Scientific Papers
Thermal Balancing Policy For Streaming Computing On Multiprocessor Architectures
As feature sizes decrease, power dissipation and heat generation density exponentially increase. Thus, temperature gradients in Multiprocessor Systems on Chip (MPSoCs) can seriously impact system performance and reliability. Thermal balancing policies based on task migration have been proposed to modulate power distribution between processing cores to achieve temperature flattening. However, in the context of MPSoC for multimedia streaming computing, where timeliness is critical, the impact of migration on quality of service must be carefully analyzed. In this paper we present the design and implementation of a lightweight thermal balancing policy that reduces on-chip temperature gradients via task migration. This policy exploits run-time temperature and load information to balance the chip temperature. Moreover, we assess the effectiveness of the proposed policy for streaming computing architectures using a cycle-accurate thermal-aware emulation infrastructure. Our results using a real-life software defined radio multitask benchmark show that our policy achieves thermal balancing while keeping migration costs bounded.
This paper is not under copyleft and it is not available for free. You can get it here.
Published on Tue 05 May 2009, at 7:53 p.m.
Design Of Low Power Dissipation Network On Chip Architectures
This paper summarizes work over one year on the Network on Chip design, low power dissipation and design flow methodologies. The results are mainly related to a network on chip designed at RTL level by our research group (University of Cagliari, Bologna, Stanford and EPFL).
Published on Tue 05 May 2009, at 7:51 p.m.