Timings for the Math Library--libm:
Using a GPS MAS281 Processor

Applies to: GCC-1750 Version 1.0.
Last updated: Friday May 03, 2002.

SUMMARY

The library libm is the ANSI standard math library. In GCC-1750 the math library is written as a number of C language files, some of which have assembly language inserts. Hardware floating point arithmetic is used where possible. In most cases libm uses extended precision floating point because in the C language, floating point operations default to the type ‘double’ and all the functions in libm take double arguments and return double results.

We ran the libm execution time tests on the 5MHz MAS281 target. We got the instruction counts using 1750 the simulator.

The results are presented in the following table:

Function call

Number of Instructions Executed

Execution Time in Microseconds
acos (0.5)

64

401
asin (0.5)

55

377
atan (0.5)

66

438
atan2 (1.0, 2.0)

98

491
ceil (1.5)

40

56
cos (1.0)

144

540
cosh (1.0)

170

574
exp (1.0)

149

460
fabs (1.0)

0

0
floor (1.5)

27

26
fmod (100.0, 3.0)

55

128
frexp (1024.0, &itmp)

12

16
ldexp (1.0, 10)

19

18
log (100.0)

70

415
log10 (100.0)

77

441
modf (1.5, &xtmp)

47

61
pow (10.0, 10.0)

357

1066
sin (1.0)

131

469
sinh (1.0)

39

233
sqrt (2.0)

72

317
tan (1.0)

191

556
tanh (1.0)

180

575
 
Updated May 11, 2005
Copyright XGC Software