Publicaciones

@article{LOPEZVILLELLAS2024313,

title = {GenArchBench: A genomics benchmark suite for arm HPC processors},

author = {Lorién López-Villellas and Rubén Langarita-Benítez and Asaf Badouh and Víctor Soria-Pardos and Quim Aguado-Puig and Guillem López-Paradís and Max Doblas and Javier Setoain and Chulho Kim and Makoto Ono and Adrià Armejach and Santiago Marco-Sola and Jesús Alastruey-Benedé and Pablo Ibáñez and Miquel Moretó},

url = {https://www.sciencedirect.com/science/article/pii/S0167739X24001250},

doi = {https://doi.org/10.1016/j.future.2024.03.050},

issn = {0167-739X},

year  = {2024},

date = {2024-01-01},

journal = {Future Generation Computer Systems},

volume = {157},

pages = {313-329},

abstract = {Arm usage has substantially grown in the High-Performance Computing (HPC) community. Japanese supercomputer Fugaku, powered by Arm-based A64FX processors, held the top position on the Top500 list between June 2020 and June 2022, currently sitting in the fourth position. The recently released 7th generation of Amazon EC2 instances for compute-intensive workloads (C7 g) is also powered by Arm Graviton3 processors. Projects like European Mont-Blanc and U.S. DOE/NNSA Astra are further examples of Arm irruption in HPC. In parallel, over the last decade, the rapid improvement of genomic sequencing technologies and the exponential growth of sequencing data has placed a significant bottleneck on the computational side. While most genomics applications have been thoroughly tested and optimized for x86 systems, just a few are prepared to perform efficiently on Arm machines. Moreover, these applications do not exploit the newly introduced Scalable Vector Extensions (SVE). This paper presents GenArchBench, the first genome analysis benchmark suite targeting Arm architectures. We have selected computationally demanding kernels from the most widely used tools in genome data analysis and ported them to Arm-based A64FX and Graviton3 processors. Overall, the GenArch benchmark suite comprises 13 multi-core kernels from critical stages of widely-used genome analysis pipelines, including base-calling, read mapping, variant calling, and genome assembly. Our benchmark suite includes different input data sets per kernel (small and large), each with a corresponding regression test to verify the correctness of each execution automatically. Moreover, the porting features the usage of the novel Arm SVE instructions, algorithmic and code optimizations, and the exploitation of Arm-optimized libraries. We present the optimizations implemented in each kernel and a detailed performance evaluation and comparison of their performance on four different HPC machines (i.e., A64FX, Graviton3, Intel Xeon Skylake Platinum, and AMD EPYC Rome). Overall, the experimental evaluation shows that Graviton3 outperforms other machines on average. Moreover, we observed that the performance of the A64FX is significantly constrained by its small memory hierarchy and latencies. Additionally, as proof of concept, we study the performance of a production-ready tool that exploits two of the ported and optimized genomic kernels.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{navarro2023balancer,

title = {BALANCER: bandwidth allocation and cache partitioning for multicore processors},

author = {Agustín Navarro-Torres and Jesús Alastruey-Benedé and Pablo Ibáñez and Víctor Viñals-Yúfera},

url = {https://doi.org/10.1007/s11227-023-05070-0},

doi = {10.1007/s11227-023-05070-0},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

journal = {The Journal of Supercomputing},

pages = {1--25},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{LOPEZVILLELLAS2023108742,

title = {Accurate and efficient constrained molecular dynamics of polymers using Newton's method and special purpose code},

author = {Lorién López-Villellas and Carl Christian Kjelgaard Mikkelsen and Juan José Galano-Frutos and Santiago Marco-Sola and Jesús Alastruey-Benedé and Pablo Ibáñez and Miquel Moretó and Javier Sancho and Pablo García-Risueño},

url = {https://www.sciencedirect.com/science/article/pii/S0010465523000875},

doi = {https://doi.org/10.1016/j.cpc.2023.108742},

issn = {0010-4655},

year  = {2023},

date = {2023-01-01},

journal = {Computer Physics Communications},

volume = {288},

pages = {108742},

abstract = {In molecular dynamics simulations we can often increase the time step by imposing constraints on bond lengths and bond angles. This allows us to extend the length of the time interval and therefore the range of physical phenomena that we can afford to simulate. We examine the existing algorithms and software for solving nonlinear constraint equations in parallel and we explain why it is necessary to advance the state-of-the-art. We present ILVES-PC, a new algorithm for imposing bond constraints on proteins accurately and efficiently. It solves the same system of differential algebraic equations as the celebrated SHAKE algorithm, but ILVES-PC solves the nonlinear constraint equations using Newton's method rather than the nonlinear Gauss-Seidel method. Moreover, ILVES-PC solves the necessary linear systems using a specialized linear solver that exploits the structure of the protein. ILVES-PC can rapidly solve constraint equations as accurately as the hardware will allow. The run-time of ILVES-PC is proportional to the number of constraints. We have integrated ILVES-PC into GROMACS and simulated proteins of different sizes. Compared with SHAKE, we have achieved speedups of up to 4.9× in single-threaded executions and up to 76× in shared-memory multi-threaded executions. Moreover, ILVES-PC is more accurate than P-LINCS algorithm. Our work is a proof-of-concept of the utility of software designed specifically for the simulation of polymers.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10093071,

title = {Porting and Optimizing BWA-MEM2 Using the Fujitsu A64FX Processor},

author = {Rubén Langarita and Adrià Armejach and Pablo Ibáñez and Jesús Alastruey-Benedé and Miquel Moretó},

doi = {10.1109/TCBB.2023.3264514},

year  = {2023},

date = {2023-01-01},

journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics},

volume = {20},

number = {5},

pages = {3139-3153},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DBLP:journals/tcbb/LangaritaASIAM22,

title = {Compressed Sparse FM-Index: Fast Sequence Alignment Using Large K-Steps},

author = {Rubén Langarita and Adrià Armejach and Javier Setoain and Pablo Ibáñez-Marín and Jesús Alastruey-Benedé and Miquel Moretó},

url = {https://doi.org/10.1109/TCBB.2020.3000253},

doi = {10.1109/TCBB.2020.3000253},

year  = {2022},

date = {2022-01-01},

journal = {IEEE ACM Trans. Comput. Biol. Bioinform.},

volume = {19},

number = {1},

pages = {355--368},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DBLP:journals/jpdc/ValeroTGGEAMRI21,

title = {A learning experience toward the understanding of abstraction-level 

 interactions in parallel applications},

author = {Alejandro Valero and Ruben Gran Tejero and Darío Suárez Gracia and Emanuel A. Georgescu and Joaquín Ezpeleta and Pedro Álvarez and Adolfo Muñoz and Luis M. Ramos and Pablo Ibáñez},

url = {https://doi.org/10.1016/j.jpdc.2021.05.008},

doi = {10.1016/j.jpdc.2021.05.008},

year  = {2021},

date = {2021-01-01},

journal = {J. Parallel Distributed Comput.},

volume = {156},

pages = {38--52},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DBLP:journals/tjs/DiazIMVL21,

title = {Near-optimal replacement policies for shared caches in multicore processors},

author = {Javier Díaz and Pablo Ibáñez and Teresa Monreal and Víctor Viñals and José M. Llabería},

url = {https://doi.org/10.1007/s11227-021-03736-1},

doi = {10.1007/s11227-021-03736-1},

year  = {2021},

date = {2021-01-01},

journal = {J. Supercomput.},

volume = {77},

number = {10},

pages = {11756--11785},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{alcolea2021fpga,

title = {FPGA Accelerator for Gradient Boosting Decision Trees},

author = {Adrián Alcolea and Javier Resano},

year  = {2021},

date = {2021-01-01},

journal = {Electronics},

volume = {10},

number = {3},

pages = {314},

publisher = {Multidisciplinary Digital Publishing Institute},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{diaz2021near,

title = {Near-optimal replacement policies for shared caches in multicore processors},

author = {Javier Díaz and Pablo Ibáñez and Teresa Monreal and Víctor Viñals and José M Llabería},

year  = {2021},

date = {2021-01-01},

journal = {The Journal of Supercomputing},

pages = {1--30},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{lamela2021offchip,

title = {Off-chip prefetching based on Hidden Markov Model for non-volatile memory architectures},

author = {Adrián Lamela and Óscar G Ossorio and Guillermo Vinuesa and Benjamín Sahelices},

url = {https://doi.org/10.1371/journal.pone.0257047},

doi = {10.1371/journal.pone.0257047},

year  = {2021},

date = {2021-01-01},

journal = {PLOS ONE},

volume = {16},

number = {9},

pages = {1-23},

publisher = {Public Library of Science},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DBLP:journals/jsa/SegarraTV21,

title = {A generic framework to integrate data caches in the WCET analysis of real-time systems},

author = {Juan Segarra and Ruben Gran Tejero and Víctor Viñals},

url = {https://doi.org/10.1016/j.sysarc.2021.102304},

doi = {10.1016/j.sysarc.2021.102304},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {J. Syst. Archit.},

volume = {120},

pages = {102304},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DBLP:journals/tcbb/HerruzoGIYAP20,

title = {Accelerating Sequence Alignments Based on FM-Index Using the Intel 

 KNL Processor},

author = {Jose Manuel Herruzo and Sonia González-Navarro and Pablo Ibáñez-Marín and Víctor Viñals Yúfera and Jesús Alastruey-Benedé and Oscar G. Plata},

url = {https://doi.org/10.1109/TCBB.2018.2884701},

doi = {10.1109/TCBB.2018.2884701},

year  = {2020},

date = {2020-01-01},

journal = {IEEE ACM Trans. Comput. Biol. Bioinform.},

volume = {17},

number = {4},

pages = {1093--1104},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{biology9080207,

title = {Expanding the Limits of Computer-Assisted Sperm Analysis through the Development of Open Software},

author = {Jesús Yániz and Carlos Alquézar-Baeta and Jorge Yagüe-Martínez and Jesús Alastruey-Benedé and Inmaculada Palacín and Sergii Boryshpolets and Vitaliy Kholodnyy and Hermes Gadêlha and Rosaura Pérez-Pe},

url = {https://www.mdpi.com/2079-7737/9/8/207},

doi = {10.3390/biology9080207},

issn = {2079-7737},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

journal = {Biology},

volume = {9},

number = {8},

abstract = {Computer assisted sperm analysis (CASA) systems can reduce errors occurring in manual analysis. However, commercial CASA systems are frequently not applicable at the forefront of challenging research endeavors. The development of open source software may offer important solutions for researchers working in related areas. Here, we present an example of this, with the development of three new modules for the OpenCASA software (hosted at Github). The first is the Chemotactic Sperm Accumulation Module, a powerful tool for studying sperm chemotactic behavior, analyzing the sperm accumulation in the direct vicinity of the stimuli. This module was validated by comparing fish sperm accumulation, with or without the influence of an attractant. The analysis clearly indicated cell accumulation in the treatment group, while the distribution of sperm was random in the control group. The second is the Sperm Functionality Module, based on the ability to recognize five sperm subpopulations according to their fluorescence patterns associated with the plasma membrane and acrosomal status. The last module is the Sperm Concentration Module, which expands the utilities of OpenCASA. These last two modules were validated, using bull sperm, by comparing them with visual counting by an observer. A high level of correlation was achieved in almost all the data, and a good agreement between both methods was obtained. With these newly developed modules, OpenCASA is consolidated as a powerful free and open-source tool that allows different aspects of sperm quality to be evaluated, with many potential applications for researchers.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{moreno2020analysis,

title = {Analysis of a Pipelined Architecture for Sparse DNNs on Embedded Systems},

author = {Adrián Alcolea Moreno and Javier Olivito and Javier Resano and Hortensia Mecha},

year  = {2020},

date = {2020-01-01},

journal = {IEEE Transactions on Very Large Scale Integration (VLSI) Systems},

volume = {28},

number = {9},

pages = {1993--2003},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{alcolea2020inference,

title = {Inference in supervised spectral classifiers for on-board hyperspectral imaging: An overview},

author = {Adrián Alcolea and Mercedes E Paoletti and Juan M Haut and Javier Resano and Antonio Plaza},

year  = {2020},

date = {2020-01-01},

journal = {Remote Sensing},

volume = {12},

number = {3},

pages = {534},

publisher = {Multidisciplinary Digital Publishing Institute},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{haut2020gpu,

title = {GPU-Friendly Neural Networks for Remote Sensing Scene Classification},

author = {Juan M Haut and Adrian Alcolea and Mercedes E Paoletti and Javier Plaza and Javier Resano and Antonio Plaza},

year  = {2020},

date = {2020-01-01},

journal = {IEEE Geoscience and Remote Sensing Letters},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}