Combating Aging with the Colt Duty Cycle Equalizer
MICRO '43 Proceedings of the 2010 43rd Annual IEEE/ACM International Symposium on Microarchitecture
Energy-optimal caches with guaranteed lifetime
Proceedings of the 2012 ACM/IEEE international symposium on Low power electronics and design
Combating NBTI-induced aging in data caches
Proceedings of the 23rd ACM international conference on Great lakes symposium on VLSI
Energy-optimal SRAM supply voltage scheduling under lifetime and error constraints
Proceedings of the 50th Annual Design Automation Conference
Application-specific memory partitioning for joint energy and lifetime optimization
DATE '12 Proceedings of the Conference on Design, Automation and Test in Europe
Hi-index | 0.00 |
Negative Bias Temperature Instability (NBTI) is an important lifetime reliability problem in microprocessors. SRAM-based structures within the processor are especially susceptible to NBTI since one of the PMOS devices in the memory cell always has an input of ‘0’. Previously proposed recovery techniques for SRAM cells aim to balance the degradation of the two PMOS devices by attempting to keep their inputs at a logic ‘0’ exactly 50% of the time. However, one of the devices is always in the negative bias condition at any given time. In this paper, we propose a technique called Recovery Boosting that allows both PMOS devices in the memory cell to be put into the recovery mode by slightly modifying the design of conventional SRAM cells. We present the circuit-level design of an issue queue that uses such cells and perform SPICE-level simulations to verify its functionality and quantify area and power consumption. We then conduct an architecture-level evaluation of the performance and reliability of using an area-neutral design of such an issue queue using the M5 simulator and the SPEC CPU2000 benchmark suite. We show that recovery boosting provides a 56% improvement in the static noise margin for the issue queue while having very little impact on power consumption and a negligible loss in performance.