diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2021-05-18 13:06:57 +0100 |
|---|---|---|
| committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2021-05-18 13:07:29 +0100 |
| commit | 560b709abedc76d7944be38d2f38b7bc8d40e32d (patch) | |
| tree | 53d5999e1c3271cfd2d2265f9fda4b7329ccfb81 /llvm/lib/Bitcode/Reader/BitcodeReader.cpp | |
| parent | 095c520fb436103c9800de0ac15fed83a86f3a43 (diff) | |
[X86][AVX] Cleanup AVX2 vector integer truncation costs
Noticed while investigating PR50364, the truncation costs for v4i64->v4i16/v4i8 and v8i32->v8i8 were way too optimistic for a shuffle sequence that usually matches the AVX1 codegen (they matched AVX512 numbers which have actual truncation instructions!).
Diffstat (limited to 'llvm/lib/Bitcode/Reader/BitcodeReader.cpp')
0 files changed, 0 insertions, 0 deletions