The eProcessor ecosystem presents a pioneering approach by integrating open-source software (SW) and hardware (HW). It establishes the inaugural fully open-source European full-stack ecosystem, featuring a novel RISC-V CPU paired with diverse accelerators. These accelerators cater to traditional high-performance computing (HPC) tasks and expand into mixed precision workloads, including High-Performance Data Analytics (HPDA), artificial intelligence (AI), machine learning (ML), deep learning (DL), and bioinformatics.
Research Group:
Computer Architecture for Parallel Paradigms
Researcher/s:
Noé Bustamante
Description:
Type of asset:
Category:
Problem:
Improve accelerator for HPC.
Solution:
The eProcessor is designed to be extendable through open-source contributions, energy-efficient with low power consumption, capable of extreme-scale performance, suitable for applications in both HPC and embedded systems. Additionally, it is easily extensible, allowing for the straightforward integration of on-chip and/or off-chip components, hence the "e" serving as a versatile wildcard in the eProcessor proposal name.
Aplication areas:
Mainly in HPC applications, HPDA and artificial intelligence.
Novelty:
The novelty of the eProcessor project lies in its holistic integration of open-source software and hardware components to create a fully open-source European full-stack ecosystem. Several key aspects contribute to its uniqueness: RISCV CPU architecture, diverse accelerators, energy efficient.
Protection:
Open-source software and hardware.
Target market:
Research institutions, HPC centers, Government Agencies, etc.
Keywords:
TRL: 5
CRL: N/A
BRL: N/A
IPRL: N/A
TmRL: N/A
FRL: N/A
More information
if you want to know more about this project do not hesitate to contact us