Speeding up particle track reconstruction using a parallel Kalman filter algorithm
Speeding up particle track reconstruction using a parallel Kalman filter algorithm
复制标题
DOI：
10.1088/1748-0221/15/09/p09030
复制
发表时间：
2020-05
影响因子：
1.3
通讯作者：
S. Lantz;K. Mcdermott;M. Reid;D. Riley;P. Wittich;S. Berkman;G. Cerati;M. Kortelainen;A. Hall;P. Elmer;Bei Wang;L. Giannini;V. Krutelyov;M. Masciovecchio;M. Tadel;F. Wurthwein;A. Yagil;B. Gravelle;Boyana Norris Cornell University;Ithaca;Ny;Usa 14853;F. N. Laboratory;Batavia;Il;Usa 60510;P. University;Princeton;Nj;Usa 08544;U. Diego;La Jolla;Ca;Usa 92093;U. Oregon;Eugene;Or;Usa 97403
中科院分区：
文献类型：
--
作者：
S. Lantz;K. Mcdermott;M. Reid;D. Riley;P. Wittich;S. Berkman;G. Cerati;M. Kortelainen;A. Hall;P. Elmer;Bei Wang;L. Giannini;V. Krutelyov;M. Masciovecchio;M. Tadel;F. Wurthwein;A. Yagil;B. Gravelle;Boyana Norris Cornell University;Ithaca;Ny;Usa 14853;F. N. Laboratory;Batavia;Il;Usa 60510;P. University;Princeton;Nj;Usa 08544;U. Diego;La Jolla;Ca;Usa 92093;U. Oregon;Eugene;Or;Usa 97403
对于高亮度大型强子对撞机（HL-LHC）来说，最具计算挑战性的问题之一是在事件重建过程中确定带电粒子的轨迹。目前在大型强子对撞机上使用的算法依赖于卡尔曼滤波，它在结合材料效应和误差估计的同时逐步建立物理轨迹。认识到需要更快的计算吞吐量，我们已经适应了基于卡尔曼滤波的方法，用于现在在高性能硬件中普遍存在的高度并行、多核SIMD架构。在本文中，我们讨论了改进的跟踪算法MKFIT的设计和性能。该算法的一个关键部分是MATRIPLEX库，其中包含用于对小矩阵进行最佳矢量化操作的专用代码。当在CMS探测器内模拟质子-质子碰撞重建轨迹时，MKFIT算法的物理性能可与标称CMS跟踪算法相媲美。我们研究了算法的缩放作为所利用的并行资源的函数，并发现矢量化和多线程都有很大的加速。当在CMS软件框架内的单线程应用程序中运行时，MKFIT实现了6倍于标称算法的加速。
One of the most computationally challenging problems expected for the High-Luminosity Large Hadron Collider (HL-LHC) is determining the trajectory of charged particles during event reconstruction. Algorithms used at the LHC today rely on Kalman filtering, which builds physical trajectories incrementally while incorporating material effects and error estimation. Recognizing the need for faster computational throughput, we have adapted Kalman-filter-based methods for highly parallel, many-core SIMD architectures that are now prevalent in high-performance hardware. In this paper, we discuss the design and performance of the improved tracking algorithm, referred to as MKFIT. A key piece of the algorithm is the MATRIPLEX library, containing dedicated code to optimally vectorize operations on small matrices. The physics performance of the MKFIT algorithm is comparable to the nominal CMS tracking algorithm when reconstructing tracks from simulated proton-proton collisions within the CMS detector. We study the scaling of the algorithm as a function of the parallel resources utilized and find large speedups both from vectorization and multi-threading. MKFIT achieves a speedup of a factor of 6 compared to the nominal algorithm when run in a single-threaded application within the CMS software framework.