Discussion PES | Assessing Power and Performance Efficiency of x86 CPU architectures

Page 7 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Det0x

Senior member
Sep 11, 2014
934
2,512
136
@Det0x
Might you do me a favor and try this LibreOffice Results file:
https://github.com/BrsVgl/PerformanceEfficiencySuite/raw/main/Results LibreOffice.ods

Just replace the existing one in your folder and try if it works.
Hint: For me it takes a while to import the data, but generally it works.
Yes that actually worked, can view the results myself now :blush:

Btw are you sure its correct to judge/rank results by runtime ?(duration)
Have you tried to compare time vs score ? Does it line up ?

Also alittle surprised by the results.. This is how a high scoring run from me look like:

Can speculate some of the benchmarks have a set runtime like 10sec, and must be judged by the score they achieve in those 10seconds, not the fact they ran for 10sec, if you understand what i mean :)
 

BorisTheBlade82

Senior member
May 1, 2020
381
543
106
@Det0x
Great, that the LibreOffice sheet works for you. So I will include that in the next minor release.

As to the nature of GB5: I had always assumed that it is a fixed Workload just like CB. Maybe I am wrong - but I don't know how to prove either way.
But yes, time vs. score at least has the same tendency.
 

BorisTheBlade82

Senior member
May 1, 2020
381
543
106
@igor_kavinski
It is technically not possible to run PES on Apple Silicon. The CB numbers for M1 were estimates, look here:

For GB5 so far only @Det0x has submitted any results which makes it hard to realize if the methodology works in general.
 

BorisTheBlade82

Senior member
May 1, 2020
381
543
106
So, regarding the nature of the GB5 workloads there is some documentation from Geekbench which can be found here:
  • Some of the explanations are not totally clear and leave some room for speculation.
  • The SQLite workload seems to be the only one which has no fixed processing amount but instead measures throughput in a fixed amount of time.
  • When only measuring the duration, the weighting for the score does not apply. So for example AVX512 supporting CPUs should have an advantage. Generally, a CPU that excels in a bigger workload should have an advantage over another CPU which excels in a smaller one.
What do you think? I guess, we first need more samples in order to judge if the methodology makes sense for GB5.
Another possibility would be to parse the results from the website - but that ATM exceeds my programming skills, to be honest. But hey, as this is open source, feel free to contribute. The GitHub repo can be found in the opening post.
 

igor_kavinski

Diamond Member
Jul 27, 2020
7,598
4,394
106
Dell Optiplex 3000 Core i5-12500

CBR23

Stock
1673106582339.png
Core memory isolation On
1673107001592.png
HT off Core memory isolation On
1673108348629.png
HT off Core memory isolation off
1673108415881.png


 

igor_kavinski

Diamond Member
Jul 27, 2020
7,598
4,394
106
Dell Optiplex 3000 Core i5-12500

Geekbench 5

Stock
1673108603820.png
Core memory isolation On
1673108700518.png
HT off Core memory isolation On
1673108751463.png
HT off Core memory isolation off
1673108814172.png

Windows build 22621.931

Looks like GB5 loves Alder Lake or ADL is very efficient when running GB5.

RAM is 8GB DDR4-3200 at 2T

1673109047919.png
 
  • Like
Reactions: lightmanek

BorisTheBlade82

Senior member
May 1, 2020
381
543
106
  • Updated Rankings and Matrices in the opening posts
  • included the results of @igor_kavinski 's mobile and Desktop Alder Lake (very strong showing of the mobile SKU in CB23 ST)
  • some more results for GB5 now available - for the moment I consider GB5 integration Beta
  • minor update to v0.8.1 - hopefully improved the LibreOffice sheet. Excel still working like a charm.
    Download v0.8.1
This is how the GB5 ranking looks right now - more contribution highly appreciated.
 
  • Like
Reactions: lightmanek

ASK THE COMMUNITY