LEADER 03954nam 2200589 a 450 001 9910437565103321 005 20200520144314.0 010 $a1-283-62229-7 010 $a9786613934741 010 $a1-4471-4492-9 024 7 $a10.1007/978-1-4471-4492-2 035 $a(CKB)2670000000246071 035 $a(EBL)1030425 035 $a(OCoLC)810077656 035 $a(SSID)ssj0000737228 035 $a(PQKBManifestationID)11439992 035 $a(PQKBTitleCode)TC0000737228 035 $a(PQKBWorkID)10782579 035 $a(PQKB)11237611 035 $a(DE-He213)978-1-4471-4492-2 035 $a(MiAaPQ)EBC1030425 035 $a(PPN)168293587 035 $a(EXLCZ)992670000000246071 100 $a20120723d2013 uy 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 00$aEnergy-efficient high performance computing $emeasurement and tuning /$fJames H. Laros III ... [et al.] 205 $a1st ed. 2013. 210 $aNew York $cSpringer$d2013 215 $a1 online resource (72 p.) 225 0$aSpringerBriefs in computer science,$x2191-5768 300 $aDescription based upon print version of record. 311 $a1-4471-4491-0 320 $aIncludes bibliographical references and index. 327 $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. 330 $aRecognition of the importance of power and energy in the field of high performance computing (HPC) has never been greater. Research has been conducted in a number of areas related to power and energy, but little existing research has focused on large-scale HPC. Part of the reason is the lack of measurement capability currently available on small or large platforms. Typically, research is conducted using coarse methods of measurement such as inserting a power meter between the power source and the platform, or fine grained measurements using custom instrumented boards (with obvious limitations in scale). To analyze real scientific computing applications at large scale, an in situ measurement capability is necessary that scales to the size of the platform. In response to this challenge, the unique power measurement capabilities of the Cray XT architecture were exploited to gain an understanding of power and energy use and the effects of tuning both CPU and network bandwidth. Modifications were made at the operating system level to deterministically halt cores when idle. Additionally, capabilities were added to alter operating P-state. At the application level, an understanding of the power requirements of a range of important DOE/NNSA production scientific computing applications running at large scale (thousands of nodes) is gained by simultaneously collecting current and voltage measurements on the hosting nodes. The effects of both CPU and network bandwidth tuning are examined and energy savings opportunities of up to 39% with little or no impact on run-time performance is demonstrated. Capturing scale effects was key. This research provides strong evidence that next generation large-scale platforms should not only approach CPU frequency scaling differently, as we will demonstrate, but could also benefit from the capability to tune other platform components, such as the network, to achieve more energy efficient performance. 410 0$aSpringerBriefs in Computer Science,$x2191-5768 606 $aHigh performance computing 615 0$aHigh performance computing. 676 $a004.3 676 $a004/.3 701 $aLaros$b James H$01752586 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910437565103321 996 $aEnergy-efficient high performance computing$94187913 997 $aUNINA