User's Manual

OVERVIEW OF NUMERIC PROCESSING
DOUBLE-PRECISION
WHETSTONE PERFORMANCE
(KOPS)
200
100
STACK TOP POINTER'"
( 80286/80287 )
.-------...../
( 8086/8087)
1980 1983
YEAR INTRODUCED
Figure 1-1. Evolution and Performance of Numeric Processors
Table 1-1. Numeric Processing Speed Comparisons
Approximate Performance Ratios:
Floatlng'Polnt Instruction
8 MHz 80287 to
G30108
8 MHz Protected Mode IAPX using E80287
FADD ST,ST (Temp Real) Addition
1: 42
FDIV DWORD PTR (Single-Precision)
Division
1:266
FXAM
(Stack(O) assumed)
Examine 1:139
FYL2X
(Stack(O),(1) assumed) Logarithm 1: 99
FPATAN (Stack(O) assumed) Arctangent
1:153
F2XM1 (Stack(O) assumed) Exponentiation 1: 41
Ease of Use
The 80287 NPX offers more than raw execution speed for computation-intensive tasks. The 80287
brii:.g3 the f!!ncticn::!lity ~nd power of Accurate numeric computation into the hands of the general user.
Like the
8087 NPX that preceded it, the 80287 is explicitly designed to deliver stable, accurate results
when programmed using straightforward
"pencil and paper" algorithms. The IEEE 754 standard
specifically addresses this issue, recognizing the fundamental importance of making numeric
compu-
tations both easy and safe to use.
For example, most computers can overflow when two single-precision floating-point numbers are
multi-
plied together and then divided by a third, even if the final result is a perfectly valid 32-bit number.
1-2