Re: Comprehensive Threadripper tests - memory vs cpu freq at capped power

2018-08-24 Thread M. L. Wilson
Many thanks for this explanation! On 08/24/2018 03:04 AM, Gerald Henriksen wrote: On Thu, 23 Aug 2018 23:17:29 +0300, you wrote: Hi, The Threadripper discussion has been very interesting. Will these adjustments to NUMA for Threadripper's topography also apply to Epyc also? Or will more

Re: Comprehensive Threadripper tests - memory vs cpu freq at capped power

2018-08-23 Thread Gerald Henriksen
On Thu, 23 Aug 2018 23:17:29 +0300, you wrote: >Hi, > >The Threadripper discussion has been very interesting. > >Will these adjustments to NUMA for Threadripper's topography also apply to >Epyc also? Or will more nuanced work need to be done once an Epyc system >becomes available? Epyc doesn't

Re: Comprehensive Threadripper tests - memory vs cpu freq at capped power

2018-08-23 Thread M. L. Wilson
Hi, The Threadripper discussion has been very interesting. Will these adjustments to NUMA for Threadripper's topography also apply to Epyc also? Or will more nuanced work need to be done once an Epyc system becomes available? M On 08/20/2018 09:05 AM, Matthew Dillon wrote: It will depend

Re: Comprehensive Threadripper tests - memory vs cpu freq at capped power

2018-08-20 Thread Matthew Dillon
It will depend on the frequency of the interconnect as well. I think the idle power use comes out in my tests too... idle power consumption is around 83W with the fabric running at 2800 or 3000 MHz, and 65W when running at 2666 MHz or slower. At idle the cpu frequency is at the same relative low

Re: Comprehensive Threadripper tests - memory vs cpu freq at capped power

2018-08-19 Thread Samuel Paik
Apparently there are some special cpu registers you can read to get power used by some components, probably not highly accurate but likely indicative. Anandtech's review ( https://www.anandtech.com/show/13124/the-amd-threadripper-2990wx-and-2950x-review/4 ) covered some of this, they found the