[all-commits] [llvm/llvm-project] b535aa: [ARM] Use reduction intrinsics for larger than leg...

[David Green via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: b535aa405a0210c5d4d161c9e792a2bab10ddf16
      https://github.com/llvm/llvm-project/commit/b535aa405a0210c5d4d161c9e792a2bab10ddf16
  Author: David Green <david.green at arm.com>
  Date:   2020-01-24 (Fri, 24 Jan 2020)

  Changed paths:
    M llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
    M llvm/test/CodeGen/Thumb2/mve-vaddv.ll
    A llvm/test/Transforms/LoopVectorize/ARM/mve-reduce.ll

  Log Message:
  -----------
  [ARM] Use reduction intrinsics for larger than legal reductions

The codegen for splitting a llvm.vector.reduction intrinsic into parts
will be better than the codegen for the generic reductions. This will
only directly effect when vectorization factors are specified by the
user.

Also added tests to make sure the codegen for larger reductions is OK.

Differential Revision: https://reviews.llvm.org/D72257