[all-commits] [llvm/llvm-project] 3f6240: [ROCDL] Added rocdl.cvt.scale.sr.pk8 ops (#162244)

[ravil-mobile via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 3f6240775501945fd36f7b66fb23de0648b07f90
      https://github.com/llvm/llvm-project/commit/3f6240775501945fd36f7b66fb23de0648b07f90
  Author: ravil-mobile <ravil.aviva.com at gmail.com>
  Date:   2025-10-07 (Tue, 07 Oct 2025)

  Changed paths:
    M mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td
    M mlir/test/Dialect/LLVMIR/rocdl.mlir
    M mlir/test/Target/LLVMIR/rocdl.mlir

  Log Message:
  -----------
  [ROCDL] Added rocdl.cvt.scale.sr.pk8 ops (#162244)

This patch introduces some missing FP conversion instructions in the
ROCDL dialect for the GFX1250 arch.

Specifically:

Downscaling 8x packed F16, Bf16, Fp32 values to Fp8, Bf8, Fp4 with
stochastic rounding
Tests:

Added lit-tests to check MLIR -> LLVM lowering



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