AMD today released the latest version of the AMD Software Adrenalin drivers. Version 23.9.3 WHQL comes with optimization for "Cyberpunk 2077: Phantom Liberty," and "PAYDAY 3." The drivers also add optimization for generative AI tools MeanVarianceNormalization (MVN) and Stable Diffusion variants. With this release, the company didn't include any fixes, but identified a handful new issues.

Adrenalin 23.9.3 WHQL, along with its preceding 23.9.2 WHQL, see AMD release separate installers for RDNA-only and RDNA + pre-RDNA GPUs, both with the same release notes. The RDNA release supports only Radeon RX 5000 series, RX 6000 series, and RX 7000 series; while the RDNA + pre-RDNA combo release is meant for Radeon RX Vega series, RX 500 series, and RX 400 series (Polaris) on top of the RX 5000 (or later) GPUs. The RDNA-only release is 640 MB in size, while the RDNA + pre-RDNA combo package is 1.2 GB.

DOWNLOAD: AMD Software Adrenalin 23.9.3 WHQL (RX 5000 and later) | AMD Software Adrenalin 23.9.3 (RX Vega and older)

TSMC today announced the new 3Dblox 2.0 open standard and major achievements of its Open Innovation Platform (OIP) 3DFabric Alliance at the TSMC 2023 OIP Ecosystem Forum. The 3Dblox 2.0 features early 3D IC design capability that aims to significantly boost design efficiency, while the 3DFabric Alliance continues to drive memory, substrate, testing, manufacturing, and packaging integration. TSMC continues to push the envelope of 3D IC innovation, making its comprehensive 3D silicon stacking and advanced packaging technologies more accessible to every customer.

"As the industry shifted toward embracing 3D IC and system-level innovation, the need for industry-wide collaboration has become even more essential than it was when we launched OIP 15 years ago," said Dr. L.C. Lu, TSMC fellow and vice president of Design and Technology Platform. "As our sustained collaboration with OIP ecosystem partners continues to flourish, we're enabling customers to harness TSMC's leading process and 3DFabric technologies to reach an entirely new level of performance and power efficiency for the next-generation artificial intelligence (AI), high-performance computing (HPC), and mobile applications."

AMD today announced the AMD Alveo UL3524 accelerator card, a new fintech accelerator designed for ultra-low latency electronic trading applications. Already deployed by leading trading firms and enabling multiple solution partner offerings, the Alveo UL3524 provides proprietary traders, market makers, hedge funds, brokerages, and exchanges with a state-of-the-art FPGA platform for electronic trading at nanosecond (ns) speed.

The Alveo UL3524 delivers a 7X latency improvement over prior generation FPGA technology, achieving less than 3ns FPGA transceiver latency for accelerated trade execution. Powered by a custom 16 nm Virtex UltraScale + FPGA, it features a novel transceiver architecture with hardened, optimized network connectivity cores to achieve breakthrough performance. By combining hardware flexibility with ultra-low latency networking on a production platform, the Alveo UL3524 enables faster design closure and deployment compared to traditional FPGA alternatives.

GIGABYTE Technology, Giga Computing, a subsidiary of GIGABYTE and an industry leader in high-performance servers, server motherboards, and workstations, today announced ahead of exhibiting at the OCP Global Summit new OCP ORv3 based solutions, including ones designed for GPU centric workloads in immersion cooling. The new GIGABYTE products include a 2OU node tray, TO25-BT0, and compute nodes: TO25-S10, TO25-S11, TO25-S12, TO25-Z10, TO25-Z11, and TO25-Z12. For immersion cooling server deployments with ORv3 specifications are the new GPU servers: TO15-S40, TO15-S41, and TO15-Z40.

Our commitment to support Open Compute Project's designs dates back almost a decade starting with our OCP v1.0 products, and now we are releasing some well-designed, in demand ORv3 products. Through discussions with several customers, we decided to move forward with the development of these configurations. These designs check the boxes for specifications that are required," said Vincent Wang, Sales VP at Giga Computing. "We will continue supporting ORv3 specifications and we have more products on the horizon in Q1 2024.

CORSAIR, a world leader in enthusiast components for gamers, creators, and PC builders, today launched the much anticipated latest addition to its award-winning memory line-up, DOMINATOR TITANIUM DDR5 memory. Built using some of the fastest DDR5 ICs alongside patented CORSAIR DHX cooling technology for improved overclocking potential, DOMINATOR TITANIUM continues the DOMINATOR legacy with a stunning design and blazing performance.

Sporting an elegant, fresh new aesthetic and built using premium materials and components, DOMINATOR TITANIUM DDR5 memory will be available for both Intel and AMD platforms, supporting Intel XMP 3.0 when paired with 12th and 13th-Gen Core processors or AMD EXPO for Ryzen 7000 CPUs. These technologies enable easy overclocking in just a couple of clicks on compatible platforms.

The burgeoning AI market is significantly impacting TSMC's CoWoS (Chip on Wafer on Substrate) advanced packaging production capacity, causing it to overflow due to high demand from major companies like NVIDIA, AMD, and Amazon. To accommodate this, TSMC is in the process of expanding its production capacity by acquiring additional CoWoS machines from equipment manufacturers like Xinyun, Wanrun, Hongsu, Titanium, and Qunyi. These expansions are expected to be operational in the first half of the next year, leading to an increased monthly production capacity, potentially close to 30,000 pieces, enabling TSMC to cater to more AI-related orders. These endeavors to increase capacity are in response to the amplified demand for AI chips from their applications in various domains, including autonomous vehicles and smart factories.

Despite TSMC's active steps to enlarge its CoWoS advanced packaging production, the overwhelming client demand is driving the company to place additional orders with equipment suppliers. It has been indicated that NVIDIA is currently TSMC's largest CoWoS advanced packaging customer, accounting for 60% of its production capacity. Due to the surge in demand, companies like AMD, Amazon, and Broadcom are also placing urgent orders, leading to a substantial increase in TSMC's advanced process capacity utilization. The overall situation indicates a thriving scenario for equipment manufacturers with clear visibility of orders extending into the following year, even as they navigate the challenges of fulfilling the rapidly growing and immediate demand in the AI market.

Scott Herkelman, Senior Vice President and General Manager of AMD's Graphics Business Unit, has announced that he will be leaving AMD at the end of this year. As noted in his Twitter post, he spent last seven years at AMD, and launches three generations of RDNA graphics architectures. Scott Herkelman is a veteran of the industry, and was General Manager for GeForce at NVIDIA back in the day. After briefly switching to a start-up, he then joined AMD back in 2016 as Vice President and General Manager of Graphics Business Unit, the role he held for seven years while becoming Senior Vice President in 2022.

Scott said farewell to his colleagues in a brief Twitter post, and we are are certainly looking forward to see where he will be going next, as Scott is a PC and a gaming industry fan, through and through. Meanwhile, as spotted by Videocardz.com and according to AMD's own website, Jack Huynh will take over at the Senior Vice President and General Manager of AMD's Graphics Business Unit.

UPDATE: As pointed out by some comments and a couple of readers, Jack Huynh will not replace Scott Herkelman. Jack Huynh replaced Rick Bergman back in April as Senior Vice President and General Manager of AMD's Graphics Business Unit.

Samsung Electronics today announced a new collaboration with AMD to advance 5G virtualized RAN (vRAN) for network transformation. This collaboration represents Samsung's ongoing commitment to enriching vRAN and Open RAN ecosystems to help operators build and modernize mobile networks with unmatched flexibility and optimized performance. The two companies have completed several rounds of tests at Samsung's lab to verify high-capacity and telco-grade performance using FDD bands and TDD Massive MIMO wide-bands, while significantly reducing power consumption. In this joint collaboration, Samsung used its versatile vRAN software integrated with the new AMD EPYC 8004 processors, focused on telco and intelligent edge. During technical verification, the EPYC 8004 processors combined with Samsung's vRAN solutions delivered optimized cell capacity per server as well as high power efficiency.

"This technical collaboration demonstrates Samsung's commitment to delivering network flexibility and high performance for service providers by building a larger vRAN and Open RAN ecosystem," said Henrik Jansson, Vice President and Head of SI Business Group, Networks Business at Samsung Electronics. "Samsung has been at the forefront of unleashing the full potential of 5G vRAN technology to meet rising demands, and we look forward to collaborating with industry leaders like AMD to provide operators the capabilities to transform their networks."

Fueled by an AI-driven inventory stocking frenzy across the supply chain, TrendForce reveals that Q2 revenue for the top 10 global IC design powerhouses soared to US $38.1 billion, marking a 12.5% quarterly increase. In this rising tide, NVIDIA seized the crown, officially dethroning Qualcomm as the world's premier IC design house, while the remainder of the leaderboard remained stable.

AI charges ahead, buoying IC design performance amid a seasonal stocking slump
NVIDIA is reaping the rewards of a global transformation. Bolstered by the global demand from CSPs, internet behemoths, and enterprises diving into generative AI and large language models, NVIDIA's data center revenue skyrocketed by a whopping 105%. A deluge of shipments, including the likes of their advanced Hopper and Ampere architecture HGX systems and the high-performing InfinBand, played a pivotal role. Beyond that, both gaming and professional visualization sectors thrived under the allure of fresh product launches. Clocking a Q2 revenue of US$11.33 billion (a 68.3% surge), NVIDIA has vaulted over both Qualcomm and Broadcom to seize the IC design throne.

Techtesters, a Dutch online publication and YouTube channel, took the time to investigate whether AMD's Radeon RX 7800 XT 16 GB GPU can compete with NVIDIA's GeForce RTX 4070 12 GB GPU in power efficiency stakes. Naturally, Team Red loses with their new mid-ranger running under normal conditions when lined up against its main rival - ranging from 252 W to 286 W versus 200 W (sometimes 196 W during gaming sessions) respectively. Nada Overbeeke (of Techtesters) chose to set a 90% power limit for their main subject matter—Gigabyte's custom design Navi 32-based Gaming OC model—through AMD software adjustments.

Its "aggressive" 200 W undervolted state was compared to stock performance in a number of modern game environments (refer to the charts below). The Gigabyte RX 7800 XT Gaming OC—using stock settings—consumed around 40% more power while managing only a 9% performance increase over its 200 W undervolted guise. VideoCardz notes that AMD's reference model requires 24% more power at stock: "As mentioned, a 9% performance boost should not be underestimated, but the substantial reduction in power consumption also resulted in quieter GPU operation and lower temperatures." It would have been interesting to see Techtesters undervolt their RTX 4070 FE candidate as well, but emphasis seemed to be placed on the newer card.

With the XMG CORE 16, XMG's CORE series gets a new 16-inch model, whose features are based on the current top models of the NEO seri
es in many details. Powered by AMD's Ryzen 7 7840HS and an NVIDIA GeForce RTX 4070 or 4060, the laptop is aimed at the upper mid-range, but also adds features from the premium segment. These include, for example, an optional keyboard with CHERRY MX Ultra Low Profile Tactile switches, a 99 Wh battery and a liquid metal thermal compound for cooling the processor and graphics card. For the first time, there is also a configuration option for up to 96 GB DDR5 RAM.

The XMG CORE 16 (L23) is the first laptop in the CORE series to come in a 16-inch format and, alongside the APEX 15 and APEX 17, is now the third model to be based on an AMD Phoenix CPU featuring the Ryzen 7 7840HS with 8 cores and 16 threads. XMG offers the laptop with either an NVIDIA GeForce RTX 4070 or an RTX 4060, each with a graphics power of 140 watts (115 watts plus 25 watts Dynamic Boost). A composite cooling system with four heat pipes, separate heat sinks on all four air outlets and liquid metal for improved heat transfer from both the CPU and GPU is utilised to provide high continuous performance.

AMD has updated its Radeon Adrenalin driver with the latest edition, 23.9.2. The newest version brings unified driver support for AMD Radeon RX 7700 and RX 7800, which the previous driver lacked, and there was a separate download for these two SKUs. Besides merging into a single unified driver, the new update brings Lies of P, Party Animals, and The Crew Motorfest game support for AMD Radeon graphics. In this driver release, the AMD Radeon Anti-Lag+ feature is introduced for Starfield, Witcher 3, ELDEN RING, Immortals of Aveum, and an Anti-Lag+ screen overlay for system latency. AMD fixed some issues like application crashing while playing Baldur Gate 3 with Vulkan API on RX 7900 XTX, limited GPU clock tuning on RX 7700 XT and RX 7800 XT, application crash while playing SMITE on RX 7900 XTX, and application crash or driver timeout while playing F1 2023 on RX 7800 XT. There is no Cyberpunk 2077 update yet in this driver release.

You can download the Radeon Adrenalin Edition 23.9.2 Driver here.See the full list of changes below:

Thermaltake, the leading PC DIY premium brand for Case, Power, Cooling, Gaming peripherals, and enthusiast Memory solutions, is pleased to unveil the Pacific SW1 Plus CPU Water Block and the Pacific SF Fittings - Silver Black. The custom liquid cooling system provides considerable flexibility in design, allowing you to demonstrate your aesthetic sense. If you are an industrial chic enthusiast, the Pacific SW1 Plus and the Pacific SF Fittings, which feature a New Industrial Style, are the ideal components for leveling up your cooling system's appearance while ensuring thermal performance and installation compatibility.

Pacific SW1 Plus CPU Water Block
Designed with a modern industrial style, the Pacific SW1 Plus CPU Water Block comes in solid aluminium alloy with a screw design, displaying a beautiful glow of metals. The copper base is finished with anti-corrosive nickel plating, matching the overall industrial design and offering an outstanding heat transfer for the CPU. The central inlet design of the base enables the coolant to be distributed evenly through the 0.2 mm microchannels, achieving more effective heat dissipation. What's more, through the TT RGB Plus 2.0 software, you can simply monitor coolant temperature and customize the lighting effects of the water block's 12 addressable LEDs. To fit the latest CPUs, the Pacific SW1 Plus is also compatible with Intel LGA 1700 and AMD AM5 sockets and can be installed without additional brackets.

Intel CEO Pat Gelsinger, in the Q&A session of InnovatiON 2023 Day 1, confirmed that the company is developing 3D-stacked cache technology for its processors. The technology involves expanding the on-die last-level cache (L3 cache) of a processor with an additional SRAM die physically stacked on top, and bonded with the cache's high-bandwidth data fabric. The stacked cache operates at the same speed as the on-die cache, and so the combined cache size is visible to software as a single contiguous addressable block of cache memory.

AMD has used 3D-stacked cache to good effect on its processors. On client processors such as the Ryzen X3D series, the cache provides significant gaming performance uplifts as the larger L3 cache makes more of the game's rendering data immediately accessible to the CPU cores; while on server processors such as EPYC "Milan-X" and "Genoa-X," the added cache provides significant uplifts to memory intensive compute workloads. Intel's approach to 3D-stacked cache will be different at the hardware level compared to AMD's, Gelsinger stated in his response. AMD's tech has been collaboratively developed with TSMC, and hinges on a TSMC-made SoIC packaging tech that facilitates high-density die-to-die wiring between the CCD and cache chiplet. Intel uses its own fabs for processor dies, and will have to use its own IP.

AMD today announced AMD Kria K24 System-on-Module (SOM) and KD240 Drives Starter Kit, the latest additions to the Kria portfolio of adaptive SOMs and developer kits. AMD Kria K24 SOM offers power-efficient compute in a small form factor and targets cost-sensitive industrial and commercial edge applications. Advanced InFO (Integrated Fan-Out) packaging makes the K24 half the size of a credit card while using half the power of the larger, connector-compatible Kria K26 SOM.

The K24 SOM provides high determinism and low latency for powering electric drives and motor controllers used in compute-intensive digital signal processing (DSP) applications at the edge. Key applications include electric motor systems, robotics for factory automation, power generation, public transportation such as elevators and trains, surgical robotics and medical equipment like MRI beds, and EV charging stations. Coupled with the KD240 Drives Starter Kit, an out-of-the-box-ready motor control-based development platform, the products offer a seamless path to production deployment with the K24 SOM. Users can quickly be up and running, speeding time to market for motor control and DSP applications without requiring FPGA programming expertise.

EK, the industry-leading manufacturer of premium liquid cooling solutions, proudly announces another addition to its Pro line - the EK-Pro CPU WB sTR, an enterprise-grade water block meticulously designed for AMD EPYC and Ryzen Threadripper processors. Engineered with precision and expertise, this liquid cooling solution promises unmatched performance and reliability.

Precision Craftsmanship
EK-Pro CPU WB sTR - Nickel + Acetal water block is custom-designed for AMD processors, making it suitable for desktop PCs, workstations, and taller server racks. With three standard G1/4" threaded ports on the top and an EK G1/4 plug equipped with an O-ring, this water block ensures effortless and secure connections for your liquid cooling system.

A trio of allegedly official presentation slides appeared on X yesterday, posted by Underfox3—the leaker stopped short of revealing the origin of this material. They simply commented: "AMD Threadripper Pro is coming...🔥." The next generation HEDT processor family is expected to arrive in the fall, and the opening slide pretty much confirms this launch window (starting September 22—autumnal equinox). There has been a noticeable uptick in Zen 4 "Storm Peak" 7000-series pre-release units appearing online lately—so the timing seems plausible. Text segments do not mention the 7000-series in specifics, but an IHS render visible on the second slide looks somewhat similar—in shape—to a grey market-listed Threadripper Pro 7985WX. VideoCardz has compiled various leaked SKUs into a chart (see below).

A very general claim is made on the second slide—boasting a 20% performance increase over their Threadripper Pro 5000 series—but detailed information (prowess in single or multi-core tests) or in-depth benchmark results are not included. VideoCardz surmises from an interpretation of the third slide—noting: "support for 96 cores, marking a 50% boost over the TR PRO 5000 series. This suggests that the 20% improvement likely pertains to the single-core Zen 4 boost." The final slide also shows said 96-core Threadripper Pro processor tipped against Intel's Xeon W9-3495X CPU (a 56-core Sapphire Rapids candidate)—the former is said to produce 75% more renders per day. Per frame completion time is 657 second versus 1125 seconds (respectively).

ASUS today announced ASUS S14NA-U12, its latest server motherboard, and designed to harness the power of the latest AMD EPYC 8004-series processors. This motherboard is engineered to deliver robust performance and energy efficiency for single-socket servers, both within and beyond the confines of traditional data centers.

Cost-efficient solutions
ASUS recognizes the paramount importance of cost-efficiency in the business realm. The all-new ASUS S14NA-U12 server motherboard leverages the impressive performance and streamlined platform componentry of EPYC 8004-series processors, enabling original equipment manufacturers (OEMs) to offer cost-effective, business-relevant server configurations. The adherence to industry standards in platform management, coupled with top-tier security features and energy efficiency of the EPYC 8004-series processors, significantly reduces operational costs compared to power-hungry, non-standard alternatives. Customers can expect best-in-class total cost of ownership (TCO) across numerous deployments with systems based on AMD EPYC 8004-series processors.

ASRock Rack, the leading innovative server company, today announced its latest server motherboard lineup now supports the AMD EPYC 8004 Series processors which extend the 4th Gen EPYC Family into new markets.

The AMD EPYC 8004 Series processors bring the benefits of the "Zen 4c" processor core to markets that seek strong performance but also have significant requirements for efficient, dense form factors, limited available power, and quieter operations. "AMD EPYC 8004 Processors are purpose-built to deliver strong performance and energy efficiency in an optimized, single-socket package," said Lynn Comp, corporate vice president, Server Product and Technology Marketing, AMD. "The combination of impressive performance and streamlined platform componentry of the EPYC 8004 Series CPUs means system builders can offer their customers cost-efficient business-relevant configurations."

GIGABYTE Technology: Giga Computing, a subsidiary of GIGABYTE and an industry leader in high-performance servers, server motherboards, and workstations, today announced new GIGABYTE enterprise series solutions for the AMD EPYC 8004 Series processors. Giga Computing is committed to reaching all sizes of data centers to deliver the best compelling solution, and now is doing so with new AMD EPYC 8004 CPUs that target edge applications, CSPs, and value enterprises. For these uses, the new R243 and R143 server series are poised alongside ME33 and ME03 motherboard series to deliver cost-optimized performance.

Leveraging the "Zen 4c" core architecture, the AMD EPYC 8004 Series CPUs deliver performance and power efficiency with built-in security capabilities in an optimized single-socket platform. Additionally, the new SP6 socket was designed to enable the power, cost, and form factor requirements for the AMD EPYC 8004 Series CPUs' target markets as well as diverse applications such as intelligent edge computing and telco.

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."

AMD today rolled out the new compacted Socket SP6 server platform designed for smaller servers locally deployed at the edge by organizations. With CPU core-counts of up to 64-core/128-thread, these processors are based on the "Zen 4c" microarchitecture, which comes with identical IPC and ISA to "Zen 4," but with smaller L3 cache available per core. The EPYC 8004 series targets traditional data-centers located on-site for organizations. Even if the heavy-lifting of the IT for them is performed by remote data-centers or cloud providers, organizations still need smaller edge server deployments. The EPYC 8004 series caters to a different kind of servers than the ones the lower core-count models of EPYC 9004 "Genoa" do.

With the EPYC 8004 series, AMD is debuting a new smaller CPU socket called SP6. The socket measures 58.5 mm x 75.4 mm, compared to the 76.0 mm x 80.0 mm of Socket SP5 powering EPYC 9004 "Genoa" and EPYC 97x4 "Bergamo." Socket SP5 is an LGA with a pin count of 4,844, compared to SP5, which is LGA-6096. The first line of processors for this socket, the EPYC 8004 series, are codenamed "Siena." These are very much part of the 4th Gen EPYC series, a lineage it shares with "Genoa" for data-center servers, "Genoa-X" for compute servers, and "Bergamo" for high-density cloud.

A pair of Dell Precision workstations have been tested in SiSoftware's Sandra benchmark suite—database entries for the 7875 Tower (Dell 00RP38) and 7875 Tower (Dell 00RP38) reveal specifications of next generation AMD Ryzen Threadripper Pro CPUs. The 32 core 7975WX model was outed a couple of weeks ago, but the Sandra benchmark database has been updated with additional scores. Its newly leaked sibling is getting a lot of attention—the recently benchmarked 7995WX sample appears to possess 96 Zen 4 cores, and 192 threads (via SMT) with a 5.14 GHz maximum single-core boost clock. Tom's Hardware is intrigued by benchmark data showing that the CPU has: "a 3.2 GHz all-core turbo frequency."

There are 12 CCDs onboard, with a combined total of 384 MB of L3 cache (each CCD has access to 32 MB of L3)—therefore Wccftech believes that "this chip is based on the Genoa SP5 die and will adopt the top 8-channel and SP5 socket platform. The chip also features 96 MB of L2 cache and the top clock speed was reported at 5.14 GHz." The repeat benched Ryzen Threadripper Pro 7975WX CPU is slightly less exciting—with 32 Zen 4 cores, 64 threads, 128 MB of L3 cache, and 32 MB of L2 cache. According to older information, this model is believed to have a TDP rating of 350 W and apparent clock speeds peaking at 4.0 GHz—Wccftech reckons that this frequency reflects an all-core boost. They have produced a bunch of comparative performance charts and further analysis—well worth checking out.

AMD has updated its third generation EPYC 7003 server-grade CPU lineup with six additional SKUs—new product pages were discovered and disclosed by momomo_us—yesterday's social media post reveals that these Zen 3 chips were launched with zero fanfare on September 5. Team Red did reveal, back in July, that: "SAP has chosen AMD EPYC processor-powered Google Cloud N2D virtual machines," but no new products were alluded to at the time. The fresh-ish sextet is comprised of EPYC 7663P, 7643P, 7303P, 7303, 7203P, and 7203 models. Evidently there seems to be some demand out there for 2021 processor technology, and AMD has acted on client feedback.

These appear to be wallet friendly options—perhaps targeting a customer base that cannot stretch their budget to fourth generation EPYC 9004 "Genoa" options. Tom's Hardware observed: "The EPYC 7663P and EPYC 7643P are fundamentally the single-socket versions of the EPYC 7663 and EPYC 7643, retaining the exact specifications. The bright side is that EPYC 7663P and EPYC 7643P have MSRPs around half of their regular counterparts. The SKUs represent a significant saving for companies with no plans to use a dual-socket configuration." Team Red has dipped back into Zen 3 a couple of times this year—at the mainstream desktop/gaming level. The EPYC 7003 series received a 3D V-Cache refresh last year, going under the "Milan-X" moniker—but the fancier tech added a fair chunk to MSRP.