vst4
Vector Store Multiple (4-Element Structure)
VST4<c>.<size> <list>, [<Rn>]{!}
Interleaves and stores four registers into memory (e.g., RGBA).
Details
Interleaves and stores four NEON registers into memory as four-element structures. The instruction reads from four consecutive registers and interleaves their elements before writing (4 × element_size × 8) bits to the address in Rn. Condition flags (N, Z, C, V) are unaffected. Execution is restricted to A32/T32 with NEON extension; post-index writeback to Rn is optional.
Pseudocode Operation
address ← Rn
for i = 0 to 7 do
element_size_bits ← size_in_bits(size)
[address + (i * element_size_bits / 8)] ← Vd[i]
[address + (i * element_size_bits / 8) + (element_size_bits / 8)] ← Vd+1[i]
[address + (i * element_size_bits / 8) + (2 * element_size_bits / 8)] ← Vd+2[i]
[address + (i * element_size_bits / 8) + (3 * element_size_bits / 8)] ← Vd+3[i]
if (writeback) then
Rn ← Rn + (4 * 8 * element_size_bits / 8)
Example
VST4.size {r0-r3}, [r1]!
Encoding
Binary Layout
111101000
D
0
0
Rn
Vd
itype
size
align
Rm
Operands
-
list
Src Registers -
Rn
First source / base general-purpose register
Reference (Arm AArch32 ISA)
Instruction Forms
| Encoding | Instruction | ISA | Bit pattern | ||
|---|---|---|---|---|---|
| 0xF480030F | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}] | A32 | 111101001 | D | 0 | 0 | Rn | Vd | 00 | 11 | index_align | 1111 | ||
| 0xF480030D | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}]! | A32 | 111101001 | D | 0 | 0 | Rn | Vd | 00 | 11 | index_align | 1101 | ||
| 0xF4800300 | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}], <Rm> | A32 | 111101001 | D | 0 | 0 | Rn | Vd | 00 | 11 | index_align | Rm | ||
| 0xF480070F | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}] | A32 | 111101001 | D | 0 | 0 | Rn | Vd | 01 | 11 | index_align | 1111 | ||
| 0xF480070D | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}]! | A32 | 111101001 | D | 0 | 0 | Rn | Vd | 01 | 11 | index_align | 1101 | ||
| 0xF4800700 | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}], <Rm> | A32 | 111101001 | D | 0 | 0 | Rn | Vd | 01 | 11 | index_align | Rm | ||
| 0xF4800B0F | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}] | A32 | 111101001 | D | 0 | 0 | Rn | Vd | 10 | 11 | index_align | 1111 | ||
| 0xF4800B0D | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}]! | A32 | 111101001 | D | 0 | 0 | Rn | Vd | 10 | 11 | index_align | 1101 | ||
| 0xF4800B00 | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}], <Rm> | A32 | 111101001 | D | 0 | 0 | Rn | Vd | 10 | 11 | index_align | Rm | ||
| 0xF980030F | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}] | T32 | 111110011 | D | 0 | 0 | Rn | Vd | 00 | 11 | index_align | 1111 | ||
| 0xF980030D | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}]! | T32 | 111110011 | D | 0 | 0 | Rn | Vd | 00 | 11 | index_align | 1101 | ||
| 0xF9800300 | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}], <Rm> | T32 | 111110011 | D | 0 | 0 | Rn | Vd | 00 | 11 | index_align | Rm | ||
| 0xF980070F | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}] | T32 | 111110011 | D | 0 | 0 | Rn | Vd | 01 | 11 | index_align | 1111 | ||
| 0xF980070D | VST4{<c>}{<q>}.<size> <list>, [<Rn>{:<align>}]! | T32 | 111110011 | D | 0 | 0 | Rn | Vd | 01 | 11 | index_align | 1101 |
Description
Store multiple 4-element structures from four registers stores multiple 4-element structures to memory from four registers, with interleaving. For more information, see Element and structure load/store instructions. Every element of each register is saved. For details of the addressing mode, see Advanced SIMD addressing mode.
Depending on settings in the CPACR, NSACR, and HCPTR registers, and the Security state and PE mode in which the instruction is executed, an attempt to execute the instruction might be undefined, or trapped to Hyp mode. For more information, see Enabling Advanced SIMD and floating-point support.
Operation
if ConditionPassed() then
EncodingSpecificOperations();
CheckAdvSIMDEnabled();
address = R[n];
boolean nontemporal = FALSE;
boolean tagchecked = FALSE;
AccessDescriptor accdesc = CreateAccDescASIMD(MemOp_STORE, nontemporal, tagchecked);
if !IsAligned(address, alignment) then
AArch32.Abort(address, AlignmentFault(accdesc));
for e = 0 to elements-1
MemU[address, ebytes] = Elem[D[d], e,8*ebytes];
MemU[address+ebytes, ebytes] = Elem[D[d2],e,8*ebytes];
MemU[address+2*ebytes,ebytes] = Elem[D[d3],e,8*ebytes];
MemU[address+3*ebytes,ebytes] = Elem[D[d4],e,8*ebytes];
address = address + 4*ebytes;
if wback then
if register_index then
R[n] = R[n] + R[m];
else
R[n] = R[n] + 32;