vmla
Vector Multiply Accumulate (VFP)
VMLA<c>.F32 <Sd>, <Sn>, <Sm>
Sd = Sd + (Sn * Sm).
Details
Vector Multiply Accumulate (VFP) computes Sn × Sm and adds the result to Sd, storing the final value back in Sd. The operation follows IEEE 754 semantics with rounding and exception handling controlled by FPSCR, updating floating-point exception flags but not ARM condition flags. Available in A32/T32 with VFP extension; execution is conditional based on the condition code suffix.
Pseudocode Operation
product ← FP_Multiply(Sn, Sm)
Sd ← FP_Add(Sd, product)
FPSCR ← updated with floating-point exception flags
Example
VMLA.F32 s0, s1, s2
Encoding
Binary Layout
cond
1110
0
D
00
Vn
Vd
10
10
N
0
M
0
Vm
Operands
-
Sd
Dest/Acc -
Sn
First source 32-bit floating-point register -
Sm
Second source 32-bit floating-point register
Reference (Arm AArch32 ISA)
Instruction Forms
| Encoding | Instruction | ISA | Bit pattern | ||
|---|---|---|---|---|---|
| 0xF2000D10 | VMLA{<c>}{<q>}.<dt> <Dd>, <Dn>, <Dm> | A32 | 1111001 | 0 | 0 | D | 0 | sz | Vn | Vd | 1101 | N | 0 | M | 1 | Vm | ||
| 0xF2000D50 | VMLA{<c>}{<q>}.<dt> <Qd>, <Qn>, <Qm> | A32 | 1111001 | 0 | 0 | D | 0 | sz | Vn | Vd | 1101 | N | 1 | M | 1 | Vm | ||
| 0x0E000900 | VMLA{<c>}{<q>}.F16 <Sd>, <Sn>, <Sm> | A32 | cond | 1110 | 0 | D | 00 | Vn | Vd | 10 | 01 | N | 0 | M | 0 | Vm | ||
| 0x0E000A00 | VMLA{<c>}{<q>}.F32 <Sd>, <Sn>, <Sm> | A32 | cond | 1110 | 0 | D | 00 | Vn | Vd | 10 | 10 | N | 0 | M | 0 | Vm | ||
| 0x0E000B00 | VMLA{<c>}{<q>}.F64 <Dd>, <Dn>, <Dm> | A32 | cond | 1110 | 0 | D | 00 | Vn | Vd | 10 | 11 | N | 0 | M | 0 | Vm | ||
| 0xEF000D10 | VMLA{<c>}{<q>}.<dt> <Dd>, <Dn>, <Dm> | T32 | 111 | 0 | 11110 | D | 0 | sz | Vn | Vd | 1101 | N | 0 | M | 1 | Vm | ||
| 0xEF000D50 | VMLA{<c>}{<q>}.<dt> <Qd>, <Qn>, <Qm> | T32 | 111 | 0 | 11110 | D | 0 | sz | Vn | Vd | 1101 | N | 1 | M | 1 | Vm | ||
| 0xEE000900 | VMLA{<c>}{<q>}.F16 <Sd>, <Sn>, <Sm> | T32 | 11101110 | 0 | D | 00 | Vn | Vd | 10 | 01 | N | 0 | M | 0 | Vm | ||
| 0xEE000A00 | VMLA{<c>}{<q>}.F32 <Sd>, <Sn>, <Sm> | T32 | 11101110 | 0 | D | 00 | Vn | Vd | 10 | 10 | N | 0 | M | 0 | Vm | ||
| 0xEE000B00 | VMLA{<c>}{<q>}.F64 <Dd>, <Dn>, <Dm> | T32 | 11101110 | 0 | D | 00 | Vn | Vd | 10 | 11 | N | 0 | M | 0 | Vm | ||
| 0xF2000900 | VMLA{<c>}{<q>}.<dt> <Dd>, <Dn>, <Dm> | A32 | 1111001 | 0 | 0 | D | size | Vn | Vd | 1001 | N | 0 | M | 0 | Vm | ||
| 0xF2000940 | VMLA{<c>}{<q>}.<dt> <Qd>, <Qn>, <Qm> | A32 | 1111001 | 0 | 0 | D | size | Vn | Vd | 1001 | N | 1 | M | 0 | Vm | ||
| 0xEF000900 | VMLA{<c>}{<q>}.<dt> <Dd>, <Dn>, <Dm> | T32 | 111 | 0 | 11110 | D | size | Vn | Vd | 1001 | N | 0 | M | 0 | Vm | ||
| 0xEF000940 | VMLA{<c>}{<q>}.<dt> <Qd>, <Qn>, <Qm> | T32 | 111 | 0 | 11110 | D | size | Vn | Vd | 1001 | N | 1 | M | 0 | Vm |
Description
Vector Multiply Accumulate multiplies corresponding elements in two vectors, and accumulates the results into the elements of the destination vector.
Depending on settings in the CPACR, NSACR, HCPTR, and FPEXC 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(); CheckAdvSIMDOrVFPEnabled(TRUE, advsimd);
if advsimd then // Advanced SIMD instruction
for r = 0 to regs-1
for e = 0 to elements-1
product = FPMul(Elem[D[n+r],e,esize], Elem[D[m+r],e,esize], StandardFPSCRValue());
addend = if add then product else FPNeg(product);
Elem[D[d+r],e,esize] = FPAdd(Elem[D[d+r],e,esize], addend, StandardFPSCRValue());
else // VFP instruction
case esize of
when 16
addend16 = (if add then FPMul(S[n]<15:0>, S[m]<15:0>, FPSCR[])
else FPNeg(FPMul(S[n]<15:0>, S[m]<15:0>, FPSCR[])));
S[d] = Zeros(16) : FPAdd(S[d]<15:0>, addend16, FPSCR[]);
when 32
addend32 = (if add then FPMul(S[n], S[m], FPSCR[])
else FPNeg(FPMul(S[n], S[m], FPSCR[])));
S[d] = FPAdd(S[d], addend32, FPSCR[]);
when 64
addend64 = (if add then FPMul(D[n], D[m], FPSCR[])
else FPNeg(FPMul(D[n], D[m], FPSCR[])));
D[d] = FPAdd(D[d], addend64, FPSCR[]);