2026-07-24T17:11:58Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:13932 2024-03-06T10:53:19Z ddc:004 open_access

Vicuna: A Timing-Predictable RISC-V Vector Coprocessor for Scalable Parallel Computation Platzer, Michael Puschner, Peter Real-time Systems Vector Processors RISC-V In this work, we present Vicuna, a timing-predictable vector coprocessor. A vector processor can be scaled to satisfy the performance requirements of massively parallel computation tasks, yet its timing behavior can remain simple enough to be efficiently analyzable. Therefore, vector processors are promising for highly parallel real-time applications, such as advanced driver assistance systems and autonomous vehicles. Vicuna has been specifically tailored to address the needs of real-time applications. It features predictable and repeatable timing behavior and is free of timing anomalies, thus enabling effective and tight worst-case execution time (WCET) analysis while retaining the performance and efficiency commonly seen in other vector processors. We demonstrate our architecture’s predictability, scalability, and performance by running a set of benchmark applications on several configurations of Vicuna synthesized on a Xilinx 7 Series FPGA with a peak performance of over 10 billion 8-bit operations per second, which is in line with existing non-predictable soft vector-processing architectures. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Michael Platzer and Peter Puschner 2021 Is Part Of LIPIcs, Volume 196, 33rd Euromicro Conference on Real-Time Systems (ECRTS 2021) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.ECRTS.2021.1 urn:nbn:de:0030-drops-139323 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2021.1 eng https://creativecommons.org/licenses/by/4.0/legalcode