Allen: A High-Level Trigger on GPUs for LHCb.

Q1 Computer Science Computing and Software for Big Science Pub Date : 2020-01-01 Epub Date: 2020-04-30 DOI:10.1007/s41781-020-00039-7

R Aaij, J Albrecht, M Belous, P Billoir, T Boettcher, A Brea Rodríguez, D Vom Bruch, D H Cámpora Pérez, A Casais Vidal, D C Craik, P Fernandez Declara, L Funke, V V Gligorov, B Jashal, N Kazeev, D Martínez Santos, F Pisani, D Pliushchenko, S Popov, R Quagliani, M Rangel, F Reiss, C Sánchez Mayordomo, R Schwemmer, M Sokoloff, H Stevens, A Ustyuzhanin, X Vilasís Cardona, M Williams

{"title":"Allen: A High-Level Trigger on GPUs for LHCb.","authors":"R Aaij, J Albrecht, M Belous, P Billoir, T Boettcher, A Brea Rodríguez, D Vom Bruch, D H Cámpora Pérez, A Casais Vidal, D C Craik, P Fernandez Declara, L Funke, V V Gligorov, B Jashal, N Kazeev, D Martínez Santos, F Pisani, D Pliushchenko, S Popov, R Quagliani, M Rangel, F Reiss, C Sánchez Mayordomo, R Schwemmer, M Sokoloff, H Stevens, A Ustyuzhanin, X Vilasís Cardona, M Williams","doi":"10.1007/s41781-020-00039-7","DOIUrl":null,"url":null,"abstract":"<p><p>We describe a fully GPU-based implementation of the first level trigger for the upgrade of the LHCb detector, due to start data taking in 2021. We demonstrate that our implementation, named Allen, can process the 40 Tbit/s data rate of the upgraded LHCb detector and perform a wide variety of pattern recognition tasks. These include finding the trajectories of charged particles, finding proton-proton collision points, identifying particles as hadrons or muons, and finding the displaced decay vertices of long-lived particles. We further demonstrate that Allen can be implemented in around 500 scientific or consumer GPU cards, that it is not I/O bound, and can be operated at the full LHC collision rate of 30 MHz. Allen is the first complete high-throughput GPU trigger proposed for a HEP experiment.</p>","PeriodicalId":36026,"journal":{"name":"Computing and Software for Big Science","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1007/s41781-020-00039-7","citationCount":"14","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computing and Software for Big Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s41781-020-00039-7","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2020/4/30 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 14

Abstract

We describe a fully GPU-based implementation of the first level trigger for the upgrade of the LHCb detector, due to start data taking in 2021. We demonstrate that our implementation, named Allen, can process the 40 Tbit/s data rate of the upgraded LHCb detector and perform a wide variety of pattern recognition tasks. These include finding the trajectories of charged particles, finding proton-proton collision points, identifying particles as hadrons or muons, and finding the displaced decay vertices of long-lived particles. We further demonstrate that Allen can be implemented in around 500 scientific or consumer GPU cards, that it is not I/O bound, and can be operated at the full LHC collision rate of 30 MHz. Allen is the first complete high-throughput GPU trigger proposed for a HEP experiment.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Allen: LHCb在gpu上的高级触发器。

我们描述了一个完全基于gpu的第一级触发器的实现，用于LHCb探测器的升级，由于2021年开始数据采集。我们证明了我们的实现，名为Allen，可以处理升级后的LHCb探测器的40 Tbit/s数据速率，并执行各种模式识别任务。这些包括寻找带电粒子的轨迹，寻找质子-质子碰撞点，识别粒子是强子还是介子，以及寻找长寿命粒子的位移衰变顶点。我们进一步证明，Allen可以在大约500个科学或消费者GPU卡中实现，它没有I/O限制，并且可以在30 MHz的完整LHC碰撞速率下运行。Allen是为HEP实验提出的第一个完整的高吞吐量GPU触发器。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊