Adaptive compute-phase prediction and thread prioritization to mitigate memory access latency
ACM International Conference Proceeding Series
Association for Computing Machinery
 - 
Item Usage Stats
MetadataShow full item record
The full potential of chip multiprocessors remains unex- ploited due to the thread oblivious memory access sched- ulers used in off-chip main memory controllers. This is especially pronounced in embedded systems due to limita- Tions in memory. We propose an adaptive compute-phase prediction and thread prioritization algorithm for memory access scheduling for embedded chip multiprocessors. The proposed algorithm eficiently categorize threads based on execution characteristics and provides fine-grained priori- Tization that allows to differentiate threads and prioritize their memory access requests accordingly. The threads in compute phase are prioritized among the threads in mem- ory phase. Furthermore, the threads in compute phase are prioritized among themselves based on the potential of mak- ing more progress in their execution. Compared to the prior works First-Ready First-Come First-Serve (FR-FCFS) and Compute-phase Prediction with Writeback-Refresh Overlap (CP-WO), the proposed algorithm reduces the execution time of the generated workloads up to 23.6% and 12.9%, respectively. Copyright 2014 ACM.
Memory access latency
Memory access scheduling
Permalink (Please cite this version)http://hdl.handle.net/11693/27152
Showing items related by title, author, creator and subject.
Ozturk, O.; Kandemir, M.; Irwin, M. J. (Institute of Electrical and Electronics Engineers, 2009-06)The memory system presents one of the critical challenges in embedded system design and optimization. This is mainly due to the ever-increasing code complexity of embedded applications and the exponential increase seen in ...
Onsori, S.; Asad, A.; Raahemifar, K.; Fathy, M. (Institute of Electrical and Electronics Engineers Inc., 2015)In this article, we present a convex optimization model to design a stacked hybrid memory system for 3D embedded chip-multiprocessors (eCMP). Our convex model optimizes numbers and placement of SRAM and STT-RAM memories ...
Oruc, F. B.; Cimen, F.; Rizk, A.; Ghaffari, M.; Nayfeh, A.; Okyay, A., K. (Institute of Electrical and Electronics Engineers, 2012-10-26)A thin-film ZnO-based single-transistor memory cell with a gate stack deposited in a single atomic layer deposition step is demonstrated. Thin-film ZnO is used as channel material and charge-trapping layer for the first ...