skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Python library for analyzing hierarchical performance data

Abstract

Hatchet Is a Python-based library to analyze performance data that has a hierarchy (calling context trees, call graphs, callpath traces, nested regions' timers, etc.)

Authors:
 [1]
  1. LLNL
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1407415
Report Number(s):
Hatchet; 005525MLTPL00
LLNL-CODE-741008
DOE Contract Number:
AC52-07NA27344
Resource Type:
Software
Software Revision:
00
Software Package Number:
005525
Software CPU:
MLTPL
Open Source:
Yes
Source Code Available:
Yes
Country of Publication:
United States

Citation Formats

Bhatele, Abhinav. Python library for analyzing hierarchical performance data. Computer software. https://www.osti.gov//servlets/purl/1407415. Vers. 00. USDOE National Nuclear Security Administration (NNSA). 6 Sep. 2017. Web.
Bhatele, Abhinav. (2017, September 6). Python library for analyzing hierarchical performance data (Version 00) [Computer software]. https://www.osti.gov//servlets/purl/1407415.
Bhatele, Abhinav. Python library for analyzing hierarchical performance data. Computer software. Version 00. September 6, 2017. https://www.osti.gov//servlets/purl/1407415.
@misc{osti_1407415,
title = {Python library for analyzing hierarchical performance data, Version 00},
author = {Bhatele, Abhinav},
abstractNote = {Hatchet Is a Python-based library to analyze performance data that has a hierarchy (calling context trees, call graphs, callpath traces, nested regions' timers, etc.)},
url = {https://www.osti.gov//servlets/purl/1407415},
doi = {},
year = 2017,
month = 9,
note =
}

Software:
To order this software, request consultation services, or receive further information, please fill out the following request.

Save / Share:
  • The Python ARM Radar Toolkit is a package for reading, visualizing, correcting and analysing data from weather radars. Development began to meet the needs of the Atmospheric Radiation Measurement Climate Research Facility and has since expanded to provide a general-purpose framework for working with data from weather radars in the Python programming language. The toolkit is built on top of libraries in the Scientific Python ecosystem including NumPy, SciPy, and matplotlib, and makes use of Cython for interfacing with existing radar libraries written in C and to speed up computationally demanding algorithms. As a result, the source code for themore » toolkit is available on GitHub and is distributed under a BSD license.« less
  • We present "scraps" (SuperConducting Analysis and Plotting Software), a Python package designed to aid in the analysis and visualization of large amounts of superconducting resonator data, specifically complex transmission as a function of frequency, acquired at many different temperatures and driving powers. The package includes a least-squares fitting engine as well as a Monte-Carlo Markov Chain sampler for sampling the posterior distribution given priors, marginalizing over nuisance parameters, and estimating covariances. A set of plotting tools for generating publication-quality figures is also provided in the package. Lastly, we discuss the functionality of the software and provide some examples of itsmore » utility on data collected from a niobium-nitride coplanar waveguide resonator fabricated at Argonne National Laboratory.« less
  • This paper discusses some of the fundamental issues facing designers of mathematical software libraries for medium scale parallel processors such as the CRAY X-MP-4 and the Denelcor HEP. We discuss the problems that arise with performance and demonstrate that it may be appropriate to exploit parallelism at all levels of the program, not just at the highest level. We give performance measurements indicating the efficiency of a linear algebra library written in terms of a few high level modules. These modules chosen at the matrix vector level extend the concept of the BLAS and provide enough computational granularity to allowmore » efficient implementations on a wide variety of architectures. Only three modules must be recoded for efficiency in order to transport the library to various machines. We report experience on machines as diverse as the CRAY X-MP and the Denelcor HEP. Finally, we report on some special algorithms for the HEP which take advantage of the fine grain parallelism capabilities.« less
  • The final library file of formatted data contains nearly 250 individual NCLAN data sets comprised from 43 studies from four continental regions collected over 7 years (1980-1986). Data were collected to study response of various cultivars to ozone. Data were formatted into three categories: descriptive information, air-quality data, and plant-response data. Coordinated analysis of the data included developing dose-response functions for the economic assessment incorporating experiment to experiment variation into measures of precision of estimated relative yield losses and investigating alternative methods of analyses. Dose-response models were developed for economic assessment by combining all data for each crop species tomore » model assumptions and homogeneity of response to ozone over cultivars, sites and years. Methods used in these combined analysis included analyses of variance, polynomial and nonlinear regression analyses. Transformations of the data and of models were used when necessary based on development of residual and normal plots, Box-Cox analyses and Barlett's Chi-square Test for homogeneity of variance. An 'average' response was computed from models for each species, even though the response was known to be heterogeneous in most cases.« less
  • Abstract not provided.

To initiate an order for this software, request consultation services, or receive further information, fill out the request form below. You may also reach us by email at: .

OSTI staff will begin to process an order for scientific and technical software once the payment and signed site license agreement are received. If the forms are not in order, OSTI will contact you. No further action will be taken until all required information and/or payment is received. Orders are usually processed within three to five business days.

Software Request

(required)
(required)
(required)
(required)
(required)
(required)
(required)
(required)