Bio
Ph.D Pedro Valero-Lara is a Senior Computer Scientist in the Programming Systems Group into the Advanced Computing Systems Research Section and Computer Science and Mathematics Division of Oak Ridge National Laboratory.
His interests have been in parallel programming models, math libraries, applications, and AI, as they are an essential component in the scientific software ecosystem. His work addresses, software sustainability, performance portability and programming productivity challenges for better scientific software across increasingly diverse heterogeneous DOE HPC systems. He is a co-principal investigator of one of the DOE projects for scientific software sustainability: Stewardship for Programming Systems and Tools (S4PST). S4PST provides a unified effort for the scientific programming model community (LLVM, OpenMP/OpenACC, Kokkos, Fortran, Julia, …) to elevate productivity, quality, and sustainability in the scientific software community. In his never-ending endeavor towards a more efficient scientific software ecosystem, he has contributed to several DOE-funded software: IRIS-SDK, Kokkos, PLASMA, Cray/HPE LibSci-ACC, NVIDIA cuSparse, among others. Each of these scientific software tools is a reference boosting performance, portability, and productivity. Recently, one of the areas where I have been very active is in the building of foundation and capabilities in Generative AI models for HPC programming to elevate the productivity of scientific software with the help of AI disruptive technologies.
Professional Experience
Senior Research Engineer at HPE-Cray.
Visiting Research at NVIDIA.
Recognized Reseacher and founder of the Linear Algebra and Math Libraries team at Barcelona Supercomputing Center, Spain.
Research Associate at the University of Manchester, UK.
Post-doc Researcher at Basque Center of Applied Mathematics, Spain.
Research Student at CIEMAT, Spain.
Awards
2024 R&D100 Winner: IRIS-SDK: Intelligent Runtime System for Extremely Heterogeneous Computer Architectures
2024, Best Paper Nomination, HPCAsia’24: sKokkos: Enabling Kokkos with Transparent Device Selection on Heterogeneous Systems using OpenACC.
2023, Best Paper Award, WORKS@SC’23 Julia as a Unifying End-to-End Workflow Language on the Frontier Exascale System.
2023, Outstanding Paper Award, IEEE HPEC’23 IRIS-DMEM: An Efficient Memory Management for Heterogeneous Computing.
2022, Best Paper Award, WACCPD@SC’22 KokkACC: Enhancing Kokkos with OpenACC.
2020, IEEE-CS Early Career Researcher Award for Excellence in HPC.
2018, Juan de la Cierva Fellowship, Government of Spain.
2011, FPI CIEMAT Fellowship, Spain.
2009, Microsoft Imagine Cup.