Blue Gene/Q: by co-design

Special Issue Paper

Abstract

Blue Gene/Q represents the third generation in the IBM Blue Gene line of supercomputer systems. Architecturally, BG/Q installations can scale to over 100 PetaFLOPS. Blue Gene/Q follows the same philosophy as the earlier Blue Gene/L and Blue Gene/P systems, namely to build a massively parallel and highly reliable High Performance Computing (HPC) system out of power-efficient processor chips. Such power-efficient chips, in turn, allow dense packaging, which consequently results in power efficient, cost efficient, and floor-space efficient systems. A focus on reliability in the design of each component contributes to the ability to run a single application across even the largest configurations.

Because of the tight interaction between the hardware, system software, and application teams, the machine was truly co-designed. The intended characteristics of architecture were presented early to the system software and application teams, and those teams requested specific features that were then incorporated into the hardware. The contributions of this paper are a description of the overall system and packaging of Blue Gene/Q, a description of the core system software, and a detailed description of the software’s needs that drove the co-design process, in turn affecting the hardware.

Keywords

Hardware-software co-design SIMD processors Super (very large) computers Large and medium (“mainframe”) computers Microprocessors and microcomputers Multicore/single-chip multiprocessors Multiple data stream architectures (multiprocessors) Multithreaded processors Parallel processors Speculative multithreading Support for multithreaded execution Hardware transactional memory Scalable atomic operations 

References

  1. 1.
    Chen D, Eisley NA, Heidelberger P, Senger RM, Sugawara Y, Kumar S, Salapura V, Satterfield DL, Stenmacher-Burow B, Parker JJ (2011) The IBM Blue Gene/Q interconnection network and message unit. In: 2011 international conference for high performance computing, networking, storage and analysis (SC2011). doi:10.1145/2063384.2063419 Google Scholar
  2. 2.
    Chen D, Eisley NA, Heidelberger P, Senger RM, Sugawara Y, Kumar S, Salapura V, Satterfield DL, Stenmacher-Burow B, Parker JJ (2012) The IBM Blue Gene/Q interconnection fabric. IEEE Micro 32(1):32–43. doi:10.1109/MM.2011.96 MATHCrossRefGoogle Scholar
  3. 3.
    Green 500 list (2010, 2011) www.green500.org
  4. 4.
    Gara A, Blumrich MA, Chen D, Chiu GL, Coteus P, Giampapa ME, Haring RA, Heidelberger P, Hoenicke D, Kopcsay GV, Liebsch TA, Ohmacht M, Steinmacher-Burow BD, Takken T, Vranas P (2005) Overview of the Blue Gene/L system architecture. IBM J Res Dev 49(2/3):195–212 CrossRefGoogle Scholar
  5. 5.
    Giampapa M, Gooding T, Inglett T, Wisniewski RW (2010) Experiences with a lightweight supercomputer kernel: lessons learned from Blue Gene’s CNK. In: 2010 international conference for high performance computing, networking, storage and analysis (SC2010), pp 1–10. doi:10.1109/SC.2010.22 CrossRefGoogle Scholar
  6. 6.
    Haring RA, Ohmacht M, Fox TW, Gschwind MK, Satterfield DL, Sugavanam K, Coteus PW, Heidelberger P, Blumrich MA, Wisniewski RW, Gara A, Chiu GL, Boyle PA, Chist NH, Kim C (2012) The IBM Blue Gene/Q Compute chip. IEEE Micro 32(2):48–60. doi:10.1109/MM.2011.108 CrossRefGoogle Scholar
  7. 7.
    IBM Blue Gene Team (2008) Overview of the Blue Gene/P project. IBM J Res Dev 52(1/2):199–220 Google Scholar
  8. 8.
    Moreira JE, Almasi G, Archer C, Bellofatto R, Bergner P, Brunheroto JR, Brutman M, Castanos JG, Crumley PG, Gupta M, Inglett T, Lieber D, Limpert D, McCarthy P, Megerian M, Mendell M, Mundy M, Reed D, Sahoo RK, Sanomiya A, Shok R, Smith B, Stewart GG (2005) Blue Gene/L programming and operating environment. IBM J Res Dev 49(2/3):367–376 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  1. 1.IBM Thomas J Watson Research CenterYorktown HeightsUSA
  2. 2.IBM Systems and Technology GroupRochesterUSA

Personalised recommendations