Validation of hardware events for successful performance pattern identification in High Performance Computing
نویسندگان
چکیده
Hardware performance monitoring (HPM) is a crucial ingredient of performance analysis tools. While there are interfaces like LIKWID, PAPI or the kernel interface perf_event which provide HPM access with some additional features, many higher level tools combine event counts with results retrieved from other sources like function call traces to derive (semi-)automatic performance advice. However, although HPM is available for x86 systems since the early 90s, only a small subset of the HPM features is used in practice. Performance patterns provide a more comprehensive approach, enabling the identification of various performancelimiting effects. Patterns address issues like bandwidth saturation, load imbalance, non-local data access in ccNUMA systems, or false sharing of cache lines. This work defines HPM event sets that are best suited to identify a selection of performance patterns on the Intel Haswell processor. We validate the chosen event sets for accuracy in order to arrive at a reliable pattern detection mechanism and point out shortcomings that cannot be easily circumvented due to bugs or limitations in the hardware. 1.
منابع مشابه
Parallel computing using MPI and OpenMP on self-configured platform, UMZHPC.
Parallel computing is a topic of interest for a broad scientific community since it facilitates many time-consuming algorithms in different application domains.In this paper, we introduce a novel platform for parallel computing by using MPI and OpenMP programming languages based on set of networked PCs. UMZHPC is a free Linux-based parallel computing infrastructure that has been developed to cr...
متن کاملValidation of Integral System Yeast Plus for rapid identification and determination of antifungal susceptibility profile of clinically important Candida species
Precise identification of microorganisms involved in candidiasis together with antifungal susceptibility evaluation could help clinicians to prescribe appropriate medicine, especially in patients with critical conditions. The present study has been conducted to evaluate discriminatory power of Integral System Yeast Plus (ISYP) for rapid identification and determination of antifungal susceptibil...
متن کاملAutonomous Drug-Encapsulated Nanoparticles: Towards a Novel Non-Invasive Approach to Prevent Atherosclerosis
Introduction This paper proposes the concept of autonomous drug-encapsulated nanoparticle (ADENP) as a novel non-invasive approach to prevent atherosclerosis. ADENP consists of three simple units of sensor, controller (computing), and actuator. The hardware complexity of ADENP is much lower than most of the nanorobots, while the performance is maintained by the synergism in the swarm architectu...
متن کاملReducing Hardware Complexity of Wallace Multiplier Using High Order Compressors Based on CNTFET
Multiplier is one of the important components in many systems such as digital filters, digital processors and data encryption. Improving the speed and area of multipliers have impact on the performance of larger arithmetic circuits that are part of them. Wallace algorithm is one of the most famous architectures that uses a tree of half adders and full adders to increase the speed and red...
متن کاملIdentification areas with inundation potential for urban runoff harvesting using the support vector machine model
Rainfall-runoff from urban areas is one of the available water resources, which is wasted due to lack of attention and proper management. Besides, urban runoff excess of drains capacity causing many problems including inundation and urban environmental pollution. Therefore, harvesting this runoff can provide a part of the required water in urban areas, and also reduce flood and urban inund...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1710.04094 شماره
صفحات -
تاریخ انتشار 2017