[PATCH] D82780: [AArch64][SVE] Put zeroing pseudos and patterns under flag.

[Sander de Smalen via Phabricator via llvm-commits]

sdesmalen created this revision.
sdesmalen added reviewers: paulwalker-arm, cameron.mcinally.
Herald added subscribers: danielkiss, psnobl, rkruppe, hiraditya, kristof.beyls, tschuett.
Herald added a reviewer: efriedma.
Herald added a project: LLVM.

This patch puts the _ZERO pseudos and corresponding patterns
under the predicate 'UseExperimentalZeroingPseudos', so that they
can be enabled/disabled through compile flags.

This is done because the zeroing pseudos use MOVPRFX to do merging of
the inactive lanes, but it depends on the uarch whether this operation
is actually merged with the destructive operation. If not, it may be
more profitable to use a SELECT and give the compiler the freedom to
schedule these instructions as normal rather than keeping them bundled
together.

Additionally, this feature is not yet fully implemented and there
are still known bugs (see D80410 <https://reviews.llvm.org/D80410>) that need to be resolved before
the 'experimental' can be dropped from the name.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D82780

Files:
  llvm/lib/Target/AArch64/AArch64.td
  llvm/lib/Target/AArch64/AArch64InstrInfo.td
  llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
  llvm/lib/Target/AArch64/AArch64Subtarget.h
  llvm/lib/Target/AArch64/SVEInstrFormats.td
  llvm/test/CodeGen/AArch64/sve-intrinsics-fp-arith-merging.ll
  llvm/test/CodeGen/AArch64/sve-intrinsics-int-arith-merging.ll
  llvm/test/CodeGen/AArch64/sve-intrinsics-shifts-merging.ll
  llvm/test/CodeGen/AArch64/sve2-intrinsics-uniform-dsp-zeroing.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D82780.274143.patch
Type: text/x-patch
Size: 15141 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200629/1293e7a2/attachment-0001.bin>