Section 3 Floating-Point Unit (FPU)
R01UH0025EJ0300 Rev. 3.00
Page 67 of 1336
Sep 24, 2010
SH7261 Group
Section 3 Floating-Point Unit (FPU)
3.1
Features
The FPU has the following features.
Conforms to IEEE754 standard
16 single-precision floating-point registers (can also be referenced as eight double-precision
registers)
Two rounding modes: Round to nearest and round to zero
Denormalization modes: Flush to zero
Five exception sources: Invalid operation, divide by zero, overflow, underflow, and inexact
Comprehensive instructions: Single-precision, double-precision, and system control
3.2
Data Formats
3.2.1
Floating-Point Format
A floating-point number consists of the following three fields:
Sign (s)
Exponent (e)
Fraction (f)
This LSI can handle single-precision and double-precision floating-point numbers, using the
formats shown in figures 3.1 and 3.2.
31
30
23
22
0
s
e
f
Figure 3.1 Format of Single-Precision Floating-Point Number
63
62
52
51
0
s
e
f
Figure 3.2 Format of Double-Precision Floating-Point Number