UVDOT (4-way)

Multi-vector unsigned integer vertical dot-product by indexed element

The unsigned integer vertical dot product instruction computes the vertical dot product of the corresponding four unsigned 8-bit or 16-bit integer values held in the four first source vectors and four unsigned 8-bit or 16-bit integer values in the corresponding indexed 32-bit or 64-bit element of the second source vector. The widened dot product results are destructively added to the corresponding 32-bit or 64-bit element of the ZA single-vector groups.

The groups within the second source vector are specified using an immediate element index which selects the same group position within each 128-bit vector segment. The index range is from 0 to one less than the number of groups per 128-bit segment, encoded in 1 to 2 bits depending on the size of the group.

The vector numbers forming the single-vector group within each quarter of the ZA array are selected by the sum of the vector select register and immediate offset, modulo quarter the number of ZA array vectors.

The vector group symbol VGx4 indicates that the ZA operand consists of four ZA single-vector groups. The vector group symbol is preferred for disassembly, but optional in assembler source code.

This instruction is unpredicated.

ID_AA64SMFR0_EL1.I16I64 indicates whether the 16-bit integer variant is implemented.

It has encodings from 2 classes: 32-bit and 64-bit

32-bit
(FEAT_SME2)

if !HaveSME2() then UNDEFINED; integer v = UInt('010':Rv); constant integer esize = 32; integer n = UInt(Zn:'00'); integer m = UInt('0':Zm); integer offset = UInt(off3); integer index = UInt(i2);

64-bit
(FEAT_SME_I16I64)

if !(HaveSME2() && HaveSMEI16I64()) then UNDEFINED; integer v = UInt('010':Rv); constant integer esize = 64; integer n = UInt(Zn:'00'); integer m = UInt('0':Zm); integer offset = UInt(off3); integer index = UInt(i1);