Easy, Fast, and Energy-Efficient Object Detection on Heterogeneous On-Chip Architectures

Ehsan Totoni, Mert Dikmen, María JesúsGarzarán

Research output: Contribution to journalArticlepeer-review


We optimize a visual object detection application (that uses Vision Video Library kernels) and show that OpenCL is a unified programming paradigm that can provide high performance when running on the Ivy Bridge heterogeneous on-chip architecture.We evaluate different mapping techniques and show that running each kernel where it fits the best and using software pipelining can provide 1.91 times higher performance and 42% better energy efficiency. We also show how to trade accuracy for energy at runtime. Overall, our application can perform accurate object detection at 40 frames per second (fps) in an energy-efficient manner.

Original languageEnglish (US)
Pages (from-to)1-25
Number of pages25
JournalACM Transactions on Architecture and Code Optimization
Issue number4
StatePublished - Jan 1 2013


  • Design
  • Energy Efficiency
  • Heterogeneous On-Chip Architectures
  • Languages
  • Opencl
  • Performance
  • Portable (Mobile) Devices
  • Simd

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Hardware and Architecture


Dive into the research topics of 'Easy, Fast, and Energy-Efficient Object Detection on Heterogeneous On-Chip Architectures'. Together they form a unique fingerprint.

Cite this