Name
Title | ||
|---|---|---|
VarCatcher: A Framework for Tackling Performance Variability of Parallel Workloads on Multi-Core. |
Abstract | ||
|---|---|---|
The non-deterministic nature of multi-threaded workloads running on multi-core platforms often leads to notable performance variability from run to run. Such variability makes experimental results prone to misinterpretations or misguided claims. To deal with such variability, statistical inference methods are usually used to summarize the experimental results with certain confidence levels by running the experiments or measurements a large number of times. However, such statistical results are often too vague or too simplistic. They are not sufficient to help users understand the causes of such variability, and allow more in-depth analysis on the results or reproduce the results for validation during design space exploration. To allow better analyzability and reproducibility, we propose a framework to tackle such variability, called VarCatcher. The key to VarCatcher is to characterize a parallel execution using Parallel Characteristics Vector (PCV). A clustering-based approach is then used to group runs with similar execution characteristics that can later be used to analyze results in-depth, to customize different evaluation strategies, reproduce the result for variability, to determine the impact of features, or to assist performance diagnosis. We have built a prototype of VarCatcher that includes a user-level toolset for runtime monitoring and measurements using the Intel Processor Trace feature on commodity Intel processors as well as an architecture extension with very low runtime overheads (around 3 and 0.01 percent accordingly). Several case studies confirm that VarCatcher enables several appealing features such as in-depth result analysis, customized evaluation strategies, and reproducibility. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/TPDS.2016.2613524 | IEEE Trans. Parallel Distrib. Syst. |
Keywords | Field | DocType |
Space exploration,Runtime,Electronic mail,Visualization,Optical wavelength conversion,Benchmark testing | Computer science,Visualization,Real-time computing,Space exploration,Statistical inference,Cluster analysis,Design space exploration,Multi-core processor,Benchmark (computing),Distributed computing,Overhead (business) | Journal |
Volume | Issue | ISSN |
28 | 4 | 1045-9219 |
Citations | PageRank | References |
3 | 0.41 | 24 |
Authors | ||
8 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Weihua Zhang | 1 | 174 | 30.34 |
| ji xiaofeng | 2 | 9 | 2.07 |
| Bo Song | 3 | 13 | 7.21 |
| Shiqiang Yu | 4 | 3 | 0.41 |
| Haibo Chen | 5 | 5 | 1.48 |
| Tao Li | 6 | 761 | 47.52 |
| P.-C. Yew | 7 | 199 | 25.56 |
| Wenyun Zhao | 8 | 526 | 54.45 |