FCVTN Half-precision convert, narrow and interleave to 8-bit floating-point Convert each half-precision element of the group of two source vectors to 8-bit floating-point while scaling the value by 2SInt(FPMR.NSCALE[4:0]), and place the two-way interleaved results in the corresponding 8-bit elements of the destination vector. The 8-bit floating-point encoding format is selected by FPMR.F8D. This instruction is unpredicated. Green False 0 1 1 0 0 1 0 1 0 0 0 0 1 0 1 0 0 0 1 1 0 0 0 FCVTN <Zd>.B, { <Zn1>.H-<Zn2>.H } if ((!IsFeatureImplemented(FEAT_SVE2) && !IsFeatureImplemented(FEAT_SME2)) || !IsFeatureImplemented(FEAT_FP8)) then UNDEFINED; constant integer n = UInt(Zn:'0'); constant integer d = UInt(Zd); <Zd> Is the name of the destination scalable vector register, encoded in the "Zd" field. <Zn1> Is the name of the first scalable vector register of the source multi-vector group, encoded as "Zn" times 2. <Zn2> Is the name of the second scalable vector register of the source multi-vector group, encoded as "Zn" times 2 plus 1. CheckFPMREnabled(); CheckSVEEnabled(); constant integer VL = CurrentVL; constant integer elements = VL DIV 16; bits(VL) result; constant bits(VL) operand1 = Z[n+0, VL]; constant bits(VL) operand2 = Z[n+1, VL]; for e = 0 to elements-1 constant bits(16) element1 = Elem[operand1, e, 16]; constant bits(16) element2 = Elem[operand2, e, 16]; Elem[result, 2*e + 0, 8] = FPConvertFP8(element1, FPCR, FPMR, 8); Elem[result, 2*e + 1, 8] = FPConvertFP8(element2, FPCR, FPMR, 8); Z[d, VL] = result;