Stargazer: Automated regression-based GPU design space exploration

Wenhao Jia, Kelly A. Shaw, Margaret Rose Martonosi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

57 Scopus citations

Abstract

Graphics processing units (GPUs) are of increasing interest because they offer massive parallelism for high-throughput computing. While GPUs promise high peak performance, their challenge is a less-familiar programming model with more complex and irregular performance trade-offs than traditional CPUs or CMPs. In particular, modest changes in software or hardware characteristics can lead to large or unpredictable changes in performance. In response to these challenges, our work proposes, evaluates, and offers usage examples of Stargazer 1, an automated GPU performance exploration framework based on stepwise regression modeling. Stargazer sparsely and randomly samples parameter values from a full GPU design space and simulates these designs. Then, our automated stepwise algorithm uses these sampled simulations to build a performance estimator that identifies the most significant architectural parameters and their interactions. The result is an application-specific performance model which can accurately predict program runtime for any point in the design space. Because very few initial performance samples are required relative to the extremely large design space, our method can drastically reduce simulation time in GPU studies. For example, we used Stargazer to explore a design space of nearly 1 million possibilities by sampling only 300 designs. For 11 GPU applications, we were able to estimate their runtime with less than 1.1% average error. In addition, we demonstrate several usage scenarios of Stargazer.

Original languageEnglish (US)
Title of host publicationISPASS 2012 - IEEE International Symposium on Performance Analysis of Systems and Software
Pages2-13
Number of pages12
DOIs
StatePublished - May 24 2012
Event2012 IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2012 - New Brunswick, NJ, United States
Duration: Apr 1 2012Apr 3 2012

Publication series

NameISPASS 2012 - IEEE International Symposium on Performance Analysis of Systems and Software

Other

Other2012 IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2012
CountryUnited States
CityNew Brunswick, NJ
Period4/1/124/3/12

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint Dive into the research topics of 'Stargazer: Automated regression-based GPU design space exploration'. Together they form a unique fingerprint.

  • Cite this

    Jia, W., Shaw, K. A., & Martonosi, M. R. (2012). Stargazer: Automated regression-based GPU design space exploration. In ISPASS 2012 - IEEE International Symposium on Performance Analysis of Systems and Software (pp. 2-13). [6189201] (ISPASS 2012 - IEEE International Symposium on Performance Analysis of Systems and Software). https://doi.org/10.1109/ISPASS.2012.6189201