Exploiting Approximate Feature Extraction via Genetic Programming for Hardware Acceleration in a Heterogeneous Microprocessor

Hongyang Jia, Naveen Verma

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


This paper presents a heterogeneous microprocessor for low-energy sensor-inference applications. Hardware acceleration has shown to enable substantial energy-efficiency and throughput gains, but raises significant challenges where programmable computations are required, as in the case of feature extraction. To overcome this, a programmable feature-extraction accelerator (FEA) is presented that exploits genetic programming for automatic program synthesis. This leads to approximate, but highly structured, computations, enabling: 1) a high degree of specialization; 2) systematic mapping of programs to the accelerator; and 3) energy scalability via user-controllable approximation knobs. A microprocessor integrating a CPU with feature-extraction and classification accelerators is prototyped in 130-nm CMOS. Two medical-sensor applications (electroencephalogram-based seizure detection and electrocardiogram-based arrhythmia detection) demonstrate 325 × and 156 × energy reduction, respectively, for programmable feature extraction implemented on the accelerator versus a CPU-only architecture, and 7.6 × and 6.5 × energy reduction, respectively, versus a CPU-with-coprocessor architecture. Furthermore, 20 × and 9 × energy scalability, respectively, is demonstrated via the approximation knobs. The energy-efficiency of the programmable FEA is 220 GOPS/W, near that of fixed-function accelerators in the same technology, exceeding typical programmable accelerators.

Original languageEnglish (US)
Pages (from-to)1016-1027
Number of pages12
JournalIEEE Journal of Solid-State Circuits
Issue number4
StatePublished - Apr 2018

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering


  • Approximate computation
  • feature extraction
  • machine learning
  • programmable accelerator
  • sensor inference


Dive into the research topics of 'Exploiting Approximate Feature Extraction via Genetic Programming for Hardware Acceleration in a Heterogeneous Microprocessor'. Together they form a unique fingerprint.

Cite this