Re:How Not to Measure Computer System Performance
by halayli on Tuesday November 18, 2014 @05:24PM
(#8626783)
Guessing, locality of reference might play a role.
[ Parent
| on HN ]
Re:How Not to Measure Computer System Performance
by fleitz on Wednesday November 19, 2014 @04:48AM
(#8629086)
That, the branch predictors, and caching behaviors, n-way, alignment, etc.
It probably explains why different runs vary so widely, I always thought it was other things going on in the OS, never really thought about the caches, etc.
Re:How Not to Measure Computer System Performance
by halayli on Wednesday November 19, 2014 @05:08PM
(#8632978)
> That, the branch predictors, and caching behaviors, n-way, alignment, etc.
Those all fall under locality of reference, btw. But yeah cache and branch prediction play a huge role in the list.
One thing that stung me in the past was OS scheduling.