Outstanding solutions
for Generative AI and HPC.
Our solutions are built on RISC-V, the open instruction set standard, using an innovative low-power approach which enables us to deliver an exceptional value proposition for AI inference and HPC applications.
Generative AI inference at a fraction of the cost.
The Esperanto AI / HPC Compute Server
Meet the world’s most efficient solution for Generative AI inference, HPC, and mixed mode (AI + HPC) workloads.
Our high-performance systems enable direct access to many thousands of high-performance, low power RISC-V cores, delivering superior compute efficiency to CPU- and GPU-based offerings. Run Generative AI, Transformers, Computer Vision and Recommendation models, as well as massively parallel HPC workloads and mixed AI plus HPC workloads. Available today for purchase or secure remote cloud access.
ET-SoC-1 Chip
The world’s most efficient RISC-V commercial chip.
The ET-SoC-1 inference chip is designed to be the world’s most efficient RISC-V commercial chip, with over a thousand RISC-V processors on a single TSMC 7nm chip delivering a massively parallel, flexible architecture that combines exceptional performance and ultra-low power consumption. ET-SoC-1 delivers low total cost of ownership for AI, HPC and mixed AI plus HPC workloads.
Energy Efficiency
Exceptional energy efficiency for a full range of AI and HPC workloads.
Power consumption continues to be the most critical problem facing high-performance computing today. To address this challenge we employ an array of over a thousand low-power ET-Minion™ cores, delivering energy efficiency with high integer and floating-point throughput, including tensor and vector acceleration optimized for AI and HPC workloads.
RISC-V ISA
RISC-V is the future of computinginnovation.
Esperanto Technologies leverages RISC-V, an open standard ISA enabling a new era of processor innovation. As a founding member of RISC-V International, Esperanto is at the forefront of the RISC-V revolution, using the instruction set architecture to develop the world’s most efficient parallelized AI and HPC accelerators. Our high-performance out-of-order processor cores can boot Linux in self-hosted mode while our energy-efficient multithreaded in-order processor cores form a very powerful compute fabric to accelerate AI and HPC workloads. Our software stacks support standard AI frameworks and leverage the rich RISC-V software ecosystem.
Scalability & Flexibility
Exceptional energy efficiency for a full range of AI and HPC workloads.
The Esperanto RISC-V architecture can scale to address different applications, different levels of performance, different power profiles, and varying system form factors – while delivering optimal energy efficiency for each target application. With over a thousand high-performance, energy-efficient 64-bit RISC-V cores per ET-SoC-1 chip and up to 16 chips per system, Esperanto can deliver PetaOps of scalable computing performance. And we are already designing the next generation of our unique architecture that will have the performance and memory bandwidth to accelerate the next generation of Generative AI transformer models as well as HPC workloads.
In quotes.
Request Access to
Esperanto Systems
Esperanto Systems