research-article

The Movidius Myriad Architecture's Potential for Scientific Computing

Authors:

Mircea Horea Ionica,

David GreggAuthors Info & Claims

IEEE Micro, Volume 35, Issue 1

Pages 6 - 14

https://doi.org/10.1109/MM.2015.4

Published: 01 January 2015 Publication History

Abstract

In recent years, a new generation of ultralow-power processors have emerged that are aimed primarily at signal processing in mobile computing. However, their architecture could make some of these useful for other applications. Algorithms originally developed for scientific computing are used increasingly in signal conditioning and emerging fields such as computer vision, increasing the demand for computing power in mobile systems. In this article, the authors describe the design and implementation of dense matrix multiplication on the Movidius Myriad architecture and evaluate its performance and energy efficiency. The authors demonstrate a performance of 8.11 Gflops on the Myriad I processor and a performance/watt ratio of 23.17 Gflops/W for a key computational kernel. These results show significant potential for scientific-computing tasks and invite further research.

References

[1]

M. Ali etal., “Level-3 BLAS on the TI C6678 Multi-Core DSP,” Proc. IEEE 24th Int'l Symp. Computer Architecture and High Performance Computing, 2012, pp. 179–186.

Google Scholar

[2]

S. Williams etal., “The Potential of the Cell Processor for Scientific Computing,” Proc. 3rd Conf. Computing Frontiers, 2006, pp. 9–20.

Digital Library

Google Scholar

[3]

D. Moloney etal., “1TOPS/W Software Programmable Media Processor,” Hot Chips 23, 2011; www.hotchips.org/wp-content/uploads/hc_archives/hc23/HC23.19.8-Video/HC23.19.811-1TOPS-Media-Moloney-Movidius.pdf.

Google Scholar

[4]

J.J. Dongarra etal., “A Set of Level 3 Basic Linear Algebra Subprograms,” ACM Trans. Mathematical Software, vol. 16, no. 1, 1990, pp. 1–17.

Digital Library

Google Scholar

[5]

D.C. Snowdon, S. Ruocco, and G. Heiser, “Power Management and Dynamic Voltage Scaling: Myths and Facts,” Proc. Workshop Power Aware Real-Time Computing, 2005; www.ssrg.nicta.com.au/publications/papers/Snowdon_RH_05.abstract.pml.

Google Scholar

[6]

A. Miyoshi etal., “Critical Power Slope: Understanding the Runtime Effects of Frequency Scaling,” Proc. 16th Int'l Conf. Supercomputing (ICS 02), 2002, pp. 35–44.

Google Scholar

[7]

B.R. Rau and C.D. Glaeser, “Some Scheduling Techniques and an Easily Schedulable Horizontal Architecture for High Performance Scientific Computing,” Proc. 14th Ann. Workshop Microprogramming (MICRO 14), 1981, pp. 183–198.

Digital Library

Google Scholar

[8]

I. Kodukula etal., “An Experimental Evaluation of Tiling and Shackling for Memory Hierarchy Management,” Proc. 13th Int'l Conf. Supercomputing (ICS 99), 1999, pp. 482–491.

Digital Library

Google Scholar

[9]

F.D. Igual etal., “Unleashing the High-Performance and Low-Power of Multi-core DSPs for General-Purpose HPC,” Proc. Int'l Conf. High Performance Computing, Networking, Storage and Analysis (SC 12), 2012, pp. 26:1–26:11.

Google Scholar

[10]

A. Pedram, R. van de Geijn, and A. Gerstlauer, “Codesign Tradeoffs for High-Performance, Low Power Linear Algebra Architectures,” IEEE Trans. Computers, vol. 61, no. 12, 2012, pp. 1724–1736.

Digital Library

Google Scholar

[11]

Intel Xeon Phi Product Family: Performance Brief, Intel, Dec. 2013; www.intel.com/content/www/us/en/benchmarks/xeon-phi-product-family-performance-brief.html.

Google Scholar

[12]

S. Oberlin, Accelerating Exascale: How the End of Moore's Law Scaling is Changing the Machines You Use, the Way You Code, and the Algorithms You Use, Nvidia, Mar. 2014; www.siam.org/meetings/ex14/02-oberlin-slides.pdf.

Google Scholar

Cited By

View all

Sun RQiu PLyu YDong JWang HWang DQu G(2023)Lightning: Leveraging DVFS-induced Transient Fault Injection to Attack Deep Learning Accelerator of GPUsACM Transactions on Design Automation of Electronic Systems10.1145/361789329:1(1-22)Online publication date: 20-Sep-2023
https://dl.acm.org/doi/10.1145/3617893
Varghese BWang NBermbach DHong CLara EShi WStewart C(2021)A Survey on Edge Performance BenchmarkingACM Computing Surveys10.1145/344469254:3(1-33)Online publication date: 22-Apr-2021
https://dl.acm.org/doi/10.1145/3444692
Ham MMoon JLim GJung JAhn HSong WWoo SKapoor PChae DJang GAhn YLee JEldh SFalessi D(2021)NNStreamerProceedings of the 43rd International Conference on Software Engineering: Software Engineering in Practice10.1109/ICSE-SEIP52600.2021.00029(198-207)Online publication date: 25-May-2021
https://dl.acm.org/doi/10.1109/ICSE-SEIP52600.2021.00029
Show More Cited By

Index Terms

The Movidius Myriad Architecture's Potential for Scientific Computing

Index terms have been assigned to the content through auto-classification.

Recommendations

The potential of the cell processor for scientific computing
CF '06: Proceedings of the 3rd conference on Computing frontiers

The slowing pace of commodity microprocessor performance improvements combined with ever-increasing chip power demands has become of utmost concern to computational scientists. As a result, the high performance computing community is examining ...
On the efficiency of the accelerated processing unit for scientific computing
HPC '16: Proceedings of the 24th High Performance Computing Symposium

The AMD APU (Accelerated Processing Unit) architecture, which combines CPU and GPU cores on the same die at a low power budget, promises a significant advent in GPU computing, in particular to applications which performance is bottlenecked by the low ...
NVIDIA cuda software and gpu parallel computing architecture
ISMM '07: Proceedings of the 6th international symposium on Memory management

In the past, graphics processors were special purpose hardwired application accelerators, suitable only for conventional rasterization-style graphics applications. Modern GPUs are now fully programmable, massively parallel floating point processors. ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

IEEE Micro Volume 35, Issue 1

Jan.-Feb. 2015

60 pages

ISSN:0272-1732

Issue’s Table of Contents

Publisher

IEEE Computer Society Press

Washington, DC, United States

Publication History

Published: 01 January 2015

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 04 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Sun RQiu PLyu YDong JWang HWang DQu G(2023)Lightning: Leveraging DVFS-induced Transient Fault Injection to Attack Deep Learning Accelerator of GPUsACM Transactions on Design Automation of Electronic Systems10.1145/361789329:1(1-22)Online publication date: 20-Sep-2023
https://dl.acm.org/doi/10.1145/3617893
Varghese BWang NBermbach DHong CLara EShi WStewart C(2021)A Survey on Edge Performance BenchmarkingACM Computing Surveys10.1145/344469254:3(1-33)Online publication date: 22-Apr-2021
https://dl.acm.org/doi/10.1145/3444692
Ham MMoon JLim GJung JAhn HSong WWoo SKapoor PChae DJang GAhn YLee JEldh SFalessi D(2021)NNStreamerProceedings of the 43rd International Conference on Software Engineering: Software Engineering in Practice10.1109/ICSE-SEIP52600.2021.00029(198-207)Online publication date: 25-May-2021
https://dl.acm.org/doi/10.1109/ICSE-SEIP52600.2021.00029
Peled LWeiser UEtsion Y(2019)A Neural Network Prefetcher for Arbitrary Memory Access PatternsACM Transactions on Architecture and Code Optimization10.1145/334500016:4(1-27)Online publication date: 15-Oct-2019
https://dl.acm.org/doi/10.1145/3345000

Abstract

References

Cited By

Index Terms

Recommendations

The potential of the cell processor for scientific computing

On the efficiency of the accelerated processing unit for scientific computing

NVIDIA cuda software and gpu parallel computing architecture

Comments

Information

Published In

Publisher

Publication History

Qualifiers

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations