Skip to main content

Hardware support for fine-grained event-driven computation in anton 2

Publication ,  Conference
Grossman, JP; Kuskin, JS; Bank, JA; Theobald, M; Dror, RO; Ierardi, DJ; Larson, RH; Ben Schafer, U; Towles, B; Young, C; Shaw, DE
Published in: International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS
April 5, 2013

Exploiting parallelism to accelerate a computation typically involves dividing it into many small tasks that can be assigned to different processing elements. An efficient execution schedule for these tasks can be difficult or impossible to determine in advance, however, if there is uncertainty as to when each task's input data will be available. Ideally, each task would run in direct response to the arrival of its input data, thus allowing the computation to proceed in a fine-grained event-driven manner. Realizing this ideal is difficult in practice, and typically requires sacrificing flexibility for performance. In Anton 2, a massively parallel special-purpose supercomputer for molecular dynamics simulations, we addressed this challenge by including a hardware block, called the dispatch unit, that provides flexible and efficient support for fine-grained eventdriven computation. Its novel features include a many-to-many mapping from input data to a set of synchronization counters, and the ability to prioritize tasks based on their type. To solve the additional problem of using a fixed set of synchronization counters to track input data for a potentially large number of tasks, we created a software library that allows programmers to treat Anton 2 as an idealized machine with infinitely many synchronization counters. The dispatch unit, together with this library, made it possible to simplify our molecular dynamics software by expressing it as a collection of independent tasks, and the resulting finegrained execution schedule improved overall performance by up to 16% relative to a coarse-grained schedule for precisely the same computation. Copyright © 2013 ACM.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS

DOI

Publication Date

April 5, 2013

Start / End Page

549 / 560
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Grossman, J. P., Kuskin, J. S., Bank, J. A., Theobald, M., Dror, R. O., Ierardi, D. J., … Shaw, D. E. (2013). Hardware support for fine-grained event-driven computation in anton 2. In International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS (pp. 549–560). https://doi.org/10.1145/2451116.2451175
Grossman, J. P., J. S. Kuskin, J. A. Bank, M. Theobald, R. O. Dror, D. J. Ierardi, R. H. Larson, et al. “Hardware support for fine-grained event-driven computation in anton 2.” In International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS, 549–60, 2013. https://doi.org/10.1145/2451116.2451175.
Grossman JP, Kuskin JS, Bank JA, Theobald M, Dror RO, Ierardi DJ, et al. Hardware support for fine-grained event-driven computation in anton 2. In: International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS. 2013. p. 549–60.
Grossman, J. P., et al. “Hardware support for fine-grained event-driven computation in anton 2.” International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS, 2013, pp. 549–60. Scopus, doi:10.1145/2451116.2451175.
Grossman JP, Kuskin JS, Bank JA, Theobald M, Dror RO, Ierardi DJ, Larson RH, Ben Schafer U, Towles B, Young C, Shaw DE. Hardware support for fine-grained event-driven computation in anton 2. International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS. 2013. p. 549–560.

Published In

International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS

DOI

Publication Date

April 5, 2013

Start / End Page

549 / 560