Highly-Efficient New Neuromorphic Chip for AI on the Edge

Brasil Notícia Notícia

Highly-Efficient New Neuromorphic Chip for AI on the Edge
Brasil Últimas Notícias,Brasil Manchetes
  • 📰 SciTechDaily1
  • ⏱ Reading Time:
  • 71 sec. here
  • 3 min. at publisher
  • 📊 Quality Score:
  • News: 32%
  • Publisher: 68%

The NeuRRAM chip is the first compute-in-memory chip to demonstrate a wide range of AI applications while using just a small percentage of the energy consumed by other platforms while maintaining equivalent accuracy. NeuRRAM , a new chip that runs computations directly in memory and can run a wid

The research team, co-led by bioengineers at the University of California San Diego , presented their results in the August 17 issue ofThe NeuRRAM chip uses an innovative architecture that has been co-optimized across the stack. Credit: David Baillot/University of California San Diego

To solve this data transfer issue, researchers used what is known as resistive random-access memory. This type of non-volatile memory allows for computation directly within memory rather than in separate computing units. RRAM and other emerging memory technologies used as synapse arrays for neuromorphic computing were pioneered in the lab of Philip Wong, Wan’s advisor at Stanford and one of the main contributors to this work.

“This chip now provides us with a platform to address these problems across the stack from devices and circuits to algorithms,” said Siddharth Joshi, an assistant professor of computer science and engineering at the One key contribution of the paper, the researchers point out, is that all the results featured are obtained directly on the hardware. In many previous works of compute-in-memory chips, AI benchmark results were often obtained partially by software simulation.

In addition, Wan is a founding member of a startup that works on productizing the compute-in-memory technology. “As a researcher and an engineer, my ambition is to bring research innovations from labs into practical use,” Wan said.The key to NeuRRAM’s energy efficiency is an innovative method to sense output in memory. Conventional approaches use voltage as input and measure current as the result. But this leads to the need for more complex and more power-hungry circuits.

Resumimos esta notícia para que você possa lê-la rapidamente. Se você se interessou pela notícia, pode ler o texto completo aqui. Consulte Mais informação:

SciTechDaily1 /  🏆 84. in US

Brasil Últimas Notícias, Brasil Manchetes

Similar News:Você também pode ler notícias semelhantes a esta que coletamos de outras fontes de notícias.

PICK SIX: Freshmen with high expectations to watch in 2022PICK SIX: Freshmen with high expectations to watch in 2022Highly touted blue-chip prospects often arrive on campus with fans' expectations very high, almost to the point of unfairness.
Consulte Mais informação »

Chip and Dale Rescue Rangers Are Back with Beast Kingdom’s DAHChip and Dale Rescue Rangers Are Back with Beast Kingdom’s DAHit is time for the return of the Rescue Rangers as Chip and Dale are back and better than ever with new set of figures from Beast Kingdom
Consulte Mais informação »

REVIEW: 'House of the Dragon' is spectacular in every sense of the wordREVIEW: 'House of the Dragon' is spectacular in every sense of the wordREVIEW: 'House of the Dragon' is spectacular in every sense of the word, writes Peter Travers.
Consulte Mais informação »

Edge of Spider-Verse Brings Back Spider-Ham, Introduces Cinderella-Themed Hero SpinstressEdge of Spider-Verse Brings Back Spider-Ham, Introduces Cinderella-Themed Hero SpinstressA fan-favorite Spider hero returns and a new one debuts in Edge of Spider-Verse 4. The September [...]
Consulte Mais informação »

5 Self-Care Essentials Bond No.9 Founder Laurice Rahmé Swears By5 Self-Care Essentials Bond No.9 Founder Laurice Rahmé Swears By'I always recommend efficient relaxation and deep breathing—you cannot do better than that.'
Consulte Mais informação »

One in 10 Bay Area neighborhoods is ‘highly segregated’ enclave of White wealth, new report saysOne in 10 Bay Area neighborhoods is ‘highly segregated’ enclave of White wealth, new report saysThe Bay Area Equity Atlas found that the most segregated communities are in San Mateo, Marin and Contra Costa counties.
Consulte Mais informação »



Render Time: 2025-03-01 03:42:13