AMD AMD-K6-2/500AFX Data Sheet - Page 48
FloatingPoint Register Data Types, Packed Decimal Data Register
View all AMD AMD-K6-2/500AFX manuals
Add to My Manuals
Save this manual to your list of manuals |
Page 48 highlights
AMD-K6®-2 Processor Data Sheet Preliminary Information 21850J/0-February 2000 Floating-Point Register Data Types Floating-point registers use four different types of data - packed decimal, single-precision real, double-precision real, and extended-precision real. Figures 15 and 16 show the formats for these registers. 79 78 72 71 Ignore S or Zero 0 Precision - 18 Digits, 72 Bits Used, 4-Bits/Digit Description Bits Ignored on Load, Zeros on Store 78-72 Sign Bit 79 Figure 15. Packed Decimal Data Register Single-Precision Real 31 30 23 22 0 S Biased Exponent Significand Double-Precision Real 63 62 52 51 S Biased Exponent S = Sign Bit 0 Significand S = Sign Bit Extended-Precision Real 79 78 64 63 62 0 S Biased I Exponent Significand S = Sign Bit I = Integer Bit Figure 16. Precision Real Data Registers 28 Software Environment Chapter 3