[all-commits] [llvm/llvm-project] 50cfdf: [MLIR][ROCDL] Add Scale Convert Packed (B)FP8 <-> ...

[Corbin Robeck via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 50cfdf545e83ad92b614e98350d44ecdaeb755ae
      https://github.com/llvm/llvm-project/commit/50cfdf545e83ad92b614e98350d44ecdaeb755ae
  Author: Corbin Robeck <corbin.robeck at amd.com>
  Date:   2025-03-07 (Fri, 07 Mar 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:
  -----------
  [MLIR][ROCDL] Add Scale Convert Packed (B)FP8 <-> (B)F16 Support for GFX950 (#130300)

Add Rocdl support for the following GFX950 instructions:

CVT_SCALE_PK_FP8_F16
CVT_SCALE_PK_BF8_F16 
CVT_SCALE_PK_FP8_BF16 
CVT_SCALE_PK_BF8_BF16 
CVT_SCALE_SR_FP8_F16 
CVT_SCALE_SR_BF8_F16 
CVT_SCALE_SR_FP8_BF16 
CVT_SCALE_SR_BF8_BF16 
CVT_SCALE_PK_F16_FP8 
CVT_SCALE_PK_F16_BF8 
CVT_SCALE_F16_FP8 
CVT_SCALE_F16_BF8



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