diff options
| author | Gil Rapaport <gil.rapaport@intel.com> | 2017-11-14 12:09:30 +0000 |
|---|---|---|
| committer | Gil Rapaport <gil.rapaport@intel.com> | 2017-11-14 12:09:30 +0000 |
| commit | 848581cadb3f5cd0229cf580c5cb56f679900d3d (patch) | |
| tree | 8efea72359f6dba678330e7b13ec420fb821d965 /clang/lib/Basic | |
| parent | 5cdc4f9c330c7d4d411e1bbc77084c1415593ded (diff) | |
| download | bcm5719-llvm-848581cadb3f5cd0229cf580c5cb56f679900d3d.tar.gz bcm5719-llvm-848581cadb3f5cd0229cf580c5cb56f679900d3d.zip | |
[LV] Introduce VPBlendRecipe, VPWidenMemoryInstructionRecipe
This patch is part of D38676.
The patch introduces two new Recipes to handle instructions whose vectorization
involves masking. These Recipes take VPlan-level masks in D38676, but still rely
on ILV's existing createEdgeMask(), createBlockInMask() in this patch.
VPBlendRecipe handles intra-loop phi nodes, which are vectorized as a sequence
of SELECTs. Its execute() code is refactored out of ILV::widenPHIInstruction(),
which now handles only loop-header phi nodes.
VPWidenMemoryInstructionRecipe handles load/store which are to be widened
(but are not part of an Interleave Group). In this patch it simply calls
ILV::vectorizeMemoryInstruction on execute().
Differential Revision: https://reviews.llvm.org/D39068
llvm-svn: 318149
Diffstat (limited to 'clang/lib/Basic')
0 files changed, 0 insertions, 0 deletions
