Leonardo Solis Vasquez

Leonardo
Solis Vasquez

Menu

I'm Researcher

Leonardo
Solis Vasquez

About Me

Explore how my commitment to pushing computational boundaries can elevate your projects and contribute to groundbreaking advancements in your field

I am a computer scientist currently working as a post-doctoral researcher at TU Darmstadt’s Embedded Systems and Applications group since 2015.

I hold a PhD in Computer Science from the same university. My dissertation explores the acceleration of molecular docking through the utilization of heterogeneous computing, incorporating CPUs, GPUs, and FPGAs, while examining the trade-offs between performance, quality, and energy efficiency.

I specialize in delivering enhanced computing performance for scientific and engineering software applications, particularly in scenarios where conventional processors fall short. My expertise extends to high-performance computing, where I contribute significantly to the field, with multiple peer-reviewed papers and active participation as a referee for well-regarded international journals and conferences. My commitment is to push the boundaries of computational efficiency, ensuring optimal solutions for complex tasks in the realms of science and engineering.

Contact Me

What Services I'm Providing

Service 1

Coming soon …

Service 2

Coming soon …

Service 3

Coming soon … 

Research Projects

Jun. 2022 - Dec. 2023

Intel Center of Excellence: Porting AutoDock-GPU to oneAPI and Intel XPUs

Technical University of Darmstadt (Germany)

Our project is funded by Intel through the oneAPI Center of Excellence at TU Darmstadt. We work together with Intel to create a single codebase for the AutoDock molecular docking software that can run efficiently on different hardware architectures.
Specifically, we explore how to port AutoDock-GPU from CUDA to SYCL, a cross-platform parallel programming framework. We also optimize the performance of SYCL implementations on high-end Intel and NVIDIA GPUs.

Mar. 2020 – May 2022

PANDAS: Programmable Appliance for Near-Data Processing Accelerated Storage

Technical University of Darmstadt (Germany)

Our project funded by German Federal Ministry of Education and Research (BMBF) aims to study how Near-Data Processing affects database architecture, performance, and algorithms. Our work involves designing and optimizing software and hardware for update-aware near-data processing systems.

Jul. 2020 – Mar. 2022

Accelerating Molecular Docking using Vector Computer Systems

Technical University of Darmstadt (Germany)

Our project is a collaboration between NEC Germany and TU Darmstadt. Our goal is to enhance AutoDock, a molecular docking software, by applying porting and optimization techniques for the SX-Aurora TSUBASA Vector Engine.

Sep. 2018 – Feb. 2019

EPHoS: Evaluation of Programming Models for Heterogeneous Systems

Technical University of Darmstadt (Germany)

Our project is funded by German Association of the Automotive Industry (VDA). Here, we explore how parallel programming models can be used in the automotive domain for heterogeneous embedded computing platforms. We use benchmarks from the autonomous driving domain to test different programming models on various execution platforms. We also assess the usability of the programming models for the automotive domain.

Mar. 2016 – Sep. 2019

Hardware Acceleration of Molecular Docking (Ph.D. thesis)

Technical University of Darmstadt (Germany) and
The Scripps Research Institute (USA)

As part of my doctoral research stay supported by German Academic Exchange Service (DAAD) and Peruvian National Program for Scholarships and Educational Loans (PRONABEC), I worked on a project to parallelize the molecular docking software AutoDock using OpenCL. I also performed a comprehensive evaluation of the execution performance, quality-of-results, and compute-energy efficiency of the parallelized software on different platforms, such as multi-core CPUs, GPUs, and FPGAs.

Mar. 2014 – May 2015

A cost-effective and portable system for automatic diagnosis of pneumonia in children

Universidad Peruana Cayetano Heredia (Peru)

With the support of Grand Challenges Canada, we develop a new way to diagnose pneumonia using ultrasound images and artificial intelligence. Our method looks at how bright the pixels are in different parts of the images and compares them to known patterns of pneumonia. We also designed a portable device that can be used by trained technicians in remote areas where doctors are scarce.

Mar. 2014 – May 2015

ePetri: Electronic Petri

Universidad Peruana Cayetano Heredia (Peru)

The goal of our project is to demonstrate a system for Microscopic Observation Drug Susceptibility (MODS) cultures interpretation. We test a lens-free imager system that can produce microscopic images of living samples. This system can scan a 24mm2 area with about 40x magnification in one shot.

Apr. 2013 – Oct. 2013

Parallelization of video streaming software

Politecnico di Torino (Italy)

The goal of our project is to test an experimental software tool that examines the data dependency in C programs and generates a visual report of their execution time and performance bottlenecks. We also utilize the tool’s outputs and suggestions to parallelize algorithms targeting multi-core CPUs.

Apr. 2012 – Nov. 2012

Set-Top Box Prototype providing Security Components on FPGA (M.Sc. thesis)

Center for Advanced Security Research Darmstadt (Germany)

As part of my Erasmus study exchange at TU Darmstadt, supported by the Lifelong Learning Programme, I worked on a project to modify a hardware-based MPEG-2 decoder for a set-top-box prototype on FPGA. The aim was to examine the broadcast security features that depend on the low-level hardware elements, such as the MPEG-2 decoder and the encryption cores.

Nov. 2008 – Aug. 2010

Various electronic-engineering related projects (as B.Sc. graduate)

Universidad Nacional de Ingeniería (Peru)

During this phase, I was involved in several projects. As an embedded systems engineer, I implemented communication protocols on MSP430 microcontrollers, evaluated voice compression algorithms on Spartan-3 FPGAs, and developed fingerprint identification algorithms on TMS320 DSPs. Additionally, I applied my cryptography skills by implementing a chaos-based Even-Mansour cipher on Cyclone IV FPGAs.

Publications

Peer-reviewed research papers in journals
Near-Data Processing in Database Systems on Native Computational Storage under HTAP Workloads.
Sep. 2022

T. Vinçon, C. Knödler, L. Solis-Vasquez, A. Bernhardt, S. Tamimi, L. Weber, F. Stock, A. Koch, I. Petrov.
VLDB Endowment, Volume 15.

DOI: 10.14778/3547305.3547307
Benchmarking the Performance of Irregular Computations in AutoDock-GPU Molecular Docking.
Nov. 2021

L. Solis-Vasquez, A. F. Tillack, D. Santos-Martins, A. Koch, S. LeGrand, S. Forli.
Elsevier, Parallel Computing.

DOI: 10.1016/j.parco.2021.102861
Porting and Optimizing Molecular Docking onto the SX-Aurora TSUBASA Vector Computer.
Sep. 2021

L. Solis-Vasquez, E. Focht, A. Koch.
South Ural State University, Supercomputing Frontiers and Innovations (JSFI).

DOI: 10.14529/jsfi210202
On the necessity of explicit cross-layer data formats in near-data processing systems.
Mar. 2021

L. Weber, T. Vinçon, C. Knödler, L. Solis-Vasquez, A. Bernhardt, I. Petrov, A. Koch.
Springer, Distributed and Parallel Databases (DADP).

DOI: 10.1007/s10619-021-07328-z
Accelerating AutoDock4 with GPUs and Gradient-Based Local Search.
Jan. 2021

D. Santos-Martins, L. Solis-Vasquez, A. F. Tillack, M. F. Sanner, A. Koch, S. Forli.
ACS, Journal of Chemical Theory and Computation (JCTC).

DOI: 10.1021/acs.jctc.0c01006
nKV in Action: Accelerating KV-Stores on Native Computational Storage with Near-Data Processing.
Aug. 2020

T. Vinçon, L. Weber, A. Bernhardt, C. Riegger, S. Hardock, C. Knoedler, F. Stock, L. Solis-Vasquez, S. Tamimi, A. Koch, I. Petrov.
VLDB Endowment, Volume 13.

DOI: 10.14778/3415478.3415524
D3R Grand Challenge 4: prospective pose prediction of BACE1 ligands with AutoDock-GPU.
Nov. 2019

D. Santos-Martins, J. Eberhardt, G. Bianco, L. Solis-Vasquez, F. A. Ambrosio, A. Koch, S. Forli.
Springer, Journal of Computer-Aided Molecular Design (JCAMD).

DOI: 10.1007/s10822-019-00241-9
Comparison of affinity ranking using AutoDock-GPU and MM-GBSA scores for BACE-1 inhibitors in the D3R Grand Challenge 4.
Nov. 2019

L. E. Khoury, D. Santos-Martins, S. Sasmal, J. Eberhardt, G. Bianco, F. A. Ambrosio, L. Solis-Vasquez, A. Koch, S. Forli, D. L. Mobley
Springer, Journal of Computer-Aided Molecular Design (JCAMD).

DOI: 10.1007/s10822-019-00240-w
Automatic classification of pediatric pneumonia based on lung ultrasound pattern recognition.
Dec. 2018

M. Correa, M. Zimic, F. Barrientos, R. Barrientos, A. Román-Gonzalez, M. J. Pajuelo, C. Anticona, H. Mayta, A. Alva,
L. Solis-Vasquez, D. A. Figueroa, M. A. Chavez, R. Lavarello, B. Castañeda, V. A. Paz-Soldán, W. Checkley, R. H. Gilman, R. Oberhelman.
Public Library of Science, PLOS ONE Journal.

DOI: 10.1371/journal.pone.0206410
Evaluation of a lens-free imager to facilitate tuberculosis diagnostics in MODS.
Dec. 2015

L. Solis, J. Coronel, D. Rueda, R. H. Gilman, P. Sheen, M. Zimic.
Elsevier, Journal of Tuberculosis.

DOI: 10.1016/j.tube.2015.12.001
Peer-reviewed research papers in conferences
GPU-Accelerated Drug Discovery with Docking on the Summit Supercomputer: Porting, Optimization, and Application to COVID-19 Research.
Jul. 2020

S. LeGrand, A. Scheinberg, A. F. Tillack, M. Thavappiragasam, J. V. Vermaas, R. Agarwal, J. Larkin, D. Poole, D. SantosMartins, L. Solis-Vasquez, A. Koch, S. Forli, O. Hernandez, J. C. Smith, A. Sedova.
ACM, 11th International Conference on Bioinformatics, Computational Biology and Health Informatics (BCB).

DOI: 10.1145/3388440.3412472
Evaluating the Energy Efficiency of OpenCL-accelerated AutoDock Molecular Docking.
Mar. 2020

L. Solis-Vasquez, D. Santos-Martins, A. Koch, S. Forli.
IEEE, 28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP).

DOI: 10.1109/PDP50117.2020.00031
Using Parallel Programming Models for Automotive Workloads on Heterogeneous Systems - a Case Study.
Mar. 2020

L. Sommer, F. Stock, L. Solis-Vasquez, A. Koch.
IEEE, 28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP).

DOI: 10.1109/PDP50117.2020.00010
Work-in-Progress: DAPHNE - An Automotive Benchmark Suite for Parallel Programming Models on Embedded Heterogeneous Platforms.
Oct. 2019

L. Sommer, F. Stock, L. Solis-Vasquez, A. Koch
ACM, International Conference on Embedded Software Companion (EMSOFT).

DOI: 10.1145/3349568.3351547
Filtering of the skin portion on lung ultrasound digital images to facilitate automatic diagnostics of pneumonia.
Nov. 2016

F. Barrientos, A. Román-Gonzalez, R. Barrientos, L. Solis, A. Alva, M. Correa, M. Pajuelo, C. Anticona, R. Lavarello, B. Castañeda, R. Oberhelman, R. H. Gilman, M. Zimic
IEEE, XXXVI Convención de Centro América y Panamá (CONCAPAN).

DOI: 10.1109/CONCAPAN.2016.7942376
Automatic detection of pneumonia analyzing ultrasound digital images.
Nov. 2016

R. Barrientos, A. Román-Gonzalez, F. Barrientos, L. Solis, M. Correa, M. Pajuelo, C. Anticona, R. Lavarello, B. Castañeda, R. Oberhelman, W. Checkley, R. H. Gilman, M. Zimic.
IEEE, XXXVI Convención de Centro América y Panamá (CONCAPAN).

DOI: 10.1109/CONCAPAN.2016.7942375
Peer-reviewed research papers in symposiums and workshops
Graphtoy: Fast Software Simulation of Applications for AMD’s AI Engines.
Mar. 2024

J. Strobl, L. Solis-Vasquez, Y. Lavan, A. Koch. Springer, 20th International Symposium on Applied Reconfigurable Computing (ARC).

DOI: 10.1007/978-3-031-55673-9_12
Altis-SYCL: Migrating Altis Benchmarking Suite from CUDA to SYCL for GPUs and FPGAs.
Nov. 2023

C. Weckert, L. Solis-Vasquez, J. Oppermann, A. Koch, O. Sinnen
ACM, SC ’23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis.

DOI: 10.1145/3624062.3624542
Experiences Migrating CUDA to SYCL: A Molecular Docking Case Study.
Apr. 2023

L. Solis-Vasquez, E. Mascarenhas, A. Koch.
ACM, 11th International Workshop on OpenCL (IWOCL).

DOI: 10.1145/3585341.3585372
Simulating Molecular Docking on the SX-Aurora TSUBASA Vector Engine.
Feb. 2023

L. Solis-Vasquez, E. Focht, A. Koch.
Springer, Joint Workshop on Sustained Simulation Performance (WSSP 2021).

DOI: 10.1007/978-3-031-18046-0_2
Mapping Irregular Computations for Molecular Docking to the SX-Aurora TSUBASA Vector Engine.
Nov. 2021

L. Solis-Vasquez, E. Focht, A. Koch.
IEEE, 11th Workshop on Irregular Applications: Architectures and Algorithms (IA3). 

DOI: 10.1109/IA354616.2021.00008
Result-Set Management for NDP Operations on Smart Storage.
Jun. 2022

T. Vinçon, C. Knödler, A. Bernhardt, L. Solis-Vasquez, L. Weber, A. Koch, I. Petrov.
ACM, 18th International Workshop on Data Management on New Hardware (DaMoN).

DOI: 10.1145/3533737.3535097
A Framework for the Automatic Generation of FPGA-based Near-Data Processing Accelerators in Smart Storage Systems.
May 2021

L. Weber, L. Sommer, L. Solis-Vasquez, T. Vinçon, C. Knödler, A. Bernhardt, I. Petrov, A. Koch.
IEEE, International Parallel and Distributed Processing Symposium Workshops (IPDPSW).

DOI: 10.1109/IPDPSW52791.2021.00028
A cost model for NDP-aware query optimization for KV-stores.
Jun. 2021

C. Knödler, T. Vinçon, A. Bernhardt, L. Solis-Vasquez, L. Weber, A. Koch, I. Petrov.
ACM, 17th International Workshop on Data Management on New Hardware (DaMoN).

DOI: 10.1145/3465998.3466013
Parallelizing Irregular Computations for Molecular Docking.
Nov. 2020

L. Solis-Vasquez, D. Santos-Martins, A. F. Tillack, A. Koch, J. Eberhardt, S. Forli.
IEEE, 1010th Workshop on Irregular Applications: Architectures and Algorithms (IA3).

DOI: 10.1109/IA351965.2020.00008
A Case Study in Using OpenCL on FPGAs: Creating an Open-Source Accelerator of the AutoDock Molecular Docking Software.
Aug. 2018

L. Solis-Vasquez, A. Koch.
IEEE, 5th International Workshop on FPGAs for Software Programmers (FSP).

https://ieeexplore.ieee.org/document/8470463
A Performance and Energy Evaluation of OpenCL-accelerated Molecular Docking.
May 2017

L. Solis-Vasquez, A. Koch.
ACM, 5th International Workshop on OpenCL (IWOCL).

DOI: 10.1145/3078155.3078167
Miscellaneous research articles and contributions
Speeding up simulations for drug discovery with Autodock-GPU.
Oct. 2021

L. Solis-Vasquez, A. F. Tillack, D. Santos-Martins, A. Koch, S. Forli.
HiPEAC, HiPEAC info 64.

https://www.hipeac.net/magazine/7160
DAPHNE - An Automotive Benchmark Suite for Parallel Programming Models on Embedded Heterogeneous Platforms.
Apr. 2020

L. Sommer, F. Stock, L. Solis-Vasquez, A. Koch.
Future Automotive HW/SW Platform Design (Dagstuhl Seminar 19502), Dagstuhl Reports. 

DOI: 10.4230/DagRep.9.12.28
EPHoS: Evaluation of Programming Models for Heterogeneous Systems.
Jun. 2019

L. Sommer, F. Stock, L. Solis-Vasquez, A. Koch.
German Association of the Automotive Industry – Verband der Automobilindustrie (VDA).

https://hds.hebis.de/ulbda
Test set of 140 complexes for AutoDock-GPU [Data set].
Sep. 2020

D. Santos-Martins, L. Solis-Vasquez, A. F. Tillack, M. F. Sanner, A. Koch, S. Forli.
Zenodo. 

DOI: 10.5281/zenodo.4031961
Theses
Accelerating Molecular Docking by Parallelized Heterogeneous Computing - A Case Study of Performance, Quality of Results, and Energy-Efficiency using CPUs, GPUs, and FPGAs.
Dec. 2019

L. Solis Vasquez.
TUprints, Ph.D. Thesis.

DOI: 10.25534/tuprints-00009288
Implementation of a Set-Top Box Architecture providing Security Components on an FPGA.
Mar. 2013

L. Solis Vasquez.
Repository – Politecnico di Torino, M.Sc. Thesis.

https://pico.polito.it

Stay In Touch

Whether you wish to discuss new ideas or have a project for me, simply fill this form and I’ll get back to you soon.
Orcid Github Linkedin-in Link Gitlab Google Twitter Instagram Researchgate