- Esperanto’s low-power design techniques enable Esperanto’s RISC-V-based processors to function in a single package with meager power.
- Esperanto plans to use IFS leading-edge silicon and advanced packaging technologies for the next generation massively parallel RISC-V-based AI accelerator.
Esperanto Technologies, a prominent developer of high-performance, energy-efficient Artificial Intelligence (AI) inference accelerators based on the RISC-V (Reduced Instruction Set Computer) instruction set, publicized that the company is entering a strategic partnership with Intel. The primary vision of Esperanto is to advance its massively parallel RISC-V-based AI acceleration solutions.
Through the partnership, Esperanto Technologies will be leveraging Intel Foundry Services (IFS) silicon and chiplet packaging technologies. This will allow Esperanto to advance its RISC-V-based technology and deliver massively parallel AI acceleration silicon solutions ranging from cloud to edge.
“Intel Foundry Services is excited to add Esperanto’s massively parallel AI accelerators to the IFS ecosystem,” said Bob Brennan, Vice President and General Manager of IFS Customer Solutions Engineering. “The combination of Esperanto’s low-power design techniques and IFS advanced silicon and packaging technologies should enable thousands of Esperanto’s RISC-V based processors to operate in a single package with remarkably low power.”
“Esperanto builds on top of the RISC-V ecosystem to deliver our leading AI acceleration solutions. Intel’s announcements of support and investment in the RISC-V Community are invaluable in helping to advance and proliferate RISC-V solutions from Esperanto and others, ultimately benefiting all end users,” said Art Swift, President and CEO at Esperanto Technologies.
“Esperanto plans to use Intel Foundry Services leading edge silicon and advanced packaging technologies with our next generation massively-parallel RISC-V based AI accelerators,” said David Ditzel, Founder and Executive Chairman at Esperanto Technologies. “Intel Foundry Services’ unique packaging technologies will make chiplet solutions both practical and cost effective, enabling a range of acceleration products to span from cloud to edge.”
Being an AI RISC-V leader, Esperanto Technologies will offer massively parallel 64-bit RISC-V-based Tensor compute cores. This is currently delivered as a single chip with 1088 ET-Minion compute cores and a high-performance memory system.
Esperanto’s existing RISC-V-based inference device is a general-purpose, parallel processing solution that can accelerate numerous parallelizable functions. It is designed to fulfill large-scale data center customers’ high-performance and low-power requirements. It is intended to perform well in any Machine Learning (ML) task and to excel at ML recommendation models, one of the most valuable types of AI workloads in several large data centers.