Abstract
Full-system execution-driven simulators are essential tools in the development of supercomputers, such as IBM Blue Gene/Q. They enable software teams to develop and run code before the real system becomes available, typically a few years after the beginning of the project. Functional simulators support early software development. The addition of timing information allows for early performance assessment of applications to provide feedback on the hardware and system design. The techniques employed to implement a timing model for Blue Gene/Q, built on top of the functional model, are presented. Our simulator runs several orders of magnitude faster than traditional cycle-accurate simulators. The experiments with micro-kernels from the Sequoia Benchmark Suite demonstrate that our simulator provides the timing accuracy between 3 to 17% of the actual measurement from the real Blue Gene/Q machine. We also present some architecture design exploration and its performance implications.
Chapter PDF
References
Asaad, S., Tierno, J., Bellofatto, R., Brezzo, B., Haymes, C., Kapur, M., Parker, B., Roewer, T., Saha, P., Takken, T.: A cycle-accurate, cycle-reproducible multi-FPGA system for accelerating multi-core processor simulation. In: Proceedings of the ACM/SIGDA International Symposium on Field Programmable Gate Arrays, pp. 153–161. ACM Press, New York (2012)
Bachega, L., Brunheroto, J., DeRose, L., Mindlin, P., Moreira, J.: The BlueGene/L pseudo cycle-accurate simulator. In: Proceedings of the 2004 IEEE International Symposium on Performance Analysis of Systems and Software, pp. 36–44. IEEE Computer Society, Washington, DC (2004)
Bohrer, P., Simpson, R., Speight, E., Sudeep, K., Van Hensbergen, E., Zhang, L., Peterson, J., Elnozahy, M., Rajamony, R., Gheith, A., Rockhold, R., Lefurgy, C., Shafi, H., Nakra, T.: Mambo - A Full System Simulator for the PowerPC Architecture. ACM SIGMETRICS Perform. Eval. Rev. 31(4), 8–12 (2004)
Chen, D., Eisley, N.A., Heidelberger, P., Senger, R.M., Sugawara, Y., Kumar, S., Salapura, V., Satterfield, D.L., Steinmacher-Burow, B., Parker, J.J.: The IBM Blue Gene/Q interconnection network and message unit. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1–10. ACM Press, New York (2011)
Dongarra, J.J., Luszczek, P., Petitet, A.: The LINPACK Benchmark: past, present and future. Concurrency and Computation: Practice and Experience 15(9), 803–820 (2003)
Fox, T., Gschwind, M., Moreno, J.: QPX Architecture: Quad Processing eXtension to the Power ISA. Tech. rep., IBM Research, Yorktown Heights, NY (2012)
Giampapa, M., Gooding, T., Inglett, T., Wisniewski, R.W.: Experiences with a Lightweight Supercomputer Kernel: Lessons Learned from Blue Gene’s CNK. In: Proceedings of the 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1–10. IEEE Computer Society, Washington, DC (2010)
Haring, R.A., Ohmacht, M., Fox, T.W., Gschwind, M.K., Sugavanam, K., Coteus, P.W., Heidelberger, P., Blumrich, M.A., Wisniewski, R.W., Gara, A., Chiu, G.L.T., Boyle, P.A., Christ, N.H., Kim, C.: The IBM Blue Gene/Q Compute Chip. IEEE Micro 32(2), 48–60 (2012)
Lawrence Livermore National Laboratories: ASC Sequoia Benchmark Codes, https://asc.llnl.gov/sequoia/benchmarks/
The Blue Gene Team: Blue Gene/Q: by co-design. Computer Science - Research and Development (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gallo, D.S., Brunheroto, J.R., Ryu, K.D. (2013). Fast Full-System Execution-Driven Performance Simulator for Blue Gene/Q. In: Wolf, F., Mohr, B., an Mey, D. (eds) Euro-Par 2013 Parallel Processing. Euro-Par 2013. Lecture Notes in Computer Science, vol 8097. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40047-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-40047-6_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40046-9
Online ISBN: 978-3-642-40047-6
eBook Packages: Computer ScienceComputer Science (R0)