Login / Signup

Towards Real-Time Monitoring of Thermal Peaks in Systems-on-Chip (SoC).

Aziz OukairaAhmad HassanMohamed AliYvon SavariaAhmed Lakhssassi
Published in: Sensors (Basel, Switzerland) (2022)
This paper presents a method to monitor the thermal peaks that are major concerns when designing Integrated Circuits (ICs) in various advanced technologies. The method aims at detecting the thermal peak in Systems on Chip (SoC) using arrays of oscillators distributed over the area of the chip. Measured frequencies are mapped to local temperatures that are used to produce a chip thermal mapping. Then, an indication of the local temperature of a single heat source is obtained in real-time using the Gradient Direction Sensor (GDS) technique. The proposed technique does not require external sensors, and it provides a real-time monitoring of thermal peaks. This work is performed with Field-Programmable Gate Array (FPGA), which acts as a System-on-Chip, and the detected heat source is validated with a thermal camera. A maximum error of 0.3 °C is reported between thermal camera and FPGA measurements.
Keyphrases
  • high throughput
  • circulating tumor cells
  • convolutional neural network
  • heat stress
  • mass spectrometry
  • high speed
  • deep learning