LD1RSB

Load and broadcast signed byte to vector

Load a single signed byte from a memory address generated by a 64-bit scalar base address plus an immediate offset which is in the range 0 to 63.

Broadcast the loaded data into all active elements of the destination vector, setting the inactive elements to zero. If all elements are inactive then the instruction will not perform a read from Device memory or cause a data abort.

Encoding: 16-bit element

Variants: FEAT_SVE || FEAT_SME (FEAT_SVE || FEAT_SME)

313029282726252423222120191817161514131211109876543210
1000010111110
dtypehimm6dtypelPgRnZt

LD1RSB { <Zt>.H }, <Pg>/Z, [<Xn|SP>{, #<imm>}]

Decoding algorithm

if !IsFeatureImplemented(FEAT_SVE) && !IsFeatureImplemented(FEAT_SME) then
    EndOfDecode(Decode_UNDEF);
constant integer t = UInt(Zt);
constant integer n = UInt(Rn);
constant integer g = UInt(Pg);
constant integer esize = 16;
constant integer msize = 8;
constant boolean unsigned = FALSE;
constant integer offset = UInt(imm6);

Encoding: 32-bit element

Variants: FEAT_SVE || FEAT_SME (FEAT_SVE || FEAT_SME)

313029282726252423222120191817161514131211109876543210
1000010111101
dtypehimm6dtypelPgRnZt

LD1RSB { <Zt>.S }, <Pg>/Z, [<Xn|SP>{, #<imm>}]

Decoding algorithm

if !IsFeatureImplemented(FEAT_SVE) && !IsFeatureImplemented(FEAT_SME) then
    EndOfDecode(Decode_UNDEF);
constant integer t = UInt(Zt);
constant integer n = UInt(Rn);
constant integer g = UInt(Pg);
constant integer esize = 32;
constant integer msize = 8;
constant boolean unsigned = FALSE;
constant integer offset = UInt(imm6);

Encoding: 64-bit element

Variants: FEAT_SVE || FEAT_SME (FEAT_SVE || FEAT_SME)

313029282726252423222120191817161514131211109876543210
1000010111100
dtypehimm6dtypelPgRnZt

LD1RSB { <Zt>.D }, <Pg>/Z, [<Xn|SP>{, #<imm>}]

Decoding algorithm

if !IsFeatureImplemented(FEAT_SVE) && !IsFeatureImplemented(FEAT_SME) then
    EndOfDecode(Decode_UNDEF);
constant integer t = UInt(Zt);
constant integer n = UInt(Rn);
constant integer g = UInt(Pg);
constant integer esize = 64;
constant integer msize = 8;
constant boolean unsigned = FALSE;
constant integer offset = UInt(imm6);

Operation

CheckSVEEnabled();
constant integer VL = CurrentVL;
constant integer PL = VL DIV 8;
constant integer elements = VL DIV esize;
bits(64) base;
constant bits(PL) mask = P[g, PL];
bits(VL) result;
bits(msize) data;
constant integer mbytes = msize DIV 8;
constant boolean contiguous = TRUE;
constant boolean nontemporal = FALSE;
constant boolean tagchecked = n != 31;
constant AccessDescriptor accdesc = CreateAccDescSVE(MemOp_LOAD, nontemporal, contiguous,
                                                     tagchecked);

if !AnyActiveElement(mask, esize) then
    if n == 31 && ConstrainUnpredictableBool(Unpredictable_CHECKSPNONEACTIVE) then
        CheckSPAlignment();
else
    if n == 31 then CheckSPAlignment();
    base = if n == 31 then SP[64] else X[n, 64];
    constant bits(64) addr = AddressAdd(base, offset * mbytes, accdesc);
    data = Mem[addr, mbytes, accdesc];

for e = 0 to elements-1
    if ActivePredicateElement(mask, e, esize) then
        Elem[result, e, esize] = Extend(data, esize, unsigned);
    else
        Elem[result, e, esize] = Zeros(esize);

Z[t, VL] = result;

Explanations

<Zt>: Is the name of the scalable vector register to be transferred, encoded in the "Zt" field.
<Pg>: Is the name of the governing scalable predicate register P0-P7, encoded in the "Pg" field.
<Xn|SP>: Is the 64-bit name of the general-purpose base register or stack pointer, encoded in the "Rn" field.
<imm>: Is the optional unsigned immediate byte offset, in the range 0 to 63, defaulting to 0, encoded in the "imm6" field.

Operational Notes

If PSTATE.DIT is 1, the timing of this instruction is insensitive to the value of the data being loaded or stored when its governing predicate register contains the same value for each execution.