BFSCALE (multiple and single vector)

Multi-vector BFloat16 adjust exponent by vector

Multiply the BFloat16 elements of the two or four first source vectors by 2.0 to the power of the signed integer values in the corresponding elements of the second source vector and destructively place the results in the corresponding elements of the two or four first source vectors.

This instruction follows SME2 non-widening BFloat16 numerical behaviors corresponding to instructions that place their results in two or four SVE Z vectors.

This instruction is unpredicated.

It has encodings from 2 classes: Two registers and Four registers

Two registers
(FEAT_SME2 && FEAT_SVE_BFSCALE)

Decode for this encoding

if !IsFeatureImplemented(FEAT_SME2) || !IsFeatureImplemented(FEAT_SVE_BFSCALE) then EndOfDecode(Decode_UNDEF); constant integer dn = UInt(Zdn:'0'); constant integer m = UInt('0':Zm); constant integer nreg = 2;

Four registers
(FEAT_SME2 && FEAT_SVE_BFSCALE)

Decode for this encoding

if !IsFeatureImplemented(FEAT_SME2) || !IsFeatureImplemented(FEAT_SVE_BFSCALE) then EndOfDecode(Decode_UNDEF); constant integer dn = UInt(Zdn:'00'); constant integer m = UInt('0':Zm); constant integer nreg = 4;