Embedding statistical tests for on-chip dynamic voltage and temperature monitoring

  • Authors:
  • Lionel Vincent;Philippe Maurine;Suzanne Lesecq;Edith Beigné

  • Affiliations:
  • CEA-LETI, Grenoble Cedex, France;LIRMM, Université Montpellier, Montpellier, Cedex, France;CEA-LETI, Grenoble Cedex, France;CEA-LETI, Grenoble Cedex, France

  • Venue:
  • Proceedings of the 49th Annual Design Automation Conference
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

All mobile applications require high performances with very long battery life. The speed and power consumption trade-off clearly appears as a prominent challenge to optimize the overall energy efficiency. In Multiprocessor System-On-Chip architectures, the trade-off is usually achieved by dynamically adapting the supply voltage and the operating frequency of a processor cluster or of each processor at fine grain. This requires monitoring accurately, on-chip and at runtime, the supply voltage and temperature across the die. Within this context, this paper introduces a method to estimate, from on-chip measurements, using embedded statistical tests, the supply voltage and temperature of small die area using low-cost digital sensors featuring a set of ring oscillators solely. The results obtained, considering a 32nm process, demonstrate the efficiency of the proposed method. Indeed, voltage and temperature measurement errors are kept, in average, below 5mV and 7°C, respectively.