Instruction Model
PowerPC e500 Core Family Reference Manual, Rev. 1
Freescale Semiconductor 3-59
The embedded floating-point APUs are described as follows:
• Vector SPFP instructions operate on a vector of two 32-bit, single-precision floating-point
numbers that reside in the upper and lower halves of the 64-bit GPRs.
• Scalar SPFP instructions operate on single 32-bit operands that reside in the lower 32-bits
of the GPRs.
• Scalar DPFP instructions (e500v2 only) operate on single 64-bit operands that reside in the
64-bit GPRs. Full descriptions of these instructions is provided in Section 10.4,
“Double-Precision Floating-Point APU (e500 v2 Only).”
These instructions are listed in Table 3-37.
NOTE
Vector and scalar versions of the instructions have the same syntax.
Table 3-37. Vector and Scalar Floating-Point APU Instructions
Instruction
Single-Precision
Scalar
Double-Precision
Scalar (e500v2)
Vector Syntax
Convert Floating-Point Double- from Single-Precision —efdcfs—rD,rB
Convert Floating-Point from Signed Fraction efscfsf efdcfsf evfscfsf rD,rB
Convert Floating-Point from Signed Integer efscfsi efdcfsi evfscfsi rD,rB
Convert Floating-Point from Unsigned Fraction efscfuf efdcfuf evfscfuf rD,rB
Convert Floating-Point from Unsigned Integer efscfui efdcfui evfscfui rD,rB
Convert Floating-Point Single- from Double-Precision —efscfd—rD,rB
Convert Floating-Point to Signed Fraction efsctsf efdctsf evfsctsf rD,rB
Convert Floating-Point to Signed Integer efsctsi efdctsi evfsctsi rD,rB
Convert Floating-Point to Signed Integer with Round toward
Zero
efsctsiz efdctsiz evfsctsiz rD,rB
Convert Floating-Point to Unsigned Fraction efsctuf efdctuf evfsctuf rD,rB
Convert Floating-Point to Unsigned Integer efsctui efdctui evfsctui rD,rB
Convert Floating-Point to Unsigned Integer with Round
toward Zero
efsctuiz efdctuiz evfsctuiz rD,rB
Floating-Point Absolute Value efsabs
1
efdabs evfsabs rD,rA
Floating-Point Add efsadd efdadd evfsadd rD,rA,rB
Floating-Point Compare Equal efscmpeq efdcmpeq evfscmpeq crD,rA,rB
Floating-Point Compare Greater Than efscmpgt efdcmpgt evfscmpgt crD,rA,rB
Floating-Point Compare Less Than efscmplt efdcmplt evfscmplt crD,rA,rB
Floating-Point Divide efsdiv efddiv evfsdiv rD,rA,rB
Floating-Point Multiply efsmul efdmul evfsmul rD,rA,rB
Floating-Point Negate efsneg
1
efdneg evfsneg rD,rA
Floating-Point Negative Absolute Value efsnabs
1
efdnabs evfsnabs rD,rA
Floating-Point Subtract efssub efdsub evfssub rD,rA,rB
To Next Page
Loading...
