| commit | 6cc3211b706ccf5149d644e45f162e0f7c5aa2f4 | |
| author | David Green <david.green@arm.com> | |
| Sun, 11 Aug 2019 08:42:57 +0000 (11 08:42 +0000) | ||
| committer | David Green <david.green@arm.com> | |
| Sun, 11 Aug 2019 08:42:57 +0000 (11 08:42 +0000) | ||
| tree | 6698dbab51fc52a9ffb299a5e1f7f7d3b93382bd | treesnapshot (tar.gz zip) |
| parent | 8d0525d1378057e57ae5826c04aba6517a8a3ccc | commitdiff |
[ARM] Permit auto-vectorization using MVE
With enough codegen complete, we can now correctly report the number and size
of vector registers for MVE, allowing auto vectorisation. This also allows FP
auto-vectorization for MVE without -Ofast/-ffast-math, due to support for IEEE
FP arithmetic and parity between scalar and vector FP behaviour.
Patch by David Sherwood.
Differential Revision: https://reviews.llvm.org/D63728
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@368529 91177308-0d34-0410-b5e6-96231b3b80d8
With enough codegen complete, we can now correctly report the number and size
of vector registers for MVE, allowing auto vectorisation. This also allows FP
auto-vectorization for MVE without -Ofast/-ffast-math, due to support for IEEE
FP arithmetic and parity between scalar and vector FP behaviour.
Patch by David Sherwood.
Differential Revision: https://reviews.llvm.org/D63728
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@368529 91177308-0d34-0410-b5e6-96231b3b80d8
| lib/Target/ARM/ARMTargetTransformInfo.h | diffblobblamehistory | |
| test/Transforms/LoopVectorize/ARM/arm-ieee-vectorize.ll | diffblobblamehistory |