Efficient control and communication paradigms for coarse-grained spatial architectures

Michael Pellauer, Angshuman Parashar, Michael Adler, Bushra Ahsan, Randy Allmon, Neal Crago, Kermin Fleming, Mohit Gambhir, Aamer Jaleel, Tushar Krishna, Daniel Lustig, Stephen Maresh, Vladimir Pavlov, Rachid Rayess, Antonia Zhai, Joel Emer

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

There has been recent interest in exploring the acceleration of nonvectorizable workloads with spatially programmed architectures that are designed to efficiently exploit pipeline parallelism. Such an architecture faces two main problems: how to efficiently control each processing element (PE) in the system, and how to facilitate inter-PE communication without the overheads of traditional shared-memory coherent memory. In this article, we explore solving these problems using triggered instructions and latency-insensitive channels. Triggered instructions completely eliminate the program counter (PC) and allow programs to transition concisely between states without explicit branch instructions. Latency-insensitive channels allow efficient communication of inter-PE control information while simultaneously enabling flexible code placement and improving tolerance for variable events such as cache accesses. Together, these approaches provide a unified mechanism to avoid overserialized execution, essentially achieving the effect of techniques such as dynamic instruction reordering and multithreading. Our analysis shows that a spatial accelerator using triggered instructions and latency-insensitive channels can achieve 8� greater area-normalized performance than a traditional general-purpose processor. Further analysis shows that triggered control reduces the number of static and dynamic instructions in the critical paths by 62% and 64%, respectively, over a PC-style baseline, increasing the performance of the spatial programming approach by 2.0�.

Original languageEnglish (US)
Article number10
JournalACM Transactions on Computer Systems
Volume33
Issue number3
DOIs
StatePublished - Aug 1 2015

Bibliographical note

Publisher Copyright:
� 2015 ACM.

Keywords

  • Reconfigurable accelerators
  • Spatial programming

Fingerprint

Dive into the research topics of 'Efficient control and communication paradigms for coarse-grained spatial architectures'. Together they form a unique fingerprint.

Cite this