LD1Q
Gather load quadwords
Gather load of quadwords to active elements of a vector register from memory addresses generated by a vector base plus a 64-bit unscaled scalar register offset. Inactive elements will not cause a read from Device memory or signal faults, and are set to zero in the destination vector.
This instruction is illegal when executed in Streaming SVE mode, unless FEAT_SME_FA64 is implemented and enabled.
Green
True
True
True
SM_0_only
1
1
0
0
0
1
0
0
0
0
0
1
0
1
LD1Q { <Zt>.Q }, <Pg>/Z, [<Zn>.D{, <Xm>}]
if !IsFeatureImplemented(FEAT_SVE2p1) then UNDEFINED;
constant integer t = UInt(Zt);
constant integer n = UInt(Zn);
constant integer m = UInt(Rm);
constant integer g = UInt(Pg);
<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.
<Zn>
Is the name of the base scalable vector register, encoded in the "Zn" field.
<Xm>
Is the optional 64-bit name of the general-purpose offset register, defaulting to XZR, encoded in the "Rm" field.
constant integer VL = CurrentVL;
constant integer PL = VL DIV 8;
CheckNonStreamingSVEEnabled();
constant integer elements = VL DIV 128;
constant bits(PL) mask = P[g, PL];
bits(VL) base;
bits(64) offset;
bits(VL) result;
constant boolean contiguous = FALSE;
constant boolean nontemporal = FALSE;
constant boolean tagchecked = TRUE;
constant AccessDescriptor accdesc = CreateAccDescSVE(MemOp_LOAD, nontemporal, contiguous,
tagchecked);
if AnyActiveElement(mask, 128) then
base = Z[n, VL];
offset = X[m, 64];
for e = 0 to elements-1
if ActivePredicateElement(mask, e, 128) then
constant bits(64) baddr = Elem[base, 2*e, 64];
constant bits(64) addr = AddressAdd(baddr, offset, accdesc);
Elem[result, e, 128] = Mem[addr, 16, accdesc];
else
Elem[result, e, 128] = Zeros(128);
Z[t, VL] = result;