Advanced search
1 file | 777.01 KB

Benchmark synthesis for architecture and compiler exploration

Luk Van Ertvelde (UGent) and Lieven Eeckhout (UGent)
Author
Organization
Abstract
This paper presents a novel benchmark synthesis framework with three key features. First, it generates synthetic benchmarks in a high-level programming language (C in our case), in contrast to prior work in benchmark synthesis which generates synthetic benchmarks in assembly. Second, the synthetic benchmarks hide proprietary information from the original workloads they are built after. Hence, companies may want to distribute synthetic benchmark clones to third parties as proxies for their proprietary codes; third parties can then optimize the target system without having access to the original codes. Third, the synthetic benchmarks are shorter running than the original workloads they are modeled after, yet they are representative. In summary, the proposed framework generates small (thus quick to simulate) and representative benchmarks that can serve as proxies for other workloads without revealing proprietary information; and because the benchmarks are generated in a high-level programming language, they can be used to explore both the architecture and compiler spaces. The results obtained with our initial framework are promising. We demonstrate that we can generate synthetic proxy benchmarks for the MiBench benchmarks, and we show that they are representative across a range of machines with different instruction-set architectures, microarchitectures, and compilers and optimization levels, while being 30 times shorter running on average. We also verify using software plagiarism detection tools that the synthetic benchmark clones hide proprietary information from the original workloads.
Keywords
workload characterization, benchmark synthesis, computer architecture, compilers

Downloads

  • iiswc10.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 777.01 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Van Ertvelde, Luk, and Lieven Eeckhout. 2010. “Benchmark Synthesis for Architecture and Compiler Exploration.” In 2010 IEEE International Symposium on Workload Characterization (IISWC 2010), 106–116. Piscataway, NJ, USA: IEEE.
APA
Van Ertvelde, L., & Eeckhout, L. (2010). Benchmark synthesis for architecture and compiler exploration. 2010 IEEE International symposium on Workload Characterization (IISWC 2010) (pp. 106–116). Presented at the 2010 IEEE International symposium on Workload Characterization (IISWC 2010), Piscataway, NJ, USA: IEEE.
Vancouver
1.
Van Ertvelde L, Eeckhout L. Benchmark synthesis for architecture and compiler exploration. 2010 IEEE International symposium on Workload Characterization (IISWC 2010). Piscataway, NJ, USA: IEEE; 2010. p. 106–16.
MLA
Van Ertvelde, Luk, and Lieven Eeckhout. “Benchmark Synthesis for Architecture and Compiler Exploration.” 2010 IEEE International Symposium on Workload Characterization (IISWC 2010). Piscataway, NJ, USA: IEEE, 2010. 106–116. Print.
@inproceedings{1104942,
  abstract     = {This paper presents a novel benchmark synthesis framework with three key features. First, it generates synthetic benchmarks in a high-level programming language (C in our case), in contrast to prior work in benchmark synthesis which generates synthetic benchmarks in assembly. Second, the synthetic benchmarks hide proprietary information from the original workloads they are built after. Hence, companies may want to distribute synthetic benchmark clones to third parties as proxies for their proprietary codes; third parties can then optimize the target system without having access to the original codes. Third, the synthetic benchmarks are shorter running than the original workloads they are modeled after, yet they are representative. In summary, the proposed framework generates small (thus quick to simulate) and representative benchmarks that can serve as proxies for other workloads without revealing proprietary information; and because the benchmarks are generated in a high-level programming language, they can be used to explore both the architecture and compiler spaces. The results obtained with our initial framework are promising. We demonstrate that we can generate synthetic proxy benchmarks for the MiBench benchmarks, and we show that they are representative across a range of machines with different instruction-set architectures, microarchitectures, and compilers and optimization levels, while being 30 times shorter running on average. We also verify using software plagiarism detection tools that the synthetic benchmark clones hide proprietary information from the original workloads.},
  author       = {Van Ertvelde, Luk and Eeckhout, Lieven},
  booktitle    = {2010 IEEE International symposium on Workload Characterization (IISWC 2010)},
  isbn         = {9781424492978},
  keywords     = {workload characterization,benchmark synthesis,computer architecture,compilers},
  language     = {eng},
  location     = {Atlanta, GA, USA},
  pages        = {106--116},
  publisher    = {IEEE},
  title        = {Benchmark synthesis for architecture and compiler exploration},
  url          = {http://dx.doi.org/10.1109/IISWC.2010.5650208},
  year         = {2010},
}

Altmetric
View in Altmetric
Web of Science
Times cited: