Segment Linking: A Highly Parallelizable Track Reconstruction Algorithm for HL-LHC
Segment Linking: A Highly Parallelizable Track Reconstruction Algorithm for HL-LHC
复制标题
段链接：HL-LHC 的高度并行化轨道重建算法
DOI：
10.1088/1742-6596/2375/1/012005
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Wang, B
中科院分区：
文献类型：
--
作者：
Chang, P;Elmer, P;Krutelyov, V;Niendorf, G;Reid, M;Sathia Narayanan, B V;Tadel, M;Vourliotis, E;Wang, B
大型强子对撞机（HL-LHC）的高亮度升级将产生多达200个同时发生的质子-质子相互作用的粒子碰撞。这些前所未有的条件将为带电粒子径迹重建创造一个组合复杂性，需要的计算成本预计将超过使用传统CPU的预计计算预算。受此启发，并考虑到异构计算在尖端的高性能计算中心的流行，我们提出了一个有效的，快速的和高度并行化的自下而上的方法来跟踪重建的HL-LHC，沿着与GPU上的相关实现，在第2阶段CMS外部跟踪器的上下文中。我们的算法，称为段链接（或线段跟踪），利用本地化的轨道存根创建，结合个别存根，逐步形成更高层次的对象，受运动学和几何要求与真正的物理轨道兼容。该算法的本地特性使其非常适合单指令多数据模式下的并行化，因为可以同时构建数百个对象。该算法的计算和物理性能已经在NVIDIA Tesla V100 GPU上进行了测试，其效率和时间测量结果与现有CMS跟踪算法的最新多CPU版本相当。
The High Luminosity upgrade of the Large Hadron Collider (HL-LHC) will produce particle collisions with up to 200 simultaneous proton-proton interactions. These unprecedented conditions will create a combinatorial complexity for charged-particle track reconstruction that demands a computational cost that is expected to surpass the projected computing budget using conventional CPUs. Motivated by this and taking into account the prevalence of heterogeneous computing in cutting-edge High Performance Computing centers, we propose an efficient, fast and highly parallelizable bottom-up approach to track reconstruction for the HL-LHC, along with an associated implementation on GPUs, in the context of the Phase 2 CMS outer tracker. Our algorithm, called Segment Linking (or Line Segment Tracking), takes advantage of localized track stub creation, combining individual stubs to progressively form higher level objects that are subject to kinematical and geometrical requirements compatible with genuine physics tracks. The local nature of the algorithm makes it ideal for parallelization under the Single Instruction, Multiple Data paradigm, as hundreds of objects can be built simultaneously. The computing and physics performance of the algorithm has been tested on an NVIDIA Tesla V100 GPU, already yielding efficiency and timing measurements that are on par with the latest, multi-CPU versions of existing CMS tracking algorithms.
登录
查看更多内容
DOI：
10.1088/0954-3899/28/3/401
发表时间：
1998-06
期刊：
Journal of Physics G
影响因子：
--
作者：
A. Sirunyan;A. Tumasyan;W. Adam;F. Ambrogi;E. Asilar;T. Bergauer;J. Brandstetter;M. Dragicevic-
通讯作者：
A. Sirunyan;A. Tumasyan;W. Adam;F. Ambrogi;E. Asilar;T. Bergauer;J. Brandstetter;M. Dragicevic-
用于 CDF 升级的在线跟踪处理器
DOI：
10.1109/nssmic.2001.1009706
发表时间：
1998
期刊：
2001 IEEE Nuclear Science Symposium Conference Record (Cat. No.01CH37310)
影响因子：
--
作者：
C. Ciobanu;J. Chung;J. Gerstenslager;J. Hoftiezer;R. Hughes;P. Koehn;C. Neu;C. Sánchez;E. Thomson;B. Winer;J. Dittmann;J. Freeman;S. Holm;J. Lewis;T. Shaw;T. Wesson;K. Bloom;D. Gerdes;N. Goldschmidt;J. Dawson;W. Haberichter
通讯作者：
W. Haberichter
影响因子：
3.1
作者：
Bocci A;Innocente V;Kortelainen M;Pantaleo F;Rovere M
通讯作者：
Rovere M
CMS数据采集系统二期升级
影响因子：
--
作者：
Gilbert Badaro;U. Behrens;A. Bocci;J. Branson;P. Brummer;S. Cittolin;Diego Da Silva;G. Darlea;C. Deldicque;M. Dobson;D. Gigi;N. Dzemaili;M. Gladki;F. Glege;G. Gomez;J. Hegeman;T. James;W. Li;F. Meijers;E. Meschi;R. Mommsen;S. Morovic;L. Orsini;I. Papakrivopoulos;C. Paus;A. Petrucci;M. Pieri;E. Puljak;D. Rabady;K. Raychinov;A. Rácz;H. Sakulin;C. Schwick;D. Simelevicius;P. Soursos;A. Stahl;U. Suthakar;C. Vazquez;P. Zejdl
通讯作者：
P. Zejdl