fmin
Floating-Point Minimum (Half-Precision)
FMIN <Vd>.8H, <Vn>.8H, <Vm>.8H
Finds min of half-precision vectors.
Details
Computes the minimum of half-precision floating-point elements in Vn and Vm element-wise, writing results to Vd. Operates on 8 half-precision (16-bit) values in 128-bit vectors, with NaN handling per IEEE 754 semantics (FPCR controls exact behavior). No condition flags are set; floating-point exceptions depend on FPCR. Requires FEAT_FP16 extension; AArch64-only.
Pseudocode Operation
for i = 0 to 7
Vd[i*16 +: 16] ← FP16_Min(Vn[i*16 +: 16], Vm[i*16 +: 16])
Example
FMIN v0.4s.8H, v1.4s.8H, v2.4s.8H
Encoding
Binary Layout
0
Q
0
01110
1
10
Rm
00
110
1
Rn
Rd
Operands
-
Vd
Destination SIMD/FP vector register -
Vn
First source SIMD/FP vector register -
Vm
Second source SIMD/FP vector register
Reference (Arm A64 ISA)
Instruction Forms
| Encoding | Instruction | ISA | Bit pattern | ||
|---|---|---|---|---|---|
| 0x0EC03400 | FMIN <Vd>.<T>, <Vn>.<T>, <Vm>.<T> | A64 | 0 | Q | 0 | 01110 | 1 | 10 | Rm | 00 | 110 | 1 | Rn | Rd | ||
| 0x0EA0F400 | FMIN <Vd>.<T>, <Vn>.<T>, <Vm>.<T> | A64 | 0 | Q | 0 | 01110 | 1 | sz | 1 | Rm | 11110 | 1 | Rn | Rd | ||
| 0x1EE05800 | FMIN <Hd>, <Hn>, <Hm> | A64 | 0 | 0 | 0 | 11110 | 11 | 1 | Rm | 01 | 01 | 10 | Rn | Rd | ||
| 0x1E205800 | FMIN <Sd>, <Sn>, <Sm> | A64 | 0 | 0 | 0 | 11110 | 00 | 1 | Rm | 01 | 01 | 10 | Rn | Rd | ||
| 0x1E605800 | FMIN <Dd>, <Dn>, <Dm> | A64 | 0 | 0 | 0 | 11110 | 01 | 1 | Rm | 01 | 01 | 10 | Rn | Rd | ||
| 0xC120A101 | FMIN { <Zdn1>.<T>-<Zdn2>.<T> }, { <Zdn1>.<T>-<Zdn2>.<T> }, <Zm>.<T> | A64 | 11000001 | size | 10 | Zm | 101000 | 0100 | 0 | Zdn | 1 | ||
| 0xC120A901 | FMIN { <Zdn1>.<T>-<Zdn4>.<T> }, { <Zdn1>.<T>-<Zdn4>.<T> }, <Zm>.<T> | A64 | 11000001 | size | 10 | Zm | 101010 | 0100 | 0 | Zdn | 0 | 1 | ||
| 0xC120B101 | FMIN { <Zdn1>.<T>-<Zdn2>.<T> }, { <Zdn1>.<T>-<Zdn2>.<T> }, { <Zm1>.<T>-<Zm2>.<T> } | A64 | 11000001 | size | 1 | Zm | 0101100 | 010 | 0 | 0 | Zdn | 1 | ||
| 0xC120B901 | FMIN { <Zdn1>.<T>-<Zdn4>.<T> }, { <Zdn1>.<T>-<Zdn4>.<T> }, { <Zm1>.<T>-<Zm4>.<T> } | A64 | 11000001 | size | 1 | Zm | 00101110 | 010 | 0 | 0 | Zdn | 0 | 1 | ||
| 0x651F8000 | FMIN <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <const> | A64 | 01100101 | size | 011 | 11 | 1 | 100 | Pg | 0000 | i1 | Zdn | ||
| 0x65078000 | FMIN <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T> | A64 | 01100101 | size | 00 | 011 | 1 | 100 | Pg | Zm | Zdn |
Description
Floating-point minimum (vector). This instruction compares corresponding elements in the vectors in the two source SIMD&FP registers, places the smaller of each of the two floating-point values into a vector, and writes the vector to the destination SIMD&FP register.
When FPCR.AH is 0, the behavior is as follows:
When FPCR.AH is 1, the behavior is as follows:
This instruction can generate a floating-point exception. Depending on the settings in FPCR, the exception results in either a flag being set in FPSR, or a synchronous exception being generated. For more information, see Floating-point exception traps.
Depending on the settings in the CPACR_EL1, CPTR_EL2, and CPTR_EL3 registers, and the current Security state and Exception level, an attempt to execute the instruction might be trapped.
Operation
CheckFPAdvSIMDEnabled64();
bits(datasize) operand1 = V[n, datasize];
bits(datasize) operand2 = V[m, datasize];
bits(datasize) result;
bits(2*datasize) concat = operand2:operand1;
bits(esize) element1;
bits(esize) element2;
for e = 0 to elements-1
if pair then
element1 = Elem[concat, 2*e, esize];
element2 = Elem[concat, (2*e)+1, esize];
else
element1 = Elem[operand1, e, esize];
element2 = Elem[operand2, e, esize];
if minimum then
Elem[result, e, esize] = FPMin(element1, element2, FPCR);
else
Elem[result, e, esize] = FPMax(element1, element2, FPCR);
V[d, datasize] = result;