Skip to content

Optimize F32 <- QAI8DXP (LHS) x QSI4C32P (RHS) for 4x8 i8mm

Michael Kozlov requested to merge 4x8_int4_i8mm into main
  • Add new assembly ukernel optimized with FEAT_I8MM for matrix multiplication with 4x8 block size.
  • Update build script.
  • Add to unit test.

Signed-off-by: Michael Kozlov michael.kozlov@arm.com

Merge request reports