NetSpeed and Esperanto Partner to Power SoCs for Artificial Intelligence
San Jose, Calif. -- May 7, 2018 — NetSpeed Systems and Esperanto Technologies today announced that Esperanto has licensed NetSpeed’s IP and intelligent design environment for its Supercomputer-on-a-Chip for Artificial Intelligence (AI) applications. Esperanto’s 7nm chip will integrate thousands of RISC-V compatible processors each with vector/tensor accelerators and all connected with NetSpeed’s NoC IP.
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. NetSpeed provided a compelling solution for interconnecting our cores with high performance and by licensing their IP we can reduce our time to market as well,” said Dave Ditzel, CEO of Esperanto Technologies.
Esperanto’s high-performance ET-Maxion™ cores are designed to deliver the highest single thread RISC-V performance. Its ET-Minion™ cores are designed for energy efficiency and high floating point throughput, including vector/tensor acceleration. With thousands of energy efficient 64-bit RISC-V cores on one chip, Esperanto will deliver industry-leading TeraFlops/Watt of scalable computing performance for artificial intelligence, machine learning and other applications.
"NetSpeed and Esperanto share a similar gene—we are both at the leading edge of what can be done in our respective domains," said Sundari Mitra, CEO of NetSpeed. "While Esperanto is focused on bringing AI to high-volume applications through their highly-parallel architecture leveraging the RISC-V instruction set, NetSpeed is focused on bringing the power of machine learning to SoC design and architecture. It is indeed an honor to work with a trailblazing partner like Esperanto. This design win is a further validation of our leadership in the AI market."
About NetSpeed Systems
NetSpeed is at the heart of next-gen system-on-chip (SoC) applications that are transforming the way we interact with each other and how we connect with the world. Whether you are a hardware architect looking for cache coherency solutions to realize your ideas into silicon or a SoC designer looking for a high performance and efficient interconnect or a safety manager looking for solutions to build resilient, fault-tolerant systems—NetSpeed has a solution for you. Learn about how NetSpeed is bringing the power of artificial intelligence to SoC design and architecture at www.netspeedsystems.com.
About Esperanto Technologies
Esperanto Technologies develops high-performance, energy-efficient computing solutions based on the open standard RISC-V ISA. Esperanto is headquartered in Mountain View, California with engineering sites in the United States, European Union, and Eastern Europe. Esperanto has brought together a seasoned team of experienced processor and software engineers with the goal of making RISC-V the architecture of choice for compute-intensive applications such as Machine Learning. For more information, please visit https://esperanto.ai.
Related Semiconductor IP
- NoC System IP
- Cloud-active NOC configuration tool for generating and simulating Coherent and Non-Coherent NoCs
- Tessent NoC Monitor
- Network-on-Chip (NoC) Interconnect IP
- Coherent Network-on-chip (NoC) IP
Related News
- Esperanto Technologies Plans Energy-Efficient Chips for Artificial Intelligence and Machine Learning, based on the open RISC-V standard
- Cambricon Licenses NetSpeed Fabric IP for Its Next-Gen Artificial Intelligence Products
- CEVA's 2nd Generation Neural Network Software Framework Extends Support for Artificial Intelligence Including Google's TensorFlow
- Graphcore Secures $30m to Accelerate Artificial Intelligence
Latest News
- HPC customer engages Sondrel for high end chip design
- PCI-SIG’s Al Yanes on PCIe 7.0, HPC, and the Future of Interconnects
- Ubitium Debuts First Universal RISC-V Processor to Enable AI at No Additional Cost, as It Raises $3.7M
- Cadence Unveils Arm-Based System Chiplet
- Frontgrade Gaisler Unveils GR716B, a New Standard in Space-Grade Microcontrollers