Goto

Collaborating Authors

AI chip startup Ceremorphic comes out of stealth mode

ZDNet

The battle to change the computer industry so that machines can better compute artificial intelligence tasks, especially deep learning, continues to birth new and interesting potential future stars. On Monday, Ceremorphic of San Jose, California, formally debuted chip efforts that have been kept in a stealth mode for two years, discussing a chip the company claims will revolutionize the efficiency of A.I. computing in terms of power consumption. "It's counterintuitive today, but higher performance is lower power, said Venkat Mattela, founder and CEO of the company, in an interview with ZDNet via Zoom. Mattela believes that numerous patents on low-power operation will enable his company's chip to produce the same accuracy on signature tasks of machine learning with much less computing effort. "What I'm trying to do is not just building a semiconductor chip but also the math and the algorithms to reduce the workload," he said.


Wi-Fi Is The Only Technology That Can Prevail The Longest

#artificialintelligence

A. When we started with nine technologies in 2002, a couple of them died a little later. Ethernet is the best proven and known networking technology but what is the equivalent of it in wireless? It's called Wireless Local Area Network (WLAN). Other wireless technologies are not WLAN, because it is the only wireless technology developed for networking. Wi-Fi has been able to deliver good throughput at a much lower power consumption than cellular with Bluetooth being the only technology better than it.


Two professors just won a $1 million prize for inventing chips that made every PC and phone faster

#artificialintelligence

Dave Patterson and John Hennessy, two San Francisco Bay Area professors now associated with Google, have won the computing industry's top prize for revolutionizing processors with a technology called RISC. The pair won the 2017 A.M. Turing Award from the Association for Computing Machinery, a $1 million prize named after the British researcher who famously helped crack German Enigma codes in World War II and lay the foundations of computer science. The high-prestige award is considered the Nobel Prize for computer science. RISC, short for reduced instruction set computing, gave a major performance boost to processors, fueled the growth of upstarts like Silicon Graphics and Sun Microsystems, and paved the way for today's smartphone industry. It's been a remarkable success over the last three decades, and one emblematic of the Silicon Valley ethos of throwing out the old way of doing things.


Startup Adds Artificial Intelligence to Debugging Tool

#artificialintelligence

Today, chips can be manufactured with a wide range of semiconductor IP, ranging from central processing (CPUs) and graphics processing units (GPUs) to power management and other analog devices, arranged on a single slab of silicon like articles on the front page of a newspaper. Not only are SoCs taking longer and longer to design, adding to overall engineering costs, but the manufacturing costs are also mounting. Testing that the hardware and software are functioning correctly is also growing more expensive. Trying to change that is UltraSoC, which has announced a new debugging tool that can evaluate complete SoCs rather than just individual cores. UltraSoC said that the new UltraDevelop tool can trim development costs, save time and even enhance software running on multicore, multithreaded chips using a number of different architectures.


NetSpeed and Esperanto Partner to Power SoCs for Artificial Intelligence

#artificialintelligence

AI applications demand new architectures to meet the need for unprecedented performance, sophisticated functionality and ultra-low power. Interconnect technology is a critical component of these architectures. "We are still in the early stages of AI maturity, but what we've learned is that sophisticated neural networks require tremendous performance," said Linley Gwennap, principal analyst at The Linley Group. "Generating this level of performance often requires a large number of cores, but these architectures can be difficult to design and test. NoC technology, such as NetSpeed's, has become an important enabling technology for AI because it automates the process of connecting CPUs and accelerators on a complex SoC." "Esperanto is putting thousands of processors and accelerators on a single chip, and our challenge was how to interconnect them.