Event-Driven Real-Time Audio Processing with GPGPUs

Leidi T, Heeb T, Colla M, Thiran JP. Event-Driven Real-Time Audio Processing with GPGPUs. In: AES Convention 130. Audio Engineering Society; 2011. Paper 8417. Available from: https://aes.org/publications/elibrary-page/?id=15884

@inproceedings{Leidi2011_15884,
  author = {Leidi, Tiziano and Heeb, Thierry and Colla, Marco and Thiran, Jean-Philippe},
  title = {{Event-Driven Real-Time Audio Processing with GPGPUs}},
  booktitle = {AES Convention 130},
  note = {Paper 8417},
  year = {2011},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=15884}
}

TY  - CPAPER
TI  - Event-Driven Real-Time Audio Processing with GPGPUs
AU  - Leidi, Tiziano
AU  - Heeb, Thierry
AU  - Colla, Marco
AU  - Thiran, Jean-Philippe
T2  - AES Convention 130
M1  - Paper 8417
PY  - 2011
DA  - 2011/05/06
UR  - https://aes.org/publications/elibrary-page/?id=15884
PB  - Audio Engineering Society
LA  - en
AB  - Development of real-time audio processing applications for GPGPUs is not without challenges. Parallel processing of audio signals is often constrained by serial dependencies within or between algorithms. On GPGPUs, insufficient data pressure further limits the attainable performance improvements, as it causes inactivity of the GPU cores. In this paper, we analyze the limits of audio processing on GPGPUs and present an approach based on event-driven scheduling, that maximizes data pressure to favour performance improvements. We also present recent enhancements of Audio n-Genie, an open-source development environment for audio-processing applications. By combining Audio n-Genie and the proposed approach, we show that it is possible to increase audio processing speed-up.
ER  -