Tuesday, September 27th 2022

Intel 13th Gen Core "Raptor Lake" Desktop Processors Launched: +15% ST, +41% MT Uplift

Intel today launched its 13th Gen Core "Raptor Lake" desktop processors, and companion 700-series motherboard chipset. These processors are built in the same LGA1700 package as the previous generation "Alder Lake," and are backwards-compatible with 600-series chipset motherboards through a BIOS update. Likewise, 700-series chipset motherboards support older "Alder Lake" processors. With the new 13th Gen Core, Intel is broadly promising an up to 15% uplift in single-threaded performance, which has a bigger bearing on gaming performance; and an up to 41% multi-threaded performance uplift; over the previous-generation, when comparing the top Core i9-13900K with its predecessor, the i9-12900K. Intel also claims to have outclassed the AMD Ryzen 9 5950X in multi-threaded performance, and the Ryzen 7 5800X3D in gaming performance.

Intel's performance claims are backed by some impressive hardware changes despite the company sticking with the same Intel 7 (10 nm Enhanced SuperFin) foundry node as "Alder Lake." To begin with, the single-thread performance uplift comes from the new "Raptor Cove" performance-core, which promises an IPC uplift over the previous-generation "Golden Cove," comes with more dedicated L2 cache of 2 MB per core (compared to 1.25 MB per core in the previous-generation); and significantly higher clock-speeds, going all the way up to 5.80 GHz. "Raptor Lake" has up to 8 P-cores, but the company has put in a lot of work in improving the contribution of E-cores to the processor's overall multi-threaded performance uplift. This is achieved by doubling the E-core count to 16. These are the same "Gracemont" E-cores as previous-generation, but Intel has doubled the L2 cache that's shared in a 4-core Gracemont cluster, from 2 MB per cluster to 4 MB. There are upgrades to even the hardware prefetchers of these cores.
Intel didn't go into the nuts and bolts of what makes up the "Raptor Cove" P-core, but broadly explained that it comes with improved speed paths that enable an up to 600 MHz P-core boost frequency uplift at comparable power to the previous-gen "Golden Cove" while staying on the same process. The Intel 7 node also seems to have got some technological improvements, with the company referring to it as the "3rd generation" of this node (optical 10 nm). This mainly concerns better electrical characteristics from improved channel mobility. Cushioning the P-core with a larger 2 MB dedicated L2 cache also appears to be contributing to the iso-power uplift, as the core spends fewer cycles fetching data from the L3 cache. We will learn more about "Raptor Cove" in the coming days, and will hopefully have a more detailed look at the new core in our reviews of these processors.
The E-core microarchitecture is the very same "Gracemont," but benefits from the node improvements to dial up E-core boost frequencies all the way up to 4.30 GHz. The cores also benefit from the larger 4 MB L2 cache that's shared among four E-cores in a "Gracemont" cluster. "Raptor Lake" has four such clusters, amounting to 16 on the silicon. The E-core clusters have access to the chip's L3 cache, just like the P-cores. As we mentioned earlier, the improved cache, and updated prefetcher algorithm should have an cumulative impact on E-core performance; and when you account for 16 of these, besides the improved 8 P-cores, you begin to see where Intel's 41% generational multi-threaded performance uplift claim is coming from.
Intel also made updates to the processor's uncore components. The L3 cache that's shared among the processor's P-cores and E-core clusters, is now enlarged to 36 MB, from 30 MB in the previous generation. This cache is a continuously addressable block due to the Ringbus interconnect making ring-stops at various physical segments of the cache. Intel has improved the clock-speed of this fabric, which now boosts up to 5.00 GHz, or 900 MHz higher than the previous-gen.

The DDR5+DDR4 memory controllers also receive an update. The processor now natively supports up to DDR5-5600 JEDEC-standard memory speeds, when using 1 DIMM per 80-bit channel (which has two 40-bit sub-channels); or up to DDR5-4400 when using 2 DIMMs per channel (i.e. populating all four memory slots on your motherboard).

Intel also updated the Thread Director middleware that gives the software some degree of awareness of the Hybrid architecture, and attempts to ensure that the right kind of workload is allocated to the right kind of CPU core. Intel has given TD greater thread class awareness through machine-learning techniques (the processor learns over time what the nature of the workload could be). The processor also takes advantage of new scheduling features of Windows 11 22H2 Update, which introduce PID QoS for system background tasks and user-initiated background tasks.
Intel claims that "Raptor Lake" processors will be memory overclocking monsters, capable of speeds as high as DDR5-10000, when pushed to the limit with enthusiast-grade memory. For the P-cores, the company says that 8.00 GHz overclocks are now within reach for enthusiasts. The updated Intel Extreme Tuner Utility (XTU), allows you to set multipliers on a per-core basis, and tune your memory frequency on-the-fly (no reboots involved).
Intel is launching the 13th Gen Core "Raptor Lake" desktop processor family with essentially three processor models—Core i9-13900K, Core i7-13700K, and Core i5-13600K; and their "KF" sub-variants that have disabled iGPUs, and are about $10-20 cheaper, depending on the model.

The Core i9-13900K is the flagship part, with 8 P-cores, and 16 E-cores (8P+16E), with the full 36 MB L3 cache available on the silicon. The P-cores have a base-frequency of 3.00 GHz, and boost up to 5.80 GHz; whereas the E-cores run at 2.20 GHz base, boosting up to 4.30 GHz. The processor base power is rated at 125 W, and the maximum turbo power at 253 W (up from 241 W for the i9-12900K). The i9-13900K comes with an MSRP of USD $589, while the i9-13900KF (which lacks the iGPU), is priced at $564.

The Core i7-13700K is an interesting SKU, as it has the same 8P+8E core-configuration as the previous-gen i9-12900K, but with all the new updates detailed above. Intel carved this SKU out by disabling two of the four E-core clusters on the "Raptor Lake" silicon, and reducing the L3 cache to 30 MB. The P-cores have a base frequency of 3.40 GHz, with a maximum boost frequency of 5.40 GHz; while the E-cores run at 2.50 GHz base, and 4.20 GHz maximum boost. These chips have the same 125 W PBP and 253 W MTP as the i9-13900K. The i7-13700K is priced at $409, and the i7-13700KF at $389.

The Core i5-13600K is an equally interesting processor with which the company hopes to hold on to the mid-range. It now comes with a 6P+8E core-configuration, compared to 6P+4E of the i5-12600K. And of course, you get all the generational improvements detailed above. This SKU is carved out by disabling two P-cores, and two E-core clusters; while also cutting down the L3 cache to 24 MB (which is still higher than the 20 MB of the i5-12600K). The P-cores run at 3.50 GHz base with 5.10 GHz boost; while the E-cores do 2.60 GHz base, with 3.90 GHz boost. While the PBP value is the same 125 W as the higher SKUs, the MTP is reduced to 181 W. Intel is pricing the Core i5-13600K at $319, and the i5-13600KF at $294.
Intel is claiming gaming performance uplifts of up to 18% when comparing the i9-13900K with the previous-gen i9-12900K, across a wide selection of games; while the comparison with the AMD Ryzen 9 5950X "Zen 3" sees gaming performance gains range between 6% to 58%. The gap only widens when you consider the 99th percentile low-water-mark analysis. Although mainly compared with the 5950X, Intel also threw in gaming performance values it tested on the Ryzen 7 5800X3D, which is shown matching the i9-13900K in games where it's beating the i9-12900K, or within 10% of it in games where the i9-13900K gets ahead. This is interesting, as Intel thinks the performance of "Zen 4" Ryzen 7000-series processors should roughly match that of the 5800X3D. In our performance reviews published on September 26, the 5800X3D is 4.5-5% behind the Ryzen 7 7700X, which means "Zen 4" should end up within 5% of the i9-13900K in gaming performance, should these numbers for the 5800X3D from Intel hold up.
The platform I/O of these processors is identical to that of "Alder Lake." You get a 2-channel (4 sub-channel) DDR5 + 2-channel DDR4 memory interface. The processor puts out 28 PCI-Express lanes; 16 of these are Gen 5, and intended for the main x16 PEG slot; while the remaining are Gen 4. The main x4 NVMe interface of the processor is Gen 4, while the DMI chipset bus takes up the remaining 8 lanes (DMI 4.0 x8). You should still find motherboards with Gen 5 M.2 NVMe slots, but these would be eating into the x16 PEG bandwidth. Given that NVIDIA's latest GeForce Ada continues to be PCIe Gen 4, cutting into the bandwidth of the PEG slot to run Gen 5 M.2 SSDs could affect graphics performance (but we'll test this theory in upcoming PCIe-scaling articles with the RTX 4090).

The complete slide-deck for the processor launch event follows.
Add your own comment

224 Comments on Intel 13th Gen Core "Raptor Lake" Desktop Processors Launched: +15% ST, +41% MT Uplift

#52
mahoney
john_The probable reason why Intel decided to NOT put a standard bar for 5800X3D in it's slides, but "hide" the X3D's results in a small red line.


Find it hilarious how intel included the 3d chip while AMD didn't even bother with it for their Zen 4 presentation.
Posted on Reply
#53
mplayerMuPDF
i5-13600k is looking sooo good. People hate on the E-cores but don't forget that you are basically getting TWO old i5s (supposedly Skylake but let's say for the sake of the argument that they are Broadwell or Haswell equivalent instead) for free with your new hexacore i5 (think of it as a Ryzen 5). For productivity tasks this is just amazing. When I finally get to buy one of these (probably many years later second hand), I will be super excited to do some reencoding and compiling on this thing. Furthermore, DDR4 is STILL supported, so I could reuse my "old" 2x8 GB DDR4-3200 and save some money on that.
Posted on Reply
#54
Super Firm Tofu
TheinsanegamerNGuys, I can tell you that THIS ISSUE has not affected ME specifically and as we all know anecdotes are fact so there is NO ISSUE so stop complaining!
Can you please share what you've experienced? I asked above for specific problems and got 'blah blah blah, cpu design, old software somethingsomethingsomething'.

I never claimed there wasn't a problem. I said that in almost a year I haven't run into anything. Please share what was broken for you with E-cores. I'd like to attempt to duplicate it.
Posted on Reply
#55
tussinman
CallandorWoTWell what are the problems with e-cores at the moment and will it affect me in gaming?
From my understanding it's mostly really old games. From everything i've heard/read 2 common complaints is 1. the e-cores simply won't be utilized (which isn't technically a good or bad thing it just means you won't get any extra benefit) or 2. on some ancient games I've heard complaints of the e-cores running the game instead of the P cores (which I don't think technically matters to be honest, a game that's 10+ years old should be a joke to run anyways).
Posted on Reply
#56
KarymidoN
AMD just lost all their leverage and advantage with ZEN4/AM5.
Platform cost = Intel (supports z690/z790 boards and DDR4/DDR5 RAM)
Temps and Price/Performance = ZEN4 struggled to beat 12th GEN in some cases, 13th gen gonna wipe the floor with ZEN4.
Boy they gonna have to rush ZEN4+ or ZEN5 ASAP cause its not looking good.
Posted on Reply
#57
P4-630
tussinman(which I don't think technically matters to be honest, a game that's 10+ years old should be a joke to run anyways).
Just remember already 8 year old GTA V.
Posted on Reply
#58
AnotherReader
Raptor Lake looks like it'll retake the gaming crown, but Zen 4 will provide stiff competition. We should all be glad that Intel and AMD are keeping each other on their toes. Note that Intel uses specint for measuring the single threaded and multithreaded speedup over Alder Lake. AnandTech ran specint in their review as is their wont. The 7950X was 15% faster than the 12900k in the single threaded test and 41% faster in the multithreaded test. So it seems that Raptor Lake will match or surpass Zen 4 in almost all applications.

SpecInt Rate (from Anandtech): multithreaded test

Test7950X12900kIncrease over 12900K
500.perlbench_r[RIGHT]134.6[/RIGHT][RIGHT]103.82[/RIGHT][RIGHT]29.6%[/RIGHT]
502.gcc_r[RIGHT]89.6[/RIGHT][RIGHT]79.13[/RIGHT][RIGHT]13.2%[/RIGHT]
505.mcf_r[RIGHT]55.8[/RIGHT][RIGHT]52.1[/RIGHT][RIGHT]7.1%[/RIGHT]
520.omentpp_r[RIGHT]43.8[/RIGHT][RIGHT]39.05[/RIGHT][RIGHT]12.2%[/RIGHT]
523.xalancbmk_r[RIGHT]99.9[/RIGHT][RIGHT]63.94[/RIGHT][RIGHT]56.2%[/RIGHT]
525.x264_r[RIGHT]273.8[/RIGHT][RIGHT]176.02[/RIGHT][RIGHT]55.6%[/RIGHT]
531.deepsjeng_r[RIGHT]144.4[/RIGHT][RIGHT]90.31[/RIGHT][RIGHT]59.9%[/RIGHT]
541.leela_r[RIGHT]163.6[/RIGHT][RIGHT]95.18[/RIGHT][RIGHT]71.9%[/RIGHT]
548.exchange2_r[RIGHT]234.9[/RIGHT][RIGHT]140.71[/RIGHT][RIGHT]66.9%[/RIGHT]
557.xz_r[RIGHT]77.8[/RIGHT][RIGHT]50.4[/RIGHT][RIGHT]54.4%[/RIGHT]
GEOMEAN[RIGHT]113.28[/RIGHT][RIGHT]80.53[/RIGHT][RIGHT]40.7%[/RIGHT]


SpecInt Rate-1 (from Anandtech): single threaded test

Test7950X12900kIncrease over 12900K
500.perlbench_r[RIGHT]10.1[/RIGHT][RIGHT]9.7[/RIGHT][RIGHT]4.1%[/RIGHT]
502.gcc_r[RIGHT]11.8[/RIGHT][RIGHT]11.7[/RIGHT][RIGHT]0.9%[/RIGHT]
505.mcf_r[RIGHT]9.6[/RIGHT][RIGHT]7.7[/RIGHT][RIGHT]24.7%[/RIGHT]
520.omentpp_r[RIGHT]7[/RIGHT][RIGHT]6.1[/RIGHT][RIGHT]14.8%[/RIGHT]
523.xalancbmk_r[RIGHT]8.3[/RIGHT][RIGHT]7.7[/RIGHT][RIGHT]7.8%[/RIGHT]
525.x264_r[RIGHT]14.9[/RIGHT][RIGHT]13.7[/RIGHT][RIGHT]8.8%[/RIGHT]
531.deepsjeng_r[RIGHT]7.3[/RIGHT][RIGHT]6.4[/RIGHT][RIGHT]14.1%[/RIGHT]
541.leela_r[RIGHT]7.5[/RIGHT][RIGHT]6.1[/RIGHT][RIGHT]23.0%[/RIGHT]
548.exchange2_r[RIGHT]15.4[/RIGHT][RIGHT]12.2[/RIGHT][RIGHT]26.2%[/RIGHT]
557.xz_r[RIGHT]6.4[/RIGHT][RIGHT]4.8[/RIGHT][RIGHT]33.3%[/RIGHT]
GEOMEAN[RIGHT]9.39[/RIGHT][RIGHT]8.15[/RIGHT][RIGHT]15.3%[/RIGHT]
Posted on Reply
#59
RandallFlagg
R0H1TI wouldn't be so sure of that, chiplets still yield better & AMD's making them on smaller/denser nodes. The profit margins on the R9 chips are insane! Intel on the other hand lost slightly more (less?) than a billion for the first time in many years.

If AMD really wanted they could price Intel out of the market completely, but just like Intel in the previous decade they won't do that. I'll let you guess why.
The number you are talking about is Net Income available to stock holders. For Intel, it's that negative number in this list, Trailing 12 months (19.1B) then last quarter and so on.



For AMD this line looks like :


I should point out, Intel increased capital expenditures by $10B vs 2020. This is mostly to start up their IDM foundries and improve their nodes - expenses AMD does not (directly) incur.

Now that you know the facts, how certain are you that you have a point?
Posted on Reply
#60
Why_Me
IllIIIlFor intel, Pre-sale has started in my region and my location is shipping on October 20th.
After currency conversion vs msrp
13900k is $690(590),
13700k is $492(410),
13600k is $380(320).

For amd, after currency conversion vs msrp,
7950x is $775(700),
7900x is $605(550),
7700x is $422(400),
7600x is $317(300)

Relative to amd's msrp, I don't know if it's intel being confident or they just want to make a fortune in my area
This is what a lot of gamers will be waiting for.

Intel Core i5 13400F + B660 / B670 board + DDR4 3600

www.pcgamer.com/intels-core-i5-13400-is-shaping-up-to-be-a-killer-budget-gaming-chip/
Posted on Reply
#61
tussinman
P4-630Just remember already 8 year old GTA V.
I only played the single player but even then my old ivybridge (which is slower than the e-cores) had no issues getting the full 75hz at the time. The only "ecore only" video I found for GTA 5 was averaging 100FPS on very high settings using only the 12600K's E-cores.
Posted on Reply
#62
P4-630
tussinmanThe only "ecore only" video I found for GTA 5 was averaging 100FPS on very high settings using only the 12600K's E-cores.
Forced in BIOS?

Can't find this video...
Posted on Reply
#63
Space Lynx
Astronaut
tussinmanFrom my understanding it's mostly really old games. From everything i've heard/read 2 common complaints is 1. the e-cores simply won't be utilized (which isn't technically a good or bad thing it just means you won't get any extra benefit) or 2. on some ancient games I've heard complaints of the e-cores running the game instead of the P cores (which I don't think technically matters to be honest, a game that's 10+ years old should be a joke to run anyways).
It does matter on super old games though, because I will be running those old games at 1440p 240hz someday, and I want the extra smoothness of highest frames possible, and I don't want e-cores holding me back.
Posted on Reply
#64
zlobby
CallandorWoTI agree with Der8auer that the Zen 4 chips have a thick heatsink over the ICC, its too thick according to him, and Intel has actually done some neat tricks regarding that in recent launches.
Yeah, like bending! :D

But yeah, apart from that I can't wait to see how much power these new 13-series CPU draw and dissipate.

Pricing is quite sus, IMO. If intel were so confidwnt that they will beat AMD across the board, then why did they priced their offerings so low?
Posted on Reply
#65
RedBear
The Intel 7 node also seems to have got some technological improvements, with the company referring to it as the "3rd generation" of this node (optical 10 nm).
Intel 7+++? Raptor Lake might turn out to be very good, especially in terms of value because of cheaper previous generation motherboards and DDR4 compatibility (*look at Ryzen 7000*), but I really hope for Intel that Intel 7 won't turn out to be the new 14nm...
Posted on Reply
#66
Wirko
btarunrIntel has given TD greater thread class awareness through machine-learning techniques (the processor learns over time what the nature of the workload could be). The
Now try to get a stable benchmarking score with this thing.
Posted on Reply
#68
tussinman
P4-630Forced in BIOS?

Can't find this video...
He used process lasso which can force whatever application you choose to use only the cores/threads that you manually select. He couldn't do bios option because the Bios requires you to have at least 1 P-core activated (you can deactivate all the e-cores in bios but can't deactivate all the p-cores)

He did the "ecore only" just to be funny but technically you can use the process lasso app to only run p-cores if you're having some sort of DRM or performance issue with older games
Posted on Reply
#69
AnotherReader
john_I don't think you are right here. TSMC doesn't build chips for free. They get payed for those and in last years they had done some price hikes themselves affecting their customers. AMD is probably paying a high price for those chiplets. On the other hand Intel is taking money from one pocket and puts it in the other by building it's CPUs at it's own fabs. And they have so many models out there and so many customers and OEMs, that probably they are salvaging almost everything faulty they build. Probalem in iGPU? No problem. It's an F model. Problem in E core cluster? No problem. We just rename it. Problem in a P core? No problem again.
TSMC's latest nodes are very expensive, but AMD's small dies mean that they have low costs. Assuming that TSMC'S N6 costs the same as N7 and applying the 10% increase in 2022 to the prices in 2020, we get a manufacturing cost of US $ 68.21 for the 7950X and $ 45.28 for the 7700X. This doesn't account for packaging and R&D costs. The costs without the 10% increase, assuming a defect density of 0.09 per square cm for both N6 and N5, are below:

NodeWafer CostGood diesDie Cost
N6[RIGHT]9346[/RIGHT][RIGHT]460[/RIGHT][RIGHT]20.32[/RIGHT]
N5[RIGHT]16988[/RIGHT][RIGHT]815[/RIGHT][RIGHT]20.84[/RIGHT]
Posted on Reply
#70
Wirko
If the die annotations are exact, the size of an E-core is 32% of that of a P-core. Same as Alder Lake or close. So if anyone is trying to compare performance per unit area, don't simply round it to 1/4.
john_And they have so many models out there and so many customers and OEMs, that probably they are salvaging almost everything faulty they build.
AMD collects the dies with one, two or three good cores but flawless L3, then assembles them into Epyc F-series processors, which are a special kind of monsters for low-threaded loads.
Posted on Reply
#71
RandallFlagg
AnotherReaderRaptor Lake looks like it'll retake the gaming crown, but Zen 4 will provide stiff competition.
[RIGHT][/RIGHT]
Read the review, with a reasonable config of DDR5-6000 Intel never lost the gaming crown.

And it's not an anomaly. Look at sites that used similar memory configs and you see similar results. See wccftech's review, or eurogamer's.
Posted on Reply
#72
truehighroller1
ARF6 GHz KS SKU coming Q1 2023:

Why does he look so sick?
Posted on Reply
#73
THU31
Pretty surprising pricing. Even though I still do not care about E-cores whatsoever, there is much more value here compared to Zen 4.

If the 13400(F) comes out under $200 with 6+4 cores and slightly higher boost clocks, it will be insanely good.
Posted on Reply
#74
mplayerMuPDF
truehighroller1Why does he look so sick?
LOL "6 GHz OUT OF THE BOX!!!" in limited volumes and only if you wait another 6 months
Posted on Reply
#75
AnotherReader
RandallFlaggRead the review, with a reasonable config of DDR5-6000 Intel never lost the gaming crown.

And it's not an anomaly. Look at sites that used similar memory configs and you see similar results. See wccftech's review, or eurogamer's.
You're right. Most reviews show the 12900k as leading the 7950X in gaming; at best, it may be a match for the 12900k, but I haven't seen one beating it.
Posted on Reply
Add your own comment
Nov 24th, 2024 05:04 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts