Climate simulation codes, such as the Community Earth System Model (CESM), are especially complex and continually evolving. Their ongoing state of development requires frequent software verification in the form of quality assurance to both preserve the quality of the code and instill model confidence. To formalize and simplify this previously subjective and computationally expensive aspect of the verification process, we have developed a new tool for evaluating climate consistency, the CESM ensemble consistency test, referred to as CESM-ECT.
Dorit Hammerling is a researcher at the Institute for Mathematics Applied to Geosciences, in the National Center for Atmospheric Research. She is interested in spatio-temporal statistical methods applied to the geosciences, with a focus on massive data from satellites and climate models. To that end, she is interested in ways to optimally use the high performance computing facilities available at NCAR.
The talk will present an overview of the TAU Performance System to instrument, measure, and analyze the performance of parallel applications. It will show a brief demo of TAU’s ParaProf profile browser. Developers are encouraged to bring codes with them to the SEA workshop and work with the TAU developers during the week.
Sameer Shende is Director of the Performance Research Laboratory at the University of Oregon
XALT collects accurate, detailed, and continuous job-level and link-time data and stores that data in a database; all the data collection is transparent to the users. The amount of data generated can be hundreds of Gigabytes per year for a large center. The data stored can be mined to generate a picture of the compilers, libraries, and other software that users need to run their jobs successfully, highlighting the products that researchers use. We showcase how data collected by XALT can be easily mined into a digestible format by presenting data from four separate HPC centers.
Doctor Robert McLay received bachelors and masters degree from the Massachusetts Institute of Technology and his Ph.D in Engineering Mechanics from The University of Texas at Austin. His research include C++ software development, regression testing, and software tools, all related to large parallel numerical simulation codes. In particular, he has done work in parallel finite-element programs solving incompressible fluid flow and heat transfer.
His interest in software tools and support of HPC programming environments has lead to his development of Lmod, a modern replacement for Environment Modules system. Lmod's major advantages are protect all users from loading incompatible software without hindering experts. This work as lead to an interest in tracking the software usage through the module system.
In this tutorial, we will cover some of the basic approaches to software testing including: various types of coverage-based testing, testing based on program graphs, input space testing, data flow testing, and syntax-based testing. In addition to providing the theoretical background and explanation for each type of testing, attendees will work through some hands-on exercises. Attendees are encouraged to bring some of their own code segments to use in the hands-on portion of the tutorial. If time permits, we will also introduce the concepts of Test Driven Development.
Dr. Jeffrey Carver is an Associate Professor in the Department of Computer Science at the University of Alabama. He earned his PhD in Computer Science from the University of Maryland. His main research interests include empirical software engineering, software engineering for science, software quality, human factors in software engineering and software process improvement. He has been an active leader in the Software Engineering for Science community over the last decade. In addition, he is the primary organizer of a workshop series focused on Software Engineering for Science. He is a Senior Member of the IEEE Computer Society and a Senior Member of the ACM.
Ryan May has a Ph.D. in radar meteorology and works as a Software Engineer at Unidata. His primary work is on the THREDDS data server and a wide array of Python efforts at Unidata: these include the MetPy and Siphon packages, putting together training materials, and contributing to other open source libraries to smooth the way for using Python in meteorology.
Sean Arms is a boundary-layer guy by training (PhD), and Software Engineer by Luck (TM) at UCAR/UCP/Unidata. His primary work is focused on THREDDS related projects, such as netCDF-Java, the THREDDS Data Server, Rosetta, and most recently, Siphon.
Dr. Kevin Goebbert is an Associate Professor of Meteorology at Valparaiso University where he teaches a broad spectrum of meteorology courses including synoptic meteorology, numerical weather prediction, and meteorological computer applications, in which he teaches Fortran and Python to upper-level undergraduate students. In addition, he currently serves on the Unidata Users Committee.
Initial data exploration often begins with an iterative approach involving reading data from files, writing small bits of code to process the data in some way, plotting data to visualize patterns and inter-variable relationships, and sharing ideas with colleagues. The combination of the Python programming language, the data analysis package pandas, and Jupyter (formerly IPython) notebooks, an interactive environment for development and sharing, provides a powerful and easy-to-use toolset for data exploration.
Open Space is an approach that enables groups of any size to address complex, important issues and achieve meaningful results quickly. In Open Space meetings and events, participants create and manage their own agenda of parallel working sessions around a central theme of strategic importance. Conference participants will have the opportunity to apply Open Space technique to self-organize and discuss relevant topics with other meeting attendees. A space to write down ideas, questions, and discussion topics will be available throughout the first two days of the conference.
Authors: John C. Linford, Srinath Vadlamani, Sameer Shende, and Allen Malony
Dr. John Linford is a Scientist at ParaTools, Inc. He received his Ph.D. from Virginia Tech, where his dissertation on accelerating atmospheric modeling through emerging multi-core technologies was selected as the outstanding doctoral dissertation of 2010. John has developed a meta-programmer for chemical kinetic simulation, airborne signal processing applications, rotocraft engineering tools, and toolkits for porting parallel HPC applications to cloud computing platforms. John helps develop the TAU Performance System and has contributed to the Scalasca project and the MoinMoin project.
The North American Regional Climate Change Assessment Program (NARCCAP) is an international, multi-institution collaboration to simulate climate change over North America using high-resolution regional models driven by global models. The NARCCAP dataset has been used in a wide variety of research contexts, and is especially useful for impacts analysis.
Seth McGinnis is an Associate Scientist IV in the Institute for Mathematics Applied to Geosciences (IMAGe) at NCAR. As the Data Manager and User Community Manager for NARCCAP, the North American Regional Climate Change Assessment Program, he makes the output from climate models usable by and available to people who need information about climate change. His research focuses on bias correction, interpolation, and other issues affecting the practical use of model output by non-specialists.
R is a powerful open source and community supported programming environment first developed to satisfy the requirements of the Statistical community. Over the years R has developed into a general purpose language, and it has been applied to solve various problems across different disciplines. Powerful R packages are now available to analytically interact with spatial data in an efficient manner.