FAMAX
Floating-point absolute maximum
This instruction determines the maximum absolute value from floating-point elements
of the first source vector and the corresponding floating-point elements
of the second source vector, and places the results in the corresponding elements
of the destination vector.
The behavior is as follows:
When FPCR.DN is 0, if either element is a NaN,
the result is a quiet NaN.
When FPCR.DN is 1, if either element is a NaN,
the result is the Default NaN.
Denormalized inputs and results are never flushed to zero, as if
FPCR.{FZ, FZ16, FIZ} is {0, 0, 0}.
Denormalized inputs never generate an Input Denormal floating-point exception.
It has encodings from 2 classes:
Half-precision
and
Single-precision and double-precision
0
0
0
1
1
1
0
1
1
0
0
0
0
1
1
1
FAMAX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>
if !IsFeatureImplemented(FEAT_FAMINMAX) then UNDEFINED;
constant integer d = UInt(Rd);
constant integer n = UInt(Rn);
constant integer m = UInt(Rm);
constant integer esize = 16;
constant integer datasize = if Q == '1' then 128 else 64;
constant integer elements = datasize DIV esize;
0
0
0
1
1
1
0
1
x
1
1
1
0
1
1
1
FAMAX <Vd>.<T>, <Vn>.<T>, <Vm>.<T>
if !IsFeatureImplemented(FEAT_FAMINMAX) then UNDEFINED;
if Q == '0' && size == '11' then UNDEFINED;
constant integer d = UInt(Rd);
constant integer n = UInt(Rn);
constant integer m = UInt(Rm);
constant integer esize = 8 << UInt(size);
constant integer datasize = if Q == '1' then 128 else 64;
constant integer elements = datasize DIV esize;
<Vd>
Is the name of the SIMD&FP destination register, encoded in the "Rd" field.
<T>
For the half-precision variant: is an arrangement specifier,
<T>
For the single-precision and double-precision variant: is an arrangement specifier,
size<0>
Q
<T>
0
0
2S
0
1
4S
1
0
RESERVED
1
1
2D
<Vn>
Is the name of the first SIMD&FP source register, encoded in the "Rn" field.
<Vm>
Is the name of the second SIMD&FP source register, encoded in the "Rm" field.
CheckFPAdvSIMDEnabled64();
constant bits(datasize) operand1 = V[n, datasize];
constant bits(datasize) operand2 = V[m, datasize];
bits(datasize) result;
for e = 0 to elements-1
constant bits(esize) op1 = Elem[operand1, e, esize];
constant bits(esize) op2 = Elem[operand2, e, esize];
Elem[result, e, esize] = FPAbsMax(op1, op2, FPCR);
V[d, datasize] = result;