STNT1B (vector plus scalar)
Scatter store non-temporal bytes
Scatter store non-temporal of bytes from the active elements of a vector register to the memory addresses generated by a vector base plus a 64-bit unscaled scalar register offset. Inactive elements are not written to memory.
A non-temporal store is a hint to the system that this data is unlikely to be referenced again soon.
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
It has encodings from 2 classes:
32-bit unscaled offset
and
64-bit unscaled offset
1
1
1
0
0
1
0
0
0
1
0
0
0
1
STNT1B { <Zt>.S }, <Pg>, [<Zn>.S{, <Xm>}]
if !IsFeatureImplemented(FEAT_SVE2) then UNDEFINED;
constant integer t = UInt(Zt);
constant integer n = UInt(Zn);
constant integer m = UInt(Rm);
constant integer g = UInt(Pg);
constant integer esize = 32;
constant integer msize = 8;
1
1
1
0
0
1
0
0
0
0
0
0
0
1
STNT1B { <Zt>.D }, <Pg>, [<Zn>.D{, <Xm>}]
if !IsFeatureImplemented(FEAT_SVE2) then UNDEFINED;
constant integer t = UInt(Zt);
constant integer n = UInt(Zn);
constant integer m = UInt(Rm);
constant integer g = UInt(Pg);
constant integer esize = 64;
constant integer msize = 8;
<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.
CheckNonStreamingSVEEnabled();
constant integer VL = CurrentVL;
constant integer PL = VL DIV 8;
constant integer elements = VL DIV esize;
constant bits(PL) mask = P[g, PL];
bits(VL) base;
bits(64) offset;
bits(VL) src;
constant integer mbytes = msize DIV 8;
constant boolean contiguous = FALSE;
constant boolean nontemporal = TRUE;
constant boolean tagchecked = TRUE;
constant AccessDescriptor accdesc = CreateAccDescSVE(MemOp_STORE, nontemporal, contiguous,
tagchecked);
if AnyActiveElement(mask, esize) then
base = Z[n, VL];
offset = X[m, 64];
src = Z[t, VL];
for e = 0 to elements-1
if ActivePredicateElement(mask, e, esize) then
constant bits(64) baddr = ZeroExtend(Elem[base, e, esize], 64);
constant bits(64) addr = AddressAdd(baddr, offset, accdesc);
Mem[addr, mbytes, accdesc] = Elem[src, e, esize]<msize-1:0>;