Intel is expanding immersion cooling collaborations with Taiwanese partners to strengthen its data center offerings for AI workloads. This includes developing an industry-first open IP complete immersion cooling solution and reference design. Partners like Kenmec and Auras Technology will be key in implementing Intel's advanced cooling roadmap. Intel is also cooperating with Taiwan's Industrial Research Institute on a new lab for certifying high-performance computing cooling technologies to international standards. With local ecosystem partners, Intel aims to accelerate next-generation cooling solutions for Taiwanese and global data centers. Advanced cooling allows packing more performance into constrained data center footprints, which is critical for AI's rapid growth. Intel touts a superfluid-based modular cooling system achieving 1500 Watts+ heat dissipation for high-density deployments.

Meanwhile, Kenmec offers a range of liquid cooling products, from Coolant Distribution Units (CDU) to customized Open Rack version 3 (ORv3) water cooling cabinets, with solutions already Intel-certified. Intel wants to solidify its infrastructure leadership as AI workloads surge by fostering an open, collaborative ecosystem around optimized cooling technologies. While progressing cutting-edge immersion and liquid cooling hardware, cultivating shared validation frameworks and best practices ensures broad adoption. With AI-focused data centers demanding ever-greater density, power efficiency, and reliability, cooling can no longer be an afterthought. Intel's substantial investments in a robust cooling ecosystem highlight it as a priority right alongside silicon advances. By lifting up Taiwanese partners as strategic cooling co-innovators, Intel aims to cement future competitiveness.

Binarly's research team has discovered a collection of security vulnerabilities known as "LogoFAIL", which affects image parsing components within the UEFI firmware of a wide array of devices. These vulnerabilities are especially concerning because they are embedded within the reference code provided by Independent BIOS Vendors (IBVs), affecting not just a single vendor but a broad spectrum of devices that utilize this code. LogoFAIL is particularly dangerous because it allows attackers to bypass crucial security measures such as Secure Boot and Intel Boot Guard by executing a payload during the device's boot process. This is achieved by storing malicious images on the EFI System Partition or within unsigned sections of firmware updates. This method can compromise system security deeply without altering the runtime integrity of the bootloader or firmware, unlike other threats such as BlackLotus or BootHole.

The potential reach of LogoFAIL vulnerability is rather wide, with millions of consumer and enterprise-grade devices from various vendors, including ones like Intel, Acer, and Lenovo, being vulnerable. The exact list of affected devices is still undetermined, but the prevalence of the IBVs' code across numerous devices suggests that the impact could be widespread, with both Windows and Linux users being affected. Only PCs that don't allow any logotype displayed in the UEFI during the boot process are safe. Apple's Macs are secure as they don't allow any add-on images during boot, and some OEM prebuilt PCs, like the ones from Dell, don't allow images in the UEFI. Some makers like Lenovo, AMI, and Insyde have already published notes about cautiously uploading custom images to the UEFI and providing BIOS updates. Consumers and enterprises must check with their OEMs and IBVs for BIOS microcode updates to patch against this vulnerability.Below, you can see the proof of concept in a YouTube video.

Micron Technology, Inc., today announced it is shipping the Micron 3500 NVMe SSD, which leverages its 232-layer NAND to power demanding workloads for business applications, scientific computing, cutting-edge gaming and content creation, pushing the limits of what is possible. The Micron 3500 SSD, available in the M.2 form factor and with capacities up to 2 TB, provides a superior user experience over the competition as proven by its best-in-class SPECwpcsm performance, including an up to 71% improvement for product development applications.

"At Micron, we are focused on delivering exceptional products that best meet the rigorous needs of end-users," said Prasad Alluri, Micron's vice president and general manager of Client Storage. "With impressive specs like a remarkable 132% improvement in scientific computing benchmark scores, the 3500 SSD will turn your next PC or workstation into a powerhouse to enable insights and empower creativity."

According to the latest Canalys forecasts, worldwide PC shipments are on the verge of recovery following seven consecutive quarters of decline. The market is expected to return to growth of 5% in Q4 2023, boosted by a strong holiday season and an improving macroeconomic environment. Looking ahead, full-year 2024 shipments are forecast to hit 267 million units, landing 8% higher than in 2023, helped by tailwinds including the Windows refresh cycle and emergence of AI-capable and Arm-based devices.

"The global PC market is on a recovery path and set to return to 2019 shipment levels by next year," said Canalys Analyst Ben Yeh. "The impact of AI on the PC industry will be profound, with leading players across OEMs, processor manufacturers, and operating system providers focused on delivering new AI-capable models in 2024. These initiatives will bolster refresh demand, particularly in the commercial sector. The total shipment share of AI-capable PCs is expected to be about 19% in 2024. This accounts for all M-series Mac products alongside the nascent offerings expected in the Windows ecosystem. However, as more compelling use-cases emerge and AI functionality becomes an expected feature, Canalys anticipates a fast ramp up in the development and adoption of AI-capable PCs."

Today, AMD announced the extension of its 3rd Gen AMD EPYC processor family with six new offerings providing a robust suite of data center CPUs to meet the needs of general IT and mainstream computing for businesses seeking to leverage the economics of established platforms. The complete family of 3rd Gen AMD EPYC CPUs complements the leadership performance and efficiency of the latest 4th Gen AMD EPYC processors with impressive price-performance, modern security features and energy efficiency for less technically demanding business critical workloads.

The race to deliver AI and high performance computing is creating a technology gap for IT decision-makers seeking mainstream performance. To meet the growing demand for widely deployed, cost effective and proven mainstream solutions in the mid-market and in the channel, AMD is extending the 3rd Gen EPYC CPU offering to provide excellent value, performance, energy efficiency and security features for business-critical applications. The 3rd Gen AMD EPYC CPU portfolio enables a wide array of broadly deployed enterprise server solutions, supported by trusted channel sellers and OEMs such as Cisco, Dell Technologies, Gigabyte, HPE, Lenovo and Supermicro.

TrendForce has issued its latest findings, indicating that the global SSD market has rectified its supply and demand dynamics in 2022, following a resolution in the shortage of master control ICs that had hampered the market in 2021. Despite the normalization of supply, global SSD shipments witnessed a decline, with only 114 million units shipped in 2022—a 10.7% decrease from the prior year.

The top three SSD shipment leaders of 2022 were Kingston, ADATA, and Lexar, with Kingston and ADATA maintaining solid advantages and experiencing growth in market share over 2021. Lexar's growth was attributed to an aggressive push for revenue in anticipation of going public. Kimtigo, in 2022, made significant strides in expanding into industrial control and OEM markets, which in turn boosted its shipment volume and market share. Netac maintained its competitive edge in the SSD market alongside securing several government orders in the enterprise SSD sector, keeping its market share and ranking consistent with the previous year.

TrendForce reports that consumer appetite for electronic products took a hit from high inflation, with global DRAM module sales in 2022 reaching US$17.3 billion—a 4.6% YoY decline. Revenue performance varied significantly among module makers due to the different domains they supply.

TrendForce's data indicated that the top five memory suppliers in 2022 accounted for 90% of total sales, with the top ten collectively capturing 96% of global market revenue. Kingston maintained its dominant market share of 78%. Even with a slight revenue dip, it held steadfast to its position as the global leader. Despite poor end-market demand, Kingston's robust brand scale, along with its comprehensive product supply chain, limited its revenue decline to a modest 5.3%, keeping it firmly at the top of market share rankings.

According to SemiAccurate, Qualcomm is currently navigating through many challenges with its Oryon SoC for laptops. The current problem is that Qualcomm is insisting on integrating its own PMICs (Power Management Integrated Circuits), which are inherently designed for cell phones, causing significant compatibility and efficiency issues. This approach is reported to have led to escalated costs and disagreements with OEMs (Original Equipment Manufacturers), seemingly hindering Qualcomm's foothold in the laptop sector. These PMICs are highlighted as unsuitable and highly priced, requiring the adoption of high-density interconnect (HDI) PCBs engineered explicitly for cell phones, thus not designed to meet the current requirements of laptops optimally. The subsequent spike in production costs has ignited conflicts with OEMs, with several contemplating withdrawing from the project.

In response to the rising tensions, Qualcomm is allegedly providing financial compensation to the OEMs, potentially leading to selling SoCs at cost. The only good thing is the reported success of Nuvia-based Oryon SoC. The silicon is perfect at A0 stepping, and performance is reportedly good. However, power usage and efficiency are still in question. Forcing OEMs to use proprietary PMICs will likely have far-reaching impacts on Qualcomm's market strategies and relationships with OEMs. With disputes like this, we expect that Qualcomm-powered laptops are nearing availability, and we could see them in the coming months.

TrendForce expects that memory suppliers will continue their strategy of scaling back production of both DRAM and NAND Flash in 2024, with the cutback being particularly pronounced in the financially struggling NAND Flash sector. Market demand visibility for consumer electronic is projected to remain uncertain in 1H24. Additionally, capital expenditure for general-purpose servers is expected to be weakened due to competition from AI servers. Considering the low baseline set in 2023 and the current low pricing for some memory products, TrendForce anticipates YoY bit demand growth rates for DRAM and NAND Flash to be 13% and 16%, respectively. Nonetheless, achieving effective inventory reduction and restoring supply-demand balance next year will largely hinge on suppliers' ability to exercise restraint in their production capacities. If managed effectively, this could open up an opportunity for a rebound in average memory prices.

PC: The annual growth rate for average DRAM capacity is projected at approximately 12.4%, driven mainly by Intel's new Meteor Lake CPUs coming into mass production in 2024. This platform's DDR5 and LPDDR5 exclusivity will likely make DDR5 the new mainstream, surpassing DDR4 in the latter half of 2024. The growth rate in PC client SSDs will not be as robust as that of PC DRAM, with just an estimated growth of 8-10%. As consumer behavior increasingly shifts toward cloud-based solutions, the demand for laptops with large storage capacities is decreasing. Even though 1 TB models are becoming more available, 512 GB remains the predominant storage option. Furthermore, memory suppliers are maintaining price stability by significantly reducing production. Should prices hit rock bottom and subsequently rebound, PC OEMs are expected to face elevated SSD costs. This, when combined with Windows increasing its licensing fees for storage capacities at and above 1 TB, is likely to put a damper on further growth in average storage capacities.

Jon Peddie Research reports the growth of the global PC-based graphics processor unit (GPU) market reached 61.6 million units in Q2'23 and PC CPU shipments decreased by -23% year over year. Overall, GPUs will have a compound annual growth rate of 3.70% during 2022-2026 and reach an installed base of 2,998 million units at the end of the forecast period. Over the next five years, the penetration of discrete GPUs (dGPUs) in the PC will grow to reach a level of 32%.

Year to year, total GPU shipments, which include all platforms and all types of GPUs, decreased by -27%, desktop graphics decreased by -36%, and notebooks decreased by -23%.

AMD appears set to enhance the core count for its renowned Threadripper series. After a prolonged wait, the high-end desktop (HEDT) platform boasting a significant CPU count returns with the Ryzen Threadripper PRO 7995WX, which features an impressive 96 cores and 192 threads. This marks the series' first core count upgrade since the Threadripper 3000 series. The 7995WX CPU was spotted in the HP Z6 G5 Workstation system, potentially one of the inaugural prebuilt systems from AMD's OEM partners. The Threadripper PRO series seems poised to dominate AMD's HEDT offerings, with no indications of non-PRO consumer models emerging for now.

The latest Geekbench listing unveiled the 7995WX CPU's 96-core configuration. Although the base frequency appears misrepresented, benchmark data hints at the 96-core CPU potentially reaching a boost clock of 5.14 GHz, a detail further confirmed by Geekbench's output. Another notable enhancement in the Threadripper series is introducing the DDR5 memory standard. While the benchmarking tool doesn't explicitly mention this, it does highlight a memory configuration of 503.27 GB (512 GB) in use. The CPU managed to score 2095 points for single-core score and 81408 points for multi-core score on Geekbench v5.5 for Linux (Ubuntu 22.04 LTS), making it one of the fastest CPUs in the database.

An unusual MSI RTX 3080 Ti SUPRIM X graphics card is up for sale, second hand, on Facebook Marketplace—the Sydney, Australia-based seller is advertising this component as a truly custom model with a non-standard allocation of VRAM: "Yes this is 20 GB not 12 GB." The used item is said to be in "good condition" with its product description elaborating on a bit of history: "There are some scuff marks from the previous owner, but the card works fine. It is an extremely rare collector's item, due to NVIDIA cancelling these variants a month before release. This is not an engineering sample card—this was a finished OEM product that got cancelled, unfortunately." The seller is seeking AU$1100 (~$740 USD), after a reduction from the original asking price of AU$1,300 (~$870 USD).

MSI and Gigabyte were reportedly on the verge of launching GeForce RTX 3080 Ti 20 GB variants two years ago, but NVIDIA had a change of heart (probably due to concerns about costs and production volumes) and decided to stick with a public release of the standard 12 GB GPU. Affected AIBs chose to not destroy their stock of 20 GB cards—these were instead sold to crypto miners and shady retailers. Wccftech points out that mining-oriented units have identifying marks on their I/O ports.

Microsoft Corp. today announced the following results for the quarter ended June 30, 2023, as compared to the corresponding period of last fiscal year:

• Revenue was $56.2 billion and increased 8% (up 10% in constant currency)
• Operating income was $24.3 billion and increased 18% (up 21% in constant currency)
• Net income was $20.1 billion and increased 20% (up 23% in constant currency)
• Diluted earnings per share was $2.69 and increased 21% (up 23% in constant currency)

"Organizations are asking not only how - but how fast - they can apply this next generation of AI to address the biggest opportunities and challenges they face - safely and responsibly," said Satya Nadella, chairman and chief executive officer of Microsoft. "We remain focused on leading the new AI platform shift, helping customers use the Microsoft Cloud to get the most value out of their digital spend, and driving operating leverage."

TrendForce reports that OEMs have continued making concerted efforts to scale back production. However, given that the trajectory of market demand is still unclear, it's expected that the NAND Flash market will continue to be in a state of oversupply in 3Q23. Cautious inventory management by buyers is preventing a stabilization in NAND Flash prices even with an anticipated seasonal surge in demand for 2H23. TrendForce predicts that NAND Flash wafers will be the first to see a price hike in 3Q23 as prices for module products such as SSDs, eMMCs, and UFS will likely continue to fall due to tepid downstream demand. Consequently, the overall ASP of NAND Flash is forecast to continue dropping by about 3~8% in 3Q23, though a possibility exists prices may recover in 4Q23.

Client SSD: Although notebook shipments are expected to gradually recover in 3Q23, reversing an oversupply of SSD will continue to be challenging. Furthermore, a portion of suppliers have implemented aggressive promotions to secure customer orders and hit shipping targets in light of weakened demand and less-than-satisfactory order volumes from major clients, putting pressure on other suppliers. TrendForce estimates that the ASP of client SSDs will fall by 8~13% in the third quarter.

TrendForce reports that continued production cuts by DRAM suppliers have led to a gradual quarterly decrease in overall DRAM supply. Seasonal demand, on the other hand, is helping to mitigate inventory pressure on suppliers. TrendForce projects that the third quarter will see the ASP for DRAM converging towards a 0~5% decline. Despite suppliers' concerted efforts, inventory levels persistently remain high, keeping prices low. While production cutbacks may help to curtail quarterly price declines, a tangible recovery in prices may not be seen until 2024.

PC DRAM: The benefits of consolidated production cuts on DDR4 by the top three suppliers are expected to become evident in the third quarter. Furthermore, inventory pressure on suppliers has been partially alleviated due to aggressive purchasing by several OEMs at low prices during 2Q23. Evaluating average price trends for PC DRAM products in 3Q23 reveals that DDR4 will continue to remain in a state of persistent oversupply, leading to an expected quarterly price drop of 3~8%. DDR5 prices—influenced by suppliers' efforts to maintain prices and unmet buyer demand—are projected to see a 0-5% quarterly decline. The overall ASP of PC DRAM is projected to experience a QoQ decline of 0~5% in the third quarter.

Ampere Computing today announced a new AmpereOne Family of processors with up to 192 single threaded Ampere cores - the highest core count in the industry. This is the first product from Ampere based on the company's new custom core, built from the ground up and leveraging the company's internal IP. CEO Renée James, who founded Ampere Computing to offer a modern alternative to the industry with processors designed specifically for both efficiency and performance in the Cloud, said there was a fundamental shift happening that required a new approach.

"Every few decades of compute there has emerged a driving application or use of performance that sets a new bar of what is required of performance," James said. "The current driving uses are AI and connected everything combined with our continued use and desire for streaming media. We cannot continue to use power as a proxy for performance in the data center. At Ampere, we design our products to maximize performance at a sustainable power, so we can continue to drive the future of the industry."

TrendForce reveals that alongside the four major CSPs reducing their procurement volumes, OEMs like Dell and HPE have also scaled back their annual shipment volume forecasts at some point between February and April, predicting YoY declines of 15% and 12%, respectively. Furthermore, server demand in China is facing headwinds due to geopolitical and economic challenges. Consequently, TrendForce projects a downward revision in global server shipment volumes for this year—a 2.85% YoY decrease at 13.835 million units.

TrendForce emphasizes that the server market in 1H23 remains pessimistic, with 1Q23 shipments experiencing a 15.9% QoQ decrease due to off-season factors and end-user inventory adjustments. The expected industry boom in 2Q23 failed to materialize, leading to a modest QoQ growth estimate of only 9.23%. Persistent influences on server shipments include OEMs lowering shipment volumes, subdued domestic demand in China, and continuous supply chain inventory adjustments. ESG issues have also led CSPs to prolong server lifecycles and reduce procurement volume. Moreover, OEMs are lengthening supports period for older platforms as businesses seek to control capital expenditures, further contributing to market strain.

Microsoft Corp. today announced the following results for the quarter ended March 31, 2023, as compared to the corresponding period of last fiscal year:

• Revenue was $52.9 billion and increased 7% (up 10% in constant currency)
• Operating income was $22.4 billion and increased 10% (up 15% in constant currency)
• Net income was $18.3 billion and increased 9% (up 14% in constant currency)
• Diluted earnings per share was $2.45 and increased 10% (up 14% in constant currency)

"The world's most advanced AI models are coming together with the world's most universal user interface - natural language - to create a new era of computing," said Satya Nadella, chairman and chief executive officer of Microsoft. "Across the Microsoft Cloud, we are the platform of choice to help customers get the most value out of their digital spend and innovate for this next generation of AI."

Resident TechPowerUp hardware database overseer T4C Fantasy has divulged some early information about a custom version of the NVIDIA GeForce RTX 4060 Ti GPU card - Colorful's catchily named iGame RTX 4060 Ti Ultra White OC model has been added to the TPU GPU database, and T4C Fantasy has revealed a couple of tidbits on Twitter. The GPU has been tuned to have a maximum boost clock of 2580 MHz, jumping from a base clock of 2310 MHz. According to past leaks the reference version of the GeForce RTX 4060 Ti has a default boost clock of 2535 MHz, so Colorful's engineers have managed to add another 45 MHz on top of that with their custom iteration - so roughly 2% more than the reference default.

T4C Fantasy also confirmed that the Colorful iGame RTX 4060 Ti Ultra W OC will be appointed with 8 GB of VRAM, which also matches the reference model's rumored memory spec. T4C Fantasy points out that brands have the option to produce RTX 4060 Ti cards with a larger pool of attached video memory, but launch models will likely stick with the standard allotment of 8 GB of VRAM. The RTX 4060 Ti is listed as being based on the Ada Lovelace GPU architecture (GPU variant AD106-350-A1), and T4C Fantasy expects that Team Green will stick with a 5 nm process size - contrary to reports of a transition to manufacturing on 4 nm (chez TSMC foundries).

Personal computers (PCs) based on Arm architecture will grow in popularity and their market share will almost double from 14% now to 25% by 2027, according to Counterpoint Research's latest projections. The ability of Arm-based hardware to run Mac OS has allowed Apple to capture 90% of the Arm-based notebook computer market. However, the full support of Windows and Office365 and the speed of native Arm-based app adoption are also critical factors in determining the Arm SoC penetration rate in PCs. Once these factors are addressed, Arm-based PCs will become a viable option for both daily users and businesses.

As more existing PC OEMs/ODMs and smartphone manufacturers enter the market, they will bring their expertise in Arm-based hardware and software, which will further boost the popularity of Arm-based PCs. The availability of more native Arm-based apps will also increase user comfort and familiarity with the platform. Overall, the trend towards Arm-based PCs is expected to continue and their market share will likely increase significantly in the coming years.

Although NAND suppliers have continued to roll back production, there is still an oversupply of NAND Flash as demand for products such as servers, smartphones, and notebooks is still too weak. Therefore, TrendForce predicts that the ASP of NAND Flash will continue to fall in 2Q23, though that decline may shrink to 5~10%. The key to supply and demand returning to a market equilibrium lies in whether NAND suppliers can cut back on production even more. TrendForce believes if demand remains stable, then the ASP of NAND Flash will have an opportunity to rebound in 4Q23; if demand is weaker than expected, then ASP will take longer to recover.

Client SSD: Currently, PC OEM's have managed to liquidate most of their component inventory, and are now gearing up in preparation for mid-year sales events. Suppliers are cutting prices to clear out their inventories of PCIe Gen 3 SSDs, which are gradually being phased out. Meanwhile, prices of PCIe Gen 4 SSDs continue to face downward pressure due to a slow intake of new customer orders. The continuous decline of QLC products in 1Q23 has also dragged down the prices of TLC products, and there is relatively little room for prices to keep falling in 2Q23. While it still remains unclear whether or not demand will recover, TrendForce projects that the prices of PC client SSDs will drop 5~10% in 2Q23.

TrendForce reports that several suppliers, such as Micron and SK hynix, have started scaling back DRAM production. The ASP of DRAM plunged 20% in 1Q23, and this price decline is predicted to slow down to 10~15% next quarter. It's uncertain whether or not demand will recover in 2H23. Therefore, the ASP of DRAM has continued to fall as inventory levels are high from the suppliers' side, and prices will only rebound if there is a significant decrease in production.

PC DRAM: Purchase quantity from buyers has fallen drastically over the past three quarters; buyers have around 9~13 weeks of PC DRAM stock remaining. Despite suppliers having already cut production in the PC DRAM segment, DDR4 8 GB module is still likely to fall by more than 10% in 2Q23. There is a possibility that PC OEMs may purchase more DRAM because prices have been down to a relatively low level, but it is still under observation whether or not this can mitigate the inventory overstock situation from the suppliers' side. TrendForce predicts the ASP of PC DRAM will fall between 10~15%.

NVIDIA has killed SLI on its graphics cards, disabling the possibility of connecting two or more GPUs to harness their power for gaming and other workloads. However, SLI is making a reincarnation today in the form of a new H100 GPU model that spots higher memory capacity and higher performance. Called the H100 NVL, the GPU is a unique edition design based on the regular H100 PCIe version. What makes the H100 HVL version so special is the boost in memory capacity, now up from 80 GB in the standard model to 94 GB in the NVL edition SKU, for a total of 188 GB of HMB3 memory, running on a 6144-bit bus. Being a special edition SKU, it is sold only in pairs, as these H100 NVL GPUs are paired together and are connected by three NVLink connectors on top. Installation requires two PCIe slots, separated by dual-slot spacing.

The performance differences between the H100 PCIe version and the H100 SXM version are now matched with the new H100 NVL, as the card features a boost in the TDP with up to 400 Watts per card, which is configurable. The H100 NVL uses the same Tensor and CUDA core configuration as the SXM edition, except it is placed on a PCIe slot and connected to another card. Being sold in pairs, OEMs can outfit their systems with either two or four pairs per certified system. You can see the specification table below, with information filled out by AnandTech. As NVIDIA says, the need for this special edition SKU is the emergence of Large Language Models (LLMs) that require significant computational power to run. "Servers equipped with H100 NVL GPUs increase GPT-175B model performance up to 12X over NVIDIA DGX A100 systems while maintaining low latency in power-constrained data center environments," noted the company.

Today, thanks to Yuuki_Ans on the Chinese Bilibili forum, we have more information about the upcoming "Avenue City" platform that powers Granite Rapids and Sierra Forest. Intel's forthcoming Granite Rapids and Sierra Forest Xeon processors will diverge the Xeon family into two offerings: one optimized for performance/core equipped with P-cores and the other for power/core equipped with E-cores. The reference platform Intel designs and shares with OEMs internally is a 16.7" x 20" board with 20 PCB layers, made as a dual-socket solution. Featuring two massive LGA-7529 sockets, the reference design shows the basic layout for a server powered by these new Xeons.

Capable of powering Granite Rapids / Sierra Forest-AP processors of up to 500 Watts, the platform also accommodates next-generation I/O. Featuring 24 DDR5 DIMMs with support for 12-channel memory, with memory speeds of up to 6400 MT/s. The PCIe selection includes six PCIe Gen 5 x16 links supporting CXL cache coherent protocol and 6x24 UPI links. Additionally, we have another piece of information that Granite Rapids will come with up to 128 cores and 256 threads in both regular and HBM-powered Xeon Max flavoring. You can see storage and reference platform configuration details on the slides below.

AMD's EPYC lineup already features the new Zen 4 core designed for better performance and efficiency. However, since the release of EPYC Milan-X processors with 3D V-cache integrated into server offerings, we wondered if AMD will continue to make such SKUs for upcoming generations. According to the report from Wccftech, we have a leaked table of specifications that showcase what some seemingly top-end Genoa-X SKUs will look like. The two SKUs listed here are the "100-000000892-04" coded engineering sample and the "100-000000892-06" coded retail sample. With support for the same SP5 platform, these CPUs should be easily integrated with the existing offerings from OEM.

As far as specifications, this processor features 384 MBs of L3 cache coming from CCDs, 768 MBs of L3 cache from the 3D V-Cache stacks, and 96 MBs of L2 cache for a total of 1248 MBs in the usable cache. A 3 MB stack of L1 cache is also dedicated to instructions and primary CPU data. Compared to the regular Genoa design, this is a 260% increase in cache sizes, and compared to Milan-X, the Genoa-X design also progresses with 56% more cache. With a TDP of up to 400 Watts, configurable to 320 Watts, this CPU can boost up to 3.7 GHz. AMD EPYC Genoa-X CPUs are expected to hit the shelves in the middle of 2023.