The future is dynamic: adaptive runtime resource management for heterogeneous computer platforms

ABSTRACT

Software developers increasingly need to take advantage of heterogeneous hardware resources, like GPUs and DSPs, while coping with dynamic events and quality of service requirements. This demonstration shows how an adaptive resource manager that dynamically assigns components to processing elements can take advantage of heterogeneous platforms, in this case a platform consisting of multiple multi-core CPUs and GPUs. It will also demonstrate a simulator that is used to see the impact of different resource management strategies and options before actually implementing them. The application used in the demonstration will be a demanding real-world video processing application that uses the GStreamer framework, used to build componentized stream-processing applications, for which we have built several CPU- and GPU- accelerated components.

INDEX TERMS

Primary Classification:
  D. Software
  D.3 PROGRAMMING LANGUAGES
      D.3.4 Processors
          Subjects: Run-time environments

Additional Classification:
  C. Computer Systems Organization
  C.1 PROCESSOR ARCHITECTURES
      C.1.3 Other Architecture Styles
          Subjects: Heterogeneous (hybrid) systems
  C.3 SPECIAL-PURPOSE AND APPLICATION-BASED SYSTEMS
      Subjects: Real-time and embedded systems

  D. Software
  D.4 OPERATING SYSTEMS
      D.4.1 Process Management
          Subjects: Multiprocessing/multiprogramming/multitasking

General Terms:
Algorithms, Experimentation, Measurement, Performance

Keywords:
embedded software engineering, heterogeneous devices, runtime resource management