[PATCH] D110476: [AArch64] Optimize add/sub with immediate
Ben Shi via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Sat Sep 25 06:10:56 PDT 2021
benshi001 added inline comments.
================
Comment at: llvm/test/CodeGen/AArch64/addimm-mulimm.ll:56
; CHECK-NEXT: mov w8, #37
-; CHECK-NEXT: movk w9, #17, lsl #16
-; CHECK-NEXT: madd x0, x0, x8, x9
+; CHECK-NEXT: mul x8, x0, x8
+; CHECK-NEXT: add x8, x8, #280, lsl #12 // =1146880
----------------
I think this is still a win, since an extra register w9 is saved, although the total amount of instructions does not change.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D110476/new/
https://reviews.llvm.org/D110476
More information about the llvm-commits
mailing list