A Deep Q-Learning Approach for Dynamic Management of Heterogeneous Processors

Ujjwal Gupta, Sumit K. Mandal, Manqing Mao, Chaitali Chakrabarti, Umit Ogras

Research output: Contribution to journalArticlepeer-review

36 Scopus citations


Heterogeneous multiprocessor system-on-chips (SoCs) provide a wide range of parameters that can be managed dynamically. For example, one can control the type (big/little), number and frequency of active cores in state-of-the-art mobile processors at runtime. These runtime choices lead to more than 10× range in execution time, 5× range in power consumption, and 50× range in performance per watt. Therefore, it is crucial to make optimum power management decisions as a function of dynamically varying workloads at runtime. This paper presents a reinforcement learning approach for dynamically controlling the number and frequency of active big and little cores in mobile processors. We propose an efficient deep Q-learning methodology to optimize the performance per watt (PPW). Experiments using Odroid XU3 mobile platform show that the PPW achieved by the proposed approach is within 1 percent of the optimal value obtained by an oracle.

Original languageEnglish (US)
Article number8607043
Pages (from-to)14-17
Number of pages4
JournalIEEE Computer Architecture Letters
Issue number1
StatePublished - Jan 1 2019


  • Deep reinforcement learning
  • Heterogeneous multi-cores
  • Power management

ASJC Scopus subject areas

  • Hardware and Architecture


Dive into the research topics of 'A Deep Q-Learning Approach for Dynamic Management of Heterogeneous Processors'. Together they form a unique fingerprint.

Cite this