Fantastic article -as always. Regarding the top-down analysis: I was a bit surprised to see that in ~1/5 of the cases the pipeline stalls b/c the pipeline is Frontend Bound. Can that be? Similarly, why is Frontend Bandwidth a subgroup of Frontend Bound? Shouldn't one micro-op be enough?
Intel's Lion Cove P-Core and Gaming Workloads
31–40 of 126 posts
Re: Intel's Lion Cove P-Core and Gaming Workloads
#32> E-Cores are turned off in the BIOS, because setting affinity to P-Cores caused massive stuttering in Call of Duty. I understand doing this for the purpose of specifically analyzing the P-core microarchitecture in isolation. However this does make the test less interesting for potential customers. I don't think many people would disable E-cores in BIOS if they bought this CPU, so for the purpose of deciding which CP…
I think many haven't yet grasped the future is heterogeneous computing, especially, when many desktops are actually laptops nowadays. Software working poorly in such setup means no effort was made to actually make it perform well in first place. Games requiring desktop cases looking like a rainbow aquarium with top everything will become a niche, in today's mobile computing world, and with diminishing sales and atten…
> Software working poorly in such setup means no effort was made to actually make it perform well in first place.
How do you optimize for a system architecture that doesn't exist yet?
(e.g. CoD could probably be fixed quite easily, but you can't do that before the hardware where that problem manifests even exists - I'd say it's much more likely that the problem is in the Windows scheduler though)
> Games requiring desktop cases looking like a rainbow aquarium with top everything will become a niche
PC gaming has been declared dead ever since the late 90s ;)
Re: Intel's Lion Cove P-Core and Gaming Workloads
#33Fantastic article -as always. Regarding the top-down analysis: I was a bit surprised to see that in ~1/5 of the cases the pipeline stalls b/c the pipeline is Frontend Bound. Can that be? Similarly, why is Frontend Bandwidth a subgroup of Frontend Bound? Shouldn't one micro-op be enough?
Take front end bound with a grain of salt. Frequently I find a backend backpressure reason for it, e.g. long-tail memory loads needed for a conditional branch or atomic. There are limitations to sampling methods and top down analysis, consider it a start point to understanding the potential bottlenecks, not the final word.
Re: Intel's Lion Cove P-Core and Gaming Workloads
#34I would like to understand more of the article, which book should I read?
Re: Intel's Lion Cove P-Core and Gaming Workloads
#35> E-Cores are turned off in the BIOS, because setting affinity to P-Cores caused massive stuttering in Call of Duty. I understand doing this for the purpose of specifically analyzing the P-core microarchitecture in isolation. However this does make the test less interesting for potential customers. I don't think many people would disable E-cores in BIOS if they bought this CPU, so for the purpose of deciding which CP…
Yeah intel either needs to ensure much better day 1 support for E / P core split or drop it entirely.
People see them as an active negative right now rather than how intel pitches them
Re: Intel's Lion Cove P-Core and Gaming Workloads
#36> E-Cores are turned off in the BIOS, because setting affinity to P-Cores caused massive stuttering in Call of Duty. I understand doing this for the purpose of specifically analyzing the P-core microarchitecture in isolation. However this does make the test less interesting for potential customers. I don't think many people would disable E-cores in BIOS if they bought this CPU, so for the purpose of deciding which CP…
Yeah intel either needs to ensure much better day 1 support for E / P core split or drop it entirely. People see them as an active negative right now rather than how intel pitches them
Is this a problem with Intel or with the OS scheduler? Haven't they had this kind of CPUs for a few years now, with this being touted as a reason to move from Win10 to 11?
Re: Intel's Lion Cove P-Core and Gaming Workloads
#37Earlier quoted context omitted.
I think many haven't yet grasped the future is heterogeneous computing, especially, when many desktops are actually laptops nowadays. Software working poorly in such setup means no effort was made to actually make it perform well in first place. Games requiring desktop cases looking like a rainbow aquarium with top everything will become a niche, in today's mobile computing world, and with diminishing sales and atten…
Which is funny because the pushback the PS3 got from developers was too much. Maybe it was "too heterogeneous" But I guess the future was already set.
That was very different, here the problem is the game's threads get scheduled on the weak E-cores and it doesn't like that for some reasons, with the PS3 that would have been impossible, SPEs had a different ISA, and didn't even have direct access to memory, the problem was developers had to write very different code for the SPEs to unlock most of the performance of the Cell.
Re: Intel's Lion Cove P-Core and Gaming Workloads
#38I suggests using a Xeon w7 2595X so that you have 26P cores and 0E cores
Re: Intel's Lion Cove P-Core and Gaming Workloads
#39Fantastic article -as always. Regarding the top-down analysis: I was a bit surprised to see that in ~1/5 of the cases the pipeline stalls b/c the pipeline is Frontend Bound. Can that be? Similarly, why is Frontend Bandwidth a subgroup of Frontend Bound? Shouldn't one micro-op be enough?
Take front end bound with a grain of salt. Frequently I find a backend backpressure reason for it, e.g. long-tail memory loads needed for a conditional branch or atomic. There are limitations to sampling methods and top down analysis, consider it a start point to understanding the potential bottlenecks, not the final word.
Interesting. You realize this by identifying the offending assembly instructions and then see that one operands comes from memory?
Re: Intel's Lion Cove P-Core and Gaming Workloads
#40> E-Cores are turned off in the BIOS, because setting affinity to P-Cores caused massive stuttering in Call of Duty. I understand doing this for the purpose of specifically analyzing the P-core microarchitecture in isolation. However this does make the test less interesting for potential customers. I don't think many people would disable E-cores in BIOS if they bought this CPU, so for the purpose of deciding which CP…
I think many haven't yet grasped the future is heterogeneous computing, especially, when many desktops are actually laptops nowadays. Software working poorly in such setup means no effort was made to actually make it perform well in first place. Games requiring desktop cases looking like a rainbow aquarium with top everything will become a niche, in today's mobile computing world, and with diminishing sales and atten…
There's a giant pile of software - decades worth of it, literally - which was already written and released, much of it now unmaintained and/or closed source, where the effort you cite is not a possibility.
By all means anything released in 2025 doesn't have that excuse - but I can't fault the authors of 15+ years old programs for not having a crystal ball and accounting for something which didn't exist at the time. Intel releasing something which behaves so poorly in that scenario is.... not really 100% fine in my eye. Maybe a big warning sticker on the box (performs poorly with pre-2024 software) would be justified. Thankfully workarounds exist.
P.S. At least I would have expected them to work more closely with OS vendors and ensure their schedulers mitigate the problem, but nope, doesn't look like they did.