FCMGE (register)

Floating-point Compare Greater than or Equal (vector). This instruction reads each floating-point value in the first source SIMD&FP register and if the value is greater than or equal to the corresponding floating-point value in the second source SIMD&FP register sets every bit of the corresponding vector element in the destination SIMD&FP register to one, otherwise sets every bit of the corresponding vector element in the destination SIMD&FP register to zero.

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 4 classes: Scalar half precision , Scalar single-precision and double-precision , Vector half precision and Vector single-precision and double-precision

Scalar half precision
(FEAT_FP16)

313029282726252423222120191817161514131211109876543210
01111110010Rm001001RnRd
UEac

FCMGE <Hd>, <Hn>, <Hm>

if !IsFeatureImplemented(FEAT_FP16) then UNDEFINED; integer d = UInt(Rd); integer n = UInt(Rn); integer m = UInt(Rm); constant integer esize = 16; constant integer datasize = esize; integer elements = 1; CompareOp cmp; boolean abs; case E:U:ac of when '000' cmp = CompareOp_EQ; abs = FALSE; when '010' cmp = CompareOp_GE; abs = FALSE; when '011' cmp = CompareOp_GE; abs = TRUE; when '110' cmp = CompareOp_GT; abs = FALSE; when '111' cmp = CompareOp_GT; abs = TRUE; otherwise UNDEFINED;

Scalar single-precision and double-precision

313029282726252423222120191817161514131211109876543210
011111100sz1Rm111001RnRd
UEac

FCMGE <V><d>, <V><n>, <V><m>

integer d = UInt(Rd); integer n = UInt(Rn); integer m = UInt(Rm); constant integer esize = 32 << UInt(sz); constant integer datasize = esize; integer elements = 1; CompareOp cmp; boolean abs; case E:U:ac of when '000' cmp = CompareOp_EQ; abs = FALSE; when '010' cmp = CompareOp_GE; abs = FALSE; when '011' cmp = CompareOp_GE; abs = TRUE; when '110' cmp = CompareOp_GT; abs = FALSE; when '111' cmp = CompareOp_GT; abs = TRUE; otherwise UNDEFINED;

Vector half precision
(FEAT_FP16)

313029282726252423222120191817161514131211109876543210
0Q101110010Rm001001RnRd
UEac

FCMGE <Vd>.<T>, <Vn>.<T>, <Vm>.<T>

if !IsFeatureImplemented(FEAT_FP16) then UNDEFINED; integer d = UInt(Rd); integer n = UInt(Rn); integer m = UInt(Rm); constant integer esize = 16; constant integer datasize = 64 << UInt(Q); integer elements = datasize DIV esize; CompareOp cmp; boolean abs; case E:U:ac of when '000' cmp = CompareOp_EQ; abs = FALSE; when '010' cmp = CompareOp_GE; abs = FALSE; when '011' cmp = CompareOp_GE; abs = TRUE; when '110' cmp = CompareOp_GT; abs = FALSE; when '111' cmp = CompareOp_GT; abs = TRUE; otherwise UNDEFINED;

Vector single-precision and double-precision

313029282726252423222120191817161514131211109876543210
0Q1011100sz1Rm111001RnRd
UEac

FCMGE <Vd>.<T>, <Vn>.<T>, <Vm>.<T>

integer d = UInt(Rd); integer n = UInt(Rn); integer m = UInt(Rm); if sz:Q == '10' then UNDEFINED; constant integer esize = 32 << UInt(sz); constant integer datasize = 64 << UInt(Q); integer elements = datasize DIV esize; CompareOp cmp; boolean abs; case E:U:ac of when '000' cmp = CompareOp_EQ; abs = FALSE; when '010' cmp = CompareOp_GE; abs = FALSE; when '011' cmp = CompareOp_GE; abs = TRUE; when '110' cmp = CompareOp_GT; abs = FALSE; when '111' cmp = CompareOp_GT; abs = TRUE; otherwise UNDEFINED;

Assembler Symbols

<Hd>

Is the 16-bit name of the SIMD&FP destination register, encoded in the "Rd" field.

<Hn>

Is the 16-bit name of the first SIMD&FP source register, encoded in the "Rn" field.

<Hm>

Is the 16-bit name of the second SIMD&FP source register, encoded in the "Rm" field.

<V>

Is a width specifier, encoded in sz:

sz <V>
0 S
1 D
<d>

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

<n>

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

<m>

Is the number of the second SIMD&FP source register, encoded in the "Rm" field.

<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, encoded in Q:

Q <T>
0 4H
1 8H

For the single-precision and double-precision variant: is an arrangement specifier, encoded in sz:Q:

sz 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.

Operation

CheckFPAdvSIMDEnabled64(); bits(datasize) operand1 = V[n, datasize]; bits(datasize) operand2 = V[m, datasize]; bits(esize) element1; bits(esize) element2; boolean test_passed; boolean merge = elements == 1 && IsMerging(FPCR); bits(128) result = if merge then V[m, 128] else Zeros(128); for e = 0 to elements-1 element1 = Elem[operand1, e, esize]; element2 = Elem[operand2, e, esize]; if abs then element1 = FPAbs(element1, FPCR); element2 = FPAbs(element2, FPCR); case cmp of when CompareOp_EQ test_passed = FPCompareEQ(element1, element2, FPCR); when CompareOp_GE test_passed = FPCompareGE(element1, element2, FPCR); when CompareOp_GT test_passed = FPCompareGT(element1, element2, FPCR); Elem[result, e, esize] = if test_passed then Ones(esize) else Zeros(esize); V[d, 128] = result;


Internal version only: aarchmrs v2024-03_relA, pseudocode v2024-03_rel, sve v2024-03_rel ; Build timestamp: 2024-03-26T09:45

Copyright © 2010-2024 Arm Limited or its affiliates. All rights reserved. This document is Non-Confidential.