CPU Tests: SPEC MT Performance - P and E-Core Scaling

Update Nov 6th:

We’ve finished our MT breakdown for the platform, investigating the various combination of cores and memory configurations for Alder Lake and the i9-12900K. We're posting the detailed scores for the DDR5 results, following up the aggregate results for DDR4 as well.

The results here solely cover the i9-12900K and various combinations of MT performance, such as 8 E-cores, 8 P-cores with 1T as well as 2T, and the full 24T 8P2T+8E scenario. The results here were done on Linux due to easier way to set affinities to the various cores, and they’re not completely comparable to the WSL results on the previous page, however should be within small margins of error for most tests.

SPECint2017 Rate-N Estimated Scores (i9-12900K Scaling)

In the integer suite, the E-cores are quite powerful, reaching scores of around 50% of the 8P2T results, or more.

Many of the more core-bound workloads appear to very much enjoy just having more cores added to the suite, and these are also the workloads that have the largest gains in terms of gaining performance when we add 8 E-cores on top of the 8P2T results.

Workloads that are more cache-heavy, or rely on memory bandwidth, both shared resources on the chip, don’t scale too well at the top-end of things when adding the 8 E-cores. Most surprising to me was the 502.gcc_r result which barely saw any improvement with the added 8 E-cores.

More memory-bound workloads such as 520.omnetpp or 505.mcf are not surprising to see them not scale with the added E-cores – mcf even seeing a performance regression as the added cores mean more memory contention on the L3 and memory controllers.

SPECfp2017 Rate-N Estimated Scores (i9-12900K Scaling)

In the FP suite, the E-cores more clearly showcase a lower % of performance relative to the P-cores, and this makes sense given their design. Only few more compute-bound tests, such as 508.namd, 511.povray, or 538.imagick see larger contributions of the E-cores when they’re added in on top of the P-cores.

The FP suite also has a lot more memory-hungry workload. When it comes to DRAM bandwidth, having either E-cores or P-cores doesn’t matter much for the workload, as it’s the memory which is bottlenecked. Here, the E-cores are able to achieve extremely large performance figures compared to the P-cores. 503.bwaves and 519.lbm for example are pure DRAM bandwidth limited, and using the E-cores in MT scenarios allows for similar performance to the P-cores, however at only 35-40W package power, versus 110-125W for the P-cores result set.

Some of these workloads also see regressions in performance when adding in more cores or threads, as it just means more memory traffic contention on the chip, such as seen in the 8P2T+8E, 8P2T regressions over the 8P1T results.

SPEC2017 Rate-N Estimated Total (i9-2900K Scaling)

What’s most interesting here is the scaling of performance and the attribution between the P-cores and the E-cores. Focusing on the DDR5 set, the 8 E-cores are able to provide around 52-55% of the performance of 8 P-cores without SMT, and 47-51% of the P-cores with SMT. At first glance this could be argued that the 8P+8E setup can be somewhat similar to a 12P setup in MT performance, however the combined performance of both clusters only raises the MT scores by respectively 25% in the integer suite, and 5% in the FP suite, as we are hitting near package power limits with just 8P2T, and there’s diminishing returns on performance given the shared L3. What the E-cores do seem to allow the system is to allows to reduce every-day average power usage and increase the efficiency of the socket, as less P-cores need to be active at any one time.

CPU Tests: SPEC MT Performance - DDR5 Advantage CPU Benchmark Performance: E-Core
Comments Locked


View All Comments

  • ajollylife - Sunday, November 7, 2021 - link

    I agree. I've got a 3995wx everything on qvl, even with an optane drive. Got too annoyed with the bugs and found a 5950x worked better for a high performance desktop. Going to swap to a 12900k once i can find parts.
  • TheJian - Sunday, November 7, 2021 - link

    If you know how to use mem timings, you idiots that depend on SPD's wouldn't have these problems (that covers about 90% of this crap, and knowing other bios settings solves almost anything else besides REAL failures). I've been building systems for decades (and owned a PC biz for 8yrs myself) and a MB's QVL list was barely used by anyone I know (perhaps to look up some ODD part but otherwise...Just not enough covered at launch etc). If I waited for my fav stuff to be included in each list I'd never build. Just buy top parts and you don't worry much about this crap.

    That said, if my job was on the line, I'd check the list, but not because I was worried about ever being wrong...LOL. I just don't have a liars face. I'd be laughing about how stupid I think it is after so many builds and seeing so many "incompatible memory" fixed in seconds in the hands of someone not afraid to disable the SPD and get to work (or hook up with a strap before blowing gigs of modules, nics repeatedly etc). Even mixing modules means nothing then (again, maybe if I was pitching servers...DUH....1 error can be millions) after just trying to make issues exists with mixing/matching but with timings CORRECT. No, they will work, if set correct barring some REAL electrical issue (like a PSU model from brand X frying a particular model mboard - say dozens in a weekend, a few myself!).

    Too many DIY people out that that really have no business building a PC. No idea what ESD is (no just because it took a hit and still works doesn't mean it isn't damaged), A+ what?? Training? Pfft, it's just some screws and slots...Whatever...Said the guy with machine after machine that have never quite worked right...LOL. If you live in SF or some wet joint OK (leo leporte etc? still around), otherwise, just buy a dell/hp and call it a day. They exist because most of you are incapable of doing the job correctly, or god forbid troubleshooting ANYTHING that doesn't just WORK OOB.
  • Qasar - Sunday, November 7, 2021 - link

    blah blah blah blah blah
  • Midland_Dog - Saturday, November 27, 2021 - link

    people like you cost amd sales
    silly amdumb
  • cyberpunx_r_ded - Friday, November 5, 2021 - link

    sounds like a Mobo problem, not a CPU problem....for someone who has put together "hundreds of systems" you should know that by the symptoms.

    That motherboard is known to be dog sh1t btw.
  • DominionSeraph - Saturday, November 6, 2021 - link

    Note Intel doesn't allow "dog sh1t motherboards" to happen, especially at the $300+ price point. That makes it an AMD issue.
    I can refurb Dell after Dell after Dell after Dell, all of them on low-end chipsets and still on the release BIOS, and they all work fabulously.
    Meanwhile two years into x570 and AMD is still working on getting USB working right.

    I think I'll put this thing on the market and see if I can recoup the better part of an i9 12900k build. I may have to drop down to one of the i7 6700's or the i7 4770k system I have until they're in stock, but that's really no issue.
  • Netmsm - Saturday, November 6, 2021 - link

    It's a pleasure to not have p*gheaded amateurs in the AMD zone.
    Others are telling you it's not AMD issue but you spamming it's AMD, AMD, AMD... having got the wrong and of the stick.
  • Wrs - Saturday, November 6, 2021 - link

    @Netmsm Regardless of whether the blame lies with ASRock for the above issue, it remains a fact that AMD didn't fix a USB connectivity problem in Zen 3 until 6-7 months after initial availability. Partly that was because the installed base of guinea pigs was constricted by limited product, but it goes to show that quick and widespread product rollouts have a better chance of ironing out the kinks. (Source if you've been under a rock heh https://www.anandtech.com/show/16554/amd-set-to-ro...

    And then recently we had Windows 11 performance regressions with Zen 3 cache and sandboxed security. These user experience hiccups suggest one company perceptibly lags the other in platform support. It's just something I've noticed switching between Intel and AMD. I might think this all to be normal were I loyal to one platform.
  • Netmsm - Sunday, November 7, 2021 - link

    I didn't realize we're here to discuss minor issues/incompatibilities of the Intel's rival. I thought we're here to talk about major inefficiencies besides improvements of Intel's new architecture. Sorry!
  • Wrs - Sunday, November 7, 2021 - link

    @Netmsm That's no minor issue/incompatibility. Maybe for you, but a USB dropout is not trivial! Think missing keystrokes, stuttering audio for USB headsets and capture cards. It didn't affect every user, and was intermittent, which was part of the difficulty. I put off a Ryzen 5000 purchase for 2 months waiting for them to fix it. (I also put it off for 4 months before that because of lack of stock lol.)

Log in

Don't have an account? Sign up now