1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 05:01:59 +01:00
Simon Pilgrim ef6c8d6574 [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!).
2021-05-18 13:07:29 +01:00
..