Intel P-Core Versus E-Core The Great Divide
We covered the P-core versus E-core aspect of Intel Xeon 6 thoroughly in our Intel Xeon 6 6700E Sierra Forest Shatters Xeon Expectations piece. It is important since Intel has a different strategy for its cloud-native CPU line than AMD. Intel is going head-to-head with Arm chips like AmpereOne with its E-cores and at the same time going head-to-head with AMD EPYC Turin with its P-core line. Here is our discussion from the Sierra Forest launch:
The reason this is, by far, the biggest change to Xeon in decades is that it is the first time we will really have two different core architectures in the mainstream sockets. Intel’s observation (albeit it is far from the first to arrive here) is that there is a set of compute that runs 24×7 at near 100% utilization. Those Performance cores, or P-cores, are designed to deliver the maximum performance per thread. If you have per-core licensed software, HPC applications, big, expensive AI servers, and so forth, you want P-core CPUs. The Efficient Cores or E-cores are designed for this huge body of workloads that needs to exist but are better suited to chasing power efficiency for cost savings rather than maximum performance.
Here is Intel’s shot at which workloads are best suited to P-cores versus E-cores. This is generally pretty good, but virtualization should have a big note on it. A target market for this is cloud CSPs with 2-8 vCPU customer instances that they want to deliver at a lower cost. If your idea of virtualization is VMware or Microsoft Windows Server with core and per socket style licensing, then you would rightly look to P-cores and will miss out on the benefits of E-cores from an efficiency standpoint.
When we say E-core, there are architectural differences. While both have a lot of similar features, AVX-512 and AMX are not present on the E-cores. The P-cores are loaded with acceleration technology.
Here is a bit more on the cores. At this point, let us simply look at the codenames. The P-core Redwood Cove is the Meteor Lake generation P-core on the desktop side. The E-core “Crestmont” is the Meteor Lake generation E-core. Of course, that is a bit of an oversimplification, but as Intel launches Lunar Lake, we want to keep folks grounded on where the new chips fall compared to their desktop counterparts.
There may be folks that hear E-core and think Atom. That is correct that those are the lineage of the E-core designs. In 2012, for example, we reviewed the all E-core Supermicro X7SPA-HF-D525 with the Atom D525 then the 2013 Intel Atom S1260. 2013 also saw Avoton/ Rangely. In 2017, we reviewed the Atom C3000 series. We have been reviewing the Snow Ridge and Alder Lake-N parts more recently. Still, the theme is that Intel has been increasing the performance per core on its E-cores at an almost absurd rate over the past few years. When we say E-core, instead of thinking about this like it is some super slow core, think of it more like an Intel Xeon E5 V4 core level of performance or a thread of 5th Gen Xeon Emerald Rapids.
Still, P-cores are far from done. We now get the Intel Xeon 6900P series with up to 128 cores, 12 memory channels, and the ability to use MCR DIMMs/ MRDIMMs. MRDIMMs/ MCRDIMMs will give this new chip bandwidth competitive with the Intel Xeon Max, but without requiring lower capacity HBM onboard. Also important is that the new P-core CPUs have twice the core count of the previous generation.
While the Intel Xeon 6900P series is the big socket P-core processor, 2025 will see the big socket Intel Xeon 6900E “Sierra Forest-AP” with up to 288 E-cores.
We will get the other models in Q1 2025, like the big socket E-core Sierra Forest-AP with 288 cores per socket and up to 86 P-cores in the smaller socket. There is also a Xeon 6 SoC or Granite Rapids-D on the roadmap for Q1. If this is confusing, here is what we can tell from Intel’s various slides in a single table.
Small socket is LGA4710 and big socket will likely be LGA7529.
If you want to see how much bigger the “big” chips are, here we can see the Xeon 6900 series Granite Rapids-AP, Sierra Forest-AP, and the upcoming Clearwater Forest-AP parts in the back with the Sierra Forest and Granite Rapids Xeon 6700 series in front.
Next, let us get to some of the Intel Xeon 6 platform features.
Wow can’t even hide Patrick’s love affair with Intel anymore can we ? Intel has not even properly launched this but yet it’s 128c Intel vs 96c Genoa, but AMD will have same 128c in 2 weeks time……just be honest finally and call it servingintel.com ;-)
Yawn… Still low on PCIe lanes for a server footprint when GPUs and NVME storage is coming fast and furious. Intel needs to be sold so someone can finally innovate.
Whether love or not, the numbers are looking good. For many an important question will be yield rates and pricing.
I wonder why Epyc is missing from the povray speed comparison.
One thing I’d like to see is a 4-core VM running Geekbench 6 while everything else is idle. After that Geekbench for an 8-core VM, 16-core, 32-core and so forth under similar circumstances. This sort of scaling analysis would help determine how well balanced the MCRDIMM memory subsystem is to the high-core-count processors–just the kind of investigative journalism needed right now.
As an asside, I had to work over eight captchas for this post.
The keyword would be availability. I checked just now, and these newer parts don’t have 1k Tray Pricing published yet. So not sure when would they be available. It felt painful to restrict the On-Premise Server procurement specification at 64 cores to get competitive bidding across vendors. Hope for the best.