Advertisement

SESH Framework: A Space Exploration Framework for GPU Application and Hardware Codesign

  • Joo Hwan LeeEmail author
  • Jiayuan Meng
  • Hyesoon Kim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8551)

Abstract

Graphics processing units (GPUs) have become increasingly popular accelerators in supercomputers, and this trend is likely to continue. With its disruptive architecture and a variety of optimization options, it is often desirable to understand the dynamics between potential application transformations and potential hardware features when designing future GPUs for scientific workloads. However, current codesign efforts have been limited to manual investigation of benchmarks on microarchitecture simulators, which is labor-intensive and time-consuming. As a result, system designers can explore only a small portion of the design space. In this paper, we propose SESH framework, a model-driven codesign framework for GPU, that is able to automatically search the design space by simultaneously exploring prospective application and hardware implementations and evaluate potential software-hardware interactions.

Keywords

SESH framework SW/HW co-design GPGPU Space exploration 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Meng, J., Wu, X., Morozov, V.A., Vishwanath, V., Kumaran, K., Taylor, V., Lee, C.-W.: SKOPE: A Framework for Modeling and Exploring Workload Behavior. Argonne National Laboratory, Tech. Rep. (2012)Google Scholar
  2. 2.
    Meng, J., Morozov, V., Kumaran, K., Vishwanath, V., Uram, T.: GROPHECY: GPU Performance Projection from CPU Code Skeletons. In: SC 2011 (2011)Google Scholar
  3. 3.
    Sim, J.W., Dasgupta, A., Kim, H., Vuduc, R.: GPUPerf: A Performance Analysis Framework for Identifying Performance Benefits in GPGPU Applications. In: PPoPP 2012 (2012)Google Scholar
  4. 4.
    Lim, J., Lakshminarayana, N., Kim, H., Song, W., Yalamanchili, S., Sung, W.: Power Modeling for GPU Architecture using McPAT. Georgia Institute of Technology. Tech. Rep. (2013)Google Scholar
  5. 5.
    Li, S., Ahn, J.H., Strong, R.D., Brockman, J.B., Tullsen, D.M., Jouppi, N.P.: McPAT: an integrated power, area, and timing modeling framework for multicore and manycore architectures. In: MICRO 42Google Scholar
  6. 6.
    Song, W.J., Cho, M., Yalamanchili, S., Mukhopadhyay, S., Rodrigues, A.F.: Energy introspector: Simulation infrastructure for power, temperature, and reliability modeling in manycore processors. In: SRC TECHCHON 2011 (2011)Google Scholar
  7. 7.
  8. 8.
    Hong, S., Kim, H.: IPP: An Integrated GPU Power and Performance Model that Predicts Optimal Number of Active Cores to Save Energy at Static Time. In: ISCA 2010 (2010)Google Scholar
  9. 9.
    Linderman, M.D., Collins, J.D., Wang, H., Meng, T.H.: Merge: a programming model for heterogeneous multi-core systems. In: ASPLOS XIIIGoogle Scholar
  10. 10.
    Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J.W., Skadron, K.: A performance study of general-purpose applications on graphics processors using CUDA. Journal of Parallel and Distributed Computing (2008)Google Scholar
  11. 11.
    Pieper, S.C., Wiringa, R.B.: Quantum Monte Carlo calculations of light nuclei. Annu. Rev. Nucl. Part. Sci. 51, 53 (2001)CrossRefGoogle Scholar
  12. 12.
    Pieper, S.C., Varga, K., Wiringa, R.B.: Quantum Monte Carlo calculations of A=9,10 nuclei. Phys. Rev. C 66, 044310-1:14 (2002)Google Scholar
  13. 13.
    NVIDIA Corporation: GeForce GTX 280 specifications (2008), http://www.nvidia.com/object/product_geforce_gtx_280_us.html
  14. 14.
    NVIDIA, Fermi: Nvidia’s next generation cuda compute architecture, http://www.nvidia.com/fermi
  15. 15.
    NVIDIA’s next generation CUDA compute architecture: Kepler GK110. NVIDIA Corporation (2012)Google Scholar
  16. 16.
    Jablin, T.B., Prabhu, P., Jablin, J.A., Johnson, N.P., Beard, S.R., August, D.I.: Automatic CPU-GPU communication management and optimization. In: PLDI 2011 (2011)Google Scholar
  17. 17.
    Jablin, T.B., Jablin, J.A., Prabhu, P., Liu, F., August, D.I.: Dynamically managed data for cpu-gpu architectures. In: CGO 2012 (2012)Google Scholar
  18. 18.
    Spafford, K., Vetter, J.: Aspen: A domain specific language for performance modeling. In: SC 2012 (2012)Google Scholar
  19. 19.
    Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Communications of the ACM - A Direct Path to Dependable Software (2009)Google Scholar
  20. 20.
    Valiant, L.G.: A bridging model for parallel computation. Commun. ACM (1990)Google Scholar
  21. 21.
    Karp, R.M., Ramachandran, V.: A survey of parallel algorithms for shared-memory machines. EECS Department, University of California, Berkeley, Tech. Rep. (1988)Google Scholar
  22. 22.
    Valluri, M., John, L.: Is Compiling for Performance == Compiling for Power. In: INTERACT-5Google Scholar
  23. 23.
    Brandolese, C., Fornaciari, W., Salice, F., Sciuto, D.: The Impact of Source Code Transformations on Software Power and Energy Consumption. Journal of Circuits, Systems, and Computers (2002)Google Scholar
  24. 24.
    Joseph, R., Martonosi, M.: Run-time power estimation in high performance microprocessors. In: ISLPED 2001 (2001)Google Scholar
  25. 25.
    Bellosa, F., Kellner, S., Waitz, M., Weissel, A.: Event-driven energy accounting for dynamic thermal management. In: COLP 2003 (2003)Google Scholar
  26. 26.
    Wu, W., Jin, L., Yang, J., Liu, P., Tan, S.-D.: A systematic method for functional unit power estimation in microprocessors. In: DAC 2006 (2006)Google Scholar
  27. 27.
    Peddersen, J., Parameswaran, S.: CLIPPER: Counter-based Low Impact Processor Power Estimation at Run-time. In: ASP-DAC 2007 (2007)Google Scholar
  28. 28.
    Powell, M., Biswas, A., Emer, J., Mukherjee, S., Sheikh, B., Yardi, S.: CAMP: A technique to estimate per-structure power at run-time using a few simple parameters. In: HPCA 2009 (2009)Google Scholar
  29. 29.
    Jacobson, H., Buyuktosunoglu, A., Bose, P., Acar, E., Eickemeyer, R.: Abstraction and microarchitecture scaling in early-stage power modeling. In: HPCA 2011 (2011)Google Scholar
  30. 30.
    Czechowski, K., Vuduc, R.: A theoretical framework for algorithm-architecture co-design. In: IPDPS 2013 (2013)Google Scholar
  31. 31.
    Wang, G.: Power analysis and optimizations for GPU architecture using a power simulator. In: ICACTE 2010 (2010)Google Scholar
  32. 32.
    Ramani, K., Ibrahim, A., Shimizu, D.: PowerRed: A Flexible Power Modeling Framework for Power Efficiency Exploration in GPUs. In: GPGPU 2007 (2007)Google Scholar
  33. 33.
    Ma, X., Dong, M., Zhong, L., Deng, Z.: Statistical Power Consumption Analysis and Modeling for GPU-based Computing. In: HotPower 2009 (2009)Google Scholar
  34. 34.
    Nagasaka, H., Maruyama, N., Nukada, A., Endo, T., Matsuoka, S.: Statistical power modeling of GPU kernels using performance counters. In: IGCC 2010 (2010)Google Scholar
  35. 35.
    Chen, J., Li, B., Zhang, Y., Peng, L., kwon Peir, J.: Tree structured analysis on gpu power study. In: ICCD 2011 (2011)Google Scholar
  36. 36.
    Zhang, Y., Hu, Y., Li, B., Peng, L.: Performance and Power Analysis of ATI GPU: A Statistical Approach. In: NAS 2011 (2011)Google Scholar
  37. 37.
    Wu, W., Lee, B.C.: Inferred Models for Dynamic and Sparse Hardware-Software Spaces. In: MICRO 2012 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.School of Computer ScienceGeorgia Institute of TechnologyAtlantaUSA
  2. 2.Argonne National Laboratory, Leadership Computing FacilityArgonneUSA

Personalised recommendations