SC 2023 Workshop

2023 Keynote Speaker

Katherine Yelick is the Vice Chancellor for Research at the University of California, Berkeley, where she also holds the Robert S. Pepper Distinguished Professor of Electrical Engineering and Computer Sciences. She is also a Senior Faculty Scientist at Lawrence Berkeley National Laboratory. Yelick was Director of the National Energy Research Scientific Computing Center (NERSC) from 2008 to 2012 and led the Computing Sciences Area at Lawrence Berkeley National Laboratory from 2010 through 2019. She is a member of the National Academy of Engineering and the American Academy of Arts and Sciences, and she is a Fellow of the Association for Computing Machinery (ACM) and the American Association for the Advancement of Sciences (AAAS).

Learn more about Katherine: http://people.eecs.berkeley.edu/~yelick/bio.html

Katherine will be presenting, “When to Jump: Managing your Career and Maximizing your Impact”

One of the exciting aspects of a research career is that it can change rapidly, including the problems you work on and the collaborators you work with, in addition to the usual options of changing jobs and institutions.  Using my own experience at universities, national labs, and a brief stint in industry, I will talk about different experiences with each and how to decide when it is time for a change.

Brendan Bouffler has 25 years of experience in the global tech industry creating large-scale systems for HPC environments, and has been responsible for designing and building hundreds of HPC systems for researchers and engineers, all over the world. Quite a number of these efforts fed the TOP500 list, a few that placed in the top 5.

After leading the HPC organization in Asia for a hardware maker, Brendan joined Amazon in 2014 when it became clear to him that cloud would become the exceptional computing tool the global research & engineering community needed to bring on the discoveries that would change the world for us all.

He holds a degree in Physics and an interest in testing several of its laws as they apply to bicycles. This has frequently resulted in hospitalization.

He is based in London when he’s not in Seattle.

Connect with boof on:

• LinkedIn
• X
• YouTube

boof will be presenting, “Surviving and thriving as an ‘outsider’ – with the help of allies”

Suzanne Parete-Koon is a High-Performance Computing Engineer at the Oak Ridge Leadership Computing Facility (OLCF), located at Oak Ridge National Laboratory (ORNL). She is responsible for supporting scientific applications running on Frontier and other HPC resources at ORNL.

After earning her PhD in astrophysics from the University of Tennessee, Knoxville, in 2008, Parete-Koon embarked on a unique career journey. She spent a year as a foreign affairs officer with the US Department of State, thanks to an American Institute of Physics diplomacy fellowship. In 2009, she joined the Scientific Computing Group at OLCF as a post-doc. During this period, her work primarily involved developing computational simulations of the nuclear reactions that power stars and stellar explosions.

Suzanne’s passion for fostering collaboration and support in computational science eventually led her to a different role. She now serves as an OLCF user support specialist and HPC Engineer, actively collaborating with OLCF staff to innovate and enhance user experiences.

Currently, Parete-Koon is also the leader of the Exascale Computing Project’s HPC Workforce Development and Retention Action Group, which focuses on building inclusive and equitable workforce development and retention for high-performance computing in the Department of Energy National Labs.

Suzanne will be presenting, “Strength in Unity: Fostering Tech Career Persistence”

With regard to diversity, many of us start our careers in computing with enthusiasm and potential, but as we progress through different career stages, our representation dwindles. In simpler terms, we’re well-represented in the early stages of our careers but less so as we advance. In this discussion, I’d like to share insights I’ve gained from facilitating the ECP High-Performance Computing Workforce Development and Retention Action (HPC-WDR) Group’s Workforce Development Webinar series. The mission of the ECP-HPC-WDR Action Group was to enable DOE national laboratories and their related computing communities to share their collective insight for inclusive and equitable workforce development and retention for high-performance computing.

The goal of this session is to have an open conversation with all of you about how we can foster a sense of belonging in our workplaces or schools and develop a strong identity within the scientific or technical domain. We’re focusing on these aspects because research shows they significantly influence how long students stay in their majors and how long professionals continue in their careers.

For this discussion, we’re all panelists. I invite you to come prepared to share your experiences on what motivates you to persist in your career and your ideas on how we can create a supportive community that not only encourages our persistence but also transforms our institutions. Together, we’ll explore solutions for better workplace retention among minority groups in computing.

Annie Ma-Weaver is the Group PM for HPC and works to build products and solutions to enable scientists, researchers and engineers to run HPC workloads on Google Cloud. She has been with Google for 13+ years in roles including Chief of Staff, Strategy and BD. Before Google, Annie conducted behavioural economics research at Columbia Business School, worked in investment banking in Hong Kong and consulted for the Scottish government. Annie received an MBA from the Haas School of Business and a BA in Economics and Psychology from Columbia University.

Annie will be co-presenting, “Fostering Diversity, Equity and Inclusion (DEI) at Big Tech Firms”

Achieving a diverse and inclusive workforce requires focus and commitment, both at the organizational level and the individual level. Last year, Google achieved its most diverse, representative workforce yet. Getting there required targeted actions, along with following the data to understand which initiatives were delivering on their potential and which were not. We will share our perspectives and stories on DEI in a large technical firm, along with some ideas on how to create and expand opportunities for underrepresented groups.

Bill Magro Chief Technologist for HPC at Google, where he drives strategy and customer success for Google Cloud. Magro joined Google in 2020, after 20 years at Intel, where he was Intel Fellow and Chief Technologist for HPC. A recognized leader in the InfiniBand industry, Magro helped found the OpenFabrics Alliance and served as InfiniBand Trade Association TWG co-chair from 2007-2020. He holds a B.Eng in applied and engineering physics from Cornell University and Ph.D. in physics from the University of Illinois.

Bill will be co-presenting, “Fostering Diversity, Equity and Inclusion (DEI) at Big Tech Firms”

Achieving a diverse and inclusive workforce requires focus and commitment, both at the organizational level and the individual level. Last year, Google achieved its most diverse, representative workforce yet. Getting there required targeted actions, along with following the data to understand which initiatives were delivering on their potential and which were not. We will share our perspectives and stories on DEI in a large technical firm, along with some ideas on how to create and expand opportunities for underrepresented groups.

Dr. Elisabeth Ortega is a Theoretical Chemist converted to an HPC specialist. Since she was a child, she has been an enthusiast of science and technology, and it motivated her to get a first degree in chemistry and a second one in computer science, followed by a master’s degree and a Ph.D. in theoretical and computational chemistry. She tasted the HPC world, being the only system administrator of the chemistry department for one year, just to pay the bills when her doctorate scholarship ended, but she realized that the academy life was not for her, and moved to the industry right after presenting her dissertation.

Dr. Ortega spent seven years designing and developing software for pharmaceutical companies, teaching her customers to use the solutions provided to them, and traveling as a salesperson, but when the lockdown affected her daily tasks, spending a few months working at home, she decided to change her career and restart her experience in the HPC with a position in customer support and as a technician for European projects. A few months later, she was promoted to create her own department and to start the “quantum journey” of the company, being focused on innovative solutions to improve user accessibility to HPC and in the optimization of computational resources.

Today, she is the R&D&I manager and one of the decision-makers of an HPC services and consulting company. Her career was combined with her participation in local community events, participating actively in PyLadies BCN community more than 10 years ago until today (+100 members), being part of the coordination team of “Hablemos Python” discord channel (close to 9000 members) and co-creator of the WHPC local chapter.

Dr. Ortega will be presenting, “Our success case of full remote working”

Remote work has been widely adopted by tech companies since the lockdown more than three years ago. However, some companies are asking their employees to come back to their seats with the promise to change taught meetings by chatting next to the coffee machine.

In this talk, I’ll show what we have done since the company was founded 11 years ago to build and keep together a team separated several kilometers away.

Laura Schulz is currently the department head of Quantum Computing and Technologies at the Leibniz Supercomputing Centre (LRZ) in Garching, Germany. She drives multiple efforts toward integrating emerging quantum accelerators into several layers of the high-performance computing (HPC) ecosystem. Laura is the PI for Germany’s Euro-Q-Exa project to seat a EuroHPC Joint Undertaking quantum system in Bavaria and manages a robust portfolio of funded projects and a great team to achieve LRZ’s quantum strategy. Before joining LRZ, she was part of the Computation directorate at Lawrence Livermore National Laboratory (LLNL) as well as LLNL’s High Performance Computing Innovation Center (HPCIC). Recently, Laura was named an HPCWire 2023 Person to Watch.

Laura will be presenting, “Leading from the Middle”

Let’s face it: Being in a leadership role where you are sandwiched between those who report to you and those to whom you report can be tough. In fact, research shows middle and upper middle management experiences the most workplace dissatisfaction in organizations. It’s often frustrating and occasionally demotivating. But! It’s also on-and-off satisfying and once-in-a-while outright inspiring. In this talk, we’ll discuss ways to harness your position, manage and advocate for your team, meet the expectations of your organization, and be an agent of achievement.

Suzanne Parete-Koon is a High-Performance Computing Engineer at the Oak Ridge Leadership Computing Facility (OLCF), located at Oak Ridge National Laboratory (ORNL). She is responsible for supporting scientific applications running on Frontier and other HPC resources at ORNL.

After earning her PhD in astrophysics from the University of Tennessee, Knoxville, in 2008, Parete-Koon embarked on a unique career journey. She spent a year as a foreign affairs officer with the US Department of State, thanks to an American Institute of Physics diplomacy fellowship. In 2009, she joined the Scientific Computing Group at OLCF as a post-doc. During this period, her work primarily involved developing computational simulations of the nuclear reactions that power stars and stellar explosions.

Suzanne’s passion for fostering collaboration and support in computational science eventually led her to a different role. She now serves as an OLCF user support specialist and HPC Engineer, actively collaborating with OLCF staff to innovate and enhance user experiences.

Currently, Parete-Koon is also the leader of the Exascale Computing Project’s HPC Workforce Development and Retention Action Group, which focuses on building inclusive and equitable workforce development and retention for high-performance computing in the Department of Energy National Labs.

Suzanne will be presenting, “Strength in Unity: Fostering Tech Career Persistence”

With regard to diversity, many of us start our careers in computing with enthusiasm and potential, but as we progress through different career stages, our representation dwindles. In simpler terms, we’re well-represented in the early stages of our careers but less so as we advance. In this discussion, I’d like to share insights I’ve gained from facilitating the ECP High-Performance Computing Workforce Development and Retention Action (HPC-WDR) Group’s Workforce Development Webinar series. The mission of the ECP-HPC-WDR Action Group was to enable DOE national laboratories and their related computing communities to share their collective insight for inclusive and equitable workforce development and retention for high-performance computing.

The goal of this session is to have an open conversation with all of you about how we can foster a sense of belonging in our workplaces or schools and develop a strong identity within the scientific or technical domain. We’re focusing on these aspects because research shows they significantly influence how long students stay in their majors and how long professionals continue in their careers.

For this discussion, we’re all panelists. I invite you to come prepared to share your experiences on what motivates you to persist in your career and your ideas on how we can create a supportive community that not only encourages our persistence but also transforms our institutions. Together, we’ll explore solutions for better workplace retention among minority groups in computing.

Annie Ma-Weaver is the Group PM for HPC and works to build products and solutions to enable scientists, researchers and engineers to run HPC workloads on Google Cloud. She has been with Google for 13+ years in roles including Chief of Staff, Strategy and BD. Before Google, Annie conducted behavioural economics research at Columbia Business School, worked in investment banking in Hong Kong and consulted for the Scottish government. Annie received an MBA from the Haas School of Business and a BA in Economics and Psychology from Columbia University.

Annie will be co-presenting, “Fostering Diversity, Equity and Inclusion (DEI) at Big Tech Firms”

Achieving a diverse and inclusive workforce requires focus and commitment, both at the organizational level and the individual level. Last year, Google achieved its most diverse, representative workforce yet. Getting there required targeted actions, along with following the data to understand which initiatives were delivering on their potential and which were not. We will share our perspectives and stories on DEI in a large technical firm, along with some ideas on how to create and expand opportunities for underrepresented groups.

Bill Magro Chief Technologist for HPC at Google, where he drives strategy and customer success for Google Cloud. Magro joined Google in 2020, after 20 years at Intel, where he was Intel Fellow and Chief Technologist for HPC. A recognized leader in the InfiniBand industry, Magro helped found the OpenFabrics Alliance and served as InfiniBand Trade Association TWG co-chair from 2007-2020. He holds a B.Eng in applied and engineering physics from Cornell University and Ph.D. in physics from the University of Illinois.

Bill will be co-presenting, “Fostering Diversity, Equity and Inclusion (DEI) at Big Tech Firms”

Achieving a diverse and inclusive workforce requires focus and commitment, both at the organizational level and the individual level. Last year, Google achieved its most diverse, representative workforce yet. Getting there required targeted actions, along with following the data to understand which initiatives were delivering on their potential and which were not. We will share our perspectives and stories on DEI in a large technical firm, along with some ideas on how to create and expand opportunities for underrepresented groups.

Dr. Elisabeth Ortega is a Theoretical Chemist converted to an HPC specialist. Since she was a child, she has been an enthusiast of science and technology, and it motivated her to get a first degree in chemistry and a second one in computer science, followed by a master’s degree and a Ph.D. in theoretical and computational chemistry. She tasted the HPC world, being the only system administrator of the chemistry department for one year, just to pay the bills when her doctorate scholarship ended, but she realized that the academy life was not for her, and moved to the industry right after presenting her dissertation.

Dr. Ortega spent seven years designing and developing software for pharmaceutical companies, teaching her customers to use the solutions provided to them, and traveling as a salesperson, but when the lockdown affected her daily tasks, spending a few months working at home, she decided to change her career and restart her experience in the HPC with a position in customer support and as a technician for European projects. A few months later, she was promoted to create her own department and to start the “quantum journey” of the company, being focused on innovative solutions to improve user accessibility to HPC and in the optimization of computational resources.

Today, she is the R&D&I manager and one of the decision-makers of an HPC services and consulting company. Her career was combined with her participation in local community events, participating actively in PyLadies BCN community more than 10 years ago until today (+100 members), being part of the coordination team of “Hablemos Python” discord channel (close to 9000 members) and co-creator of the WHPC local chapter.

Dr. Ortega will be presenting, “Our success case of full remote working”

Remote work has been widely adopted by tech companies since the lockdown more than three years ago. However, some companies are asking their employees to come back to their seats with the promise to change taught meetings by chatting next to the coffee machine.

In this talk, I’ll show what we have done since the company was founded 11 years ago to build and keep together a team separated several kilometers away.

2023 WHPC Travel Fellow

Leslie Cook holds a Bachelor’s degree in Chemistry and is on cusp of completing a Master’s in Computer Science. Her STEM journey was fortified by an internship at the NIH Biomedical Informatics Section, where she delved into the intersections of data science and healthcare. Furthermore, Leslie was awarded a SIGHPC Fellowship that ignited a desire to explore how research in HPC is moving the world forward. This passion for innovation led her to an appointment with Oak Ridge National Laboratory/Department of Energy, where she was immersed in the realm of HPC. Leslie is a tenacious advocate for women in STEM and her journey exemplifies the ability to overcome challenges to carve a path that bridges scientific prowess with unwavering commitment, all while ensuring the best for her family and future.

Leslie will be presenting, “Investigating Linear Solvers for Power Grid Analysis with Exascale Computing: A Journey of Learning and Collaboration”

This work is a contribution to the advancement of linear solvers for the Exascale Computing Project. It focuses on direct sparse linear solvers using High-Performance Computing (HPC) for large-scale power systems, resembling the United States power grids. This paper explores supercomputers at Oak Ridge Leadership Computing Facility, Summit and Frontier, comparing both performance and optimization strategies. The project encompasses a comprehensive test bench for Trilinos Amesos2 CPU-based solvers, KLU2 and ShyLUBasker, and the testing of GPU-based solvers from NVIDIA cuSolver to AMD rocSolver on distinct architecture configurations. The challenges of power flow analysis are addressed through optimization techniques, like matrix symmetry and GPU acceleration, and by evaluating accuracy and stability of linear solvers through residual analysis. Beyond technical gains, this work underscores the significance of collaboration and diverse expertise in HPC for innovative analysis of power grid systems, critical for resilient infrastructure against burgeoning threats like climate change and cyberattacks.

2023 WHPC Travel Fellow

Babar Zaman Khan is a PhD candidate in the Computer Science department at Technical University Darmstadt, Germany. His current PhD research is conducted in collaboration with the industrial partner SAP, Germany, where he is part of the hardware team. Prior to his PhD, he earned his M.Sc. in Electrical Engineering from the University of Bremen, Germany, where he completed his thesis with the highest distinction in a joint partnership with Intel, Germany. The thesis focused on ASIC verification. He obtained his B.Sc. in Electrical Engineering from Lahore, Pakistan. His current PhD research primarily focuses on accelerating distributed storage through hardware accelerators such as FPGAs and SmartNICs. Additionally, he consistently contributes to open-source software and hardware projects. In his free time, he enjoys jogging, hiking, and cycling.

Babar will be presenting, “Accelerating the HPC I/O stack for Low Latency and High Throughput with FPGA-based Hardware Accelerators”

This talk addresses the complexity of the HPC I/O stack, which grapples with the increasing demands of HPC workloads and adds a significant overhead along the entire I/O request path. For instance, our measurements have shown that it takes more than 30,000 instructions to send and receive a single 4KB I/O request. A novel hardware-software framework, DeLiBA (Development of Linux Block I/O Accelerators), introduced in the talk is a proposal to alleviate the complexity of HPC I/O stack for easier research.  DeLiBA aims to bridge this gap by facilitating the development of software components within the I/O stack in user space, rather than the kernel space, and leverages a 16 nanometer (nm) FPGA to accelerate the I/Os with the help of FPGA-based I/O accelerators.  As a first use-case for DeLiBA, a proof-of-concept of an I/O accelerator for the client side of the distributed storage protocol called Ceph is implemented. For final hardware evaluation, the client-side host in DeLiBA framework uses an AMD EPYC Rome 7302P 16-core CPU with 128GB of memory, attached by 10Gb/s Ethernet to the Ceph server. The FPGA card is attached to the client host by PCIe and uses a system clock of 200MHz. The initial results achieve a 10% increase in throughput and demonstrates up to 2.3 times the I/O operations per second compared to conventional methods. Above all, DeLiBA is an open-source framework, and it is regularly being improved to serve as a common platform for HPC I/O researchers.

Meriam Gay Bautista is a Postdoctoral Researcher at the Computer Architecture Group in the Applied Mathematics and Computational Research Division( AMCRD) at Lawrence Berkeley National Laboratory, her research interest includes, mixed-signal IC, mmwave/RF circuits, superconducting circuits/logics, and quantum control hardware.

Meriam will be presenting, “Potential of Cryogenics Electronics for Future Computing Systems”

Cryogenic electronics have great potential to advance computing capabilities and quantum information processing. We explore two categories: Superconducting Electronics (SCE) and Cryogenic semiconductor electronics (Cryo-Semi). Taking advantage of the inherent phenomenon of superconductivity with zero resistance and Josephson junctions, SCE presents notable advantages in energy efficiency, minimal power dissipation, and gigahertz processing speed. Similarly, cryo-semi electronics offers a compelling advantage over their room temperature counterpart; these include lower noise, higher operating speed, increased efficiency, and wide-range operating temperature. Both SCE and cryo-semi exhibit compatibility with quantum technologies and deep space applications. Both have the capacity to operate at deep cryogenic temperatures, making them an appealing candidate for quantum computing. Their integration enables the seamless integration of classical and quantum resources in a shared cryogenic environment, improving quantum error correction and operating temperature compatibility.

We are excited to have Claire Barale joining us from the University of Edinburgh.

Claire will be presenting, “fAsyLex: Accelerating Legal NLP through Comparative Analysis of Multi-GPU Approaches”

The primary objective of this work is to conduct an evaluation of the acceleration of NLP training for the task of text classification on legal documents. The dataset used is AsyLex, a dataset of refugee claims from Canada. We implement fast AsyLex (fAsylex) and scale it across up to 64 GPUs. Through systematic experimentation, we seek to address the following research questions: How does the training time differ between single-GPU and multi-GPU setups for two commonly used PLMs? Does the choice of training approach (single-GPU vs. multi-GPU) influence the classification performance on the chosen dataset? We offer an investigation into the practical implications of employing single-GPU and multi-GPU training, we compare two of the most commonly used masked language models, RoBERTa and DeBERTa and reduce runtime out-of-the-box by 49% and 37% respectively, and we demonstrate that there is a trade-off in terms of NLP metrics and distributed training.

Dr. Vijayalakshmi Saravanan is currently working as Assistant Professor, Computer Science, at the University of South Dakota. Prior to this, she was a Visiting Assistant Professor, Computer Science, Vassar College, NY and an Adjunct Faculty at Rochester Institute of Technology, USA. Earlier she was a Postdoctoral Associate at University at Buffalo, SUNY, USA and University of Waterloo, Canada under the prestigious “Schlumberger Faculty for the Future” Fellowship award (2015-2017). She completed her Ph.D. under the prestigious Erasmus Mundus EU-Govt Fellowship award at Malardalen University, Sweden as a research exchange student. Prior to this, she was Assistant Professor of Practice at UTSA, USA. She is serving as a program committee member for reputed conferences & journals such as GHC, SIGCSE and Springer. Her research interests include Big Data in Healthcare, AI, Data Analytics/Visualization and Power-Aware Processor Design. She is also a lead editor for Pattern Recognition Letters (2020), Special Issue of Multimedia Tools and Applications (2020) and CRC Press Taylor & Francis, USA. She is a Senior Member of IEEE, ACM, ACM Distinguished speaker, CSI and Chair of IEEE WIE Affinity Group at VIT University during 2009-2015, Chair of NPA (National Postdoctoral Association) Annual Meetings, SRP-HPC ECP Fellow, and a Board Member of N2WOMEN.

Vijayalakshmi will be presenting, “An Analysis of Change Point Detection in High Performance Computing”

As high-performance computing approaches the Exa-scale era, the analysis of the vast amount of monitoring data generated by supercomputers has become increasingly challenging for data analysts. The detection of change points, which plays a critical role in anomaly detection, performance optimization, and root cause analysis of problems and failures, has grown beyond human capacity for manual review. To address this issue, our focus lies in developing an effective model capable of identifying anomalous behavior, and to achieve this, we introduce the concept of an online adaptive sampling algorithm. By evaluating the model’s performance across various use cases, we conduct tests on a complex datasets to detect change points. Overall, we observe that the model successfully captures key features of normal behavior, and we believe it opens promising avenues for further research, particularly in assisting with various tasks related to anomaly detection and performance optimization in high-performance computing environments.

Chelsea John is a researcher at Jülich Supercomputing Center. She is part of the Accelerating Devices Lab. Her areas of interests are in Natural Language Processing (NLP), Artificial Intelligence (AI), analysing and optimizing GPU applications, investigating new hardware resources, and testing out new performance opportunities for AI. She is a postgraduate in Physics with a keen interest in AI/ML and HPC.

Chelsea will be presenting, “OpenGPT-X: Novel Architecture Exploration”

The OpenGPT-X project is a German initiative with ten collaborators to build, train, and deploy a multilingual open-source language model. Models trained within the project will be used for pilot cases by industry partners and commercialized through the Gaia-X Federation. Due to the substantial memory and compute resources required for efficiently training large language models, high-performance computing systems such as JUWELS Booster are essential. This paper presents the results of the exploration of novel hardware architecture conducted within the scope of the project.

Naw Safrin Sattar is a Postdoctoral Research Associate in the Analytics & AI Methods at Scale group in Oak Ridge National Laboratory. She completed her Ph.D. in the field of Big Data Analytics and High Performance Computing from the University of New Orleans (UNO). Concurrently she completed her Master’s Degree from UNO in Spring 2019. She obtained her Bachelor’s Degree in Computer Science and Engineering from Bangladesh University of Engineering and Technology (BUET) in 2016. Her research interest includes Machine / Deep Learning at Scale, High Performance Computing, Parallel Algorithms, Graph Mining & Analysis, and Big Data Analytics.

Naw will be presenting, “Scalable Graph Analytics and HPC Operational Enhancement: Parallel Computing and ML/DL Innovations”

Parallel computing plays a pivotal role in the efficient processing of vast-scale graph. Complex network analysis stands as a captivating frontier of research, holding promise across diverse scientific domains such as sociology, biology, online media, and recommendation systems. In this era, Machine Learning (ML) and Deep Learning (DL) emerge as indispensable tools, underpinning remarkable technological achievements. Within this dynamic landscape, my research revolves around the advancement of parallel algorithms tailored for large-scale graph operations. To achieve this, I harness the power of cutting-edge technologies including OpenMP, MPI, HIP, and CUDA, on the High-Performance Computing (HPC) platforms to unlock optimal performance. I also apply ML/DL techniques to HPC operational data, to streamline the monitoring and maintenance of supercomputers, alleviating the complexities associated with their upkeep and enhancing user support. My research echoes the synergy between parallel computing, large-scale graph analysis, and ML/DL, enhancing computational efficiency and user experience.

Nan Ding is an early career researcher at LBNL. She accomplished her PhD at Tsinghua University in 2018 and became a postdoc at LBNL until 2021. Nan’s research interests include high-performance computing and performance modelling. She is also a proud mother of two toddlers.

Nan will be presenting, “Exploring the Potential of GPU-initiated Communications in HPC applications”

The two-sided MPI has become a de facto standard for communication on a distributed memory system. As high-performance GPU computing becomes the trend, some numerical methods have a relatively simple communication pattern adhering to the BSP model find MPI and its CUDA-aware variant can satisfy the performance requirements. Conversely, DAG-like computations have a more complex communication pattern and find it hard to scale to multiple GPUs. Thus, GPU-initiated one-sided communication becomes a viable solution for multi-GPU scaling. However, the lack of deep understanding of GPU-initiated one-sided communication and the real impact on applications performance become a hurdle. In this work, we use a multi-GPU SpTRSV, which is used in conjunction with Sparse LU for solving sparse linear systems, either as a direct solver or as a precondition, to demonstrate our multi-GPU SpTRSV implementation using NVSHMEM achieves up to 3x speedup on Perlmutter compared to a single GPU implementation.

K. Grace Johnson is a Research Engineer at Hewlett Packard Labs where she works on integrating quantum computing with supercomputing. She received her PhD in Chemical Physics in 2023 from Stanford University where she studied with Prof. Todd Martinez. During her PhD, Grace was a U.S. Department of Energy Computational Science Graduate Fellow, and in her research developed frameworks to parallelize and accelerate quantum chemistry simulations for HPC as well as simulating quantum circuits using tensor network methods. Her current work aims to develop hybrid quantum/classical approaches to solve challenging real-world problems in the near term. Grace is originally from Salt Lake City, Utah but now calls the SF Bay Area home.

Grace will be presenting, “Simulating Quantum Chemistry on Heterogeneous Architectures”

Simulating chemistry with quantum mechanical accuracy is a challenging task, while at the same time crucial to describing certain molecular interactions. On a classical machine, the scaling of quantum chemistry methods ranges from cubic for popular but less accurate methods to exponential for the highest quality methods. Quantum computers may be able to reduce the exponential scaling for high-accuracy methods, but while current quantum devices remain noisy, it is important to fully leverage modern high performance computing hardware. Doing so will enable pushing past present limits to study or even design new chemistry. In this work we present efforts to scale quantum chemistry simulations to heterogeneous HPC systems, simulate quantum circuits efficiently on classical hardware, and provide an outlook on hybrid quantum/classical approaches.

Jenny Wong holds a BSc, MMath in Mathematics and a PhD, in Fluid Dynamics from the University of Leeds. After her PhD, she spent 3 years in France at l’Institut de Physique du Globe de Paris and l’Institut des Sciences de la Terre for her postdoctoral research investigating the dynamics of the Earth’s core, using mathematical and numerical models. Jenny joined The University of Birmingham’s Research Software Group as a Senior Research Software Engineer in December 2021. Since then, she has collaborated on various research software coding projects from the School of Medicine and the School of Engineering, and provides HPC support to Baskerville, a national UK Tier 2 service, to enhance accessibility and performance of research software using GPU resources.

Jenny will be presenting, “Operationalising HPC tasks for space weather forecasting using Celery and Django: Making automated, HPC-powered scientific results accessible in near-real time.”

Forecasting space weather conditions in the Earth’s ionosphere is critical to protecting key infrastructure, such as satellite-based positioning and navigation systems, high-frequency radio communications, and the electric power grid. Variations in space weather are caused by coronal mass ejections from the Sun’s surface, energizing electrons in the ionosphere to produce disturbances in communications and electrical systems, as well as spectacular aurorae.

We present a system for operationalizing HPC tasks for data assimilation in space weather forecasting using Celery and Django. Celery is used to execute and distribute tasks asynchronously, while Django is a popular web framework. Our system integrates these tools to automate running space weather simulations on an HPC cluster for data assimilation and presenting outputs on a website in near real-time. Our system applies to a wide range of HPC tasks in research software, and we believe this is useful for researchers to operationalize similar workflows.

Dr. Nwamaka Okafor is currently a Postdoctoral Appointee at Argonne National Laboratory. Her work focuses on developing novel methods for analyzing High Performance Computing (HPC) systems logs as well as developing robust and interpretable AI models to improve HPC systems operations and efficiencies. She received her PhD in Electrical and Electronic Engineering (2022) from University College Dublin, Ireland where her research focused on applying AI and IoTs in environmental monitoring. Amaka holds a masters degree in Computer Forensics and Cyber Security from the University of Greenwich London. She also holds a postgraduate diploma in Information Management Technology from Federal University of Technology Owerri and a Higher National Diploma in Computer Science from Federal Polytechnic Nekede, Owerri, Nigeria.

Nwamaka will be presenting, “Queue Wait Time Prediction in Supercomputers”

High Performance Computing systems play critical role in advancing scientific research. They use schedulers for allocating resources to queued jobs. Waiting time can vary, even among jobs of similar characteristics, making it difficult to accurately estimate the exact time a job will wait in the queue. Knowing how long a job will wait is beneficial for adequate planning and to avoid frustrations that may arise when a user’s expectation of waiting time is not met. Efficient job wait time estimation is also crucial for optimizing resource allocation.

This paper investigates the impact of job characteristics and user behaviors on job wait time on leadership-class HPC systems. The paper evaluates the performance of different supervised learning algorithms for job wait time estimation. While this study focuses on the workload and hardware characteristics of Theta CrayXC40, the processes and tools developed in this study can be applied to any other leadership-class machine.

Dr. Bethany Lusch is a Computer Scientist in the data science group at the Argonne Leadership Computing Facility at Argonne National Lab. Her research expertise includes developing methods and tools to integrate AI with science, especially for dynamical systems and PDE-based simulations. Her recent work includes developing machine-learning emulators to replace expensive parts of simulations, such as computational fluid dynamics simulations of engines and climate simulations. She is also working on methods that incorporate domain knowledge in machine learning, representation learning, and using machine learning to analyze supercomputer logs. She holds a PhD and MS in applied mathematics from the University of Washington and a BS in mathematics from the University of Notre Dame.

Bethany will be presenting, “Queue Wait Time Prediction in Supercomputers”

High Performance Computing systems play critical role in advancing scientific research. They use schedulers for allocating resources to queued jobs. Waiting time can vary, even among jobs of similar characteristics, making it difficult to accurately estimate the exact time a job will wait in the queue. Knowing how long a job will wait is beneficial for adequate planning and to avoid frustrations that may arise when a user’s expectation of waiting time is not met. Efficient job wait time estimation is also crucial for optimizing resource allocation.

This paper investigates the impact of job characteristics and user behaviors on job wait time on leadership-class HPC systems. The paper evaluates the performance of different supervised learning algorithms for job wait time estimation. While this study focuses on the workload and hardware characteristics of Theta CrayXC40, the processes and tools developed in this study can be applied to any other leadership-class machine.

Jade Buzinski is mathematics Masters student at Arizona State University (ASU) as part of a 4+1 program, working in the HPC-adjacent Computational Research Accelerator as a student researcher and software engineer. Jade has been driving an international research project that applies machine learning techniques to experimentally obtained stratified-fluid mixing data, in an effort to reduce the barrier to discovering fundamental science that has implications for better modeling the global climate. Jade was awarded travel to this conference (supercomputing) by the Rocky Mountain Advanced Computing Consortium (RMACC) as a result of the Student Poster Competition at the May RMACC HPC symposium. Jade is currently serving as Vice President in ASU’s Association for Women in Mathematics (AWM) student chapter, and regularly participates in RMACC’s DEI meetings. After the Masters, Jade plans on pursing her Ph.D. to continue her research in HPC-enabled applied and computational mathematics, specifically in inverse problems and artificial intelligence.

Jade will be presenting, “Spatiotemporal Analysis and Prediction of Laboratory-Generated Turbulence”

Internal waves below the ocean’s surface significantly contribute to heat transfer in the global climate system, and are often studied with laboratory experiments like the Stratified Inclined Duct (SID). These experiments generate large amounts of data, creating expensive storage costs. This work is an effort to reduce the volume of data by developing a machine learning model that can accurately classify and predict mixing events in real time, enabling researchers to record and save particular moments of an experiment.

The model, a convolutional neural network, is trained on 107 experimental shadowgraph videos and achieves nearly 97% accuracy in classifying turbulence on roughly 7,000 shadowgraph frames. Preliminary work indicates promising results for predictive spatiotemporal modeling, as well as the implementation of the curvelet transform in pre-processing to reduce the model size and improve training times.

Jason Yalim is an Assistant Research Professor in Arizona State University’s Computational Research Accelerator, an HPC service unit that strives to reduce the time-to-science for ASU computational research. Jason has a Ph.D. in Applied Mathematics.

Jason will be presenting, “Spatiotemporal Analysis and Prediction of Laboratory-Generated Turbulence”

Internal waves below the ocean’s surface significantly contribute to heat transfer in the global climate system, and are often studied with laboratory experiments like the Stratified Inclined Duct (SID). These experiments generate large amounts of data, creating expensive storage costs. This work is an effort to reduce the volume of data by developing a machine learning model that can accurately classify and predict mixing events in real time, enabling researchers to record and save particular moments of an experiment.

The model, a convolutional neural network, is trained on 107 experimental shadowgraph videos and achieves nearly 97% accuracy in classifying turbulence on roughly 7,000 shadowgraph frames. Preliminary work indicates promising results for predictive spatiotemporal modeling, as well as the implementation of the curvelet transform in pre-processing to reduce the model size and improve training times.