projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 881b6a0) | patch
[LoopVectorize] Test in-loop reductions with tail folding for scalable vectors
authorKerry McLaughlin <kerry.mclaughlin@arm.com>
Wed, 19 Jan 2022 14:18:28 +0000 (14:18 +0000)
committerKerry McLaughlin <kerry.mclaughlin@arm.com>
Wed, 19 Jan 2022 14:36:23 +0000 (14:36 +0000)
commitc740a07863b464a922d7601a4bcea75b017254c6
tree5d2804af471cd6a6ec208f30474ab701305dd57ctree | snapshot
parent881b6a009fb6e2dd5fb924524cd6eacd14148a08commit | diff
[LoopVectorize] Test in-loop reductions with tail folding for scalable vectors

Adds `-prefer-inloop-reductions` to the RUN line of sve-tail-folding.ll & adds
a new test where in-loop reductions cannot be used (`@cond_xor_reduction`). NFC.

Reviewed By: david-arm

Differential Revision: https://reviews.llvm.org/D117578
llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll diff | blob | history
Domain: System / Toolchain;