projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 8b127a8) | patch
[AArch64] Improve lowering of insert_vector_elt with 0.0 consts.
authorFlorian Hahn <flo@fhahn.com>
Wed, 28 Oct 2020 21:20:52 +0000 (21:20 +0000)
committerFlorian Hahn <flo@fhahn.com>
Wed, 28 Oct 2020 21:35:33 +0000 (21:35 +0000)
commit772aaa602383cf82795572ebcd86b0e660f3579f
tree844ef08c7401df2bf29c0bfc6780eb4f78e85827tree | snapshot
parent8b127a8661a160a12b09d32094268c4988c5424ccommit | diff
[AArch64] Improve lowering of insert_vector_elt with 0.0 consts.

When moving +0.0 into a float vector, we can use to vi*gpr variants of
INS.

Reviewed By: efriedma

Differential Revision: https://reviews.llvm.org/D90176
llvm/lib/Target/AArch64/AArch64InstrInfo.td diff | blob | history
llvm/test/CodeGen/AArch64/arm64-vector-insertion.ll diff | blob | history
llvm/test/CodeGen/AArch64/vecreduce-fadd-legalization.ll diff | blob | history
Domain: System / Toolchain;