Kepler Computing claims a new approach to chip design--and a proprietary material--can help end the supply bottlenecks that have sent memory prices surging. An ambitious chip startup that has spent more than seven years quietly trying to redesign the architecture for computer memory has just come out of stealth mode and believes its new approach can help ease the global memory-chip shortage --provided it can produce its technology at scale. Kepler Computing, a San Jose, California-based startup founded in 2018 by a team of physicists and computer scientists, says it has developed a new architecture for high-bandwidth memory (HBM) that directly addresses some of the chip supply bottlenecks that are constraining the computing market. While chipmakers typically rely on expensive extreme ultraviolet lithography (EUV) to shrink the transistors on a chip, thereby packing more technology into the same amount of space, Kepler claims that its "3D stacking" approach and a proprietary new material allow it to increase density without relying on EUV at all--and it can work with existing semiconductor fabrication plants. Kepler says it has made similar gains for the high-speed cache memory typically used in CPUs, GPUs, and XPUs.

Artificial intelligence (AI) technology has made great strides in recent years, evolving from limited use in a small number of applications into …

Imec and GlobalFoundries have demonstrated a processor-in-memory chip that can achieve energy efficiency up to 2900 TOPS/W, approximately two orders of magnitude above today's commercial processor-in-memory chips. The chip uses an established idea, analog computing, implemented in SRAM in GlobalFoundries' 22nm fully-depleted silicon-on-insulator (FD-SOI) process technology. Imec's analog in-memory compute (AiMC) will be available to GlobalFoundries customers as a feature that can be implemented on the company's 22FDX platform. Analog compute Analog compute, or processor-inmemory, is an established technique that is already used in commercial AI accelerator chips from startups Mythic, Syntiant, Gyrfalcon and others. Since a neural network model may have tens or hundreds of millions of weights, sending data back and forth between the memory and the processor is inefficient.

Electric carmaker Tesla Inc is working with Advanced Micro Devices Inc to develop its own artificial intelligence chip for self-driving cars, CNBC reported on Wednesday, citing a source familiar with the matter. AMD spin-off GlobalFoundries Inc Chief Executive Sanjay Jha said his company is working directly with Tesla, according to the CNBC report. GlobalFoundries, which fabricates chips, has a wafer supply agreement in place with AMD. Electric carmaker Tesla Inc is working with AMD to develop its own artificial intelligence chip for self-driving cars, CNBC reported on Wednesday, citing a source familiar with the matter. Tesla isn't completely going it alone in chip development, according to the source, and will build on top of AMD intellectual property, CNBC reported.

Looking toward a future in which AI and human skills combine to resolve problems, Higashi predicted that today's Von Neumann-based architectures and neuromorphic device will complement each other. AI also will play a role in enhancing the immersive experiences promised by virtual reality, experiences which visionaries have predicted but which thus far mankind "has never fully experienced." When the industry moved from 28nm to 14nm technologies, performance increased by fully 50 percent. "Memory, logic, and sensing make it possible for AI systems to solve problems much faster than a team of geniuses.