News for hackers. Stuff that matters.

A comment on The software development final exam: Computer Architecture and Operating Systems. Parent comment

Re:The software development final exam: Computer Architectur... by tcbawo on Tuesday October 09, 2012 @08:33AM (#4631125)
I believe when traversing memory in a predictable, linear fashion the CPU will prefetch data. I thought the CPUs are smart enough to do that for the more complex examples as well, but maybe not for steps of 1024.
[ Parent | on HN ]
Re:The software development final exam: Computer Architectur... by kd0amg on Tuesday October 09, 2012 @12:39PM (#4632493)
Intel Core architecture has a stride prefetcher, but it will not prefetch across page boundaries (which you hit pretty often with a 1k step size).
[ Parent | on HN ]
Re:The software development final exam: Computer Architectur... by alexkus on Tuesday October 09, 2012 @05:29PM (#4634056)
You'll hit it every time given a typical x86 4KB page size and a step of 1024*sizeof(double)=8KB.

I would guess that the example was explicitly contrived so that prefetching would be useless.

[ Parent | on HN ]
Re:The software development final exam: Computer Architectur... by cperciva on Tuesday October 09, 2012 @09:41PM (#4634705)
I would guess that the example was explicitly contrived so that prefetching would be useless.

Yes -- even if prefetching could happen, the first function would be faster than the second, but I thought removing the whole issue of prefetching would simplify the question.

[ Parent | on HN ]