Re: [PATCH] Fix wrong-code x86 issue with avx512{f,vl} fma (PR target/93009)

2020-01-14 Thread Jeff Law
On Sat, 2019-12-21 at 00:34 +0100, Jakub Jelinek wrote: > Hi! > > As mentioned in the PR, the following testcase is miscompiled with avx512vl. > The reason is that the fma *_bcst_1 define_insns have two alternatives: > "=v,v" "0,v" "v,0" "m,m" and use the same > vfmadd213* %3, %2, %0 > pattern. I

[PATCH] Fix wrong-code x86 issue with avx512{f,vl} fma (PR target/93009)

2019-12-20 Thread Jakub Jelinek
Hi! As mentioned in the PR, the following testcase is miscompiled with avx512vl. The reason is that the fma *_bcst_1 define_insns have two alternatives: "=v,v" "0,v" "v,0" "m,m" and use the same vfmadd213* %3, %2, %0 pattern. If the first alternative is chosen, everything is ok, but if the second