This is the goal of a new “ChipGPT” type tool, that Cadence Design Systems is bringing to market, which employs Large Language Models and generative AI to do much of the heavy lifting in this early semiconductor definition and design verification phase.
Read MoreIt turns out that virtually all of the major players in the space turned to multi-die systems, which have supplanted large monolithic chips for many applications. For the uninitiated, multi-die systems are essentially chips that feature multiple silicon dies, often dubbed chiplets, integrated into a single package.
Read MoreNow it seems the US Congress is setting its sights on securing an even more pervasive network of systems and devices, known as the IoT, or the Internet of Things. However, this time the initiative could impact literally millions of devices and systems already deployed here in the US, from fire and police communications systems, to the automotive industry and critical infrastructure, like public utilities and modern smart city communication networks.
Read MoreThe digitization of the modern car or truck has kicked into high gear over the past few years, from Advanced Driver Assistance Systems (ADAS) and Infotainment systems, to ECUs for engine control, PCMs for powertrain control, and more. It’s against the backdrop of this major growth trajectory that EDA (Electronic Design Automation) semiconductor tools bellwether, Synopsys, stepped out today to announce the acquisition of German automotive software testing and verification house PikeTec GmbH, for an undisclosed sum.
Read MoreNVIDIA RTX 40 Series STEM Laptops Offer Next-Level Performance Gains Over Mainstream Machines
Read MoreArtificial Intelligence is a new hotbed of opportunity, and along with this new market comes a requirement for a very different set of silicon and software solutions to accelerate and process specialized AI workloads. It’s in this burgeoning field that Tenstorrent hopes to disrupt the silicon landscape with more flexible chip architectures not based on either of the legacy X86 or Arm instruction sets and ecosystems, but instead on the open standard RISC-V instruction set architecture that’s available royalty free and open source.
Read MoreThrough the pandemic, I became passionate about photography. Although I’ve technically been doing “professional” product photography for articles featured on-line and in print for a couple of decades, it was only in the last few years that I stepped up my game. As much as I love my pro camera gear though, it’s not something you can carry around perpetually. As the old saying goes, “the best camera is the one that’s with you”, and like most of you, my smartphone camera is the one that’s almost always within reach. So, when presented with the opportunity to test a couple of the top smartphones for photography, I jumped at the chance.
Read MoreThis morning, AMD marked yet another milestone with the announcement of its new Versal Premium VP1902 adaptive SoC (System On Chip) products. Semiconductor chip design is challenging and expensive. As such, there’s a lot of emulation, prototyping and verification work that goes into designing the next greatest processor, accelerator or platform product, and that’s where FPGAs (Field Programmable Gate Arrays) come in. You can think of FPGAs as both a virtual and physical sandbox for chip engineers to work in and emulate their designs in pre-production silicon, before committing to sending them out to expensive tape-out and chip fab processes for production ASIC (Application Specific IC) designs.
Read MoreAn ergonomic workspace is vital for comfort and long-term employee health. A poorly optimized setup can result in increased fatigue, loss of focus, or even potential injuries. A worker’s comfort and ergonomic needs, however, can vary over time, often as frequently as multiple times a day for different activities. As such, it is important for elements such as the keyboard, mouse, monitor(s), and chair to be as adjustable as possible.
Read MoreToday, at its Data Center and AI Technology event in San Francisco, Advanced Micro Devices (AMD) announced the availability of its 4th Gen EPYC data center processor expansion based on the company’s Bergamo and Genoa-X CPU architectures for cloud-native, general-purpose compute and HPC (High Performance Computing) workloads, respectively. The company also announced it will sample its new Instinct MI300X AI accelerator later this year, along with its Infinity Architecture platform that incorporates up to eight MI300X accelerators together for complex AI inferencing and training workloads.
Read MoreHigh-End Smartphone Camera Systems Require Massive Processing Power
Read MorePC gaming is big business these days, from eSports to game streaming, and the lion’s share of the unit volume in the GPU market is delivered at price points south of $400, driving display resolutions at 1080p. This is the target gamer demographic that Nvidia’s recent GeForce RTX 4060 Ti is aimed to address, and this week AMD launched an even more budget-friendly offering of its own with the new Radeon RX 7600, that drops in at just $269…
Read MoreThe PC gaming market is big business these days, and hard core gaming enthusiasts love burly, flagship graphics cards that are frankly too expensive for most mainstream consumers.
Read MoreQualcomm was able to get Stable Diffusion running on a hand-held device without internet connectivity, by optimizing and scaling the AI model down to run on more efficient INT8 (8-bit integer) precision operations, rather than the larger, more complex FP32 (32-bit floating point) operations that were used to train the model. The result is that for inference (running the model to accurately create the image and inferring details from text), the Stable Diffusion model was shrunk dramatically, or quantized, to a fraction of its size with little to no degradation in accuracy, but with significantly better performance on a low-power Snapdragon AI accelerator (Qualcomm Hexagon Processor) with much less storage and memory bandwidth required.
Read MoreAt this moment in time, there are a myriad of resolution upscaling technologies available across the console, mobile and PC gaming markets. NVIDIA offers DLSS (Deep Learning Super Sampling), AMD offers FSR (FidelityFX Super Resolution), Intel has XeSS (Xe Super Sampling), and there are a number of more basic Integer and Bilinear upscaling solutions out there as well, not to mention simplified scaling tools integrated directly into some game engines.
Read MoreThe reality of trillion transistor chips is something that Dr. Anirudh Devgan of Cadence Design Systems feels is attainable by the year 2030, though he and his company have a vision of bringing the power of simulation, modeling and computational software to far more than just semiconductor chip design.
Read MoreSome estimates claim the global video streaming market was valued at over $89 billion in 2022, with expectations that it would expand at a compound annual growth rate (CAGR) of 21.5% between now 2030. As the industry expands, the demand for servers and appliances purpose-built to handle the workloads and optimize for latency, bandwidth, density and power will commensurately expand as well.
Read MoreAt its longstanding SNUG (Synopsys Users Group) Conference, currently underway at the Santa Clara Convention Center in California, Synopsys unveiled powerful additions to its AI-enhanced Electronic Design Automation (EDA) tools suite, with new solutions for functional verification and silicon testing, aptly named Synopsys VSO.ai and Synopsys TSO.ai, respectively. VSO.ai and TSO.ai join the company’s existing DSO.ai to complete what Synopsys is calling Synopsys.ai for chip design.
Read MoreWhile virtually all of the industry is buzzing about AI, accelerated computing and AI powerhouse NVIDIA has just announced a new software library, called cuLitho, that promises an exponential acceleration in chip design development times, as well as reduced chip fab data center carbon footprint and the ability to push the boundaries of bleeding-edge semiconductor design. In fact, NVIDIA cuLitho has already been adopted by the world’s top chip foundry, TSMC, leading EDA chip design tools company Synopsys and chip manufacturing equipment maker ASML.
Read MoreIntel made a couple of announcements this morning that relate to its leadership teams across multiple groups within the company. First, on a more positive note, Intel has appointed Stuart Pann to Lead Intel Foundry Services. Pann, whose title will be senior vice president and general manager of Intel Foundry Services (IFS), will report to Intel CEO Pat Gelsinger.
Read More
