Power monitoring with PAPI for extreme scale architectures and dataflow-based programming models

Abstract

Abstract-For more than a decade, the PAPI performancemonitoring library has provided a clear, portable interface to the hardware performance counters available on all modern CPUs and other components of interest (e.g., GPUs, network, and I/O systems). Most major end-user tools that application developers use to analyze the performance of their applications rely on PAPI to gain access to these performance counters.One of the critical roadblocks on the way to larger, more complex high performance systems, has been widely identified as being the energy efficiency constraints. With modern extreme scale machines having hundreds of thousands of cores, the ability to reduce power consumption for each CPU at the software level becomes critically important, both for economic and environmental reasons. In order for PAPI to continue playing its well established role in HPC, it is pressing to provide valuable performance data that not only originates from within the processing cores but also delivers insight into the power consumption of the system as a whole.An extensive effort has been made to extend the Performance API to support power monitoring capabilities for various platforms. This paper provides detailed information about three components that allow power monitoring on the Intel Xeon Phi and Blue Gene/Q. Furthermore, we discuss the integration of PAPI in PARSEC -a task-based dataflow-driven execution engine -enabling hardware performance counter and power monitoring at true task granularity.

Investigating power capping toward energy‐efficient scientific applications

“…The PAPI performance monitoring library provides a coherent methodology and standardization layer to performance counter information for a variety of hardware and software components, including CPUs, graphics processing units (GPUs), memory, networks,() I/O systems, power systems,() and virtual cloud environments . PAPI can be used independently as a performance monitoring library and tool for application analysis; however, PAPI finds its greatest utility as a middleware component for a number of third‐party profiling, tracing, and sampling toolkits (eg, CrayPat, HPCToolkit, Scalasca, Score‐P, TAU, Vampir, PerfExpert), making it the de facto standard for performance counter analysis.…”

A Unified Hardware/Software Monitoring Method for Reconfigurable Computing Architectures Using PAPI

“…Likewise, in [21], the use of PAPI to monitor energy and power is discussed. In that work, the effort of McCraw et al is to extend the use of PAPI to support power monitoring capabilities for various platforms and, specifically, for the Intel Xeon Phi and Blue Gene/Q.…”

Energy Measurement Tools for Ultrascale Computing: A Survey

“…The Performance API (PAPI) [8], from the University of Tennessee, is well-established as a library interface for hardware performance counters. In recent years, it has included support for many energy measurement sources, such as RAPL, NVML, Xeon Phi or IBM EMON [29,51,52]. This allows for easy extraction of power data for projects and researchers which are already users of PAPI.…”