News Posts matching #Nova Lake-S

Return to Keyword Browsing

Intel Razor Lake Gets a 12 P-Core bLLC Chip With No E-Cores, Per Leak

Intel's Razor Lake desktop lineup could include an unlocked gaming chip with 12 P-cores and no regular E-cores at all. Well-known Intel leaker Jaykihn shared the "12+0+4" configuration on X, which pairs those 12 P-cores with four low-power E-cores and Intel's big Last Level Cache (bLLC), the company's answer to AMD's X3D chips. In a follow-up post, he said this SKU replaces a locked 8+0+4 bLLC part that was rumored earlier. Apparently, all 12 P-cores sit on a single compute die designed only for P-cores, rather than a hybrid die with its E-cores switched off, and Jaykihn later said that tile is built on Intel's own 18A-P node. That would make it an outlier, since most Razor Lake compute tiles are reportedly headed to TSMC.

Jaykihn also claims the 125 W 6+12+4 bLLC chip, one of the two 22-core Nova Lake-S parts that leaked back in July, has been pushed from Nova Lake to Razor Lake. If that's accurate, it seems Nova Lake-S will launch with one less bLLC option than expected. There's no word on the 65 W version. Razor Lake-S is currently a 2028 product that should use the same LGA-1954 socket as Nova Lake-S, according to Jaykihn's earlier posts. Intel has listed Razor Lake model IDs in its ISA reference, but none of these specs are official. Plans this far out can change, so it's reasonable to treat the 12 P-core chip as just a target for now.

Intel Razor Lake-S Reportedly Due in 2028 on LGA-1954

Intel's Razor Lake desktop processors, the generation that follows Nova Lake-S, are currently slated for 2028, according to well-known Intel leaker Jaykihn. When asked on X whether Razor Lake-S was planned for 2027, Jaykihn replied "not currently," then followed up saying Razor Lake is a 2028 product for now. A leaked partner slide placed the first Nova Lake-S SKUs in Q1 2027 and indicated Intel plans to keep LGA-1954 for multiple generations, so Razor Lake-S should drop into the same boards roughly a year later. Apparently, Razor Lake will use new Griffin Cove P-cores, which Jaykihn previously called "an entire tock" rather than a refinement. The same core will reportedly also power Intel's next-generation Coral Rapids Xeon processors, though simultaneous multithreading (SMT) stays exclusive to Xeon.

Jaykihn says the client and server versions are separate architectures built around a similar core, comparing it to how Coyote Cove relates to Panther Cove. Earlier leaks pointed to Intel using TSMC's N2X node for some Razor Lake production, and the 12 Xe3P core iGPU SKU originally meant for Nova Lake-S was reportedly pushed to Razor Lake. HWiNFO also added support for Razor Lake-H, HX, and S in a recent beta. If the plan holds, Nova Lake-S buyers would get a proper CPU upgrade path without swapping motherboards, which is a welcome change after Intel went through three sockets in the last five years. Of course, timelines this far out can move, and Intel hasn't confirmed any of this, so it's reasonable to treat 2028 as a target for now.

Unreleased Radeon RX 7500 and Intel Razor Lake-H/HX/S Appear in Latest HWiNFO Beta

HWiNFO's newest beta, v8.55-6115, adds recognition for an AMD Radeon RX 7500, a graphics card AMD has not yet announced. The changelog entry is a single line with only the name, so the specs, the GPU underneath, and any launch plans are all unknown for now. The most likely candidate is probably the 6 nm "Navi 33" RDNA 3 chip, which already powers the 28 CU RX 7400 and the fully enabled 32 CU RX 7600. Of course, a card squeezed between those two would leave AMD very little room to work with, so the name is a bit puzzling. AMD hasn't said anything about the card so far, but we have heard the name before.

When the RX 7400 and RX 7300 first appeared in rumors back in 2024, there were rumblings of an RX 7500 XT desktop graphics card, though nothing concrete ever followed. Moving onto other additions to HWiNFO, the same build also adds enhanced support for Intel's Nova Lake-E and Razor Lake-H, HX, and S processors. Razor Lake is the platform expected to follow Nova Lake, and Intel has yet to officially announce it. CPUID added Razor Lake support to CPU-Z 3.02 earlier this week, while HWiNFO picked up preliminary Razor Lake-AX support back in August. With the first Nova Lake-S desktop chips not expected until Q1 2027, retail Razor Lake chips are probably still a long way out.

CPUID Readies CPU-Z for Intel Razor Lake, Two Generations Out

CPUID has released CPU-Z 3.02, and the first line of its changelog simply reads "Intel Razor Lake support." Razor Lake is the processor family expected to follow Nova Lake, and Intel has yet to officially announce it. The changelog doesn't say which Razor Lake variants are covered or how deep that support goes, so this could be anything from basic detection to early groundwork. The November 4 update also adds the AMD Radeon AI PRO R9700, along with fixes for an SPD reading issue on Intel Broadwell-E and a validation problem on Windows XP.

Of course, system tools tend to pick up new chips well before they reach store shelves. HWiNFO added early Nova Lake support back in August 2025, and the first Nova Lake-S desktop chips still aren't expected until Q1 2027. HWiNFO also added preliminary support for Razor Lake-AX in August this year, the rumored large APU that could pack up to 32 Xe3 GPU cores alongside on-package memory.

Intel Nova Lake-S CPUs Reportedly Drop to 5.1 GHz Max Above 90°C

Intel's upcoming Core Ultra 4000 "Nova Lake-S" desktop processors will reportedly cap their maximum core frequency at 5.1 GHz whenever they run above 90°C, according to Intel leaker Jaykihn on X. He says the limit applies to the entire Nova Lake-S desktop lineup, works separately from regular TjMax throttling at 100°C, and can't be raised. He also notes that the information is still preliminary. In practice, it looks like a safety net that sits between normal boost behavior and full thermal throttling. Below 90°C, the chips should presumably boost as usual, and models that don't exceed 5.1 GHz in the first place wouldn't be affected at all.

Final Nova Lake clocks aren't official yet, though the current Core Ultra 9 285K already boosts up to 5.7 GHz, so a high-end Nova Lake chip that runs hot could lose a sizable chunk of its peak frequency. A 100°C TjMax would also be lower than Arrow Lake's 105°C, which can be manually raised to 115°C on the 285K. That puts more weight on cooling, since the 28-core Core Ultra 9 4970K BFC was reportedly set to pull up to 296 W at PL2 despite its 125 W rating, and staying under 90°C at that kind of power draw will probably take a really capable cooler. Nova Lake-S is currently expected to arrive in Q1 2027, and Intel hasn't confirmed any of this yet.

Intel Nova Lake-S Promises Up To 17% Single-Thread and 20% Gaming Performance Improvements

A lot of information relating to Intel Nova Lake-S has emerged leading up to the official launch in early 2027, including official information from Intel detailing the Nova Lake architecture and a recent benchmark leak that promised significant single-thread performance improvements on a 28-core Nova Lake-S part. However, a recent leak out of @Haze2K1 on X, shared by VideoCardz, purports that the real-world performance improvements for Intel's Nova Lake desktop CPUs are in the double digit range.

While the leaker has been around for a while, there is no guarantee that this information is accurate, since the only cited source is "circulating chatter," however, the claim is that Intel's Nova Lake will outperform comparable last-generation Arrow Lake CPUs by 8-17% in raw single-thread performance, 15% in general-purpose workloads, and up to 20% in gaming. There is some nuance to these claims, with the 17% improvement figure exclusive to the higher-end CPUs that feature bLLC, while the 17% boost allegedly comes from the implementation of Intel's new Advanced Performance Extensions.

Intel "Nova Lake" Xeon E Series Carries Only P-Core or E-Core SKUs, No Hybrid Configurations

Intel is preparing to launch its upcoming "Nova Lake" processors in multiple versions, and the latest leaks highlight a particularly interesting Xeon E lineup. According to well-known leaker Jaykihn, Intel will be releasing its Xeon E-series based on "Nova Lake" silicon in two versions: big P-Core only or efficiency E-Core only SKUs. Reportedly, the P-Core only lineup will include five configurations with 4, 6, 8, 12, and 16 P-Cores. Meanwhile, the E-Core lineup will be slightly smaller, featuring four SKUs with 4, 8, 16, and 32 E-Core versions. At the top of the range, Intel Xeon E-series buyers can choose between a 16 P-Core design or a 32 E-Core configuration. There will be no hybrid SKUs with both P-Cores and E-Cores, as those will be reserved for the regular "Nova Lake-S" desktop processors.

Intel's new Xeon E designs will be powered by the W980 chipset platform. Motherboards with the W980 chipset will support native DDR5 memory with ECC, up to 48 PCIe lanes, including 12 PCIe 5.0 lanes directly from the chipset alongside 12 PCIe 4.0 lanes, and Intel vPro technology, along with numerous other optimizations typical of workstation chipsets. The DMI chipset bus bandwidth is set to 128 Gbps per direction, thanks to the implementation of DMI 5.0 x4, which is another great platform addition. It also offers two 40 Gbps USB4 or Thunderbolt 4 ports from the CPU. The PCI-Express 5.0 x16 PEG slot from the processor can be segmented into x8/x8 or other combinations using lane switches. Both CPU-attached M.2 NVMe slots can be configured as Gen 5.

Intel Core Ultra 4000 Naming Reportedly Extends to "Nova Lake-HX" Mobile Processors

Intel's "new" four-digit Core Ultra 4000 naming apparently isn't limited to desktop chips. Prominent leaker Jaykihn says on X that "Nova Lake-HX" laptop processors will use the same four-number format, while H-series and suffix-less mobile chips continue with the three-digit naming of the previous generation. The clarification follows a leaked list of seven "Nova Lake-S" desktop processors that showed names like Core Ultra 9 4970K BFC and Core Ultra 7 4870K BFC. In that list, the BFC suffix seems to mark the models with bLLC (big last-level cache). As for the mobile versions, HX chips have traditionally been BGA versions of Intel's desktop silicon, so it looks like Intel is grouping them with Nova Lake-S instead of the other laptop chips. Those would presumably fall under Core Ultra 400, although Jaykihn didn't name the series.

The HX claim isn't entirely new, either. When the Core Ultra 9 4950K surfaced in a CPU-Z leak in August, leaker Golden Pig Upgrade had already mentioned Core Ultra 4000HX naming for laptops. Jaykihn also seems to have cleared up one detail from the desktop list. Apparently, the non-BFC models keep their four LPE cores, even though the leaked table didn't show them for every SKU. We haven't seen any HX model names yet, and Intel hasn't confirmed the naming change. Nova Lake-S qualification samples are already showing up in HWiNFO, and reports point to an early 2027 launch. As if Nova Lake-S reusing Haswell's 4000-series numbering wasn't enough, laptop buyers will probably have to deal with two naming schemes in one generation.

Update Oct 17th: Leaker Jaykihn has now retracted part of that statement. Apparently, H-series and suffix-less Nova Lake Mobile CPUs also utilize the four-number "Ultra 4000" naming scheme.

Intel "Nova Lake-HX" and "Nova Lake-H" Die Shots Appear

Intel's upcoming "Nova Lake" lineup for mobile devices has been revealed in bare-die form, thanks to the Moore's Law Is Dead YouTube channel. Leading the lineup is the "Nova Lake-HX," featuring an 8+16+4 core configuration with 8 P-Cores, 16 E-Cores, and 4 LPE-Cores. The total silicon size measures 12x30 mm, amounting to 360 mm², which is divided across six different dies manufactured on various nodes. The first die is the graphics tile, built on the Intel 3-E node, embedding 4 Xe GPU cores and covering roughly 26 mm². Adjacent to it is a dummy die occupying 21 mm², used for the structural integrity of the package. Next, there is a large 72 mm² die built on the Intel 18A-P node, hosting 4 LPE-Cores and serving as a central hub. Beside it is another 18A-P silicon die that functions as a peripheral control tile, measuring 58 mm². Finally, Intel uses an external foundry for the main compute tile, which is on the TSMC N2P node and hosts the 8P+16E CPU core configuration. This compute tile occupies the largest area of 104 mm². Additionally, there is a passive tile next to it, with 85 mm² dedicated to the structural integrity of the package and the intended operation of the "Nova Lake-HX" chip.

Next, we move to the less powerful "Nova Lake-H" variant, which will feature a 4+8+4 configuration with 4 P-Cores, 8 E-Cores, and 4 LPE-Cores. This package is significantly smaller, measuring only 12x23 mm for a total die area of 276 mm², also consisting of both functional and dummy dies. The die configuration remains the same except for the main compute tile, which hosts a 4P+8E-core configuration on the TSMC N2P node, occupying 55 mm² of area. The adjacent passive die is also smaller, with an area of only 45 mm², while the peripheral control die, central hub die, and graphics tile are all made on Intel nodes and remain the same as in the "HX" variant.

GIGABYTE BIOS Update Points to New DDR4 Intel Processors Coming Next Year

GIGABYTE has released BIOS updates that prepare its entire Intel B760 and H610 motherboard lineup for upcoming LGA1700 processors, which the company says are "expected to launch in early 2027." As reported by Videocardz, the update covers DDR4 and DDR5 boards alike, so owners only need to flash the new firmware and drop in the new CPU once it arrives. GIGABYTE doesn't name the processors in its press release, and Intel has yet to announce anything new for the socket. However, the timing lines up what we've been reporting for months. Intel is said to be readying "Raptor Lake Next" chips for LGA1700 in 2027, based on the original Raptor Lake silicon.

That makes GIGABYTE's BIOS the closest thing to a confirmation of new DDR4-compatible Intel processors for 2027, and it comes before Intel has announced them. It looks like the firmware was rolling out quietly even before the press release. The B760 Gaming X AX, for example, received its F18 BIOS on September 29, with a changelog that lists a CPU microcode update and "preparation for upcoming processor support." GIGABYTE also claims to be the first vendor to cover every B760 and H610 model. The press release makes no mention of Z790, Z690, or B660 boards, and there's no word on whether those will follow.

Intel Reportedly Limits "Nova Lake DS" Samples, Rollout Starts in December

Intel is reportedly limiting access to some of its most interesting "Nova Lake" processors during the early development stages. According to leaker Jaykihn, chips with the internal "DS" designation are being distributed to a much smaller group of testers compared to the rest of the "Nova Lake" lineup. This "DS" designation reportedly includes parts built around two compute tiles, which are expected to be among the first to be released. These SKUs are currently known to carry the "BFC" suffix, which has appeared on several leaked Core Ultra 4000 desktop processors and is linked to Intel's larger big last-level cache (bLLC) implementation. For example, the leaked Core Ultra 9 4970K BFC is a 28-core processor combining eight P-cores, 16 E-cores, and four LPE cores.

The scarcity of BFC hardware in public leaks may be more related to Intel's sampling policy than to availability. The leaker claims these processors are being kept within a restricted testing group, preventing them from appearing through the standard qualification-sample pipeline that usually produces early benchmarks and hardware detections. This way, no public benchmark scores are surfacing, leaving us in complete dark before the official launch happens.
Intel Nova Lake

Intel Core Ultra 4000 "Nova Lake-S" Lineup Leaks With 28-Core 4970K BFC

A new leak by @laurentschoice lists seven desktop Nova Lake-S processors under what looks like Intel's new four-digit Core Ultra 4000 naming, led by a Core Ultra 9 4970K BFC. It apparently has 8 P-cores, 16 E-cores, and 4 LPE cores for 28 in total, plus bLLC (big last-level cache), a 125 W rating, and a 32 EU iGPU. That puts it above the Core Ultra 9 4950K, which first surfaced in a CPU-Z leak in August as a 28-core chip. This list shows the 4950K with 24 cores (8 P-cores and 16 E-cores), without LPE cores or bLLC.

The rest of the list follows a similar pattern. The Core Ultra 7 4870K BFC has 24 cores and bLLC, while the 4850K gets 20 cores without it. There is also a Core Ultra 9 4900 BFC with 22 cores, bLLC, and a 65 W rating. We currently don't know what BFC stands for, although the models carrying it appear to be the ones with bLLC, which Intel is introducing as its answer to AMD's 3D V-Cache. Intel hasn't confirmed any of these names, so they may well change before Nova Lake's official launch.

Intel "Nova Lake" Launch Nears as Platform Passes USB4 and PCIe 5.0 Compliance Testing

Intel's Core Ultra 400-series "Nova Lake" CPUs are reportedly nearing launch as Intel has successfully passed USB and PCIe compliance testing. This means the platform has officially passed testing with the two organizations, and all the advertised specifications are working correctly. Starting with the USB Implementers Forum (USB-IF), a governing body of the USB standard, there are two "Nova Lake-H" device IDs certified for compliance with USB4. These include devices with IDs D331 and D333. Additionally, USB-IF lists ID 6E6E for the "Nova Lake" PCH-S chipset for desktop motherboards, compliant with USB 3.2 Gen 2. Intel likely chose a desktop chipset and a laptop CPU to achieve Qualification by Similarity, where testing one product can earn certification for other products easily. To avoid revealing too much before the launch, Intel opted for this strategy instead of testing a full flagship desktop CPU.

For the PCI-SIG, a governing body for PCIe compliance, Intel's 900-series chipset has long been present with the IDs 6E38-6E3F, 6E30-6E35, and 6E40-6E47. These were added back in April, but in August, another set of entries for CPUs specifically appeared. Certifying the PCIe 5.0 x16 root complex were device IDs D461, D465, and D467-D46A, which are likely "Nova Lake-S" CPUs or some mobile variation. Regardless, the verification process is the final stage that a platform and the CPU usually go through before the launch is finalized.

Thermal Grizzly Launches Mycro Pro Stainless Steel Water Blocks With LGA1954 Support for Nova Lake-S CPUs

Thermal Grizzly has launched the Mycro Pro Stainless Steel CPU water blocks, which list support for Intel's upcoming LGA1954 socket. The AMD version covers AM4 and AM5, while the Intel version covers LGA1700, LGA1851, and LGA1954. Thermal Grizzly sells both at $116.88, and European listings show €99.90. LGA1954 is the socket for Intel's upcoming Nova Lake-S desktop CPUs, which Intel seems to have confirmed through an internal validation tool listing, and recent leaks point to a Q1 2027 launch. Cooler makers have been signaling compatibility for a while, with Thermaltake's leaked installation guide and Noctua's FAQ update both saying LGA1851 coolers should carry over. Since the socket is expected to keep the same mounting as LGA1851, this block looks like it follows suit.

As for the block itself, the main change from the existing Mycro Pro RGB line is the materials. These blocks use an unplated copper coldplate with 0.2 mm microfins (68 on AMD, 70 on Intel), a stainless steel housing, and an anodized aluminium mounting frame. Thermal Grizzly dropped the nickel plating, which it says can give a slight thermal edge and lowers production costs. The tradeoff is that the bare copper will probably discolor over time, and there is no RGB. Neither block is meant for direct-die use, and the Intel inlet is tuned for LGA1851 chips with the stock heat spreader. However, the key point remains that Intel's new LGA1954 socket is now appearing in official product listings.

Intel Z990 Motherboards Spotted In Shipping Records Ahead Of Nova Lake Launch

Some Z990 motherboards for Intel's upcoming Nova Lake platform have started showing up in shipping records, suggesting the launch is getting closer. Club386 spotted at least five boards with "Z990" in their names listed in customs data from Taiwan and Vietnam, dated July 2026.

Z990 is expected to be the flagship chipset for Nova Lake-S, Intel's next Core Ultra desktop lineup on the new LGA1954 socket. Intel is also prepping a cheaper Z970 chipset that keeps multiplier overclocking but offers a less diverse expansion suite overall. Also, these aren't the first Z990 boards spotted in the wild either. A Gigabyte AORUS Z990 Pro turned up at Computex earlier this year with its socket taped over, though the branding gave it away. With boards already moving through shipping channels, Nova Lake's early 2027 window looks increasingly realistic, though the rumored 52-core flagship apparently won't arrive until later in the year.

Intel's Big 12 Xe Core iGPU for "Nova Lake-S" Postponed to "Razor Lake"

Intel's long-rumored "big iGPU" version of the upcoming "Nova Lake-S" desktop processor family might not materialize, according to well-known Intel leaker Jaykihn. Intel had been working on a desktop "Nova Lake-S" version with 12 Xe3P cores and a 16-core (4+8+4) CPU cluster, designed to provide enough graphics power for light gaming and 3D work using the integrated graphics solution. However, the future of this Intel APU is now uncertain, as it has reportedly been postponed to launch with the "Razor Lake" generation, which is set to debut a year after "Nova Lake." Considering that "Nova Lake" is still months away and this SKU has been moved to the next generation, it seems we are quite far from seeing a desktop APU from Intel capable of delivering excellent integrated graphics performance.

Previously, we reported that this specific "big APU" SKU could support DDR5-8000 memory through CSODIMM modules, with a Power Limit 2 (PL2) setting of about 40 W. This builds on earlier rumors that this integrated graphics solution would come with two VCCGT phases for up to 65 W of power. This SKU includes four P-Cores, eight E-Cores, and four LPE-Cores, along with 12 Xe3P GPU cores. This 4+8+4 CPU core and 12 GPU core configuration is one of the few processors where integrated graphics would require two VCCGT phases. In regular SKUs, VCCGT is a single-phase power rail for the integrated graphics inside the processor. However, it is now known that the PL2 setting will only use 40 W, with the 65 W threshold reserved for extreme scenarios like PL3, and the graphics processor's PL4 capped at that 65 W figure. The Xe3P features more microarchitectural changes compared to the Xe3 found in "Panther Lake."

Mobile Intel 12 Xe "Nova Lake" May Support Upgradeable DDR5-8000 Memory

Intel's next-generation Nova Lake mobile chips with 12 Xe-core graphics may support DDR5-8000 memory through CSODIMM modules, according to leaker Golden Pig Upgrade Pack on Weibo. If that pans out, it would be the first mobile Nova Lake variant to officially support DDR5, a notable departure from the soldered LPDDR memory that dominates thin-and-light laptops right now. Current Panther Lake systems with 12 Xe cores, like the Core Ultra X7 358H, don't officially list DDR5 support, though ASRock Industrial already ships mini PCs with two DDR5 SO-DIMM slots running at DDR5-7200 on that platform, and Intel itself includes this configuration among its Core Ultra Series 3 developer systems.

Nova Lake-S, the desktop version, has already been tied to DDR5-8000 through leaked B960 chipset details and platform documents, so Intel appears to be pushing that same memory ceiling down into at least part of the mobile lineup too. Unlike soldered LPDDR5X, CSODIMM support would let OEMs offer upgradable RAM again in these systems, an option that's grown rare in slimmer laptop designs built around battery life and board space. Despite the leaker's solid track record, this is still a single leak rather than anything Intel has confirmed, so I'd hold off treating the exact speeds as final. If it checks out, it suggests Intel is willing to give at least some mobile Nova Lake configurations more memory flexibility, even as most of the market keeps drifting toward soldered memory for efficiency.

Leak Confirms Intel's Long-Term Socket Plan with LGA-1954

Intel's "Nova Lake-S" desktop processors are drawing nearer, and today a leaked partner slide from China confirmed many of the plans we anticipated. Starting with the LGA-1954 socket, Intel's testing tools had already verified the pin count. This slide not only confirms the pin count but also introduces a small detail about it. In the bottom left corner, there is a disclaimer stating that Intel plans to keep the LGA-1954 socket for multiple generations. This allows enthusiasts to make a one-time investment and maintain the platform for many years. This is a welcome change, considering Intel has switched between three sockets in the last five years: from LGA-1200 to LGA-1700, and then to LGA-1851.

This long-term socket support suggests that Intel is finally adopting a strategy similar to AMD's, as seen with the introduction of AM4, which served for nearly a decade, and AM5, which is planned for support until 2029. With LGA-1954, Intel aims to achieve the same result, providing enthusiasts and cooler makers with a single socket solution for multiple generations. The slide below is machine-translated from Chinese.

Intel Confirms LGA1954 as the Socket for "Nova Lake-S" Processors Through Internal Tools

The upcoming Nova Lake-S lineup of Intel desktop CPUs has been the subject of strong rumors for a while, and one of them concerned the socket itself. Intel is moving away from LGA1851 and will have a brand-new socket for its upcoming Core Ultra 400 series processors, namely LGA1954. We already know about LGA1954 as its records appeared in shipping manifests months ago, and we even know what the socket looks like. Nova Lake-S will debut on this new socket, and Intel has now officially confirmed this, though not in the usual way.

Intel has just published an internal test tool on its website that connects the LGA1954 socket to Nova Lake-S processors. This listing is for validation hardware and provides some engineering and technical enablement equipment. Nevertheless, the important part is that this is the first time Intel itself has mentioned Nova Lake-S alongside LGA1954 in any sort of official capacity. This is confirmation that Nova Lake-S will indeed launch alongside the LGA1954 socket and Intel 900-series motherboards. Nova Lake is currently expected to launch in Q1 2027.

Intel "Nova Lake-S" 28-Core SKU With bLLC to Draw Nearly 300 W at PL2

Intel's upcoming "Nova Lake-S" desktop processors are nearing launch, and the rumor mill is intensifying as we receive more information about clock speeds, core configurations, and power consumption. According to a post on the Weibo forums, Intel's 28-core SKU with a big last-level cache (bLLC) integrated into the package will reach up to 296 W of power consumption at the Power Level 2 (PL2) setting. This is the maximum power draw the CPU can achieve during short bursts of turbo clocking, reaching its peak. Compared to the current top-end "Arrow Lake-S" 24-core Core Ultra 9 285K, which has a PL2 setting of 250 W, the additional four LPE-Cores on the latest "Nova Lake-S" will increase that number by about 18.4%.

Previously, we learned that "Nova Lake-S" will be very power-hungry, especially in the top-end SKUs. For example, Intel's top-end, overclocking-focused, dual compute die "Nova Lake-S" CPU with 52 cores will feature a PL2 mode with a power level of 474 W. This is an unprecedented number for an Intel consumer desktop platform, typically expected from a high-end desktop (HEDT) design. However, since this is a 52-core design that can be overclocked, it represents the highest CPU PL2 setting that Intel will be shipping with "Nova Lake-S." For single compute die SKUs, the PL2 limit appears to be 296 W.

Intel Core Ultra 9 4950K Could Signal New Naming Scheme for "Nova Lake-S"

Intel's upcoming desktop CPU generation, part of the "Nova Lake-S" processor family, might adopt a new naming convention that returns to a four-digit format, unlike the current three-digit format used in the "Arrow Lake" family. According to a leaked CPU-Z submission, Intel's Core Ultra 9 4950K has been identified as a 28-core "Nova Lake-S" desktop chip. It features 8 "Coyote Cove" P-Cores, 16 "Arctic Wolf" E-Cores, and 4 LPE-Cores. This chip was tested on an unknown Z990 high-end overclocking platform, where it achieved over 1,000 points in single-core CPU-Z rankings and exceeded 20,000 points in multicore performance. This performance surpasses any consumer-focused desktop CPU currently available.

Despite this information, it's still uncertain if the naming convention is final. Intel is testing many SKUs for "Nova Lake-S," and a four-digit naming could be necessary due to the numerous SKUs and configurations. Some leakers, like Golden Pig Upgrade and Gotou_3rd, have suggested that the four-digit naming is a possibility, leaving room for speculation. Interestingly, qualification samples for NVL-S have not yet started shipping, but we can expect these shipments in the coming weeks, before manufacturers and motherboard makers begin integrating the latest CPU generation into their products.

Intel's New CPU Cores Debut on "Nova Lake-S" Desktop Before Xeon Servers

Intel's approach to releasing the latest CPU technology differs significantly from AMD's. Robert Hallock, the company's VP and general manager of the enthusiast business, confirms that desktop PC DIY enthusiasts are the first to experience the latest CPU cores. In an interview with Tom's Hardware, Hallock emphasized that Intel prioritizes bringing its newest CPU cores to desktops first, subtly hinting at the upcoming "Nova Lake-S" processor generation. Unlike AMD, which introduces its latest core designs in the server segment first, Intel debuts them on the desktop. While these cores will eventually be used in Xeon server processors, they initially appear on the desktop platform. This means that the "Coyote Cove" P-Cores and "Arctic Wolf" E-Cores will first be available for desktops, in contrast to AMD's Zen 6 CPU technology, which debuts with the EPYC "Venice" and only later appears in desktop CPUs.
Intel's Robert HallockWhat I would say is, as we think about our own roadmap, I have a new core. It's coming to desktop first. I mean, I hope enthusiasts do the math about that one, and that's all I'm going to say.

Intel "Nova Lake-S" iGPU with 12 Xe3P Cores to Feature 40 W PL2 and 20 MB of L2 Cache

According to the reliable Intel leaker Jaykihn, Intel's upcoming "Nova Lake-S," featuring 12 Xe3P cores, currently has a Power Limit 2 (PL2) setting of about 40 W. This builds on the previous rumor that this integrated graphics solution will arrive with two VCCGT phases for up to 65 W of power. This SKU includes four P-Cores, eight E-Cores, and four LPE-Cores, along with 12 Xe3P GPU cores. This 4+8+4 CPU core and 12 GPU core configuration is one of the few processors where integrated graphics require two VCCGT phases. In regular SKUs, VCCGT is a single-phase power rail for the integrated graphics inside the processor.

However, we now know that the PL2 setting will only use 40 W, as the 65 W threshold is set for extreme scenarios like PL3, and the graphics processor's PL4 is capped at that 65 W figure. The Xe3P features more microarchitectural changes compared to the Xe3 found in "Panther Lake." If readers recall, a 12 Xe3-core iGPU found in "Panther Lake" has 16 MB of L2 cache, while the Xe3P iGPU dedicated to "Nova Lake" will have a 20 MB L2 cache configuration, a 25% increase. More L2 cache means that some workloads will naturally benefit, but we still don't know preliminary performance. The Xe3P microarchitecture is expected to carry more changes, especially since it has a larger L2 cache.

Intel "Nova Lake-S" 12 Xe3P iGPU to Draw Up to 65 Watts

Intel's upcoming "Nova Lake-S" is gearing up for a launch later this year. However, rumors suggest that certain "Nova Lake-S" models with large integrated graphics might require significant power, increasing the TDP and peak power. According to the well-known Intel leaker Jaykihn on X, Intel's 16-core CPU SKU with 12 Xe3P cores will need specialized power delivery, with 65 W dedicated to integrated graphics. This SKU includes four P-Cores, eight E-Cores, and four LPE-Cores, along with 12 Xe3P GPU cores. This 4+8+8+12 core configuration is one of the few processors where integrated graphics require two VCCGT phases. In regular SKUs, VCCGT is a single-phase power rail for the integrated graphics inside the processor. However, since Intel aims to enhance its iGPU performance with "Nova Lake," a single phase is insufficient.

Previously, we learned that Intel's top-end, overclocking-focused, dual compute die "Nova Lake-S" CPU with 52 cores will feature a PL2 mode with a power level of 474 W. This also includes the possibility of three 8-pin CPU power connectors on high-end Z990 motherboards, an intriguing design choice considering that most enthusiast boards typically have two 8-pin EPS CPU connectors. The three 8-pin connectors are mainly intended for the highest-end overclocking designs, rather than being necessary for running the dual compute die designs. Motherboards with either two or three EPS connectors are still expected to support Intel's upcoming high-end 44-core and 52-core processors on the 175 W platform. However, we are likely to see various configurations, and motherboard designs are preparing for higher TDPs. Below image is illustration only.

Intel Shifts Majority of "Nova Lake" Production In-House Amid Yield Improvements

Intel's upcoming "Nova Lake-S" generation of processors is on the horizon, and the company is already making preliminary manufacturing decisions before entering high-volume production. According to a research note from investment bank KeyBanc Capital Markets, Intel initially planned to outsource the main compute tile production for "Nova Lake" to TSMC, utilizing its 2 nm N2 node. The majority of the production, about 60-70%, was to be handled by TSMC, with the remainder produced in-house by Intel Foundry on the 18A node. This meant Intel would dual-source production for its next-generation chip. However, the latest supply chain information suggests that the company now intends to bring the majority of "Nova Lake" compute tile production in-house, with about 80-90% of the tiles being manufactured by Intel Foundry.

This shift comes as Intel's 18A node yields have improved to levels that are finally reliable enough to avoid any product delays, while the company remains fully satisfied with the yield rate and the number of dies that go to waste. Intel has reportedly resolved all yield issues it experienced with its 18A node over the past few months. Our earlier report indicated that the company has addressed these yield issues, making high-volume production of its latest node sustainable from both a manufacturing yield and economic standpoint. For a mature node like 18A, defect rates are now low, around D0=0.1 or D0=0.2, and it is likely that Intel has achieved the lower end of that spectrum due to node advancements and months of high-volume production with "Panther Lake."
Return to Keyword Browsing
Nov 18th, 2026 16:47 PST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts