Esperanto Technologies develops massively parallel, energy-efficient chips based on the RISC-V instruction set architecture, specifically designed for Generative AI and high-performance computing (HPC) applications. Their ET-SoC-1 chip features over a thousand low-power RISC-V cores, providing superior compute efficiency and significantly reducing total cost of ownership for AI inference and HPC workloads.
Funding
$61M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
The increasing computational demands of generative AI and high-performance computing (HPC) applications require energy-intensive hardware, leading to high operational costs and environmental concerns. Existing CPU- and GPU-based solutions often struggle to deliver the necessary performance and scalability within reasonable power budgets.
Solution
Esperanto Technologies offers a RISC-V based solution for generative AI inference and HPC workloads, delivering compute efficiency and reduced total cost of ownership. The ET-SoC-1 chip features over a thousand low-power RISC-V cores on a single die, providing a massively parallel architecture optimized for both AI and HPC. Esperanto's systems provide direct access to thousands of RISC-V cores, offering an alternative to CPU- and GPU-based solutions. The architecture is designed to scale to address different applications, performance levels, power profiles, and system form factors.
Target Audience
The primary target audience includes organizations involved in generative AI, high-performance computing, and mixed AI/HPC workloads seeking energy-efficient and scalable compute solutions.
Features
- ET-SoC-1 chip with over a thousand 64-bit RISC-V cores
- Massively parallel, low-power architecture optimized for AI inference and HPC
- Support for standard AI frameworks and the RISC-V software ecosystem
- Scalable architecture supporting various performance levels and system form factors
- High integer and floating-point throughput with tensor and vector acceleration
- Ability to run Generative AI, Transformers, Computer Vision, and Recommendation models
- Support for mixed AI plus HPC workloads