Fri, 05 May 2017 19:28:54 -0700 vdeshpande 8178811: Minimize the AVX <-> SSE transition penalty through generation of vzeroupper instruction on x86
Sat, 06 May 2017 00:05:32 +0000 cjplummer Merge
(0) -30000 -10000 -3000 -1000 -300 -100 -30 -10 -2 +2 +10 +30 +100 +300 +1000 +3000 +10000 tip