AMD is extending the longevity of its AM5 platform, further adding more life into the socket with future Ryzen CPU support. AM4 Is Still Going Strong, & AM5 Is Looking To Follow Its Predecessor With Extended Longevity The first AMD AM4 motherboards launched back in 2016. At that time, the socket supported one of the last AMD A-series APU family based on a Non-Zen architecture, called Bristol Ridge. Following these, the company introduced its "Ryzen" family featuring the Zen 1 architecture in 2017. This was followed by new Zen architectures such as Zen+, Zen 2, and Zen 3. Even to […]

Read full article at https://wccftech.com/amd-extends-am5-longevity-through-2029-giving-it-am4-treatment/

Lisuan Tech has launched the latest Gaming Graphics Card for the Chinese markets, the 7G100 Extreme Founders Edition, which is priced around $500. The Lisuan 7G100 Was Looking To Be A Great Graphics Card For Chinese Gamers, But Launch Reviews Show Otherwise In March, Chinese tech company Lisuan Tech unveiled its brand new consumer/prosumer lineup based on its 7G106 GPU. The lineup included four models, three of which were aimed at the Pro/AI segments, & just one that was aimed at the gaming segment. The gaming variant was the Lisuan Extreme "LX 7G100" graphics card, which was specifically designed with […]

Read full article at https://wccftech.com/chinas-first-real-gaming-gpu-7g100-arrives-costs-rtx-5060-ti-money-delivers-rtx-3060-performance/

AMD is reportedly readying a new RDNA 4 GPU, and it's the slowest one yet. However, the specifications reveal the same shader count as the RX 9060 XT. AMD is Quietly Preparing Radeon RX 9050 GPU, Featuring 2048 Stream Processors, 8 GB GDDR6 VRAM, and Up To 2600 MHz Boost The current AMD RDNA 4 lineup has a few SKUs, but AMD appears to be quietly expanding the Radeon RX 9000 series. Up until now, we have only had the Radeon RX 9070 and RX 9060 series, bringing a total of five models, including the Radeon RX 9060, which is […]

Read full article at https://wccftech.com/amd-is-reportedly-preparing-radeon-rx-9050-with-8-gb-vram/

Samsung, SK Hynix, and Micron have reportedly initiated the pre-development phase for DDR6 memory substrates. The major memory manufacturers have requested that substrate partners begin designing components based on partial design data, including early specifications for memory thickness, stack-up structures, and wiring, to prepare prototypes for validation.

The report, from The Elec (via TechPowerUP), states that this collaboration began recently. The joint development between memory and substrate companies typically starts more than two years before a product's launch.

While the JEDEC standard for DDR6 has not yet been finalised (work on it started in 2024), the race to establish the standard is accelerating due to increasing bandwidth demands from the AI sector. DDR6 is expected to deliver a significant performance uplift over DDR5, with target data transfer speeds ranging from 8.8Gbps to 17.6Gbps. This increase is supported by a shift to a 4×24-bit sub-channel architecture, a change from the 2×32-bit structure utilised by DDR5. To address signalling challenges at these higher frequencies, the industry is exploring the use of CAMM2 technology to overcome the physical limitations of traditional DIMM form factors.

Current industry estimates project the commercialisation of DDR6 in 2028 or later, with server platforms expected to lead the transition.

KitGuru says: Do you think the memory market will be better by the time DDR6 launches?

DDR6 memory development is in full swing with major DRAM makers including Samsung, SK Hynix & Micron all racing towards completion to meet growing AI demands. The Next Chapter of DRAM Just Kicked off With Samsung, SK Hynix & Micron All In The Race To Complete DDR6 Development & Deployment By 2028-2029 As AI continues to demand speedier and higher-capacity memory, DRAM makers are now initiating the development plan for next-gen standards. Last year, JEDEC announced the LPDDR6 standard, bringing improved performance and efficiency versus LPDDR5. LPDDR memory has already become the favorite of the AI industry, offering faster speeds, […]

Read full article at https://wccftech.com/ddr6-memory-development-kicks-off-samsung-sk-hynix-micron-race-to-commercialization-by-2028-2029/

Intel's recently released Arc Pro B70 32 GB GPU has been tested in games, outperforming the Arc B580, and trading blows with the RTX 5060 Ti. Intel Arc Pro B70 GPU Gaming Benchmarks Give Us A Hint of What The Arc B770 "Big Battlemage" GPU Could've Offered To Gamers Back in March, Intel launched its Arc Pro B70 graphics card based on the Battlemage BMG-G31 GPU, which we all know as Big Battlemage. This bigger Battlemage chip was long-awaited in the gaming segment, but Intel decided to focus its efforts towards the AI market, equipping the card with a large […]

Read full article at https://wccftech.com/intel-arc-pro-b70-32-gb-gpu-tested-in-games-65-percent-faster-vs-b580-trades-blows-with-5060-ti/

Elon Musk lays out the plans for Tesla's future AI ecosystem, utilizing both Samsung & TSMC 2nm tech for AI6 & AI6.5 chips. Tesla's 2nm Duo Confirmed: AI6 Goes Samsung With LPDDR6 & AI6.5 Goes TSMC With Improved Performance A few days ago, Tesla announced the successful tape out of its AI5 chip, made at Samsung. The chip is just one of the many custom silicon designs that Elon Musk and his enterprises are making to fulfill their in-house AI demand. Musk also talked about the next-generation chips, such as AI6 and the Dojo3 supercomputer project. The company is aiming […]

Read full article at https://wccftech.com/tesla-pulls-2nm-ai-chip-production-onto-us-soil-splits-ai6-ai6-5-between-samsung-tsmc/

With limited reviews available, you will hardly hear about the Arc Pro B70's performance. Here's a sneak peek into the analysis by Hardware Luxx. Hardware Luxx Intel Arc Pro B70 Review Reveals GPU's Performance Against Its Competitors Intel's flagship workstation Big Battlemage GPUs were released roughly two weeks ago, but since then, we have hardly seen any reviews for the Arc Pro B65 and the Arc Pro B70. It appears that the GPUs don't have good availability, and similar to what we heard about the Arc Pro B60 last year, both the newer GPUs may not be that abundant in […]

Read full article at https://wccftech.com/intel-arc-pro-b70-quad-gpu-setup-reportedly-consumes-up-to-720w-in-inference-workloads/

New LLVM patches confirm additional RDNA 4m variants alongside GFX1170 with similar instruction capabilities. AMD Quietly Expands Next-Gen iGPU Roadmap by Adding New RDNA 4m Graphics Targets, GFX1171 and GFX1172 Earlier compiler patches showed that RDNA 4m incorporates several RDNA 4-style instruction-set upgrades, such as support for FP8 and BF8 data formats, along with WMMA matrix instructions used in AI workloads. Now, AMD is further expanding its next-gen integrated GPU roadmap, as new Linux compiler patches unveil two additional RDNA 4m graphics targets. These are the GFX1171 and GFX1172. These targets are now joining the recently discovered GFX1170, confirming that […]

Read full article at https://wccftech.com/amd-adds-rdna-4m-gpu-targets-gfx1171-and-gfx1172-hinting-at-next-gen-zen-6-apu-graphics/

Future Intel Desktop sockets might support several generations of CPUs, as hinted by Robert Hallock in an interview with Club386. Intel Might Finally Offer Extended Desktop Socket Support For Multiple CPU Generations If there's one area where Intel has lagged versus AMD, that's socket support. Since the release of the first "Ryzen" CPU back in 2017, AMD has released two sockets, AM4 and AM5. Meanwhile, Intel has a total of four socket releases since then, starting with LGA 1151, LGA 1200, LGA 1700, & the most recent, LGA 1851 socket. Later this year, Intel will release a fifth socket, LGA […]

Read full article at https://wccftech.com/intel-offer-amd-like-desktop-socket-longetivity-supporting-multiple-cpu-generations/

Tenstorrent has unveiled its TT-QuietBox 2 AI Workstation, powered by the RISC-V architecture, featuring liquid cooling & 128 GB of VRAM for $9999. Tenstorrent Makes Its Own Liquid-Cooled & Fully RISC-V Powered AI Workstation With The Ability To Run 120B Models With Ease The Tenstorrent TT-QuietBox 2 is an AI workstation designed to fulfill the needs of AI enterprises and customers. It features the company's Blackhole AIC, which is powered by 16 big RISC-V cores & pack up to 32 GB of GDDR6 memory. The QuietBox 2 is configured with up to four of these Blackhole cards and up to […]

Read full article at https://wccftech.com/tenstorrent-tt-quietbox-2-risc-v-ai-workstation-128-gb-memory-liquid-cooling-9999-usd/

After the regular fan version, MAXSUN has also debuted two more Arc PRO B60 Dual cards, featuring fanless and liquid-cooled designs. MAXSUN Officially Introduces Single-Slot Arc PRO B60 Dual 48G Liquid Edition, Equipped With 16-pin Power Connector It's not just the Turbo edition that comes with the 16-pin power connector; the new "Liquid-Cooled" Intel workstation GPU also features the same connector on the PCB. MAXSUN has introduced two new editions for the Arc PRO B60 Dual 48G card, including a Passive one and a Liquid-Cooled edition. Last year, the company debuted the Arc PRO B60 Dual 48G Turbo, which brought […]

Read full article at https://wccftech.com/maxsun-unveils-liquid-cooled-intel-arc-pro-b60-dual-48g-liquid-gpu-with-12v-2x6-connector/