[all-commits] [llvm/llvm-project] c511c9: [mlir][ArmNeon] Updates LowerContractionToSMMLAPat...

[Kojo Acquah via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c511c90680eecae2e4adb87f442f41d465feb0f2
      https://github.com/llvm/llvm-project/commit/c511c90680eecae2e4adb87f442f41d465feb0f2
  Author: Kojo Acquah <KoolJBlack at users.noreply.github.com>
  Date:   2024-04-03 (Wed, 03 Apr 2024)

  Changed paths:
    M mlir/lib/Dialect/ArmNeon/Transforms/LowerContractionToSMMLAPattern.cpp
    M mlir/test/Dialect/ArmNeon/lower-to-arm-neon.mlir

  Log Message:
  -----------
  [mlir][ArmNeon] Updates LowerContractionToSMMLAPattern with vecmat unroll patterns (#86005)

Updates smmla unrolling patterns to handle vecmat contracts where `dimM=1`. This includes explicit vecmats in the form: `<1x8xi8> x <8x8xi8> --> <1x8xi32>` or implied with the leading dim folded: `<8xi8> x <8x8xi8> --> <8xi32>` 

Since the smmla operates on two `<2x8xi8>` input vectors to produce `<2x2xi8>` accumulators, half of each 2x2 accumulator tile is dummy data not pertinent to the computation, resulting in half throughput.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications