Neural network-based cooling design for high-performance processors

Zihao Yuan; Ayse K Coskun

doi:10.1016/j.isci.2021.103582

Neural network-based cooling design for high-performance processors

iScience. 2021 Dec 9;25(1):103582. doi: 10.1016/j.isci.2021.103582. eCollection 2022 Jan 21.

Authors

Zihao Yuan¹, Ayse K Coskun¹

Affiliation

¹ Electrical and Computer Engineering Department from Boston University, Boston, MA 02148, USA.

Abstract

Ultra-high chip power densities that are expected to surpass 1-2kW/cm² in future high-performance systems cannot be easily handled by conventional cooling methods. Various emerging cooling methods, such as liquid cooling via microchannels, thermoelectric coolers (TECs), two-phase vapor chambers, and hybrid cooling options have been designed to efficiently remove heat from high-performance processors. However, selecting the optimal cooling solution for a given chip and determining the optimal cooling parameters for that solution to achieve high efficiency are open problems. These problems are, in fact, computationally expensive because of the massive space of possible solutions. To address this design challenge, this article introduces a deep learning-based cooling design optimization flow that rapidly and accurately converges to the optimal cooling solution as well as the optimal cooling parameters for a given chip floorplan and its power profile.

Keywords: Applied computing; Computer architecture; Computer hardware; Computer science; Computer systems organization.