Lenovo started offering the Ryzen 9 7900 and Ryzen 7 7700 processors as options for its prebuilt desktops, confirming that the 7900 and 7700 will be OEM-exclusives, at least initially. That doesn't mean these chips won't make it to the retail channel, as OEM-only parts from AMD in the past have somehow found their way to retailers, who bought them in trays, and sold them piecemeal as combos with motherboards and CPU coolers. The 7900 is a 12-core/24-thread part, just like its retail-channel sibling, the 7900X. The 7700 is an 8-core/16-thread part, again, similar to the 7700X. Not much else is known about these chips, except for their base frequency of just 3.60 GHz (compared to 4.70 GHz for the 7900X, and 4.50 GHz for the 7700X). Both chips are expected to feature a lowered TDP, with just 65 W for the 7700 (down from 105 W for the 7700X), and possibly 65 W or 105 W for the 7900 (down from 170 W for the 7900X).

The unified shader (stream processor) counts of AMD's upcoming second- and third-largest GPUs based on the RDNA3 graphics architecture, have been leaked in some ROCm code, discovered by Kepler_L2 on Twitter. The "performance.hpp" file references "Navi 32" with a compute unit count of 60, and the "Navi 33" with 32 compute units. We know from the "Navi 31" specifications that an RDNA3 compute unit still amounts to 64 stream processors (although with significant IPC uplifts over the RDNA2 stream processor due to dual-instruction issue-rate).

60 compute units would give the "Navi 32" silicon a stream processor count of 3,840, a 50% numerical increase over the 2,560 of its predecessor, the "Navi 22," powering graphics cards such as the Radeon RX 6750 XT. Meanwhile, the 32 CU count of the "Navi 33" amounts to 2,048 stream processors, which is numerically unchanged from that of the "Navi 23" powering the RX 6650 XT. The new RDNA3 compute unit has significant changes over RDNA2, besides the dual-issue stream processors—it gets second-generation Ray Accelerators, and two AI accelerators for matrix-multiplication.

Xilinx Field Programmable Gate Arrays (FPGAs), now part of AMD, are always in demand in the semiconductor industry. Today, AMD has shared a letter to Xilinx customers that the selected FPGA device series will receive an 8-25% price increase. Citing AMD's investment into the supply chain, along with increased prices from the suppliers, Xilinx FPGAs will get more expensive. From January 9, 2023, the cost of the Spartan 6 series will increase by 25%, the price of the Versal series will not increase, and all other Xilinx products will increase by 8%. Interestingly, the older series manufactured on 40-28 nm nodes will increase while the latest Versal series doesn't experience any change.

Regarding lead times, the 16 nm UltraScale+ series, 20 nm UltraScale series, and 28 nm 7 series all take 20 weeks from order to delivery, which will remain until the third quarter of 2023. You can read the entire document below.

Semiconductor manufacturing is a significant investment that requires long lead times and constant improvement. According to the latest DigiTimes report, the pricing of a 3 nm wafer is expected to reach $20,000, which is a 25% increase in price over a 5 nm wafer. For 7 nm, TSMC managed to produce it for "just" $10,000; for 5 nm, it costs the company to make it for the $16,000 mark. And finally, the latest and greatest technology will get an even higher price point at $20,000, a new record in wafer pricing. Since TSMC has a proven track record of delivering constant innovation, clients are expected to remain on the latest tech purchasing spree.

Companies like Apple, AMD, and NVIDIA are known for securing orders for the latest semiconductor manufacturing node capacities. With a 25% increase in wafer pricing, we can expect the next-generation hardware to be even more expensive. Chip manufacturing price is a significant price-determining factor for many products, so the 3 nm edition of CPUs, GPUs, etc., will get the highest difference.

Innodisk, a leading global provider of industrial-grade flash storage, DRAM memory and embedded peripherals, has announced its latest step into the AI market, with the launch of EXMU-X261, an FPGA Machine Vision Platform. Powered by AMD's Xilinx Kria K26 SOM, which was designed to enable smart city and smart factory applications, Innodisk's FPGA Machine Vision Platform is set to lead the way for industrial system integrators looking to develop machine vision applications.

Automated defect inspection, a key machine vision application, is an essential technology in modern manufacturing. Automated visual inspection guarantees that the product works as expected and meets specifications. In these cases, it is vital that a fast and highly accurate inspection system is used. Without AI, operators must manually inspect each product, taking an average of three seconds per item. Now, with the help of AI solutions such as Innodisk's FPGA Machine Vision Platform, product inspection in factories can be automated, and the end result is not only faster and cheaper, but can be completely free of human error.

AMD Radeon RX 7900 XTX and RX 7900 XT RDNA3 graphics cards debut on December 13, 2022. This is when you will be able to buy one, at an MSRP of $999 for the RX 7900 XTX, and $899 for the RX 7900 XT. These will, however, only be reference-design MBA (made by AMD) graphics cards sold though the company's various add-in board (AIB) partners. The non-reference (custom design) RX 7900 series reportedly releases to the market 1 to 2 weeks after December 13, according to a Board Channels report seen by Wccftech.

Unlike the NVIDIA Founders Edition graphics card that's sold exclusively under the NVIDIA marquee, AMD's reference-design cards are sold by its AIB partners, with minimal or nil partner branding on the cards. The after-sales support, including product warranties and other brand-specific inclusions, are handled by the AIBs themselves. Custom-design cards are those designed by the AIB partners, with customization extending to both the cooling solution and the PCB; and with some cards even featuring factory-overclocked speeds. These are the ones that could launch 1 to 2 weeks after December 13, which would put their launch anywhere between December 20 to 27 (our yikes go out to reviewers).

AMD late Tuesday released the AMD Software Adrenalin 22.11.1 WHQL drivers. These are essentially identical to the Adrenalin 22.11.1 beta drivers the company released on November 16, but with the added WHQL certification. Compared to the previous 22.10.3 beta drivers, these add optimization for Call of Duty: Warzone 2.0, and Marvel's Spider-Man: Miles Morales. It also comes with the same set of fixed and discovered issues as the 22.11.1 beta; including missing prediction lines in World of Warships on Radeon RX 6000 series GPUs; an beep heard in the background when you hold down shift + backspace key with Radeon Anti-Lag enabled; visual corruption in OpenGL applications with MSAA enabled; higher than expected idle memory clocks on multi-monitor setups; and missing objects in Edificius.

DOWNLOAD: AMD Software Adrenalin 22.11.1 WHQL

Based on the latest data and research, TrendForce has further corrected down the projected YoY growth rate of whole server shipments for 2023 to 2.8%. Three factors are behind this revision. First, lead time has started to return to its usual length for most orders related to server components from 3Q23 onward. Seeing this, server OEMs and cloud service providers (CSPs) have also begun to correct the component mismatch issue by lowering demand for items that are in excess while maintaining a constant inventory level for items that are still in tight supply. This development, in turn, has reduced the flow of server orders going to ODMs. Second, the wave of demand that was generated earlier from the effects of the COVID-19 pandemic is dissipating. Hence, expansion activities have cooled off noticeably for services such as video streaming, e-commerce, etc. Among CSPs, Meta, Google, and ByteDance (TikTok) have lowered their server procurement quantities for next year. Lastly, the global economic outlook has remained fairly negative, so companies across most industry sectors have formulated a more conservative expenditure plan and scaled back IT-related spending for next year.

Jon Peddie Research reports the growth of the global PC-based graphics processor unit (GPU) market reached 75.5 million units in Q3'22 and PC CPU shipments decreased by -19% year over year. Overall, GPUs will have a compound annual growth rate of 2.8% during 2022-2026 and reach an installed base of 3,138 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 26%.

Year-to-year total GPU shipments, which include all platforms and all types of GPUs, decreased by -25.1%, desktop graphics decreased by -15.43%, and notebooks decreased by -30%—the biggest drop since the 2009 recession. AMD's overall market share percentage from last quarter decreased by -8.5%, Intel's market share increased by 10.3%, and NVIDIA's market share decreased by -1.87%, as indicated in the following chart.

AMD and Analog Devices, Inc. today announced that they have resolved all their ongoing patent litigations, based on mutually agreed upon terms. As part of this resolution, the two companies have committed to pursue technology collaborations to bring next generation solutions to their communications and data center customers.

For more than 50 years AMD has driven innovation in high-performance computing, graphics and visualization technologies. Billions of people, leading Fortune 500 businesses and cutting-edge scientific research institutions around the world rely on AMD technology daily to improve how they live, work and play. AMD employees are focused on building leadership high-performance and adaptive products that push the boundaries of what is possible. Analog Devices, Inc. operates at the center of the modern digital economy, converting real-world phenomena into actionable insight with its comprehensive suite of analog and mixed signal, power management, radio frequency (RF), and digital and sensor technologies. ADI serves 125,000 customers worldwide with more than 75,000 products in the industrial, communications, automotive, and consumer markets. ADI is headquartered in Wilmington, MA.

AMD Ryzen 7000-series "Zen 4" desktop processors got their first round of price-cuts on leading retailer Newegg, as the company has a hard time justifying their launch-prices in the wake of Intel's 13th Gen Core "Raptor Lake" and declining demand in the PC components market. The new pricing sees the top Ryzen 9 7950X 16-core/32-thread chip priced at USD $574, down from $700 (an 18% price-cut). The 12-core/24-thread Ryzen 9 7900X sees its price go down from $550 to $474 (down 14%).

The 8-core/16-thread Ryzen 7 7700X gets a $50 price-cut sending its price down from $400 to roughly $350. The 6-core/12-thread Ryzen 5 7600X gets a similar $50 cut, which means the chip can now be had for roughly $250, down from its $300 launch price. All four SKUs face stiff competition from the aggressively priced 13th Gen Core SKUs, which include the i9-13900K, the i7-13700K, and the i5-13600K. Prices of Socket AM5 motherboards are another big put-off as they're a major contributor to platform costs, which is restricted to DDR5 memory. The Intel platform currently includes entry-level chipset options, as well as motherboards with DDR4 support.

Although we're only some three weeks away from the launch of AMD's Radeon RX 7000-series cards, it has been pretty quiet from its partners. That said, PowerColor has finally revealed more than just a tiny detail of its upcoming Radeon RX 7900 Red Devil via a post on Facebook. The company didn't reveal any specs and it's unclear if this will be an RX 7900 XT or an RX 7900 XTX based card.

What we can see from the picture is that it's a triple-slot card with air being vented out the rear, something AMD's reference cards don't do. It's obviously a triple-fan card and PowerColor has equipped it with some LED lights as one would expect. Not much else is revealed by the single picture of the card, due to the angle the card sits at, so we don't know what kind of ports to expect, or what kind of power connectors the card will have. Hopefully PowerColor will reveal more details before the official launch on the 13th of December.

AMD will build "Zen 4" based Ryzen Threadripper processors in an attempt to meet competition from Intel, which is rumored to launch HEDT processors of its own based on "Sapphire Rapids." While Intel's chip tops out at 60-core/120-thread and has a constellation of task-specific hardware-accelerators, AMD will arm its processors with raw CPU core-count, going as high up as 96-core/192-thread. The company has assigned the codename "Storm Peak" for these chips.

The Ryzen Threadripper 7000-series "Storm Peak" processor engineering samples surfaced on the Einstein@Home user database. As many as three OPNs have surfaced, "AMD Eng Sample: 100-000000884-21_N" and "AMD Eng Sample: 100-000000884-20_Y," which are 96-core/192-thread; and the "AMD Eng Sample: 100-000000454-20_Y," which is 64-core/128-thread. "Storm Peak" is likely just a variation of EPYC "Genoa," geared for higher frequencies.

The Razer Blade 14, the world's most powerful 14" gaming laptop, is now available in a fresh new Mercury edition finish. This colorway combines the Mercury anodized aluminium chassis with a matte black keyboard for a truly striking aesthetic package. This new colorway is exclusive to two Blade 14 GPU configurations: the NVIDIA GeForce RTX 3060 and the NVIDIA GeForce RTX 3070 Ti. The addition of Mercury to the Blade 14 line marks the first time any Razer Blade is available in three different colorways simultaneously (Mercury, Quartz, and Black).

Along with the colorway release, a software update is now available for 2022 models of the Blade 14, upgrading the two Type-C USB-3.2 Gen 2 ports to USB4 and bringing support for Microsoft Pluton. USB4 expands peripheral compatibility, increasing device connectivity options and enabling multi-monitor deployments, support for Thunderbolt peripherals including Razer's Thunderbolt dock and Core X external graphics enclosures, and more. Microsoft Pluton's chip-to-cloud security technology protects users with an array of hardware-based security capabilities and services. New and existing 2022 Blade 14 owners should contact Razer Support to download this update.

The 60th edition of the TOP500 reveals that the Frontier system is still the only true exascale machine on the list.

With an HPL score of 1.102 EFlop/s, the Frontier machine at Oak Ridge National Laboratory (ORNL) did not improve upon the score it reached on the June 2022 list. That said, Frontier's near-tripling of the HPL score received by second-place winner is still a major victory for computer science. On top of that, Frontier demonstrated a score of 7.94 EFlop/s on the HPL-MxP benchmark, which measures performance for mixed-precision calculation. Frontier is based on the HPE Cray EX235a architecture and it relies on AMD EPYC 64C 2 GHz processor. The system has 8,730,112 cores and a power efficiency rating of 52.23 gigaflops/watt. It also relies on gigabit ethernet for data transfer.

SiPearl, the company designing the highperformance, low-power microprocessor for European supercomputers, has entered into a business collaboration agreement with AMD to provide a joint offering for exascale supercomputing systems, combining SiPearl's HPC microprocessor, Rhea, with AMD Instinct accelerators.

Initially, AMD and SiPearl will jointly assess the interoperability of the AMD ROCm open software with the SiPearl Rhea microprocessor and build an optimized software solution that would strengthen the capabilities of a SiPearl microprocessor combined with an AMD Instinct accelerator. This joint work targets porting and optimization activities of the AMD HIP backend, openMP compilers and libraries, will enable scientific applications to benefit from both technologies.

AMD in its technical presentation confirmed the reference clock speeds of the Radeon RX 7900 XTX and RX 7900 XT RDNA3 graphics cards. The company also made its first reference to a GeForce RTX 40-series "Ada" product, the RTX 4080 (16 GB), which is going to launch later today. The RX 7900 XTX maxes out the "Navi 31" silicon, featuring all 96 RDNA3 compute units or 6,144 stream processors; while the RX 7900 XT is configured with 84 compute units, or 5,376 stream processors. The two cards also differ with memory configuration. While the RX 7900 XTX gets 24 GB of 20 Gbps GDDR6 across a 384-bit memory interface (960 GB/s); the RX 7900 XT gets 20 GB of 20 Gbps GDDR6 across 320-bit (800 GB/s).

The RX 7900 XTX comes with a Game Clocks frequency of 2300 MHz, and 2500 MHz boost clocks, whereas the RX 7900 XT comes with 2000 MHz Game Clocks, and 2400 MHz boost clocks. The Game Clocks frequency is more relevant between the two. AMD achieves 20 GB memory on the RX 7900 XT by using ten 16 Gbit GDDR6 memory chips across a 320-bit wide memory bus created by disabling one of the six 64-bit MCDs, which also subtracts 16 MB from the GPU's 96 MB Infinity Cache memory, leaving the RX 7900 XT with 80 MB of it. The slide describing the specs of the two cards compares them to the GeForce RTX 4080, which is what the two could compete more against, especially given their pricing. The RX 7900 XTX is 16% cheaper than the RTX 4080, and the RX 7900 XT is 25% cheaper.

AMD Radeon RX 7900 XTX reference-design isn't a first-party product with limited availability like the NVIDIA Founders Edition; but rather a classic reference-design that's sold by AMD's add-in board partners under their marquee (without sticking their own labels on the product). AMD and its partners internally refer to reference-design cards as "MBA cards" (made by AMD cards). The company gave us a technical overview of the reference-design PCB. As with every reference AMD PCB for the past several generations, the RX 7900 XTX PCB has a premium selection of components. The card uses an expensive 14-layer PCB with 4 additional layers of 2-oz copper. 14-layer PCBs are typically used with enterprise-grade products, and graphics cards typically tend to have PCB layer counts of around 10. The PCB also uses ITEQ IT-170GRA epoxy and laminate materials, which enable a glass transition temperature (Tg) of 175 °C (no, the GPU won't get anywhere near as hot).

The reference-design RX 7900 XTX PCB draws power from two 8-pin PCIe power connectors. With the typical board power of the RX 7900 XTX rated at 355 W, this falls inside the 375 total power-draw capability when you add up the 150 W input from the two connectors, and 75 W from the PCIe slot. AMD worked to minimize power-draw spikes at least from the PCIe slot. Excursions, if any, should be localized to the 8-pin power connectors. The card features 20-phase VRM solution, using "high efficiency" DrMOS power-stage phases (could be very high current). The "Navi 31" GPU is surrounded by 12 GDDR6 memory chips given the GPU's 384-bit memory interface. Two of these memory pads could end up unused on the RX 7900 XT, which has a 320-bit memory interface. Display outputs of the RX 7900 series include two standard-size DisplayPort 2.1, one USB type-C with DisplayPort passthrough; and one HDMI 2.1a.

Cerebras Systems, the pioneer in accelerating artificial intelligence (AI) compute, today unveiled Andromeda, a 13.5 million core AI supercomputer, now available and being used for commercial and academic work. Built with a cluster of 16 Cerebras CS-2 systems and leveraging Cerebras MemoryX and SwarmX technologies, Andromeda delivers more than 1 Exaflop of AI compute and 120 Petaflops of dense compute at 16-bit half precision. It is the only AI supercomputer to ever demonstrate near-perfect linear scaling on large language model workloads relying on simple data parallelism alone.

With more than 13.5 million AI-optimized compute cores and fed by 18,176 3rd Gen AMD EPYC processors, Andromeda features more cores than 1,953 Nvidia A100 GPUs and 1.6 times as many cores as the largest supercomputer in the world, Frontier, which has 8.7 million cores. Unlike any known GPU-based cluster, Andromeda delivers near-perfect scaling via simple data parallelism across GPT-class large language models, including GPT-3, GPT-J and GPT-NeoX.

AMD, in its technical presentation for the new Radeon RX 7900 series "Navi 31" GPU, gave us an elaborate explanation on why it had to take the chiplets route for high-end GPUs, devices that are far more complex than CPUs. The company also enlightened us on what sets chiplet-based packages apart from classic multi-chip modules (MCMs). An MCM is a package that consists of multiple independent devices sharing a fiberglass substrate.

An example of an MCM would be a mobile Intel Core processor, in which the CPU die and the PCH die share a substrate. Here, the CPU and the PCH are independent pieces of silicon that can otherwise exist on their own packages (as they do on the desktop platform), but have been paired together on a single substrate to minimize PCB footprint, which is precious on a mobile platform. A chiplet-based device is one where a substrate is made up of multiple dies that cannot otherwise independently exist on their own packages without an impact on inter-die bandwidth or latency. They are essentially what should have been components on a monolithic die, but disintegrated into separate dies built on different semiconductor foundry nodes, with a purely cost-driven motive.

PowerColor put out its first teaser of a custom-design Radeon RX 7900 XTX graphics card, the RX 7900 XTX HellHound. The teaser is a back 3-quarter picture of the card, revealing its well-ventilated dual aluminium fin-stack heatsink and a triple fan setup, which make up a triple-slot cooling solution. The cooler's fans, and the HellHound logo on the backplate, are illuminated.

A striking aspect of this card is that it has the same set of power connectors as the AMD reference design, with just two 8-pin PCIe power connectors for a power-delivery capability of 375 W. It's possible that PowerColor is using a common board design for both the RX 7900 XTX and RX 7900 XT HellHound products. Besides the two power connectors, we spot a switch to control the LED illumination. There's another switch toward the front-end of the card, which works as a dual-BIOS selector.

AIC Inc., (from now on referred to as "AIC"), a leading provider in enterprise storage and server solutions, today revealed its new edge server appliance powered by 4th Gen AMD EPYC processors (codename Genoa). The new server, EB202-CP, is designed to deliver superior performance in a compact size while offering excellent cost efficiency. Combined with the 4th Gen AMD EPYC processors, EB202-CP is expected to drive the innovations in AI, training simulation, autonomous vehicles and edge applications. AIC will showcase EB202-CP at SC22 expo from November 14th to 17th, 2022.

AIC EB202-CP is a 2U rackmount server with 22 inches in depth. It supports eight E1.S/ E3.S or U.2 SSDs which are front-serviceable and hot-swappable. The E1.S/ E3.S drives are Enterprise and Datacenter SSD Form Factor (EDSFF) that enables EB202-CP to provide high-density all-flash NVMe for half petabyte storage capabilities and enhance IOPS and space utilization. EB202-CP has great expansion functionality and supports up to two double-stack GPU or accelerator cards, two FHHL/HHHL PCIe 5.0 cards and an OCP 3.0 card. Based on AIC server board Capella, EB202-CP supports single 4th Gen AMD EPYC processor and eight DDR5 DIMMs. The 4th Gen AMD EPYC processors, built on "Zen 4" architecture, are optimized for general-purpose workloads across enterprise, cloud and edge. This new generation of AMD EPYC features the world's highest-performing x86 processor, PCIe 5.0 ready, and enables low TCO. It also delivers leadership energy efficiency as well as state-of-the-art security features.

Yesterday, AMD announced its latest addition to the data center family of processors called EPYC Genoa. Named the 4th generation EPYC processors, they feature a Zen 4 design and bring additional I/O connectivity like PCIe 5.0, DDR5, and CXL support. To disrupt the cloud, enterprise, and HPC offerings, AMD decided to manufacture SKUs with up to 96 cores and 192 threads, an increase from the previous generation's 64C/128T designs. Today, we are learning more about the performance and power aspects of the 4th generation AMD EPYC Genoa 9654, 9554, and 9374F SKUs from 3rd party sources, and not the official AMD presentation. Tom's Hardware published a heap of benchmarks consisting of rendering, compilation, encoding, parallel computing, molecular dynamics, and much more.

In the comparison tests, we have AMD EPYC Milan 7763, 75F3, and Intel Xeon Platinum 8380, a current top-end Intel offering until Sapphire Rapids arrives. Comparing 3rd-gen EPYC 64C/128T SKUs with 4th-gen 64C/128T EPYC SKUs, the new generation brings about a 30% increase in compression and parallel compute benchmarks performance. When scaling to the 96C/192T SKU, the gap is widened, and AMD has a clear performance leader in the server marketplace. For more details about the benchmark results, go here to explore. As far as comparison to Intel offerings, AMD leads the pack as it has a more performant single and multi-threaded design. Of course, beating the Sapphire Rapids to market is a significant win for team red, so we are still waiting to see how the 4th generation Xeon stacks up against Genoa.

TYAN, an industry-leading server platform design manufacturer and a MiTAC Computing Technology Corporation subsidiary, today introduced AMD EPYC 9004 Series processor-based server platforms highlighting energy efficiency and performance breakthroughs designed for next generation server architecture for data centers. "Facing the post-COVID economy world, data centers are required to build on more environmentally friendly, secure and flexible features to respond to the growing of teleworking, video streaming, IoT and 5G," said Danny Hsu, Vice President of MiTAC Computing Technology Corporation's Server Infrastructure BU. "TYAN's new server platforms powered by 4th Gen AMD EPYC processors efficiently enable data centers by doing more tasks with the same number of servers."

"We designed 4th Gen AMD EPYC processors to give our customers exactly what they said they needed, high performance, exceptional energy efficiency and low total cost of ownership," said Ram Peddibhotla, corporate vice president, EPYC product management, AMD. "With the latest "Zen 4" architecture that incorporates modern security by design, 4th Gen AMD EPYC processors are an outstanding choice for IT professionals looking to optimize their data centers for leadership performance while helping address environmental goals."

SK hynix announced that its DRAM, and CXL solutions have been validated with the new AMD EPYC 9004 Series processors, which were unveiled during the company's "together we advance_data centers" event on November 10. SK hynix has worked closely with AMD to provide fully compatible memory solutions for the 4th Gen AMD EPYC processors.

4th Gen AMD EPYC processors are built on an all-new SP5 socket and offer innovative technologies and features including support for advanced DDR5 and CXL 1.1+ memory expansion. SK hynix 1ynm, 1a nm 16 Gb DDR5 and 1a nm 24Gb DDR5 DRAM support 4800 Mbps on 4th Gen AMD EPYC processors, which deliver up to 50% more memory bandwidth than DDR4 product. SK hynix also provides CXL memory device that is a 96 GB product composed of 24 Gb DDR5 DRAMs based on 1a nm. The company expects high customer satisfaction of this product with flexible configuration of bandwidth and capacity expanded cost-efficiently.