000 04367nam a22005535i 4500
001 vtls000483447
003 RU-ToGU
005 20210922065801.0
007 cr nn 008mamaa
008 140715s2013 xxk| s |||| 0|eng d
020 _a9781447144922
_9978-1-4471-4492-2
024 7 _a10.1007/978-1-4471-4492-2
_2doi
035 _ato000483447
040 _aSpringer
_cSpringer
_dRU-ToGU
050 4 _aTK5105.5-5105.9
072 7 _aUKN
_2bicssc
072 7 _aCOM075000
_2bisacsh
082 0 4 _a004.6
_223
100 1 _aLaros III, James H.
_eauthor.
_9414514
245 1 0 _aEnergy-Efficient High Performance Computing
_h[electronic resource] :
_bMeasurement and Tuning /
_cby James H. Laros III, Kevin Pedretti, Suzanne M. Kelly, Wei Shu, Kurt Ferreira, John Van Dyke, Courtenay Vaughan.
260 _aLondon :
_bSpringer London :
_bImprint: Springer,
_c2013.
300 _aXIV, 67 p. 19 illus., 8 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
490 1 _aSpringerBriefs in Computer Science,
_x2191-5768
505 0 _aIntroduction -- Platforms -- Measuring Power -- Applications -- Reducing Power During Idle Cycles -- Tuning CPU Power During Application Run-Time -- Network Bandwidth Tuning During Application Run-Time -- Energy Delay Product -- Conclusions.
520 _aRecognition of the importance of power and energy in the field of high performance computing (HPC) has never been greater. Research has been conducted in a number of areas related to power and energy, but little existing research has focused on large-scale HPC. Part of the reason is the lack of measurement capability currently available on small or large platforms. Typically, research is conducted using coarse methods of measurement such as inserting a power meter between the power source and the platform, or fine grained measurements using custom instrumented boards (with obvious limitations in scale). To analyze real scientific computing applications at large scale, an in situ measurement capability is necessary that scales to the size of the platform. In response to this challenge, the unique power measurement capabilities of the Cray XT architecture were exploited to gain an understanding of power and energy use and the effects of tuning both CPU and network bandwidth. Modifications were made at the operating system level to deterministically halt cores when idle. Additionally, capabilities were added to alter operating P-state. At the application level, an understanding of the power requirements of a range of important DOE/NNSA production scientific computing applications running at large scale (thousands of nodes) is gained by simultaneously collecting current and voltage measurements on the hosting nodes. The effects of both CPU and network bandwidth tuning are examined and energy savings opportunities of up to 39% with little or no impact on run-time performance is demonstrated. Capturing scale effects was key. This research provides strong evidence that next generation large-scale platforms should not only approach CPU frequency scaling differently, as we will demonstrate, but could also benefit from the capability to tune other platform components, such as the network, to achieve more energy efficient performance.
650 0 _aComputer Science.
_9155490
650 0 _aOperating systems (Computers).
_9303025
650 0 _aComputer Communication Networks.
_9566243
650 1 4 _aComputer Science.
_9155490
650 2 4 _aComputer Communication Networks.
_9566243
650 2 4 _aPerformance and Reliability.
_9566342
650 2 4 _aOperating Systems.
_9303029
700 1 _aPedretti, Kevin.
_eauthor.
_9414516
700 1 _aKelly, Suzanne M.
_eauthor.
_9414517
700 1 _aShu, Wei.
_eauthor.
_9414518
700 1 _aFerreira, Kurt.
_eauthor.
_9414519
700 1 _aVan Dyke, John.
_eauthor.
_9414520
700 1 _aVaughan, Courtenay.
_eauthor.
_9414521
710 2 _aSpringerLink (Online service)
_9143950
773 0 _tSpringer eBooks
830 0 _aSpringerBriefs in Computer Science,
_9412137
856 4 0 _uhttp://dx.doi.org/10.1007/978-1-4471-4492-2
912 _aZDB-2-SCS
999 _c356764