TYAN, an industry-leading server platform design manufacturer and a subsidiary of MiTAC Computing Technology Corporation, today announced availability of new single-socket server platforms supporting AMD EPYC 8004 Series processors. These platforms are purpose built for cloud services and intelligent edge deployments while offering lower operating costs and delivering impressive energy efficiency.

"The AMD EPYC 8004 Series CPUs deliver a great combination of impressive performance and streamlined platform componentry which enables us to develop business-relevant server configurations for our customers," said Eric Kuo, Vice President of the Server Infrastructure Business Unit at MiTAC Computing Technology. "TYAN's innovative server platform, fueled by EPYC 8004 Series CPUs, empowers us to provide our customers with cost-effective solutions while also expanding into new markets."

Supermicro, Inc., a Total IT Solution Provider for Cloud, AI/ML, Storage, and 5G/Edge, is announcing the AMD based Supermicro H13 generation of WIO Servers, optimized to deliver strong performance and energy efficiency for edge and telco datacenters powered by the new AMD EPYC 8004 Series processors. The new Supermicro H13 WIO and short-depth front I/O systems deliver energy-efficient single socket servers that lower operating costs for enterprise, telco, and edge applications. These systems are designed with a dense form factor and flexible I/O options for storage and networking, making the new servers ideal for deploying in edge networks.

"We are excited to expand our AMD EPYC-based server offerings optimized to deliver excellent TCO and energy efficiency for data center networking and edge computing," said Charles Liang, president and CEO of Supermicro. "Adding to our already industry leading edge-to-cloud rack scale IT solutions, the new Supermicro H13 WIO systems with PCIe 5.0 and DDR5-4800 MHz memory show tremendous performance for edge applications."

The advent of PCIe 5.0 SSDs with Phison's E26 controllers has been a double-edged sword. While these SSDs offer impressively high data throughputs, they come with a significant drawback: severe overheating issues that can cause the SSDs not only to throttle down but to shut off entirely. TechPowerUp first noted this issue back in May, in our Corsair MP700 review, where the uncooled drive shut down after 86 seconds of reads and after 55 seconds of writes. Regarding criticism from tech reviewers, Corsair has released a firmware update (version 22.1) for its MP700 SSD to ensure that it throttles down rather than shutting off when overheated. Yet, many other SSDs like the Crucial T700, Seagate FireCuda 540, Gigabyte Aorus Gen 5 10000, and ADATA Legend 970 still suffer from temperature issues.

However, it's crucial to note that these extreme overheating problems occur only when the SSDs run without any cooling. While some manufacturers have planned firmware updates to address the issue, Corsair is the only company that has taken tangible action so far. Crucial has released a new firmware (PACR5102), but the ComputerBase report indicates that the SSD continues to shut off at high temperatures. The problem, though, can generally be mitigated with proper cooling. Whether using the included cooler or placing the SSD under a motherboard cover, temperatures usually stay below the critical limit, thus avoiding a complete shutdown. When we tested the SSTC Tiger Shark Elite 2 TB with Phison E26 (with updated firmware) without adequate cooling, the SSD continued to operate and throttled down, indicating that the remaining SSDs using this controller need a proper firmware update that throttles the SSD instead of shutting it down.

Verbatim, a global leader in data storage and computer peripherals, is pleased to announce its participation in this year's IFA exhibition in Berlin (01-05 Sept 2023). Attendees at the Verbatim stand, located in Hall 10.2, Booth 112, will have the opportunity to explore an impressive selection of new storage products and mobile and desktop accessories designed to enhance everyday practicality, efficiency, and peace of mind.

Innovative SSDs take centre stage
Verbatim will be proud to demonstrate its new Vi12000 Generation 5 PCIe NVMe M.2 internal SSD, one of the fastest internal SSDs on the market, with read / write speeds of 12300 MB/s and 11,888 MB/s respectively. Alongside this flagship product, Verbatim will also present an assortment of internal and external SSDs, including the Vi7000G internal SSD, tailored for gaming enthusiasts and compatible with PlayStation 5 consoles.

TrendForce research reveals that, due to the impacts of high inflation and economic downturn, CSPs are adopting more conservative strategies when it comes to capital expenditure and consistently reducing their annual server demand forecasts. Currently, CSPs in China have reported a decline in cloud orders compared to last year, leading to a subsequent decrease in annual procurement volumes for enterprise SSDs. In North America, some clients have postponed mass production timelines for new server platforms while ramping up investments in AI servers. These factors have resulted in enterprise SSD orders falling below expectations. Consequently, global enterprise SSD revenue hit an all-time low in the second quarter, totaling just $1,500 million—a QoQ decrease of 24.9%.

Demand for AI servers remains strong in the third quarter, while orders and shipment momentum for general-purpose servers have yet to show signs of recovery. This continues to put pressure on the purchasing volume of enterprise SSDs, and annual bit volume is expected to be lower than last year. Meanwhile, vendors have once again reduced capacity utilization to slow down inventory growth. Server customers still maintain high inventory levels, and their purchasing momentum remains insufficient. This is expected to lead to an approximate 15% QoQ decline in the average price of enterprise SSDs in the third quarter, which may further result in a lackluster revenue performance for the peak season.

Supermicro, Inc., a Total IT Solution Provider for Cloud, AI/ML, Storage, and 5G/Edge, today announced a new VMware vSAN solution optimized to run enterprise class hyperconverged virtualized workloads. As virtualized workloads become more advanced, processing power and storage performance requirements increase, requiring greater capacity to meet application SLAs and maximize virtual machine density. This solution also utilizes the latest Intel AMX accelerator for AI workloads.

When compared to the Supermicro X11 BigTwin, benchmark testing conducted by Supermicro showed up to 4.7X higher IO throughput and 8.2X lower latency on the HCIBench benchmark, up to 4.9X faster image classification inference throughput on the ResNet50 model and up to 4X faster natural language processing throughput on BERT-Large model. In addition, the superior power and efficiency of the Supermicro X13 BigTwin architecture can deliver up to 3X cost and performance improvement within the same node footprint compared to a similar deployment based on older generation Supermicro systems, creating a compelling case for organizations to upgrade their aging infrastructure.

Supermicro, Inc., a Total IT Solution Provider for Cloud, AI/ML, Storage, and 5G/Edge, is delivering a high-throughput, low latency E3.S storage solutions supporting the industry's first PCIe Gen 5 drives and CXL modules to meet the demands of large AI Training and HPC clusters, where massive amounts of unstructured data must be delivered to the GPUs and CPUs to achieve faster results.

Supermicro's Petascale systems are a new class of storage servers supporting the latest industry standard E3.S (7.5 mm) Gen 5 NVMe drives from leading storage vendors for up to 256 TB of high throughput, low latency storage in 1U or up to a half petabyte in 2U. Inside, Supermicro's innovative symmetrical architecture reduced latency by ensuring the shortest signal paths for data and maximized airflow over critical components, allowing them to run at optimal speeds. With these new systems, a standard rack can now hold over 20 Petabytes of capacity for high throughput NVMe-oF (NVMe over Fabrics) configurations, ensuring that GPUs remain saturated with data. Systems are available with either the 4th Gen Intel Xeon Scalable processors or 4th Gen AMD EPYC processors.

It appears that Silicon Motion is ready to start competing with Phison in the PCIe 5.0 NVMe SSD controller market, as the company has shown a new controller at the Flash Memory Summit 2023 which should give Phison a run for its money. The SM2508 as the controller is called is set to be the most power efficient PCIe 5.0 NVMe controller to date, with a power consumption of 3.5 W, which is in line with most PCIe 4.0 SSD controllers. This still means that a decent heatsink will be needed, but not active cooling or massive heatsinks that we've seen on the current crop of PCIe 5.0 drives based on Phison's E26 controller.

Silicon Motion also appears to have the Phison E26 beat, in terms of performance, as the SM2508 promises to deliver sequential read and write speeds of up to 14 GB/s. Random performance is rated at 2.5 million IOPS read and 2.4 million IOPS write. To get the most out of the SM2508 2400 MT/s or faster NAND flash is going to be needed to deliver the claimed performance figures though, but according to Anandtech, the SM2508 is future proofed by supporting NAND flash speeds of up to 3600 MT/s, so we might see faster drives based on the controller once faster NAND appears, such as SK Hynix new 321-layer NAND, which is scheduled for a 2025 introduction. The SM2508 on the other hand is said to be launching at the end of this year or early 2024.

KIOXIA America, Inc. today announced the addition of the KIOXIA CD8P Series to its lineup of data center-class solid state drives (SSDs). KIOXIA CD8P drives are well-suited to general purpose server and cloud environments that can take advantage of PCIe 5.0 (32 gigatransfers/s x4) performance. These data center applications can generate complex mixed workloads spread across large scale virtualized systems. The new drives are available in capacities up to 30.72 terabytes (TB) and in both Enterprise and Data Center Standard Form Factor (EDSFF) E3.S and 2.5-inch (U.2) form factors.

Optimized for the performance, latency, reduced power and thermal requirements of data center environments where power and cooling efficiency is critical, the KIOXIA CD8P Series provides the predictability and consistency needed for a seamless user experience. According to Jeff Janukowicz, Research Vice President, IDC, "Growth in NVMe SSDs continues with PCIe capacity shipments in servers and storage systems expected to grow at a 40% CAGR between 2022 and 2027. The new CD8P Series SSDs gives these customers the range of performance, capacity, and security choices essential for meeting the storage requirements of next-generation digital enterprise and data center infrastructure."

The first batch of PCIe 5.0 NVMe SSDs didn't quite deliver on the promise of doubling performance from PCIe 4.0 NVMe SSDs, but now it appears that Sabrent has managed to work some magic with its upcoming Rocket X5 SSD. The SSD is still based on the same Phison E26 controller as all other current PCIe 5.0 NVMe drives and from what we know, the controller is paired to Micron's 232-layer B58R NAND, a combination that should be able to reach 2400 MT/s across eight channels. However, it's not the only drive with this combination of components, so it seems like the magic here might be in the firmware.

A 2 TB version of the Rocket X5 was tested in CrystalDiskMark 8.0.4 and reached a read speed of 14,179 MB/s or just over 14 GB/s, with write speeds trailing somewhat at 12,280 MB/s. The random 4K numbers are looking good too with 106 MB/s for reads and 448 MB/s for writes, a step up from the competition at least, if not a major one with regards to the read speed. The downside you ask? Sabrent has equipped the Rocket X5 with not only a heatsink and heatpipes, but also a tiny fan, which is likely to add some noise at some time in the future when the fan starts to give up. We obviously don't know the price of the Rocket X5 either, but Sabrent tends to have competitively priced products.

Not entirely unexpected, Seagate is getting ready to launch its first PCIe 5.0 NVMe SSD which will be going under the name of FireCuda 540 and now details of the upcoming drive have appeared online courtesy of Amazon UK, B&H Photo and others that have put up the product for pre-order. For those worried about the lack of a 4 TB SKU, you can relax, as the company is planning a 4 TB SKU, which is made clear from the pictures posted by Amazon UK. However, changing the digit in the model number that represents the drive size, doesn't bring up any info about a 4 TB SKU at the moment.

It doesn't look like the FireCuda 540 will be competing with the fastest PCI 5.0 NVMe drives, as it's only listed as offering sequential drives speeds of up to 10 GB/s, although this applies to both read and write speeds for the 2 TB SKU, with the 1 TB SKU being somewhat slower with read speeds of 9.5 GB/s and write speeds of 8.5 GB/s. The 1 TB SKU is good for 1,000 TB TBW, with the 2 TB SKU doubling this to 2,000 TB and the 4 TB SKU apparently hitting 3,949 TB or as Seagate put it, this allows you to erase 90 percent of the drive every day for five years. B&H Photo has the drives listed at US$189.99 for the 1 TB SKU and US$319,99 for the 2 TB SKU—making both SKUs cheaper than Crucials T700—with Amazon UK listing the 1 TB SKU for £203.48 and no pricing for the 2 TB SKU. It's unclear when the Seagate FireCuda 540 will launch, but it can't be far away.

Neo Forza, a Taiwanese brand entity under Goldkey Technology Corporation, had a booth at Computex 2023, where the company showed its next-generation memory and storage products. Starting off, the company presented its DDR5 memory kits running at 8000 MHz speeds, indicating the maturity of DDR5 and that we are way past the initial 4800 MHz speeds at launch. The demonstrated kit was a part of the company's TRINITY lineup, which was displayed in white. For demo purposes, the kit was configured as two 16 GB DIMMs.

Next up, Neo Forza has showcased its next-generation PCIe Gen 5 NVMe SSD. Running at x4 lanes of the new PCIe 5.0 protocol, the 2 TB SSD was spotted running at 10 GB/s speeds in both read and write tasks set by CrystalDiskMark benchmark. Interestingly, the SSD also boasted a massive heatsink, as shown below.

be quiet!, a German company focusing on creating PC components and accessories, had a strong presence at Computex 2023. Showing off its cases and power supplies, the company introduced a few additions to its portfolio of offerings. For starters, be quiet! has introduced a new case series called Shadow Base. The new Shadow Base lineup is focused on maximum airflow and maximum performance, where the company has made a new open mesh design that allows for "exceptionally high airflow." Inaugurating model of the series is the Shadow Base 800, which comes in three flavors: standard, DX, and FX. The standard edition is just a regular case without flashy RGB; the DX model has an RGB strip, while the FX model is tailored for maximum RGB illumination across the case. With up to E-ATX motherboard support, the case supports three or four 140 mm fans, depending on the variant. You can see the specification sheet below.

Chinese InnoGrit has proved to be something of a competent contender in the high-end SSD controller market and at Computex 2023 the company was displaying an early sample of its upcoming IG5666 consumer focused PCIe 5.0 NVMe SSD controller. At the moment the company has taped out the controller, but aren't happy with the physical size of the chip and will be doing another tape out for a more optimised chip. Innogrit is using a 16 nm node for the controller, which might be part of the reason why they're having a hard time to get it the right size, but there's also cost reasons that have to be taken into consideration.

Based on the early samples, InnoGrit is expecting it to reach sequential speeds of up to 14 GB/s read and 11 GB/s write. Random performance is said to reach 3 million read and 2.5 million write IOPs. The controller should support up to 16 TB of NAND flash and it supports all common types of NAND up to a speed of 2400 MT/s. The IG5666 is based on the same Tacoma architecture as InnoGrit's IG5669, which is targeting enterprise use, yet delivers similar performance.

TYAN, an industry-leading server platform design manufacturer and a subsidiary of MiTAC Computing Technology Corporation, will be showcasing its latest HPC, cloud and storage platforms at Computex 2023, Booth #M0701a in Taipei, Taiwan from May 30 to June 2. These platforms are powered by AMD EPYC 9004 Series processors, which offer superior energy efficiency and are designed to enhance data center computing performance.

"As businesses increasingly prioritize sustainability in their operations, data centers - which serve as the computational core of an organization - offer a significant opportunity to improve efficiency and support ambitious sustainability targets," said Eric Kuo, Vice President of the Server Infrastructure Business Unit at MiTAC Computing Technology Corporation. "TYAN's server platforms powered by 4th Gen AMD EPYC processor enable IT organizations to achieve high performance while remaining cost-effective and contributing to environmental sustainability."

ASRock, a global leader in motherboards, graphics cards, monitors, and small form factor PCs, is excited to announce its participation in the upcoming COMPUTEX Taipei 2023 after years of anticipation. ASRock will showcase a range of breathtaking innovative products and highly anticipated technology demonstrations. Attendees will have the opportunity to explore the ASRock latest products and solutions firsthand; also, get the immersive gaming experience at ASRock booth.

Unveiling the Next-Gen ASRock Monitors
ASRock is set to showcase an exciting lineup of monitors at COMPUTEX 2023, featuring six existing products along with new gaming and business models. The spotlight will be on the PG558KF and PG32UMF, two high-end monitors.

Achronix Semiconductor Corporation, a leader in high-performance FPGAs and embedded FPGA (eFPGA) IP, today announced that its VectorPath accelerator card featuring a Speedster 7t FPGA has been certified by PCI-SIG for PCIe Gen 5 and is the first and only FPGA accelerated CEM add-in card certified for PCIe Gen 5 x16 at 32 gigatransfers per second (GT/s) on the PCI-SIG Integrator's list. VectorPath S7t-VG6 accelerator cards are designed to reduce time to market when developing high-performance compute and acceleration functions for AI, ML, networking and data center applications and are shipping today.

"Achronix continues to drive acceleration in the high-performance FPGA add-in card market," said Craig Petrie, Vice President at BittWare. "Achieving PCI-SIG Gen 5 certification is an important milestone. Our customers can be assured of the highest PCIe bandwidths and have confidence that VectorPath cards will interoperate with Gen 5 servers."

Supermicro, Inc., a Total IT Solution Provider for Cloud, AI/ML, Storage, and 5G/Edge, continues to expand its data center offerings with liquid cooled NVIDIA HGX H100 rack scale solutions. Advanced liquid cooling technologies entirely from Supermicro reduce the lead time for a complete installation, increase performance, and result in lower operating expenses while significantly reducing the PUE of data centers. Savings for a data center are estimated to be 40% for power when using Supermicro liquid cooling solutions compared to an air-cooled data center. In addition, up to 86% reduction in direct cooling costs compared to existing data centers may be realized.

"Supermicro continues to lead the industry supporting the demanding needs of AI workloads and modern data centers worldwide," said Charles Liang, president, and CEO of Supermicro. "Our innovative GPU servers that use our liquid cooling technology significantly lower the power requirements of data centers. With the amount of power required to enable today's rapidly evolving large scale AI models, optimizing TCO and the Total Cost to Environment (TCE) is crucial to data center operators. We have proven expertise in designing and building entire racks of high-performance servers. These GPU systems are designed from the ground up for rack scale integration with liquid cooling to provide superior performance, efficiency, and ease of deployments, allowing us to meet our customers' requirements with a short lead time."

KIOXIA America, Inc. today announced that its lineup of CD7 Series Enterprise and Datacenter Standard Form Factor (EDSFF) E3.S NVMe SSDs are first to ship on servers and storage from Hewlett Packard Enterprise (HPE). The industry's first EDSFF drives designed with PCIe 5.0 technology, KIOXIA CD7 E3.S SSDs increase flash storage density per drive for optimized power efficiency and rack consolidation. HPE ProLiant Gen11 servers, HPE Alletra 4000 data storage servers and the HPE Synergy 480 Gen11 Compute Module are enabled with the latest PCIe 5.0 interface, enabling up to twice the performance over PCIe 4.0, and come with optionally equipped EDSFF E3.S drive bays.

As a natural evolution of the 2.5-inch form factor, EDSFF E3.S is designed for the needs of high performance flash storage. E3.S enables more dense, efficient deployments in the same rack unit compared to 2.5-inch drives, while improving cooling and thermal characteristics and raising capacities by up to 1.5 - 2x.

A strong growth in AI server shipments has driven demand for high bandwidth memory (HBM). TrendForce reports that the top three HBM suppliers in 2022 were SK hynix, Samsung, and Micron, with 50%, 40%, and 10% market share, respectively. Furthermore, the specifications of high-end AI GPUs designed for deep learning have led to HBM product iteration. To prepare for the launch of NVIDIA H100 and AMD MI300 in 2H23, all three major suppliers are planning for the mass production of HBM3 products. At present, SK hynix is the only supplier that mass produces HBM3 products, and as a result, is projected to increase its market share to 53% as more customers adopt HBM3. Samsung and Micron are expected to start mass production sometime towards the end of this year or early 2024, with HBM market shares of 38% and 9%, respectively.

AI server shipment volume expected to increase by 15.4% in 2023
NVIDIA's DM/ML AI servers are equipped with an average of four or eight high-end graphics cards and two mainstream x86 server CPUs. These servers are primarily used by top US cloud services providers such as Google, AWS, Meta, and Microsoft. TrendForce analysis indicates that the shipment volume of servers with high-end GPGPUs is expected to increase by around 9% in 2022, with approximately 80% of these shipments concentrated in eight major cloud service providers in China and the US. Looking ahead to 2023, Microsoft, Meta, Baidu, and ByteDance will launch generative AI products and services, further boosting AI server shipments. It is estimated that the shipment volume of AI servers will increase by 15.4% this year, and a 12.2% CAGR for AI server shipments is projected from 2023 to 2027.

Based on a leak courtesy of @momomo_us on Twitter, we now know that Gigabyte will be launching at least four different NVIDIA GeForce RTX 4070 based SKUs next week. Although the leaker only posted a single image of all four cards seen from the edge, it still gives us an idea of what to expect. The leaker also confirmed a rumour, that there will be two different types of GeForce RTX 4070 cards, namely those with a single 8-pin power connector and those with the 16-pin 12VHPWR PCIe 5.0 connector.

Gigabyte's four SKUs start with the Eagle and Windforce as the more budget friendly options, with the Eagle being the one we'd expect that will sell for the rumoured US$599.99 MSRP. Both of these cards obviously have the 8-pin power connector and seemingly a more basic heatsink compared to the other two cards. The higher-end models include the Gaming and Aero cards, both with 16-pin power connectors and a beefier heatsink with more heatpipes. It's unclear if we'll see a higher-end Aorus branded SKU or not at this point in time, but Gigabyte might forgo it to try to avoid making an overly expensive card that won't sell, considering that the 4070 is still largely an upper mid-range card.

ASUS today announced its participation in NVIDIA GTC, a developer conference for the era of AI and the metaverse. ASUS will offer comprehensive NVIDIA-certified server solutions that support the latest NVIDIA L4 Tensor Core GPU—which accelerates real-time video AI and generative AI—as well as the NVIDIA BlueField -3 DPU, igniting unprecedented innovation for supercomputing infrastructure. ASUS will also launch the new ProArt Studiobook Pro 16 OLED laptop with the NVIDIA RTX 3000 Ada Generation Laptop GPU for mobile creative professionals.

Purpose-built GPU servers for generative AI
Generative AI applications enable businesses to develop better products and services, and deliver original content tailored to the unique needs of customers and audiences. ASUS ESC8000 and ESC4000 are fully certified NVIDIA servers that support up to eight NVIDIA L4 Tensor Core GPUs, which deliver universal acceleration and energy efficiency for AI with up to 2.7X more generative AI performance than the previous GPU generation. ASUS ESC and RS series servers are engineered for HPC workloads, with support for the NVIDIA Bluefield-3 DPU to transform data center infrastructure, as well as NVIDIA AI Enterprise applications for streamlined AI workflows and deployment.

ADLINK Technology Inc., a global leader in edge computing, a global supplier of industrial PCs and motherboards, and a Titanium member of the Intel Partner Alliance, announces the launch of the new IMB-M47H industrial ATX motherboard for 12th/13th Gen Intel Core i9/i7/i5/i3, Pentium and Celeron processors. The IMB-M47H ATX motherboard delivers scalable, high-performance computing power and supports three simultaneous independent displays, external USB, 2.5GbE, and high-performance add-on cards for complex processing tasks in smart manufacturing, 5G manufacturing, semiconductor, and machine vision applications.

The IMB-M47H industrial ATX motherboard supports Gen 12 Intel processors and importantly the latest Intel Core processors that utilize a high-performance hybrid architecture with up to eight E-cores (Efficient-cores) for multi-threaded background task management and multitasking, and up to eight P-cores (Performance-cores) for demanding single-threaded work such as graphics and video rendering. The 12th/13th Gen Intel Core processors boost single-thread performance by 1.36x and multi-thread performance by 1.35x compared to 10th Gen Intel Core processors delivering more power-efficient general-purpose processing and offering powerful processing for intensive operations.

TYAN, an industry-leading server platform design manufacturer and a MiTAC Computing Technology Corporation subsidiary, will showcase its latest cloud server platforms powered by AMD EPYC 9004 Series processors and 4th Gen Intel Xeon Scalable processors for next-generation data centers at CloudFest 2023, Booth #H12 in Europa-Park from March 21-23.

"With the exponential advancement of technologies like AI and Machine Learning, data centers require robust hardware and infrastructure to handle complex computations while running AI workloads and processing big data," said Danny Hsu, Vice President of MiTAC Computing Technology Corporation's Server Infrastructure BU. "TYAN's cloud server platforms with storage performance and computing capability can support the ever-increasing demand for computational power and data processing."

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.