Selecting Optimal Parallel Microchannel Configuration(s) for Active Hot Spot Mitigation of Multicore Microprocessors in Real Time

Abstract

Design of effective micro cooling systems to address the challenges of ever increasing heat flux from microdevices requires deep examination of real time problems and has been tackled in depth. The most common (and apparently misleading) assumption while designing micro cooling systems is that the heat flux generated by the device is uniform, but the reality is far from this.Detailed simulations have been performed by considering non uniform heat load employing the configurations U, I, Z for parallel microchannel systems with water and nanofluids as the coolants. An Intel® Core™ i7-4770 3.40GHz quad core processor has been mimicked using heat load data retrieved from a real microprocessor with non-uniform core activity. The study clearly demonstrates that there is a non-uniform thermal load induced temperature maldistribution along with the already existent flow maldistribution induced temperature maldistribution. The suitable configuration(s) for maximum possible overall heat removal for a hot zone while maximizing the uniformity of cooling have been tabulated. An Eulerian-Lagrangian model of the nanofluids show that such 'smart' coolants not only reduce the hot spot core temperature, but also the hot spot core region and thermal slip mechanisms of Brownian diffusion and thermophoresis are at the crux of this. The present work conclusively shows that high flow maldistribution leads to high thermal maldistribution, as the common prevalent notion, is no longer valid and existing maldistribution can be effectively utilized to tackle specific hot spot location, making the present study important to the field.

Efficacy of parallel microchannel configurations towards hot-spot thermal management of 8-core microprocessors

“…Since the heat load emitted by the processor is non-uniform, finding the best suitable flow configuration for a given case can be done by quantifying the thermal performance. The Figure of Merit (FoM) 34 is used to perform the quantitative analysis of all the configurations to choose best configuration for a given situation. The FoM represented as, FoM = T max T max − T min and it helps in assessing the thermal performance of PMCHS with respect to cooling calibre as well as uniformity of cooling.…”

“…32,33 . Maganti et al 34 has mimicked the non-uniform thermal load data with respective active core locations taken from an Intel ® Core™ i7-4770 3.40 GHz quad-core processor. In the simulations, the non-uniform thermal load conditions were applied, and different flow configurations (U, I and Z, see Figure 1) of PMCHS were studied.…”

Tailoring the fluid flow distribution in a parallel mini-channel heat sink under multiple-peak heat flux

“…But in reality, the heat flux profile generated by the electronic devices is not uniform, instead, it presents multiple peaks [26,27]. This multiple-peak heat flux could either be due to the non-uniform heat generation of a single chip (e.g., multi-core microprocessors) [28], or due to the existence of multiple chips on the module (MCM) [29]. Under these circumstances, the intentional flow non-uniform distribution may be a better option to be adapted to decrease the local maximum temperature, as pointed out by Kumar and Singh [13].…”

Design and Optimization of a Composite Heat Spreader to Improve the Thermal Management of a Three-Dimensional Integrated Circuit

“…It should be noted that thermal management is vital in the design of 2D and 3D integrated circuits (ICs) technology since the thermal conductivity of dielectric materials is low, which results in thermal hotspots throughout the component. Most of the research to overcome this issue has been done by devising innovative designs for the heat sinks [16][17][18][19][20][21][22]. For instance, conductive heat tree structures at micro-and nanoscales have been generated for cooling electronic disk-shaped pieces in Daneshi et al [23].…”