Intel's next-generation client CPU staple product, "Nova Lake-S", has reportedly taped out of TSMC's fabs in Taiwan. Our previous speculation from the rumor mill suggested that Intel would utilize its own internal 18A node, with help from TSMC's 2 nm high-volume manufacturing. According to SemiAccurate, Intel has taped out a compute tile on TSMC's N2 node, meaning that Nova Lake-S will likely utilize a mix of 18A and TSMC N2 for its compute tiles. A possible reason for this decision is that Intel is building a chain of fall-backs to rely on in case its 18A node doesn't deliver, or it anticipates demand so high that its internal manufacturing capacity can't provide. Either way, clients can expect the product to be delivered on time in H2 of 2026, but under the hood, some interesting solutions may be present.

As far as the exact date, the time from a tapeout to final product is months away. Right now, the taped-out silicon tile is being powered on in Intel's labs and tested, running various test cases that stress out the silicon for multiple use cases and check for correctness of operation. Typically, power on takes a few weeks to a month to achieve, and final high-volume manufacturing will commence only a few months later. From that point, another two to three months are needed for manufacturing and shipping the product, meaning that Q3 of 2026 is the most likely target for Nova Lake-S. As a reminder, the CPU will combine 52 cores (16 P-cores, 32 E-cores, and four LPE-cores) paired with 8,800 MT/s memory controller and Xe3 "Celestial" for graphics rendering and Xe4 "Druid" for media and display duties, making it definitely an interesting product, as well as a difficult manufacturing target due to the heterogenous complexity.

Intel's presentation at the VLSI Symposium in Japan offered a detailed look at the upcoming Intel 18A process, which is set to enter mass production in the second half of 2025. This node combines Gate-All-Around transistors with the PowerVia backside power delivery network, resulting in a completely new metal stack architecture. By routing power through the rear of the die, Intel has been able to tighten interconnect pitches on critical layers while relaxing spacing on the top layer, improving yield and simplifying fabrication. In standardized power, performance, and area tests on an Arm core sub-block, Intel 18A demonstrated roughly 15% higher performance at the same power draw compared to Intel 3. When operating at 1.1 volts, clock speeds increase by up to 25% without incurring additional energy costs, and at around 0.75 volts, performance can rise by 18%, or power consumption can drop by nearly 40%.

Under the hood, the process features significant cell height reductions: performance‑tuned cells measure 180 nanometers tall, while high‑density designs sit at 160 nanometers, both smaller than their predecessors. The front‑side metal layers have been reduced from between 12 and 19 on Intel 3 to between 11 and 16 on Intel 18A, with three additional rear metal layers added for PowerVia support. Pitches on layers M1 through M10 have been tightened from as much as 60 nanometers down to 32 nanometers before easing again in the upper layers. Low-NA EUV exposure is used on layers M0 through M4, cutting the number of masks required by 44% and simplifying the manufacturing flow. Intel plans to debut 18A in its low‑power "Panther Lake" compute chiplet and the efficiency‑core‑only Clearwater Forest Xeon 7 family. A cost-optimized 17-layer variant, a balanced 21-layer option, and a performance-focused 22-layer configuration will address different market segments.

More confirmations regarding the final release of the Intel Arc "Battlemage" B770 GPU have landed, this time with the update of the popular AIDA64 tool. Just days after support for BMG-G31 GPUs, supposedly the SKUs behind the higher-end B770 and B750 models, has landed in the open-source Mesa driver, diagnostic tools are next. In the latest AIDA64 beta version 7.99.7817, FinalWire has added an interesting "GPU information for Intel Battlemage (BMG-G31)" section as a feature update. This means that the tool can now officially recognize Intel's upcoming GPUs and allow users to perform diagnostics. Additionally, the tool also supports the now finalized PCI Express 7.0 controllers and devices, as PCI-SIG has ratified the final specifications of the PCIe Gen 7 standard.

With this confirmation, higher-end Intel Arc B770 and B750 GPUs are getting more credibility for an actual release. We expect to hear more about it in the coming weeks as the rumored Q4 launch nears. Earlier rumors suggest that Intel will pair 32 Xe2 cores for the B770 model with 16 GB of GDDR6 memory on a 256-bit bus. Will Intel satisfy the needs of Arc graphics gamers who have been waiting for a higher-end card remains to be seen. Drop your expectations in the comments, and let us know.

Sparkle has quietly revealed that it will offer three versions of its upcoming Arc Pro B60 graphics card, designed to meet the varying needs of professional users. The first model employs a familiar blower‐style cooler that exhausts heat from the rear of the chassis, while a fully passive variant relies on cooling from case/server/workstation fans. A liquid‐cooled edition, set for a later release, promises the lowest possible temperatures under sustained load. At its core, the Arc Pro B60 is powered by Intel's new workstation‐class "BMG-G21" GPU, featuring 160 XMX AI engines capable of delivering 197 TOPS at INT8 precision, 20 Xe cores, 20 ray‐tracing units, and a peak graphics clock of 2,400 MHz. It is equipped with 24 GB of GDDR6 memory on a 192-bit interface, yielding up to 456 GB/s of bandwidth, and the card's dual-encoder Xe media engine supports modern codecs, including AV1.

All three cooling configurations share a total board power of 200 W supplied via a single 8-pin PCIe connector and include four DisplayPort 2.1 outputs capable of driving displays at up to 8K resolution at 120 Hz with HDR and Display Stream Compression. The blower and passive models were pictured in Sparkle's press release, showing a compact 289×120×42 mm, a two-slot design that should fit most workstations, while the details of the water-cooled version remain mysterious until closer to its debut. No pricing information is available for now.

Intel's official X/Twitter account has started replying to fans asking for a more powerful GPU, teasing the long‑rumored Arc "Battlemage" B770. Over the past week, users who replied to Intel's Arc PRO announcement asking about the B770 have received brief but intriguing responses like "stay tuned," "we're just getting started," and "more to come." On the surface, these could be generic marketing lines. But with NVIDIA gearing up to launch the RTX 5060 and AMD expected to unveil the RX 9060 XT next week, the timing feels deliberate—and perhaps a sign that Intel plans its own midrange contender. Clues are already stacking up. Shipping manifests from Intel's Vietnam assembly plant—the same facility that produced limited‑run B570 and B580 cards—show a batch of BMG‑G31 GPUs en route. Tipster OneRaichu has said the Arc B770 may feature 24 to 32 Xe2 compute units, a 256‑bit memory bus, and up to 16 GB of GDDR6 memory.

Those specifications would position the B770 as a serious rival to NVIDIA's RTX 5060 and AMD's RX 9060 XT in both gaming and compute tasks. Beyond Battlemage, Intel's next‑generation Xe3 "Celestial" architecture is reportedly deep into pre‑silicon validation. Whether Intel opts to reveal the Arc B770 at Computex in late May or in a standalone livestream, the recent social media exchanges have already done their job by building excitement among enthusiasts. Community reaction has been enthusiastic. Many fans hope to see Intel hit the price target of, ideally, under $300. If Intel can deliver strong real‑world gaming performance at an attractive price and ensure wide availability, the Arc B770 could become the breakout midrange card that shifts the balance in this highly competitive segment.

Maxsun's parent company has quietly registered new 24 GB versions of Intel's Arc B580 graphics card with the EEC. While regulatory filings often cover placeholder or speculative hardware, this submission lines up with ongoing rumors about a high-memory "Battlemage" model aimed at both gamers and professionals. Back in December and January, Intel launched the Arc B580 and B570 GPUs, bringing the Battlemage architecture to desktops just a few months after "Lunar Lake" appeared on laptops. Those first cards came with 12 GB of GDDR6 memory, a surprisingly generous amount for graphics cards selling under $300, and they helped establish Intel as a real contender in the mainstream GPU market. Since then, chatter about a 24 GB version has never died down. The story gained weight when board partner Sparkle briefly hinted at such a variant and then retracted the comment under NDA obligations. Further fueling speculation, a Sparkle representative in China discussed the planned "B580 24 GB" during a March social-media exchange.

Now, Maxsun's EEC filing lists two models called "iCraft 24G" and "iCraft 24G OC," and those names match what Sparkle first mentioned. There's no guarantee these cards will actually hit store shelves, but the matching details and timing suggest Intel may be testing the waters for a memory-heavy Arc B580. That would make sense given recent leaks about an Arc PRO A60 workstation card also packing 24 GB of memory. Under the hood, the Arc B580's BMG-G21 chip offers up to 20 Xe cores and 2,560 shader units, putting it in the same ballpark as NVIDIA's GeForce RTX 4060. With Computex just days away, Intel will finally reveal whether these high-memory Arc B580 cards, or perhaps even bigger Battlemage-based workstation GPUs, are coming our way. Additionally, enthusiasts are keeping an eye on the rumored Arc B770, which is expected next quarter and likely to be detailed at Computex alongside Intel's broader Battlemage and upcoming Xe3 "Celestial" roadmap.

GIGABYTE, a global leader in technology, today announced the availability of its flagship ultra-compact mini-PC, the New BRIX Mainstream series, accompanied by an exclusive product video release. This series is powered by the latest Intel Core Ultra processors (Series 2) and boasts an integrated GPU with a remarkable 20% performance increase over the previous generation. Furthermore, it unleashes exceptional AI performance, delivering up to 96 Tera Operations Per Second (TOPS), making it perfectly suited for demanding generative AI tasks and intensive multitasking scenarios.

⁠Designed to meet the growing needs of smart home solutions, commercial deployments, content creation, and edge computing, the BRIX Mainstream series packs this impressive performance into a remarkably compact 0.46-liter chassis with a sleek 3.5 cm profile. Despite its size, it offers top-tier computing power, flexible expansion options, and an eco-conscious, energy-efficient design - delivers performance that exceeds expectation.

Die shots of Intel's "Arrow Lake" desktop processors have appeared online, confirming the chiplet design we have known about since the launch. The images annotated by the YouTube channel HighYield show a four‑tile arrangement mounted on a base die made with Intel's 22 nm FinFET process. The compute tile sits at the top left, built on TSMC's N3B node and covering 117.24 mm². To its right are the SoC tile on TSMC's N6 node measuring 86.65 mm², and the GPU tile, which houses four Xe cores alongside an Arc Alchemist render slice. The I/O tile, at 24.48 mm² on the same N6 node, completes the group at the bottom left. Intel has redesigned its hybrid core layout for Arrow Lake, moving away from separate P‑core and E‑core clusters. Four of the eight high‑performance P‑cores line the die's outer edges, with the remaining four in the center. In between these lie the four efficiency E‑core clusters, each sharing 3 MB of L2 cache. A unified 36 MB L3 cache ring bus connects to every core, allowing E‑cores to tap into that larger cache pool for the first time. Intel aims to spread heat more evenly and boost background task performance.

The I/O tile integrates Thunderbolt 4 controllers, PCIe buffers and PHYs. The SoC tile carries display engines, media accelerators and DDR5 memory controllers. All tiles are bonded to the base die via Intel's Foveros Omni stacking technology. Arrow Lake also reflects a shift in Intel's manufacturing strategy. Plans to use Intel's 20A node were dropped in favor of TSMC processes, making this the first desktop CPU from Intel that relies almost entirely on external foundries. On the software side, Intel has begun offering its IPO profiles in select prebuilt systems. These presets optimize CPU and memory settings for a hassle‑free performance boost that remains within warranty limits. Meanwhile, the native 200S Boost overclocking option is rolling out via BIOS updates. Early tests suggest that 200S Boost alone yields modest gains unless paired with very high-speed DDR5 modules, while IPO profiles deliver more consistent improvements with mainstream memory configurations.

In December, we reported that Intel's next‑generation Arc graphics cards, based on the Xe3 "Celestial" IP, are finished. Tom Petersen of Intel confirmed that the Xe3 IP is baked, meaning that basic media engines, Xe cores, XMX matrix engines, ray‑tracing engines, and other parts of the gaming GPU are already designed and most likely awaiting trial fabrication. Today, we learn that Intel has reached pre‑silicon validation, meaning that trial production is imminent. According to the X account @Haze2K1, which shared a snippet of Intel's milestones, a pre‑silicon hardware model of the Intel Arc Xe3 Celestial IP is being used to map out frequency and power usage in firmware. As a reminder, Intel's pre‑silicon validation platform enables OEM and IBV partners to boot and test new chip architectures months before any physical silicon is available, catching design issues much earlier in the development cycle.

Intel provides OEMs and IBVs access to a secure, cloud‑based environment that faithfully emulates hardware‑representative systems, allowing developers to validate firmware and software stacks from anywhere without the need for physical labs. Most likely, Intel is running massive emulations of hardware on FPGAs, which act as an ASIC chip—an Arc Xe3 GPU in this case. The pre‑silicon validation team is now optimizing the power‑frequency curve and the voltage in sleep, rest, and boost states, as well as their respective frequencies. With the Xe3 IP taking many forms, engineers are experimenting with every possible form factor, from mobile to discrete graphics. Additionally, data pathways depend on these frequency curves, which in turn rely on power states that allow voltage to spike up and down as the application requires. As this work is now complete, engineers are moving on to other areas for optimization, and once the silicon returns from volume production, it will be fully optimized. We expect the first trial of silicon soon, with volume production by the end of the year or in early 2026.

Intel is preparing to launch its first "Panther Lake" mobile processor later this year, but only one configuration will arrive in 2025. This SKU features four high-performance P-cores paired with eight E-cores, leaves out the lower-power efficiency cores, and packs four Xe3 GPU cores. With a 45 W TDP, it is clearly aimed at mainstream gaming laptops rather than ultralight notebooks. Panther Lake fills the gap left by "Lunar Lake" with a higher power envelope and a more performance-oriented design. Lunar Lake ranged from 17 W to 28 W, while Panther Lake's 45 W shows Intel is targeting users who need more sustained compute and graphics throughput. Rumors indicate additional Panther Lake variants will arrive in Q1 of 2026, when Intel plans to have more SKUs shipping to OEMs from volume production.

One such SKU is expected to feature 12 Xe3 GPU cores for premium thin-and-light laptops without discrete graphics. All of Panther Lake processors combine "Cougar Cove" performance cores with "Darkmont" efficiency cores, following Intel's hybrid approach introduced with "Meteor Lake". Intel's decision to stagger the rollout reflects supply chain considerations and product segmentation by power and graphics capability. Gaming laptops that can rely on integrated Xe3 graphics will welcome this 45 W chip, while other form factors may wait for next year's lower-power or ultralight 15 W models. Qualification with OEM partners should begin later this year, with laptop shipments expected by late Q4 2025. Until Intel shares more details on the rest of the Panther Lake lineup, much remains speculative.

Intel today announced that the latest Arc GPU Graphics Drivers update brings significant performance uplifts to the integrated graphics solution of the company's Core Ultra 200V "Lunar Lake" mobile processors. The processor comes with an iGPU based on the Xe2 "Battlemage" graphics architecture, and depending on the processor model, up to 8 Xe cores, the latest XMX AI accelerators, the company's 2nd generation Ray Tracing Unit, and an 8 MB dedicated last-level cache. When it launched, it was expected that the iGPU of "Lunar Lake" would perform in the league of at least the discrete Arc A380 GPU, but fell slightly behind, probably because the iGPU shares memory bandwidth with the CPU complex and the memory-intensive NPU.

With the latest driver updates, Intel is promising a 10% increase in FPS averaged over a test suite of 9 game titles, but more importantly, a significant 25% increase in 99th percentile performance. The test suite covers titles relevant to this performance class, including Counter-Strike 2, Fortnite, and Payday, but also certain AAA titles, such as Cyberpunk 2077 and Black Myth Wukong. Intel recommends the drivers for anyone with a Core Ultra 200V processor model that has either Arc 140V or Arc 130V iGPU models.

Intel's upcoming "Panther Lake" architecture has just popped up in a perfmon platform update, which now recognizes its core codenames and CPUID via the InstLatX64 lookup table. Tagged "GenuineIntel-6-CC" (Family 6, Model 204), the patch confirms that Panther Lake will combine "Cougar Cove" P-cores with Darkmont E-cores and even hints at a third tier of LPE cores in some configurations. It's the clearest sign yet that Intel is sticking firmly to its hybrid-core strategy. We've also got our first look at the actual SKUs. On the high-performance side (PTL-H), there's a 45 W model with 4 P-cores, 8 E-cores, no LP-E-Cores, and 4 Xe3 graphics cores. Two 25 W models share the same 4 P-cores and 8 E-cores but differ in the rest: one adds 4 LP-E-Cores plus 12 Xe3 cores, while the other pairs 4 LP-E-Cores with just 4 Xe3 cores.

The PTL-U series will offer a 15 W chip with 4 P-cores, 4 LPE-Cores, and 4 Xe3 graphics cores for ultralight devices, dropping the traditional E-cores entirely. Intel plans to move Panther Lake into mass production later this year, lining it up behind the risk production of its cutting-edge 18A process. If things follow the Meteor Lake timeline, we'll likely see most Panther Lake chips hitting shelves in Q1 2026. This isn't Lunar Lake 2.0—Lunar Lake was a niche effort aimed at extreme efficiency with on-package memory. Panther Lake, by contrast, seems built for real-world mobile performance. Most laptops will stick with standard SODIMM or soldered LPDDR memory, though a few OEMs are talking up next-generation LP-CAMM slots for easy RAM upgrades. With a rumored maximum TDP of 64 W, Panther Lake can power everything from budget notebooks and handheld gaming devices to serious gaming laptops and even car infotainment systems.

Intel just reported its Q1 revenue results, and there are several interesting highlights from the earnings call. Intel Foundry, long touted for a comeback, is generating most of its revenue from a single customer, and it isn't the latest node. Intel's biggest customer is actually itself, predominantly using the "Intel 7" node (Intel's name for its 10 nm SuperFin process), which underpins the Alder Lake and Raptor Lake consumer CPU generations as well as the Sapphire Rapids Xeon server generation. As Intel ramps up 18A-node production and external clients begin testing their ASIC designs, 18A still isn't the Foundry division's primary revenue driver. Instead, demand for Intel 7 wafers is being fueled by massive orders for Intel's 13th- and 14th-generation Raptor Lake processors.

During the Q1 earnings call, Intel CFO Dave Zinsner noted, "Intel Foundry delivered revenue of $4.7 billion, up 8% sequentially on pull-ins of Intel 7 wafers and increased advanced packaging services." He also commented on the Q1 Foundry operating loss of $2.3 billion, attributing it to "startup costs associated with the ramp of products on Intel 18A." While the 18A node is gradually scaling to volume production for upcoming internal and external products, older nodes continue to fuel the revenue stream. Zinsner further confirmed that "we have a lot of important building blocks in place, including the ramp of Intel 18A in the second half of 2025 to support the launch of our first Panther Lake SKU by year-end, with additional SKUs coming in the first half of 2026."

Thanks to a well-known industry leaker, Jaykihn, Intel's Panther Lake-H processor family, built on the 18A process node, features three distinct configurations, with several power profiles for each case. The flagship model combines four "Cougar Cove" P-cores, eight "Skymont" E-cores, and four LPE cores alongside a 12-core Xe3 "Celestial" GPU. This variant supports LPDDR5X memory exclusively and delivers 180 TOPS of computational power for local AI workloads, operating at 25 W PL1 (base) and 64 W PL2 (turbo) power levels. Secondary configurations include a 4P+8E+4LP+4Xe3 model and a 4P+0E+4LP+4Xe3 variant, both rated at 100 TOPS and supporting both LPDDR5X and DDR5 memory.

The entry-level model operates at 15 W PL1 with 44 W PL2 in baseline mode, scaling to 25 W PL1 and 55 W PL2 in performance mode. All variants feature Thunderbolt 4 connectivity, with high-end models incorporating expanded PCIe 5.0 lane configurations. The integrated Xe3 graphics architecture scales from four to 12 cores across the product stack, with the top SKU eliminating DDR5 compatibility in favor of LPDDR5X optimization. The Panther Lake processor family is slated for launch within the latter half of 2025, and it will be the company's leading 18A product. As a "Lunar Lake" successor, Panther Lake will deliver improved IPC and optimization for new cores in the same device form-factor like laptops, ultrabooks, and handhelds.

Late last week, Team Blue's gaming division celebrated a new milestone—their social media account released a 20-second-long video that swept across a large sprawl of modern titles. The accompanying message boasted: "we've hit the mark on 150+ games with XeSS support, with more on the way! Experience peak gaming for yourself with Intel XeSS AI upscaling today." Intel's launch of Arc "Alchemist" discrete graphics cards marked a more mainstream introduction for their proprietary Xe Super Sampling (XeSS) technology. Earlier in 2022, Xe LP-based iGPUs and Iris Xe MAX discrete GPUs were the first pieces of Team Blue hardware to be enabled with XeSS support.

XeSS 2 was introduced last December—during the official unveiling of Intel's Arc B580 "Battlemage" graphics card—but not enough time has elapsed to gain widespread support. VideoCardz's weekend sleuthing revealed only two compatible titles—in contrast, Team Blue's first-gen super sampling upscaler support list now numbers 159. Since late last year, PC gamers have been snapping up wallet-friendly Arc B580 models. Another—slightly cheaper—XeSS 2-enabled product arrived last month; with the release of Arc B570 cards. We hope that the number of (XeSS 2) supported titles increases, in parallel with the rising popularity of Battlemage GPUs.

"Twin Lake" is codename for a line of low-power x86-64 processors by Intel, which succeed the Core i3 N-series and N200 series "Alder Lake-N" processors. These non-socketed (BGA) chips power a wide range of devices from entry level notebooks and mini PCs to consumer NAS servers, and other embedded applications. The chips feature only E-cores. While "Alder Lake-N" used "Gracemont" cores, "Twin Lake" uses the swanky new "Skymont" cores, which serve as E-cores in "Lunar Lake" and "Arrow Lake" hybrid processors. "Skymont" cores feature massive IPC and clock-speed gains over "Gracemont," of nearly 50%, which pulls up their performance levels to match the "Golden Cove" and "Raptor Cove" P-cores of "Alder Lake" and "Raptor Lake," although these cores can't boost up to 5.00 GHz. We got the first name-drop of "Twin Lake" way back in May 2024. Jaykihn leaked what the processor lineup could look like.

The "Twin Lake" silicon features two "Skymont" E-core clusters sharing an L3 cache. At this point, the sizes of the shared L2 caches of the E-core clusters, and the size of the shared L3 cache are not known. On "Alder Lake-N," each "Gracemont" cluster features 2 MB of L2 cache, and the two clusters share a 6 MB L3 cache. The silicon also features an iGPU based on what is very likely the Xe-LPG graphics architecture, with four Xe cores worth 32 execution units (EU). The series is led by the Intel N355. This chip maxes out the "Twin Lake" silicon, enabling both "Skymont" clusters, for an 8-core/8-thread CPU configuration. The CPU comes with a base frequency of 3.00 GHz, and boosts up to 3.90 GHz. The chip comes with a configurable TDP of 9 W and 15 W. It comes with a maxed out iGPU, with all 32 EU being enabled, and a graphics frequency of 1.35 GHz.

According to recently discovered shipping manifests, Intel is developing a new processor series codenamed "Wildcat Lake," potentially succeeding their entry-level "Intel Processor" lineup based on Alder Lake-N. The documents, revealed by x86deadandback, suggest a 2025 launch timeline for these chips targeting lightweight laptops and mini-PCs. The shipping records from October 30 mention CPU reball equipment compatible with BGA 1516 sockets, measuring 35 x 25 mm, indicating early validation testing is underway. These processors are expected to be manufactured using Intel's advanced 18A process technology, sharing the same manufacturing node as the upcoming Panther Lake series. Early technical specifications of Wildcat Lake point to a hybrid architecture combining next-generation "Cougar Cove" performance cores with "Darkmont" low-power efficiency (LPE) cores in a 2P+4LPE configuration.

This design appears to separate the core clusters, departing from traditional shared ring bus arrangements, similar to the approach taken in Intel's Lunar Lake and Arrow Lake processors. While Wildcat Lake's exact position in Intel's product stack remains unclear, it could serve as a modernized replacement for the what were Pentium and Celeron processor families. These chips traditionally power devices like Chromebooks, embedded systems, and home servers, with the new series potentially offering significant performance improvements for these market segments. The processor is expected to operate in the sub-double-digit TDP power envelope, positioning it below the more powerful Lunar Lake series. Graphics capabilities will likely be more modest than Lunar Lake's Xe2 architecture, aligning with its entry-level market positioning.

During Barclays 22nd Annual Global Technology Conference, Intel was a guest and two of the interim company co-CEOs Michelle Johnston Holthaus and David Zinsner gave a little update on the state of affairs at Intel. One of the most interesting aspects of the talk was Intel's upcoming "Panther Lake" processor—a direct successor to Intel Core Ultra 200S "Arrow Lake-H" mobile processors. The company confirmed that Panther Lake would utilize an Intel 18A node and that a few select customers have powered on Panther Lake on the E0 engineering sample chip. "Now we are using Intel Foundry for Panther Lake, which is our 2025 product, which will land on 18A. And this is the first time that we're customer zero in a long time on an Intel process," said interim co-CEO Michelle Johnston Holthaus, adding, "But just to give some assurances, on Panther Lake, we have our ES0 samples out with customers. We have eight customers that have powered on, which gives you just kind of an idea that the health of the silicon is good and the health of the Foundry is good."

While we don't know what ES0 means for Intel internally, we can assume that it is one of the first engineering samples on the 18A. The "ES" moniker usually refers to engineering samples, and zero after it could be the first design iteration. For reference, Intel's "Panther Lake-H" will reportedly have up to 18 cores: 6 P-cores, 8 E-cores, and 4 LP cores. The design brings back low-power island E-cores in the SoC tile. The P-cores use "Cougar Cove," which should have a higher IPC than "Lion Cove," while keeping the existing "Skymont" E-cores. The SoC tile may move from Arrow Lake's 6 nm to a newer process to fit the LP cores and an updated NPU. The iGPU is said to use the Xe3 "Celestial" architecture. With Arrow Lake-H launching in early 2025, Panther Lake-H likely won't arrive until 2026.

We have already confirmed that Intel is continuing the development of Arc gaming GPUs beyond the current Xe2 "Battlemage" series, with the new Xe3 "Celestial" architecture in the works. However, thanks to PCWorld's The Full Nerd podcast, Tom Petersen of Intel confirmed that the Xe3 IP has been finished, and the hardware teams are already working on the next Xe4 "Druid" GPU IP. "Our architects are way ahead of us, and they are already working on not the next thing but the next thing after the next thing," said Petersen, adding: "The way I would like to comment is our IP that's kind of called Xe3, which is the one after Xe2, that's pretty much baked, right. And so the software teams have a lot of work to do on Xe3. The hardware teams are off on the next thing, right. That's our cadence, that we need to keep going."

The base IP of next-generation Xe3 "Celestial" GPUs is done. That means the basic media engines, Xe cores, XMX matrix engines, ray tracing engines, and other parts of the gaming GPU are already designed and most likely awaiting trial fabrication. The software to support this Xe3 is also being developed while Intel's team is working on enabling more optimizations for the Xe2 "Battlemage" architecture, which we previewed recently. We assume that Intel's Xe GPU will now follow a stricter cadence of releases, with SKUs getting updated much faster, given that a lot is prepared for the future.

SPARKLE Intel Arc B-Series Graphics Card offer offers high-resolution gaming with Intel XeSS AI upscaling, ray tracing, and 8K media support, plus accelerated AI features for enhanced creation and editing through Intel AI Playground.

SPARKLE, an Intel official AIB partner, is announcing:

SPARKLE Intel Arc B580 TITAN OC - with Limited GPU Holder
The SPARKLE Intel Arc B580 TITAN OC debuts with 12 GB GDDR6 memory and advanced TORN Cooling 2.0 featuring triple AXL fans, a 2.2-slot design, and a full-metal backplate. With a boost clock of 2740 MHz and 200 W power consumption, it delivers top-tier gaming performance.
A blue breathing light effect adds elegance, while a limited SPARKLE GPU Holder completes this powerhouse package. The TITAN Series continues its legacy of performance and style.

Acer today announced an expansion to its gaming portfolio with the new Nitro Intel Arc B-Series graphics cards, aimed at DIY gamers seeking high-performance gaming and content creation upgrades for their PC setups.

The Nitro Intel Arc B570 OC 10 GB and Nitro Intel Arc B580 OC 12 GB graphics cards, with clock speeds up to 2,740 MHz and up to 12 GB GDDR6 memory, offer gamers an immersive experience and access to the latest AI technologies via the Intel AI Playground application. These graphics cards are equipped with Acer's advanced FrostBlade cooling systems to ensure peak performance.

Today, Intel announced the new Intel Arc B-Series graphics cards (code-named Battlemage). The Intel Arc B580 and B570 GPUs offer best-in-class value for performance at price points that are accessible to most gamers, deliver modern gaming features and are engineered to accelerate AI workloads. The included Intel Xe Matrix Extensions (XMX) AI engines power the newly introduced XeSS 2, comprised of three technologies that together increase performance, visual fluidity and responsiveness.

"The new Intel Arc B-Series GPUs are the perfect upgrades for gamers. They deliver leading performance-per-dollar and great 1440p gaming experiences with XeSS 2, second-generation ray tracing engines and XMX AI engines. We're delighted to be joined by more partners than ever so that gamers have more choice in finding their perfect design." -Vivian Lien, Intel vice president and general manager of Client Graphics[Editor's note: Our preview of the Arc Battlemage Series is now live]

Sparkle introduced an interesting new graphics card meant for those with four high-resolution displays tied to a workstation, or a digital-signage setup. The new Arc A310 OmniView is based on an underclocked version of the Intel Arc A310 "Alchemist," with the idea being to cap the card at 50 W typical power. The card comes with a 1.00 GHz GPU clock and 15.5 Gbps memory speed, compared to the reference A310, which ticks at 1.75 GHz, but at 75 W typical board power. The card comes with 6 Xe cores, and a 64-bit wide memory interface, pulling 4 GB of GDDR6 memory. The A310 OmniView features a single-slot, full-height design, with no additional power connectors. It uses a simple fan-heatsink to keep cool. Perhaps the most striking aspect of the card is its display I/O, featuring four HDMI 2.0b ports, each of which can drive a 4K display at 60 Hz. The card is 14.5 cm long, and 10.5 cm tall. The company didn't reveal pricing.

Intel's discrete GPUs are close, and recent reports indicate Intel will reveal its next-generation Arc Battlemage graphics cards in December, moving from an earlier expected Black Friday announcement. Hardware insider Golden Pig Upgrade first mentioned this timeline shift, with data researcher Tomasz Gawroński providing supporting evidence through shipping manifest analysis. The December timing appears to position Intel's announcement before CES 2025, where AMD plans to showcase its Radeon RX 8000 series with RDNA 4 architecture, and NVIDIA will present its GeForce RTX 50 line. This will give Intel ample room to "steal" the attention of the tech press, who will be busy with NVIDIA and AMD during CES.

X account Bionic_Squash has confirmed Battlemage won't be Intel's final discrete graphics card, addressing questions about the company's long-term graphics development plans. Intel's future roadmap includes the Xe3 "Celestial" architecture, though current information only confirms its initial implementation in mobile chips at a reduced scale. The timeline for a full discrete graphics card using Celestial architecture remains unspecified. We are also left to wonder about Intel's approach to discrete GPU marketing push, as the company has yet to gain any significant footing among enthusiasts. In the coming years, Intel's expansion could prove worthwhile as it updates its GPUs with more performance from newer generations.

Intel is expanding its Core Ultra 200S lineup with seven new SKUs, a recent leak by @momomo_us shows. The leak gives details on non-K, T, and F versions across the Core Ultra 5 7, and 9 families. The top-end Core Ultra 9 285 will come in 65 W and 35 W versions. These match the 285K's 24-core setup but run at lower speeds. The 285T keeps the 4-core Xe built-in graphics.

The Core Ultra 7 series adds three models: 265 265F, and 265T. All share a 30 MB L3 cache being differentiated by different clock speeds. The T version has much lower base clocks. For the Core Ultra 5 series, the leak shows two models: 225 and 225F. Both have 10 cores running at 3.3/4.9 GHz (P-cores) and 2.7/4.4 GHz (E-cores), with 2 Xe GPU cores and a 65 W TDP. Unlike their higher-end models, this tier doesn't plan to have a T version right now.