projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 9a7286b) | patch
[AAch64] Optimize muls with operands having enough zero bits.
authorbipmis <biplob.mishra@arm.com>
Wed, 21 Dec 2022 11:14:45 +0000 (11:14 +0000)
committerbipmis <biplob.mishra@arm.com>
Wed, 21 Dec 2022 11:14:45 +0000 (11:14 +0000)
commiteb7b8e3e2aab6bca3d4403ceb1402e10c4e853b6
treedbfafa3b4b468771f1aff45593ba4f1a483d7d5etree | snapshot
parent9a7286b61f61b78db1197fdedcaaa4cac1b04fe3commit | diff
[AAch64] Optimize muls with operands having enough zero bits.

Fix the regression in the reported test case lagarith-preproc.c.
Specfic to the incorrect umsubl generation.

Differential Revision: https://reviews.llvm.org/D139411
llvm/lib/Target/AArch64/AArch64InstrInfo.td diff | blob | history
llvm/test/CodeGen/AArch64/aarch64-mull-masks.ll diff | blob | history
Domain: System / Toolchain;