A Portable Programming Interface for Performance Evaluation on Modern Processors

By S. Browne, Jack J. Dongarra, N. Garner, George Ho, P. Mucci. The international journal of high performance computing applications, 2000

773 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Tau Parallel Performance System (2006, background): “TAU supports different timing sources, choice of hardware counters through the PAPI (Browne et al. 2000) or PCL (Berrendorf, Ziegler, and Mohr) interfaces, and access to system performance data.”
On the Detection of Kernel-Level Rootkits Using Hardware Performance Counters (2017, methodology): “Finally, there are many libraries and software toolkits available for accessing HPCs, such as [3, 5] and [13].”
Communication-Optimal Parallel Recursive Rectangular Matrix Multiplication (2013, methodology): “Figure 3 shows the number of level 3 cache misses for CARMA and for MKL on m = n = 64, k = 524288, a case where CARMA is significantly faster, obtained using the Performance Application Programming Interface (PAPI [18]).”
Collecting Performance Data with PAPI-C (2009, methodology): “The use of hardware counters to measure and improve software performance has become an accepted and integral method in the software development cycle [1].”