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

[Mike Melanson]

Mike Melanson wrote:
> Interesting notes:

	I should point out that I am running this on a VIA CPU (?). This is the 
/proc/cpuinfo:

processor       : 0
vendor_id       : CentaurHauls
cpu family      : 6
model           : 7
model name      : VIA Samuel 2
stepping        : 3
cpu MHz         : 533.507
cache size      : 64 KB
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 1
wp              : yes
flags           : fpu de tsc msr cx8 mtrr pge mmx pni 3dnow
bogomips        : 1048.57


	Now that the source is available, you can see that there is an 
ITERATIONS constant at the top of math.asm. Change that if you want to 
change the number of instructions benchmarked. Making it larger (even 
20) begins to degrade the average per-instruction performance, though 
float still seems to perform better than int.

-- 
	-Mike Melanson