Abstract | ||
---|---|---|
With continuously shrinking technology, reliability issues such as Negative Bias Temperature Instability (NBTI) has resulted in considerable degradation of device performance, and eventually the short mean-time-to-failure (MTTF) of the whole multicore system. This article proposes a new workload balancing scheme based on device-level fractional NBTI model to balance the workload among active cores while relaxing stressed ones. Starting with NBTI-induced threshold voltage degradation, we define a concept of Capacity Rate (CR) as an indication of one core's ability to accept workload. Capacity rate captures core's performance variability in terms of delay and power metrics under the impact of NBTI aging. The proposed workload balancing framework employs the capacity rates as workload constraints, applies a Dynamic Zoning (DZ) algorithm to group cores into zones to process task flows, and then uses Dynamic Task Scheduling (DTS) to allocate tasks in each zone with balanced workload and minimum communication cost. Experimental results on a 64-core system show that by allowing a small part of the cores to relax over a short time period, the proposed methodology improves multicore system yield (percentage of core failures) by 20%, while extending MTTF by 30% with insignificant degradation in performance (less than 3%). |
Year | DOI | Venue |
---|---|---|
2014 | 10.1145/2539124 | JETC |
Keywords | Field | DocType |
64-core system show,balanced workload,capacity rate,capacity rate captures core,workload assignment,nbti aging,new workload,workload constraint,active core,nbti degradation,multicore system,proposed workload,nbti-induced threshold voltage degradation | Mean time between failures,Scheduling (computing),Workload,Computer science,Degradation (geology),Real-time computing,Negative-bias temperature instability,Multi-core processor,Multicore systems | Journal |
Volume | Issue | ISSN |
10 | 1 | 1550-4832 |
Citations | PageRank | References |
5 | 0.44 | 24 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jin Sun | 1 | 40 | 5.97 |
Roman Lysecky | 2 | 605 | 60.43 |
Karthik Shankar | 3 | 54 | 9.46 |
Avinash Kodi | 4 | 74 | 5.76 |
Ahmed Louri | 5 | 398 | 47.97 |
Janet Roveda | 6 | 14 | 5.96 |