Pablo Ibañez

@article{navarro2025complexity,

title = {A Complexity-Effective Local Delta Prefetcher},

author = {Agustín Navarro-Torres and Biswabandan Panda and Jesús Alastruey-Benedé and Pablo Ibáñez and Víctor Viñnals-Yúfera and Alberto Ros},

year  = {2025},

date = {2025-01-01},

journal = {IEEE Transactions on Computers},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{lopez2025ilves,

title = {ILVES: Accurate and Efficient Bond Length and Angle Constraints in Molecular Dynamics},

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 Pablo Echenique and Miquel Moretó and Maria Cristina De Rosa and Pablo García-Risueño},

year  = {2025},

date = {2025-01-01},

journal = {Journal of Chemical Theory and Computation},

volume = {21},

number = {18},

pages = {8711–8719},

publisher = {American Chemical Society},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{lopez2025singletrack,

title = {Singletrack: An Algorithm for Improving Memory Consumption and Performance of Gap-Affine Sequence Alignment},

author = {Lorién López-Villellas and Cristian Iñiguez and Albert Jiménez-Blanco and Quim Aguado-Puig and Miquel Moretó and Jesús Alastruey-Benedé and Pablo Ibáñez and Santiago Marco-Sola},

year  = {2025},

date = {2025-01-01},

journal = {bioRxiv},

pages = {2025–10},

publisher = {Cold Spring Harbor Laboratory},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@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}

}