Real-Time Audio Processing on the T-CREST Multicore Platform

Daniel Sanz Ausin, Luca Pezzarossa, Martin Schoeberl

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

188 Downloads (Pure)

Abstract

Multicore platforms are nowadays widely used for audio processing applications, due to the improvement of computational power that they provide. However, some of these systems are not optimized for temporally constrained environments, which often leads to an undesired increase in the latency of the audio signal. This paper presents a real-time multicore audio processing system based on the T-CREST platform. T-CREST is a time-predictable multicore processor for real-time embedded systems. Multiple audio effect tasks have been implemented, which can be connected together in different configurations forming sequential and parallel effect chains, and using a network-onchip for intercommunication between processors. The evaluation of the system shows that real-time processing of multiple effect
configurations is possible, and that the estimation and control of latency ensures real-time behavior.
Original languageEnglish
Title of host publicationProceedings of IEEE 11th International Symposium on Embedded Multicore/Many-core Systems-on-Chip
Number of pages8
PublisherIEEE
Publication date2017
Publication statusPublished - 2017
EventIEEE 11th International Symposium on Embedded Multicore/Many-core Systems-on-Chip - Korea University, Seoul, Korea, Republic of
Duration: 18 Sep 201720 Sep 2017

Conference

ConferenceIEEE 11th International Symposium on Embedded Multicore/Many-core Systems-on-Chip
LocationKorea University
CountryKorea, Republic of
CitySeoul
Period18/09/201720/09/2017

Cite this

Ausin, D. S., Pezzarossa, L., & Schoeberl, M. (2017). Real-Time Audio Processing on the T-CREST Multicore Platform. In Proceedings of IEEE 11th International Symposium on Embedded Multicore/Many-core Systems-on-Chip IEEE.