[Ffmpeg-devel] int vs. float: Hard Numbers

[Corey Hickey]

Rich Felker wrote:
> On Fri, May 20, 2005 at 12:46:24PM -0600, Mike Melanson wrote:
> 
>>  rdtsc            ; get a timestamp
>>  mov    ebx, eax  ; save the lower 32 bits of the timestamp
>>  mov    eax, 1    ; set up the base for multiplication
>>  times ITERATIONS  mul  ecx  ; perform n int mults (eax *= ecx)
>>  mov    ecx, eax  ; save the final product before fetching timestamp
>>  rdtsc            ; get another timestamp
> 
> 
> Each mul depends on the output of the previous one. Very bad test...
> :)
> 
> Rich

Would that explain why I'm sometimes getting different results when I
run the test repeatedly?

-Corey