I couldn't spend the time to test it, unfortunately. -
@icculus @r_c_muschong Amusingly, the De Bruijn one seems to perform comparable to native ctz, but of course it uses more L1 cache space.
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.