[PATCH] D83830: [ARM] VBIT/VBIF support added.

Pavel Iliin via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Tue Jul 14 16:31:02 PDT 2020


ilinpv created this revision.
ilinpv added reviewers: dmgreen, SjoerdMeijer, grosbach.
Herald added subscribers: llvm-commits, danielkiss, javed.absar, hiraditya, kristof.beyls.
Herald added a project: LLVM.

Vector bitwise selects are matched by pseudo VBSP instruction
and expanded to VBSL/VBIT/VBIF after register allocation
depend on operands registers to minimize extra copies.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D83830

Files:
  llvm/lib/Target/ARM/ARMExpandPseudoInsts.cpp
  llvm/lib/Target/ARM/ARMISelLowering.cpp
  llvm/lib/Target/ARM/ARMISelLowering.h
  llvm/lib/Target/ARM/ARMInstrNEON.td
  llvm/lib/Target/ARM/ARMScheduleA57.td
  llvm/lib/Target/ARM/ARMScheduleR52.td
  llvm/lib/Target/ARM/ARMScheduleSwift.td
  llvm/test/CodeGen/ARM/fcopysign.ll
  llvm/test/CodeGen/ARM/fp16-promote.ll
  llvm/test/CodeGen/ARM/vbsl-constant.ll
  llvm/test/CodeGen/ARM/vbsl.ll
  llvm/test/CodeGen/ARM/vselect_imax.ll
  llvm/test/CodeGen/Thumb2/float-intrinsics-double.ll
  llvm/test/CodeGen/Thumb2/float-intrinsics-float.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D83830.277971.patch
Type: text/x-patch
Size: 61837 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200714/a1f1610f/attachment.bin>


More information about the llvm-commits mailing list