[Mlir-commits] [mlir] [MLIR][AArch64] Lower `vector.contract` to SVE FEAT_BF16 operations (PR #147052)
Momchil Velikov
llvmlistbot at llvm.org
Tue Jul 8 08:04:04 PDT 2025
================
@@ -23,4 +23,14 @@ def ApplyArmSVELowerContractionPatternsOp
let assemblyFormat = "attr-dict";
}
+def ApplyArmSVELowerContractionToBFMMLAPatternsOp
+ : Op<Transform_Dialect, "apply_patterns.arm_sve.vector_contract_to_bfmmla",
+ [DeclareOpInterfaceMethods<PatternDescriptorOpInterface>]> {
+ let description = [{
+ Indicates that vector contraction-like operations should be lowered to
+ finer-grained vector primitives using the ArmSVE dialect.
----------------
momchil-velikov wrote:
Done.
https://github.com/llvm/llvm-project/pull/147052
More information about the Mlir-commits
mailing list