🚀 go-pugleaf

In article <stephenkDp0JpA.F6u@netcom.com>, stephenk@netcom.com (Stephen
Knilans) wrote:
] 
] Ya know, I WAS going to mail this post back seperate, but I guess I'll do it 
] HERE!  the P5 was "EATEN ALIVE" by the 601, HUH?  Look at this, and tell
me how
] we are mistaken!
] 
] #include <stdio.h>
] #include <math.h>
]  
] void main(void)
] {
]         double  sum, i;
]         
]         sum = 0;
]         for(i=1;i<10000000;i++)
]         {
]                 sum = sum + sqrt(sin(i/4.2)*sin(i/4.2) + log(i));
]         }
]         printf("total: %f", sum);
] }
] /*** end ***/
] /*  

This benchmark is pretty useless as a general indicator or even as a
floating point benchmark.  It is far too heavily laden with
trancendentals, which are going to be library implemented on most risc
chips and even some cisc chips.  I.E. drop in a different mathlib on the
same machine and this mark will probably get vastly different marks.

Also, this mark is static in scale and branch.  Try varying both the loop
size and also add a memory reference or two (to a varying memory structure
size) and see how the relative marks between machines will vary
tremendously.

Creating useful benchmarks is not a trivial task.

In other words, don't put too much stock in any results from timing this mark.

Bit bucket.

Cheers,

Mel Martinez
The Johns Hopkins University
Dept. of Physics
mem@jhu.edu