| Preprint | |
| Report number | CERN-IT-2011-009 |
| Title | Parallelization of maximum likelihood fits with OpenMP and CUDA |
| Author(s) | Jarp, S (CERN openlab, Geneva, Switzerland) ; Lazzaro, A (CERN openlab, Geneva, Switzerland) ; Leduc, J (CERN openlab, Geneva, Switzerland) ; Nowak, A (CERN openlab, Geneva, Switzerland) ; Pantaleo, F (CERN openlab, Geneva, Switzerland) |
| Publication | 2011 |
| Imprint | 15 Feb 2011 |
| Number of pages | 7 |
| Presented at | Conference on Computing in High Energy and Nuclear Physics 2010, Taipei, Taiwan, 18 - 22 Oct 2010 |
| Subject category | Computing and Computers |
| Keywords | x86 ; x86-64 ; multi-core ; multi-threading ; many-core ; manycore ; multicore ; multithreading ; processor ; cpu ; intel ; amd ; architecture ; hep ; C++ ; vector ; Nehalem ; Westmere ; threading ; WSM ; NHM ; ROOT ; RooFit ; benchmark ; benchmarking ; scalability ; scaling ; hyper-threading ; hyper threading ; smt ; CUDA ; GPU ; latency ; speed-up |
| Abstract | Data analyses based on maximum likelihood fits are commonly used in the high energy physics community for fitting statistical models to data samples. This technique requires the numerical minimization of the negative log-likelihood function. MINUIT is the most common package used for this purpose in the high energy physics community. The main algorithm in this package, MIGRAD, searches the minimum by using the gradient information. The procedure requires several evaluations of the function, depending on the number of free parameters and their initial values. The whole procedure can be very CPU-time consuming in case of complex functions, with several free parameters, many independent variables and large data samples. Therefore, it becomes particularly important to speed-up the evaluation of the negative log-likelihood function. In this paper we present an algorithm and its implementation which benefits from data vectorization and parallelization (based on OpenMP) and which was also ported to Graphics Processing Units using CUDA. |
| Copyright/License | Preprint: © 2011-2025 CERN (License: CC-BY-3.0) |
| Submitted by | [email protected] |
Element opprettet 2011-02-15, sist endret 2016-01-11
