In response to the COVID-19 pandemic and transition to remote work, ECP and the IDEAS Productivity project launched the panel series Strategies for Working Remotely, which explores important topics in this area. This panel discussion will be conducted during the annual International Conference for High Performance Computing, Networking, Storage, and Analysis (SC21).

Abstract:

• In Spring 2020 many of us abruptly transitioned from a primarily on-site to a primarily remote work experience. Unplanned and imposed remote work created a sea change that has altered the way we work now and will likely impact the way we work in the future. This panel will explore strategies for working remotely, with emphasis on how teams in high-performance computing (HPC) can be effective and efficient in long-term hybrid settings, where some staff work remotely and others on site, or collaborate while geographically dispersed. This shift provides an opportunity to be more inclusive and compassionate, opening doors for technological innovation to support how we work and communicate as teams of scientists. By exploring how hybrid settings can help with hiring and retaining a diverse set of employees, this panel session will offer an opportunity for dialog to help shape and influence the future of HPC work (Raybourn, 2020).

Panelists:

• Sadaf R. Alam, Swiss National Supercomputing Centre (CSCS)
• Christian Bischof, Technical University (TU) Darmstadt
• Helen Cadematori, Lawrence Berkeley National Laboratory
• Devin Hodge, Argonne National Laboratory
• Kenjo Nakajima, University of Tokyo
• Pat Quillen, Mathworks

Moderator:

• Elaine Raybourn, Sandia National Laboratories

The IDEAS Productivity project, in partnership with the DOE Computing Facilities of the ALCF, OLCF, and NERSC, and the DOE Exascale Computing Project (ECP), organizes the webinar series on Best Practices for HPC Software Developers.

As part of this series, we offer one-hour webinars on topics in scientific software development and high-performance computing, approximately once a month. The December webinar is titled Scientific software ecosystems and communities: Why we need them and how each of us can help them thrive; and will be presented by Lois Curfman McInnes (Argonne National Laboratory). The webinar will take place on Wednesday, December 8, 2021 at 1:00 pm ET.

Abstract:

HPC software is a cornerstone of long-term collaboration and scientific progress, but software complexity is increasing due to disruptive changes in computer architectures and the challenges of next-generation science. Thus, the HPC community has the unique opportunity to fundamentally change how scientific software is designed, developed, and sustained—embracing community collaboration toward scientific software ecosystems, while fostering a diverse HPC workforce who embody a broad range of skills and perspectives. This webinar will introduce work in the U.S. Exascale Computing Project, where a varied suite of scientific applications builds on programming models and runtimes, math libraries, data and visualization packages, and development tools that comprise the Extreme-scale Scientific Software Stack (E4S). The webinar will introduce crosscutting strategies that are increasing developer productivity and software sustainability, thereby mitigating technical risks by building a firmer foundation for reproducible, sustainable science. The webinar will also mention complementary community efforts and opportunities for involvement.

This webinar was originally scheduled for January 12, 2022, and has been rescheduled for February 16, 2022.

The IDEAS Productivity project, in partnership with the DOE Computing Facilities of the ALCF, OLCF, and NERSC, and the DOE Exascale Computing Project (ECP), organizes the webinar series on Best Practices for HPC Software Developers.

As part of this series, we offer one-hour webinars on topics in scientific software development and high-performance computing, approximately once a month. The February webinar is titled Wrong Way: Lessons Learned and Possibilities for Using the “Wrong” Programming Approach on Leadership Computing Facility Systems; and will be presented by Philip C. Roth (Oak Ridge National Laboratory). The webinar will take place on Wednesday, February 16, 2022 at 1:00 pm ET.

Abstract:

Large scale computing systems such as those deployed and being deployed at U.S. Department of Energy computing facilities rely greatly on compute accelerators (currently graphics processing units, GPUs) for their performance potential. Each of these systems has a small number of natural approaches for representing the code that runs on these accelerators. For instance, for the Oak Ridge Leadership Computing Facility’s Frontier system, the natural approaches include the Heterogeneous-Compute Interface for Portability (HIP) and OpenMP with target offload. But it is often interesting, and sometimes even useful, to consider the impact of using a “wrong” programming approach for a given system. In this webinar, the speaker will present a few of these “wrong” programming approaches for current and near-term future systems, including a discussion of the specific software packages that enable the approach, and lessons learned in cases where the approach has been attempted.

HDF5 Tutorial: Constructing a Simple Terminal VOL Connector

This two-hour tutorial will cover the basics needed to construct a simple terminal Virtual Object Layer (VOL) connector. The tutorial will focus on the mapping of HDF5 API calls to alternative storage and setting up VOL fields and callbacks to support it. At the end of the tutorial, participants should be able to get started writing their own terminal VOL connectors. Familiarity with the HDF5 API, C programming and some basic knowledge of the VOL architecture will be helpful.

The tutorial will be held virtually on February 25, 2022. More information about the agenda and registration (required) can be found here.

The IDEAS Productivity project, in partnership with the DOE Computing Facilities of the ALCF, OLCF, and NERSC, and the DOE Exascale Computing Project (ECP), organizes the webinar series on Best Practices for HPC Software Developers.

As part of this series, we offer one-hour webinars on topics in scientific software development and high-performance computing, approximately once a month. The March webinar is titled Software Design Patterns in Research Software with Examples from OpenFOAM; and will be presented by Tomislav Maric (TU Darmstadt). The webinar will take place on Wednesday, March 9, 2022 at 1:00 pm ET.

Abstract:

Combining sub-algorithms to develop robust, scalable, and convergent numerical methods carries with itself a high level of uncertainty. Extensive automatic testing reduces this uncertainty for methods whose properties cannot be proven mathematically in all application scenarios – basically, most numerical methods. Methods with a more solid theoretical basis still require extensive testing since the jump between theory and practice is often challenging. The ability to select numerical sub-algorithms and combine them easily at runtime, speeds up research immensely. Software Design Patterns already very successfully address the requirements of runtime selection and algorithm combinations and are staples of modern Software Engineering. This webinar covers a handful of beneficial Software Design Patterns that provide a solid basis for developing numerical methods in a modular way – drawing concrete examples from OpenFOAM, a highly modular open-source software for Computational Fluid Dynamics.

This panel discussion was held during SC21 and is being rebroadcast with live chat Q&A. The panel explored strategies for working remotely, with emphasis on how teams in high-performance computing (HPC) can be effective and efficient in long-term hybrid settings, where some staff work remotely and others on site, or collaborate while geographically dispersed.

Abstract:

In Spring 2020 many of us abruptly transitioned from a primarily on-site to a primarily remote work experience. Unplanned and imposed remote work created a sea change that has altered the way we work now and will likely impact the way we work in the future. This panel will explore strategies for working remotely, with emphasis on how teams in high-performance computing (HPC) can be effective and efficient in long-term hybrid settings, where some staff work remotely and others on site, or collaborate while geographically dispersed. This shift provides an opportunity to be more inclusive and compassionate, opening doors for technological innovation to support how we work and communicate as teams of scientists. By exploring how hybrid settings can help with hiring and retaining a diverse set of employees, this panel session will offer an opportunity for dialog to help shape and influence the future of HPC work (Raybourn, 2020).

Panelists:

• Sadaf R. Alam, Swiss National Supercomputing Centre (CSCS)
• Christian Bischof, Technical University (TU) Darmstadt
• Helen Cadematori, Lawrence Berkeley National Laboratory
• Devin Hodge, Argonne National Laboratory
• Kenjo Nakajima, University of Tokyo
• Pat Quillen, Mathworks

Moderator:

• Elaine Raybourn, Sandia National Laboratories

The IDEAS Productivity project, in partnership with the DOE Computing Facilities of the ALCF, OLCF, and NERSC, and the DOE Exascale Computing Project (ECP), organizes the webinar series on Best Practices for HPC Software Developers.

As part of this series, we offer one-hour webinars on topics in scientific software development and high-performance computing, approximately once a month. The April webinar is titled Evaluating Performance Portability of HPC Applications and Benchmarks Across Diverse HPC Architectures; and will be presented by JaeHyuk Kwack (Argonne National Laboratory). The webinar will take place on Wednesday, April 13, 2022 at 1:00 pm ET.

Abstract:

As HPC communities move into the exascale era, GPU-accelerated systems become one of the primary HPC architectures, and major processor vendors proactively lead technical innovation in the GPU ecosystem. The U.S. DOE has successfully supported this transformation to the next generation of HPC infrastructure through the Exascale Computing Project (ECP). NVIDIA has played a leading role to deploy multiple pre-exascale GPU systems (Summit at OLCF, Sierra at LLNL, Perlmutter at NERSC, and Polaris at ALCF). AMD and Intel are playing critical roles in developing exascale GPU systems, such as Frontier at OLCF, Aurora at ALCF, and El Capitan at LLNL. Simultaneously with the dynamic shifts in hardware, application developer communities have endeavored to maintain or increase their scientific throughputs by adopting performance portable programming models or frameworks, and it turns out a smooth transition is one of the necessary conditions to maintain productivity. In this webinar, the speaker will evaluate the progress being made on achieving performance portability by a subset of ECP applications or their related mini-apps, and approaches to achieving performance portability across diverse HPC architectures including AMD, Intel, and NVIDIA GPUs.

The IDEAS Productivity project, in partnership with the DOE Computing Facilities of the ALCF, OLCF, and NERSC, and the DOE Exascale Computing Project (ECP), organizes the webinar series on Best Practices for HPC Software Developers.

As part of this series, we offer one-hour webinars on topics in scientific software development and high-performance computing, approximately once a month. The May webinar is titled Acquisition and Analysis of Times Series of Satellite Data in the Cloud – Lessons from the Field; and will be presented by Marisol Garcia-Reyes (Farallon Institute). The webinar will take place on Wednesday, May 11, 2022 at 1:00 pm ET.

Abstract:

Satellite data has grown and matured to levels that allow powerful and relevant analysis in climate science, which requires time series spanning decades. Acquiring such data has been a technical and coding challenge given the historical formats in which data is stored, and analyzing the data has required high levels of coding expertise. With technological advances, like the coding language Python and new storage and process capabilities available in the cloud, there is great potential to increase the use of satellite data in new and diverse research areas. This requires, however, expanding the user base by building capacity in groups with limited coding or technological expertise. A challenge is the steep learning curve for these new technological advances, which can be intimidating and discouraging. To provide a taste of the new technologies and opportunities they provide, the presenter has developed a tutorial to teach potential new users how to acquire, synthesize and analyze satellite and satellite-based time series of data, while learning and using Python and cloud advances in the process. In this webinar, the speaker will share the lessons learned in making and teaching the tutorial, which can be found at https://github.com/marisolgr/python_sat_tutorials.

Mentoring is vital to developing and retaining a diverse, talented, and enabled workforce. The first session in our Workforce Development Webinar series will feature a panel of experienced mentors drawn from High-Performance Computing (HPC) and STEM related careers, who will discuss tips for building the important mentor/mentee relationship and best practices in mentoring. They will share what they have learned from their mentees about developing, networking, and sponsoring the next generation of HPC and STEM professionals.

This webinar is brought to you by the Exascale Computing Project (ECP) HPC Workforce Development and Retention Action Group, that organizes a webinar series on topics related to developing a diverse, equitable, and inclusive work culture in the computing sciences.