State-of-the-art in Heterogeneous Computing

Brodtkorb, Andre R.; Dyken, Christopher; Hagen, Trond R.; Hjelmervik, Jon M.; Storaasli, Olaf O.

doi:10.1155/2010/540159

Title: State-of-the-art in Heterogeneous Computing

Full Record
Other Related Research

Abstract

Node level heterogeneous architectures have become attractive during the last decade for several reasons: compared to traditional symmetric CPUs, they offer high peak performance and are energy and/or cost efficient. With the increase of fine-grained parallelism in high-performance computing, as well as the introduction of parallelism in workstations, there is an acute need for a good overview and understanding of these architectures. We give an overview of the state-of-the-art in heterogeneous computing, focusing on three commonly found architectures: the Cell Broadband Engine Architecture, graphics processing units (GPUs), and field programmable gate arrays (FPGAs). We present a review of hardware, available software tools, and an overview of state-of-the-art techniques and algorithms. Furthermore, we present a qualitative and quantitative comparison of the architectures, and give our view on the future of heterogeneous computing.

Authors:

Brodtkorb, Andre R. ^[1]; Dyken, Christopher ^[1]; Hagen, Trond R. ^[1]; Hjelmervik, Jon M. ^[1]; Storaasli, Olaf O. ^[2]

SINTEF ICT, Department of Applied Mathematics, Blindern, Oslo, Norway
Oak Ridge National Laboratory, Future Technologies Group, Oak Ridge, TN, USA

Publication Date:: Fri Jan 01 00:00:00 EST 2010

Sponsoring Org.:: USDOE

OSTI Identifier:: 1198007

Grant/Contract Number:: AC05-00OR22725; 186947; 180023

Resource Type:: Published Article

Journal Name:: Scientific Programming

Additional Journal Information:: Journal Name: Scientific Programming Journal Volume: 18 Journal Issue: 1; Journal ID: ISSN 1058-9244

Publisher:: Hindawi Publishing Corporation

Country of Publication:: Egypt

Language:: English

Citation Formats


                    Brodtkorb, Andre R., Dyken, Christopher, Hagen, Trond R., Hjelmervik, Jon M., and Storaasli, Olaf O. State-of-the-art in Heterogeneous Computing.  Egypt: N. p., 2010. 
Web.  doi:10.1155/2010/540159.

Copy to clipboard


                    Brodtkorb, Andre R., Dyken, Christopher, Hagen, Trond R., Hjelmervik, Jon M., & Storaasli, Olaf O. State-of-the-art in Heterogeneous Computing.  Egypt.  https://doi.org/10.1155/2010/540159

Copy to clipboard


                    Brodtkorb, Andre R., Dyken, Christopher, Hagen, Trond R., Hjelmervik, Jon M., and Storaasli, Olaf O. Fri .  
"State-of-the-art in Heterogeneous Computing".  Egypt.  https://doi.org/10.1155/2010/540159.

Copy to clipboard


                    
@article{osti_1198007,

  title        = {State-of-the-art in Heterogeneous Computing},

  author       = {Brodtkorb, Andre R. and Dyken, Christopher and Hagen, Trond R. and Hjelmervik, Jon M. and Storaasli, Olaf O.},

  abstractNote = {Node level heterogeneous architectures have become attractive during the last decade for several reasons: compared to traditional symmetric CPUs, they offer high peak performance and are energy and/or cost efficient. With the increase of fine-grained parallelism in high-performance computing, as well as the introduction of parallelism in workstations, there is an acute need for a good overview and understanding of these architectures. We give an overview of the state-of-the-art in heterogeneous computing, focusing on three commonly found architectures: the Cell Broadband Engine Architecture, graphics processing units (GPUs), and field programmable gate arrays (FPGAs). We present a review of hardware, available software tools, and an overview of state-of-the-art techniques and algorithms. Furthermore, we present a qualitative and quantitative comparison of the architectures, and give our view on the future of heterogeneous computing.},

  doi          = {10.1155/2010/540159},

  journal      = {Scientific Programming},

  number       = 1,

  volume       = 18,

  place        = {Egypt},

  year         = {Fri Jan 01 00:00:00 EST 2010},

  month        = {Fri Jan 01 00:00:00 EST 2010}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Publisher's Version of Record
https://doi.org/10.1155/2010/540159

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

State-of-the-Art in Heterogeneous Computing

Journal Article Brodtkorb, Andre R ; Dyken, Christopher ; Hagen, Trond R ; ... - Scientific Programming

Node level heterogeneous architectures have become attractive during the last decade for several reasons: compared to traditional symmetric CPUs, they offer high peak performance and are energy and/or cost efficient. With the increase of fine-grained parallelism in high-performance computing, as well as the introduction of parallelism in workstations, there is an acute need for a good overview and understanding of these architectures. We give an overview of the state-of-the-art in heterogeneous computing, focusing on three commonly found architectures: the Cell Broadband Engine Architecture, graphics processing units (GPUs), and field programmable gate arrays (FPGAs).We present a review of hardware, available softwaremore »« less
State-of-the-art in hterogeneous computing

Journal Article Brodtkorb, Andre R. ; Dyken, Christopher ; Hagen, Trond R. ; ... - Scientific Programming

Node level heterogeneous architectures have become attractive during the last decade for several reasons: compared to traditional symmetric CPUs, they offer high peak performance and are energy and/or cost efficient. With the increase of fine-grained parallelism in high-performance computing, as well as the introduction of parallelism in workstations, there is an acute need for a good overview and understanding of these architectures. We give an overview of the state-of-the-art in heterogeneous computing, focusing on three commonly found architectures: the Cell Broadband Engine Architecture, graphics processing units (GPUs), and field programmable gate arrays (FPGAs).We present a review of hardware, available softwaremore »« less
https://doi.org/10.1155/2010/540159
FPGAs as a Service to Accelerate Machine Learning Inference [PowerPoint]

Technical Report Duarte, Javier ; Holzman, Burt ; Jindariani, Sergo ; ...

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutionalmore »« less
https://doi.org/10.2172/1570210

Full Text Available
FPGA-Accelerated Machine Learning Inference as a Service for Particle Physics Computing

Journal Article Duarte, Javier ; Harris, Philip ; Hauck, Scott ; ... - Computing and Software for Big Science

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model. As examples, we retrain the ResNet-50more »« less
https://doi.org/10.1007/s41781-019-0027-2

Full Text Available
Field Programmable Gate Arrays for Enhancing the Speed and Energy Efficiency of Quantum Dynamics Simulations

Journal Article Rodrı́guez-Borbón, José M. ; Kalantar, Amin ; Yamijala, Sharma S. R. K. C. ; ... - Journal of Chemical Theory and Computation

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, wemore »« less
Cited by 8
https://doi.org/10.1021/acs.jctc.9b01284

Full Text Available

Similar Records