Micron Technology, Inc., today announced two new Crucial Pro Series products with the addition of overclocking-capable memory and the world's fastest Gen 5 SSD. The Crucial DDR5 Pro Memory: Overclocking Edition modules are available in 16 GB densities up to DDR5-6000 to deliver higher performance, lower latencies and better bandwidth to fuel gaming wins and reduce performance bottlenecks. These powerful DDR5 overclocking DRAM modules are compatible with the latest DDR5 Intel and AMD CPUs and support both Intel XMP 3.0 and AMD EXPO specifications on every module, eliminating compatibility hassles. Built with leading-edge Micron 232-layer TLC NAND, the Crucial T705 SSD unleashes the full potential of Gen 5 performance.

Lightning-fast sequential reads and writes up to 14,500 MB/s and 12,700 MB/s (up to 1,550K/1,800K IOPS random reads and writes) respectively, enable faster gaming, video editing, 3D rendering and heavy workload AI application processing. With DDR5 Pro Overclocking DRAM and the T705 SSD, enthusiasts, gamers and professionals can harness the speed, bandwidth and performance they need for AI-ready PC builds capable of processing, rendering and storing large volumes of AI generated content.

ASUS today announced brand-new ASUS Vivobook S series laptops for 2024, designed for a sleek and lightweight lifestyle. These laptops - all featuring ASUS Lumina OLED display options - are driven by up to the latest AI-enabled processors from AMD, and offer exceptional performance. The series includes the 14.0-inch ASUS Vivobook S 14 OLED M5406, the 15.6-inch ASUS Vivobook S 15 OLED M5506, and the 16.0-inch ASUS Vivobook S 16 OLED M5606. ASUS Vivobook S series laptops are not only powerful but also lightweight, making them perfect for individuals who need both productivity and entertainment while on the move. They come in contemporary color options and feature a minimalist, high-end design, striking a balance between mobility and performance.

The latest 2024 ASUS Vivobook S series laptops are equipped with up to AMD Ryzen 8040 Series Processors, boasting a TDP of up to 50 watts and built-in AMD Ryzen AI acceleration for efficient performance in modern AI applications. A dedicated Copilot key on the keyboard allows users to effortlessly dive into Windows 11's AI-powered tools with just one press.The laptops provide lifelike visuals through ASUS Lumina OLED displays, offering resolutions of up to 3.2K (M5606), a 120 Hz refresh rate, a 100% DCI-P3 color gamut, and VESA DisplayHDR True Black 600 certification. The ASUS ErgoSense keyboard, known for its style and comfort, now features customizable single-zone RGB backlighting, and there's an extra-large ErgoSense touchpad. Prioritizing user experience, these ASUS Vivobook S models include a lay-flat 180° hinge, an IR camera with a physical shutter, a full range of I/O ports, and immersive Dolby Atmos audio from the powerful Harman Kardon-certified stereo speakers.

AI workloads are split into two different categories: training and inference. While training requires large computing and memory capacity, access speeds are not a significant contributor; inference is another story. With inference, the AI model must run extremely fast to serve the end-user with as many tokens (words) as possible, hence giving the user answers to their prompts faster. An AI chip startup, Groq, which was in stealth mode for a long time, has been making major moves in providing ultra-fast inference speeds using its Language Processing Unit (LPU) designed for large language models (LLMs) like GPT, Llama, and Mistral LLMs. The Groq LPU is a single-core unit based on the Tensor-Streaming Processor (TSP) architecture which achieves 750 TOPS at INT8 and 188 TeraFLOPS at FP16, with 320x320 fused dot product matrix multiplication, in addition to 5,120 Vector ALUs.

Having massive concurrency with 80 TB/s of bandwidth, the Groq LPU has 230 MB capacity of local SRAM. All of this is working together to provide Groq with a fantastic performance, making waves over the past few days on the internet. Serving the Mixtral 8x7B model at 480 tokens per second, the Groq LPU is providing one of the leading inference numbers in the industry. In models like Llama 2 70B with 4096 token context length, Groq can serve 300 tokens/s, while in smaller Llama 2 7B with 2048 tokens of context, Groq LPU can output 750 tokens/s. According to the LLMPerf Leaderboard, the Groq LPU is beating the GPU-based cloud providers at inferencing LLMs Llama in configurations of anywhere from 7 to 70 billion parameters. In token throughput (output) and time to first token (latency), Groq is leading the pack, achieving the highest throughput and second lowest latency.

The U.S. Department of Commerce today announced $1.5 billion in planned direct funding for GlobalFoundries (Nasdaq: GFS) (GF) as part of the U.S. CHIPS and Science Act. This investment will enable GF to expand and create new manufacturing capacity and capabilities to securely produce more essential chips for automotive, IoT, aerospace, defense, and other vital markets.

New York-headquartered GF, celebrating its 15th year of operations, is the only U.S.-based pure play foundry with a global manufacturing footprint including facilities in the U.S., Europe, and Singapore. GF is the first semiconductor pure play foundry to receive a major award (over $1.5 billion) from the CHIPS and Science Act, designed to strengthen American semiconductor manufacturing, supply chains and national security. The proposed funding will support three GF projects:

Colorful is now exclusively a GeForce RTX graphics card vendor, but it had a brief stint with AMD Radeon under the separate Colorfire brand. This brand is reportedly making it back, but not for graphics cards. Colorful isn't just selling graphics cards and motherboards, but also has a growing line of gaming notebooks. Apparently, the Colorfire brand will denote notebooks powered by AMD Ryzen mobile processors. The discrete GPUs are still GeForce RTX 40-series. The news emerged from a regulatory filing by Colorful's notebook ODM, Clevo, which is a well known notebook manufacturer for several brands. The filings speak of the Colorfire MEOW R15 24, and the MEOW R16 24, which presumably feature 15-inch 16:9 and 16-inch 16:10 displays, respectively.

Both the Colorfire notebooks are powered by AMD Ryzen 8040 series "Hawk Point" mobile processors with full Ryzen AI enablement, while their discrete graphics options include GeForce RTX 4060 series and RTX 4070 series Laptop GPUs. The listings also mention at 180 W power supply for the MEOW R15 24; and a 230 W one for the MEOW R16 24, which seems to tally well with a combination of a Ryzen 8040HS series 45 W-class processor, and a GeForce RTX 4060/4070 series GPU with configured total graphics power in the 130 W to 160 W range.

Systems running on older hardware could be excluded from upcoming public versions of Windows 11—the recently released preview/insider build (26052) has introduced all sorts of new features including "Sudo for Windows", an improved regedit, and hidden beneath the surface, an AI-flavored Super Resolution settings menu. Early partakers of version 24H2 are running into instruction set-related problems—Windows operating expert, Bob Pony, was one of the unlucky candidates. Microsoft's preview code seems to require a specific instruction set to reach operational status—Pony documented his frustrations on social media: "Using the command line argument "/product server" for setup.exe, BYPASSES the system requirement checks for the Windows 11 24H2 setup program. But unfortunately, after setup completes then reboots into the next stage. It'll be indefinitely stuck on the Windows logo boot screen."

He continued to narrow in on the source of blame: "Windows 11 Version 24H2 Build 26058's setup (if ran in a live Windows Install) now checks for a CPU instruction: PopCnt." The Register provided some history/context on the SSE4 set: "POPCNT/PopCnt counts the number of bits in a machine word that have been set (or different from zero.) You might see it in cryptography and it has been lurking in CPU architectures for years, pre-dating Intel and AMD's implementation by decades." It is believed that Microsoft has deployed PopCnt as part of its push into AI-augmented software features, although a segment of online discussion proposes that an engineer has "accidentally enabled" newer CPU instruction sets. Tom's Hardware marked a line in the sand: "PopCnt has been supported since the Intel Nehalem and AMD Phenom II (microarchitecture) era—14 years ago—so compatibility won't be an issue for any modern systems. The only users that will be affected are enthusiasts running modified versions of Windows 11 on 15+ year-old chips like Core 2 Duos or Athlon 64." Bob Pony's long-serving Core 2 Quad Q9650 processor—a late summer 2008 product—was deemed unworthy by the preview build's setup process.

Chinese review outlets have received MSI Claw sample units—the "Please, Xiao Fengfeng" Bilibili video channel has produced several comparison pieces detailing how the plucky Intel Meteor Lake-powered handheld stands up against its closest rival; ASUS ROG Ally. The latter utilizes an AMD Ryzen Z1 APU—in Extreme or Standard forms—many news outlets have pointed out that the Z1 Extreme processor is a slightly reworked Ryzen 7 7840U "Phoenix" processor. Intel and its handheld hardware partners have not dressed up Meteor Lake chips with alternative gaming monikers—simply put, the MSI Claw arrives with Core Ultra 7-155H or Ultra 5-135H processors onboard. The two rival systems both run on Window 11, and also share the same screen size, resolution, display technology (IPS) and 16 GB LPDDR5-6400 memory configuration. The almost eight months old ASUS handheld seems to outperform its near-launch competition.

Xiao Fengfeng's review (Ultra 7-155H versus Z1 Extreme) focuses on different power levels and how they affect handheld performance—the Claw and Ally have user selectable TDP modes. A VideoCardz analysis piece lays out key divergences: "Both companies offer easy TDP profile switches, allowing users to adjust performance based on the game's requirements or available battery life. The Claw's larger battery could theoretically offer more gaming time or higher TDP with the same battery life. The system can work at 40 W TDP level (but in reality it's between 35 and 40 watts)...In the Shadow of the Tomb Raider test, the Claw doesn't seem to outperform the ROG Ally. According to a Bilibili creator's test, the system falls short at four different power levels: 15 W, 20 W, 25 W, and max TDP (40 W for Claw and 30 W for Ally)."

Samsung Electronics and Vodafone, in collaboration with AMD, today announced that the three companies have successfully demonstrated an end-to-end call with the latest AMD processors enabling Open RAN technology, a first for the industry. This joint achievement represents the companies' technical leadership in enriching the Open RAN ecosystem throughout the industry. Conducted in Samsung's R&D lab in Korea, the first call was completed using Samsung's versatile, O-RAN-compliant, virtualized RAN (vRAN) software, powered by AMD EPYC 8004 Series processors on Supermicro's Telco/Edge servers, supported by Wind River Studio Container-as-a-Service (CaaS) platform. This demonstration aimed to verify optimized performance, energy efficiency and interoperability among partners' solutions.

The joint demonstration represents Samsung and Vodafone's ongoing commitment to reinforce their position in the Open RAN market and expand their ecosystem with industry-leading partners. This broader and growing Open RAN ecosystem helps operators to build and modernize mobile networks with greater flexibility, faster time-to-market (TTM), and unmatched performance. "Open RAN represents the forthcoming major transformation in advancing mobile networks for the future. Reaching this milestone with top industry partners like Samsung and AMD shows Vodafone's dedication to delivering on the promise of Open RAN innovation," said Nadia Benabdallah, Network Strategy and Engineering Director at Vodafone Group. "Vodafone is continually looking to innovate its network by exploring the potential and diversity of the ecosystem."

AMD is reportedly building its upcoming "Zen 5" and "Zen 5c" CPU Core Dies (CCDs) on two different foundry nodes, a report by Chinese publication UDN, claims. The Zen 5 CCD powering the upcoming Ryzen "Granite Ridge" desktop processors, "Fire Range" mobile processors, and EPYC "Turin" server processors, will be reportedly built on the 4 nm EUV foundry node, a slightly more advanced node than the current 5 nm EUV the company is building "Zen 4" CCDs on. The "Zen 5c" CCD, or the chiplet with purely "Zen 5c" cores in a high density configuration; on the other hand, will be built on an even more advanced 3 nm EUV foundry node, the report says. Both CCDs will go into mass production in Q2-2024, with product launches expected across the second half of the year.

The "Zen 5c" chiplet has a mammoth 32 cores spread across two CCXs of 16 cores, each. Each CCX has 16 cores sharing a 32 MB L3 cache. It is to cram these 32 cores, each with 1 MB of L2 cache; and a total of 64 MB of L3 cache, that AMD could be turning to the 3 nm foundry node. Another reason could be voltages. If "Zen 4c" is anything to go by, the "Zen 5c" core is a highly compacted variant of "Zen 5," which operates at a lower voltage band than its larger sibling, without any change in IPC or instruction sets. The decision to go with 3 nm could be a move aimed at increasing clock speeds at those lower voltages, in a bid to generationally improve performance using clock speeds, besides IPC and core count. The EPYC processor with "Zen 5c" chiplets will feature no more than six such large CCDs, for a maximum core count of 192. The regular "Zen 5" CCD has just 8 cores in a single CCX, with 32 MB of L3 cache shared among the cores; and TSV provision for 3D Vertical Cache, to increase the L3 cache in special variants.

Japanese tech billionaire and founder of the SoftBank Group, Masayoshi Son, is embarking on a hugely ambitious new project to build an AI chip company that aims to rival NVIDIA, the current leader in AI semiconductor solutions. Codenamed "Izanagi" after the Japanese god of creation, Son aims to raise up to $100 billion in funding for the new venture. With his company SoftBank having recently scaled back investments in startups, Son is now setting his sights on the red-hot AI chip sector. Izanagi would leverage SoftBank's existing chip design firm, Arm, to develop advanced semiconductors tailored for artificial intelligence computing. The startup would use Arm's instruction set for the chip's processing elements. This could pit Izanagi directly against NVIDIA's leadership position in AI chips. Son has a chest of $41 billion in cash at SoftBank that he can deploy for Izanagi.

Additionally, he is courting sovereign wealth funds in the Middle East to contribute up to $70 billion in additional capital. In total, Son may be seeking up to $100 billion to bankroll Izanagi into a chip powerhouse. AI chips are seeing surging demand as machine learning and neural networks require specialized semiconductors that can process massive datasets. NVIDIA and other names like Intel, AMD, and select startups have capitalized on this trend. However, Son believes the market has room for another major player. Izanagi would focus squarely on developing bleeding-edge AI chip architectures to power the next generation of artificial intelligence applications. It is still unclear if this would be an AI training or AI inference project, but given that the training market is currently bigger as we are in the early buildout phase of AI infrastructure, the consensus might settle on training. With his track record of bold bets, Son is aiming very high with Izanagi. It's a hugely ambitious goal, but Son has defied expectations before. Project Izanagi will test the limits of even his vision and financial firepower.

In case you missed it, Sam Altman of OpenAI took the Internet by storm late last week with the unveiling of Sora, the generative AI that can congure up photoreal video clips based on prompts, with deadly accuracy. While Altman and his colleagues in the generative AI industry had a ton of fun generating videos based on prompts from the public on X; it became all too clear that the only thing holding back the democratization of generative AI is the volume of AI accelerator chips. Altman wants to solve this by designing his own AI acceleration hardware from the grounds up, for which he initially pitched an otherworldly $7 trillion in investment—something impossible with the financial markets, but one that's possible only by "printing money," or through sovereign wealth fund investments.

Jim Keller needs no introduction—the celebrity VLSI architect has been designing number crunching devices of all shapes and sizes for some of the biggest tech companies out there for decades, including Intel, Apple, and AMD, just to name a few. When as part of his "are you not entertained?" victory lap, Altman suggested that his vision for the future needs an even larger $8 trillion investment, Keller responded that he could design an AI chip for less than $1 trillion. Does Altman really need several trillions of Dollars to build a grounds-up AI chip at the costs and volumes needed to mainstream AI?

The AMD Radeon RX 7900 GRE 16 GB reference model has reached UK shores, albeit very briefly and with a very low stock count—e-tailer AWD-IT Gaming PC (ADMI Ltd.) was the first shop in the region to offer XFX's Navi 31 XL partner card. Team Red's formerly Chinese market-exclusive Radeon RDNA 3 GPU has made its way West—as of late last year—but retail presence in Europe is less than inspiring. Circumstances could change—recent rumblings indicate that more custom options are incoming—GIGABYTE is readying a Gaming OC variant, possibly paving the way for a wider release through mainstream channels. PowerColor's Hellhound Radeon RX 7900 GRE OC model has also been spotted on European price comparison engines.

UK buyers were treated to an initial batch of a dozen (or fewer) XFX Radeon RX 7900 GRE Reference graphics card, at £659.99 (~$832) including VAT and free delivery. AWD-IT's listing is inactive at the time of writing, but the SKU remains as a searchable asset on their web store. It appears that curious UK hardware enthusiasts have snapped up the first round of Golden Rabbit Edition (GRE) curiosities, although the price point was nowhere near as attractive when lined up against past offerings within EU mainlands. For example, Italy's PSK Mega Store had reference stock priced at €542.66 (~$585) a piece, with a digital copy of AVATAR: Frontiers of Pandora bundled in. The XFX Radeon RX 7900 XT 20 GB SPEEDSTER MERC 310 model is currently discounted—£699.99 via Ebuyer UK—representing a very tempting higher-specced custom design prospect (going for only £40 more than the RX 7900 GRE) .

Building on our previously announced support of the AMD Radeon RX 7900 XT, XTX and Radeon PRO W7900 GPUs with AMD ROCm 5.7 and PyTorch, we are now expanding our client-based ML Development offering, both from the hardware and software side with AMD ROCm 6.0. Firstly, AI researchers and ML engineers can now also develop on Radeon PRO W7800 and on Radeon RX 7900 GRE GPUs. With support for such a broad product portfolio, AMD is helping the AI community to get access to desktop graphics cards at even more price points and at different performance levels.

Furthermore, we are complementing our solution stack with support for ONNX Runtime. ONNX, short for Open Neural Network Exchange, is an intermediary Machine Learning framework used to convert AI models between different ML frameworks. As a result, users can now perform inference on a wider range of source data on local AMD hardware. This also adds INT8 via MIGraphX—AMD's own graph inference engine—to the available data types (including FP32 and FP16). With AMD ROCm 6.0, we are continuing our support for the PyTorch framework bringing mixed precision with FP32/FP16 to Machine Learning training workflows.

EK, the global leader in premium PC water cooling, is proud to introduce extraordinary EK-Quantum Velocity² Edge Special Edition CPU water blocks for the AM5 socket. After the successful launch of their LGA 1700-based counterpart earlier this year, these Special Edition Edge water blocks confirm EK's commitment to aesthetic excellence. The top cover is at the forefront of this design revolution, featuring a striking assembly of irregular tetrahedrons that transform each water block into a modern artwork. These tetrahedrons create a captivating interplay of light and shadow, adding a dynamic and sophisticated visual appeal to the water block.

Explicitly designed for platforms based on the AMD Socket AM5, they fit Ryzen 7000 series CPUs. The cold plate, precisely machined of the highest-grade 99.99% pure electrolytic copper, ensures unparalleled heat transfer. The top cover of the EK-Quantum Velocity² Edge D-RGB - AM5 Special Edition is available in Black and Silver. These color options allow enthusiasts to choose a style that best complements their PC build, transforming these water blocks from mere components for efficient cooling into central elements of a PC's aesthetic identity. The top cover is CNC-milled out of a 30 mm thick aluminium sheet, separated from the coolant with a layer of acrylic to ensure no mixing of metals.

AMD's small but fledgling Ryzen 8000 line of Socket AM5 desktop APUs is about to grow, with the addition of four new low-power SKUs, under the Ryzen 8000GE line. These chips come with a TDP of 35 W compared to the 65 W of the regular 8000G APUs, and a lowered PPT (package power tracking) value, making them energy-efficient variants. To be clear, these are not AMD's 8000-series APUs meant for the commercial desktop market, for that the company has the Ryzen PRO 8000 series and Ryzen PRO 7000 series.

The Ryzen 8000GE series are meant to square off against Intel's 14th Gen Core T-series SKUs that have processor base power values of 35 W, and significantly lower maximum turbo power values than the regular processor models. To carve out these chips, AMD has lowered the clock speeds and TDP compared to the regular 8000G series. Since the underlying 4 nm "Hawk Point" silicon achieves fairly good clocks in its 35 W HS-segment notebook processors, one can expect reasonably good boost residency with the 8000GE desktop chips.

AMD Ryzen 9 7900X3D is the often-ignored middle child of the 7000X3D series that's flanked by the reigning gaming CPU champion, the Ryzen 7 7800X3D; and the company's flagship Ryzen 9 7950X3D, which performs within 5% of the 7800X3D in gaming, but with the added 8 cores shoring up its productivity performance against the Core i9-14900K. Pricing of the 7900X3D dropped to $409 on Amazon, which is a huge departure from its $600 launch price. At this price, the 7900X3D is set up for a direct clash with the Intel Core i7-14700K, which is going for $400, with its iGPU-disabled sibling, the i7-14700KF listed at $392.

The Ryzen 9 7900X3D is is a 12-core/24-thread dual-CCD processor, with its 12 cores spread among two CCDs in a 6+6 configuration. The first of the two CCDs has the 96 MB L3 cache thanks to the 3D Vertical Cache (3D V-cache) technology, while the second is a regular CCD with just the 32 MB on-die L3 cache, but which can sustain higher clock speeds than the 3D V-cache CCD. The similar 16 core 7950X3D flagship can be had for $600, or about $50 higher than the i9-14900K, while the 7800X3D is going for $370.

Redevelopment of the AMD Radeon Anti-Lag+ feature is in full swing, and the feature is coming back soon, the company confirmed. Responding to a specific question on Twitter on reintroduction of Anti-Lag+, AMD's gaming solutions head Frank Azor confirmed that it is coming soon. Anti-Lag+ is AMD's whole system latency reduction technology that rivals NVIDIA Reflex.

Anti-Lag+ benefits not just competitive online gaming, but is also supposed to be a vital component for FSR 3 frame-generation, as the technology imposes a considerable amount of latency. You can notice this in current titles with FSR 3, including in some cases, ghosting artifacts with fast-moving objects in a 3D scene. This is why NVIDIA Reflex is an integral component of DLSS 3 Frame Generation, and is enabled along with it. AMD had withdrawn Anti-Lag+ as the technology had inadvertently tripped Anti-Cheat mechanisms of several online games, causing automated player bans that game developers had to manually identify and reverse. The company will have to redesign the way Anti-Lag+ works, and extensively test it with competitive games before reintroducing it.

iBUYPOWER, a leading manufacturer of high-performance custom gaming PCs, today announced it has become the official PC of VALORANT Champions Tour (VCT) Americas, VCT Game Changers North America, and VCT Game Changers Brazil. As iBUYPOWER celebrates its 25th anniversary, the partnership amplifies and highlights iBUYPOWER's dedication and integral role in supporting esports players with quality and reliable tools to succeed in their craft.

The 'iBUYPOWER ACE' moment will bring added excitement and value to both professional players and their communities of fans throughout the 2024 VCT Americas schedule. To celebrate the iBUYPOWER ACE, a triumphant, high-skill, moment where a single player eliminates all five of the opposing team's players to achieve victory, iBUYPOWER will be unlocking PC giveaways for VCT Americas fans (currently available to residents of the United States and Canada).

AMD has quietly funded an effort over the past two years to enable binary compatibility for NVIDIA CUDA applications on their ROCm stack. This allows CUDA software to run on AMD Radeon GPUs without adapting the source code. The project responsible is ZLUDA, which was initially developed to provide CUDA support on Intel graphics. The developer behind ZLUDA, Andrzej Janik, was contracted by AMD in 2022 to adapt his project for use on Radeon GPUs with HIP/ROCm. He spent two years bringing functional CUDA support to AMD's platform, allowing many real-world CUDA workloads to run without modification. AMD decided not to productize this effort for unknown reasons but did open-source it once funding ended per their agreement. Over at Phoronix, there were several benchmarks testing AMD's ZLUDA implementation over a wide variety of benchmarks.

Benchmarks found that proprietary CUDA renderers and software worked on Radeon GPUs out-of-the-box with the drop-in ZLUDA library replacements. CUDA-optimized Blender 4.0 rendering now runs faster on AMD Radeon GPUs than the native ROCm/HIP port, reducing render times by around 10-20%, depending on the scene. The implementation is surprisingly robust, considering it was a single-developer project. However, there are some limitations—OptiX and PTX assembly codes still need to be fully supported. Overall, though, testing showed very promising results. Over the generic OpenCL runtimes in Geekbench, CUDA-optimized binaries produce up to 75% better results. With the ZLUDA libraries handling API translation, unmodified CUDA binaries can now run directly on top of ROCm and Radeon GPUs. Strangely, the ZLUDA port targets AMD ROCm 5.7, not the newest 6.x versions. Only time will tell if AMD continues investing in this approach to simplify porting of CUDA software. However, the open-sourced project now enables anyone to contribute and help improve compatibility. For a complete review, check out Phoronix tests.

GIGABYTE is ready with its first custom design graphics card based on the AMD Radeon RX 7900 GRE (Golden Rabbit Edition). Originally designed for the Chinese domestic market, the RX 7900 GRE is finding its way across other Asian markets, and is also available in Europe. This GIGABYTE graphics card could be among the RX 7900 GRE cards to make it to the old continent. The card's design resembles that of the company's RX 7800 XT Gaming OC, which is slightly smaller than that of the RX 7900 XT Gaming OC. It features a triple-slot WindForce 3X cooling solution with a dual aluminium fin-stack heatsink that uses a copper base-plate, four heatpipes, and a trio of 80 mm fans. The card is about 30 cm long, 13 cm tall, and 5.6 cm thick. It uses a pair of 8-pin PCIe power connectors.

The Radeon RX 7900 GRE is based on the "Navi 31" XL silicon, which is essentially the "Navi 31" chiplet GPU on a compact package that's about the size of a "Navi 32." AMD designed this smaller package for its mobile RX 7900 series SKUs. The RX 7900 GRE is configured with 80 RDNA3 compute units, which make up 5,120 stream processors, 160 AI accelerators, 80 Ray accelerators, and 320 TMUs. It gets the full 192 ROP count of the silicon. The SKU only has four out of six MCDs (memory cache dies) enabled, which gives it 64 MB of Infinity Cache, and a 256-bit wide memory bus, driving 16 GB of 18 Gbps GDDR6 for 576 GB/s of memory bandwidth. The total board power (TBP) of the RX 7900 GRE is configured at 260 W, which is about the same as that of the RX 7800 XT. The GIGABYTE Gaming OC card is expected to come with a slight factory overclock for the GPU.

AMD Ryzen 7 8700G continues to be the favorite new toy for overclockers and enthusiasts. Der8auer succeeded in de-lidding the chip (removing its IHS), to reveal the monolithic "Hawk Point" silicon underneath. By default, the chip uses soldered TIM, but with the IHS removed and sTIM residue cleaned off, the chip could be prepared for direct die cooling, through liquid metal TIM. This feat enabled load temperatures to drop from 85°C to just over 60°C. This enabled a 5.00 GHz all-core overclock for the chip's 8 "Zen 4" CPU cores.

Also over the last week, SkatterBencher succeeded in getting the iGPU engine clock of the 8700G to 3.30 GHz, which is 50 MHz higher than the slider limit for Precision Boost Overdrive. SkatterBencher's report says that an 8700G can have its power limits raised all the way up to 170 W. The 3.30 GHz iGPU overclock was supported by a core voltage of 1.25 V (which is high considering the tight vCore limits AMD sets for its APUs). The increased power limits and clock speeds result in a 22.31% iGPU performance increase when averaged over 14 tests.

AMD's upcoming family of Ryzen 9000 series of processors on the AM5 platform will carry a new silicon SKU under the hood—Zen 5. The latest revision of AMD's x86-64 microarchitecture will feature a few interesting improvements over its current Zen 4 that it is replacing, targeting the rumored 10-15% IPC improvement. Thanks to the latest set of patches for GNU Compiler Collection (GCC), we have the patch set that proposes changes taking place with "znver5" enablement. One of the most interesting additions to the Zen 5 over the previous Zen 4 is the expansion of the AVX instruction set, mainly new AVX and AVX-512 instructions: AVX-VNNI, MOVDIRI, MOVDIR64B, AVX512VP2INTERSECT, and PREFETCHI.

AVX-VNNI is a 256-bit vector version of the AVX-512 VNNI instruction set that accelerates neural network inferencing workloads. AVX-VNNI delivers the same VNNI instruction set for CPUs that support 256-bit vectors but lack full 512-bit AVX-512 capabilities. AVX-VNNI effectively extends useful VNNI instructions for AI acceleration down to 256-bit vectors, making the technology more efficient. While narrow in scope (no opmasking and extra vector register access compared to AVX-512 VNNI), AVX-VNNI is crucial in spreading VNNI inferencing speedups to real-world CPUs and applications. The new AVX-512 VP2INTERSECT instruction is also making it in Zen 5, as noted above, which has been present only in Intel Tiger Lake processor generation, and is now considered deprecated for Intel SKUs. We don't know the rationale behind this inclusion, but AMD sure had a use case for it.

AMD FSR 3 Is Coming To The Thaumaturge—a Gripping and Dark RPG. The Thaumaturge is a story-driven RPG with morally ambiguous choices, taking place in the culturally diverse world of early 20th century Warsaw. In this world, Salutors exist: esoteric beings that only Thaumaturges can truly perceive and use for their needs. The Thaumaturge launches February 20th, with AMD FSR 3. Watch the brand new story trailer below.

When it launches later this month, The Thaumaturge will feature AMD FidelityFX Super Resolution 3. FSR 3 transforms gaming experiences with massive and responsive framerates in supported games using a combination of temporal upscaling technology, advanced frame generation, and built-in latency reduction technology.

An AMD Athlon K7 "Pluto" processor has been examined by Fritzchens Fritz, a well known close-up photographer of CPU and GPU dies—his latest project has uncovered a decades old hidden secret. He posted this discovery to social media earlier this week, and made sure to include various images for context purposes: "AMD Athlon K7 Pluto Top Metal Layer. A revolver and Texas Map can be found in one of the four corners! And some explanations about the stone relief. The relief contains the AMD Athlon K7 Series from: Argon -> Pluto -> Thunderbird -> Palomino -> Thoroughbred -> Barton." Team Red's turn of the millennium mainstream processor family fought off Intel's Pentium III CPU architecture (1999 to 2000)—many contemporary reports have handed that time period's victory to AMD. Fritz's funny find received a lot of news coverage, with many authors expressing disbelief about the miniscule revolver and Map of Texas being hidden in (sort of) plain sight for nearly 25 years.

Phil Park, an AMD veteran—currently working in the memory systems department as a Fabric performance engineer—posted an insightful reply to Fritz's historical guesstimations (Greco-Roman themes via the stone relief). Another Team Red revelation was revealed: "The original Athlon naming scheme (Mustang, Thunderbird, Spitfire) had a different theme (cars), but the rumor was that some companies got wind of this, so we changed themes rather than get involved in dumb trademark battles over internal codenames. So it became horses." If we read between the very obvious lines, Park suggests that Ford, Chevrolet, and BMW were keeping an eye on AMD product naming conventions.

The NVIDIA GeForce RTX 4070 Ti an now be found for as low as $699, which means it is now selling at the same price as the AMD Radeon RX 7900 XT graphics card. The GeForce RTX 4070 Ti definitely lags behind the Radeon RX 7900 XT, and packs less VRAM (12 GB vs. 20 GB), and the faster GeForce RTX 4070 Ti SUPER is selling for around $100 more. The Radeon RX 7900 XT is around 6 to 11 percent faster, depending on the game and the resolution.

The GeForce RTX 4070 Ti card in question comes from MSI and it is Ventus 2X OC model listed over at Newegg.com for $749.99 with a $50-off promotion code. Bear in mind that this is a dual-fan version from MSI and we are quite sure we'll see similar promotions from other NVIDIA AIC partners.