screenshot-2022.07.03-09_54_341656856474336.jpg

Intel's 13th-Gen Raptor Lake processors will bring more cores, more connectivity, a revamped core architecture, support for PCIe 5.0 SSDs, and possibly even a rumored 6.0 GHz peak boost clock to bear. And that's not to mention any potential IPC improvements. These chips will arrive this year to square off with AMD's Zen 4 Ryzen 7000 processors, setting the stage for a fierce battle for desktop PC supremacy — particularly for the crown of the best CPU for gaming as the Intel vs AMD rivalry enters a new stage.

Intel's Alder Lake brought the company back from what had been a slow erosion of its leadership position in our CPU benchmarks rankings as AMD relentlessly iterated on its Ryzen processor lineup. AMD's continuous string of innovations eventually culminated in an embarrassing loss of the performance crown for Intel as the Ryzen 5000 processors outclassed Intel's chips in every performance, price, and power metric that mattered back in 2020, capping Intel's decline from grace after incessant delays moving to its oft-delayed and seemingly doomed 10nm process node.

Alder Lake righted the ship. These chips brought the best of Intel's newly re-worked 10nm process, now re-named 'Intel 7,' enabling higher clock rates and lower power consumption, paving the way for Raptor Lake. Intel will etch the Raptor Lake processors on a refined version of that same process node and pair it with its newly-revamped x86 hybrid architecture, a design that combines a mix of larger high-performance cores paired with smaller high-efficiency cores.

Like its predecessor, Raptor Lake will also support disruptive new features like PCIe 5.0 and DDR5 but preserves DDR4 support for less-expensive build options. Raptor Lake will also drop right into existing motherboards to offer an upgrade path for Alder Lake users, but there will be new 700-series motherboards at launch. Intel is also introducing more CPU overclock features, too.

Even though Raptor Lake is clearly on the cusp of coming to market this year — we've even seen chips sold at auction and benchmarks in the wild — Intel has been uncharacteristically silent about its pending line of chips for desktop PCs. In fact, the company has said more about its next-next-gen Meteor Lake chips than it has about Raptor Lake. That hasn't stopped us from gathering all of the information we know from official and unofficial sources into this article. We'll update the article as we learn more, but here's what we know so far.

INTEL 13TH-GEN ROCKET LAKE SERIES AT A GLANCE

• Codename Raptor Lake
• Launches in Q4 2022 (October)
• Up to 24 cores and 32 threads on 'Intel 7' process node
• Up to 8 Raptor Cove Performance cores (P-Cores) and 16 Gracemont Efficiency cores (E-Cores)
• Rumored 5.8 GHz boost
• Up to 36MB of L3 Cache (20% increase), up to 32MB L2 (2.3x increase)
• Dual-Channel DDR4-3200 and DDR5-5600 memory support, x16 PCIe 5.0 and x4 PCIe 4.0 interface, Thunderbolt 4 / USB 4
• Support for PCIe 5.0 M.2 SSDs
• Desktop 65W to 125W TDP, scales to mobile as well
• "Up to double-digit performance boost"
• No word of IPC gain, though it is expected
• Socket LGA 1700, Raptor Lake backward compatible with existing coolers
• Mobile chips are BGA compatible with existing chips
• 700-Series Chipset: Z790, H770, B760 Motherboards
• Chipset: Up to 20 PCH PCIe 4.0 and eight PCIe 3.0
• Enhanced CPU overclocking features, including per-core and Efficient Thermal Velocity Boost
• Support for AI M.2 Module
• Intel's Thread Director is a hardware-based technology that assures threads are assigned to either the P or E cores in an optimized manner

INTEL 13TH-GEN ROCKET LAKE RELEASE DATE WINDOW

Intel hasn't given an official launch date for Raptor Lake yet, but all signs point to a Q4 2022 launch. Our own sources tell us that we'll see an announcement in late September, but the launch will land in mid-to-late October. Naturally, this is early information and subject to change — vendors often push back timelines — but the chips and the requisite motherboards are said to be currently scheduled to launch in that timeframe.

Above, we can see Intel's demo of a working Raptor Lake processor in February. In fact, several common CPU utilities already have Raptor Lake support baked in, a typical development we see as chips come to market. If that isn't convincing enough, there's even been an engineering sample of the flagship Core i9-13900K auctioned online, meaning near-final silicon is already in the wild.

INTEL 13TH-GEN ROCKET LAKE SPECIFICATIONS AND FEATURES

screenshot-2022.07.03-10_00_161656856816591.jpg

Official information about Raptor Lake is thin on the ground, with the slide above reflecting Intel's most comprehensive listing of features thus far. The company touts up to 24 cores and 32 threads on the 'Intel 7' process that will deliver an 'up to double-digit performance boost,' enhanced overclocking features, support for an AI M.2 module, and that the chips are compatible with Alder Lake. That isn't much to work with, but luckily we already know a few chip configurations from leaked benchmark results.

The Raptor Lake chips will have Performance Cores (P-Cores) with a new microarchitecture, rumored to be named Raptor Cove, designed to handle single- and lightly-threaded tasks, like gaming and productivity workloads. The Efficiency Cores (E-Cores) also bear signs of a revamped microarchitecture, but these cores are still rumored to have the Gracemont design. These cores step in for heavily-threaded workloads, background tasks, and multi-tasking.

screenshot-2022.07.03-10_01_431656856903881.jpg

Above, we can see the Core i9, i7, and i5 flagships from Intel's previous-gen family, along with what we know about the new Core i9-13900K model from the various leaks and information we've collected. Intel will only release Core i9, i7, i5, and i3 models for Raptor Lake, while Pentium and Celeron will be served by refreshed previous-gen Alder Lake chips (Intel took a similar approach with its 11th-Gen Rocket Lake processors).

Above, we can see that the Core i9-13900K comes with a total of 24 cores, with eight P-Cores and 16 E-Cores, representing an additional eight E-Cores over the previous-gen flagship (but the same number of P-Cores). These additional E-Cores come from a new larger 8+16 die (8 P-Core + 16 E-Core) that Intel will use for the Core i9, i7, and i5 chips only. This larger die comes with additional cache capacity for the cores (more on that in the architecture section), but Core i3 and below will have the same amount of cache as found with the existing Alder Lake models.

We know the flagship gets eight more E-Cores, but we aren't sure how Intel will increase the number of cores for the Raptor Lake Core i7 and i5 models — the former might see an increase to eight E-Cores, but we have no concrete indication of that yet. Intel might also change its Core i5 E-Core strategy. The current K-series Core i5, the Core i5-12600K, comes with four E-Cores while the rest of the non-K Core i5 models, like the Core i5-12400, don't have E-Cores. Intel could add E-cores to the non-K Core i5 Raptor Lake chips, and it could also increase the number of E-Cores on the K-series Core i5-13600K model to maintain the differentiation within the Core i5 family.

We don't have any concrete clock speed information on the Raptor Lake SKUs yet, as the benchmarks we've seen of Engineering Samples (ES) chips aren't representative of the final clock speeds. These chips go through different revisions, like ES1, ES2, and so on, and the rumor mill points to up to 5.5 GHz with the ES3 version of the Core i9-13900K — but bear in mind that these are not the final clock speeds. However, this represents a marked increase over the rumored 4.5 GHz boost with ES1 silicon.

As a reminder, Intel has redefined its power terminology to have a 'Processor Boost Power' (PBP) value representing the guaranteed base performance level (PL1). This replaces TDP. CPU-Z entries show the Core i9-13900K with a 125W PBP, along with screenshots for a 65W variant with the same 8+16 core counts that is likely the 65W Core i9-13900. Intel also lists a 'Maximum Turbo Power' (MTP) specification that quantifies the power consumption during Turbo Boost (PL2). This is rumored to remain at 241W for the Core i9-13900K. By assigning the same peak PBP for the Core i9, it's fair to assume that the Core i7, i5, and i3 ranges will have similar power limits as the Alder Lake processors. That means we'll see 125W, 65W, and 35W versions for desktop PCs and sub-45W for the mobile chips.

screenshot-2022.07.03-10_03_271656857007220.jpg

Intel has confirmed that the Alder Lake chips will drop into the LGA 1700 socket, meaning they are backward compatible with the existing 600-series chipsets, and older coolers are also forward compatible with the new Raptor Lake motherboards. In addition, the 16 PCIe 5.0 PCIe lanes coming off the CPU can now be split into dual x8 arrangements, thus enabling support for PCIe 5.0 M.2 SSDs. We'll dive much deeper into this topic in the motherboard section.

The Raptor Lake chips support DDR4-3200, just like the previous-gen chips, and are currently qualified for DDR5-5200, which is faster than the DDR5-4800 with previous-gen chips. However, we're told that Intel is working on getting DDR5-5600 qualified in time for launch, so memory data transfer rates aren't final. As before, Raptor Lake will have a dual-channel memory interface. Intel will also carry over ECC memory support for its consumer-class W-series motherboards.

We will still also see a complicated DDR5 memory support matrix that sees speeds decline if the motherboard has more than one DIMM slot per channel (SPC), if you populate more than 1 DIMM per channel (DPC) on boards that have two SPC, or based on varying DIMM ranks. However, you can now expect increased speed with each type of configuration. Non-K and Core i3 chips will also have slower supported peak speeds than the K-series chips.

As evidenced by Intel's own statements, Raptor Lake will continue to have a heavy focus on CPU overclock features. Tantalizing unofficial details recently emerged via an update to Intel's own eXtreme Tuning Utility (XTU). Intel has added support for 'future platforms' to leverage added support for per-core and package-level Thermal Velocity Boost (TVB) tech, which allows the processor to boost higher than the base specification if the chip is under a certain temperature threshold. Intel also added support for a new type of TVB, called 'Efficiency TVB.' We've also heard rumblings of a 6 GHz clock rate for a Core i9-13900KS, the successor to the Core i9-12900KS, enabled by this new boost. Take this with a grain of salt, as it is based on a single claim.

The Raptor Lake iGPU is said to be based on the same Xe-LP Gen 12.2 architecture found with Alder Lake. But besides some early benchmarks that were clearly from an early engineering sample and not indicative of final performance, we haven't heard more about the integrated graphics engine. We don't expect any meaningful changes.

Intel has also teased a new AI accelerator that will slot into an M.2 slot. It's hard to tell what practical purpose this would serve for most uses, though some edge use-cases might benefit. Intel hasn't shared any more information about this product, and there hasn't been any other information, so we'll have to wait to learn more.

INTEL 13TH-GEN ROCKET LAKE ARCHITECTURE

screenshot-2022.07.03-10_05_301656857130236.jpg

Intel hasn't shared the names of the chip microarchitectures that it will etch onto the Intel 7 node for the Raptor Lake CPUs, but rumors indicate the P-Cores will use 'Raptor Cove' naming while the E-Cores will stick with Gracemont. However, both cores do have significantly more L2 cache, suggesting a re-working of the underlying designs. We caution that we can't find any indication of the 'Raptor Cove' codename being real, so take that particular naming with a pinch of salt.

One thing is for sure: Intel has significantly re-worked the cache hierarchies of both types of cores, so we should expect new code names. The Rocket Lake chip will now share up to 36 MB of L3 cache, representing an increase of 6MB over the previous generation. However, this simply represents the addition of two more 3MB L3 cache clusters and not an increase in per-core cache capacity.

screenshot-2022.07.03-10_08_261656857306978.jpg

As you can see in the image of the Alder Lake die above, the hybrid architecture pairs a 3MB slice of L3 cache (labeled as LLC) next to each 'block' of cores. The P-cores, in dark blue, each have an L3 slice nearby, while the E-cores, in light blue, come in quad-core clusters that also have a 3MB slice of L3 cache nearby. These slices of cache are shared among all cores.

The new Raptor Lake 8+ 16 die (covered in the previous section) comes with 16 E-Cores. Those additional E-Cores would equate to the above Alder Lake die being stretched to accommodate two more light blue quad-core clusters of E-Cores. Those two clusters would come with two more 3MB L3 cache slices, bringing the total capacity to the 36MB we see with the Core i9-13900K.

Interestingly, Alder Lake's cache scheme introduced a new way for Intel to disable cache for lower core count SKUs. In the past, to create lower-end SKUs with fewer cores, Intel disabled entire slices of L3 cache (the LLC blocks in the image) in lockstep with any cores it disabled. With Alder Lake, Intel transitioned to not disabling any entire slice of L3, instead merely disabling some banks in each slice, thus reducing per-slice capacity (from 3MB to 2MB, for instance). This makes plenty of sense as it keeps stops on the ring bus active, and it also allows for creating SKUs with higher cache capacity than we would typically expect based on the number of disabled cores.

As such, we can't simply guess the amount of L3 cache per Raptor Lake chip based on the core count alone. Instead, we'll have to wait to see more detailed information. For now, we simply have confirmation that the Core i9-13900K and Core i9-13900 will come with 36MB of total L3 cache. However, Intel's new L3 cache policy leaves room for cache capacity improvements on all SKUs that leverage the 8+16 die.

Intel has increased per-core L2 cache capacity for both the P-Cores and the E-Cores. The E-Cores see an increase to 2MB of private L2 cache per core, a 60% increase over the 1.25 MB per core found in Alder Lake. Intel also boosted the amount of L2 cache shared among each quad-core cluster of E-Cores to 4 MB, a doubling over the 2MB with Alder Lake. That means we'll see up to 32MB of L2 cache. As we've seen with Intel's previous chips that got a big increase in L2 capacity, this type of improvement tends to result in better performance in multi-threaded workloads, but it is possible that it could result in higher IPC in some workloads due to keeping the cores fed with more data. It should also help free the ring from some traffic that would otherwise be present for shuffling around L3 data, thus allowing greater scalability.

The L1 cache for both types of cores remains the same (L1i$ 32kB, L1D$ 48Kb for P-Cores — L1i$ 64kB, L2D$ 32kB for E-Cores).

A leaked roadmap listed a new feature, a Digital Linear Voltage Regulator (D-LVR), alongside the Raptor Lake chips. According to an Intel patent, this feature helps reduce the CPU VID and power consumed by the cores, possibly reducing power consumption by up to 25% in some cases. Naturally, given that it is in a pitched battle for performance supremacy in the desktop PC space, we would expect Intel to use the headroom afforded from those power savings to deliver yet more effective power to the cores. We aren't sure of this tech's role in the Raptor Lake chips yet, or how effective it will be (if present). We aren't sure if this will be used for the desktop PC or mobile chips, or both, but it could be part of Intel's recipe to improve Raptor Lake's performance-per-watt.

Raptor Lake's E-Cores still do not support AVX-512, so we expect that Intel will keep the feature disabled, which is odd given that AMD's Ryzen 7000 will fully support the extensions. As before, AVX2 and VNNI remain enabled for the E-Cores. We have much more to learn about the Raptor Lake design, but details are still scarce. We'll update this section as we learn more.

INTEL 13TH-GEN ROCKET LAKE 700-SERIES MOTHERBOARDS, Z790, H770, B760, H610

The Raptor Lake chips will use the same LGA1700 socket as Alder Lake, meaning they have the same socket and pinout, and both Raptor and Alder will be compatible with both the 600- and 700-series motherboards, providing quite a bit of flexibility for both generations. However, if you use a Raptor Lake chip on a 600-series motherboard, you'll lose the improvements in PCH PCIe lane configurations that we'll outline below. All LGA1700 coolers are compatible, so you won't need a new CPU cooler for Raptor Lake. Naturally, existing 600-series boards will require an update to support Raptor Lake.

Raptor Lake brings a significant number of big steps forward in connectivity. The previous-gen Alder Lake chips support 16 PCIe 5.0 lanes for a discrete GPU and four PCIe 4.0 lanes from the CPU for an M.2 SSD. Those same lanes are still present on Raptor Lake, but a new connection scheme allows for expanded functionality.

For Raptor Lake, motherboard vendors can now split the 16 PCIe 5.0 PCIe lanes from the CPU into dual x8 arrangements, thus enabling support for PCIe 5.0 M.2 SSDs. This does mean that the connection to the discrete GPU will be split into a x8 connection (a switch could be used here), but the existing PCIe 4.0 link from the CPU for an M.2 SSD will also remain active, providing a total of three M.2 SSD ports that hang directly off the CPU.

screenshot-2022.07.03-10_10_241656857424516.jpg

Intel itself leaked the 700-series chipset changes. The x8 DMI 4.0 connection between the CPU and the chipset (PCH) remains present, but the chipset also has improvements. In the past, the PCH supported up to 16 PCIe 3.0 lanes and up to 12 PCIe 4.0 lanes, but Intel has increased the number of PCIe 4.0 lanes to 20 and reduced the number of PCIe 3.0 lanes to eight, thus expanding connectivity. Intel also increased the number of USB 3.2 Gen 2x2 (20G) connections from a peak of four to five.

screenshot-2022.07.03-10_11_361656857496165.jpg

All other PCH connectivity options found with the Alder Lake motherboards remain unchanged with the Raptor Lake chipset itself. However, we will see somewhat different allocations with the Z790, H770, and B760 motherboards based on the new features. You can see Intel's accidentally-released breakdown, which we've independently confirmed, above. The highlighted regions list the changes (Z690 = Z790, H670 = H770, B660 = B760).

INTEL 13TH-GEN ROCKET LAKE GAMING BENCHMARKS AND IPC

Intel demoed Raptor Lake at its Investor Day 2022 using a chip with eight P-Cores and 16 E-Cores, so it was a flagship Core i9 model. The demo of a Blender and After Effects workload didn't give us any performance data to work with. Instead, it merely showed the cores were in good working order and that the chip supports minimizing background tasks to running on the E-Cores only, thus providing more performance for foreground tasks that run on the P-Cores. Aside from the company's vague claims of 'up to double-digit performance boost,' we don't know much about Raptor Lake's performance.

Luckily, we've seen plenty of leaked benchmarks that give us a better idea of what Raptor Lake will look like. Just remember to take these with a grain of salt, as the clock speeds and feature set are not final with the Engineering Samples (ES) chips we've seen in the wild thus far.

The first Raptor Lake benchmark to emerge came from the Crossmark database, but it was later deleted. The benchmark showed 49.3% more performance for a previous-gen chip, indicating this was the rawest of ES silicon. A similarly-unimpressive Raptor Lake benchmark result also appeared in the Ashes of the Singularity benchmark database. Luckily, more expansive benchmarks have emerged since.

We've seen Raptor Lake continue to perform better as new benchmarks are posted, with a 24-core 32-thread Core i9 model showing a 20% improvement in threaded work over the current-gen Core i9-12900K flagship in the UserBenchmark database.

screenshot-2022.07.03-10_14_281656857668524.jpg

screenshot-2022.07.03-10_15_261656857726222.jpg

We tend to see early benchmarks emerge in the SiSoft database, but the outfit took that one step further and wrote up a full report on a test submission for the Core i9-13900, showing that the chip boasted up to 33% more performance in integer and 100% more performance in floating-point work than its Alder Lake predecessor. However, in vectorized work, the chip only beat Rocket Lake by 4 to 6%, with the latter holding the lead due to its support for AVX-512.

screenshot-2022.07.03-10_21_591656858119616.jpg

These test results came from an anonymous submission to the SiSoft database, so again, these are assuredly not representative of final silicon: According to the specifications the outlet provided that you can see in the above table, the Raptor Lake chip was limited to a 3.7 GHz all-core boost for P-Cores and a 2.76 GHz all-core for the E-Cores, while the Core i9-12900 comparison chip ran at 5.0 / 3.8 GHz, respectively.

screenshot-2022.07.03-10_24_361656858276367.jpg

screenshot-2022.07.03-10_25_341656858334431.jpg

The best Raptor Lake performance benchmarks that we've seen come from a full review posted by EXP Review. The outlet compared an ES Core i9-13900 to a Core i9-12900K locked to the same frequencies, thus providing a great measuring stick for general performance trends. However, remember that this is still not final silicon, and the chip was tested on a motherboard that isn't optimized for the Raptor Lake silicon yet.

screenshot-2022.07.03-10_26_531656858413761.jpg

The outlet performed a wide range of tests, with the big takeaway being that the Raptor Lake model was roughly 20% faster in non-gaming multi-threaded work than the Core i9-12900K, which is quite the achievement but hardly unexpected given that the Raptor chip has eight more E-Cores than the 12900K.

More impressively, the Raptor Lake chip took a 12% lead in single-threaded applications, suggesting we'll see a significant IPC performance increase that will extend Intel's lead further over the Ryzen 5000 chips and possibly keep the lead when AMD's Zen 4 comes to market.

The outlet also ran gaming benchmarks, but the difference between the two chips fell within the margin of error. This is hardly surprising because games are more sensitive to poor latency of any sort, like unrefined memory support or motherboard BIOSes, than other types of applications. As such, we wouldn't take the gaming results too seriously until we see final silicon emerge. However, given the plethora of benchmark leaks we've seen recently, we probably won't have to wait much longer.

INTEL ROCKET LAKE THREAD DIRECTOR

screenshot-2022.07.03-10_28_351656858515700.jpg

Alder Lake pioneered the hybrid era for x86 desktop PCs, and Intel's Thread Director, which ensures that threads are placed on the correct cores, is the magic that glues the design together. It's likely that Raptor Lake will come with improvements to the Thread Director technology, a result of what Intel says is an upgradeable and tunable design that will improve over time.

Just like we saw with Alder, Raptor Lake will use both faster and slower cores that are optimized for different voltage/frequency profiles. As such, unlocking the maximum performance and efficiency requires the operating system and applications to have an awareness of the chip topology to ensure workloads (threads) land in the correct core based on the type of application.

That's where Intel's Thread Director technology comes in. This hardware-based technology provides enhanced telemetry data to Windows 11 to assure that threads are scheduled to either the P or E cores in an optimized and intelligent manner, but in a way that's transparent to software.

This technology works by feeding the Windows 11 operating system with low-level telemetry data collected from within the processor itself, thus informing the scheduler about the state of the core, be it power, thermal, or otherwise. Alder Lake chips will also work fine with a bog-standard Windows 10 operating system – existing thread-scheduling techniques continue to work with the processors, just not as well. While the chips work, you'll miss out on the enhanced capabilities of Thread Director (that's Windows 11 only), which will have a varying impact on performance and power consumption based on instruction type and application usage models. In other words, your mileage will vary.

INTEL 13TH-GEN ROCKET LAKE PRICING

Intel hasn't released any pricing information yet, but the company has already taken a no-holds-barred bare-knuckle approach to pricing with Alder Lake as it looks to steal back market share from AMD, and we can expect that to continue. We expect that Intel will still charge quite the premium for its Core i9 models, but the Core i7 and Core i5 models should have exceptionally competitive pricing, just as we see now. Overall, we expect very similar pricing tiers to form, with the K-series Core i9 models peaking at $589, Core i7 K's at $409, and Core i5 K's at $289, but Intel hasn't confirmed pricing yet.

In the end, much of the difference in pricing between Intel's Raptor Lake and AMD's Ryzen 7000 will boil down to platform costs. We can expect some of the same trends that we saw with Alder Lake motherboards: DDR5-supporting boards will carry a premium over their DDR4 counterparts due to the more expensive manufacturing techniques and materials required to support the faster interface. However, the option for DDR4 motherboards will be a significant advantage over competing Ryzen 7000 platforms, which are DDR5-only. We do expect DDR5 pricing to recede significantly by the time both of these platforms are on the market, but while the pricing differences will become smaller over time, DDR5 will remain more expensive than DDR4, regardless of supply.

However, AMD's AM5 motherboard product stack will include provisions for PCIe 4.0-only motherboards, another way to save on cost, while Intel's lineup won't have that option. That will provide two tiers of motherboard pricing for AMD, too, but costs will be adjusted on a different axis. It will certainly be interesting to see which approach offers the biggest pricing deltas between the full-fledged implementations.

In either case, we expect that both Intel and AMD will be exceptionally competitive on chip pricing as Raptor Lake comes to market, which is good for everyone.