AI predictions and announcements filled the news this week, including a statement from the Center for AI Safety that was signed by some top AI execs — including Sam Altman, CEO of OpenAI — warning that uncontrolled AI could end up smarter than us and lead to our extinction. Foxconn estimates its artificial intelligence server revenue will double this year with the popularity of generative AI. Tenstorrent, an AI chip startup headquartered in Canada, is working with LG Electronics to design and produce new RISC-V, AI, and video codec chiplets for LG’s TV and automotive products and Tenstorrent’s ..read more

Arm debuted its latest platform for mobile computing. Arm Total Compute Solutions 2023 adds the new Immortalis-G720 GPU based on the 5th Generation GPU architecture, which redefines parts of the graphics pipeline to reduce memory bandwidth for the next generation of high geometry games and real-time 3D applications. The company also added two new Mali GPUs. In addition, Arm introduced a cluster of Armv9 CPUs, which it claims offers double-digit performance gains alongside significant efficiency improvements. CPU introductions include the high-performance Cortex-X4, which was taped out on the T ..read more

A technical paper titled “Benchmarking and modeling of analog and digital SRAM in-memory computing architectures” was published by researchers at KU Leuven. Abstract: “In-memory-computing is emerging as an efficient hardware paradigm for deep neural network accelerators at the edge, enabling to break the memory wall and exploit massive computational parallelism. Two design models have surged: analog in-memory-computing (AIMC) and digital in-memory-computing (DIMC), offering a different design space in terms of accuracy, efficiency and dataflow flexibility. This paper targets the fair compariso ..read more

A technical paper titled “Chip-Chat: Challenges and Opportunities in Conversational Hardware Design” was published by researchers at NYU and University of New South Wales. Abstract “Modern hardware design starts with specifications provided in natural language. These are then translated by hardware engineers into appropriate Hardware Description Languages (HDLs) such as Verilog before synthesizing circuit elements. Automating this translation could reduce sources of human error from the engineering process. But, it is only recently that artificial intelligence (AI) has demonstrated capabilitie ..read more

A new technical paper titled “An Experimental Analysis of RowHammer in HBM2 DRAM Chips” was published by researchers at ETH Zurich and American University of Beirut. Abstract: “RowHammer (RH) is a significant and worsening security, safety, and reliability issue of modern DRAM chips that can be exploited to break memory isolation. Therefore, it is important to understand real DRAM chips’ RH characteristics. Unfortunately, no prior work extensively studies the RH vulnerability of modern 3D-stacked high-bandwidth memory (HBM) chips, which are commonly used in modern GPUs. In this work, we experi ..read more

The recent AutoSens conference in Detroit left me questioning whether I should turn in my driver’s license. The answer the attending OEMs gave to all the discussions about the advantages of RGB cameras, ultrasound, radar, lidar, and thermal sensors was a unanimous “We probably need all of them in some form of combination” to make autonomy a reality in automotive. Together, these sensors are much better than my eyes and ears. Technology progress is speedy in Automated Driving Assistance Systems (ADAS) and autonomous driving, but we are not there yet holistically. So I am keeping my license for ..read more

Over the last few years, the basic architecture of how a vehicle is put together has changed a lot. This has also resulted in a change in how the automotive supply chain is put together, too. The traditional ECU-based architecture and the automobile supply chain Historically, vehicles have been put together like the picture on the left in the above diagram. Vehicles could have as many as 100+ electronic control units, or ECUs. If you don’t know much about the automotive industry beyond driving your own car, you might assume that the automobile manufacturer (Ford, say) designed and b ..read more

Cyberattacks are increasing in frequency and sophistication, and the impact of those attacks is increasing almost exponentially as the amount and value of data continues to grow. Cybersecurity Ventures projected the annual cost of cybercrime will grow from $8 trillion in 2023 to $210.5 trillion by 2025, with no end in sight. On the target list are a slew of industrial and commercial segments, including health care, infrastructure, banking, and education, as well as government agencies. The question now is how “unbreakable” can these systems really be, and what is the cost? More cyberattacks ar ..read more

Security is becoming a bigger issue in AI and machine learning chips, in part because the chip industry is racing just to get new devices working, and in part because it’s difficult to secure a new technology that is expected to adapt over time. And unlike in the past, when tools and methodologies were relatively fixed, nearly everything is in motion. Algorithms are being changed, EDA tools are incorporating, and chips themselves are disaggregating into component parts that may or may not include some form of AI/ML/DL. The result is much greater potential for mischief, for IP theft, and for fr ..read more

By Dan Yu, Harry Foster, and Tom Fitzpatrick Welcome to the era of EDA 4.0, where we are witnessing a revolutionary transformation in electronic design automation driven by the power of artificial intelligence. The history of EDA can be delineated into distinct periods marked by significant technological advancements that have propelled faster design iterations, improved productivity, and furthered the development of intricate electronic systems. Notably, the advent of EDA 1.0 was ushered in by the introduction of SPICE (simulation program with integrated circuit emphasis) at the University of ..read more