Performance variation of FWQ and HPCCG on a dual-socket Intel E5-2650 v2

Performance variation of FWQ and HPCCG on a dual-socket Intel E5-2650 v2

Source publication
Chapter
Full-text available
The FFMK project designs, builds and evaluates a system-software architecture to address the challenges expected in Exascale systems. In particular, these challenges include performance losses caused by the much larger impact of runtime variability within applications, hardware, and operating system (OS), as well as increased vulnerability to failu...

Context in source publication

Context 1
... this simple benchmark kernel, may be suitable to quantify interruptions caused by system software, but they are insufficient to capture hardware-induced noise. We hypothesize that the full extent of hardware performance variation can only be observed when the resources which cause these variations are actually used. And indeed, as shown in Fig. 6, the HPCCG proxy code running on IHK/McKernel on an Intel Ivy Bridge system shows about 1% of performance variation among all cores of a ...