Re: [PATCH] i386: Fix up cvtsd2ss splitter [PR104502]

2022-02-12 Thread Uros Bizjak via Gcc-patches
On Sat, Feb 12, 2022 at 10:02 AM Jakub Jelinek wrote: > > Hi! > > The following testcase ICEs, because AVX512F is enabled, AVX512VL is not, > and the cvtsd2ss insn has %xmm0-15 as output operand and %xmm16-31 as > input operand. For output operand %xmm16+ the splitter just gives up > in such case

[PATCH] i386: Fix up cvtsd2ss splitter [PR104502]

2022-02-12 Thread Jakub Jelinek via Gcc-patches
Hi! The following testcase ICEs, because AVX512F is enabled, AVX512VL is not, and the cvtsd2ss insn has %xmm0-15 as output operand and %xmm16-31 as input operand. For output operand %xmm16+ the splitter just gives up in such case, but for such input it just emits vmovddup which requires AVX512VL