Giga Computing, a subsidiary of GIGABYTE and an industry leader in generative AI servers and advanced cooling technologies, today announced new flagship GIGABYTE G593 series servers supporting direct liquid cooling (DLC) technology to advance green data centers using NVIDIA HGX H200 GPU. As DLC technology is becoming a necessity for many data centers, GIGABYTE continues to increase its product portfolio with new DLC solutions for GPU and CPU technologies, and for these new G593 servers the cold plates are made by CoolIT Systems.

G593 Series - Tailored Cooling
The GPU-centric G593 series is custom engineered to house an 8-GPU baseboard, and its design had foresight for both air and liquid cooling. The compact 5U chassis leads the industry in its readily scalable nature, fitting up to sixty-four GPUs in a single rack and supporting 100kW of IT hardware. This helps to consolidate the IT hardware, and in turn, decrease the data center footprint. The G593 series servers for DLC are in response to the rising customer demand for greater energy efficiency. Liquids have a higher thermal conductivity than air, so they can rapidly and effectively remove heat from hot components to maintain lower operating temperatures. And by relying on water and heat exchangers, the overall energy consumption of the data center is reduced.

The MLCommons consortium on Wednesday posted MLPerf Inference v4.1 benchmark results for popular AI inferencing accelerators available in the market, across brands that include NVIDIA, AMD, and Intel. AMD's Instinct MI300X accelerators emerged competitive to NVIDIA's "Hopper" H100 series AI GPUs. AMD also used the opportunity to showcase the kind of AI inferencing performance uplifts customers can expect from its next-generation EPYC "Turin" server processors powering these MI300X machines. "Turin" features "Zen 5" CPU cores, sporting a 512-bit FPU datapath, and improved performance in AI-relevant 512-bit SIMD instruction-sets, such as AVX-512, and VNNI. The MI300X, on the other hand, banks on the strengths of its memory sub-system, FP8 data format support, and efficient KV cache management.

The MLPerf Inference v4.1 benchmark focused on the 70 billion-parameter LLaMA2-70B model. AMD's submissions included machines featuring the Instinct MI300X, powered by the current EPYC "Genoa" (Zen 4), and next-gen EPYC "Turin" (Zen 5). The GPUs are backed by AMD's ROCm open-source software stack. The benchmark evaluated inference performance using 24,576 Q&A samples from the OpenORCA dataset, with each sample containing up to 1024 input and output tokens. Two scenarios were assessed: the offline scenario, focusing on batch processing to maximize throughput in tokens per second, and the server scenario, which simulates real-time queries with strict latency limits (TTFT ≤ 2 seconds, TPOT ≤ 200 ms). This lets you see the chip's mettle in both high-throughput and low-latency queries.

In a recent report by Mercury Research, AMD has shown significant progress in the CPU market during Q2 2024, particularly in the data center and laptop segments. AMD's most notable achievement comes in the server CPU space, where it now holds 24.1% of the market, a 5.6% increase year-over-year, and a 0.5% increase from the previous quarter. This growth is particularly impressive in terms of revenue, with AMD capturing 33.7% of server CPU revenue despite its lower unit share. This suggests that AMD's high-end EPYC processors carry premium prices in the data center market and are most of the unit volume. AMD has also made advancements in the laptop CPU segment, reaching a 20.3% market share. This represents a 1% increase from the previous quarter and a 3.8% rise year-over-year. The company's success in laptops can be attributed to solid demand for its existing products, propelled by Intel's reported supply issues with Meteor Lake processors.

However, AMD experienced a slight setback in the desktop CPU market, losing a 1% share to Intel quarter-over-quarter. AMD now controls 23% of this segment, compared to Intel's 77%. This dip may be due to AMD's preparation for the launch of its new Zen 5-based CPUs in August. Despite AMD's gains, Intel maintains its overall dominance in the CPU market. In the total client PC space, Intel holds a 78.9% market share, with AMD at 21.1%. Intel still holds the majority of revenue and market share on all fronts. However, AMD is executing well, and Intel's financial troubles could be a setback for team blue. More competition at every front is great to see, and we are curious to look at the data from upcoming quarters and analyze how well both of companies perform.

Giga Computing, a subsidiary of GIGABYTE and an industry leader in generative AI servers and advanced cooling technologies, today released two GIGABYTE R-series servers (R183-ZK0 and R283-ZK0) with enhanced performance and reliability for cloud services and data-intensive applications. These highly scalable memory capacity servers support AMD EPYC 9004 processors and are ready for select 5th generation AMD EPYC processors with up to 192 CPU cores.

These new GIGABYTE servers are the first and only ones in the market that are one node with two CPUs that support 48 memory DIMMs. GIGABYTE's rich history in motherboard design and engineering with great signal integrity make this possible, a server with 12 TB memory using 256 GB DDR5 3DS RDIMMs. To accommodate a 12-memory channel platform with a 2DPC configuration and without compromising, a new memory layout was developed.

AIC, a global leader in design and manufacturing of industrial-strength servers, in partnership with Unigen Corporation has launched the EB202-CP-UG, an ultra-efficient Artificial Intelligence (AI) inference server boasting over 400 trillion operations per second (TOPS) of performance. This innovative server is designed around the robust EB202-CP, a 2U Genoa-based storage server featuring a removable storage cage. By integrating eight Unigen Biscotti E1.S AI modules in place of standard E1.S SSDs, AIC is offering a specialized configuration for AI, the EB202-CP-UG—an air-cooled AI inference server characterized by an exceptional performance-per-watt ratio that ensures long-term cost savings.

"We are excited to partner with AIC to introduce innovative AI solutions," said Paul W. Heng, Founder and CEO of Unigen. "Their commitment to excellence in every product, especially their storage servers, made it clear that our AI technology would integrate seamlessly."

MSI, a leading global server provider, is showcasing its new CXL (Compute Express Link)-based server platform powered by 4th Gen AMD EPYC processors at The Future of Memory and Storage 2024, at the Samsung booth (#407) and MemVerge booth (#1251) in the Santa Clara Convention Center from August 6-8. The CXL memory expansion server is designed to enhance In-Memory Database, Electronic Design Automation (EDA), and High Performance Computing (HPC) application performance.

"By adopting innovative CXL technology to expand memory capacity and bandwidth, MSI's CXL memory expansion server integrates cutting-edge technology from AMD EPYC processors, CXL memory devices, and advanced management software," said Danny Hsu, General Manager of Enterprise Platform Solutions. "In collaboration with key players in the CXL ecosystem, including AMD, Samsung, and MemVerge, MSI and its partners are driving CXL technology to meet the demands of high-performance data center computing."

AMD in its architecture deep-dive Q&A session with the press, confirmed that the "Zen 5" and "Zen 5c" cores on the "Strix Point" silicon only feature 256-bit wide FPU data-paths, unlike the "Zen 5" cores in the "Granite Ridge" Ryzen 9000 desktop processors. "The Zen 5c used in Strix has a 256-bit data-path, and so does the Zen 5 used inside of Strix," said Mike Clark, AMD corporate fellow and chief architecture of the "Zen" CPU cores. "So there's no delta as you move back and forth [thread migration between the Zen 5 and Zen 5c complexes] in vector throughput," he added.

It doesn't seem like AMD disabled a physically available feature, but rather, the company developed a variant of both the "Zen 5" and "Zen 5c" cores that physically lack the 512-bit data-paths. "And you get the area advantage to be able to scale out a little bit more," Clark continued. This suggests that the "Zen 5" and "Zen 5c" cores on "Strix Point" are physically smaller than the ones on the 4 nm "Eldora" 8-core CCD that is featured in "Granite Ridge" and some of the key models of the upcoming 5th Gen EPYC "Turin" server processors.

ASUS today announced an all-new range of servers, workstations and motherboards driven by the power of AMD EPYC 4004 CPUs - heralding next-level performance and density. The new offerings include: ASUS Pro ER100A B6, a compact, 1U rack server. ASUS ExpertCenter Pro ET500A B6, a power-efficient Zen 4 workstation, ASUS Pro WS 665-ACE, a resilient ATX workstation motherboard; and ASUS Pro WS 600M-CL, a compact, chipset-less mATX motherboard for workstation applications.

Engineered specifically for the dynamic needs of small businesses and hosted IT service providers, these business-grade platforms empower high-performance computing in diverse forms, from ready-to-roll workstations to powerful motherboards. Ideal for a variety of applications, from cloud services to dedicated hosting or content delivery, ASUS equipment with AMD EPYC 4004-series processors ensure that that evolving business operations are powered by the performance the modern world demands - and backed by the ASUS expertise enterprise expects.

AMD reportedly plans to incorporate glass substrates into its high-performance system-in-packages (SiPs) sometimes between 2025 and 2026. Glass substrates offer several advantages over traditional organic substrates, including superior flatness, thermal properties, and mechanical strength. These characteristics make them well-suited for advanced SiPs containing multiple chiplets, especially in data center applications where performance and durability are critical. The adoption of glass substrates aligns with the industry's broader trend towards more complex chip designs. As leading-edge process technologies become increasingly expensive and yield gains diminish, manufacturers turn to multi-chiplet designs to improve performance. AMD's current EPYC server processors already incorporate up to 13 chiplets, while its Instinct AI accelerators feature 22 pieces of silicon. A more extreme testament is Intel's Ponte Vecchio, which utilized 63 tiles in a single package.

Glass substrates could enable AMD to create even more complex designs without relying on costly interposers, potentially reducing overall production expenses. This technology could further boost the performance of AI and HPC accelerators, which are a growing market and require constant innovation. The glass substrate market is heating up, with major players like Intel, Samsung, and LG Innotek also investing heavily in this technology. Market projections suggest explosive growth, from $23 million in 2024 to $4.2 billion by 2034. Last year, Intel committed to investing up to 1.3 trillion Won (almost one billion USD) to start applying glass substrates to its processors by 2028. Everything suggests that glass substrates are the future of chip design, and we await to see first high-volume production designs.

TYAN, an industry leader in server platform design and a subsidiary of MiTAC Computing Technology Corporation, brings its latest AMD EPYC server platforms to the COMPUTEX 2024, Booth # M1120 in Taipei, Taiwan from June 4 to June 7.

"With the advanced capabilities of 4th Gen AMD EPYC Processors, TYAN's AMD EPYC server platforms deliver optimized performance for modern data centers and large-scale AI/HPC infrastructure, ensuring high energy efficiency and robust security," said Rick Hwang, President of MiTAC Computing Technology Corporation. "For the group of smaller businesses and dedicated hosters, TYAN offers AMD EPYC 4004 CPU-based servers that provide cost-effective, user-friendly solutions with enterprise-grade reliability, scalability, and security."

MSI, a leading global server provider, will introduce its latest server platforms based on the 4th Gen AMD EPYC processors at Computex 2024, booth #M0806 in Taipei, Taiwan, from June 4-7. These new platforms, designed for growing cloud-native environments, deliver a combination of performance and efficiency for data centers.

"Leveraging the advantages of 4th Gen AMD EPYC processors, MSI's latest server platforms feature scalability and flexibility with new adoption of CXL technology and DC-MHS architecture, helping data centers achieve the most scalable cloud applications while delivering leading performance," said Danny Hsu, General Manager of Enterprise Platform Solutions.

Giga Computing, a subsidiary of GIGABYTE and an industry leader in AI servers and green computing, today announced its participation in COMPUTEX and unveiling of solutions tackling complex AI workloads at scale, as well as advanced cooling infrastructure that will lead to greater energy efficiency. Additionally, to support innovations in accelerated computing and generative AI, GIGABYTE will have NVIDIA GB200 NVL72 systems available in Q1 2025. Discussions around GIGABYTE products will be held in booth #K0116 in Hall 1 at the Taipei Nangang Exhibition Center. As an NVIDIA-Certified System provider, GIGABYTE servers also support NVIDIA NIM inference microservices, part of the NVIDIA AI Enterprise software platform.

Redefining AI Servers and Future Data Centers
All new and upcoming CPU and accelerated computing technologies are being showcased at the GIGABYTE booth alongside GIGA POD, a rack-scale AI solution by GIGABYTE. The flexibility of GIGA POD is demonstrated with the latest solutions such as the NVIDIA HGX B100, NVIDIA HGX H200, NVIDIA GH200 Grace Hopper Superchip, and other OAM baseboard GPU systems. As a turnkey solution, GIGA POD is designed to support baseboard accelerators at scale with switches, networking, compute nodes, and more, including support for NVIDIA Spectrum -X to deliver powerful networking capabilities for generative AI infrastructures.

GIGABYTE Technology, Giga Computing, a subsidiary of GIGABYTE and an industry leader in AI servers, server motherboards, and workstations, today announced its support of AMD EPYC 4004 Series processors on AM5 socket servers and server motherboards for entry-level enterprise customers. This will require a BIOS update, which will come pre-installed in the near future.

The new AMD EPYC 4004 platform, built on the AM5 socket, delivers enterprise-grade features that allow small businesses and cloud services to have dependable daily operations with minimal downtime. For reliability and manageability, the platform has been validated for compatibility with server operating systems: Ubuntu, RHEL, and Windows Server. By doing so IT administrators can better control and monitor systems, as well as protect businesses against cyberthreats.

Today at Microsoft Build, AMD (NASDAQ: AMD) showcased its latest end-to-end compute and software capabilities for Microsoft customers and developers. By using AMD solutions such as AMD Instinct MI300X accelerators, ROCm open software, Ryzen AI processors and software, and Alveo MA35D media accelerators, Microsoft is able to provide a powerful suite of tools for AI-based deployments across numerous markets. The new Microsoft Azure ND MI300X virtual machines (VMs) are now generally available, giving customers like Hugging Face, access to impressive performance and efficiency for their most demanding AI workloads.

"The AMD Instinct MI300X and ROCm software stack is powering the Azure OpenAI Chat GPT 3.5 and 4 services, which are some of the world's most demanding AI workloads," said Victor Peng, president, AMD. "With the general availability of the new VMs from Azure, AI customers have broader access to MI300X to deliver high-performance and efficient solutions for AI applications."

Today, TYAN, a leading server platform design manufacturer and a MiTAC Computing Technology Corporation subsidiary, introduced its latest offering: affordable and high-performance servers and motherboards powered by the new AMD EPYC 4004 Series CPUs. "The new AMD EPYC 4004 Series CPUs, along with our strong ecosystem of technology partners, bring enterprise solutions to a traditionally underserved market and ensure that small and medium businesses have access to highly-performant technologies that help them stay competitive," said John Morris, corporate vice president, Enterprise and HPC Business Group, AMD. "The AMD EPYC 4004 CPUs fill an important market gap, providing cost-optimized solutions with enterprise-grade dependability, scalability and security in cost-optimized system configurations that make sense for smaller businesses and dedicated hosters."

AMD EPYC 4004 Series processors complement the broad AMD EPYC processor offering, extending the established high performance, highly efficient "Zen4" core architecture into an expanded range of entry level system designs desired by small business customers as well as regional hosted IT services providers. With new low core count CPU offerings and TDP ranges as low as 65 W, attractively priced server systems featuring AMD EPYC 4004 Processors deliver the strong performance, scalability and dependability needed by growing businesses and 24x7 hosted services. With an optimized, single-socket package, 2 channels of DDR5 memory and up to 28 lanes of Gen 5 PCIe connectivity, these servers offer a compelling balance of performance and scalability in an affordable, easy-to-deploy, easy-to-manage package.

Supermicro, Inc., a Total IT Solution Provider for AI, Cloud, Storage, and 5G/Edge, is announcing additions to the AMD based H13 generation of CPU Servers, optimized to deliver an outstanding balance of performance and efficiency and powered by the AMD EPYC 4004 Series processors. Supermicro will feature its new MicroCloud multi-node solution, which supports up to ten nodes in a 3U form factor. This very high-density option is designed for cloud-native workloads.

"Supermicro continues to offer innovative solutions for a wide range of applications, and with this new entry, based on the AMD EPYC 4004 processor, we can address the needs of on-premises or cloud service providers who need a cost-effective solution in a compact form factor," said Charles Liang, president and CEO of Supermicro. "In a single rack, 160 individual nodes can be made available for cloud-native applications, which reduces real estate need and decreases a data center TCO."

MSI, a leading global server provider, today announced the availability of high-performance server platforms supporting AMD EPYC 4004 Processors for small and medium businesses and regional-hosted IT service providers to deliver essential security capabilities and energy efficiency. "Businesses across all scales are discovering the advantages of advanced computing, connectivity, and analytics capabilities as applications and services become more widespread," said Danny Hsu, General Manager of Enterprise Platform Solutions. "MSI server platforms, supporting AMD EPYC 4004 Processors, empower our customers to implement high-performance computing with cost-effective, ease of deployment, and manageability features. This capability addresses challenges such as system costs, limited IT expertise, and other infrastructure constraints that were previously prohibitive."

"The new AMD EPYC 4004 Series CPUs, along with our strong ecosystem of technology partners, bring enterprise solutions to a traditionally underserved market and ensure that small and medium businesses have access to highly-performant technologies that help them stay competitive," said John Morris, corporate vice president, Enterprise and HPC Business Group, AMD. "The AMD EPYC 4004 CPUs fill an important market gap, providing cost-optimized solutions with enterprise-grade dependability, scalability and security in cost-optimized system configurations that make sense for smaller businesses and dedicated hosters."

AMD today introduced the EPYC 4004 line of server processors in the Socket AM5 package. These chips come with up to 16 "Zen 4" CPU cores, a 2-channel DDR5 memory interface, and a 28-lane PCIe Gen 5 I/O, and are meant to power small-business servers, as well as cater to the dedicated web-server hosting business that generally attracts client-segment processors. This is the exact segment of market that Intel addresses with its Xeon E-2400 series processors in the LGA1700 package. The EPYC 4004 series offers a superior support and warranty regime compared to client-segment processors, besides ECC memory support, and AMD Secure Processor, and all of the security features you get with Ryzen PRO 7000 series processors for commercial desktops.

AMD's offer over the Xeon E-2400 series is its CPU core count of up to 16, which lets you fully utilize the 16-core limit of the Windows 2022 Server base license. The EPYC 4004 series is functionally the same processor as the Ryzen 7000 "Raphael" except for its ECC memory support. This chip features up to two 5 nm "Zen 4" CCDs with up to 8 cores, each; and an I/O die that puts out two DDR5 memory channels, and 28 PCIe Gen 5 lanes. Besides today's processor launch, several server motherboard vendors are announcing Socket AM5 server boards that are rackmount-friendly, and with server-relevant features.

The 63rd edition of the TOP500 reveals that Frontier has once again claimed the top spot, despite no longer being the only exascale machine on the list. Additionally, a new system has found its way into the Top 10.

The Frontier system at Oak Ridge National Laboratory in Tennessee, USA remains the most powerful system on the list with an HPL score of 1.206 EFlop/s. The system has a total of 8,699,904 combined CPU and GPU cores, an HPE Cray EX architecture that combines 3rd Gen AMD EPYC CPUs optimized for HPC and AI with AMD Instinct MI250X accelerators, and it relies on Cray's Slingshot 11 network for data transfer. On top of that, this machine has an impressive power efficiency rating of 52.93 GFlops/Watt - putting Frontier at the No. 13 spot on the GREEN500.

AMD has reached a significant milestone, capturing a record-high share of the X86 CPU market in the first quarter of 2024, according to the latest report from Mercury Research. This achievement marks a significant step forward for the chipmaker in its long battle against rival Intel's dominance in the crucial computer processor space. The surge was fueled by strong demand for AMD's Ryzen and EPYC processors across consumer and enterprise markets. The Ryzen lineup's compelling price-to-performance ratio has struck a chord with gamers, content creators, and businesses seeking cost-effective computing power without sacrificing capabilities. It secured AMD's 23.9% share, an increase from the previous Q4 of 2023, which has seen a 19.8% market share.

The company has also made major inroads on the data center front with its EPYC server CPUs. AMD's ability to supply capable yet affordable processors has enabled cloud providers and enterprises to scale operations on AMD's platform. Several leading tech giants have embraced EPYC, contributing to AMD's surging server market footprint. Now, it is at 23.6%, a significant increase over the past few years, whereas AMD was just above 10% four years ago in 2020. AMD lost some share to Intel on the mobile PC front due to the Meteor Lake ramp, but it managed to gain a small percentage of the market share of client PCs. As AMD rides the momentum into the second half of 2024, all eyes will be on whether the chipmaker can sustain this trajectory and potentially claim an even larger slice of the x86 CPU pie from Intel in the coming quarters.Below, you can see additional graphs of mobile PC and client PC market share.

Micron Technology, Inc. (Nasdaq: MU), today announced it is leading the industry by validating and shipping its high-capacity monolithic 32Gb DRAM die-based 128 GB DDR5 RDIMM memory in speeds up to 5,600 MT/s on all leading server platforms. Powered by Micron's industry-leading 1β (1-beta) technology, the 128 GB DDR5 RDIMM memory delivers more than 45% improved bit density, up to 22% improved energy efficiency and up to 16% lower latency over competitive 3DS through-silicon via (TSV) products.

Micron's collaboration with industry leaders and customers has yielded broad adoption of these new high-performance, large-capacity modules across high-volume server CPUs. These high-speed memory modules were engineered to meet the performance needs of a wide range of mission-critical applications in data centers, including artificial intelligence (AI) and machine learning (ML), high-performance computing (HPC), in-memory databases (IMDBs) and efficient processing for multithreaded, multicore count general compute workloads. Micron's 128 GB DDR5 RDIMM memory will be supported by a robust ecosystem including AMD, Hewlett Packard Enterprise (HPE), Intel, Supermicro, along with many others.

AMD is readying a new line of EPYC branded server processors in the Socket AM5 package, VideoCardz reports. The new processor lineup is being built to target two distinct classes of customers—small business servers, and data-centers selling small-size dedicated servers that were otherwise having to offer Ryzen chips. Intel currently has the Xeon E-2400 series "Raptor Lake-E" processors in the Socket LGA1700 package to target these exact kinds of customers. The EPYC 4004 series will be based on the same "Raphael" package as the Ryzen 7000 series, and will be a step up from the Ryzen PRO 7000 series. What sets the Ryzen PRO 7000 apart from the EPYC 4004 series are the target markets. The Ryzen PRO series target commercial desktops. Perhaps the biggest differentiator between EPYC 4004 and Ryzen PRO 7000 series is the support and warranty AMD provides to its server processors.

The "Raphael" package gives the EPYC 4004 series CPU core counts ranging between 6 and 16. These CPU cores are based on the "Zen 4" microarchitecture. The memory controllers in the I/O die will probably be reconfigured to support server memory densities, besides ECC support like on the Ryzen PRO 7000 series. There's even talk of variants with 3D V-cache, although it remains to be seen if the 12-core and 16-core variants are similar to the 7900X3D and 7950X3D, where only one of the two CCDs has 3D V-cache; or if they're the chip we all dreamed about—a "Raphael" with both CCDs featuring 3D V-cache. There are already Socket AM5 motherboards by companies such as Advantech, which are server-grade, with server-relevant I/O, like the one pictured below, and so the ecosystem for EPYC 4004 series already exists, along with upgrade headroom for future generations.

MSI, a leading global server provider, is showcasing its latest GPU servers powered by AMD processors at the 2024 NAB Show, Booth #SL9137 in the Las Vegas Convention Center from April 14-17. These servers are designed to meet the evolving needs of modern creative projects in Media and Entertainment industry. "As AI continues to reshape the Media and Entertainment industry, it brings unprecedented speed and performance to tasks such as animation, visual effects, video editing, and rendering," said Danny Hsu, General Manager of Enterprise Platform Solutions. "MSI's GPU platforms empower content creators to execute every project with efficiency, speed, and uncompromising quality."

The G4101 is a 4U 4GPU server platform, purpose-built to unleash the full potential of creative professionals in the Media and Entertainment industry. It supports a single AMD EPYC 9004 Series processor equipped with a liquid cooling module, along with twelve DDR5 RDIMM slots. Additionally, it features four PCIe 5.0 x16 slots tailored for triple-slot graphic cards with coolers, ensuring increased airflow and sustained performance. With twelve front 2.5-inch U.2 NVMe/SATA drive bays, it offers high-speed and flexible storage options, catering to the diverse needs of AI workloads. The G4101 combines air flow spacing and liquid closed-loop cooling, making it the optimal thermal management solution for even the most demanding tasks.

AMD's next-gen EPYC Zen 5 processor family seems to be nearing launch status—late last week, momomo_us uncovered an unnamed motherboard's datasheet; this particular model will accommodate a single 9000-series CPU—with a maximum 400 W TDP—via an SP5 socket. 500 W and 600 W limits have been divulged (via leaks) in the past, so the 400 W spec could be an error or a: "legitimate compatibility issue with the motherboard, though 400 Watts would be in character with high-end Zen 4 SP5 motherboards," according to Tom's Hardware analysis.

AMD's current-gen "Zen 4" based EPYC "Genoa" processor family—sporting up to 96-cores/192-threads—is somewhat limited by its DDR5 support transfer rates of up to 4800 MT/s. The latest leak suggests that "Turin" is upgraded quite nicely in this area—when compared to predecessors—the SP5 board specs indicate DDR5 speeds of up to 6000 MT/s with 4 TB of RAM. December 2023 reports pointed to "Zen 5c" variants featuring (max.) 192-core/384-thread configurations, while larger "Zen 5" models are believed to be "modestly" specced with up to 128-cores and 256-threads. AMD has not settled on an official release date for its EPYC "Turin" 9000-series processors, but a loose launch window is expected "later in 2024" based on timeframes presented within product roadmaps.

On February 26, 2024, AMD received new research related to an industry-wide DRAM issue documented in "ZENHAMMER: Rowhammering Attacks on AMD Zen-based Platforms" from researchers at ETH Zurich. The research demonstrates performing Rowhammer attacks on DDR4 and DDR5 memory using AMD "Zen" platforms. Given the history around Rowhammer, the researchers do not consider these rowhammering attacks to be a new issue.

Mitigation
AMD continues to assess the researchers' claim of demonstrating Rowhammer bit flips on a DDR5 device for the first time. AMD will provide an update upon completion of its assessment.