[PATCH] D77448: [PowerPC] Canonicalize shuffles to match more single-instruction masks on LE
Roland Froese via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri May 15 13:03:52 PDT 2020
RolandF added inline comments.
================
Comment at: llvm/test/CodeGen/PowerPC/build-vector-tests.ll:1723
+; P9LE-NEXT: xscvdpsxws f0, f0
+; P9LE-NEXT: xxspltw v2, vs0, 1
; P9LE-NEXT: blr
----------------
Looks like the code got worse here?
================
Comment at: llvm/test/CodeGen/PowerPC/build-vector-tests.ll:3243
+; P9LE-NEXT: xscvdpuxws f0, f0
+; P9LE-NEXT: xxspltw v2, vs0, 1
; P9LE-NEXT: blr
----------------
This code is also worse.
================
Comment at: llvm/test/CodeGen/PowerPC/build-vector-tests.ll:4918
+; P9LE-NEXT: xscvdpsxds f0, f0
+; P9LE-NEXT: xxspltd v2, vs0, 0
; P9LE-NEXT: blr
----------------
Okay it looks like there are a number of similar cases where the code is slightly worse. I will stop flagging them individually.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D77448/new/
https://reviews.llvm.org/D77448
More information about the llvm-commits
mailing list