%0 Conference Paper %B 2014 IEEE International Conference on Cluster Computing %D 2014 %T Power Monitoring with PAPI for Extreme Scale Architectures and Dataflow-based Programming Models %A Heike McCraw %A James Ralph %A Anthony Danalis %A Jack Dongarra %X For more than a decade, the PAPI performance-monitoring 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 road-blockers 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 taskbased dataflow-driven execution engine – enabling hardware performance counter and power monitoring at true task granularity. %B 2014 IEEE International Conference on Cluster Computing %I IEEE %C Madrid, Spain %8 2014-09 %G eng %R 10.1109/CLUSTER.2014.6968672 %0 Generic %D 2013 %T PAPI 5: Measuring Power, Energy, and the Cloud %A Vincent Weaver %A Dan Terpstra %A Heike McCraw %A Matt Johnson %A Kiran Kasichayanula %A James Ralph %A John Nelson %A Phil Mucci %A Tushar Mohan %A Shirley Moore %I 2013 IEEE International Symposium on Performance Analysis of Systems and Software %C Austin, TX %8 2013-04 %G eng %0 Conference Proceedings %B International Workshop on Power-Aware Systems and Architectures %D 2012 %T Measuring Energy and Power with PAPI %A Vincent M Weaver %A Matt Johnson %A Kiran Kasichayanula %A James Ralph %A Piotr Luszczek %A Dan Terpstra %A Shirley Moore %K papi %X Energy and power consumption are becoming critical metrics in the design and usage of high performance systems. We have extended the Performance API (PAPI) analysis library to measure and report energy and power values. These values are reported using the existing PAPI API, allowing code previously instrumented for performance counters to also measure power and energy. Higher level tools that build on PAPI will automatically gain support for power and energy readings when used with the newest version of PAPI. We describe in detail the types of energy and power readings available through PAPI. We support external power meters, as well as values provided internally by recent CPUs and GPUs. Measurements are provided directly to the instrumented process, allowing immediate code analysis in real time. We provide examples showing results that can be obtained with our infrastructure. %B International Workshop on Power-Aware Systems and Architectures %C Pittsburgh, PA %8 2012-09 %G eng %R 10.1109/ICPPW.2012.39 %0 Journal Article %J Procedia Computer Science %D 2011 %T User-Defined Events for Hardware Performance Monitoring %A Shirley Moore %A James Ralph %K mumi %K papi %X PAPI is a widely used cross-platform interface to hardware performance counters. PAPI currently supports native events, which are those provided by a given platform, and preset events, which are pre-defined events thought to be common across platforms. Presets are currently mapped and defined at the time that PAPI is compiled and installed. The idea of user-defined events is to allow users to define their own metrics and to have those metrics mapped to events on a platform without the need to re-install PAPI. User-defined events can be defined in terms of native, preset, and previously defined user-defined events. The user can combine events and constants in an arbitrary expression to define a new metric and give a name to the new metric. This name can then be specified as a PAPI event in a PAPI library call the same way as native and preset events. End-user tools such as TAU and Scalasca that use PAPI can also use the user-defined metrics. Users can publish their metric definitions so that other users can use them as well. We present several examples of how user-defined events can be used for performance analysis and modeling. %B Procedia Computer Science %I Elsevier %V 4 %P 2096-2104 %8 2011-05 %G eng %R https://doi.org/10.1016/j.procs.2011.04.229