DOE OSTI · 2318665
Portable Acceleration of CMS Computing Workflows with Coprocessors as a Service
Abstract
Computing demands for large scientific experiments, such as the CMS experiment at the CERN LHC, will increase dramatically in the next decades. To complement the future performance increases of software running on central processing units (CPUs), explorations of coprocessor usage in data processing hold great potential and interest. Coprocessors are a class of computer processors that supplement CPUs, often improving the execution of certain functions due to architectural design choices. We explore the approach of Services for Optimized Network Inference on Coprocessors (SONIC) and study the deployment of this as-a-service approach in large-scale data processing. In the studies, we take a data processing workflow of the CMS experiment and run the main workflow on CPUs, while offloading several machine learning (ML) inference tasks onto either remote or local coprocessors, specifically graphics processing units (GPUs). With experiments performed at Google Cloud, the Purdue Tier-2 computing center, and combinations of the two, we demonstrate the acceleration of these ML algorithms individually on coprocessors and the corresponding throughput improvement for the entire workflow. This approach can be easily generalized to different types of coprocessors and deployed on local CPUs without decreasing the throughput performance. We emphasize that the SONIC approach enables high coprocessor usage and enables the portability to run workflows on different types of coprocessors.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Hayrapetyan, Aram, Tumasyan, Armen, Adam, Wolfgang, Andrejkovic, Janik Walter, Bergauer, Thomas, Chatterjee, Suman, Damanakis, Konstantinos, Dragicevic, Marko, Hussain, Priya Sajid, Jeitler, Manfred, Krammer, Natascha, Ang Li, Ang Li, Liko, Dietrich, Mikulec, Ivan, Schieck, Jochen, Schöfbeck, Robert, Schwarz, Dennis, Sonawane, Mangesh, Templ, Sebastian, Waltenberger, Wolfgang, Wulz, Claudia-Elisabeth, Darwish, Mohamed Rashad, Janssen, Tahys, Van Mechelen, Pierre, Bols, Emil Sørensen, D'Hondt, Jorgen, Dansana, Soumya, De Moor, Alexandre, Delcourt, Martin, El Faham, Hesham, Lowette, Steven, Makarenko, Inna, Müller, Denise, Sahasransu, Abanti Ranadhir, Tavernier, Stefaan, Tytgat, Michael, Van Onsem, Gerrit Patrick, Van Putte, Senne, Vannerom, David, Clerbaux, Barbara, Das, Aloke Kumar, De Lentdecker, Gilles, Favart, Laurent, Gianneios, Paraskevas, Hohov, Dmytro, Jaramillo, Johny, Khalilzadeh, Ali, Khan, Fakhri Alam, Lee, Kyeongpil, Mahdavikhorrami, Mostafa, Malara, Andrea, Paredes, Santiago, Thomas, Laurent, Vanden Bemden, Max, Vander Velde, Catherine, Vanlaer, Pascal, De Coen, Maarten, Dobur, Didar, Hong, Yanwen, Knolle, Joscha, Lambrecht, Luka, Mestdach, Gianny, Mota Amarilo, Kevin, Rendón, César, Samalan, Amrutha, Skovpen, Kirill, Van Den Bossche, Niels, van der Linden, Jan, Wezenbeek, Liam, Benecke, Anna, Bethani, Agni, Bruno, Giacomo, Caputo, Claudio, Delaere, Christophe, Donertas, Izzeddin Suat, Giammanco, Andrea, Jaffel, Khawla, Jain, Sa., Jain, Sandhya, Lemaitre, Vincent, Lidrych, Jindrich, Mastrapasqua, Paola, Mondal, Kuntal, Tran, Tu Thong, Wertz, Sébastien, Alves, Gilvan, Coelho, Eduardo, Hensel, Carsten, Menezes De Oliveira, Thales, Moraes, Arthur, Rebello Teles, Patricia, Soeiro, Mariana, Aldá Júnior, Walter Luiz, Alves Gallo Pereira, Miguel, Barroso Ferreira Filho, Mapse, Brandao Malbouisson, Helena, Carvalho, Wagner, Chinellato, Jose, Da Costa, Eliza Melo, Da Silveira, Gustavo Gil. 2024-09-04. Portable Acceleration of CMS Computing Workflows with Coprocessors as a Service. https://doi.org/10.1007/s41781-024-00124-1
Cite the original work for its findings. Save a collection to share your selection of sources.