You copied the Doc URL to your clipboard.

FMAXP (scalar)

Floating-point Maximum of Pair of elements (scalar). This instruction compares two vector elements in the source SIMD&FP register and writes the largest of the floating-point values as a scalar to the destination SIMD&FP register.

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.

It has encodings from 2 classes: Half-precision and Single-precision and double-precision

Half-precision
(Armv8.2)

313029282726252423222120191817161514131211109876543210
0101111000110000111110RnRd
o1sz

Half-precision

FMAXP <V><d>, <Vn>.<T>

if !HaveFP16Ext() then UNDEFINED;

integer d = UInt(Rd);
integer n = UInt(Rn);

integer esize = 16;
integer datasize = 32;

Single-precision and double-precision

313029282726252423222120191817161514131211109876543210
011111100sz110000111110RnRd
o1

Single-precision and double-precision

FMAXP <V><d>, <Vn>.<T>

integer d = UInt(Rd);
integer n = UInt(Rn);

integer esize = 32;
integer datasize = 64;

Assembler Symbols

<V> For the half-precision variant: is the destination width specifier, encoded in sz:
sz <V>
0 H
1 RESERVED
For the single-precision and double-precision variant: is the destination width specifier, encoded in sz:
sz <V>
0 S
1 D
<d>

Is the number of the SIMD&FP destination register, encoded in the "Rd" field.

<Vn>

Is the name of the SIMD&FP source register, encoded in the "Rn" field.

<T> For the half-precision variant: is the source arrangement specifier, encoded in sz:
sz <T>
0 2H
1 RESERVED
For the single-precision and double-precision variant: is the source arrangement specifier, encoded in sz:
sz <T>
0 2S
1 2D

Operation

CheckFPAdvSIMDEnabled64();
bits(datasize) operand = V[n];
V[d] = Reduce(ReduceOp_FMAX, operand, esize);
Was this page helpful? Yes No