News for hackers. Stuff that matters.

A comment on CPU Utilization is Wrong.

Re:CPU Utilization is Wrong by flamedoge on Tuesday May 09, 2017 @04:09PM (#14303400)
> If your IPC is < 1.0, you are likely memory stalled,

depends on the workload.

[ Parent | on HN ]
Re:CPU Utilization is Wrong by IIIIIIIIIIII on Tuesday May 09, 2017 @04:52PM (#14303704)
It's always nice to see when people take even less than a complete sentence and pretend that this is what the author said and that this was all.
[ Parent | on HN ]
Re:CPU Utilization is Wrong by qb45 on Tuesday May 09, 2017 @07:24PM (#14304723)
Better yet if the response is even shorter than the excerpt quoted ;)
[ Parent | on HN ]
Re:CPU Utilization is Wrong by squeaky-clean on Tuesday May 09, 2017 @06:02PM (#14304183)
> For my above rules, I split on an IPC of 1.0. Where did I get that from? I made it up, based on my prior work with PMCs. Here's how you can get a value that's custom for your system and runtime: write two dummy workloads, one that is CPU bound, and one memory bound. Measure their IPC, then calculate their mid point.
[ Parent | on HN ]