Skip to content
Commit ca0cd670 authored by Philip Reames's avatar Philip Reames Committed by Philip Reames
Browse files

[RISCV] Improve SK_Reverse shuffle costs for fixed length vectors 

As noted by @luke (https://reviews.llvm.org/D145953#inline-1409312), we were accounting for the cost of vector element size using vlenb whereas the expression can be constant folded for fixed length vectors.

Differential Revision: https://reviews.llvm.org/D145973
parent f18915da
Show whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please to comment