Differences
This shows you the differences between two versions of the page.
seminars:seminar_3_29_17 [2017/09/21 02:02] |
seminars:seminar_3_29_17 [2017/09/21 02:02] (current) |
||
---|---|---|---|
Line 1: | Line 1: | ||
+ | ====== Power- and Performance-constrained Thread Mapping and DVFS on Heterogeneous Multi-Core Systems ====== | ||
+ | Wednesday March 29, 2017\\ | ||
+ | Location: CIC Panther Hollow Room\\ | ||
+ | Time: 4:30PM\\ | ||
+ | |||
+ | **Dimitrios Stamoulis (CMU)**\\ | ||
+ | |||
+ | =====Abstract===== | ||
+ | Modern many-core systems must cope with a wide range of heterogeneity | ||
+ | due to either the numerous processing components that are heterogeneous | ||
+ | by design, or due to the different performance requirements of multi-application, | ||
+ | multi-threaded workloads. This raises an important question for chip multiprocessor | ||
+ | designers: Can we guarantee per-application performance constraints under | ||
+ | workload and core heterogeneity, while staying within the power budget? | ||
+ | |||
+ | In this talk, I will present our work on an approach for simultaneous thread mapping | ||
+ | and Dynamic Voltage Frequency Scaling (DVFS) on heterogeneous multi-core systems | ||
+ | to maximize overall performance, while satisfying the power budget and per-application | ||
+ | performance requirements. We formulate this optimization problem as a constrained 0-1 | ||
+ | integer linear program (ILP) and we propose a heuristic-based algorithm for efficiently | ||
+ | solving it. Compared with an optimal solver, our method produces results less than 1.5% | ||
+ | away from optimum on average, with four orders of magnitude improvement in runtime. | ||
+ | We also show that our method always meets per-application performance requirements, | ||
+ | while agnostic approaches could result in performance bound violations up to 48.1%. | ||
+ | |||
+ | |||
+ | =====Bio===== | ||
+ | Dimitrios Stamoulis is a second year PhD student advised by Professor Diana | ||
+ | Marculescu. His research is focused on performance optimization for heterogeneous | ||
+ | and dark silicon multi-core systems under power and variability constraints. | ||
+ | |||
+ | |||
+ | \\ | ||
+ | \\ | ||
+ | **[[seminars| Back to the seminar page]]** |