Field Programmable Gate Arrays for Enhancing the Speed and Energy Efficiency of Quantum Dynamics Simulations
Abstract
We present the first application of field programmable gate arrays (FPGAs) as new, customizable hardware architectures for carrying out fast and energy-efficient quantum dynamics simulations of large chemical/material systems. Instead of tailoring the software to fixed hardware, which is the typical case for writing quantum chemistry code for central processing units (CPUs) and graphics processing units (GPUs), FPGAs allow us to directly customize the underlying hardware (even at the level of specific electrical signals in the circuit) to give a truly optimized computational performance for quantum dynamics calculations. By offloading the most intensive and repetitive calculations onto an FPGA, we show that the computational performance of our real-time electron dynamics calculations can even exceed that of optimized commercial mathematical libraries running on high-performance GPUs. In addition to this impressive computational speedup, we show that FPGAs are immensely energy-efficient and consume 4 times less energy than modern GPU or CPU architectures. These energy savings are a practical and important metric for supercomputing centers (many of which exceed over $1 million in power costs alone), as exascale computing capabilities become more widespread and commonplace. Taken together, the implementation techniques and performance metrics of our study demonstrate that FPGAs could play a promisingmore »
- Authors:
-
- Univ. of California, Riverside, CA (United States)
- Univ. Nacional de Córdoba, Córdoba (Argentina). Inst. de Investigaciones en Fisicoquı́mica de Córdoba (INFIQC), UNC−CONICET
- Publication Date:
- Research Org.:
- Univ. of California, Riverside, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Basic Energy Sciences (BES)
- OSTI Identifier:
- 1596516
- Grant/Contract Number:
- FE0030582
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Chemical Theory and Computation
- Additional Journal Information:
- Journal Volume: 15; Journal Issue: 5; Journal ID: ISSN 1549-9618
- Publisher:
- American Chemical Society
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; Elements; circuits; Hamiltonians; two dimensional materials; chemical calculations
Citation Formats
Rodrı́guez-Borbón, José M., Kalantar, Amin, Yamijala, Sharma S. R. K. C., Oviedo, M. Belén, Najjar, Walid, and Wong, Bryan M. Field Programmable Gate Arrays for Enhancing the Speed and Energy Efficiency of Quantum Dynamics Simulations. United States: N. p., 2020.
Web. doi:10.1021/acs.jctc.9b01284.
Rodrı́guez-Borbón, José M., Kalantar, Amin, Yamijala, Sharma S. R. K. C., Oviedo, M. Belén, Najjar, Walid, & Wong, Bryan M. Field Programmable Gate Arrays for Enhancing the Speed and Energy Efficiency of Quantum Dynamics Simulations. United States. https://doi.org/10.1021/acs.jctc.9b01284
Rodrı́guez-Borbón, José M., Kalantar, Amin, Yamijala, Sharma S. R. K. C., Oviedo, M. Belén, Najjar, Walid, and Wong, Bryan M. Fri .
"Field Programmable Gate Arrays for Enhancing the Speed and Energy Efficiency of Quantum Dynamics Simulations". United States. https://doi.org/10.1021/acs.jctc.9b01284. https://www.osti.gov/servlets/purl/1596516.
@article{osti_1596516,
title = {Field Programmable Gate Arrays for Enhancing the Speed and Energy Efficiency of Quantum Dynamics Simulations},
author = {Rodrı́guez-Borbón, José M. and Kalantar, Amin and Yamijala, Sharma S. R. K. C. and Oviedo, M. Belén and Najjar, Walid and Wong, Bryan M.},
abstractNote = {We present the first application of field programmable gate arrays (FPGAs) as new, customizable hardware architectures for carrying out fast and energy-efficient quantum dynamics simulations of large chemical/material systems. Instead of tailoring the software to fixed hardware, which is the typical case for writing quantum chemistry code for central processing units (CPUs) and graphics processing units (GPUs), FPGAs allow us to directly customize the underlying hardware (even at the level of specific electrical signals in the circuit) to give a truly optimized computational performance for quantum dynamics calculations. By offloading the most intensive and repetitive calculations onto an FPGA, we show that the computational performance of our real-time electron dynamics calculations can even exceed that of optimized commercial mathematical libraries running on high-performance GPUs. In addition to this impressive computational speedup, we show that FPGAs are immensely energy-efficient and consume 4 times less energy than modern GPU or CPU architectures. These energy savings are a practical and important metric for supercomputing centers (many of which exceed over $1 million in power costs alone), as exascale computing capabilities become more widespread and commonplace. Taken together, the implementation techniques and performance metrics of our study demonstrate that FPGAs could play a promising role in upcoming quantum chemistry and materials science applications, particularly for the acceleration and energy-efficient execution of quantum dynamics calculations.},
doi = {10.1021/acs.jctc.9b01284},
journal = {Journal of Chemical Theory and Computation},
number = 5,
volume = 15,
place = {United States},
year = {Fri Mar 27 00:00:00 EDT 2020},
month = {Fri Mar 27 00:00:00 EDT 2020}
}
Web of Science
Works referenced in this record:
FPGA accelerator for floating-point matrix multiplication
journal, January 2012
- Jovanović, Ž.; Milutinović, V.
- IET Computers & Digital Techniques, Vol. 6, Issue 4
Double Precision Is Not Needed for Many-Body Calculations: Emergent Conventional Wisdom
journal, June 2018
- Pokhilko, Pavel; Epifanovsky, Evgeny; Krylov, Anna I.
- Journal of Chemical Theory and Computation, Vol. 14, Issue 8
Heterogeneous CPU+GPU-Enabled Simulations for DFTB Molecular Dynamics of Large Chemical and Biological Systems
journal, March 2019
- Allec, Sarah I.; Sun, Yijing; Sun, Jianan
- Journal of Chemical Theory and Computation, Vol. 15, Issue 5
CSR5: An Efficient Storage Format for Cross-Platform Sparse Matrix-Vector Multiplication
conference, January 2015
- Liu, Weifeng; Vinter, Brian
- Proceedings of the 29th ACM on International Conference on Supercomputing - ICS '15
Atomic-Level Characterization of the Structural Dynamics of Proteins
journal, October 2010
- Shaw, D. E.; Maragakis, P.; Lindorff-Larsen, K.
- Science, Vol. 330, Issue 6002
DFTB+, a Sparse Matrix-Based Implementation of the DFTB Method †
journal, July 2007
- Aradi, B.; Hourahine, B.; Frauenheim, Th.
- The Journal of Physical Chemistry A, Vol. 111, Issue 26
Power estimation techniques for FPGAs
journal, October 2004
- Anderson, J. H.; Najm, F. N.
- IEEE Transactions on Very Large Scale Integration (VLSI) Systems, Vol. 12, Issue 10
Millisecond-scale molecular dynamics simulations on Anton
conference, January 2009
- Shaw, David E.; Bowers, Kevin J.; Chow, Edmond
- Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis - SC '09
What every computer scientist should know about floating-point arithmetic
journal, March 1991
- Goldberg, David
- ACM Computing Surveys, Vol. 23, Issue 1
Reversible, opto-mechanically induced spin-switching in a nanoribbon-spiropyran hybrid material
journal, January 2012
- Wong, Bryan M.; Ye, Simon H.; O'Bryan, Greg
- Nanoscale, Vol. 4, Issue 4
Quantum Dynamics of Light-Induced Charge Injection in a Model Dye–Nanoparticle Complex
journal, July 2012
- Negre, Christian F. A.; Fuertes, Valeria C.; Oviedo, M. Belén
- The Journal of Physical Chemistry C, Vol. 116, Issue 28
1.1 Computing's energy problem (and what we can do about it)
conference, February 2014
- Horowitz, Mark
- 2014 IEEE International Solid- State Circuits Conference (ISSCC), 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC)
FPGA Based High Performance Double-Precision Matrix Multiplication
journal, February 2010
- Kumar, Vinay B. Y.; Joshi, Siddharth; Patkar, Sachin B.
- International Journal of Parallel Programming, Vol. 38, Issue 3-4
Introduction to special issue on sustainable computing for ultrascale computing
journal, March 2018
- Lefèvre, Laurent; Pierson, Jean-Marc
- Sustainable Computing: Informatics and Systems, Vol. 17
Quantum Dynamical Simulations as a Tool for Predicting Photoinjection Mechanisms in Dye-Sensitized TiO 2 Solar Cells
journal, August 2012
- Oviedo, M. Belén; Zarate, Ximena; Negre, Christian F. A.
- The Journal of Physical Chemistry Letters, Vol. 3, Issue 18
Photoelectrochemical Hole Injection Revealed in Polyoxotitanate Nanocrystals Functionalized with Organic Adsorbates
journal, November 2014
- Negre, Christian F. A.; Young, Karin J.; Oviedo, Ma. Belén
- Journal of the American Chemical Society, Vol. 136, Issue 46
A Non-Thermal Plasma Route to Plasmonic TiN Nanoparticles
journal, January 2017
- Alvarez Barragan, Alejandro; Ilawe, Niranjan V.; Zhong, Lanlan
- The Journal of Physical Chemistry C, Vol. 121, Issue 4
Scalable and Modular Algorithms for Floating-Point Matrix Multiplication on Reconfigurable Computing Systems
journal, April 2007
- Zhuo, Ling; Prasanna, Viktor K.
- IEEE Transactions on Parallel and Distributed Systems, Vol. 18, Issue 4
Parallel sparse matrix-vector and matrix-transpose-vector multiplication using compressed sparse blocks
conference, January 2009
- Buluç, Aydin; Fineman, Jeremy T.; Frigo, Matteo
- Proceedings of the twenty-first annual symposium on Parallelism in algorithms and architectures - SPAA '09
Real-Time Quantum Dynamics Reveals Complex, Many-Body Interactions in Solvated Nanodroplets
journal, March 2016
- Oviedo, M. Belén; Wong, Bryan M.
- Journal of Chemical Theory and Computation, Vol. 12, Issue 4
Real-Time Quantum Dynamics of Long-Range Electronic Excitation Transfer in Plasmonic Nanoantennas
journal, July 2017
- Ilawe, Niranjan V.; Oviedo, M. Belén; Wong, Bryan M.
- Journal of Chemical Theory and Computation, Vol. 13, Issue 8
Exascale Computing: A New Dawn for Computational Biology
journal, September 2018
- Lee, Christopher T.; Amaro, Rommie E.
- Computing in Science & Engineering, Vol. 20, Issue 5
Effect of quantum tunneling on the efficiency of excitation energy transfer in plasmonic nanoparticle chain waveguides
journal, January 2018
- Ilawe, Niranjan V.; Oviedo, M. Belén; Wong, Bryan M.
- Journal of Materials Chemistry C, Vol. 6, Issue 22
Anton, a special-purpose machine for molecular dynamics simulation
journal, July 2008
- Shaw, David E.; Chao, Jack C.; Eastwood, Michael P.
- Communications of the ACM, Vol. 51, Issue 7
Paving the Way Towards a Highly Energy-Efficient and Highly Integrated Compute Node for the Exascale Revolution: The ExaNoDe Approach
conference, August 2017
- Rigo, Alvise; Pinto, Christian; Pouget, Kevin
- 2017 Euromicro Conference on Digital System Design (DSD)
64-bit floating-point FPGA matrix multiplication
conference, January 2005
- Dou, Yong; Vassiliadis, S.; Kuzmanov, G. K.
- Proceedings of the 2005 ACM/SIGDA 13th international symposium on Field-programmable gate arrays - FPGA '05
Floating-Point Matrix Product on FPGA
conference, May 2007
- Bensaali, Faycal; Amira, Abbes; Sotudeh, Reza
- 2007 IEEE/ACS International Conference on Computer Systems and Applications
LIKWID: A Lightweight Performance-Oriented Tool Suite for x86 Multicore Environments
conference, September 2010
- Treibig, Jan; Hager, Georg; Wellein, Gerhard
- 2010 International Conference on Parallel Processing Workshops (ICPPW), 2010 39th International Conference on Parallel Processing Workshops
The Scalable Heterogeneous Computing (SHOC) benchmark suite
conference, January 2010
- Danalis, Anthony; Marin, Gabriel; McCurdy, Collin
- Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units - GPGPU '10
FPGA vs. GPU for sparse matrix vector multiply
conference, December 2009
- Zhang, Yan; Shalabi, Yasser H.; Jain, Rishabh
- 2009 International Conference on Field-Programmable Technology (FPT)
Exploring irregular memory accesses on FPGAs
conference, January 2011
- Halstead, Robert J.; Villarreal, Jason; Najjar, Walid
- Proceedings of the first workshop on Irregular applications: architectures and algorithm - IAAA '11
Measuring GPU Power with the K20 Built-in Sensor
conference, October 2018
- Burtscher, Martin; Zecena, Ivan; Zong, Ziliang
- GPGPU-7: Seventh Workshop on General Purpose Processing Using GPUs, Proceedings of Workshop on General Purpose Processing Using GPUs
Technology Scaling in FPGAs: Trends in Applications and Architectures
conference, May 2015
- Shannon, Lesley; Cojocaru, Veronica; Dao, Cong Nguyen
- 2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)