FDOT (2-way, indexed, FP8 to FP16)

8-bit floating-point dot product by indexed element to half-precision

This instruction calculates the fused sum-of-products of a pair of 8-bit floating-point values held in each 16-bit element of the first source vector and a pair of 8-bit floating-point values in an indexed 16-bit element of the second source vector. The half-precision sum-of-products are scaled by 2^{-UInt(FPMR.LSCALE[3:0])}, before being destructively added without intermediate rounding to the corresponding half-precision elements of the destination vector.

The 8-bit floating-point groups within the second source vector are specified using an immediate index that selects the same group position within each 128-bit vector segment. The 8-bit floating-point encoding format for the elements of the first source vector and the second source vector is selected by FPMR.F8S1 and FPMR.F8S2 respectively.

This instruction is unpredicated.

SVE2
((FEAT_SVE2 && FEAT_FP8DOT2) || FEAT_SSVE_FP8DOT2)

Decode for this encoding

if !HaveSVE2FP8DOT2() then EndOfDecode(Decode_UNDEF); end; let n : integer = UInt(Zn); let m : integer = UInt(Zm); let da : integer = UInt(Zda); let index : integer = UInt(i3h::i3l);