Deffe: A data-efficient framework for performance characterization in domain-specific computing

Frank Liu, Narasinga Rao Miniskar, Dwaipayan Chakraborty, Jeffrey S. Vetter

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

As the computer architecture community moves toward the end of traditional device scaling, domain-specific architectures are becoming more pervasive. Given the number of diverse workloads and emerging heterogeneous architectures, exploration of this design space is a constrained optimization problem in a high-dimensional parameter space. In this respect, predicting workload performance both accurately and efficiently is a critical task for this exploration. In this paper, we present Deffe: a framework to estimate workload performance across varying architectural configurations. Deffe uses machine learning to improve the performance of this design space exploration. By casting the work of performance prediction itself as transfer learning tasks, the modelling component of Deffe can leverage the learned knowledge on one workload and "transfer" it to a new workload. Our extensive experimental results on a contemporary architecture toolchain (RISC-V and GEM5) and infrastructure show that the method can achieve superior testing accuracy with an effective reduction of 32-80× in terms of the amount of required training data. The overall run-time can be reduced from 400 hours to 5 hours when executed over 24 CPU cores. The infrastructure component of Deffe is based on scalable and easy-to-use open-source software components.

Original languageEnglish
Title of host publication17th ACM International Conference on Computing Frontiers 2020, CF 2020 - Proceedings
PublisherAssociation for Computing Machinery, Inc
Pages182-191
Number of pages10
ISBN (Electronic)9781450379564
DOIs
StatePublished - May 11 2020
Event17th ACM International Conference on Computing Frontiers, CF 2020 - Catania, Italy
Duration: May 11 2020May 13 2020

Publication series

Name17th ACM International Conference on Computing Frontiers 2020, CF 2020 - Proceedings

Conference

Conference17th ACM International Conference on Computing Frontiers, CF 2020
Country/TerritoryItaly
CityCatania
Period05/11/2005/13/20

Funding

In this paper, we have presented Deffe, a general framework for workload performance prediction in domain-specific computing. The modeling component of the framework is built on a CNN and the transfer learning technique. The modeling component is supported by the infrastructure component, which is based on a

Keywords

  • RISC-V
  • machine learning
  • multichannel convolution
  • transfer learning
  • workload characterization

Fingerprint

Dive into the research topics of 'Deffe: A data-efficient framework for performance characterization in domain-specific computing'. Together they form a unique fingerprint.

Cite this