[llvm-bugs] [Bug 34876] New: [X86] Should we prefer AVX VBLENDPS/VBLENDPS over VMOVSS/VMOVSD even with AVX512?
llvm-bugs at lists.llvm.org
Sun Oct 8 10:18:40 PDT 2017
Bug ID: 34876
Summary: [X86] Should we prefer AVX VBLENDPS/VBLENDPS over
VMOVSS/VMOVSD even with AVX512?
Component: Backend: X86
Assignee: unassignedbugs at nondot.org
Reporter: craig.topper at gmail.com
CC: llvm-bugs at lists.llvm.org
There are no EVEX versions of VBLENDPS/VBLENDPD so when AVX512 is enabled we
prefer EVEX VMOVSS/VMOVSD. This enables us to use the XMM16-XMM31 registers,
but the BLEND instructions have better throughput and that may outweight the
increased register freedom.
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the llvm-bugs