triton.experimental.gluon.language.amd.cdna5.wmma_scaled

triton.experimental.gluon.language.amd.cdna5.wmma_scaled(a, a_scale, a_format, b, b_scale, b_format, acc, _semantic=None)

AMD Scaled WMMA operation.

c = a * a_scale @ b * b_scale + acc

a and b use microscaling formats described in “OCP Microscaling Formats (MX) Specification”: https://www.opencompute.org/documents/ocp-microscaling-formats-mx-v1-0-spec-final-pdf.

Parameters:

  • a (tensor) – The operand A to be multiplied.

  • a_scale (Optional[tensor]) – Scale factor for operand A.

  • a_format (str) – Format of operand A. Available formats: e2m1, e4m3, e5m2.

  • b (tensor) – The operand B to be multiplied.

  • b_scale (Optional[tensor]) – Scale factor for operand B.

  • b_format (str) – Format of operand B. Available formats: e2m1, e4m3, e5m2.

  • acc (tensor) – Accumulator tensor.