projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 6f4ed8c) | patch
[AArch64] Improve vector reverse lowering
authorDavid Green <david.green@arm.com>
Thu, 22 Apr 2021 20:01:25 +0000 (21:01 +0100)
committerDavid Green <david.green@arm.com>
Thu, 22 Apr 2021 20:01:25 +0000 (21:01 +0100)
commitc0bf5929eea7ee86d664f069c2cfb9c65fcda05c
treec48c54e6af5445f411daf908192e6b087852d742tree | snapshot
parent6f4ed8c0bd5000819864f0584c0ce086c388b720commit | diff
[AArch64] Improve vector reverse lowering

This improves the lowering of v8i16 and v16i8 vector reverse shuffles.
Instead of going via a generic tbl it uses a rev64; ext pair, as already
happens for v4i32.

Differential Revision: https://reviews.llvm.org/D100882
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp diff | blob | history
llvm/test/CodeGen/AArch64/named-vector-shuffle-reverse-neon.ll diff | blob | history
llvm/test/CodeGen/AArch64/neon-reverseshuffle.patch diff | blob | history
Domain: System / Toolchain;