AIRA: A Framework for Flexible Compute Kernel Execution in Heterogeneous Platforms

Robert Lyerly, Alastair Murray, Antonio Barbalace, Binoy Ravindran

Research output: Contribution to journalArticlepeer-review

Abstract

Heterogeneous-ISA computing platforms have become ubiquitous, and will be used for diverse workloads which render static mappings of computation to processors inadequate. Dynamic mappings which adjust an application’s usage in consideration of platform workload can reduce application latency and increase throughput for heterogeneous platforms. We introduce AIRA, a compiler and runtime for flexible execution of applications in CPU-GPU platforms. Using AIRA, we demonstrate up to a 3.78x speedup in benchmarks from Rodinia and Parboil, run with various workloads on a server-class platform. Additionally, AIRA is able to extract up to an 87 percent increase in platform throughput over a static mapping.
Original languageEnglish
Pages (from-to)269-282
Number of pages14
JournalIEEE Transactions on Parallel and Distributed Systems
Volume29
Issue number2
DOIs
Publication statusPublished - 10 Oct 2017

Keywords

  • graphics processing units
  • microprocessor chips
  • multiprocessing systems
  • parallel processing
  • program compilers
  • AIRA
  • compiler
  • flexible compute kernel execution runtime
  • static mapping
  • platform throughput
  • server-class platform
  • CPU-GPU platforms
  • platform workload
  • dynamic mappings
  • heterogeneous-ISA computing platforms
  • Computer architecture
  • Kernel
  • Runtime
  • Graphics processing units
  • Throughput
  • Atmospheric modeling
  • Heterogeneous architectures
  • compilers
  • runtimes
  • programming models

Fingerprint Dive into the research topics of 'AIRA: A Framework for Flexible Compute Kernel Execution in Heterogeneous Platforms'. Together they form a unique fingerprint.

Cite this