NVLink Fusion represents a new branch of how Nvidia approaches the cloud data center and hyperscaler markets, empowering partners like Qualcomm, Marvell, Fujitsu and MediaTek to design purpose-built silicon solutions that can interface directly to Nvidia’s Blackwell GPU architecture via the company’s now open and extensible NVLink architecture.

EPYC 4005 Series spec sheets may not stand out versus high-end server platforms, but this new AMD CPU family is a smart, strategic play in a fast-growing segment.

Built in collaboration with Nvidia, and leveraging the latter’s latest Blackwell GPU architecture, the M2000 is more than a spec sheet upgrade—it’s a structural shift in how simulation infrastructure is architected.

SiTime, a Silicon Valley company specializing in MEMS-based timing solutions — tiny mechanical structures built on silicon that deliver precise system clock timing with superior resilience to shock, vibration, and temperature fluctuations — is expanding its footprint to the mobile market with the introduction of its SiT30100 Symphonic clock generator.

Intel has to establish more trust in the industry and not only prove the competitiveness of its processes, but also that partners can make the chips with familiar and established workflows, consistently and with high reliability. Just about everything I heard today made me believe Intel is on track to do just that.

In a joint announcement reflecting the growing importance of ecosystem collaboration in semiconductor design, Synopsys and Intel Foundry have expanded their partnership in support of chip development on Intel’s 18A and 18A-P process technologies.

At Intel Vision 2025, newly appointed CEO Lip-Bu Tan took the stage to outline his plans for Intel's future.

Chips and systems are getting more complex and there is a shortage of humans with the experience and expertise to design and build them. Faster, more capable, intelligent tools are paramount to ensure quality and ensure optimal time to market.

From Copilot+ PCs to gaming, AI-enhanced printing and IT management tools, HP made it clear that its embedding AI across its product lines to streamline workflows, boost security, and optimize hybrid work environments.

Nvidia has been working on a set of performance testing tools, called DGX Cloud Benchmark Recipes, that are designed to help organizations evaluate how their hardware and cloud infrastructure perform when running the most advanced AI models available today. Our team at HotTech had a chance to kick the tires on a few of these recipes recently, and found the data they can capture to be extremely insightful.

Intel launched its high-performance Arrow Lake-H and HX series mobile processors, officially known as the Core Ultra 200H and 200HX, at CES 2025 and showed off an array of partner systems based on the chips as well. For those unfamiliar, Arrow Lake-H is very different than the lower-power Lunar Lake-based Core Ultra 200S series for notebooks that launched a few months back. Arrow Lake-H is a higher-power mobile platform, that uses the same “Lion Cove” P-cores and “Skymont” E-cores as Arrow Lake-based desktop processors, but tuned for lower-power mobile applications. Arrow Lake-H also features an NPU and a relatively powerful integrated Xe-LPG+ GPU, but the NPU isn’t quite as powerful as what’s utilized in Lunar Lake. In fact Arrow Lake-H’s NPU is akin to the one Intel employed on the previous-gen Meteor Lake and desktop Arrow Lake processors. Don’t let that make you think Arrow Lake-H isn’t well suited for AI workloads, though.

leaders in the EDA space like Cadence have continuously bolstered their toolsets to better assist customers of all sizes in the design, simulation and testing of their wares. But a few weeks ago, Cadence took things a significant step further, and actually architected, designed, and taped out what the company calls the industry’s first Arm-based system chiplet, in an effort to help customers design and implement their own chiplets.

Just as it leads in data center AI accelerators, NVIDIA’s lead in the PC graphics space has been dominant for years and generations of products. When the company announced its forthcoming GeForce RTX 50 series of graphic cards based on its Blackwell GPU architecture back at CES in Las Vegas this year, there was almost no question as to whether NVIDIA would have the most powerful product on the market, competitively, when cards ship to gamers later this month. However, details and the nuanced picture of performance with the new GeForce RTX 5090, which is first out of the gate, had to wait until today’s embargo lift.

It’s not uncommon to see major chip players introduce new and novel approaches to traditional computing paradigms at CES in Las Vegas in January. And if ever there was a limelight moment in that regard, AMD found it with the introduction of its new chip and platform architecture formerly known by the code name Strix Halo, and unveiled officially last week as Ryzen AI Max Series. This chip cojoins existing AMD CPU and GPU architectures, along with a high speed memory interface, in an unprecedented way, compared to traditional X86 laptop or desktop chip designs. And it’s safe to say this new Application Processing Unit, as AMD likes to call them, stole the show for many…

At what was likely the most widely attended keynote in CES history, Nvidia CEO Jensen Huang took to the stage at the jam-packed Michelob Ultra arena, with a dizzying array of announcements of new technologies, from consumer devices like the new GeForce RTX 50 Series of gaming graphics cards, to a new secure autonomous vehicle platform called Thor that’s based on the company’s latest Blackwell GPU technology, and more – a lot more. However, a new Nvidia generative AI technology dubbed Cosmos, that some folks might have glossed over due to its complexity was, in my opinion, another star of the show. I’d even dare say, if Cosmos plays out as the company is intending, it could be a launch-pad for rocketing Nvidia’s robotics and autonomous vehicle businesses…

Dave Altavilla says the train won't slow down "anytime soon" with demand outstripping supply. Near-double earnings on the quarter and exponential data center growth still take a backseat as clients await Nvidia's (NVDA) Blackwell chip set to ramp-up even more in 2025…

Qualcomm’s Snapdragon X Elite has caused quite the shake-up in the laptop market, with very competitive performance, fantastic battery life and a dedicated 45 TOPS neural engine for currently evolving AI workloads. I’ve written about Snapdragon X-based laptops and the platform in the past, but in this report, I’m going to delve into my experience living on Lenovo’s new Snapdragon X Elite-powered Yoga Slim 7x laptop, using the machine as my daily driver and travel workhorse.

RISC-V chip design and IP powerhouse, SiFive, just announced availability of its new HiFive Premier P550 development board, and it's sure to make waves at the RISC-V Summit this week in Santa Clara. The new board is being billed as the highest-performing RISC-V development vehicle to date. If you're looking to push the boundaries of what's possible with RISC-V, this could be the test and development platform you’ve been waiting for.

On October 10th, Intel took the wraps off its new Core Ultra 200S series of desktop processors, formerly know by the code name Arrow Lake. As a follow-on to the company’s recent Lunar Lake Core Ultra 200V Series for laptops, Arrow Lake marks a transition that follows suit with Intel’s tiled architecture approach for its processors, which was first introduced with the Meteor Lake Core Ultra 100 series for laptops back in late 2023 in the consumer space. Intel’s tiled chiplet design, with external chip fabrication at TSMC that’s coupled with Intel’s cutting-edge Foveros chip stacking and packaging tech, has served the company well thus far. Further expanding this design approach to its desktop chip portfolio is likely just what the doctor ordered…

The Synsopsys 40G UCIe IP affords up to 12.9Tbps per mm of data to efficiently travel between heterogeneous and/or homogeneous chiplet dies, with minimal silicon footprint. Higher bandwidth between chiplets is critical for enabling next-generation processor designs, and advanced AI and automotive ADAS systems, which must move massive amounts of data. Of note is that, despite its higher performance, Synopsys’ IP remains compliant with the UCIe 2.0 specification.