Esperanto teams up with Rapidus for ‘post-GPU’ AI

Esperanto teams up with Rapidus for ‘post-GPU’ AI

Business news |
By Peter Clarke

RISC-V processor developer Esperanto Technologies Inc. (Mountain View, Calif.) has teamed up with Japanese foundry Rapidus Corp. to develop AI processors.

Esperanto claims that the partnership will enable more energy-efficient designs for an upcoming “post-GPU era.”

Esperanto has signed a Memorandum of Cooperation with Rapidus, which aims to begin mass production on a 2nm manufacturing process in 2027 with a focus on enabling faster time-to-market for customers.

 The initial focus of the partnership is to enable the development of more energy efficient solutions for AI inference and high performance computing workloads for data center and enterprise edge applications.

The global electricity consumption of data centers was an estimated 460 terewatt-hours (TWh) in 2022 and could exceed 1,000 TWh in 2026 according to the International Energy Agency (IEA). This demand is roughly equivalent to the entire electricity consumption of Japan.

“Rapidus represents a new approach to leading-edge semiconductor manufacturing, and we are very impressed with the direction and speed at which they are operating,” said Art Swift, CEO of Esperanto Technologies, in a statement. “The strategic partnership with Rapidus plays a key role in our expansion plans, particularly in Japan. Along with our other partners there, we hope our new relationship will extend the benefits of our energy efficient technology to a broader set of AI chip designers in the future.”

Related links and articles:

News articles:

Esperanto runs generative-AI on RISC-V

Tenstorrent to help design 2nm edge AI accelerator in Japan

Rapid Silicon lets engineers use GPT for FPGA design

Interview: Henri Richard on Rapidus, experience and ecosystem

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News


Linked Articles