GMS30C2116 Datasheet, PDF (246/322 Pages) Hynix Semiconductor – USERS MANUAL

A-72
Floating-point Compare (single precision)
Appendix A. Instruction Set Details
FCMP
Format:
LL format
15
OP-code
1100 1000
87
43
0
Ld-code
Ls-code
Ls-code encodes L0..L15 for Ls
Ld-code encodes L0..L15 for Ld
Notation:
FCMPU Ld, Ls
Description:
Two operands are compared by subtracting the source operand form the destination
operand and all condition flags remain unchanged to allow future concurrent execution.
The floating-point instructions comply with the ANSI/IEEE standard 754-1985. In the
present version, they are executed as Software instructions.
This instruction uses single-precision operands and it must not placed as delay instructions.
A floating-point Not a Number (NaN) is encoded by bits 30..19 = all ones in the operand
word containing the exponent; all other bits of the operand are ignored for differentiating a
NaN form a non-NaN.
This instruction can raise only the Invalid Operation exception (at unordered). If the data
type of two operands are different (unordered) the Invalid Operation exception is occurred.
Operation:
result := Ld - Ls;
Z := Ld = Ls and not unordered;
N := Ld < Ls or unordered;
C := Ld < Ls and not unordered;
V := unordered;
if unordered then
Invalid Operation exception
Exceptions:
Invalid Operation.