projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 78e3168) | patch
[X86] Do not lower INSERT_VECTOR_ELT to vselect for vXf16 without BWI
authorPhoebe Wang <phoebe.wang@intel.com>
Sat, 14 Jan 2023 03:18:56 +0000 (11:18 +0800)
committerPhoebe Wang <phoebe.wang@intel.com>
Sat, 14 Jan 2023 06:22:29 +0000 (14:22 +0800)
commit974ebe619d179756540527cd71294f86529ff9ec
tree17779f541a34f5762b3a7efd724863edde0b321ctree | snapshot
parent78e3168c979229b011d4127f10c74a9f20a7b482commit | diff
[X86] Do not lower INSERT_VECTOR_ELT to vselect for vXf16 without BWI

We cannot handle i8/i16/f16 vselect without BWI.

Fixes #59980

Reviewed By: RKSimon, skan

Differential Revision: https://reviews.llvm.org/D141668
llvm/lib/Target/X86/X86ISelLowering.cpp diff | blob | history
llvm/test/CodeGen/X86/pr59980.ll [new file with mode: 0644] blob
Domain: System / Toolchain;