Sunday, February 26th 2023
Intel to Go Ahead with "Meteor Lake" 6P+16E Processor on the Desktop Platform?
Late last year, it was reported that Intel is skipping its upcoming "Meteor Lake" microarchitecture for the desktop platform, giving it a mobile-platform debut in late-2023, with "Arrow Lake" following on in 2024, which would address both platforms. In the interim, Intel was expected to release a "Raptor Lake Refresh" architecture for desktop in 2023. It turns out now, that both the "Raptor Lake Refresh" and "Meteor Lake" architectures are coming to desktop—we just don't know when.
Apparently, Intel will brazen it out against AMD with a maximum CPU core-count of just 6 performance cores and 16 efficiency cores possible for "Meteor Lake." It's just that both the P-cores and a E-cores get an IPC uplift with "Meteor Lake." The processor features up to six "Redwood Cove" P-cores with an IPC uplift over the current "Raptor Cove" cores; and introduce the new "Crestmont" E-cores. A lot will depend on the IPC uplift of the latter. Leaf_hobby, a reliable source with Intel leaks on social media, has some interesting details on the I/O capabilities of "Meteor Lake" on the desktop platform.
Apparently, "Meteor Lake-S" (the desktop variant), comes with a PCI-Express host interface of 20 PCIe Gen 5 lanes, and 12 PCIe Gen 4 lanes from the processor. This works out to a PCI-Express 5.0 x16 PEG interface, one PCI-Express 5.0 x4 interface for the first CPU-attached NVMe SSD, one PCI-Express 4.0 x4 for a second CPU-attached NVMe SSD; and 8 PCI-Express 4.0 lanes toward the DMI chipset bus.
The companion Z890 chipset, the top desktop motherboard chipset option for "Meteor Lake-S," comes with an all-Gen 4 PCIe interface. It puts out 24 PCIe Gen 4 downstream lanes. With this platform, Intel could standardize Wi-Fi 7 (IEEE 802.11be), a new wireless networking standard with a theoretical maximum bandwidth of over 40 Gbps.
Lastly, there's the question of platform. "Meteor Lake-S" is unlikely to be supported on the current LGA1700 platform, and Intel is expected to debut the new Socket LGA1851 for "Meteor Lake-S" and its succeeding "Arrow Lake." The new socket could maintain cooler-compatibility with LGA1700, though.
Source:
leaf_hobby
Apparently, Intel will brazen it out against AMD with a maximum CPU core-count of just 6 performance cores and 16 efficiency cores possible for "Meteor Lake." It's just that both the P-cores and a E-cores get an IPC uplift with "Meteor Lake." The processor features up to six "Redwood Cove" P-cores with an IPC uplift over the current "Raptor Cove" cores; and introduce the new "Crestmont" E-cores. A lot will depend on the IPC uplift of the latter. Leaf_hobby, a reliable source with Intel leaks on social media, has some interesting details on the I/O capabilities of "Meteor Lake" on the desktop platform.
The companion Z890 chipset, the top desktop motherboard chipset option for "Meteor Lake-S," comes with an all-Gen 4 PCIe interface. It puts out 24 PCIe Gen 4 downstream lanes. With this platform, Intel could standardize Wi-Fi 7 (IEEE 802.11be), a new wireless networking standard with a theoretical maximum bandwidth of over 40 Gbps.
Lastly, there's the question of platform. "Meteor Lake-S" is unlikely to be supported on the current LGA1700 platform, and Intel is expected to debut the new Socket LGA1851 for "Meteor Lake-S" and its succeeding "Arrow Lake." The new socket could maintain cooler-compatibility with LGA1700, though.
128 Comments on Intel to Go Ahead with "Meteor Lake" 6P+16E Processor on the Desktop Platform?
I would treat this as a 6 core CPU
Now we are back to 2017 where 8700k just came out ?
Also, that's a big-ass SOC tile (yes, different process but still). Better be something valuable in there, hopefully a new IMCRaptor Cove already is an IPC brute, but clearly there's something else keeping it from performing better in games, whether it's IMC not running in Gear 1 or not enough L3 or whatever.
I mean they already do a 6 core variant with no e-cores, I just wish they would do the same with 8 p-cores and bring the cost down, or keep cost the same if they do what I say above there.
that would be the best gaming chip on the planet, and should stay cold too, since no extra heat from the ecores.
The e-cores can be great, but not fucking 16 of them o_O
i don't want ANY E-Cores in my DESKTOP CPU. they make sense for devices running off a battery but they are completely useless in a normal PC.
give me 16 P Cores, downclock them to keep heat and power consumption tame enough for the average user and let me overclock it back to it's limit with a high end cooler.
But 16 e-cores!? What am I (or anyone) supposed to do with that? Servers will probably eat up this increased reliance on e-cores, it seems like it's the only response Intel has to massive epyc/threadripper core counts, but for client? It just doesn't compute for me
What I don't like are,
1. Intel pitched these E-cores as being efficient. They are for sure, but what is the point of 16 E-cores? Efficient or just an excuse to bump performance on the cheap?
2. Intel is effectively selling cheap E-cores at higher prices. Think Raptor Lake, and you can see Intel basically justifying a higher price tag for a bunch of E-cores. Whereas you are getting 16 cutting edge cores from AMD. Again not to say E-cores are worthless, but one is paying a lot for what should have been some Celeron/ Pentium Silver class processors.
I am using an i7 Alder Lake now and a Comet Lake before, and I am not impressed with Raptor Lake. And it seems like Intel is doubling down this path of spamming E-cores while keeping cutting edge and expensive P-cores low in number. Considering that AMD previously patented some P and E core CPU design, I guess it may be a matter of time AMD may eventually go down this path.
It wouldn't be as bad if they didn't keep switching sockets every 2nd gen...
1 P-core takes roughly as much space as 4 E-cores, and the E-cores would perform better in pure multi-threaded scenarios.
Given a choice between 10P + 0E cores or 6P +16E cores, there's a very good case to be made for 6+16 config. Games will see negligible impact with 2 fewer P-cores, and multi-threaded apps that can actually use 6+ cores, will see a massive boost because of the extra performance that comes with additional E-cores.
The caveat to all this is that the 6P+16E part can't be a 14900, it must be a 14600-class part, and be priced as such.
Change the socket to LGA1700 just because it's 6P max, and cancel the 800 boards? I don't think it's that easy for a lot of reasons.
Suddently, LGA1851 only works with only one CPU generation (Arrow) instead of two.
Telling board makers to shelve development? Nope.
Think about it, if Meteor had at least 8P it would surprise absolutely no one that it required a new board. (Despite millions of shocked/bitter/dramatic comments about having to change board.)