Add pure assembly version of f32_bf16p_bf16p
This change changes the following kernel to use pure assembly:
- kai_matmul_clamp_f32_bf16p2vlx2_bf16p2vlx2_2vlx2vl_sme2_mopa
Signed-off-by: Emil Ohlsson emil.ohlsson@arm.com
This change changes the following kernel to use pure assembly:
Signed-off-by: Emil Ohlsson emil.ohlsson@arm.com