Thursday 2:00pm-6:00pm Tutorial Compression for Scientific & Engineering Data Franck Cappello (ANL), Peter Lindstrom (Lawrence Livermore National Laboratory), and Sheng Di (Argonne National Laboratory) Biographies Biographies Franck Cappello
Peter Lindstrom
Sheng Di (Argonne National Laboratory) Sheng Di received his Ph.D. from the University of Hong Kong in 2011 (certificated in 2012). He was a postdoctoral fellow at INRIA, where he worked on workload/hostload prediction for Google data centers and optimization of resource allocation. He is now a computer scientist in the mathematics and computer science (MCS) division of Argonne National Laboratory. His current research interest includes lossy compression for scientific datasets, high performance computing, scalable computing, and fault tolerance. He is a senior member of IEEE and institute fellow of NAISE. He is also the scientist at Large through the Consortium for Advanced Science and Engineering (CASE) at the University of Chicago. He is the recipient of 2018 IEEE-Chicago Distinguished Mentoring Award and 2019 IEEE-Chicago Distinguished R&D Award. Abstract Abstract Large-scale numerical simulations, observations and experiments are generating very large datasets that are difficult to analyze, store and transfer. Data compression is an attractive and efficient technique to significantly reduce the size of scientific datasets. This tutorial reviews the state of the art in lossy compression of scientific datasets covering the most effective decorrelation, approximation and coding techniques. It details the two leading compressors (SZ and ZFP) that offer lossless and lossy compressions.It also introduces compression error assessment metrics and the Z-checker tool to analyze the difference between initial and decompressed datasets. The tutorial offers hands-on exercises using SZ and ZFP as well as Z-checker. It addresses the following questions: Why compression? How does compression work? How to measure and control compression error of lossy compressors? The tutorial uses examples of real-world compressors and scientific/engineering datasets to illustrate the different compression techniques and their performance. The tutorial is given by two of the leading teams in this domain and targets primarily beginners interested in learning about lossy compression for scientific data. This half-day tutorial is improved from the evaluations of the highly rated tutorials given on this topic at ISC17, SC17, SC18, ISC19, SC19. Thursday 2:00pm-6:00pm Tutorial The Scalable Vector Extension: Programming Tools and Performance Analysis John Linford, Olly Perks, and Roxana Rusitoru (Arm); Simon McIntosh-Smith (University of Bristol); John Levesque (HPE); and Shinji Sumimoto (Fujitsu) Abstract Abstract The Scalable Vector Extension (SVE) is the next-generation SIMD instruction set for Armv8-A. SVE does not specify a vector length and it uses predicates to dynamically select vector lanes. For many developers, this presents an entirely new way of thinking about vectorization. This tutorial will introduce tools from the Arm community for SVE programming and performance analysis, i.e. compilers, scientific libraries, profilers, and debuggers. The content of this tutorial will be notably different from past SVE tutorials as this will be the first time a public SVE tutorial will be taught on SVE hardware. We plan to provide remote access to SVE-enabled CPUs for this tutorial. Hands-on exercises will explore the unique features of SVE and demonstrate their applicability to a range of common programing motifs. This tutorial will demonstrate how to capture high-utility information and present it in meaningful ways, i.e. how much time is spent in application routines, where these routines are called in the source code, and how well the routines vectorize. Attendees will complete the tutorial with a working understanding of SVE and knowledge of how SVE may be used in their applications. Thursday 2:00pm-6:00pm Tutorial Mastering Tasking with OpenMP Christian Terboven (RWTH Aachen University); Michael Klemm (OpenMP ARB, AMD); Bronis R. de Supinski (Lawrence Livermore National Laboratory); and Xavier Teruel (Barcelona Supercomputing Center) Abstract Abstract With the increasing prevalence of multi-core processors, shared-memory programming models are essential. OpenMP is a popular, portable, widely supported and easy-to-use shared-memory model. Since version 3.0 released in 2008, OpenMP offers tasking to support the creation of composable parallel software blocks and the parallelization of irregular algorithms. Developers usually find OpenMP easy to learn. However, mastering the tasking concept of OpenMP requires a change in the way developers reason about the structure of their code and how to expose the parallelism of it. Our tutorial addresses this critical aspect by examining the tasking concept in detail and presenting patterns as solutions to many common problems. Thursday 2:00pm-6:00pm Tutorial Advanced MPI Programming Pavan Balaji (Argonne National Laboratory), Torsten Hoefler (ETH Zurich), Antonio Peña (Barcelona Supercomputing Center), and Yanfei Guo (Argonne National Laboratory) Abstract Abstract The Message Passing Interface (MPI) has been the de facto standard for parallel programming for nearly two decades now. However, a vast majority of applications only rely on basic MPI-1 features without taking advantage of the rich set of functionality the rest of the standard provides. Further, with the advent of MPI-3 (released in September 2012), a vast number of new features have been introduced in MPI, including efficient one-sided communication, support for external tools, non-blocking collective operations, and improved support for topology-aware data movement. The upcoming MPI- 4 standard aims at introducing further improvements to the standard in a number of aspects. This is an advanced-level tutorial that will provide an overview of various powerful features in MPI, especially with MPI-2 and MPI-3, and will present a brief preview into what is being planned for MPI-4. Thursday 2:00pm-6:00pm Tutorial Determining Parallel Application Execution Efficiency and Scaling using the POP Methodology Judit Giménez (Polytechnic University of Catalonia, Barcelona Supercomputing Center) and Brian J. N. Wylie (Forschungszentrum Jülich GmbH, Jülich Supercomputing Centre) Abstract Abstract HPC application developers encounter significant challenges getting their codes to run correctly on leadership computer systems consisting of large numbers of interconnected multi-socket multicore processor nodes often with attached accelerator devices. They also need effective tools and methods to track and assess their codes’ execution performance as they aim to get ready for production on current or prospective exascale computer systems. Thursday 2:00pm-6:00pm Tutorial High Performance Distributed Deep Learning Dhabaleswar Panda (Ohio State University) and Hari Subramoni and Arpan Jain (The Ohio State University) Abstract Abstract The recent advances in Deep Learning (DL) have led to many exciting challenges and opportunities for CS and AI researchers alike. Modern DL frameworks like TensorFlow, PyTorch, and several others have emerged that offer ease of use and flexibility to train, and deploy Deep Neural Networks (DNNs). In this tutorial, we will provide an overview of interesting trends in DNN design and how cutting-edge hardware architectures and high-performance interconnects are playing a key role in moving the field forward. We will also present an overview of different DNN architectures and DL frameworks. Most DL frameworks started with a single-node design. However, approaches to parallelize the process of DNN training are also being actively explored. The DL community has moved along different distributed training designs that exploit communication runtimes like MPI and NCCL. We highlight new challenges and opportunities for communication runtimes to exploit high-performance CPU and GPU architectures to efficiently support large-scale distributed DNN training. We also highlight some of our co-design efforts to utilize MPI for large-scale DNN training on cutting-edge CPU and GPU architectures. Finally, we include hands-on exercises to enable the attendees to gain first-hand experience of running distributed DNN training experiments on a modern GPU cluster. Thursday 2:00pm-6:00pm Tutorial Hands-on Practical Hybrid Parallel Application Performance Engineering Christian Feld and Markus Geimer (Jülich Supercomputing Centre); Sameer Shende (University of Oregon; ParaTools, Inc.); and Bill Williams (Technische Universität Dresden, ZIH) Abstract Abstract This tutorial presents state-of-the-art performance tools for leading-edge HPC systems founded on the community-developed Score-P instrumentation and measurement infrastructure, demonstrating how they can be used for performance engineering of effective scientific applications based on standard MPI, OpenMP, hybrid combination of both, and increasingly common usage of accelerators. Parallel performance tools from the Virtual Institute - High Productivity Supercomputing (VI-HPS) are introduced and featured in hands-on exercises with Score-P, Scalasca, Vampir, and TAU. We present the complete workflow of performance engineering, including instrumentation, measurement (profiling and tracing, timing and PAPI hardware counters), data storage, analysis, tuning, and visualization. Emphasis is placed on how tools are used in combination for identifying performance problems and investigating optimization alternatives. Using their own notebook computers with a provided E4S [https://e4s.io] OVA image containing all of the necessary tools (running within a virtual machine), participants will conduct exercises on a contemporary HPC system where remote access will be provided for the hands-on sessions through AWS running the E4S image. This will help to prepare participants to locate and diagnose performance bottlenecks in their own parallel programs. Thursday 2:00pm-6:00pm Tutorial Getting Started with Containers on HPC Richard S. Canon (Lawrence Berkeley National Lab, NERSC); Andrew J. Younge (Sandia National Labs); Carlos Eduardo Arango Gutierrez (Red Hat, Universidad del Valle); Marco De La Pierre (Pawsey Supercomputing Centre); and Sameer Shende (University of Oregon) Abstract Abstract Within just the past few years, the use of containers has revolutionized the way in which industries and enterprises have developed and deployed computational software and distributed systems. The containerization model has gained traction within the HPC community as well with the promise of improved reliability, reproducibility, portability, and levels of customization that were previously not possible on supercomputers. This adoption has been enabled by a number of HPC-compatible Container runtimes that have emerged including Singularity, Shifter, Enroot, Charliecloud, Podman and others. Thursday 2:00pm-6:00pm Tutorial Better Scientific Software David E. Bernholdt (Oak Ridge National Laboratory), Anshu Dubey (Argonne National Laboratory), Patricia A. Grubel (Los Alamos National Laboratory), Rinku Gupta (Argonne National Laboratory), and David Rogers (Oak Ridge National Laboratory) Abstract Abstract The computational science and engineering (CSE) community is in the midst of an extremely challenging period created by the confluence of disruptive changes in computing architectures, demand for greater scientific reproducibility, and new opportunities for greatly improved simulation capabilities, especially through coupling physics and scales. Computer architecture changes require new software design and implementation strategies, including significant refactoring of existing code. Reproducibility demands require more rigor across the entire software endeavor. Code coupling requires aggregate team interactions including integration of software processes and practices. These challenges demand large investments in scientific software development and improved practices. Focusing on improved developer productivity and software sustainability is both urgent and essential. Thursday 2:00pm-6:00pm Tutorial Managing HPC Software Complexity with Spack Todd Gamblin and Gregory Becker (Lawrence Livermore National Laboratory), Massimiliano Culpo (Sylabs), Tamara Dahlgren (Lawrence Livermore National Laboratory), Michael Kuhn (Otto von Guericke University Magdeburg), and Peter Scheibel (Lawrence Livermore National Laboratory) Abstract Abstract The modern scientific software stack includes thousands of packages, from C, C++, and Fortran libraries, to packages written in interpreted languages like Python and R. HPC applications may depend on hundreds of packages spanning all of these ecosytems. To achieve high performance, they must also leverage low- level and difficult-to-build libraries such as MPI, BLAS, and LAPACK. Integrating this stack is extremely challenging. The complexity can be an obstacle to deployment at HPC sites and deters developers from building on each others’ work. Spack is an open source tool for HPC package management that simplifies building, installing, customizing, and sharing HPC software stacks. In the past few years, its adoption has grown rapidly: by end-users, by HPC developers, and by the world’s largest HPC centers. Spack provides a powerful and flexible dependency model, a simple Python syntax for writing package build recipes, and a repository of over 3,800 community-maintained packages. This tutorial provides a thorough introduction to Spack’s capabilities: installing and authoring packages, integrating Spack with development workflows, and using Spack for deployment at HPC facilities. Attendees will leave with foundational skills for using Spack to automate day-to-day tasks, along with deeper knowledge for applying Spack to advanced use cases. Thursday 2:00pm-6:00pm Tutorial Kokkos: Performance Portability for C++ Applications and Libraries Christian R. Trott and Sivasankaran Rajamanickam (Sandia National Labs), Damien Lebrun-Grandie (Oak Ridge National Laboratory), Mikael Simberg (Swiss National Supercomputing Centre), Jonathan Madsen (Lawrence Berkeley National Laboratory), and Geoffrey Womeldorff (Los Alamos National Laboratory) Abstract Abstract The trend over the past decade towards increasingly diverse heterogeneous hardware has had a profound impact on the landscape of programming models and execution models. Single-source heterogeneous programming models for performance portability have particularly gained popularity in the past few years due to the increasingly insurmountable plethora of vendor-specific interfaces for heterogeneous hardware. With more than a decade of experience in the field, Kokkos has emerged as a leader in the area of performance-portable parallel programming models, with more than a hundred projects utilizing the latest in CPU and GPU hardware through its generic interface. This tutorial, given in various forms and venues around the globe, presents a practical introduction to the Kokkos programming model. Many iterations on the tutorial material have shown that most attendees acquire the necessary skills to begin porting production applications to the Kokkos programming model after just one day of instruction. Interactive practice exercises teach not only the fundamental syntax and semantics of the programming model, but also the performance characteristics of parallel applications on modern heterogeneous hardware. Presentations of the Kokkos Kernels and Tooling libraries are also included, leaving attendees with all of the necessary skills to use Kokkos in their own HPC applications. Friday 2:00pm-6:00pm Tutorial OpenMP Common Core: Learning Parallelization of Real Applications from the Ground-Up Manuel Arenaz (Appentra Solutions, University of A Coruña); Barbara Chapman (Brookhaven National Lab); Oscar Hernandez (NVIDIA); Reuben D. Budiardja (Oak Ridge National Lab (ORNL)); and Dossay Oryspayev (Brookhaven National Lab) Abstract Abstract As HPC continues to move towards a model of multicore and accelerator programming, a detailed understanding of shared-memory models and how best to use accelerators has never been more important. OpenMP is the de facto standard for writing multithreaded code to take advantage of shared memory platforms, but to make optimal use of it can be incredibly complex. Friday 2:00pm-6:00pm Tutorial Productive Parallel Programming for FPGA with High-Level Synthesis Johannes de Fine Licht and Torsten Hoefler (ETH Zurich) Abstract Abstract Energy efficiency has become a first class citizen in the design of large computing systems. While GPUs and custom processors show merit in this regard, reconfigurable architectures, such as FPGAs, promise another major improvement in energy efficiency, constituting a middle ground between fixed hardware architectures and custom-built ASICs. This tutorial shows how high-level synthesis (HLS) can be harnessed to productively achieve scalable pipeline parallelism on FPGAs. Attendees will learn how to target FPGA resources from high-level C++ or OpenCL code, guiding the mapping from imperative code to hardware, enabling them to develop massively parallel designs. We treat well-known examples from the software world, relating traditional code optimizations to hardware, building on existing knowledge when introducing new topics. By bridging the gap between software and hardware optimization, our tutorial aims to enable developers from a large set of backgrounds to start tapping into the potential of FPGAs for high performance codes. Friday 2:00pm-6:00pm Tutorial Hands-On HPC Application Development Using C++ and SYCL Gordon Brown and Michael Wong (Codeplay Software), Michael Steyer (Intel), Rod Burns (Codeplay Software), Aksel Alpay (Heidelberg University), Peter Zuzek (Codeplay Software), Ronan Keryell (Xilinx), and Igor Vorobtsov (Intel) Abstract Abstract SYCL is a programming model that lets developers write parallel applications for a wide variety of devices (CPUs, GPUs, FPGAs and more) from a single code base using standard C++. Given the growing heterogeneity of processor roadmaps, moving to a platform-independent model such as SYCL is essential for modern software developers. SYCL has the further advantage of supporting a single-source style of programming from completely standard C++. In this tutorial, we will introduce SYCL and provide programmers with a solid foundation they can build on to gain mastery of this language. The real value in SYCL comes from its use in writing applications. We will explore how SYCL can be used to write serious applications, covering intermediate to advanced features of SYCL as well as some of the tools and libraries that support SYCL application development. This is a hands-on tutorial. Students will be given exercises that represent key design patterns encountered by people who program heterogeneous systems. Friday 2:00pm-6:00pm Tutorial InfiniBand, High-speed Ethernet, RoCE, Omni-Path, EFA, and Slingshot for Beginners Dhabaleswar Panda and Hari Subramoni (The Ohio State University) Abstract Abstract InfiniBand (IB), High-speed Ethernet (HSE), RoCE, Omni-Path, EFA, and Slingshot technologies are generating a lot of excitement towards building next generation High-End Computing (HEC) systems including clusters, datacenters, file systems, storage, cloud computing and Big Data (Hadoop, Spark, HBase and Memcached) environments. This tutorial will provide an overview of these emerging technologies, their offered architectural features, their current market standing, and their suitability for designing HEC systems. It will start with a brief overview of IB, HSE, RoCE, Omni-Path, EFA, Slingshot, and Omni-Path. In-depth overview of the architectural features of IB, HSE (including iWARP and RoCE), and Omni-Path, their similarities and differences, and the associated protocols will be presented. An overview of the emerging NVLink, NVLink2, and NVSwitch architectures will also be given. Next, an overview of the OpenFabrics stack which encapsulates IB, HSE, and RoCE (v1/v2) in a unified manner will be presented. An overview of libfabrics stack will also be provided. Hardware/software solutions and the market trends behind these networking technologies will be highlighted. Sample performance numbers of these technologies and protocols for different environments will be presented. Finally, hands-on exercises will be carried out for the attendees to gain first-hand experience of running experiments with high-performance networks. Friday 2:00pm-6:00pm Tutorial Modern Mixed- and Multi-Precision Methods Hartwig Anzt (Karlsruhe Institute of Technology, University of Tennessee); Jack Dongarra (University of Tennessee, Oak Ridge National Laboratory); and Piotr Luszczek (University of Tennessee, Tickle College of Engineering) Abstract Abstract This tutorial will expose the audience to the rapidly expanding landscape of mixed- and multi-precision methods. The ongoing cross-pollination between high-performance computing (HPC) and machine learning (ML) is leading to intelligent computational steering of large-scale simulations. More importantly for this tutorial, sharing of the hardware platforms and exploiting their wide range of computational modes has led to proliferation of multiple representations of floating-point data—and increased interest in new methods that exploit them. Against the backdrop of high-performance libraries produced by internet-scale companies, hardware vendors, national laboratories, and academic institutions, we will show the recent algorithmic progress in exploiting multiple precisions for increased efficiency in performance, communication, and/or storage. The techniques presented in the tutorial employ floating-point representations such as limited precision, quantized integers, and modular precision ecosystems. A portion of this tutorial will cover the fundamentals of the HPC software development in order to introduce the audience to some of the low-level details of coding for multiple precisions on modern hardware, including accelerators. The hardware focus of the tutorial will feature floating-point representation and performance of the recent supercomputing and industrial computing CPUs and accelerators, as well as less mainstream devices meant for more specific tasks at limited power envelopes. Friday 2:00pm-6:00pm Tutorial Maintaining a Modern Scientific Software Stack Made Easy with EasyBuild Kenneth Hoste (Ghent University), Alan O'Cais and Markus Geimer (Forschungszentrum Juelich GmbH), and Bart Oldeman (Compute Canada) Abstract Abstract Installing scientific software for supercomputers is known to be a tedious and time-consuming task. Increasing HPC user community diversity, as well as hardware complexity, continues to deepen the application software stack. Delivering optimised software installations and providing access to these installations in a reliable, user-friendly way is a highly non-trivial task that affects the application developer, the HPC user support teams, and the users themselves. This tutorial addresses this issue, providing the attendees with the knowledge to install and manage software in a clean and reproducible way. For this, the tutorial introduces EasyBuild, a software build and installation framework implemented in Python. It supports implementing (complex) installation procedures concisely, and is able to fully autonomously perform optimised software installations. It is open source and has a thriving community, and supports more than 2,200 (scientific) software packages. It is well integrated with different implementations of environment modules (Lmod, Tcl, C) to generate module files automatically and present them in a consistent way. Friday 2:00pm-6:00pm Tutorial Introduction to HPC: Applications, Systems, and Programming Models Bernd Mohr (Jülich Supercomputing Centre (JSC)) Biography Biography Bernd Mohr
Abstract Abstract In this introductory tutorial, you will learn what "high performance computing" means and what differentiates it from more mainstream areas of computing. You will also be introduced to the major applications that use high performance computing for research and commercial purposes, and how AI and HPC interact with each other. Then, we present the major HPC system architectures needed to run these applications. Finally, you will be provided with an overview of the languages and paradigms used to program HPC applications and systems. The tutorial will be presented by Dr.-Ing. Bernd Mohr from the Jülich Supercomputing Centre. Friday 2:00pm-6:00pm Tutorial OpenMP Common Core: Learning Parallelization of Real Applications from the Ground-Up Manuel Arenaz (Appentra Solutions, University of A Coruña); Barbara Chapman (Brookhaven National Lab); Oscar Hernandez (NVIDIA); Reuben D. Budiardja (Oak Ridge National Lab (ORNL)); and Dossay Oryspayev (Brookhaven National Lab) Abstract Abstract As HPC continues to move towards a model of multicore and accelerator programming, a detailed understanding of shared-memory models and how best to use accelerators has never been more important. OpenMP is the de facto standard for writing multithreaded code to take advantage of shared memory platforms, but to make optimal use of it can be incredibly complex. Friday 2:00pm-6:00pm Tutorial Productive Parallel Programming for FPGA with High-Level Synthesis Johannes de Fine Licht and Torsten Hoefler (ETH Zurich) Abstract Abstract Energy efficiency has become a first class citizen in the design of large computing systems. While GPUs and custom processors show merit in this regard, reconfigurable architectures, such as FPGAs, promise another major improvement in energy efficiency, constituting a middle ground between fixed hardware architectures and custom-built ASICs. This tutorial shows how high-level synthesis (HLS) can be harnessed to productively achieve scalable pipeline parallelism on FPGAs. Attendees will learn how to target FPGA resources from high-level C++ or OpenCL code, guiding the mapping from imperative code to hardware, enabling them to develop massively parallel designs. We treat well-known examples from the software world, relating traditional code optimizations to hardware, building on existing knowledge when introducing new topics. By bridging the gap between software and hardware optimization, our tutorial aims to enable developers from a large set of backgrounds to start tapping into the potential of FPGAs for high performance codes. Friday 2:00pm-6:00pm Tutorial Hands-On HPC Application Development Using C++ and SYCL Gordon Brown and Michael Wong (Codeplay Software), Michael Steyer (Intel), Rod Burns (Codeplay Software), Aksel Alpay (Heidelberg University), Peter Zuzek (Codeplay Software), Ronan Keryell (Xilinx), and Igor Vorobtsov (Intel) Abstract Abstract SYCL is a programming model that lets developers write parallel applications for a wide variety of devices (CPUs, GPUs, FPGAs and more) from a single code base using standard C++. Given the growing heterogeneity of processor roadmaps, moving to a platform-independent model such as SYCL is essential for modern software developers. SYCL has the further advantage of supporting a single-source style of programming from completely standard C++. In this tutorial, we will introduce SYCL and provide programmers with a solid foundation they can build on to gain mastery of this language. The real value in SYCL comes from its use in writing applications. We will explore how SYCL can be used to write serious applications, covering intermediate to advanced features of SYCL as well as some of the tools and libraries that support SYCL application development. This is a hands-on tutorial. Students will be given exercises that represent key design patterns encountered by people who program heterogeneous systems. Friday 2:00pm-6:00pm Tutorial InfiniBand, High-speed Ethernet, RoCE, Omni-Path, EFA, and Slingshot for Beginners Dhabaleswar Panda and Hari Subramoni (The Ohio State University) Abstract Abstract InfiniBand (IB), High-speed Ethernet (HSE), RoCE, Omni-Path, EFA, and Slingshot technologies are generating a lot of excitement towards building next generation High-End Computing (HEC) systems including clusters, datacenters, file systems, storage, cloud computing and Big Data (Hadoop, Spark, HBase and Memcached) environments. This tutorial will provide an overview of these emerging technologies, their offered architectural features, their current market standing, and their suitability for designing HEC systems. It will start with a brief overview of IB, HSE, RoCE, Omni-Path, EFA, Slingshot, and Omni-Path. In-depth overview of the architectural features of IB, HSE (including iWARP and RoCE), and Omni-Path, their similarities and differences, and the associated protocols will be presented. An overview of the emerging NVLink, NVLink2, and NVSwitch architectures will also be given. Next, an overview of the OpenFabrics stack which encapsulates IB, HSE, and RoCE (v1/v2) in a unified manner will be presented. An overview of libfabrics stack will also be provided. Hardware/software solutions and the market trends behind these networking technologies will be highlighted. Sample performance numbers of these technologies and protocols for different environments will be presented. Finally, hands-on exercises will be carried out for the attendees to gain first-hand experience of running experiments with high-performance networks. Friday 2:00pm-6:00pm Tutorial Modern Mixed- and Multi-Precision Methods Hartwig Anzt (Karlsruhe Institute of Technology, University of Tennessee); Jack Dongarra (University of Tennessee, Oak Ridge National Laboratory); and Piotr Luszczek (University of Tennessee, Tickle College of Engineering) Abstract Abstract This tutorial will expose the audience to the rapidly expanding landscape of mixed- and multi-precision methods. The ongoing cross-pollination between high-performance computing (HPC) and machine learning (ML) is leading to intelligent computational steering of large-scale simulations. More importantly for this tutorial, sharing of the hardware platforms and exploiting their wide range of computational modes has led to proliferation of multiple representations of floating-point data—and increased interest in new methods that exploit them. Against the backdrop of high-performance libraries produced by internet-scale companies, hardware vendors, national laboratories, and academic institutions, we will show the recent algorithmic progress in exploiting multiple precisions for increased efficiency in performance, communication, and/or storage. The techniques presented in the tutorial employ floating-point representations such as limited precision, quantized integers, and modular precision ecosystems. A portion of this tutorial will cover the fundamentals of the HPC software development in order to introduce the audience to some of the low-level details of coding for multiple precisions on modern hardware, including accelerators. The hardware focus of the tutorial will feature floating-point representation and performance of the recent supercomputing and industrial computing CPUs and accelerators, as well as less mainstream devices meant for more specific tasks at limited power envelopes. Friday 2:00pm-6:00pm Tutorial Maintaining a Modern Scientific Software Stack Made Easy with EasyBuild Kenneth Hoste (Ghent University), Alan O'Cais and Markus Geimer (Forschungszentrum Juelich GmbH), and Bart Oldeman (Compute Canada) Abstract Abstract Installing scientific software for supercomputers is known to be a tedious and time-consuming task. Increasing HPC user community diversity, as well as hardware complexity, continues to deepen the application software stack. Delivering optimised software installations and providing access to these installations in a reliable, user-friendly way is a highly non-trivial task that affects the application developer, the HPC user support teams, and the users themselves. This tutorial addresses this issue, providing the attendees with the knowledge to install and manage software in a clean and reproducible way. For this, the tutorial introduces EasyBuild, a software build and installation framework implemented in Python. It supports implementing (complex) installation procedures concisely, and is able to fully autonomously perform optimised software installations. It is open source and has a thriving community, and supports more than 2,200 (scientific) software packages. It is well integrated with different implementations of environment modules (Lmod, Tcl, C) to generate module files automatically and present them in a consistent way. Friday 2:00pm-6:00pm Tutorial Introduction to HPC: Applications, Systems, and Programming Models Bernd Mohr (Jülich Supercomputing Centre (JSC)) Biography Biography Bernd Mohr
Abstract Abstract In this introductory tutorial, you will learn what "high performance computing" means and what differentiates it from more mainstream areas of computing. You will also be introduced to the major applications that use high performance computing for research and commercial purposes, and how AI and HPC interact with each other. Then, we present the major HPC system architectures needed to run these applications. Finally, you will be provided with an overview of the languages and paradigms used to program HPC applications and systems. The tutorial will be presented by Dr.-Ing. Bernd Mohr from the Jülich Supercomputing Centre. Friday 2:00pm-6:00pm Workshop Second International Workshop on the Application of Machine Learning Techniques to Computational Fluid Dynamics and Solid Mechanics Simulations and Analysis Volodymyr Kindratenko (National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign); Andreas Lintermann (Jülich Supercomputing Centre, Forschungszentrum Jülich); Charalambos Chrysostomou (The Cyprus Institute); Ashley Scillitoe (The Alan Turing Institute); Eloisa Bentivegna (IBM Research Europe); Jiahuan Cui (Zhejiang University); George Karniadakis (Brown University, MIT); Kazuto Ando (RIKEN Center for Computational Science (R-CCS)); Mario Rüttgers (Institute of Aerodynamics and Chair of Fluid Mechanics, RWTH Aachen University; Jülich Supercomputing Centre, FZ Jülich); Michael Gauding (CORIA and University of Rouen); Mario Bedrunka and Felipe de Castro Teixeira Carvalho (University of Siegen); Jinhui Yan (University of Illinois at Urbana-Champaign); Thomas Brown (George Mason University, Center for Mathematics and Artificial Intelligence, Center for Computational Fluid Dynamics); Sarath Radhakrishnan (Barcelona Supercomputing Center); Yaning Wang (Zhejiang University); and Shirui Luo (University of Illinois at Urbana-Champaign) Biographies Biographies Volodymyr Kindratenko
Andreas Lintermann
Charalambos Chrysostomou
Ashley Scillitoe
Eloisa Bentivegna
Jiahuan Cui
George Karniadakis
Kazuto Ando
Mario Rüttgers
Michael Gauding
Mario Bedrunka
Felipe de Castro Teixeira Carvalho
Jinhui Yan
Thomas Brown
Sarath Radhakrishnan
Yaning Wang
Shirui Luo
Abstract Abstract Combination of computational fluid dynamics (CFD) with machine learning (ML) is a newly emerging research direction with the potential to enable solving so far unsolved problems in many application domains. This workshop aims to demonstrate the use of high-fidelity CFD simulations to generate data and utilize it to train ML models to better predict the underlying physics in fluid dynamics utilizing the breakthrough in computational power, the evolution of data science techniques, and the ability to generate terabytes of data from high-fidelity simulations. ML techniques have the potential to support the identification and extraction of hidden features in large-scale flow computations, hence allowing to shift the focus from time-consuming feature detection to in-depth examinations of such features. Furthermore, ML techniques have the ability to find undetected correlations between phenomena in the flow, which will lead to deeper insight of the physics involved in complex natural processes. Apart from pure fluid dynamic, other research areas, such as constitutive modeling of heterogeneous materials, multiphase flow modelling, dynamics of the atmospheric, ocean, and climate system, and combustion/chemical reactions are working on similar techniques. The workshop will stimulate this research by providing a venue to exchange new ideas and discuss challenges and opportunities. Friday 2:00pm-6:00pm Workshop HPC I/O in the Data Center Julian Kunkel (University of Reading), Jay Lofstead (Sandia National Laboratories), Jean-Thomas Acquaviva (Data Direct Networks), Bingsheng He (National University of Singapore), Richard Lawrence (MetOffice), Erdem Yilmaz (University of Reading), Glenn Lockwood (Lawrence Berkeley National Laboratory), Frank Gadban (University of Hamburg), Luke Logan (Illinois Tech), Jack Kolokasis (Foundation for research and Technology Hellas), Alberto Scionti (Linksfoundation), and Bruno Silva (Amazon) Biographies Biographies Julian Kunkel (University of Reading) Dr. Kunkel is a Lecturer at the Computer Science Department at the University of Reading. Previously, he worked as postdoc in the research department of the German Climate Computing Center (DKRZ) that partners with the Scientific Computing group at the Universität Hamburg. He manages several research projects revolving around High-Performance Computing and particularly high-performance storage. Julian became interested in the topic of HPC storage in 2003, during his studies of computer science. Besides his main goal to provide efficient and performance-portable I/O, his HPC-related interests are: data reduction techniques, performance analysis of parallel applications and parallel I/O, management of cluster systems, cost-efficiency considerations, and the software engineering of scientific software. Jay Lofstead (Sandia National Laboratories) Dr. Jay Lofstead is a Principal Member of Technical Staff at Sandia National Laboratories in Albuquerque, New Mexico. Since 2010, Jay has been working on HPC simulation workflows focusing on data management issues and as well as general I/O and storage issues for HPC. His prior work includes the R&D100 Award winning ADIOS I/O componentization framework in use in more than 30 production scientific simulations. He is a member of several conference and workshop program committees. Jean-Thomas Acquaviva (Data Direct Networks) Jean-Thomas has obtained his Ph.D in 2000 from CEA, DAM (French Atomic Commission, Military Dept.) and University of Versailles (France). After spending 2 years at Intel Compiler group in Santa Clara, he joined the University of Versailles as a Research Engineer, and afterward joined CEA (civilian department) still as a Research Engineer. Jean-Thomas was one of the founding members of the Exascale Research Centre, a joint lab between Intel, CEA and UVSQ, where he took the head of the performance group. He’s now actively participating in the development of DDN’s newly set Advanced Technology Center in France. Jean-Thomas is chairing two workshops focused on parallel file systems and performance scalability of file systems. He has authored or co-authored around 20 international publications. Bingsheng He (National University of Singapore) - Richard Lawrence (MetOffice) - Erdem Yilmaz (University of Reading) - Glenn Lockwood (Lawrence Berkeley National Laboratory) - Frank Gadban (University of Hamburg) - Luke Logan (Illinois Tech) - Jack Kolokasis (Foundation for research and Technology Hellas) - Alberto Scionti (Linksfoundation) - Bruno Silva (Amazon) - Abstract Abstract Managing scientific data at scale is challenging for scientists but also for the host data center. The storage and file systems deployed within a data center are expected to meet users' requirements for data integrity and high performance across heterogeneous and concurrently running applications. Workshop Website https://hps.vi4io.org/events/2021/iodc pdfFriday 2:00pm-6:00pm Workshop 5th International Workshop on In Situ Visualization Tom Vierjahn (Westphalian University of Applied Sciences), Thomas Theussl (KAUST Core Labs), Steffen Frey (University of Groningen), Kenneth Moreland (Sandia National Laboratories), Guido Reina (University of Stuttgart), and Andrew Bauer (United States Army Corps of Engineers) Biographies Biographies Tom Vierjahn (Westphalian University of Applied Sciences) Tom Vierjahn is a Professor of Computer Science at the Westphalian University of Applied Sciences, Germany. There, he is working on visualization, rendering, and virtual reality. During his postdoc stay at RWTH Aachen University, Germany, he researched analysis and visualization of performance data acquired from massively parallel application runs on supercomputers. Furthermore, he applied in situ visualization to parallel simulations stemming from neuroscience research. Tom received his Diploma and Master's degree from Dusseldorf University of Applied Sciences, Germany. He received his PhD in computer science from the University of Münster, Germany, for his work on online surface reconstruction from unorganized point clouds with integrated texture mapping. Thomas Theussl (KAUST Core Labs) Thomas Theussl is currently a Visualization Scientist in the KAUST Visualization Core Lab. He received his M.S. in Computer Science from the Vienna University of Technology in 2000. Steffen Frey (University of Groningen) Steffen Frey is a is an Assistant Professor at the University of Groningen. His research interests are in visual analysis techniques for large and complex spatio-temporal data, with a particular focus on performance-related aspects and the expressive visual representations of dynamic processes. Kenneth Moreland (Sandia National Laboratories) Dr. Kenneth Moreland is a principal member of technical staff at Sandia National Laboratories. He received BS degrees in computer science and in electrical engineering from the New Mexico Institute of Mining and Technology in 1997. He received MS and Ph.D. degrees in computer science from the University of New Mexico in 2000 and 2004, respectively. Dr. Moreland specializes in large-scale visualization and graphics and has played an active role in the development of several HPC products including ParaView, VTK, IceT, Catalyst, Dax, and VTK-m. His current interests include the design and development of visualization algorithms and systems to run on multi-core, many-core, and future-generation computer hardware. Guido Reina (University of Stuttgart) Dr. Guido Reina is senior lecturer and research associate at the Visualization Research Center of the University of Stuttgart. He received his diploma in Software Engineering and his Doctoral degree in Visualization from the University of Stuttgart. His research interests include large data visualization, parallel and in situ methods especially for particle data, focusing on molecular data sets. He is the MegaMol development team leader and interested in visualization system design and engineering as well as in long-term software sustainability issues. Andrew Bauer (United States Army Corps of Engineers) Andy is a Research Mechanical Engineer at the United States Army Corps of Engineers. He works primarily on developing algorithms and interfaces for software that numerically discretizes partial differential equations (PDE). His focus has been on the finite element method (FEM) for spatial discretizations of the PDE using adaptive techniques and parallel computing to ensure efficient use of available computing resources. Previously, Andy was a Staff R&D Engineer at Kitware where he has worked on the Visualization Toolkit (vtk.org) and ParaView (paraview.org) open source projects focusing on ParaView Catalyst. Abstract Abstract The ever increasing scale of today’s HPC simulations with their inherent I/O bottleneck makes in situ an essential approach for data analysis. Nowadays, the rate of data generation easily exceeds available bandwidth or storage capabilities significantly. Consequently, analysis and visualization has to be coubled in situ to a live simulation in order to facilitate comprehensive investigation. In doing so, data abstracts are generated that capture much more information than otherwise possible. Workshop Website https://woiv.gitlab.io pdfFriday 2:00pm-6:00pm Workshop Fourth HPC Applications in Precision Medicine Workshop Eric Stahlberg (Frederick National Laboratory for Cancer Research), Thomas Steinke (Zuse Institute Berlin), Jan Nygard (The Cancer Registry of Norway), Marco Berghoff (Karlsruhe Institute of Technology), Sunita Chandrasekaran (University of Delaware), Petrina Hollingsworth (Frederick National Laboratory for Cancer Research), and Andreas Deutsch (Dresden University of Technology) Biographies Biographies Eric Stahlberg (Frederick National Laboratory for Cancer Research) Dr. Stahlberg is director of Biomedical Informatics and Data Science (BIDS) at the Frederick National Laboratory for Cancer Research, spanning explorations from the molecular level to clinical trials. He has been instrumental in the laboratory's high-performance computing initiative and in assembling scientific teams across multiple, complex organizations to advance predictive oncology. Stahlberg has played a leadership role in establishing a collaboration between the NCI and the Department of Energy (DOE) to accelerate progress in precision oncology and computing. The Joint Design of Advanced Computing Systems for Cancer (JDACS4C) collaboration is rooted in three national initiatives and undertakes exploring predictive oncology and exascale computing in fundamental RAS biology, predicting tumor response, developing patient level health trajectories, and uses of AI to accelerate drug discovery. Dr. Stahlberg holds a Ph.D. in computational chemistry from The Ohio State University. Thomas Steinke (Zuse Institute Berlin) Thomas Steinke (organizer) heads the Supercomputing Dept. at the Zuse Institute Berlin (ZIB) and is responsible for the HPC research, consulting and operation His research interest is in high performance computing, heterogeneous systems for scientific and data analytics applications, and parallel simulation methods. Thomas leads the Intel Parallel Computing Center at ZIB since 2013. He received his Doctorate in Natural Sciences (Dr. rer. nat.) in chemistry from the Humboldt University of Berlin. Jan Nygard (The Cancer Registry of Norway) As Head of the Registry Informatics department at the Cancer Registry, responsibility include modernization and digitalisation of the Cancer Registry, including the development and deployment of an IKT-framework for cancer registries with electronic cancer reporting using the Norwegian Health Network, establishing the IT-system for the pilot project for Colorectal screening programme, modernization of the cervical cancer screening programme, and the insourcing the ICT-systems of the National Mammography programme. He is a board member of the CERTUS SFI, as well as serving on several reference and steering committees. Marco Berghoff (Karlsruhe Institute of Technology) Marco Berghoff received the diploma degree in mathematics from the University of Paderborn, Germany, with a focus on microlocal analysis, numerics, and physics. He received the PhD degree in computational materials science from the Institute for Applied Materials. He has been a member of the Karlsruhe Institute of Technology, at the Institute for Applied Materials. He has years of experience in multiscale modeling and high-performance optimization, and with the scale-bridging of the atomistic phase-field crystal model to the mesoscopic phase-field method. As a postdoctoral researcher in the Simulation Laboratory “NanoMicro”, he has introduced the framework NAStJA, and currently leads the developments. He is involved in several activities within this project, in particular in the development of large-scale simulations for biological or material science research topics. The NAStJA Framework is used to simulate the growth and treatment of cancerous tumor with a cell geometric resolution. Sunita Chandrasekaran (University of Delaware) Sunita Chandrasekaran is assistant professor in the Computer and Information Sciences Department at the University of Delaware. Her research interests include exploring the suitability of high-level programming models and runtime systems for HPC and embedded platforms, and migrating scientific applications to heterogeneous computing systems. Dr. Chandrasekaran was a post-doctoral fellow at the University of Houston and holds a Ph.D. from Nanyang Technological University, Singapore. She is a member of OpenACC, OpenMP, MCA and SPEC HPG. She has served on the program committees of various conferences and workshops including SC, ISC, ICPP, CCGrid, Cluster, and PACT, and has co-chaired parallel programming workshops co-located with SC, ISC, IPDPS, and SIAM. Petrina Hollingsworth (Frederick National Laboratory for Cancer Research) Petrina Hollingsworth serves as an engagement manager for NCI-DOE collaborations at Frederick National Laboratory for Cancer Research. Andreas Deutsch (Dresden University of Technology) Andreas Deutsch is head of the department of Innovative Methods of Computing at the Centre for Information Services and High Performance Computing (Dresden University of Technology). His research is focused on mathematical biology, especially cellular automata and agent-based modeling, cancer invasion and collective phenomena in the life sciences. Abstract Abstract High-performance computing has become central to the future success of precision medicine. Catalyzed by the dramatic increase in the volume of research and clinical data available through sequencing and advanced imaging techniques, clinical data available through medical records and mobile health devices, research data from automated platforms, combined with molecular and multi-scale simulations and the rapid adoption of deep learning approaches has created a convergence shaping the frontiers of computing and precision medicine. New approaches to drug discovery, data sharing, aggregation and safeguards, use of machine learning models in research and clinical contexts, multi-scale observations integrated with predictive modeling, and biomedical digital twins have identified new challenges and opportunities in these rapidly evolving frontiers. Workshop Website https://ncihub.org/groups/hapm21 pdfFriday 2:00pm-6:00pm Workshop Compiler-assisted Correctness Checking and Performance Optimization for HPC Emmanuelle Saillard (Inria), Julien Jaeger (CEA), Ira Baxter (Semantic Designs), Tim Jammer (TU Darmstadt), Julia Lawall (Inria), Michael Blesel (Otto-von-Guericke-University Magdeburg), and Reed Milewicz (Sandia National Laboratories) Biographies Biographies Emmanuelle Saillard
Julien Jaeger
Ira Baxter (Semantic Designs) Dr. Baxter has been involved with computing since 1966, initially in hardware working with relay, discrete transistor logic and early Diode-Transistor Logic ICs. He learned to program with IBM 1401 (Autocoder), 1620 (Fortran) and 360 systems (BAL, PL/1, APL). He implemented one of the first commercial minicomputer timesharing systems on a Data General Nova in 1970, before receiving his B.S. in Computer Science (1973). During a brief stint in the numerical controls business, he designed and implemented a complete 16 bit virtual memory minicomputer, its OS and development tools for automated milling systems. In 1976, he started Software Dynamics, a systems software house, where he designed compilers, time-sharing and distributed network operating systems. The similarity in concepts and dissimilarity in implementation of the various OSes suggested that managing designs was key to managing long-lived software systems, and turned Ira's interests towards deeper software engineering research. In 1990, he received a Ph.D. in Computer Science from the University of California at Irvine, where he studied Software Engineering, focusing on design reuse using transformational methods. Dr. Baxter spent several years with Schlumberger, working on a PDE-solver generator for CM-5 supercomputers (Sinapse). He was consulting Research Scientist for Rockwell International, focusing on industrial control automation software engineering tools for several years. Tim Jammer (TU Darmstadt) Tim Jammer is a PhD candidate at the Institute for Scientific Computing at Technical University of Darmstadt. He received his Bachelor and Master degree from the University of Hamburg, while also working as a student research assistant at the DKRZ. His research interests are mainly in parallel and high performance computing with a particular focus on compiler-based analysis and rewriting tools for the efficient use of MPI. He is one of the authors and main contributors of the MPI correctness benchmark suite MPI-CorrBench, as well as other MPI-related tools that can be found at https://github.com/tudasc. In addition to his research position, he is a staff member at the Hessian Competence Center for High Performance Computing (www.hkhlr.de), providing user support and regular training courses for Hessian HPC users. Julia Lawall (Inria) Julia Lawall is a senior research at Inria-Paris. Previously, she was on the faculty of the University of Copenhagen. She received her PhD in 1994 from Indiana University, USA. She has been program chair of GPCE, ICFP, and ASE, a member of the SIGPLAN Executive Committee, and is on the editorial board of Science of Computer Programming. Her research is at the crossroads of programming languages, software engineering, and operating systems. She is particularly interested in the design of tools that address problems in the maintenance of large software. She is the primary developer of the open-source Coccinelle program transformation system and has over 2000 patches in the Linux kernel based on her research. Michael Blesel (Otto-von-Guericke-University Magdeburg) Michael Blesel is a doctoral candidate at the Otto von Guericke University Magdeburg in the Parallel Computing and I/O group. His main research is in the field of compiler-assisted correctness checks for SPMD applications in the context of high-performance computing. During his time as a student at the University of Hamburg he has worked for the Scientific Computing group as a research and teaching assistant for their high-performance computing related courses. His interests include compiler-based tools, high-performance computing in general and performance optimizations for parallel applications. Reed Milewicz (Sandia National Laboratories) Reed Milewicz is a senior member of technical staff in the Department of Software Engineering and Research within the Center for Computing Research at Sandia National Laboratories. He does research in the areas of software engineering, formal verification, and compilers. He believes that the quality of our lives depends upon the quality of our software, and that’s why he focuses on developing better practices, processes, and tools to target all phases of the software development lifecycle. This is a course of research that straddles the line between systems and human factors, and it’s carried out in close coordination with the communities he supports. Since joining Sandia in late 2016, his focus has been on the scientific software development community. Abstract Abstract Practical compiler-enabled programming environments, applied analysis methodologies, and end-to-end toolchains can contribute significantly to performance portability in the exascale era. The practical and applied use of compilation techniques, methods, and technologies, including static analysis and transformation, are imperative to improve the performance, correctness, and scalability of high-performance applications, middleware, and reusable libraries. This workshop brings together a diverse group of researchers with a shared interest in applying compilation and source-to-source translation methodologies, among others, to enhance explicit parallel programming such as MPI, OpenMP, and hybrid models. These types of compiler technologies can also be applied to heterogeneous programming elements including FPGAs and GPUs in order to deliver higher achievable performance as compared to library-based methods and human-coded approaches taken in isolation. Workshop Website https://c3po-workshop.github.io/2021/index pdfFriday 2:00pm-6:00pm Workshop Sixth International Workshop on Communication Architectures for HPC, Big Data, Deep Learning and Clouds at Extreme Scale Dhabaleswar Panda, Hari Subramoni, and Aamir Shafi (The Ohio State University); Satoshi Matsuoka (RIKEN Center for Computational Science); Gilad Shainer (NVIDIA/Mellanox); Duncan Roweth (HPE); Phil Murphy (Cornelius Networks); Hemal Shah and Moshe Voloshin (Broadcom); Matthew Williams (Rockport Networks); and Sanjay Basu (Oracle) Biographies Biographies Dhabaleswar Panda
Hari Subramoni
Aamir Shafi
Satoshi Matsuoka
Gilad Shainer
Duncan Roweth
Phil Murphy
Hemal Shah
Moshe Voloshin
Matthew Williams
Sanjay Basu
Abstract Abstract Extreme-Scale Computing in HPC, Big Data, Deep Learning, and Clouds are marked by multiple-levels of hierarchy and heterogeneity ranging from the compute units (many-core CPUs, GPUs, APUs, etc) to storage devices (NVMe, NVMe over Fabrics etc) to the network interconnects (InfiniBand, High-Speed Ethernet, Slingshot, etc). Owing to the plethora of heterogeneous communication paths with different cost models expected to be present in extreme-scale systems, data movement is seen as the soul of different challenges for exascale computing. On the other hand, advances in networking technologies such as NoCs (like NVLink and Stormlake), emergence of new I/O interface architecture standards (CCIX, Gen-Z, CAPI etc), and RDMA enabled networks and the likes are constantly pushing the envelope of research in the field of novel communication and computing architectures for extreme-scale computing. The goal of this workshop is to bring together researchers and software/hardware designers from academia, industry and national laboratories who are involved in creating network-based computing solutions for extreme-scale architectures. The scope of the workshop includes, but not limited to: scalable communication architectures and protocols, high performance networks, runtime/middleware designs, novel hardware/software co-design, high performance communication solutions for accelerator-based computing, power-aware techniques and designs, performance evaluations, QoS, and virtualization. Workshop Website http://nowlab.cse.ohio-state.edu/exacomm/ pdfFriday 2:00pm-6:00pm Workshop Third Workshop on HPC Education and Training for Emerging Technologies Nitin Sukhija (Slippery Rock University Of Pennsylvania); Scott Lathrop (University of Illinois); Nia Alexandrov (Hartree Centre, STFC, UKRI); Andrew Jones (Microsoft); Marjut Dieringer and Kevin McFall (NVIDIA); Kjartan Thor Wikfeldt (EuroCC National Competence Center Sweden); Mozhgan Chimeh (NVIDIA); Weronika Filinger (Edinburgh Parallel Computing Centre (EPCC)); Julia Mullen (MIT Lincoln Laboratory); Ann Backhaus (Pawsey Supercomputing Centre); and Richard Lawrence (Texas A&M University) Biographies Biographies Nitin Sukhija (Slippery Rock University Of Pennsylvania) Dr. Nitin Sukhija, is a Director of Center of Cybersecurity and Advanced Computing (C2AC), an assistant professor and one of the XSEDE Campus Champion specializes in the area of high performance data analytics and security. He has been involved in research and management of various projects pertaining to the HPC and software challenges in industry and academia for over a decade. Dr. Sukhija chaired and co-chaired many conferences such as ACM XSEDE16, ACM MEDES18, and IEEE WHPBDC(16, 17) conference and is also serving as an active member of the organizing committees of various esteemed (national and international) ACM and IEEE conferences and workshops, such as, XSEDE,IPDPS, PASA, ICPP, ISPDC, WHPBDC, SC EduHPC, SC18 Early Career Program, SIAM CSE Broader Engagement and others. He currently co-chairs the SIGHPC Education Chapter workshop committee and has been active in the planning and participation in HPC Training Workshops series at the SC, ISC and other conferences since 2015. Scott Lathrop (University of Illinois) Through his position with the Shodor Education Foundation, Inc., Scott Lathrop is the Blue Waters Technical Program Manager for Education. Lathrop has been involved in high performance computing and communications activities since 1986. Lathrop coordinates the community engagement activities for the Blue Waters project. He helps ensure that Blue Waters education, outreach and training activities are meeting the needs of the community. Lathrop has been involved in the SC Conference series since 1989, served as a member of the SC Steering Committee for six years. He served as the Conference Chair for the SC’11 and XSEDE14 Conferences. He helped form the International HPC Training Consortium which was merged into the ACM SIGHPC Education Chapter during 2018, and has been active in the planning and participation in HPC Training Workshops at the SC and ISC Conferences. Nia Alexandrov (Hartree Centre, STFC, UKRI) Dr. Nia Alexandrova is the Training Manager at Hartree Centre. She was a Training Coordinator at BSC, Barcelona (2011- 16) and was involved in PRACE Projects 1-5, as a PRACE Advanced Training Centre coordinator. She has over 17 years of experience as a PG Studies Coordinator and Research Assistant at the School of Systems Engineering and ACET (Advanced Computing and Emerging Technologies) Centre at the University of Reading, at BSC and now at STFC. Her research is in the area of collaborative learning in technology-rich environments in university education and professional training and developing evaluation methodologies for professional training programs. She co-edited and co-authored the book entitled Technological Advances in Interactive Collaborative Learning as well as authored 30 research papers in journals and peer-reviewed conference proceedings, up to date. She is a co-chair of a number of training and education related workshops on HPC and Computational Science Conferences. Andrew Jones (Microsoft) Andrew works on future HPC & AI capabilities for Azure, as part of the corporate engineering & product group. He joined Microsoft in early 2020, after nearly 25 years experience in the supercomputing community. Andrew has been an HPC end-user, researcher, software developer, HPC service manager, and impartial consultant. He has been a trusted voice on HPC strategy, technology evaluation and benchmarking, metrics, cost/value models and more. He has been lucky to have had rare exposure to state-of-practice in a wide range of HPC services/facilities across industry, government and academia around the world. Andrew is active on twitter as @hpcnotes. Marjut Dieringer (NVIDIA) Marjut manages NVIDIA’s Deep Learning Institute (DLI) in EMEA. In her role, Marjut is responsible for advising corporations, universities, and governments on the importance of AI and why now is the right time for employees to start developing their skills. Over the past four+ years, she has helped over 5000 organizations educate their staff. Kevin McFall (NVIDIA) Kevin McFall contributes to the NVIDIA Deep Learning Institute (DLI) as a Master Instructor by teaching workshops and supporting DLI certified instructors in the Europe, Middle East, and Africa region. He applies his prior academic experience as an educator and scholar to making the student experience in DLI workshops engaging and informative. His areas of expertise span computer vision, robotics, and autonomous systems. Kjartan Thor Wikfeldt (EuroCC National Competence Center Sweden) Thor has an academic background in computational chemistry and materials science. After obtaining his Ph.D. from Stockholm University in 2011 he worked as a postdoc first at University College London and then the University of Iceland, before returning to a researcher position at Stockholm University. In 2016 Thor jumped over to HPC and worked as an application expert in molecular dynamics at the PDC HPC center at KTH. During this time he became increasingly drawn towards teaching workshops and developing training material, both at PDC and within the CodeRefinery project. Thor is passionate about helping researchers write better and more scalable code with less effort, is helping to build a community of research software engineers in the Nordics through the Nordic-RSE initiative, and enjoys programming in Julia. Mozhgan Chimeh (NVIDIA) Dr Mozhgan Kabiri Chimeh is a GPU developer advocate at NVIDIA helping to bring GPU and HPC to growing user community in Europe and around the world. She is a community builder with a passion for open source software and is actively involved in the HPC and RSE communities. As a Software Sustainability Institute fellow, and Research Software Engineer (RSE) advocate, she is actively promoting reproducible and sustainable software, use of HPC and particularly GPUs through training, seminars, research software consultancy and outreach. Prior to joining Nvidia, Mozhgan was a Research Software Engineer in Massive Scale Complex Systems Simulation with Accelerated Computing at the University of Sheffield, UK. She worked in the area of complex system modelling using emerging high-performance parallel architectures. Mozhgan served as the chair of the women in HPC series of workshops at the International Supercomputing Conference and was on the organizing and program committee of leading conferences in the HPC field. She holds a Ph.D. in computer science and a master's degree in Information Technology from the University of Glasgow, UK. Weronika Filinger (Edinburgh Parallel Computing Centre (EPCC)) Weronika Filinger is an HPC Applications Consultant working at EPCC, The University of Edinburgh. She has been deeply involved in the design and development of the first Massive Open Online Course (MOOC) on Supercomputing and facilitated all runs of the course. She is teaching Practical Introduction to HPC – a postgraduate online course offered by the University of Edinburgh. For years Weronika has been a member of the EPCC outreach team, taking HPC related activities to public events. She is serving as the co-chair of the Outreach Committee of the ACM SIGHPC Education Chapter and the publicity chair of the International HPC Certification Program. She is also involved in running the International HPC Summer School. Over the years she has worked on a number of collaborative projects such as CRESTA, ADEPT, APES, SARGASSO and DEEP-EST, and provided consultancy for the Software Sustainability Institute. Julia Mullen (MIT Lincoln Laboratory) Dr. Julie Mullen is a member of the technical staff in the MIT Lincoln Laboratory Supercomputing Center (LLSC), where she assists researchers in maximizing their use of high-performance computing resources in order to minimize their time to solution. As an expert in high-performance computing for computational engineering applications, she focuses on redesigning scientific workflows to streamline processing and improve the performance of computational engineering applications. Dr. Mullen leads the design and creation of online professional education courseware for the LLSC. As part of this effort, she facilitates the development of new tools for the Open edX platform to provide support for online Laboratory courseware. Her research includes learning analytics for adaptive learning design and the integration of hands-on physical construction and experimentation with massive open online course technologies. Her work has been published in both the scientific computing and educational domains. Ann Backhaus (Pawsey Supercomputing Centre) Ann Backhaus has a passion for lifelong learning. Ann lives this passion, as exampled by her doing a ‘refresher’ Teaching and Learning Graduate Certificate “for fun” before joining Pawsey in 2019, even though she already had previous degrees as well as 25 years of experience in training and talent development in private industry and academia. “I enjoy teaching and learning at all levels and in all forms, from designing programs to developing content across a range of platforms,” says Ann. Richard Lawrence (Texas A&M University) Richard Lawrence obtained his Bachelor’s degree from the University of California, Davis in 2012 and his Master’s degree in 2018 from Texas A&M University, both in Physics. He has been a graduate student at Texas A&M University since 2014 pursuing his Ph.D., currently in progress. He works under the supervision of his advisor David Toback on a joint project between the Cryogenic Dark Matter Search collaboration and the Quantum Information Science group at Pacific Northwest National Laboratory, studying cryogenic silicon devices. Richard joined the High Performance Research Computing Group at Texas A&M University in 2020 as a User Support Specialist to assist with software maintenance and training for scientific research. He is interested in high-performance computing technologies including containers and machine learning. In his spare time Richard volunteers for a local Girl Scouts troop. Abstract Abstract HPC is central for empowering progress in diverse scientific and non-scientific domains. A myriad of technologies in the post peta-scale computing demand a significantly greater degree of parallelism than we currently observe. The rapid advancement of new HPC technologies has facilitated the convergence of Artificial Intelligence (AI), Big Data Analytics, and the HPC platforms to solve complex, large-scale, real-time analytics and applications for scientific and non-scientific fields. As we move towards exascale, the convergent computing platforms along with a paradigm shift in the programming applications for them provide both challenges and opportunities, for cyberinfrastructure facilitators and educators to prepare and support a diverse community of professionals to utilize evolving HPC, equipping them to solve complex scientific, engineering, and technological problems. Workshop Website https://sighpceducation.acm.org/events/HETET21.html pdfFriday 2:00pm-6:00pm Workshop Machine Learning on HPC Systems Janis Keuper (Fraunhofer Institut für Techno- und Wirtschaftsmathematik ITWM; Institute for machine Learning and Analytics (IMLA), Offenburg University); Sunna Torge (TU Dresdden); Jenia Jitsev (Institute for Advanced Simulation (IAS)); Juan Jose Durillo (Leibniz Supercomputing Centre); Dennis Hoppe (HLRS); Daniel Soudry (Technion); Jenia Jitsev (Juelich Supercomputer Center); Nico Hoffmann (TU Dresden); Stefanie Günther (LLNL); Ahmed Elnaggar (TU Munich); Kalun Ho (Fraunhofer Center HPC); Niranjan Hasabnis (Intel); Mathias Esteban and Jonathan Muraña (Universidad de la República); and Peter Winkler (TU Dresden) Biographies Biographies Janis Keuper (Fraunhofer Institut für Techno- und Wirtschaftsmathematik ITWM; Institute for machine Learning and Analytics (IMLA), Offenburg University) Janis Keuper is full professor for Data Science and Analytics at the Institute for Machine Learning and Analytics (IMLA), Offenburg University and scientific advisor at the "Large Scale Machine Learning" group at the Fraunhofer Competence Center for High Performance Computing. His current research is focused on scalable machine learning systems, especially Deep Learning. Before joining IMLA in 2019, he was a Group Leader at Fraunhofer ITWM and the Intel Visual Computing Institute (Saarbrücken, Germany). Janis was the chair of the Deep Learning tracs at the ISC Supercomputing 2017 and 2018 conference and member of the organizing committee of the "Machine Learning in HPC" Workshop at the ACM Supercomputing 2018/2019 conferences. Sunna Torge (TU Dresdden) Sunna Torge is a senior researcher in the national AI and Big Data competence center ScaDS.AI Dresden/Leipzig at ZIH (TU Dresden). She obtained a diploma in mathematics (minor physics) from the University of Freiburg and a PhD in computer science with focus on mathematical logic and automated deduction. After working in the research group man-machine-interface at Sony International (Europe) and the machine learning group at University of Freiburg she was a full professor for theoretical computer science at the University of Applied Science Furtwangen. After her move to Dresden Sunna Torge worked in machine learning and data analytics groups within the TU Dresden and Fraunhofer Institute for Transportation and Infrastructure Systems with focus on text data analytics. Her main research topics currently are text and sequence analysis on large data sets. Jenia Jitsev (Institute for Advanced Simulation (IAS)) TBA Juan Jose Durillo (Leibniz Supercomputing Centre) PD Dr. Juan José Durillo Barrionuevo (male) received the MSc and PhD degrees in computer science from the University of Málaga in 2006 and 2011. From 2011 to 2017, he worked as Assistant Professor at UIBK (Austria), where he also did his habilitation work focusing on workflow scheduling as the main topic. He has authored more than 50 publications in international journals, conferences and books. As a lecturer, he taught courses on optimisation, operating systems, GPU programming and C++. Since 2018, he has worked as a scientist at the BADW-LRZ. His research interests include automatic tuning of scientific applications, workflow scheduling, multi-criteria optimisation, GPU computing, and artificial intelligence. Dennis Hoppe (HLRS) -TBA- Daniel Soudry (Technion) Daniel is an assistant professor and in the Electrical Engineering Department at the Technion, working in the areas of machine learning and neural networks. His recent works focus on resource efficiency and implicit bias in neural networks. He did his post-doc working with Prof. Liam Paninski in the Department of Statistics and the Center for Theoretical Neuroscience at Columbia University, and his Ph.D. in the Electrical Engineering Department at the Technion. He is the recipient of the Gruss Lipper Fellowship, the Taub Fellowship, the Goldberg Award, and Intel's Rising Star Faculty Award. Nico Hoffmann (TU Dresden) Nico Hoffmann, young investigator group leader. Nico earned his PhD in 2016 from Technische Universität Dresden in medical image analysis. He developed statistical machine learning methods for analysis of intraoperative neuroimaging data of the exposed human brain. He visited the Laboratory of Mathematics in Imaging of Harvard University from 2018 to 2019. During that time, he developed recurrent convolutional neural networks for reconstruction of nerve fibre bundles of the human brain. He is currently heading a Helmholtz AI Young Investigators Group at Helmholtz-Zentrum Dresden-Rossendorf “AI for Future Photon Sciences” researching Physics-guided Neural Networks for PDE learning as well as inverse problems. Stefanie Günther (LLNL) TBA Ahmed Elnaggar (TU Munich) Ahmed Elnaggar is a Ph.D. candidate at the Technical University of Munich. His main focus of research is self-supervised learning on various modalities (Text, Protein, Source code, Images, and speech) using high-performance computing. Kalun Ho (Fraunhofer Center HPC) TBA Niranjan Hasabnis (Intel) TBA Mathias Esteban (Universidad de la República) TBA Jonathan Muraña (Universidad de la República) TBA Peter Winkler (TU Dresden) TBA Abstract Abstract Over the last few years, Machine Learning (and in particular Deep Learning) (ML / DL) has become an important research topic in the High Performance Computing (HPC) community. This comes along with new users and data intensive applications on HPC systems, which increasingly affects the design and operation of compute infrastructures. Bringing new users and data intensive applications on HPC systems, Learning methods are increasingly affecting the design and operation of compute infrastructures. On the other hand, the learning community is just getting started to utilize the performance of HPC, leaving many opportunities for better parallelization and scalability. The intent of this workshop is to bring together researchers and practitioners from all communities to discuss three key topics in the context of High Performance Computing and learning methods: parallelization and scaling of ML / DL algorithms, learnig applications on HPC systems, and HPC systems design and optimization for ML / DL workloads. Workshop Website http://www.MLHPCS.org pdfFriday 2:00pm-6:00pm Workshop ISC'21 SuperCompCloud: 4th International Workshop on Interoperability of Supercomputing and Cloud Technologies Sadaf Alam (Swiss National Supercomputing Centre); David Hancock (Indiana University); François Tessier (INRIA); David Y. Hancock (Indiana University); Nic Bellingham (UK Met Office); Stig Telfer (StackHPC); Andrew Jones (MS Azure); Mallikarjun (Arjun) Shankar (ORNL); Bjoern Enders and Gabor Torok (NERSC, LBNL); and Christopher Haine (HPE HPC/AI EMEA Research Lab) Biographies Biographies Sadaf Alam (Swiss National Supercomputing Centre) Sadaf R. Alam is Chief Technology Officer (CTO) at the Swiss National Supercomputing Centre (CSCS) in Lugano, Switzerland. Dr. Alam studied computer science at the University of Edinburgh, UK, where she received her Ph.D. in 2004. Until March 2009, she was a computer scientist at the Oak Ridge National Laboratory, USA. In her role as the CTO, she ensures end-to-end integrity of HPC systems and storage solutions and leads strategic projects at the centre. She has held different roles at CSCS including group lead of future systems, chief architect and head of operations. She is a member of ACM, ACM-W, SIGHPC and Women in HPC. David Hancock (Indiana University) David Hancock is the director for advanced cyberinfrastructure in IU's Research Technologies division. Hancock is responsible for directing IU's local and national high performance computing (HPC), storage, and cloud resources for research. Hancock is the primary investigator for the Jetstream project funded by the National Science Foundation (NSF). He is also responsible for directing IU system administrators who participate in the NSF XSEDE and Wrangler projects. Hancock is an active member in multiple HPC community organizations and currently a member on the board of the Cray User Group where he has served as president and vice president. Hancock is also an elected member of the XSEDE Advisory Board, and a representative in the XSEDE Service Provider (SP) Forum. Previously he served as the vice president for the IBM HPC User Group (SPXXL) and vice chair of the XSEDE SP Forum. François Tessier (INRIA) François Tessier has been a Research Scientist at Inria (Rennes, France) since November 2020. He received a Ph.D in Computer Science in 2015 from University of Bordeaux. His thesis focused on topology and affinity-aware process placement and load balancing algorithms for large-scale applications. From 2016 to 2018, he was a postdoctoral appointee at Argonne National Laboratory, IL, USA, within the LCF division (Leadership Computing Facility) where his research work has been more oriented towards I/O optimization in parallel libraries. Before joining Inria, he was a Computational Scientist at ETH Zürich within CSCS (Swiss National Supercomputing Center) located in Lugano, Switzerland, where he addressed the problem of dynamically provisioning of storage resources for HPC applications and large-scale workflows on supercomputers. At Inria, he is now working on various I/O and storage challenges in a context of HPC/Cloud convergence. David Y. Hancock (Indiana University) David Hancock is the director for advanced cyberinfrastructure in IU's Research Technologies division. Hancock is responsible for directing IU's local and national high performance computing (HPC), storage, and cloud resources for research. Hancock is the primary investigator for the Jetstream project funded by the National Science Foundation (NSF). He is also responsible for directing IU system administrators who participate in the NSF XSEDE and Wrangler projects. Hancock is an active member in multiple HPC community organizations and currently a member on the board of the Cray User Group where he has served as president and vice president. Hancock is also an elected member of the XSEDE Advisory Board, and a representative in the XSEDE Service Provider (SP) Forum. Previously he served as the vice president for the IBM HPC User Group (SPXXL) and vice chair of the XSEDE SP Forum. Nic Bellingham (UK Met Office) Nic Bellingham joined the Met Office as a graduate in 1992 with a degree in Mathematics & Computer Science. Most of her career has been in IT-focused roles, from developing mainframe and PC applications to working with the Programme that will deliver the Met Office’s Supercomputing capability through to 2032. In 2012 she moved from software engineering into an IT Service Management role, with responsibility for the delivery of a range of operational services, including forecaster applications and public and commercial web offerings. From 2014 to 2016, Nic was Deputy Head of IT Infrastructure & Operations with day-to-day responsibility for all Met Office IT services. In late 2016, she became Head of IT Infrastructure & Operations, leading the delivery of the Met Office IT estate and associated services. Since April 2019 Nic has been seconded to the Met Office’s Supercomputing Programme, leading the engagement with the Programme from the organisation’s Technology directorate. Stig Telfer (StackHPC) Stig has a background in R&D working for various prominent technology companies, particularly in HPC and software-defined networking. Stig is now CTO for StackHPC, a consultancy specialising in the convergence of cloud, HPC and big data. Stig is also co-chair of the OpenStack Scientific Special Interest Group, a globally-distributed grouping of research institutions using OpenStack for research computing use cases Andrew Jones (MS Azure) Andrew leads planning of future capabilities for HPC & AI within Microsoft Azure, as part of the corporate engineering & product group. He joined Microsoft in early 2020, after nearly 25 years experience in the supercomputing community. Andrew has been an HPC end-user, researcher, software developer, HPC service manager, and impartial consultant. He has been a trusted voice on HPC strategy, technology evaluation and benchmarking, metrics, cost/value models and more. He has been lucky to have had rare exposure to state-of-practice in a wide range of HPC services/facilities across industry, government and academia around the world. Andrew is active on twitter as @hpcnotes. Mallikarjun (Arjun) Shankar (ORNL) Arjun Shankar is a distinguished staff member and the section head for Advanced Technologies in the National Center for Computational Sciences at Oak Ridge National Laboratory (ORNL). He also directs the Compute and Data Environment for Science (CADES) institutional computing capability at ORNL. Arjun’s research in the national laboratory setting has involved designing large-scale data analysis and modeling systems, sensor networking systems, energy grid monitoring and control frameworks, and deploying middleware to overlay data, computation, and control across systems and infrastructure. His sponsored R&D project outputs have several active users in the federal government as well as in the commercial sector. His research has resulted in over seventy peer-reviewed publications including those that address jointly modeling and simulating systems coupled with observational data, incorporating policy constraints, and creating scalable cross-facility data infrastructures. Arjun received his B.Tech. from the Indian Institute of Technology, Mumbai, and his M.S. and Ph.D. in computer science from the University of Illinois, Urbana. He has served on the DOE ASCAC subcommittee on Scientific and Technical Information, is a member of the AAAS, and a Senior Member of the ACM and the IEEE. Bjoern Enders (NERSC, LBNL) Bjoern Enders joined NERSC in 2019 as a Data Science Workflows Architect in the Data Science Engagement Group where he liaises with various large-scale experimental facilities, engages with the wider scientific workflows community and contributes to NERSC's API efforts. He works towards a future where HPC resources integrate seamlessly and effortlessly into experimental science workflows. Bjoern has a background in software development for experimental sciences with a specialization for computational microscopy at synchrotron light sources. He holds a PhD in Physics from the Technical University of Munich, Germany and a MSc equivalent degree in physics from the University of Goettingen, Germany. Gabor Torok (NERSC, LBNL) Gabor has decades of experience building, maintaining and debugging large-scale web applications. He started his career at Berkeley Lab in the 1990-s. A few years later, he worked as a back-end and fullstack software engineer for various start-ups and larger companies. After about 20 years in the private sector, he is now working for NERSC and couldn't be more excited to use his experience to make computing for science run smoother. Gabor's recent contributions are Iris, the NERSC banking and account management system, as well as the Superfacility API which allows for programmatic access to NERSC resources. Christopher Haine (HPE HPC/AI EMEA Research Lab) Christopher Haine earned in 2017 a Ph.D. from the University of Bordeaux, on the topic of loop kernel optimisation and data layout restructuring. Christopher then joined Cray (now HPE) in the HPC/AI EMEA Research Lab, where he focuses on data-aware middleware, data movement in complex memory hierarchies, and optimisation and programmability of scientific applications and workflows. Abstract Abstract Imminent arrival and deployment of exascale systems among multiple hyperscaler cloud providers are expected to enable breakthroughs for various scientific disciplines. Increasingly, these systems utilize cloud technologies, enabling complex and distributed workflows that improve not only scientific productivity, but accessibility of resources to a wide range of communities. Such an integrated and seamlessly orchestrated system for supercomputing and cloud technologies is indispensable for experimental facilities that have been experiencing an unprecedented rate of data growth. While limited-scale HPC services has been available in public cloud environments, petascale and beyond data and computing capabilities are provisioned within HPC data centers using close-to-metal provisioning services to ensure performance, scaling, and cost effectiveness. This workshop aims to bring together experts and practitioners from academia, national laboratories and industry to discuss technologies, use cases and best practices in order to set a vision and direction for leveraging extreme-scale computing and on-demand cloud ecosystems. Friday 2:00pm-6:00pm Workshop 2nd ISC-HPC International Workshop on “Monitoring and Operational Data Analytics” (MODA) Florina Ciorba (University of Basel); Daniele Tafani (Fujitsu, Germany); Utz-Uwe Haus (Cray EMEA Research Lab); Nicolas Lachiche (University of Strasbourg); Ann Gentile (Sandia National Laboratories); Natalie Bates (Energy Efficiency HPC WG); Torsten Wilde (HPE); Aleš Zamuda (University of Maribor); Martin Molan (University of Bologna); and Masaaki Terai (RIKEN Centre for Computational Science) Biographies Biographies Florina Ciorba (University of Basel) Florina Ciorba is an Associate Professor of High Performance Computing at the University of Basel, Switzerland. She received her Diploma in Computer Engineering in 2001 from University of Oradea, Romania and her doctoral degree in Computer Engineering in 2008 from National Technical University of Athens, Greece. She has held postdoctoral research associate positions at the Center for Advanced Vehicular Systems at Mississippi State University, Mississippi State, USA (2008 to 2010) and at the Center for Information Services and High Performance Computing at Technische Universität Dresden, Dresden Germany (2010-2015). Her research interests include parallelization, dynamic load balancing, loop scheduling, robustness, resilience, scalability, reproducibility of scientific applications executing on small to large scale parallel computing systems, and system and application monitoring for improving their operations. More information at https://hpc.dmi.unibas.ch/en/people/florina-ciorba/ Daniele Tafani (Fujitsu, Germany) Daniele Tafani received his PhD in Electronic Engineering from Dublin City University (DCU) in 2012, where he conducted research on analytic modelling and resource optimisation of optical burst switched networks. He worked at the IBM Tivoli Rome Labs as a software engineer, and was a visiting researcher at the University of Ottawa, where he developed algorithms for energy-efficient light paths in computational grids. Daniele spent 8 years as a research scientist in the High-Performance Systems division of the Leibniz Supercomputing Centre (LRZ), focusing his interests on energy efficiency of HPC systems, scalable sensor monitoring and operational data analytics. He is now Technical Product Manager at Fujitsu. Utz-Uwe Haus (Cray EMEA Research Lab) Utz-Uwe Haus is a Senior Research Engineer at CRAY. He studied Mathematics and Computer Science at the TU Berlin. After obtaining a Doctorate in Mathematics at the University of Magdeburg he worked on nonstandard applications of Mathematical Optimization in Chemical Engineering, Material Science and Systems Biology. After 5 years as a Senior Researcher at the Department of Mathematics at ETH Zürich he is now leading the Cray European Research Lab in Basel, developing the Mathematical Optimization and Operations Research group, working on data-dependency driven workflow optimization on future HPC architectures. Nicolas Lachiche (University of Strasbourg) Nicolas Lachiche received his PhD in Computer Science from the University of Nancy, France in 1997, where he conducted research on machine learning. After a postdoc at the University of Bristol, he joined the University of Strasbourg as an associate professor. He is the head of the Data Science and Knowledge research group in the ICube laboratory. His research interests are in mining relational or sequential data. Ann Gentile (Sandia National Laboratories) Ann Gentile is the Manager of the HPC Development Department at Sandia National Laboratories. Prior to that, she was a Distinguished Member of Technical Staff and she continues her interests in Resource-Aware Computing in her current role. Ann is a co-author of the R&D 100 award-winning, open source Lightweight Distributed Metric Service (LDMS) which is deployed at large-scale HPC sites within the US national labs and the NSF for monitoring and resource utilization understanding on large-scale HPC systems. HPE/Cray has implemented LDMS in its monitoring solution to be part of every currently announced NNSA exascale machine. Ann serves on investment area teams determining priorities for Sandia’s Computational CoDesign and Trusted AI Research and on evaluation teams of extreme-scale architectures for the US national labs. Ann is also a co-founder of the Workshop on Monitoring and Analysis for High Performance Computing Systems Plus Applications (HPCMASPA), now in its 9th year held in conjunction with IEEE Cluster. She earned her Ph.D. in Chemical Physics and M.S. in Chemistry from UIUC and her B.S. in Physics from Carnegie-Mellon University. Natalie Bates (Energy Efficiency HPC WG) Natalie Bates has led the Energy Efficient High Performance Computing Working Group (EE HPC WG) since its inception in 2010. The purpose of the WG is to drive implementation of energy efficient design in HPC. Today, there are ~800 members from 25+ countries. Natalie has been the technical and executive leader for this ‘open source’ working group that disseminates best practices, shares information (peer to peer exchange), and takes collective action. The EE HPC WG has collaborated and negotiated with industry standards committees and major HPC organizations as well as influenced HPC system development. Prior to leading the EE HPC WG, Natalie's career spanned twenty years with Intel Corporation where she was a senior manager of highly complex programs taking new products to market, delivering multi-component and multi-partner platforms, and negotiating strategic technical industry initiatives. Torsten Wilde (HPE) Torsten is a system architect for Exascale monitoring and system power and energy management at Hewlett Packard Enterprise (HPE). His research activities are related to high volume, high frequency data collection and analytics for improved IT operations as well as dynamic power management. He is the lead architect for HPE's Exascale monitoring framework developed as part of the ECP funded PathForward project. Torsten is part of the leadership team of the Energy Efficient High Performance Computing Working Group (EE HPC WG) and currently serves as the Workshop and Conferences Co-Chair. Torsten received his MSc in parallel and scientific computation from the University of Liverpool, UK, and a MSc in Computer Engineering from the University of Applied Sciences in Berlin, Germany. He received his Dr. rer. nat. degree in computer science from the Technical University of Munich, Germany, in 2018. Aleš Zamuda (University of Maribor) Ales Zamuda received his B.Sc., M.Sc., and Ph.D. degrees in computer science from University of Maribor, Slovenia, in 2006, 2008, and 2012, respectively. As an affiliate of Faculty of Electrical Engineering and Computer Science at the University of Maribor he acts within research group Computer Architecture and Languages Laboratory and programme-funded unit Computer Systems, Methodologies, and Intelligent Services. His areas of interest include evolutionary algorithms, multicriterion optimization, artificial life, and computer animation. He has written over 50 scientific papers and among them several journal papers ranked in first quarter of computer science category such as Applied Soft Computing and Information Sciences and received several citations of his scientific works. Martin Molan (University of Bologna) Martin Molan is a PhD student of data science and computation at University of Bologna. He has received BA in mathematics at University of Ljubljana and MA in ICT at JSI institute. As a student he has collaborated with CERN openlab, UCL center for AI, UNESCO International Research Center On Artificial Intelligence, and CINECA. Masaaki Terai (RIKEN Centre for Computational Science) Coming Soon... Abstract Abstract This workshop aims to provide insight into the current state and trends in Monitoring and Operational Data Analytics (MODA), to identify potential gaps, and to offer an outlook into the future of MODA at a large scale together with possible solutions for the upcoming Exascale systems. The focus of the MODA21 workshop will be on currently envisioned solutions and best practices for monitoring systems at data centers and HPC sites, as well as on effective strategies for analyzing and interpreting the collected operational data. The workshop is unique to the European HPC arena in addressing these topics. We envision a balanced mix between a keynote address, peer-reviewed technical paper presentations, invited talks, and a panel discussion. Workshop Website https://moda21.sciencesconf.org/ pdfFriday 2:00pm-6:00pm Workshop 16th Workshop on Virtualization in High-Performance Cloud Computing Michael Alexander (BOKU, Vienna); Anastassios Nanos (Nubificus Ltd.); Anastasios Nanos and Charalampos Mainas (Nubificus LTD); Panagiotis Kokkinos (ICCS/NTUA); Yiannis Gkoufas and David Yu Yuan (IBM Research, Ireland); Sezar Jarrous-Holtrup (University of Münster,); Folker Schamel (Spinor GmbH, Germany); Argyrios Kokkinis (Aristotle University of Thessaloniki, Greece); Achilleas Tzenetopoulos (National Technical University of Athens); Remo Andreoli (Scuola Superiore Sant'Anna, Italy); Ricardo Rocha and Maria Girone (CERN); and Stefan Hajnoczi (Red Hat Research) Biographies Biographies Michael Alexander (BOKU, Vienna) Michael Alexander holds degrees in electrical engineering (TGM), business administration (University of Southern California) and economics (University of Vienna). He is currently performing large data analytics for multiple domains and the architecting of clusters. His professional experience includes education and product management at IBM, and Alcatel. Prior he was a HPC Specialist at TU Wien and a Product Line Manager for Alcatel ADSL and Optical Access Networks. He is the author of a textbook on networks and network security published by Hüthig/Verlagsgruppe Süddeutsche, and editor of a special issue on mathematical methods in network management of the Wiley International Journal of Network Management. For the last sixteen years, he has served as the Program Committee Chair for VHPC, Workshop on Virtualization in High-Performance Cloud Computing. His current research interests include content centric networking, distributed databases, virtualization system-network management. Anastassios Nanos (Nubificus Ltd.) With over 12 years of experience in Virtualization technologies, Anastassios Nanos is currently working on the lower-level parts of the stack to attack issues related to performance, scalability, power-efficiency, and security in hypervisors. Previously, he was a post-doc at CSLab, NTUA, working on bridging the gap between common HPC practices and virtualization. His research interests include I/O Virtualization, systems software for high-performance I/O in virtualized environments, systems support for heterogeneous platforms, communication architectures for clusters, and scalable storage architectures based on clusters. He holds a Diploma in Engineering (2006) from ECE, NTUA and a PhD in Computer Engineering (2013) from NTUA. He has been involved in EU-funded projects, conducting research in emerging, power-efficient micro-server architectures on scalable network and storage I/O, and energy-driven resource management in cloud architectures. Anastasios Nanos (Nubificus LTD) With over 12 years of experience in Virtualization technologies, Anastassios Nanos is currently working on the lower-level parts of the stack to attack issues related to performance, scalability, power-efficiency, and security in hypervisors. Previously, he was a post-doc at CSLab, NTUA, working on bridging the gap between common HPC practices and virtualization. His research interests include I/O Virtualization, systems software for high-performance I/O in virtualized environments, systems support for heterogeneous platforms, communication architectures for clusters, and scalable storage architectures based on clusters. He holds a Diploma in Engineering (2006) from ECE, NTUA and a PhD in Computer Engineering (2013) from NTUA. He has been involved in EU-funded projects, conducting research in emerging, power-efficient micro-server architectures on scalable network and storage I/O, and energy-driven resource management in cloud architectures. Charalampos Mainas (Nubificus LTD) TBU Panagiotis Kokkinos (ICCS/NTUA) TBU Yiannis Gkoufas (IBM Research, Ireland) TBU David Yu Yuan (IBM Research, Ireland) TBU Sezar Jarrous-Holtrup (University of Münster,) TBU Folker Schamel (Spinor GmbH, Germany) TBU Argyrios Kokkinis (Aristotle University of Thessaloniki, Greece) TBU Achilleas Tzenetopoulos (National Technical University of Athens) TBU Remo Andreoli (Scuola Superiore Sant'Anna, Italy) TBU Ricardo Rocha (CERN) TBU Maria Girone (CERN) TBU Stefan Hajnoczi (Red Hat Research) TBU Abstract Abstract Containers and virtualization technologies constitute key enabling factors for flexible resource management in modern data centers, and particularly in cloud environments. HPC operators and cloud providers need to manage complex infrastructures in a seamless fashion to support the highly dynamic and heterogeneous workloads and hosted applications customers deploy. Various virtualization-containerization technologies contribute to the overall picture in different ways: machine virtualization, with its capability to enable consolidation of multiple underutilized servers with heterogeneous software and operating systems (OSes), and its capability to live-migrate a fully operating virtual machine (VM) with a very short downtime, enables novel and dynamic ways to manage physical servers; OS-level virtualization (i.e., containerization), with its capability to isolate multiple user-space environments and to allow for their coexistence within the same OS kernel, promises to provide many of the advantages of machine virtualization with high levels of responsiveness and performance; lastly, unikernels provide for many virtualization benefits with a minimized OS/library surface. The Workshop on Virtualization in High-Performance Cloud Computing (VHPC) aims to bring together researchers and industrial practitioners facing the challenges posed by virtualization, containerization, and orchestration techniques for deploying HPC and HPC-like applications in large data centers. Workshop Website https://vhpc.org pdfFriday 2:00pm-6:00pm Workshop Deep Learning on Supercomputers Valeriu Codreanu (SURFsara); Ian T. Foster (University of Chicago, Argonne National Laboratory); Zhao Zhang (Texas Advanced Computing Center); Torsten Hoefler (ETH Zurich); Arvind Ramanathan (Argonne National Laboratory); Alexandre Bonvin and Manon Réau (Utrecht University); Stefan Kesselheim (Jülich Supercomputing Center); Jonas Teuwen (Netherlands Cancer Institute); and Chen Liu (SambaNova Systems) Biographies Biographies Valeriu Codreanu (SURFsara) Valeriu Codreanu studied Electrical Engineering and got his MSc at the Polytechnic University of Bucharest. He followed-up with a PhD in Computer Architecture at the same institute, graduating in 2011. Valeriu continued as a researcher at Eindhoven University of Technology and University of Groningen, working on GPU computing, computer vision, and embedded systems. In 2014, he joined SURFsara as an HPC consultant, and in 2016 he became the PI of an Intel Parallel Computing Center project on ‘Scaling up deep learning’. Valeriu is currently leading the High-Performance Machine Learning group at SURFsara, and is focused on applying deep learning techniques to real-world applications from various scientific fields. Ian T. Foster (University of Chicago, Argonne National Laboratory) Dr. Ian Foster is the Director of Argonne’s Data Science and Learning Division, Argonne Senior Scientist and Distinguished Fellow and the Arthur Holly Compton Distinguished Service Professor of Computer Science at the University of Chicago. Foster’s research contributions span high-performance computing, distributed systems, and data-driven discovery. He has published hundreds of scientific papers and eight books on these and other topics. Methods and software developed under his leadership underpin many large national and international cyberinfrastructures. Foster received a BSc (Hons I) degree from the University of Canterbury, New Zealand, and a PhD from Imperial College, United Kingdom, both in computer science. His awards include the Global Information Infrastructure (GII) Next Generation award, the British Computer Society’s Lovelace Medal, R&D Magazine’s Innovator of the Year, the IEEE Tsutomu Kanai award. Zhao Zhang (Texas Advanced Computing Center) Dr. Zhao Zhang is a computer scientist at Texas Advanced Computing Center. His current research focus is scalable deep learning on supercomputers. Dr. Zhang's past work include astronomy data processing with Apache Spark, machine learning diagnostics, and I/O optimization for many-task computing applications on supercomputers, such as Argonne's IBM Blue Gene/P. Before joining TACC, Dr. Zhang was a postdoc researcher in AMPLab and a data science fellow at Berkeley Institute for Data Science at University of California, Berkeley, working with Prof. Michael J. Franklin. He received Ph.D in computer science from University of Chicago in 2014 under supervision of Prof. Ian T. Foster. Torsten Hoefler
Arvind Ramanathan
Alexandre Bonvin
Manon Réau
Stefan Kesselheim
Jonas Teuwen (Netherlands Cancer Institute) Jonas is currently the "AI for Oncology" group leader at the Netherlands Cancer Institute. Previously, after his studies in Applied Mathematics at the Delft University of Technology he completed his PhD titled "Shedding new light on Gaussian harmonic analysis" at the same university. He started as a postdoctoral researcher in 2016 at the Netherlands Cancer Institute/Antoni van Leeuwenhoek hospital and continued within the Diagnostic Image Analysis Group at the Radboud Medical Center. His current work focuses on efficient deep learning algorithms for cancer detection in breast image modalities. Chen Liu
Abstract Abstract The Deep Learning (DL) on Supercomputers workshop provides a forum for practitioners working on any and all aspects of DL for science and engineering in the High Performance Computing (HPC) context to present their latest research results and development, deployment, and application experiences. The general theme of this workshop series is the intersection of DL and HPC; the theme of this particular workshop is the applications of DL methods in science and engineering: novel uses of DL methods, e.g., convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), and reinforcement learning (RL), in the natural sciences, social sciences, and engineering, to enhance innovative applications of DL in traditional numerical computation. Its scope encompasses application development in scientific scenarios using HPC platforms; DL methods applied to numerical simulation; fundamental algorithms, enhanced procedures, and software development methods to enable scalable training and inference; hardware changes with impact on future supercomputer design; and machine deployment, performance evaluation, and reproducibility practices for DL applications with an emphasis on scientific usage. This workshop will be centered around published papers. Submissions will be peer-reviewed, and accepted papers will be published as part of the Joint Workshop Proceedings by Springer. Workshop Website https://dlonsc.github.io/ pdfFriday 2:00pm-6:00pm Workshop 2nd International Workshop on Machine Learning Hardware Pete Beckman and Swann Perarnau (Argonne National Laboratory), Rosa M. Badia (Barcelona Supercomputing Center), Kentaro Sano (RIKEN), Valentin Reis (Groq), Prasanna Balaprakash (ANL), Rob Schreiber (Cerebras), Tony Hey (STFC), Michaela Blott (Xilinx), Tianjian Lu (Google Research), Haohuan Fu (Tsinghua University), and Takano Ryousei (AIST) Biographies Biographies Pete Beckman (Argonne National Laboratory) Pete Beckman is the co-director of the Northwestern-Argonne Institute for Science and Engineering. From 2008-2010 he was the director of the Argonne Leadership Computing Facility, where he led the Argonne team working with IBM on the design of Mira, a 10 petaflop Blue Gene/Q. Pete coordinates the collaborative research activities in extreme-scale computing between the US Department of Energy and Japan’s ministry of education, science, and technology (MEXT), and leads Argo, an Exascale Computing Project focused on low-level resource management for the OS and runtime. He is the founder and leader of the Waggle project for AI@Edge. The Waggle technology and software framework is being used by the Chicago Array of Things project and is deployed in over 10 cities around the world. Dr. Beckman has a Ph.D. in Computer Science from Indiana University (1993) Swann Perarnau (Argonne National Laboratory) Swann Perarnau is an Assistant Computer Scientist at Argonne. He leads the topology, memory and power management efforts for the Argo ECP project. In particular, he is designing low-level system software mechanisms to help applications discover the features and performance of complex heterogeneous hardware, as well as composable abstractions to make the most efficient use of it. Rosa M. Badia (Barcelona Supercomputing Center) Rosa M. Badia holds a PhD from the UPC (1994). She is the manager of the Workflows and Distributed computing group at the Barcelona Supercomputing Center (BSC). She is a Scientific Researcher at the Spanish National Research Council (CSIC). She graduated on Computer Science at the Facultat d' Informàtica de Barcelona (UPC, 1989). She was lecturing and doing research at the Computer Architecture Department (DAC) at the UPC from 1989 to 2008, where she held an Associate Professor position from 1997 to 2008; she is currently part-time lecturing again at the same department. Kentaro Sano (RIKEN) Kentaro Sano is the team leader of the Processor Research team at RIKEN. Dr. Kentaro Sano received his Ph.D. from GSIS, Tohoku University, in 2000. Since 2000 until 2005, he had been a Research Associate at Tohoku University. Since 2005 until 2018, he has been an Associate Professor at Tohoku University. He was a visiting researcher at the Department of Computing, Imperial College, London, and Maxeler corporation in 2006 and 2007. Since 2017 until present, he has been a team leader of a processor research team at R-CCS, Riken. His research interests include FPGA-based high-performance reconfigurable computing systems especially for scientific numerical simulations and machine learning, high-level synthesis compilers and tools for reconfigurable custom computing machines, and system architectures for next-generation supercomputing based on the data-flow computing model. Valentin Reis (Groq) Valentin Reis is a Software Engineer at Groq, Inc. He previously was a Postdoctoral appointee at Argonne National Laboratory and obtained his PhD from the University of Grenoble Alpes. His interests span machine learning, functional programming and HPC infrastructure. Prasanna Balaprakash
Rob Schreiber
Tony Hey
Michaela Blott
Tianjian Lu
Haohuan Fu
Takano Ryousei
Abstract Abstract Recent years have seen a surge of investment in AI chip companies worldwide. These companies are however mostly targeting applications outside of the scientific computing community. As the use of ML accelerates in the HPC field itself, there is concern that the scientific community should influence the design of this new specialized hardware. Indeed, scientific computing has a distinctive set of requirements regarding workload type, usage model, and platform administration. How those chips answer those demands will shape the future of their integration within the global scientific computing infrastructure. In this workshop, we propose to let the community and select vendors engage on questions related to the low-level aspects of this new hardware and its integration with HPC systems, as well as to the software APIs and compiler toolchains that will be available. This proposal follows the outcome of a successful ISC20 workshop where an emphasis on compiler technology emerged. In this iteration, we will push the agenda further by discussing existing efforts to leverage ML hardware for scientific HPC applications. Workshop Website https://mlhardware.github.io pdfFriday 2:00pm-6:00pm Workshop Numerical Algorithms and Libraries for Exascale Hatem Ltaief, Bilel Hadri, and David Keyes (KAUST); Daniel Grünewald (Fraunhofer ITWM); Laura Grigori (INRIA); Alfredo Buttari (CNRS-IRIT); Hartwig Anzt (Karlsruhe Institute of Technology); Ulrike Yang (Lawrence Livermore National Laboratory); and John Shalf (Lawrence Berkeley National Laboratory) Biographies Biographies Hatem Ltaief (KAUST) Hatem Ltaief is a Principal Research Scientist in the Extreme Computing Research Center at KAUST, where is also advising several KAUST students in their MS and PhD research. His research interests include parallel numerical algorithms, parallel programming models, performance optimizations for manycore architectures and high performance computing. Hatem received the engineering degree from Polytech Lyon at the University of Claude Bernard Lyon I, the MSc in applied mathematics and the PhD degree in computer science at the University of Houston. He has contributed to the integration of numerical algorithms into mainstream vendors’ scientific libraries, such as NVIDIA cuBLAS and Cray LibSci. He has been collaborating with domain scientists, i.e., astronomers, statisticians, computational chemists and geophysicists, on leveraging their applications to meet the challenges at exascale. Bilel Hadri (KAUST) Bilel Hadri is a computational scientist at the Supercomputing Lab at KAUST since July 2013. He is leading efforts in benchmarking and performance optimization and helping in coordinating strategic efforts for systems procurements, upgrades and provides regular training to users. He received his Master in Applied Mathematics and his PhD in Computer Science from the University of Houston in 2008. He joined the National Institute for Computational Science at Oak Ridge National Lab as a computational scientist in December 2009 following a Postdoctoral Position in June 2008 at the University of Tennessee Innovative Computing Laboratory lead by Dr. Jack Dongarra. His expertise area includes Linear Algebra, Numerical Analysis, Performance Analysis Tuning and Optimization, System Utilization Analysis, Monitoring and Library Tracking Usage. David Keyes
Daniel Grünewald
Laura Grigori
Alfredo Buttari
Hartwig Anzt
Ulrike Yang
John Shalf
Abstract Abstract With the hardware technology scaling and the trend on heterogeneous chip design, the existing numerical algorithms and software framework may break down due to load imbalance. There is currently a fundamental mismatch between the underlying hardware architecture with high thread concurrency and the software deployment of numerical libraries, which relies on the traditional bulk synchronous programming model. Numerical software should first squeeze performance out of single node by efficiently running on manycore architectures with processor counts sharing a common memory in the hundreds. Programming and extracting performance from these advanced architecture chips remain a challenging effort, which is further exacerbated in distributed-memory environment. Algorithmic solutions such as fine-grained computations, communication/synchronization-reducing, and mixed precisions come to the rescue. They represent some of the key ingredients to embrace for software libraries moving forward and leverage extreme-scale computing capabilities. Workshop Website https://cemse.kaust.edu.sa/hicma/events/event/isc21-workshop-numerical-algorithms-and-libraries-exascale-nal-x pdfFriday 2:00pm-6:00pm Workshop Approximate and Transprecision Computing on Emerging Technologies (ATCET) - Second Edition A. Cristiano I. Malossi (IBM Research - Zurich); Luca Benini (Dep. of Inform.Technol. Electrical Eng., ETH Zurich, Switzerland); Norbert Wehn (Dep. of Electrical and Computer Engineering, Technische Universität Kaiserslautern, Germany); Roger Woods (School of Electronics, Electrical Engineering and Computer Science, Queen's University, Belfast, United Kingdom); Andrew Emerson (Department of High Performance Computing, CINECA, Italy); Frank K. Gurkaynak (ETH Zürich); Alberto Bosio (École Centrale de Lyon); Dimitrios S. Nikolopoulos (Virginia Tech); Christos-Savvas Bouganis (Imperial College); and Enrique Salvador Quintana Ortí (Universitat Politècnica de València) Biographies Biographies A. Cristiano I. Malossi
Luca Benini
Norbert Wehn
Roger Woods
Andrew Emerson
Frank K. Gurkaynak
Alberto Bosio
Dimitrios S. Nikolopoulos
Christos-Savvas Bouganis
Enrique Salvador Quintana Ortí
Abstract Abstract Guaranteed numerical precision of each elementary step in a complex computation has been the mainstay of traditional computing systems for many years. This era is at its twilight: to overcome the “power wall” in Exascale systems, a shift from traditional computing paradigms is now mandatory. This workshop will investigate the theoretical and practical understanding of the energy efficiency boost obtainable when accuracy requirements on data being processed, stored and communicated can be lifted for intermediate calculations. The target applications range from Big Data Analytic and Deep Learning, up to classical scientific computing simulations in HPC environments. Workshop Website http://oprecomp.eu/atcet-2021 pdfFriday 2:00pm-6:00pm Workshop Arm HPC User Group (AHUG) 2021 Jonathan C. Beard (Arm Research), Jeffrey Young (Georgia Tech), Roxana Rusitoru (Arm Research), Oscar Hernandez (NVIDIA), Andrew Younge (Sandia National Lab), RuQing (G.) Xu Xu (University of Tokyo), Yuetsu Kodama (RIKEN R-CCS), Steve Messenger (Amazon), Srinath Vadlamani (Arm), Miwako Tsuji (RIKEN R-CCS), Stepan Nassyr (Juelich Supercomputing Centre), Federica Filippini (Politecnico di Milano), Andrei Poenaru (University of Bristol), John Linford (Arm), Jeff Hammond (NVIDIA), Luigi Genovese (Atomistic Simulation Laboratory (L_Sim) - CEA Grenoble), Miquel Moreto (Barcelona Supercomputing Center), Hatem Ltaief (KAUST), Bine Brank (Juelich Supercomputing Centre), Eva Siegmann (Stony Brook University), Sarat Sreepathi (Oak Ridge National Laboratory), Andrew Younge (Sandia National Laboratories), Thomas Chen (U.S. Technology Policy Committee), and Craig Prunty (SiPearl) Biographies Biographies Jonathan C. Beard (Arm Research) Jonathan is currently a staff computer architecture researcher focusing on next generation architectures for Big Data beyond exascale. Jonathan also has served as a technical advisor to many start-up companies, and has given talks ranging from C++ parallel runtimes to debating exascale memory architectures at Supercomputing. Jonathan Beard received a BS (Biology) and BA (International Studies) in 2005 from the Louisiana State University, MS (Bioinformatics) in 2010 from The Johns Hopkins University, and a PhD in Computer Science from Washington University in St. Louis in 2015. Jonathan served as a U.S. Army Officer where he served in roles ranging from medical administrator, to Aide-de-Camp, to acting director of the medical informatics department for the U.S. Army in Europe. Jonathan's research interests also include online modeling of stream/data-flow parallel systems and extremely heterogeneous systems. Jeffrey Young (Georgia Tech) Jeffrey (Jeff) Young is a research scientist in Georgia Tech's School of Computer Science and the managing director of the Arm HPC User Group. His main research interests include investigating scheduling and data movement for accelerators like GPU and Xeon Phi and working to model and map algorithms to high-performance architectures. He is currently working on a collaborative research program that is focused on mapping bandwidth-intensive algorithms to 3D stacked memories like Hybrid Memory Cube (HMC) and High Bandwidth Memory (HBM) and on performing near-memory computation on devices like FPGAs and GPUs. He received his PhD in computer engineering in 2013 from Georgia Tech's ECE department. Roxana Rusitoru (Arm Research) Roxana Rusitoru is a Senior Research Engineer in Arm’s Research division, working in Software and Large Scale Systems. She joined Arm in 2012 after obtaining an MEng degree in Computing (Software Engineering) from Imperial College London in optimising unstructured mesh CFD applications on multicores via machine learning and code transformation. At Arm, amongst others, she has worked on Linux kernel optimizations aimed at HPC and sensitivity studies aimed to showcase Arm AArch64 microprocessor characteristics suitable for HPC. Most recently, she has been working on power-aware scheduling at OS level for heterogeneous cores and methodologies to identify representative sub-sections from multi-threaded applications. Some of her research interests are software performance optimization and next-gen heterogeneous architectures. Roxana has been a part of the Mont-Blanc 1 and 2 projects, and is now leading the Software ecosystem in Mont-Blanc 3, in addition to technical contributions. Oscar Hernandez (NVIDIA) Oscar Hernandez has a Phd in Computer Science and recently joined NVIDIA/Mellanox in 2021 after working 12 years at Oak Ridge National Laboratory (ORNL) where he was a senior staff member of the Programming Systems Group, which does research on programming models, compilers and tools that are deployed at supercomputers like Summit and Frontier at the Leadership Computing Facility (OLCF). At ORNL he helped standardize parallel languages and APIs for accelerated nodes such as OpenACC/OpenMP and communication libraries and frameworks like OpenSHMEM and UCX. He also worked for the Exascale Computing Project where he led different efforts to deploy these technologies on Exascale systems. He also worked closely with application teams including the CAAR, INCITE and ALCC projects and on many projects funded by DOE, DoD, NSF, and Industrial Partners in the Oil & Gas industry.Oscar has a lot of experience giving tutorials in different venues, like Supercomputing, ISC, ECP Annual Meeting and NSF. Andrew Younge (Sandia National Lab) Andrew Younge is a R&D Computer Scientist at Sandia National Laboratories with the Scalable System Software group. His research interests include High Performance Computing, Virtualization, Distributed Systems, and energy efficient computing. The central focal point of Andrew’s work is to improve the usability and efficiency of supercomputing system software. Andrew has a Ph.D in Computer Science from Indiana University, where he was the Persistent Systems fellow and a member of the FutureGrid project, an NSF-funded experimental cyberinfrastructure test-bed. Over the years, Andrew has held visiting positions at the MITRE Corporation, the University of Southern California / Information Sciences Institute, and the University of Maryland, College Park. He received his Bachelors and Masters of Science from the Computer Science Department at Rochester Institute of Technology (RIT) in 2008 and 2010, respectively. RuQing (G.) Xu Xu (University of Tokyo) RuQing (G) Xu is a 2nd year postgrad in physics now in the University of Tokyo. (https://qsl.r-xu.dns-cloud.net). I'm primarily working on computational sciences in a solid state physics context, with special focus on variational wavefunction optimization and tensor network methods. As a result, my work is very sensitive to the performance of linear algebra libraries (BLAS-level, LAPACK-level, sparse LAPACK-level, etc.). I got to know BLIS and Arm on HPC when trying to optimize our variational quantum solver on supercomputer Fugaku. Experience working with Arm processors turned out to be smooth and fruitful, with our lab program accelerated up to ~6x and BLIS on SVE almost production-ready. Apart from performance libraries, I'm a keen user of programming language Julia. Wrappers for BLIS and TBLIS are made to exploit flexibility of BLIS framework as well as Julia language itself. Improving Julia ecosystem on aarch64 is yet another thing I want to contribute to in the coming few years. Yuetsu Kodama (RIKEN R-CCS) Yuetsu Kodama is a senior scientist at RIKEN CCS (Center for Computational Science) from 2015. He received the B.E., M.E. and Ph.D degree in engineering from the University of Tokyo in 1986, 1988 and 2003, respectively. He was a professor at University of Tsukuba in 2011-2015, a senior researcher at AIST (National Institute of Advanced Industrial Science and Technology) in 2000-2011 and a senior researcher at ETL (Electrotechnical Laboratory) in 1988-1999. He has been engaged in the research on parallel computer architecture. He is a member of IEEE CS, IEICE and IPSJ. Steve Messenger (Amazon) Stephen Messenger is a Senior HPC specialist Solutions Architect for AWS. He has worked with HPC and Cloud technology for the last 15 years, working on many different projects from personal clusters that fit under a desk, to some of the largest Super Computers in the world. He is still slightly amazed that anyone will pay him for tinkering with computers. When Stephen is not working he enjoys spending time mountain biking, in the New Forest or the South Downs in England. Srinath Vadlamani (Arm) Srinath Vadlamani, Ph.D. is an HPC Field Application Engineer with Arm. Inc. He specializes in scientific application efficacy on HPC systems with a focus on Arm enabled systems. Current interests include computation/communication overlap strategies and threading strategies. Srinath is part of the US Fortran Programming Language Standards Technical Committee. Miwako Tsuji (RIKEN R-CCS) Miwako Tsuji received master and PhD degrees from Information Science and Technology, Hokkaido University. From 2007 to 2013, she was working in University of Hokkaido, University of Tokyo, University of Tsukuba and Universite de Versailles Saint-Quentin-en-Yvelines. She is a research scientist at RIKEN Center for Computational Science. She was a member of the flagship 2020 project, which had conducted the disign and development of the supercomputer Fugaku during the full period of the project. Her current research interests are programming model and performance model of the large-scale high performance computing. She is a coauthor of the ACM Gordon Bell Prize in 2011. Stepan Nassyr (Juelich Supercomputing Centre) After studying physics at the Bergische Universitat Wuppertal, Stepan Nassyr joined the Juelich Supercomputing Centre in July 2017 to work on his PhD dealing with future ARM-based supercomputer architectures. As part of the application oriented technology group at the Juelich Supercomputing Centre he has worked extensively with the ARM ecosystem and the ARM SVE extension, focusing mostly on hand-written assembly kernels and the requirements to the microarchitecture and memory architecture to effectively exploit the available compute capabilities in the context of HPC applications. Aside from his PhD, he is also administering a small ARM-based cluster at the JSC and has experience with a number of ARM-based HPC architectures, including Marvell ThunderX2, Huawei Kunpeng 920 and Fujitsu's A64FX. Federica Filippini (Politecnico di Milano) tbd Andrei Poenaru (University of Bristol) Andrei Poenaru is a final-year PhD Student with the High Performance Computing Group at the University of Bristol. His research is centred around advanced and future architectures for HPC, and he has been involved in several studies aiming to characterise performance and evaluate portability across diverse modern architectures. His current projects are focused on vectorisation in the context of Arm SVE and upcoming Arm-based high-performance processors. John Linford (Arm) John is Arm's Director for HPC Engineering. He leads a worldwide team of HPC experts focused on making Arm a win for HPC and vice versa. Jeff Hammond (NVIDIA) Jeff Hammond is a Principal Architect at NVIDIA, where he focuses on parallel programming models for GPUs and ARM CPUs. He has contributed to NWChem since 2006. Luigi Genovese (Atomistic Simulation Laboratory (L_Sim) - CEA Grenoble) I am a Computational Physicists in the domain of Material Sciences, with a education in Theoretical High Energy Physics. My present research interests are related to the conception, development, and implementation of new theoretical algorithms and methods exploiting advanced computing resources, enabling large-scale computation in diverse areas in Solid-State physics, Quantum Chemistry, and Electronic Structure calculations with applications in Life-Sciences and Biology. Miquel Moreto (Barcelona Supercomputing Center) Miquel Moreto is a Ramon y Cajal Fellow at the Computer Architecture Departament (DAC) at the Universitat Politecnica de Catalunya-Barcelona Tech (UPC), where he teaches Computer Architecture. He is leading the High Performance Domain Specific Architectures team at the Barcelona Supercomputing Center (BSC). He received the BSc, MSc, and PhD from the UPC. His PhD thesis advisors were Mateo Valero (UPC) and Francisco J. Cazorla (BSC). During his PhD, he interned at IBM T. J. Watson Research Center for 4 months, and visited the Universities of Edinburgh and Cantabria for 3 months. After finishing the PhD, he spent 15 months at the International Computer Science Institute (ICSI), affiliated with UC Berkeley, as a Fulbright Postdoctoral Research Fellowship Holder during 2011 and 2012. Finally, he spent 2 months in Arm Research (Cambridge, UK) as a Visiting Professor in 2017. Hatem Ltaief (KAUST) Hatem Ltaief is a principal research scientist with the Extreme Computing Research Center, King Abdullah University of Science and Technology, Saudi Arabia. His research interests include parallel numerical algorithms, parallel programming models, and performance optimizations for multicore architectures and hardware accelerators. Bine Brank (Juelich Supercomputing Centre) "Bine Brank is a PhD student at Juelich Supercomputing Centre. After obtaining his Master's degree in Computer Simulation from the University of Wuppertal, he has joined the application-oriented technology development team at JSC. There, he is working in the context of Mont-Blanc 2020 and the European Processor Initiative project. The main topic of his dissertation is SIMD parallelisation with a focus on Arm's SVE. This includes porting of applications to Arm architectures as well as evaluation of compiler's auto-vectorisation capabilities. " Eva Siegmann (Stony Brook University) Eva Siegmann has a PhD in applied mathematics. She has extensive experience in the field of high-performance computing with special focus on simulations in the field of pharmaceutical engineering. Beginning of this year Eva joined the Stony Brook University where she is the lead research scientist in the Ookami project. Ookami is testbed which provides researchers with state-of-the-art hardware, including Fujitsu A64FX processors. Sarat Sreepathi (Oak Ridge National Laboratory) Sarat Sreepathi is a Computer Scientist interested in interdisciplinary research at the intersection of High Performance Computing and domain sciences. He is a member of the Computational Earth Sciences Group in the Computational Sciences and Engineering Division at Oak Ridge National Laboratory. He received his Ph.D. in Computer Science from North Carolina State University. He is the Chair of the OLCF User Group Executive Board and serves on the NERSC User Group Executive Committee. He co-leads the Performance group for the Energy Exascale Earth System Model. He is also a member of Exascale Computing Project (ECP) application teams (Climate: E3SM-MMF and Nuclear Fusion: XGC) . Thomas Chen (U.S. Technology Policy Committee) Thomas Chen is a researcher scientist whose primary interests lie in machine learning and high-performance computing. He serves on the U.S. Technology Policy Committee of the Association for Computing Machinery. As much of his work lies at the nexus of artificial intelligence and earth science, he is also an active early-career scientist member of the European Geosciences Union and the American Geophysical Union. He particularly enjoys using Python to conduct research that has real-world impacts. Previously, Thomas has presented work at a number of conferences, workshops, and meetings, from NeurIPS workshops, to Applied Machine Learning Days, to the Open Data Science Conference, to Machine Learning Week Europe. Craig Prunty (SiPearl) Craig Prunty, SiPearl VP Marketing & Business Development, joined SiPearl in May 2020. Prior to SiPearl, Craig was Marketing Director for Marvell Semiconductor’s Server Processor Business Unit in Santa Clara, California. His 20+ years in the Semiconductor industry include sales, marketing, and technical roles with Cavium, AppliedMicro (AMCC), Lockheed-Martin, and Unisys. Craig holds a B.S. in Mathematics from Lewis & Clark College in Portland, Oregon, and an MS in Electrical Engineering from San Diego State University. Abstract Abstract After the success and great interest from the last 3 years, Arm HPC User's Group at ISC will be bringing an even more diverse and exciting panel of topics ranging from the latest Arm-based systems, to programming for arm, co-design, to new HPC areas, such as deep learning, edge, and data-center analytics. Workshop Website https://a-hug.org/isc-2021-event/ pdfFriday 2:00pm-6:00pm Workshop Workshop on the In Situ Co-Execution of High-Performance Computing & Data Analysis Julien Bigot (Commissariat à l'énergie atomique et aux énergies alternatives), Bruno Raffin (Inria), Leonardo Bautista Gomez (Barcelona Supercomputing Center), Wounter Klinj (Forschungszentrum Julich), Charles Gueunet (Kitware), Sai Narasimhamurthy (Seagate Systems), Achim Basermann (DLR), Matthieu Dorier (ANL), Amal Gueroudji (CEA), Tiago Quintino (ECMWF), Dirk Pleiter (Forschungszentrum Julich), Alejandro Ribes (EDF), Virginie Grandgirard (CEA), and Yuuichi Asahi (JAEA) Biographies Biographies Julien Bigot
Bruno Raffin
Leonardo Bautista Gomez (Barcelona Supercomputing Center) Dr. Leonardo Bautista Gomez is a Senior Research Scientist at the Barcelona Supercomputing Center where he work on resilience and scalability for high-performance computing and machine learning. He was awarded the 2016 IEEE TCSC Award for Excellence in Scalable Computing (Early Career Researcher). Before moving to BSC he was a Postdoctoral researcher for 3 years at the Argonne National Laboratory, where he investigated data corruption detection techniques and error propagation. Prior to that, he did his PhD. in resilience for supercomputers at the Tokyo Institute of Technology. He developed a scalable multilevel checkpointing library called Fault Tolerance Interface (FTI) to guarantee application resilience at extreme scale. For this work, he was awarded the 2011 ACM/IEEE George Michael Memorial High-Performance Computing Ph.D. Fellow at Supercomputing Conference 2011 (SC11), Honorable Mention. Before moving to Tokyo Tech, he graduated in Master for Distributed Systems from the Paris 6 University. Wounter Klinj (Forschungszentrum Julich) Wouter Klijn completed a MSc in Artificial Intelligence from the University of Groningen in the Netherlands. His Master thesis was on the information content of cell species in a 3 layer model of a cortical micro-column. He currently is a software architect in the Simlab Neuroscience at the Forschungzentrum Jülich with a focus on in Artificial Intelligence, information theory of neural networks, big data real-time streaming systems and development of complex HPC processing pipelines. He is responsible for science and use case management in the Human Brain Project, an EU Flagship Project and ICEI, the Interactive Computing E-Infrastructure for the Human Brain Project. He is currently creating the science and software infrastructure architecture for the HBP. He also works with advanced HPC oriented AI solutions and multiple neural simulators. His modelling work is focused on self-organizing dynamics of extremely large neural networks with a 2d spatial structure. Charles Gueunet (Kitware) Charles Gueunet joined Kitware in February 2016. For the first three years, he worked on his PhD on the topic of “High Performance Level-set based Topological Data Analysis”, and became one of the main contributors of the Topology ToolKit (TTK). After defending in February 2019, Charles joined the Scientific Visualization team at Kitware. He now works on various projects involving parallel programming, discrete geometry and data analysis algorithms. Sai Narasimhamurthy
Achim Basermann (DLR) Dr Achim Basermann is head of the department “High-Performance Computing” at German Aerospace Center’s (DLR) Simulation and Software Technology institute and German Research Foundation (DFG) review board member in computer science, topic “Massively Parallel and Data Intensive Systems”. In 2019, he became chairman of the strategy commission for national high-performance computing (NHR) in Germany. He coordinated the application workpackage in the European Grid computing project NextGRID (2004-2007), the pre- and postprocessing activities in the European Exascale computing project CRESTA (2011-2014) and the algorithmic research in the Exascale computing projects ESSEX I and II (2013-2018) of DFG. In 1995, he obtained his Ph.D. in Electrical Engineering from RWTH Aachen followed by a postdoctoral position in Computer Science at Research Centre Jülich GmbH, Central Institute for Applied Mathematics. From 1997 to 2009 he led a team of HPC application experts at the C&C Research Laboratories, NEC Europe Ltd., in Sankt Augustin, Germany and contributed to the Japanese Earth Simulator project. Current research is focussed on massively parallel linear algebra algorithms, partitioning methods, optimization tools in the area of computational fluid dynamics for many-core architectures and GPGPU clusters, high-performance data analytics and quantum computing. Matthieu Dorier
Amal Gueroudji
Tiago Quintino (ECMWF) Dr Tiago Quintino is a Senior Analyst and Team Leader for Development of Production Services at ECMWF. He and his team develop high-throughput specialist software that supports ECMWF’s operational meteorological forecast model, systems for acquisition of incoming observations, management of direct model output, perpetual archival of weather observations and forecast data, and post-processing, generation and dissemination of meteorological products. His team also develops cloud meteorological and climate data provisioning services (Data-as-a-Service) in support of ECMWF’s cloud activities. Dr Quintino’s career spans 20 years researching numerical algorithms and developing high performance scientific software in the areas of Aerospace and Numerical Weather Prediction. Lately, his research focuses on scalable data handling algorithms for generation of meteorological forecast products, optimising their workloads and I/O of massive data-sets. Dirk Pleiter
Alejandro Ribes (EDF) Dr. Alejandro Ribés graduated in computer science (bachelor’s and master’s) from the Universitat Jaume I, Castelló (ES). He later graduated, from Université de Nice Sophia-Antipolis (FR), in a master in image processing and computer vision. Alejandro Ribés also holds a Ph.D. in multispectral imaging applied to fine art paintings, from the Ecole Nationale Supérieure des Télécommunications (FR). He later was a postdoctoral fellow at the CEA laboratory in Orsay (FR), working on parallel MRI reconstruction. During this postdoc he was appointed as a lecturer at the Computer Science Department of Ecole Polytechnique, Palaiseau, France, where he taught for two years. Alejandro also worked in MRI technology, during more than two years, as a visiting scholar at the National Yang-Ming University, Taipei, Taiwan. In 2009, Alejandro Ribés became a Research Scientist at the R&D department of EDF. In December 2016, he became Principal Research Scientist. He recently introduced AI based methods on the context of advanced numerical simulation, especially deep neural networks trained using GPU clusters. From 2013, Alejandro Ribés also collaborates with Sorbonne Université (FR). Virginie Grandgirard
Yuuichi Asahi
Abstract Abstract Exascale promises to support disruptive numerical experiments generating unprecedented quantity and quality of data. Only the latest advances in automated data analytics based on machine-learning or statistical analysis will make it possible to extract knowledge out of the data generated at this scale. It is thus critical to consider the numerical experiment as a whole, encompassing both its simulation (HPC) and data-analytics (HPDA) aspects. These two aspects need to be efficiently coupled to overcome the widening performance gap between compute and I/O. This also opens the road for innovative numerical patterns where the outcome of analytics is used to steer the simulation and greatly increase the scientific return of investment for numerical experiments. Workshop Website https://hpcda.github.io/ pdfFriday 2:00pm-6:00pm Workshop The Second Workshop on LLVM Compiler and Tools for HPC Johannes Doerfert (Argonne National Laboratory), Anja Gerbes (Center for Information Services and High Performance Computing), Sameer Shende (University of Oregon), Jeremy Bennett (Embecosm), Shintaro Iwasaki (Argonne National Laboratory), Ernesto Su and Xinmin Tian (Intel), Valentin Clement (Oak Ridge National Laboratory), Arnamoy Bhattacharyya (Huawei), Saiyedul Islam (Advanced Micro Devices (AMD)), Tobias Grosser (University of Edinburgh), and Jeffrey Sandoval (HPE) Biographies Biographies Johannes Doerfert (Argonne National Laboratory) Johannes Doerfert is a researcher in the Argonne Leadership Computing Facility at the Argonne National Laboratory. He develops LLVM and Clang enhancements that enable compiler optimization for parallel programs. Johannes is also part of several ongoing efforts to make compiler software ready for exascale computing. He is an active member of the OpenMP Language Committee and already organized various LLVM related workshops and conferences, including the LLVM Performance Workshops @ CGO, and the EuroLLVM in 2017. Johannes received his Ph.D. in Computer Science from Saarland University in 2018. Anja Gerbes (Center for Information Services and High Performance Computing) Anja works at the Center for Information Services and High Performance Computing at TU Dresden. A considerable part of her job role is to develop a range of courses and resources to enable users to work with the cluster. In addition, she is doing a PhD at the German Climate Research Center in Hamburg as an external member. The main topic is Compiler Optimization in High-Performance Computing with an aim to improve weather forecasting and climate modeling. The goal of her PhD is to study the compiler for deficits in terms of performance when translating HPC applications and to understand the limitations of compilers in making the necessary optimizations. These insights can then be incorporated into the compiler for future automatic compiler optimization. Automatic program transformation using source-to-source instrumentation of parallel programs will prepare HPC applications for future performance analysis. Sameer Shende
Jeremy Bennett (Embecosm) Jeremy Bennett founded in 2008 Embecosm. He is an expert on hardware modeling and embedded software development. Previously Dr Bennett was Vice President of ARC International plc, following their acquisition of Tenison Design where he had been CEO and CTO. Dr Bennett is author of the popular textbook, “Introduction to Compiling Techniques” (McGraw-Hill 1990, 1995, 2003) and holds an MA and PhD in Computer Science from Cambridge University. Shintaro Iwasaki
Ernesto Su
Xinmin Tian
Valentin Clement
Arnamoy Bhattacharyya (Huawei) Arnamoy received his PhD from University of Toronto and currently working in the Heterogeneous compiler lab in Huawei, Canada as a research engineer. He is broadly interested in the area of performance enhancement through compiler optimization, cloud computing and machine learning guided optimizations. He has been actively contributing in the LLVM Flang project (especially for the driver and semantic analysis for OpenMP). Saiyedul Islam
Tobias Grosser
Jeffrey Sandoval
Abstract Abstract The LLVM framework is a vast ecosystem surrounding a compiler core which enabled various advances in source-code tools, debuggers, linkers, and a whole host of programming-language and toolchain-related components. In addition to the open source components in the LLVM framework, e.g., Clang, Flang, MLIR, LLDB, etc., LLVM also serves as a foundation for a majority of vendor compilers and toolchains. As such, most current and future HPC system will come with LLVM components that are developed in large parts in the open source LLVM code base, a multi-company, multi-research institute, industry-academia, joint-venture. Workshop Website https://hps.vi4io.org/events/2021/llvm pdfFriday 2:00pm-6:00pm Workshop 7th Annual High Performance Container Workshop Christian Kniep (AWS); Shane Canon (Lawrence Berkeley National Labs); Andrew Younge (Sandia National Laboratories); Carlos Eduardo Arango Gutierrez (Red Hat); Abdulrahman Azab (University of Oslo, Partnership for Advanced Computing in Europe (PRACE)); Umesh Upadhyaya (HPC Nepal); Michael Kuhn (Otto von Guericke University Magdeburg); and Carsten Kutzner (Max Planck Institute for Biophysical Chemistry) Biographies Biographies Christian Kniep (AWS) Christian is a Specialist Solutions Architect with AWS. With a 10 year journey rooted in the HPC parts of the german automotive industry, Christian Kniep started to support CAE applications and VR installations. When told at a conference that HPC can not learn anything from the emerging Cloud and BigData companies, he became curious and was leading the containerization effort of the cloud-stack at Playstation Now followed by working at Docker Inc as a Technical Account Manager to help push the adoption forward and be part of the innovation instead of an external bystander. At AWS he is helping customers to adopt the cloud efficiently. Shane Canon (Lawrence Berkeley National Labs) Shane Canon joined NERSC in 2000 to serve as a system administrator for the PDSF cluster. While working with PDSF he gained experience in cluster administration, batch systems, parallel file systems and the Linux kernel. In 2005, Shane left LBNL to take a position as Group Leader at Oak Ridge National Laboratory. One of the more significant accomplishments while at ORNL was architecting the 10 petabyte Spider File System. In 2008, Shane returned to NERSC to lead the Data Systems Group. More recently Shane has focused on enabling data intensive applications on HPC platforms and engaging with bioinformatics applications. Shane joined the Data & Analytics Services group in 2016 to focus on these topics. Shane is involved in a number of projects outside of NERSC. He is the Production Lead on the KBase project which is developing a platform to enable predictive biology. Shane has a Ph.D in Physics from Duke University and B.S. in Physics from Auburn University. Andrew Younge (Sandia National Laboratories) Andrew J. Younge is a Senior Member of Technical Staff in the Scalable System Software department at Sandia National Laboratories. He currently serves as the Lead PI for the Supercontainers project under the DOE Exascale Computing Project and is a key contributor to the Astra system, the world's first supercomputer based on the Arm processor deployed under Sandia's Vanguard program. Prior to joining Sandia, Andrew held visiting positions at the MITRE Corporation, the University of Southern California's Information Sciences Institute, and the University of Maryland, College Park. He received his PhD in computer science from Indiana University in 2016. His research interests include high performance computing, virtualization, distributed systems, and energy efficient computing. The focus of his research is on improving the usability and efficiency of system software for supercomputing systems. Carlos Eduardo Arango Gutierrez (Red Hat) Eduardo is a performance engineer at Red Hat, working on the OpenShift performance & latency sensitive applications. Eduardo is also a Computer Science PhD student at Universidad del Valle, Cali, Colombia, working on containerized distributed systems for research computing, with high focus on automated workflows and DevOps. His research interests include High Performance Computing, Distributed systems, Dependency management, Linux containers and most recently, Container orchestration. Over the past 5 years Eduardo has focused on enabling researchers to build and deploy performance sensitive applications with containers on distributed environments. Abdulrahman Azab (University of Oslo, Partnership for Advanced Computing in Europe (PRACE)) Abdulrahman Azab works at the Department of Research Computing, University of Oslo, Norway. In addition he is a senior lecturer at the Department of Computer Engineering and Control Systems, Mansoura University, Egypt. He is leading the Containers-for-HPC service at PRACE (Partnership for Advanced Computing in Europe). Abdulrahman is also the Norwegian sub-project manager at NeIC/Tryggve (Collaboration on Sensitive Data in the Nordics). Abdulrahman is leading the sensitive data working group in both EOSC-hub and EOSC-Nordic (EOSC: European Open Science Cloud). His research interests are: High Performance Computing, High Throughput Computing, High Availability Computing, Linux Containers, Cloud Computing, Cyber Security, Control systems, and Bioinformatics. Umesh Upadhyaya
Michael Kuhn (Otto von Guericke University Magdeburg) Michael Kuhn is a junior professor for Parallel Computing and I/O at Otto von Guericke University Magdeburg. He conducts research in the area of high performance I/O with a special focus on I/O interfaces and data reduction techniques. Other interests of his include file systems and high performance computing in general. Michael is the principal investigator of the CoSEMoS project funded by the German Research Foundation (DFG). Moreover, he is the lead developer of the JULEA storage framework and received a 2019 R&D 100 award for his contributions to the Spack package manager. He regularly offers lectures and courses related to HPC and parallel I/O. Carsten Kutzner
Abstract Abstract Linux Containers have become an industry standard for sharing and distributing software. This workshop will create a space of interaction between field experts,end-users, and newcomers to discuss container technologies and their current and future challenges. Workshop Website https://hpcw.github.io pdfFriday 2:00pm-6:00pm Workshop Second International Workshop on the Application of Machine Learning Techniques to Computational Fluid Dynamics and Solid Mechanics Simulations and Analysis Volodymyr Kindratenko (National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign); Andreas Lintermann (Jülich Supercomputing Centre, Forschungszentrum Jülich); Charalambos Chrysostomou (The Cyprus Institute); Ashley Scillitoe (The Alan Turing Institute); Eloisa Bentivegna (IBM Research Europe); Jiahuan Cui (Zhejiang University); George Karniadakis (Brown University, MIT); Kazuto Ando (RIKEN Center for Computational Science (R-CCS)); Mario Rüttgers (Institute of Aerodynamics and Chair of Fluid Mechanics, RWTH Aachen University; Jülich Supercomputing Centre, FZ Jülich); Michael Gauding (CORIA and University of Rouen); Mario Bedrunka and Felipe de Castro Teixeira Carvalho (University of Siegen); Jinhui Yan (University of Illinois at Urbana-Champaign); Thomas Brown (George Mason University, Center for Mathematics and Artificial Intelligence, Center for Computational Fluid Dynamics); Sarath Radhakrishnan (Barcelona Supercomputing Center); Yaning Wang (Zhejiang University); and Shirui Luo (University of Illinois at Urbana-Champaign) Biographies Biographies Volodymyr Kindratenko
Andreas Lintermann
Charalambos Chrysostomou
Ashley Scillitoe
Eloisa Bentivegna
Jiahuan Cui
George Karniadakis
Kazuto Ando
Mario Rüttgers
Michael Gauding
Mario Bedrunka
Felipe de Castro Teixeira Carvalho
Jinhui Yan
Thomas Brown
Sarath Radhakrishnan
Yaning Wang
Shirui Luo
Abstract Abstract Combination of computational fluid dynamics (CFD) with machine learning (ML) is a newly emerging research direction with the potential to enable solving so far unsolved problems in many application domains. This workshop aims to demonstrate the use of high-fidelity CFD simulations to generate data and utilize it to train ML models to better predict the underlying physics in fluid dynamics utilizing the breakthrough in computational power, the evolution of data science techniques, and the ability to generate terabytes of data from high-fidelity simulations. ML techniques have the potential to support the identification and extraction of hidden features in large-scale flow computations, hence allowing to shift the focus from time-consuming feature detection to in-depth examinations of such features. Furthermore, ML techniques have the ability to find undetected correlations between phenomena in the flow, which will lead to deeper insight of the physics involved in complex natural processes. Apart from pure fluid dynamic, other research areas, such as constitutive modeling of heterogeneous materials, multiphase flow modelling, dynamics of the atmospheric, ocean, and climate system, and combustion/chemical reactions are working on similar techniques. The workshop will stimulate this research by providing a venue to exchange new ideas and discuss challenges and opportunities. Friday 2:00pm-6:00pm Workshop HPC I/O in the Data Center Julian Kunkel (University of Reading), Jay Lofstead (Sandia National Laboratories), Jean-Thomas Acquaviva (Data Direct Networks), Bingsheng He (National University of Singapore), Richard Lawrence (MetOffice), Erdem Yilmaz (University of Reading), Glenn Lockwood (Lawrence Berkeley National Laboratory), Frank Gadban (University of Hamburg), Luke Logan (Illinois Tech), Jack Kolokasis (Foundation for research and Technology Hellas), Alberto Scionti (Linksfoundation), and Bruno Silva (Amazon) Biographies Biographies Julian Kunkel (University of Reading) Dr. Kunkel is a Lecturer at the Computer Science Department at the University of Reading. Previously, he worked as postdoc in the research department of the German Climate Computing Center (DKRZ) that partners with the Scientific Computing group at the Universität Hamburg. He manages several research projects revolving around High-Performance Computing and particularly high-performance storage. Julian became interested in the topic of HPC storage in 2003, during his studies of computer science. Besides his main goal to provide efficient and performance-portable I/O, his HPC-related interests are: data reduction techniques, performance analysis of parallel applications and parallel I/O, management of cluster systems, cost-efficiency considerations, and the software engineering of scientific software. Jay Lofstead (Sandia National Laboratories) Dr. Jay Lofstead is a Principal Member of Technical Staff at Sandia National Laboratories in Albuquerque, New Mexico. Since 2010, Jay has been working on HPC simulation workflows focusing on data management issues and as well as general I/O and storage issues for HPC. His prior work includes the R&D100 Award winning ADIOS I/O componentization framework in use in more than 30 production scientific simulations. He is a member of several conference and workshop program committees. Jean-Thomas Acquaviva (Data Direct Networks) Jean-Thomas has obtained his Ph.D in 2000 from CEA, DAM (French Atomic Commission, Military Dept.) and University of Versailles (France). After spending 2 years at Intel Compiler group in Santa Clara, he joined the University of Versailles as a Research Engineer, and afterward joined CEA (civilian department) still as a Research Engineer. Jean-Thomas was one of the founding members of the Exascale Research Centre, a joint lab between Intel, CEA and UVSQ, where he took the head of the performance group. He’s now actively participating in the development of DDN’s newly set Advanced Technology Center in France. Jean-Thomas is chairing two workshops focused on parallel file systems and performance scalability of file systems. He has authored or co-authored around 20 international publications. Bingsheng He (National University of Singapore) - Richard Lawrence (MetOffice) - Erdem Yilmaz (University of Reading) - Glenn Lockwood (Lawrence Berkeley National Laboratory) - Frank Gadban (University of Hamburg) - Luke Logan (Illinois Tech) - Jack Kolokasis (Foundation for research and Technology Hellas) - Alberto Scionti (Linksfoundation) - Bruno Silva (Amazon) - Abstract Abstract Managing scientific data at scale is challenging for scientists but also for the host data center. The storage and file systems deployed within a data center are expected to meet users' requirements for data integrity and high performance across heterogeneous and concurrently running applications. Workshop Website https://hps.vi4io.org/events/2021/iodc pdfFriday 2:00pm-6:00pm Workshop 5th International Workshop on In Situ Visualization Tom Vierjahn (Westphalian University of Applied Sciences), Thomas Theussl (KAUST Core Labs), Steffen Frey (University of Groningen), Kenneth Moreland (Sandia National Laboratories), Guido Reina (University of Stuttgart), and Andrew Bauer (United States Army Corps of Engineers) Biographies Biographies Tom Vierjahn (Westphalian University of Applied Sciences) Tom Vierjahn is a Professor of Computer Science at the Westphalian University of Applied Sciences, Germany. There, he is working on visualization, rendering, and virtual reality. During his postdoc stay at RWTH Aachen University, Germany, he researched analysis and visualization of performance data acquired from massively parallel application runs on supercomputers. Furthermore, he applied in situ visualization to parallel simulations stemming from neuroscience research. Tom received his Diploma and Master's degree from Dusseldorf University of Applied Sciences, Germany. He received his PhD in computer science from the University of Münster, Germany, for his work on online surface reconstruction from unorganized point clouds with integrated texture mapping. Thomas Theussl (KAUST Core Labs) Thomas Theussl is currently a Visualization Scientist in the KAUST Visualization Core Lab. He received his M.S. in Computer Science from the Vienna University of Technology in 2000. Steffen Frey (University of Groningen) Steffen Frey is a is an Assistant Professor at the University of Groningen. His research interests are in visual analysis techniques for large and complex spatio-temporal data, with a particular focus on performance-related aspects and the expressive visual representations of dynamic processes. Kenneth Moreland (Sandia National Laboratories) Dr. Kenneth Moreland is a principal member of technical staff at Sandia National Laboratories. He received BS degrees in computer science and in electrical engineering from the New Mexico Institute of Mining and Technology in 1997. He received MS and Ph.D. degrees in computer science from the University of New Mexico in 2000 and 2004, respectively. Dr. Moreland specializes in large-scale visualization and graphics and has played an active role in the development of several HPC products including ParaView, VTK, IceT, Catalyst, Dax, and VTK-m. His current interests include the design and development of visualization algorithms and systems to run on multi-core, many-core, and future-generation computer hardware. Guido Reina (University of Stuttgart) Dr. Guido Reina is senior lecturer and research associate at the Visualization Research Center of the University of Stuttgart. He received his diploma in Software Engineering and his Doctoral degree in Visualization from the University of Stuttgart. His research interests include large data visualization, parallel and in situ methods especially for particle data, focusing on molecular data sets. He is the MegaMol development team leader and interested in visualization system design and engineering as well as in long-term software sustainability issues. Andrew Bauer (United States Army Corps of Engineers) Andy is a Research Mechanical Engineer at the United States Army Corps of Engineers. He works primarily on developing algorithms and interfaces for software that numerically discretizes partial differential equations (PDE). His focus has been on the finite element method (FEM) for spatial discretizations of the PDE using adaptive techniques and parallel computing to ensure efficient use of available computing resources. Previously, Andy was a Staff R&D Engineer at Kitware where he has worked on the Visualization Toolkit (vtk.org) and ParaView (paraview.org) open source projects focusing on ParaView Catalyst. Abstract Abstract The ever increasing scale of today’s HPC simulations with their inherent I/O bottleneck makes in situ an essential approach for data analysis. Nowadays, the rate of data generation easily exceeds available bandwidth or storage capabilities significantly. Consequently, analysis and visualization has to be coubled in situ to a live simulation in order to facilitate comprehensive investigation. In doing so, data abstracts are generated that capture much more information than otherwise possible. Workshop Website https://woiv.gitlab.io pdfFriday 2:00pm-6:00pm Workshop Fourth HPC Applications in Precision Medicine Workshop Eric Stahlberg (Frederick National Laboratory for Cancer Research), Thomas Steinke (Zuse Institute Berlin), Jan Nygard (The Cancer Registry of Norway), Marco Berghoff (Karlsruhe Institute of Technology), Sunita Chandrasekaran (University of Delaware), Petrina Hollingsworth (Frederick National Laboratory for Cancer Research), and Andreas Deutsch (Dresden University of Technology) Biographies Biographies Eric Stahlberg (Frederick National Laboratory for Cancer Research) Dr. Stahlberg is director of Biomedical Informatics and Data Science (BIDS) at the Frederick National Laboratory for Cancer Research, spanning explorations from the molecular level to clinical trials. He has been instrumental in the laboratory's high-performance computing initiative and in assembling scientific teams across multiple, complex organizations to advance predictive oncology. Stahlberg has played a leadership role in establishing a collaboration between the NCI and the Department of Energy (DOE) to accelerate progress in precision oncology and computing. The Joint Design of Advanced Computing Systems for Cancer (JDACS4C) collaboration is rooted in three national initiatives and undertakes exploring predictive oncology and exascale computing in fundamental RAS biology, predicting tumor response, developing patient level health trajectories, and uses of AI to accelerate drug discovery. Dr. Stahlberg holds a Ph.D. in computational chemistry from The Ohio State University. Thomas Steinke (Zuse Institute Berlin) Thomas Steinke (organizer) heads the Supercomputing Dept. at the Zuse Institute Berlin (ZIB) and is responsible for the HPC research, consulting and operation His research interest is in high performance computing, heterogeneous systems for scientific and data analytics applications, and parallel simulation methods. Thomas leads the Intel Parallel Computing Center at ZIB since 2013. He received his Doctorate in Natural Sciences (Dr. rer. nat.) in chemistry from the Humboldt University of Berlin. Jan Nygard (The Cancer Registry of Norway) As Head of the Registry Informatics department at the Cancer Registry, responsibility include modernization and digitalisation of the Cancer Registry, including the development and deployment of an IKT-framework for cancer registries with electronic cancer reporting using the Norwegian Health Network, establishing the IT-system for the pilot project for Colorectal screening programme, modernization of the cervical cancer screening programme, and the insourcing the ICT-systems of the National Mammography programme. He is a board member of the CERTUS SFI, as well as serving on several reference and steering committees. Marco Berghoff (Karlsruhe Institute of Technology) Marco Berghoff received the diploma degree in mathematics from the University of Paderborn, Germany, with a focus on microlocal analysis, numerics, and physics. He received the PhD degree in computational materials science from the Institute for Applied Materials. He has been a member of the Karlsruhe Institute of Technology, at the Institute for Applied Materials. He has years of experience in multiscale modeling and high-performance optimization, and with the scale-bridging of the atomistic phase-field crystal model to the mesoscopic phase-field method. As a postdoctoral researcher in the Simulation Laboratory “NanoMicro”, he has introduced the framework NAStJA, and currently leads the developments. He is involved in several activities within this project, in particular in the development of large-scale simulations for biological or material science research topics. The NAStJA Framework is used to simulate the growth and treatment of cancerous tumor with a cell geometric resolution. Sunita Chandrasekaran (University of Delaware) Sunita Chandrasekaran is assistant professor in the Computer and Information Sciences Department at the University of Delaware. Her research interests include exploring the suitability of high-level programming models and runtime systems for HPC and embedded platforms, and migrating scientific applications to heterogeneous computing systems. Dr. Chandrasekaran was a post-doctoral fellow at the University of Houston and holds a Ph.D. from Nanyang Technological University, Singapore. She is a member of OpenACC, OpenMP, MCA and SPEC HPG. She has served on the program committees of various conferences and workshops including SC, ISC, ICPP, CCGrid, Cluster, and PACT, and has co-chaired parallel programming workshops co-located with SC, ISC, IPDPS, and SIAM. Petrina Hollingsworth (Frederick National Laboratory for Cancer Research) Petrina Hollingsworth serves as an engagement manager for NCI-DOE collaborations at Frederick National Laboratory for Cancer Research. Andreas Deutsch (Dresden University of Technology) Andreas Deutsch is head of the department of Innovative Methods of Computing at the Centre for Information Services and High Performance Computing (Dresden University of Technology). His research is focused on mathematical biology, especially cellular automata and agent-based modeling, cancer invasion and collective phenomena in the life sciences. Abstract Abstract High-performance computing has become central to the future success of precision medicine. Catalyzed by the dramatic increase in the volume of research and clinical data available through sequencing and advanced imaging techniques, clinical data available through medical records and mobile health devices, research data from automated platforms, combined with molecular and multi-scale simulations and the rapid adoption of deep learning approaches has created a convergence shaping the frontiers of computing and precision medicine. New approaches to drug discovery, data sharing, aggregation and safeguards, use of machine learning models in research and clinical contexts, multi-scale observations integrated with predictive modeling, and biomedical digital twins have identified new challenges and opportunities in these rapidly evolving frontiers. Workshop Website https://ncihub.org/groups/hapm21 pdfFriday 2:00pm-6:00pm Workshop Compiler-assisted Correctness Checking and Performance Optimization for HPC Emmanuelle Saillard (Inria), Julien Jaeger (CEA), Ira Baxter (Semantic Designs), Tim Jammer (TU Darmstadt), Julia Lawall (Inria), Michael Blesel (Otto-von-Guericke-University Magdeburg), and Reed Milewicz (Sandia National Laboratories) Biographies Biographies Emmanuelle Saillard
Julien Jaeger
Ira Baxter (Semantic Designs) Dr. Baxter has been involved with computing since 1966, initially in hardware working with relay, discrete transistor logic and early Diode-Transistor Logic ICs. He learned to program with IBM 1401 (Autocoder), 1620 (Fortran) and 360 systems (BAL, PL/1, APL). He implemented one of the first commercial minicomputer timesharing systems on a Data General Nova in 1970, before receiving his B.S. in Computer Science (1973). During a brief stint in the numerical controls business, he designed and implemented a complete 16 bit virtual memory minicomputer, its OS and development tools for automated milling systems. In 1976, he started Software Dynamics, a systems software house, where he designed compilers, time-sharing and distributed network operating systems. The similarity in concepts and dissimilarity in implementation of the various OSes suggested that managing designs was key to managing long-lived software systems, and turned Ira's interests towards deeper software engineering research. In 1990, he received a Ph.D. in Computer Science from the University of California at Irvine, where he studied Software Engineering, focusing on design reuse using transformational methods. Dr. Baxter spent several years with Schlumberger, working on a PDE-solver generator for CM-5 supercomputers (Sinapse). He was consulting Research Scientist for Rockwell International, focusing on industrial control automation software engineering tools for several years. Tim Jammer (TU Darmstadt) Tim Jammer is a PhD candidate at the Institute for Scientific Computing at Technical University of Darmstadt. He received his Bachelor and Master degree from the University of Hamburg, while also working as a student research assistant at the DKRZ. His research interests are mainly in parallel and high performance computing with a particular focus on compiler-based analysis and rewriting tools for the efficient use of MPI. He is one of the authors and main contributors of the MPI correctness benchmark suite MPI-CorrBench, as well as other MPI-related tools that can be found at https://github.com/tudasc. In addition to his research position, he is a staff member at the Hessian Competence Center for High Performance Computing (www.hkhlr.de), providing user support and regular training courses for Hessian HPC users. Julia Lawall (Inria) Julia Lawall is a senior research at Inria-Paris. Previously, she was on the faculty of the University of Copenhagen. She received her PhD in 1994 from Indiana University, USA. She has been program chair of GPCE, ICFP, and ASE, a member of the SIGPLAN Executive Committee, and is on the editorial board of Science of Computer Programming. Her research is at the crossroads of programming languages, software engineering, and operating systems. She is particularly interested in the design of tools that address problems in the maintenance of large software. She is the primary developer of the open-source Coccinelle program transformation system and has over 2000 patches in the Linux kernel based on her research. Michael Blesel (Otto-von-Guericke-University Magdeburg) Michael Blesel is a doctoral candidate at the Otto von Guericke University Magdeburg in the Parallel Computing and I/O group. His main research is in the field of compiler-assisted correctness checks for SPMD applications in the context of high-performance computing. During his time as a student at the University of Hamburg he has worked for the Scientific Computing group as a research and teaching assistant for their high-performance computing related courses. His interests include compiler-based tools, high-performance computing in general and performance optimizations for parallel applications. Reed Milewicz (Sandia National Laboratories) Reed Milewicz is a senior member of technical staff in the Department of Software Engineering and Research within the Center for Computing Research at Sandia National Laboratories. He does research in the areas of software engineering, formal verification, and compilers. He believes that the quality of our lives depends upon the quality of our software, and that’s why he focuses on developing better practices, processes, and tools to target all phases of the software development lifecycle. This is a course of research that straddles the line between systems and human factors, and it’s carried out in close coordination with the communities he supports. Since joining Sandia in late 2016, his focus has been on the scientific software development community. Abstract Abstract Practical compiler-enabled programming environments, applied analysis methodologies, and end-to-end toolchains can contribute significantly to performance portability in the exascale era. The practical and applied use of compilation techniques, methods, and technologies, including static analysis and transformation, are imperative to improve the performance, correctness, and scalability of high-performance applications, middleware, and reusable libraries. This workshop brings together a diverse group of researchers with a shared interest in applying compilation and source-to-source translation methodologies, among others, to enhance explicit parallel programming such as MPI, OpenMP, and hybrid models. These types of compiler technologies can also be applied to heterogeneous programming elements including FPGAs and GPUs in order to deliver higher achievable performance as compared to library-based methods and human-coded approaches taken in isolation. Workshop Website https://c3po-workshop.github.io/2021/index pdfFriday 2:00pm-6:00pm Workshop Sixth International Workshop on Communication Architectures for HPC, Big Data, Deep Learning and Clouds at Extreme Scale Dhabaleswar Panda, Hari Subramoni, and Aamir Shafi (The Ohio State University); Satoshi Matsuoka (RIKEN Center for Computational Science); Gilad Shainer (NVIDIA/Mellanox); Duncan Roweth (HPE); Phil Murphy (Cornelius Networks); Hemal Shah and Moshe Voloshin (Broadcom); Matthew Williams (Rockport Networks); and Sanjay Basu (Oracle) Biographies Biographies Dhabaleswar Panda
Hari Subramoni
Aamir Shafi
Satoshi Matsuoka
Gilad Shainer
Duncan Roweth
Phil Murphy
Hemal Shah
Moshe Voloshin
Matthew Williams
Sanjay Basu
Abstract Abstract Extreme-Scale Computing in HPC, Big Data, Deep Learning, and Clouds are marked by multiple-levels of hierarchy and heterogeneity ranging from the compute units (many-core CPUs, GPUs, APUs, etc) to storage devices (NVMe, NVMe over Fabrics etc) to the network interconnects (InfiniBand, High-Speed Ethernet, Slingshot, etc). Owing to the plethora of heterogeneous communication paths with different cost models expected to be present in extreme-scale systems, data movement is seen as the soul of different challenges for exascale computing. On the other hand, advances in networking technologies such as NoCs (like NVLink and Stormlake), emergence of new I/O interface architecture standards (CCIX, Gen-Z, CAPI etc), and RDMA enabled networks and the likes are constantly pushing the envelope of research in the field of novel communication and computing architectures for extreme-scale computing. The goal of this workshop is to bring together researchers and software/hardware designers from academia, industry and national laboratories who are involved in creating network-based computing solutions for extreme-scale architectures. The scope of the workshop includes, but not limited to: scalable communication architectures and protocols, high performance networks, runtime/middleware designs, novel hardware/software co-design, high performance communication solutions for accelerator-based computing, power-aware techniques and designs, performance evaluations, QoS, and virtualization. Workshop Website http://nowlab.cse.ohio-state.edu/exacomm/ pdfFriday 2:00pm-6:00pm Workshop Third Workshop on HPC Education and Training for Emerging Technologies Nitin Sukhija (Slippery Rock University Of Pennsylvania); Scott Lathrop (University of Illinois); Nia Alexandrov (Hartree Centre, STFC, UKRI); Andrew Jones (Microsoft); Marjut Dieringer and Kevin McFall (NVIDIA); Kjartan Thor Wikfeldt (EuroCC National Competence Center Sweden); Mozhgan Chimeh (NVIDIA); Weronika Filinger (Edinburgh Parallel Computing Centre (EPCC)); Julia Mullen (MIT Lincoln Laboratory); Ann Backhaus (Pawsey Supercomputing Centre); and Richard Lawrence (Texas A&M University) Biographies Biographies Nitin Sukhija (Slippery Rock University Of Pennsylvania) Dr. Nitin Sukhija, is a Director of Center of Cybersecurity and Advanced Computing (C2AC), an assistant professor and one of the XSEDE Campus Champion specializes in the area of high performance data analytics and security. He has been involved in research and management of various projects pertaining to the HPC and software challenges in industry and academia for over a decade. Dr. Sukhija chaired and co-chaired many conferences such as ACM XSEDE16, ACM MEDES18, and IEEE WHPBDC(16, 17) conference and is also serving as an active member of the organizing committees of various esteemed (national and international) ACM and IEEE conferences and workshops, such as, XSEDE,IPDPS, PASA, ICPP, ISPDC, WHPBDC, SC EduHPC, SC18 Early Career Program, SIAM CSE Broader Engagement and others. He currently co-chairs the SIGHPC Education Chapter workshop committee and has been active in the planning and participation in HPC Training Workshops series at the SC, ISC and other conferences since 2015. Scott Lathrop (University of Illinois) Through his position with the Shodor Education Foundation, Inc., Scott Lathrop is the Blue Waters Technical Program Manager for Education. Lathrop has been involved in high performance computing and communications activities since 1986. Lathrop coordinates the community engagement activities for the Blue Waters project. He helps ensure that Blue Waters education, outreach and training activities are meeting the needs of the community. Lathrop has been involved in the SC Conference series since 1989, served as a member of the SC Steering Committee for six years. He served as the Conference Chair for the SC’11 and XSEDE14 Conferences. He helped form the International HPC Training Consortium which was merged into the ACM SIGHPC Education Chapter during 2018, and has been active in the planning and participation in HPC Training Workshops at the SC and ISC Conferences. Nia Alexandrov (Hartree Centre, STFC, UKRI) Dr. Nia Alexandrova is the Training Manager at Hartree Centre. She was a Training Coordinator at BSC, Barcelona (2011- 16) and was involved in PRACE Projects 1-5, as a PRACE Advanced Training Centre coordinator. She has over 17 years of experience as a PG Studies Coordinator and Research Assistant at the School of Systems Engineering and ACET (Advanced Computing and Emerging Technologies) Centre at the University of Reading, at BSC and now at STFC. Her research is in the area of collaborative learning in technology-rich environments in university education and professional training and developing evaluation methodologies for professional training programs. She co-edited and co-authored the book entitled Technological Advances in Interactive Collaborative Learning as well as authored 30 research papers in journals and peer-reviewed conference proceedings, up to date. She is a co-chair of a number of training and education related workshops on HPC and Computational Science Conferences. Andrew Jones (Microsoft) Andrew works on future HPC & AI capabilities for Azure, as part of the corporate engineering & product group. He joined Microsoft in early 2020, after nearly 25 years experience in the supercomputing community. Andrew has been an HPC end-user, researcher, software developer, HPC service manager, and impartial consultant. He has been a trusted voice on HPC strategy, technology evaluation and benchmarking, metrics, cost/value models and more. He has been lucky to have had rare exposure to state-of-practice in a wide range of HPC services/facilities across industry, government and academia around the world. Andrew is active on twitter as @hpcnotes. Marjut Dieringer (NVIDIA) Marjut manages NVIDIA’s Deep Learning Institute (DLI) in EMEA. In her role, Marjut is responsible for advising corporations, universities, and governments on the importance of AI and why now is the right time for employees to start developing their skills. Over the past four+ years, she has helped over 5000 organizations educate their staff. Kevin McFall (NVIDIA) Kevin McFall contributes to the NVIDIA Deep Learning Institute (DLI) as a Master Instructor by teaching workshops and supporting DLI certified instructors in the Europe, Middle East, and Africa region. He applies his prior academic experience as an educator and scholar to making the student experience in DLI workshops engaging and informative. His areas of expertise span computer vision, robotics, and autonomous systems. Kjartan Thor Wikfeldt (EuroCC National Competence Center Sweden) Thor has an academic background in computational chemistry and materials science. After obtaining his Ph.D. from Stockholm University in 2011 he worked as a postdoc first at University College London and then the University of Iceland, before returning to a researcher position at Stockholm University. In 2016 Thor jumped over to HPC and worked as an application expert in molecular dynamics at the PDC HPC center at KTH. During this time he became increasingly drawn towards teaching workshops and developing training material, both at PDC and within the CodeRefinery project. Thor is passionate about helping researchers write better and more scalable code with less effort, is helping to build a community of research software engineers in the Nordics through the Nordic-RSE initiative, and enjoys programming in Julia. Mozhgan Chimeh (NVIDIA) Dr Mozhgan Kabiri Chimeh is a GPU developer advocate at NVIDIA helping to bring GPU and HPC to growing user community in Europe and around the world. She is a community builder with a passion for open source software and is actively involved in the HPC and RSE communities. As a Software Sustainability Institute fellow, and Research Software Engineer (RSE) advocate, she is actively promoting reproducible and sustainable software, use of HPC and particularly GPUs through training, seminars, research software consultancy and outreach. Prior to joining Nvidia, Mozhgan was a Research Software Engineer in Massive Scale Complex Systems Simulation with Accelerated Computing at the University of Sheffield, UK. She worked in the area of complex system modelling using emerging high-performance parallel architectures. Mozhgan served as the chair of the women in HPC series of workshops at the International Supercomputing Conference and was on the organizing and program committee of leading conferences in the HPC field. She holds a Ph.D. in computer science and a master's degree in Information Technology from the University of Glasgow, UK. Weronika Filinger (Edinburgh Parallel Computing Centre (EPCC)) Weronika Filinger is an HPC Applications Consultant working at EPCC, The University of Edinburgh. She has been deeply involved in the design and development of the first Massive Open Online Course (MOOC) on Supercomputing and facilitated all runs of the course. She is teaching Practical Introduction to HPC – a postgraduate online course offered by the University of Edinburgh. For years Weronika has been a member of the EPCC outreach team, taking HPC related activities to public events. She is serving as the co-chair of the Outreach Committee of the ACM SIGHPC Education Chapter and the publicity chair of the International HPC Certification Program. She is also involved in running the International HPC Summer School. Over the years she has worked on a number of collaborative projects such as CRESTA, ADEPT, APES, SARGASSO and DEEP-EST, and provided consultancy for the Software Sustainability Institute. Julia Mullen (MIT Lincoln Laboratory) Dr. Julie Mullen is a member of the technical staff in the MIT Lincoln Laboratory Supercomputing Center (LLSC), where she assists researchers in maximizing their use of high-performance computing resources in order to minimize their time to solution. As an expert in high-performance computing for computational engineering applications, she focuses on redesigning scientific workflows to streamline processing and improve the performance of computational engineering applications. Dr. Mullen leads the design and creation of online professional education courseware for the LLSC. As part of this effort, she facilitates the development of new tools for the Open edX platform to provide support for online Laboratory courseware. Her research includes learning analytics for adaptive learning design and the integration of hands-on physical construction and experimentation with massive open online course technologies. Her work has been published in both the scientific computing and educational domains. Ann Backhaus (Pawsey Supercomputing Centre) Ann Backhaus has a passion for lifelong learning. Ann lives this passion, as exampled by her doing a ‘refresher’ Teaching and Learning Graduate Certificate “for fun” before joining Pawsey in 2019, even though she already had previous degrees as well as 25 years of experience in training and talent development in private industry and academia. “I enjoy teaching and learning at all levels and in all forms, from designing programs to developing content across a range of platforms,” says Ann. Richard Lawrence (Texas A&M University) Richard Lawrence obtained his Bachelor’s degree from the University of California, Davis in 2012 and his Master’s degree in 2018 from Texas A&M University, both in Physics. He has been a graduate student at Texas A&M University since 2014 pursuing his Ph.D., currently in progress. He works under the supervision of his advisor David Toback on a joint project between the Cryogenic Dark Matter Search collaboration and the Quantum Information Science group at Pacific Northwest National Laboratory, studying cryogenic silicon devices. Richard joined the High Performance Research Computing Group at Texas A&M University in 2020 as a User Support Specialist to assist with software maintenance and training for scientific research. He is interested in high-performance computing technologies including containers and machine learning. In his spare time Richard volunteers for a local Girl Scouts troop. Abstract Abstract HPC is central for empowering progress in diverse scientific and non-scientific domains. A myriad of technologies in the post peta-scale computing demand a significantly greater degree of parallelism than we currently observe. The rapid advancement of new HPC technologies has facilitated the convergence of Artificial Intelligence (AI), Big Data Analytics, and the HPC platforms to solve complex, large-scale, real-time analytics and applications for scientific and non-scientific fields. As we move towards exascale, the convergent computing platforms along with a paradigm shift in the programming applications for them provide both challenges and opportunities, for cyberinfrastructure facilitators and educators to prepare and support a diverse community of professionals to utilize evolving HPC, equipping them to solve complex scientific, engineering, and technological problems. Workshop Website https://sighpceducation.acm.org/events/HETET21.html pdfFriday 2:00pm-6:00pm Workshop Machine Learning on HPC Systems Janis Keuper (Fraunhofer Institut für Techno- und Wirtschaftsmathematik ITWM; Institute for machine Learning and Analytics (IMLA), Offenburg University); Sunna Torge (TU Dresdden); Jenia Jitsev (Institute for Advanced Simulation (IAS)); Juan Jose Durillo (Leibniz Supercomputing Centre); Dennis Hoppe (HLRS); Daniel Soudry (Technion); Jenia Jitsev (Juelich Supercomputer Center); Nico Hoffmann (TU Dresden); Stefanie Günther (LLNL); Ahmed Elnaggar (TU Munich); Kalun Ho (Fraunhofer Center HPC); Niranjan Hasabnis (Intel); Mathias Esteban and Jonathan Muraña (Universidad de la República); and Peter Winkler (TU Dresden) Biographies Biographies Janis Keuper (Fraunhofer Institut für Techno- und Wirtschaftsmathematik ITWM; Institute for machine Learning and Analytics (IMLA), Offenburg University) Janis Keuper is full professor for Data Science and Analytics at the Institute for Machine Learning and Analytics (IMLA), Offenburg University and scientific advisor at the "Large Scale Machine Learning" group at the Fraunhofer Competence Center for High Performance Computing. His current research is focused on scalable machine learning systems, especially Deep Learning. Before joining IMLA in 2019, he was a Group Leader at Fraunhofer ITWM and the Intel Visual Computing Institute (Saarbrücken, Germany). Janis was the chair of the Deep Learning tracs at the ISC Supercomputing 2017 and 2018 conference and member of the organizing committee of the "Machine Learning in HPC" Workshop at the ACM Supercomputing 2018/2019 conferences. Sunna Torge (TU Dresdden) Sunna Torge is a senior researcher in the national AI and Big Data competence center ScaDS.AI Dresden/Leipzig at ZIH (TU Dresden). She obtained a diploma in mathematics (minor physics) from the University of Freiburg and a PhD in computer science with focus on mathematical logic and automated deduction. After working in the research group man-machine-interface at Sony International (Europe) and the machine learning group at University of Freiburg she was a full professor for theoretical computer science at the University of Applied Science Furtwangen. After her move to Dresden Sunna Torge worked in machine learning and data analytics groups within the TU Dresden and Fraunhofer Institute for Transportation and Infrastructure Systems with focus on text data analytics. Her main research topics currently are text and sequence analysis on large data sets. Jenia Jitsev (Institute for Advanced Simulation (IAS)) TBA Juan Jose Durillo (Leibniz Supercomputing Centre) PD Dr. Juan José Durillo Barrionuevo (male) received the MSc and PhD degrees in computer science from the University of Málaga in 2006 and 2011. From 2011 to 2017, he worked as Assistant Professor at UIBK (Austria), where he also did his habilitation work focusing on workflow scheduling as the main topic. He has authored more than 50 publications in international journals, conferences and books. As a lecturer, he taught courses on optimisation, operating systems, GPU programming and C++. Since 2018, he has worked as a scientist at the BADW-LRZ. His research interests include automatic tuning of scientific applications, workflow scheduling, multi-criteria optimisation, GPU computing, and artificial intelligence. Dennis Hoppe (HLRS) -TBA- Daniel Soudry (Technion) Daniel is an assistant professor and in the Electrical Engineering Department at the Technion, working in the areas of machine learning and neural networks. His recent works focus on resource efficiency and implicit bias in neural networks. He did his post-doc working with Prof. Liam Paninski in the Department of Statistics and the Center for Theoretical Neuroscience at Columbia University, and his Ph.D. in the Electrical Engineering Department at the Technion. He is the recipient of the Gruss Lipper Fellowship, the Taub Fellowship, the Goldberg Award, and Intel's Rising Star Faculty Award. Nico Hoffmann (TU Dresden) Nico Hoffmann, young investigator group leader. Nico earned his PhD in 2016 from Technische Universität Dresden in medical image analysis. He developed statistical machine learning methods for analysis of intraoperative neuroimaging data of the exposed human brain. He visited the Laboratory of Mathematics in Imaging of Harvard University from 2018 to 2019. During that time, he developed recurrent convolutional neural networks for reconstruction of nerve fibre bundles of the human brain. He is currently heading a Helmholtz AI Young Investigators Group at Helmholtz-Zentrum Dresden-Rossendorf “AI for Future Photon Sciences” researching Physics-guided Neural Networks for PDE learning as well as inverse problems. Stefanie Günther (LLNL) TBA Ahmed Elnaggar (TU Munich) Ahmed Elnaggar is a Ph.D. candidate at the Technical University of Munich. His main focus of research is self-supervised learning on various modalities (Text, Protein, Source code, Images, and speech) using high-performance computing. Kalun Ho (Fraunhofer Center HPC) TBA Niranjan Hasabnis (Intel) TBA Mathias Esteban (Universidad de la República) TBA Jonathan Muraña (Universidad de la República) TBA Peter Winkler (TU Dresden) TBA Abstract Abstract Over the last few years, Machine Learning (and in particular Deep Learning) (ML / DL) has become an important research topic in the High Performance Computing (HPC) community. This comes along with new users and data intensive applications on HPC systems, which increasingly affects the design and operation of compute infrastructures. Bringing new users and data intensive applications on HPC systems, Learning methods are increasingly affecting the design and operation of compute infrastructures. On the other hand, the learning community is just getting started to utilize the performance of HPC, leaving many opportunities for better parallelization and scalability. The intent of this workshop is to bring together researchers and practitioners from all communities to discuss three key topics in the context of High Performance Computing and learning methods: parallelization and scaling of ML / DL algorithms, learnig applications on HPC systems, and HPC systems design and optimization for ML / DL workloads. Workshop Website http://www.MLHPCS.org pdfFriday 2:00pm-6:00pm Workshop ISC'21 SuperCompCloud: 4th International Workshop on Interoperability of Supercomputing and Cloud Technologies Sadaf Alam (Swiss National Supercomputing Centre); David Hancock (Indiana University); François Tessier (INRIA); David Y. Hancock (Indiana University); Nic Bellingham (UK Met Office); Stig Telfer (StackHPC); Andrew Jones (MS Azure); Mallikarjun (Arjun) Shankar (ORNL); Bjoern Enders and Gabor Torok (NERSC, LBNL); and Christopher Haine (HPE HPC/AI EMEA Research Lab) Biographies Biographies Sadaf Alam (Swiss National Supercomputing Centre) Sadaf R. Alam is Chief Technology Officer (CTO) at the Swiss National Supercomputing Centre (CSCS) in Lugano, Switzerland. Dr. Alam studied computer science at the University of Edinburgh, UK, where she received her Ph.D. in 2004. Until March 2009, she was a computer scientist at the Oak Ridge National Laboratory, USA. In her role as the CTO, she ensures end-to-end integrity of HPC systems and storage solutions and leads strategic projects at the centre. She has held different roles at CSCS including group lead of future systems, chief architect and head of operations. She is a member of ACM, ACM-W, SIGHPC and Women in HPC. David Hancock (Indiana University) David Hancock is the director for advanced cyberinfrastructure in IU's Research Technologies division. Hancock is responsible for directing IU's local and national high performance computing (HPC), storage, and cloud resources for research. Hancock is the primary investigator for the Jetstream project funded by the National Science Foundation (NSF). He is also responsible for directing IU system administrators who participate in the NSF XSEDE and Wrangler projects. Hancock is an active member in multiple HPC community organizations and currently a member on the board of the Cray User Group where he has served as president and vice president. Hancock is also an elected member of the XSEDE Advisory Board, and a representative in the XSEDE Service Provider (SP) Forum. Previously he served as the vice president for the IBM HPC User Group (SPXXL) and vice chair of the XSEDE SP Forum. François Tessier (INRIA) François Tessier has been a Research Scientist at Inria (Rennes, France) since November 2020. He received a Ph.D in Computer Science in 2015 from University of Bordeaux. His thesis focused on topology and affinity-aware process placement and load balancing algorithms for large-scale applications. From 2016 to 2018, he was a postdoctoral appointee at Argonne National Laboratory, IL, USA, within the LCF division (Leadership Computing Facility) where his research work has been more oriented towards I/O optimization in parallel libraries. Before joining Inria, he was a Computational Scientist at ETH Zürich within CSCS (Swiss National Supercomputing Center) located in Lugano, Switzerland, where he addressed the problem of dynamically provisioning of storage resources for HPC applications and large-scale workflows on supercomputers. At Inria, he is now working on various I/O and storage challenges in a context of HPC/Cloud convergence. David Y. Hancock (Indiana University) David Hancock is the director for advanced cyberinfrastructure in IU's Research Technologies division. Hancock is responsible for directing IU's local and national high performance computing (HPC), storage, and cloud resources for research. Hancock is the primary investigator for the Jetstream project funded by the National Science Foundation (NSF). He is also responsible for directing IU system administrators who participate in the NSF XSEDE and Wrangler projects. Hancock is an active member in multiple HPC community organizations and currently a member on the board of the Cray User Group where he has served as president and vice president. Hancock is also an elected member of the XSEDE Advisory Board, and a representative in the XSEDE Service Provider (SP) Forum. Previously he served as the vice president for the IBM HPC User Group (SPXXL) and vice chair of the XSEDE SP Forum. Nic Bellingham (UK Met Office) Nic Bellingham joined the Met Office as a graduate in 1992 with a degree in Mathematics & Computer Science. Most of her career has been in IT-focused roles, from developing mainframe and PC applications to working with the Programme that will deliver the Met Office’s Supercomputing capability through to 2032. In 2012 she moved from software engineering into an IT Service Management role, with responsibility for the delivery of a range of operational services, including forecaster applications and public and commercial web offerings. From 2014 to 2016, Nic was Deputy Head of IT Infrastructure & Operations with day-to-day responsibility for all Met Office IT services. In late 2016, she became Head of IT Infrastructure & Operations, leading the delivery of the Met Office IT estate and associated services. Since April 2019 Nic has been seconded to the Met Office’s Supercomputing Programme, leading the engagement with the Programme from the organisation’s Technology directorate. Stig Telfer (StackHPC) Stig has a background in R&D working for various prominent technology companies, particularly in HPC and software-defined networking. Stig is now CTO for StackHPC, a consultancy specialising in the convergence of cloud, HPC and big data. Stig is also co-chair of the OpenStack Scientific Special Interest Group, a globally-distributed grouping of research institutions using OpenStack for research computing use cases Andrew Jones (MS Azure) Andrew leads planning of future capabilities for HPC & AI within Microsoft Azure, as part of the corporate engineering & product group. He joined Microsoft in early 2020, after nearly 25 years experience in the supercomputing community. Andrew has been an HPC end-user, researcher, software developer, HPC service manager, and impartial consultant. He has been a trusted voice on HPC strategy, technology evaluation and benchmarking, metrics, cost/value models and more. He has been lucky to have had rare exposure to state-of-practice in a wide range of HPC services/facilities across industry, government and academia around the world. Andrew is active on twitter as @hpcnotes. Mallikarjun (Arjun) Shankar (ORNL) Arjun Shankar is a distinguished staff member and the section head for Advanced Technologies in the National Center for Computational Sciences at Oak Ridge National Laboratory (ORNL). He also directs the Compute and Data Environment for Science (CADES) institutional computing capability at ORNL. Arjun’s research in the national laboratory setting has involved designing large-scale data analysis and modeling systems, sensor networking systems, energy grid monitoring and control frameworks, and deploying middleware to overlay data, computation, and control across systems and infrastructure. His sponsored R&D project outputs have several active users in the federal government as well as in the commercial sector. His research has resulted in over seventy peer-reviewed publications including those that address jointly modeling and simulating systems coupled with observational data, incorporating policy constraints, and creating scalable cross-facility data infrastructures. Arjun received his B.Tech. from the Indian Institute of Technology, Mumbai, and his M.S. and Ph.D. in computer science from the University of Illinois, Urbana. He has served on the DOE ASCAC subcommittee on Scientific and Technical Information, is a member of the AAAS, and a Senior Member of the ACM and the IEEE. Bjoern Enders (NERSC, LBNL) Bjoern Enders joined NERSC in 2019 as a Data Science Workflows Architect in the Data Science Engagement Group where he liaises with various large-scale experimental facilities, engages with the wider scientific workflows community and contributes to NERSC's API efforts. He works towards a future where HPC resources integrate seamlessly and effortlessly into experimental science workflows. Bjoern has a background in software development for experimental sciences with a specialization for computational microscopy at synchrotron light sources. He holds a PhD in Physics from the Technical University of Munich, Germany and a MSc equivalent degree in physics from the University of Goettingen, Germany. Gabor Torok (NERSC, LBNL) Gabor has decades of experience building, maintaining and debugging large-scale web applications. He started his career at Berkeley Lab in the 1990-s. A few years later, he worked as a back-end and fullstack software engineer for various start-ups and larger companies. After about 20 years in the private sector, he is now working for NERSC and couldn't be more excited to use his experience to make computing for science run smoother. Gabor's recent contributions are Iris, the NERSC banking and account management system, as well as the Superfacility API which allows for programmatic access to NERSC resources. Christopher Haine (HPE HPC/AI EMEA Research Lab) Christopher Haine earned in 2017 a Ph.D. from the University of Bordeaux, on the topic of loop kernel optimisation and data layout restructuring. Christopher then joined Cray (now HPE) in the HPC/AI EMEA Research Lab, where he focuses on data-aware middleware, data movement in complex memory hierarchies, and optimisation and programmability of scientific applications and workflows. Abstract Abstract Imminent arrival and deployment of exascale systems among multiple hyperscaler cloud providers are expected to enable breakthroughs for various scientific disciplines. Increasingly, these systems utilize cloud technologies, enabling complex and distributed workflows that improve not only scientific productivity, but accessibility of resources to a wide range of communities. Such an integrated and seamlessly orchestrated system for supercomputing and cloud technologies is indispensable for experimental facilities that have been experiencing an unprecedented rate of data growth. While limited-scale HPC services has been available in public cloud environments, petascale and beyond data and computing capabilities are provisioned within HPC data centers using close-to-metal provisioning services to ensure performance, scaling, and cost effectiveness. This workshop aims to bring together experts and practitioners from academia, national laboratories and industry to discuss technologies, use cases and best practices in order to set a vision and direction for leveraging extreme-scale computing and on-demand cloud ecosystems. Friday 2:00pm-6:00pm Workshop 2nd ISC-HPC International Workshop on “Monitoring and Operational Data Analytics” (MODA) Florina Ciorba (University of Basel); Daniele Tafani (Fujitsu, Germany); Utz-Uwe Haus (Cray EMEA Research Lab); Nicolas Lachiche (University of Strasbourg); Ann Gentile (Sandia National Laboratories); Natalie Bates (Energy Efficiency HPC WG); Torsten Wilde (HPE); Aleš Zamuda (University of Maribor); Martin Molan (University of Bologna); and Masaaki Terai (RIKEN Centre for Computational Science) Biographies Biographies Florina Ciorba (University of Basel) Florina Ciorba is an Associate Professor of High Performance Computing at the University of Basel, Switzerland. She received her Diploma in Computer Engineering in 2001 from University of Oradea, Romania and her doctoral degree in Computer Engineering in 2008 from National Technical University of Athens, Greece. She has held postdoctoral research associate positions at the Center for Advanced Vehicular Systems at Mississippi State University, Mississippi State, USA (2008 to 2010) and at the Center for Information Services and High Performance Computing at Technische Universität Dresden, Dresden Germany (2010-2015). Her research interests include parallelization, dynamic load balancing, loop scheduling, robustness, resilience, scalability, reproducibility of scientific applications executing on small to large scale parallel computing systems, and system and application monitoring for improving their operations. More information at https://hpc.dmi.unibas.ch/en/people/florina-ciorba/ Daniele Tafani (Fujitsu, Germany) Daniele Tafani received his PhD in Electronic Engineering from Dublin City University (DCU) in 2012, where he conducted research on analytic modelling and resource optimisation of optical burst switched networks. He worked at the IBM Tivoli Rome Labs as a software engineer, and was a visiting researcher at the University of Ottawa, where he developed algorithms for energy-efficient light paths in computational grids. Daniele spent 8 years as a research scientist in the High-Performance Systems division of the Leibniz Supercomputing Centre (LRZ), focusing his interests on energy efficiency of HPC systems, scalable sensor monitoring and operational data analytics. He is now Technical Product Manager at Fujitsu. Utz-Uwe Haus (Cray EMEA Research Lab) Utz-Uwe Haus is a Senior Research Engineer at CRAY. He studied Mathematics and Computer Science at the TU Berlin. After obtaining a Doctorate in Mathematics at the University of Magdeburg he worked on nonstandard applications of Mathematical Optimization in Chemical Engineering, Material Science and Systems Biology. After 5 years as a Senior Researcher at the Department of Mathematics at ETH Zürich he is now leading the Cray European Research Lab in Basel, developing the Mathematical Optimization and Operations Research group, working on data-dependency driven workflow optimization on future HPC architectures. Nicolas Lachiche (University of Strasbourg) Nicolas Lachiche received his PhD in Computer Science from the University of Nancy, France in 1997, where he conducted research on machine learning. After a postdoc at the University of Bristol, he joined the University of Strasbourg as an associate professor. He is the head of the Data Science and Knowledge research group in the ICube laboratory. His research interests are in mining relational or sequential data. Ann Gentile (Sandia National Laboratories) Ann Gentile is the Manager of the HPC Development Department at Sandia National Laboratories. Prior to that, she was a Distinguished Member of Technical Staff and she continues her interests in Resource-Aware Computing in her current role. Ann is a co-author of the R&D 100 award-winning, open source Lightweight Distributed Metric Service (LDMS) which is deployed at large-scale HPC sites within the US national labs and the NSF for monitoring and resource utilization understanding on large-scale HPC systems. HPE/Cray has implemented LDMS in its monitoring solution to be part of every currently announced NNSA exascale machine. Ann serves on investment area teams determining priorities for Sandia’s Computational CoDesign and Trusted AI Research and on evaluation teams of extreme-scale architectures for the US national labs. Ann is also a co-founder of the Workshop on Monitoring and Analysis for High Performance Computing Systems Plus Applications (HPCMASPA), now in its 9th year held in conjunction with IEEE Cluster. She earned her Ph.D. in Chemical Physics and M.S. in Chemistry from UIUC and her B.S. in Physics from Carnegie-Mellon University. Natalie Bates (Energy Efficiency HPC WG) Natalie Bates has led the Energy Efficient High Performance Computing Working Group (EE HPC WG) since its inception in 2010. The purpose of the WG is to drive implementation of energy efficient design in HPC. Today, there are ~800 members from 25+ countries. Natalie has been the technical and executive leader for this ‘open source’ working group that disseminates best practices, shares information (peer to peer exchange), and takes collective action. The EE HPC WG has collaborated and negotiated with industry standards committees and major HPC organizations as well as influenced HPC system development. Prior to leading the EE HPC WG, Natalie's career spanned twenty years with Intel Corporation where she was a senior manager of highly complex programs taking new products to market, delivering multi-component and multi-partner platforms, and negotiating strategic technical industry initiatives. Torsten Wilde (HPE) Torsten is a system architect for Exascale monitoring and system power and energy management at Hewlett Packard Enterprise (HPE). His research activities are related to high volume, high frequency data collection and analytics for improved IT operations as well as dynamic power management. He is the lead architect for HPE's Exascale monitoring framework developed as part of the ECP funded PathForward project. Torsten is part of the leadership team of the Energy Efficient High Performance Computing Working Group (EE HPC WG) and currently serves as the Workshop and Conferences Co-Chair. Torsten received his MSc in parallel and scientific computation from the University of Liverpool, UK, and a MSc in Computer Engineering from the University of Applied Sciences in Berlin, Germany. He received his Dr. rer. nat. degree in computer science from the Technical University of Munich, Germany, in 2018. Aleš Zamuda (University of Maribor) Ales Zamuda received his B.Sc., M.Sc., and Ph.D. degrees in computer science from University of Maribor, Slovenia, in 2006, 2008, and 2012, respectively. As an affiliate of Faculty of Electrical Engineering and Computer Science at the University of Maribor he acts within research group Computer Architecture and Languages Laboratory and programme-funded unit Computer Systems, Methodologies, and Intelligent Services. His areas of interest include evolutionary algorithms, multicriterion optimization, artificial life, and computer animation. He has written over 50 scientific papers and among them several journal papers ranked in first quarter of computer science category such as Applied Soft Computing and Information Sciences and received several citations of his scientific works. Martin Molan (University of Bologna) Martin Molan is a PhD student of data science and computation at University of Bologna. He has received BA in mathematics at University of Ljubljana and MA in ICT at JSI institute. As a student he has collaborated with CERN openlab, UCL center for AI, UNESCO International Research Center On Artificial Intelligence, and CINECA. Masaaki Terai (RIKEN Centre for Computational Science) Coming Soon... Abstract Abstract This workshop aims to provide insight into the current state and trends in Monitoring and Operational Data Analytics (MODA), to identify potential gaps, and to offer an outlook into the future of MODA at a large scale together with possible solutions for the upcoming Exascale systems. The focus of the MODA21 workshop will be on currently envisioned solutions and best practices for monitoring systems at data centers and HPC sites, as well as on effective strategies for analyzing and interpreting the collected operational data. The workshop is unique to the European HPC arena in addressing these topics. We envision a balanced mix between a keynote address, peer-reviewed technical paper presentations, invited talks, and a panel discussion. Workshop Website https://moda21.sciencesconf.org/ pdfFriday 2:00pm-6:00pm Workshop 16th Workshop on Virtualization in High-Performance Cloud Computing Michael Alexander (BOKU, Vienna); Anastassios Nanos (Nubificus Ltd.); Anastasios Nanos and Charalampos Mainas (Nubificus LTD); Panagiotis Kokkinos (ICCS/NTUA); Yiannis Gkoufas and David Yu Yuan (IBM Research, Ireland); Sezar Jarrous-Holtrup (University of Münster,); Folker Schamel (Spinor GmbH, Germany); Argyrios Kokkinis (Aristotle University of Thessaloniki, Greece); Achilleas Tzenetopoulos (National Technical University of Athens); Remo Andreoli (Scuola Superiore Sant'Anna, Italy); Ricardo Rocha and Maria Girone (CERN); and Stefan Hajnoczi (Red Hat Research) Biographies Biographies Michael Alexander (BOKU, Vienna) Michael Alexander holds degrees in electrical engineering (TGM), business administration (University of Southern California) and economics (University of Vienna). He is currently performing large data analytics for multiple domains and the architecting of clusters. His professional experience includes education and product management at IBM, and Alcatel. Prior he was a HPC Specialist at TU Wien and a Product Line Manager for Alcatel ADSL and Optical Access Networks. He is the author of a textbook on networks and network security published by Hüthig/Verlagsgruppe Süddeutsche, and editor of a special issue on mathematical methods in network management of the Wiley International Journal of Network Management. For the last sixteen years, he has served as the Program Committee Chair for VHPC, Workshop on Virtualization in High-Performance Cloud Computing. His current research interests include content centric networking, distributed databases, virtualization system-network management. Anastassios Nanos (Nubificus Ltd.) With over 12 years of experience in Virtualization technologies, Anastassios Nanos is currently working on the lower-level parts of the stack to attack issues related to performance, scalability, power-efficiency, and security in hypervisors. Previously, he was a post-doc at CSLab, NTUA, working on bridging the gap between common HPC practices and virtualization. His research interests include I/O Virtualization, systems software for high-performance I/O in virtualized environments, systems support for heterogeneous platforms, communication architectures for clusters, and scalable storage architectures based on clusters. He holds a Diploma in Engineering (2006) from ECE, NTUA and a PhD in Computer Engineering (2013) from NTUA. He has been involved in EU-funded projects, conducting research in emerging, power-efficient micro-server architectures on scalable network and storage I/O, and energy-driven resource management in cloud architectures. Anastasios Nanos (Nubificus LTD) With over 12 years of experience in Virtualization technologies, Anastassios Nanos is currently working on the lower-level parts of the stack to attack issues related to performance, scalability, power-efficiency, and security in hypervisors. Previously, he was a post-doc at CSLab, NTUA, working on bridging the gap between common HPC practices and virtualization. His research interests include I/O Virtualization, systems software for high-performance I/O in virtualized environments, systems support for heterogeneous platforms, communication architectures for clusters, and scalable storage architectures based on clusters. He holds a Diploma in Engineering (2006) from ECE, NTUA and a PhD in Computer Engineering (2013) from NTUA. He has been involved in EU-funded projects, conducting research in emerging, power-efficient micro-server architectures on scalable network and storage I/O, and energy-driven resource management in cloud architectures. Charalampos Mainas (Nubificus LTD) TBU Panagiotis Kokkinos (ICCS/NTUA) TBU Yiannis Gkoufas (IBM Research, Ireland) TBU David Yu Yuan (IBM Research, Ireland) TBU Sezar Jarrous-Holtrup (University of Münster,) TBU Folker Schamel (Spinor GmbH, Germany) TBU Argyrios Kokkinis (Aristotle University of Thessaloniki, Greece) TBU Achilleas Tzenetopoulos (National Technical University of Athens) TBU Remo Andreoli (Scuola Superiore Sant'Anna, Italy) TBU Ricardo Rocha (CERN) TBU Maria Girone (CERN) TBU Stefan Hajnoczi (Red Hat Research) TBU Abstract Abstract Containers and virtualization technologies constitute key enabling factors for flexible resource management in modern data centers, and particularly in cloud environments. HPC operators and cloud providers need to manage complex infrastructures in a seamless fashion to support the highly dynamic and heterogeneous workloads and hosted applications customers deploy. Various virtualization-containerization technologies contribute to the overall picture in different ways: machine virtualization, with its capability to enable consolidation of multiple underutilized servers with heterogeneous software and operating systems (OSes), and its capability to live-migrate a fully operating virtual machine (VM) with a very short downtime, enables novel and dynamic ways to manage physical servers; OS-level virtualization (i.e., containerization), with its capability to isolate multiple user-space environments and to allow for their coexistence within the same OS kernel, promises to provide many of the advantages of machine virtualization with high levels of responsiveness and performance; lastly, unikernels provide for many virtualization benefits with a minimized OS/library surface. The Workshop on Virtualization in High-Performance Cloud Computing (VHPC) aims to bring together researchers and industrial practitioners facing the challenges posed by virtualization, containerization, and orchestration techniques for deploying HPC and HPC-like applications in large data centers. Workshop Website https://vhpc.org pdfFriday 2:00pm-6:00pm Workshop Deep Learning on Supercomputers Valeriu Codreanu (SURFsara); Ian T. Foster (University of Chicago, Argonne National Laboratory); Zhao Zhang (Texas Advanced Computing Center); Torsten Hoefler (ETH Zurich); Arvind Ramanathan (Argonne National Laboratory); Alexandre Bonvin and Manon Réau (Utrecht University); Stefan Kesselheim (Jülich Supercomputing Center); Jonas Teuwen (Netherlands Cancer Institute); and Chen Liu (SambaNova Systems) Biographies Biographies Valeriu Codreanu (SURFsara) Valeriu Codreanu studied Electrical Engineering and got his MSc at the Polytechnic University of Bucharest. He followed-up with a PhD in Computer Architecture at the same institute, graduating in 2011. Valeriu continued as a researcher at Eindhoven University of Technology and University of Groningen, working on GPU computing, computer vision, and embedded systems. In 2014, he joined SURFsara as an HPC consultant, and in 2016 he became the PI of an Intel Parallel Computing Center project on ‘Scaling up deep learning’. Valeriu is currently leading the High-Performance Machine Learning group at SURFsara, and is focused on applying deep learning techniques to real-world applications from various scientific fields. Ian T. Foster (University of Chicago, Argonne National Laboratory) Dr. Ian Foster is the Director of Argonne’s Data Science and Learning Division, Argonne Senior Scientist and Distinguished Fellow and the Arthur Holly Compton Distinguished Service Professor of Computer Science at the University of Chicago. Foster’s research contributions span high-performance computing, distributed systems, and data-driven discovery. He has published hundreds of scientific papers and eight books on these and other topics. Methods and software developed under his leadership underpin many large national and international cyberinfrastructures. Foster received a BSc (Hons I) degree from the University of Canterbury, New Zealand, and a PhD from Imperial College, United Kingdom, both in computer science. His awards include the Global Information Infrastructure (GII) Next Generation award, the British Computer Society’s Lovelace Medal, R&D Magazine’s Innovator of the Year, the IEEE Tsutomu Kanai award. Zhao Zhang (Texas Advanced Computing Center) Dr. Zhao Zhang is a computer scientist at Texas Advanced Computing Center. His current research focus is scalable deep learning on supercomputers. Dr. Zhang's past work include astronomy data processing with Apache Spark, machine learning diagnostics, and I/O optimization for many-task computing applications on supercomputers, such as Argonne's IBM Blue Gene/P. Before joining TACC, Dr. Zhang was a postdoc researcher in AMPLab and a data science fellow at Berkeley Institute for Data Science at University of California, Berkeley, working with Prof. Michael J. Franklin. He received Ph.D in computer science from University of Chicago in 2014 under supervision of Prof. Ian T. Foster. Torsten Hoefler
Arvind Ramanathan
Alexandre Bonvin
Manon Réau
Stefan Kesselheim
Jonas Teuwen (Netherlands Cancer Institute) Jonas is currently the "AI for Oncology" group leader at the Netherlands Cancer Institute. Previously, after his studies in Applied Mathematics at the Delft University of Technology he completed his PhD titled "Shedding new light on Gaussian harmonic analysis" at the same university. He started as a postdoctoral researcher in 2016 at the Netherlands Cancer Institute/Antoni van Leeuwenhoek hospital and continued within the Diagnostic Image Analysis Group at the Radboud Medical Center. His current work focuses on efficient deep learning algorithms for cancer detection in breast image modalities. Chen Liu
Abstract Abstract The Deep Learning (DL) on Supercomputers workshop provides a forum for practitioners working on any and all aspects of DL for science and engineering in the High Performance Computing (HPC) context to present their latest research results and development, deployment, and application experiences. The general theme of this workshop series is the intersection of DL and HPC; the theme of this particular workshop is the applications of DL methods in science and engineering: novel uses of DL methods, e.g., convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), and reinforcement learning (RL), in the natural sciences, social sciences, and engineering, to enhance innovative applications of DL in traditional numerical computation. Its scope encompasses application development in scientific scenarios using HPC platforms; DL methods applied to numerical simulation; fundamental algorithms, enhanced procedures, and software development methods to enable scalable training and inference; hardware changes with impact on future supercomputer design; and machine deployment, performance evaluation, and reproducibility practices for DL applications with an emphasis on scientific usage. This workshop will be centered around published papers. Submissions will be peer-reviewed, and accepted papers will be published as part of the Joint Workshop Proceedings by Springer. Workshop Website https://dlonsc.github.io/ pdfFriday 2:00pm-6:00pm Workshop 2nd International Workshop on Machine Learning Hardware Pete Beckman and Swann Perarnau (Argonne National Laboratory), Rosa M. Badia (Barcelona Supercomputing Center), Kentaro Sano (RIKEN), Valentin Reis (Groq), Prasanna Balaprakash (ANL), Rob Schreiber (Cerebras), Tony Hey (STFC), Michaela Blott (Xilinx), Tianjian Lu (Google Research), Haohuan Fu (Tsinghua University), and Takano Ryousei (AIST) Biographies Biographies Pete Beckman (Argonne National Laboratory) Pete Beckman is the co-director of the Northwestern-Argonne Institute for Science and Engineering. From 2008-2010 he was the director of the Argonne Leadership Computing Facility, where he led the Argonne team working with IBM on the design of Mira, a 10 petaflop Blue Gene/Q. Pete coordinates the collaborative research activities in extreme-scale computing between the US Department of Energy and Japan’s ministry of education, science, and technology (MEXT), and leads Argo, an Exascale Computing Project focused on low-level resource management for the OS and runtime. He is the founder and leader of the Waggle project for AI@Edge. The Waggle technology and software framework is being used by the Chicago Array of Things project and is deployed in over 10 cities around the world. Dr. Beckman has a Ph.D. in Computer Science from Indiana University (1993) Swann Perarnau (Argonne National Laboratory) Swann Perarnau is an Assistant Computer Scientist at Argonne. He leads the topology, memory and power management efforts for the Argo ECP project. In particular, he is designing low-level system software mechanisms to help applications discover the features and performance of complex heterogeneous hardware, as well as composable abstractions to make the most efficient use of it. Rosa M. Badia (Barcelona Supercomputing Center) Rosa M. Badia holds a PhD from the UPC (1994). She is the manager of the Workflows and Distributed computing group at the Barcelona Supercomputing Center (BSC). She is a Scientific Researcher at the Spanish National Research Council (CSIC). She graduated on Computer Science at the Facultat d' Informàtica de Barcelona (UPC, 1989). She was lecturing and doing research at the Computer Architecture Department (DAC) at the UPC from 1989 to 2008, where she held an Associate Professor position from 1997 to 2008; she is currently part-time lecturing again at the same department. Kentaro Sano (RIKEN) Kentaro Sano is the team leader of the Processor Research team at RIKEN. Dr. Kentaro Sano received his Ph.D. from GSIS, Tohoku University, in 2000. Since 2000 until 2005, he had been a Research Associate at Tohoku University. Since 2005 until 2018, he has been an Associate Professor at Tohoku University. He was a visiting researcher at the Department of Computing, Imperial College, London, and Maxeler corporation in 2006 and 2007. Since 2017 until present, he has been a team leader of a processor research team at R-CCS, Riken. His research interests include FPGA-based high-performance reconfigurable computing systems especially for scientific numerical simulations and machine learning, high-level synthesis compilers and tools for reconfigurable custom computing machines, and system architectures for next-generation supercomputing based on the data-flow computing model. Valentin Reis (Groq) Valentin Reis is a Software Engineer at Groq, Inc. He previously was a Postdoctoral appointee at Argonne National Laboratory and obtained his PhD from the University of Grenoble Alpes. His interests span machine learning, functional programming and HPC infrastructure. Prasanna Balaprakash
Rob Schreiber
Tony Hey
Michaela Blott
Tianjian Lu
Haohuan Fu
Takano Ryousei
Abstract Abstract Recent years have seen a surge of investment in AI chip companies worldwide. These companies are however mostly targeting applications outside of the scientific computing community. As the use of ML accelerates in the HPC field itself, there is concern that the scientific community should influence the design of this new specialized hardware. Indeed, scientific computing has a distinctive set of requirements regarding workload type, usage model, and platform administration. How those chips answer those demands will shape the future of their integration within the global scientific computing infrastructure. In this workshop, we propose to let the community and select vendors engage on questions related to the low-level aspects of this new hardware and its integration with HPC systems, as well as to the software APIs and compiler toolchains that will be available. This proposal follows the outcome of a successful ISC20 workshop where an emphasis on compiler technology emerged. In this iteration, we will push the agenda further by discussing existing efforts to leverage ML hardware for scientific HPC applications. Workshop Website https://mlhardware.github.io pdfFriday 2:00pm-6:00pm Workshop Numerical Algorithms and Libraries for Exascale Hatem Ltaief, Bilel Hadri, and David Keyes (KAUST); Daniel Grünewald (Fraunhofer ITWM); Laura Grigori (INRIA); Alfredo Buttari (CNRS-IRIT); Hartwig Anzt (Karlsruhe Institute of Technology); Ulrike Yang (Lawrence Livermore National Laboratory); and John Shalf (Lawrence Berkeley National Laboratory) Biographies Biographies Hatem Ltaief (KAUST) Hatem Ltaief is a Principal Research Scientist in the Extreme Computing Research Center at KAUST, where is also advising several KAUST students in their MS and PhD research. His research interests include parallel numerical algorithms, parallel programming models, performance optimizations for manycore architectures and high performance computing. Hatem received the engineering degree from Polytech Lyon at the University of Claude Bernard Lyon I, the MSc in applied mathematics and the PhD degree in computer science at the University of Houston. He has contributed to the integration of numerical algorithms into mainstream vendors’ scientific libraries, such as NVIDIA cuBLAS and Cray LibSci. He has been collaborating with domain scientists, i.e., astronomers, statisticians, computational chemists and geophysicists, on leveraging their applications to meet the challenges at exascale. Bilel Hadri (KAUST) Bilel Hadri is a computational scientist at the Supercomputing Lab at KAUST since July 2013. He is leading efforts in benchmarking and performance optimization and helping in coordinating strategic efforts for systems procurements, upgrades and provides regular training to users. He received his Master in Applied Mathematics and his PhD in Computer Science from the University of Houston in 2008. He joined the National Institute for Computational Science at Oak Ridge National Lab as a computational scientist in December 2009 following a Postdoctoral Position in June 2008 at the University of Tennessee Innovative Computing Laboratory lead by Dr. Jack Dongarra. His expertise area includes Linear Algebra, Numerical Analysis, Performance Analysis Tuning and Optimization, System Utilization Analysis, Monitoring and Library Tracking Usage. David Keyes
Daniel Grünewald
Laura Grigori
Alfredo Buttari
Hartwig Anzt
Ulrike Yang
John Shalf
Abstract Abstract With the hardware technology scaling and the trend on heterogeneous chip design, the existing numerical algorithms and software framework may break down due to load imbalance. There is currently a fundamental mismatch between the underlying hardware architecture with high thread concurrency and the software deployment of numerical libraries, which relies on the traditional bulk synchronous programming model. Numerical software should first squeeze performance out of single node by efficiently running on manycore architectures with processor counts sharing a common memory in the hundreds. Programming and extracting performance from these advanced architecture chips remain a challenging effort, which is further exacerbated in distributed-memory environment. Algorithmic solutions such as fine-grained computations, communication/synchronization-reducing, and mixed precisions come to the rescue. They represent some of the key ingredients to embrace for software libraries moving forward and leverage extreme-scale computing capabilities. Workshop Website https://cemse.kaust.edu.sa/hicma/events/event/isc21-workshop-numerical-algorithms-and-libraries-exascale-nal-x pdfFriday 2:00pm-6:00pm Workshop Approximate and Transprecision Computing on Emerging Technologies (ATCET) - Second Edition A. Cristiano I. Malossi (IBM Research - Zurich); Luca Benini (Dep. of Inform.Technol. Electrical Eng., ETH Zurich, Switzerland); Norbert Wehn (Dep. of Electrical and Computer Engineering, Technische Universität Kaiserslautern, Germany); Roger Woods (School of Electronics, Electrical Engineering and Computer Science, Queen's University, Belfast, United Kingdom); Andrew Emerson (Department of High Performance Computing, CINECA, Italy); Frank K. Gurkaynak (ETH Zürich); Alberto Bosio (École Centrale de Lyon); Dimitrios S. Nikolopoulos (Virginia Tech); Christos-Savvas Bouganis (Imperial College); and Enrique Salvador Quintana Ortí (Universitat Politècnica de València) Biographies Biographies A. Cristiano I. Malossi
Luca Benini
Norbert Wehn
Roger Woods
Andrew Emerson
Frank K. Gurkaynak
Alberto Bosio
Dimitrios S. Nikolopoulos
Christos-Savvas Bouganis
Enrique Salvador Quintana Ortí
Abstract Abstract Guaranteed numerical precision of each elementary step in a complex computation has been the mainstay of traditional computing systems for many years. This era is at its twilight: to overcome the “power wall” in Exascale systems, a shift from traditional computing paradigms is now mandatory. This workshop will investigate the theoretical and practical understanding of the energy efficiency boost obtainable when accuracy requirements on data being processed, stored and communicated can be lifted for intermediate calculations. The target applications range from Big Data Analytic and Deep Learning, up to classical scientific computing simulations in HPC environments. Workshop Website http://oprecomp.eu/atcet-2021 pdfFriday 2:00pm-6:00pm Workshop Arm HPC User Group (AHUG) 2021 Jonathan C. Beard (Arm Research), Jeffrey Young (Georgia Tech), Roxana Rusitoru (Arm Research), Oscar Hernandez (NVIDIA), Andrew Younge (Sandia National Lab), RuQing (G.) Xu Xu (University of Tokyo), Yuetsu Kodama (RIKEN R-CCS), Steve Messenger (Amazon), Srinath Vadlamani (Arm), Miwako Tsuji (RIKEN R-CCS), Stepan Nassyr (Juelich Supercomputing Centre), Federica Filippini (Politecnico di Milano), Andrei Poenaru (University of Bristol), John Linford (Arm), Jeff Hammond (NVIDIA), Luigi Genovese (Atomistic Simulation Laboratory (L_Sim) - CEA Grenoble), Miquel Moreto (Barcelona Supercomputing Center), Hatem Ltaief (KAUST), Bine Brank (Juelich Supercomputing Centre), Eva Siegmann (Stony Brook University), Sarat Sreepathi (Oak Ridge National Laboratory), Andrew Younge (Sandia National Laboratories), Thomas Chen (U.S. Technology Policy Committee), and Craig Prunty (SiPearl) Biographies Biographies Jonathan C. Beard (Arm Research) Jonathan is currently a staff computer architecture researcher focusing on next generation architectures for Big Data beyond exascale. Jonathan also has served as a technical advisor to many start-up companies, and has given talks ranging from C++ parallel runtimes to debating exascale memory architectures at Supercomputing. Jonathan Beard received a BS (Biology) and BA (International Studies) in 2005 from the Louisiana State University, MS (Bioinformatics) in 2010 from The Johns Hopkins University, and a PhD in Computer Science from Washington University in St. Louis in 2015. Jonathan served as a U.S. Army Officer where he served in roles ranging from medical administrator, to Aide-de-Camp, to acting director of the medical informatics department for the U.S. Army in Europe. Jonathan's research interests also include online modeling of stream/data-flow parallel systems and extremely heterogeneous systems. Jeffrey Young (Georgia Tech) Jeffrey (Jeff) Young is a research scientist in Georgia Tech's School of Computer Science and the managing director of the Arm HPC User Group. His main research interests include investigating scheduling and data movement for accelerators like GPU and Xeon Phi and working to model and map algorithms to high-performance architectures. He is currently working on a collaborative research program that is focused on mapping bandwidth-intensive algorithms to 3D stacked memories like Hybrid Memory Cube (HMC) and High Bandwidth Memory (HBM) and on performing near-memory computation on devices like FPGAs and GPUs. He received his PhD in computer engineering in 2013 from Georgia Tech's ECE department. Roxana Rusitoru (Arm Research) Roxana Rusitoru is a Senior Research Engineer in Arm’s Research division, working in Software and Large Scale Systems. She joined Arm in 2012 after obtaining an MEng degree in Computing (Software Engineering) from Imperial College London in optimising unstructured mesh CFD applications on multicores via machine learning and code transformation. At Arm, amongst others, she has worked on Linux kernel optimizations aimed at HPC and sensitivity studies aimed to showcase Arm AArch64 microprocessor characteristics suitable for HPC. Most recently, she has been working on power-aware scheduling at OS level for heterogeneous cores and methodologies to identify representative sub-sections from multi-threaded applications. Some of her research interests are software performance optimization and next-gen heterogeneous architectures. Roxana has been a part of the Mont-Blanc 1 and 2 projects, and is now leading the Software ecosystem in Mont-Blanc 3, in addition to technical contributions. Oscar Hernandez (NVIDIA) Oscar Hernandez has a Phd in Computer Science and recently joined NVIDIA/Mellanox in 2021 after working 12 years at Oak Ridge National Laboratory (ORNL) where he was a senior staff member of the Programming Systems Group, which does research on programming models, compilers and tools that are deployed at supercomputers like Summit and Frontier at the Leadership Computing Facility (OLCF). At ORNL he helped standardize parallel languages and APIs for accelerated nodes such as OpenACC/OpenMP and communication libraries and frameworks like OpenSHMEM and UCX. He also worked for the Exascale Computing Project where he led different efforts to deploy these technologies on Exascale systems. He also worked closely with application teams including the CAAR, INCITE and ALCC projects and on many projects funded by DOE, DoD, NSF, and Industrial Partners in the Oil & Gas industry.Oscar has a lot of experience giving tutorials in different venues, like Supercomputing, ISC, ECP Annual Meeting and NSF. Andrew Younge (Sandia National Lab) Andrew Younge is a R&D Computer Scientist at Sandia National Laboratories with the Scalable System Software group. His research interests include High Performance Computing, Virtualization, Distributed Systems, and energy efficient computing. The central focal point of Andrew’s work is to improve the usability and efficiency of supercomputing system software. Andrew has a Ph.D in Computer Science from Indiana University, where he was the Persistent Systems fellow and a member of the FutureGrid project, an NSF-funded experimental cyberinfrastructure test-bed. Over the years, Andrew has held visiting positions at the MITRE Corporation, the University of Southern California / Information Sciences Institute, and the University of Maryland, College Park. He received his Bachelors and Masters of Science from the Computer Science Department at Rochester Institute of Technology (RIT) in 2008 and 2010, respectively. RuQing (G.) Xu Xu (University of Tokyo) RuQing (G) Xu is a 2nd year postgrad in physics now in the University of Tokyo. (https://qsl.r-xu.dns-cloud.net). I'm primarily working on computational sciences in a solid state physics context, with special focus on variational wavefunction optimization and tensor network methods. As a result, my work is very sensitive to the performance of linear algebra libraries (BLAS-level, LAPACK-level, sparse LAPACK-level, etc.). I got to know BLIS and Arm on HPC when trying to optimize our variational quantum solver on supercomputer Fugaku. Experience working with Arm processors turned out to be smooth and fruitful, with our lab program accelerated up to ~6x and BLIS on SVE almost production-ready. Apart from performance libraries, I'm a keen user of programming language Julia. Wrappers for BLIS and TBLIS are made to exploit flexibility of BLIS framework as well as Julia language itself. Improving Julia ecosystem on aarch64 is yet another thing I want to contribute to in the coming few years. Yuetsu Kodama (RIKEN R-CCS) Yuetsu Kodama is a senior scientist at RIKEN CCS (Center for Computational Science) from 2015. He received the B.E., M.E. and Ph.D degree in engineering from the University of Tokyo in 1986, 1988 and 2003, respectively. He was a professor at University of Tsukuba in 2011-2015, a senior researcher at AIST (National Institute of Advanced Industrial Science and Technology) in 2000-2011 and a senior researcher at ETL (Electrotechnical Laboratory) in 1988-1999. He has been engaged in the research on parallel computer architecture. He is a member of IEEE CS, IEICE and IPSJ. Steve Messenger (Amazon) Stephen Messenger is a Senior HPC specialist Solutions Architect for AWS. He has worked with HPC and Cloud technology for the last 15 years, working on many different projects from personal clusters that fit under a desk, to some of the largest Super Computers in the world. He is still slightly amazed that anyone will pay him for tinkering with computers. When Stephen is not working he enjoys spending time mountain biking, in the New Forest or the South Downs in England. Srinath Vadlamani (Arm) Srinath Vadlamani, Ph.D. is an HPC Field Application Engineer with Arm. Inc. He specializes in scientific application efficacy on HPC systems with a focus on Arm enabled systems. Current interests include computation/communication overlap strategies and threading strategies. Srinath is part of the US Fortran Programming Language Standards Technical Committee. Miwako Tsuji (RIKEN R-CCS) Miwako Tsuji received master and PhD degrees from Information Science and Technology, Hokkaido University. From 2007 to 2013, she was working in University of Hokkaido, University of Tokyo, University of Tsukuba and Universite de Versailles Saint-Quentin-en-Yvelines. She is a research scientist at RIKEN Center for Computational Science. She was a member of the flagship 2020 project, which had conducted the disign and development of the supercomputer Fugaku during the full period of the project. Her current research interests are programming model and performance model of the large-scale high performance computing. She is a coauthor of the ACM Gordon Bell Prize in 2011. Stepan Nassyr (Juelich Supercomputing Centre) After studying physics at the Bergische Universitat Wuppertal, Stepan Nassyr joined the Juelich Supercomputing Centre in July 2017 to work on his PhD dealing with future ARM-based supercomputer architectures. As part of the application oriented technology group at the Juelich Supercomputing Centre he has worked extensively with the ARM ecosystem and the ARM SVE extension, focusing mostly on hand-written assembly kernels and the requirements to the microarchitecture and memory architecture to effectively exploit the available compute capabilities in the context of HPC applications. Aside from his PhD, he is also administering a small ARM-based cluster at the JSC and has experience with a number of ARM-based HPC architectures, including Marvell ThunderX2, Huawei Kunpeng 920 and Fujitsu's A64FX. Federica Filippini (Politecnico di Milano) tbd Andrei Poenaru (University of Bristol) Andrei Poenaru is a final-year PhD Student with the High Performance Computing Group at the University of Bristol. His research is centred around advanced and future architectures for HPC, and he has been involved in several studies aiming to characterise performance and evaluate portability across diverse modern architectures. His current projects are focused on vectorisation in the context of Arm SVE and upcoming Arm-based high-performance processors. John Linford (Arm) John is Arm's Director for HPC Engineering. He leads a worldwide team of HPC experts focused on making Arm a win for HPC and vice versa. Jeff Hammond (NVIDIA) Jeff Hammond is a Principal Architect at NVIDIA, where he focuses on parallel programming models for GPUs and ARM CPUs. He has contributed to NWChem since 2006. Luigi Genovese (Atomistic Simulation Laboratory (L_Sim) - CEA Grenoble) I am a Computational Physicists in the domain of Material Sciences, with a education in Theoretical High Energy Physics. My present research interests are related to the conception, development, and implementation of new theoretical algorithms and methods exploiting advanced computing resources, enabling large-scale computation in diverse areas in Solid-State physics, Quantum Chemistry, and Electronic Structure calculations with applications in Life-Sciences and Biology. Miquel Moreto (Barcelona Supercomputing Center) Miquel Moreto is a Ramon y Cajal Fellow at the Computer Architecture Departament (DAC) at the Universitat Politecnica de Catalunya-Barcelona Tech (UPC), where he teaches Computer Architecture. He is leading the High Performance Domain Specific Architectures team at the Barcelona Supercomputing Center (BSC). He received the BSc, MSc, and PhD from the UPC. His PhD thesis advisors were Mateo Valero (UPC) and Francisco J. Cazorla (BSC). During his PhD, he interned at IBM T. J. Watson Research Center for 4 months, and visited the Universities of Edinburgh and Cantabria for 3 months. After finishing the PhD, he spent 15 months at the International Computer Science Institute (ICSI), affiliated with UC Berkeley, as a Fulbright Postdoctoral Research Fellowship Holder during 2011 and 2012. Finally, he spent 2 months in Arm Research (Cambridge, UK) as a Visiting Professor in 2017. Hatem Ltaief (KAUST) Hatem Ltaief is a principal research scientist with the Extreme Computing Research Center, King Abdullah University of Science and Technology, Saudi Arabia. His research interests include parallel numerical algorithms, parallel programming models, and performance optimizations for multicore architectures and hardware accelerators. Bine Brank (Juelich Supercomputing Centre) "Bine Brank is a PhD student at Juelich Supercomputing Centre. After obtaining his Master's degree in Computer Simulation from the University of Wuppertal, he has joined the application-oriented technology development team at JSC. There, he is working in the context of Mont-Blanc 2020 and the European Processor Initiative project. The main topic of his dissertation is SIMD parallelisation with a focus on Arm's SVE. This includes porting of applications to Arm architectures as well as evaluation of compiler's auto-vectorisation capabilities. " Eva Siegmann (Stony Brook University) Eva Siegmann has a PhD in applied mathematics. She has extensive experience in the field of high-performance computing with special focus on simulations in the field of pharmaceutical engineering. Beginning of this year Eva joined the Stony Brook University where she is the lead research scientist in the Ookami project. Ookami is testbed which provides researchers with state-of-the-art hardware, including Fujitsu A64FX processors. Sarat Sreepathi (Oak Ridge National Laboratory) Sarat Sreepathi is a Computer Scientist interested in interdisciplinary research at the intersection of High Performance Computing and domain sciences. He is a member of the Computational Earth Sciences Group in the Computational Sciences and Engineering Division at Oak Ridge National Laboratory. He received his Ph.D. in Computer Science from North Carolina State University. He is the Chair of the OLCF User Group Executive Board and serves on the NERSC User Group Executive Committee. He co-leads the Performance group for the Energy Exascale Earth System Model. He is also a member of Exascale Computing Project (ECP) application teams (Climate: E3SM-MMF and Nuclear Fusion: XGC) . Thomas Chen (U.S. Technology Policy Committee) Thomas Chen is a researcher scientist whose primary interests lie in machine learning and high-performance computing. He serves on the U.S. Technology Policy Committee of the Association for Computing Machinery. As much of his work lies at the nexus of artificial intelligence and earth science, he is also an active early-career scientist member of the European Geosciences Union and the American Geophysical Union. He particularly enjoys using Python to conduct research that has real-world impacts. Previously, Thomas has presented work at a number of conferences, workshops, and meetings, from NeurIPS workshops, to Applied Machine Learning Days, to the Open Data Science Conference, to Machine Learning Week Europe. Craig Prunty (SiPearl) Craig Prunty, SiPearl VP Marketing & Business Development, joined SiPearl in May 2020. Prior to SiPearl, Craig was Marketing Director for Marvell Semiconductor’s Server Processor Business Unit in Santa Clara, California. His 20+ years in the Semiconductor industry include sales, marketing, and technical roles with Cavium, AppliedMicro (AMCC), Lockheed-Martin, and Unisys. Craig holds a B.S. in Mathematics from Lewis & Clark College in Portland, Oregon, and an MS in Electrical Engineering from San Diego State University. Abstract Abstract After the success and great interest from the last 3 years, Arm HPC User's Group at ISC will be bringing an even more diverse and exciting panel of topics ranging from the latest Arm-based systems, to programming for arm, co-design, to new HPC areas, such as deep learning, edge, and data-center analytics. Workshop Website https://a-hug.org/isc-2021-event/ pdfFriday 2:00pm-6:00pm Workshop Workshop on the In Situ Co-Execution of High-Performance Computing & Data Analysis Julien Bigot (Commissariat à l'énergie atomique et aux énergies alternatives), Bruno Raffin (Inria), Leonardo Bautista Gomez (Barcelona Supercomputing Center), Wounter Klinj (Forschungszentrum Julich), Charles Gueunet (Kitware), Sai Narasimhamurthy (Seagate Systems), Achim Basermann (DLR), Matthieu Dorier (ANL), Amal Gueroudji (CEA), Tiago Quintino (ECMWF), Dirk Pleiter (Forschungszentrum Julich), Alejandro Ribes (EDF), Virginie Grandgirard (CEA), and Yuuichi Asahi (JAEA) Biographies Biographies Julien Bigot
Bruno Raffin
Leonardo Bautista Gomez (Barcelona Supercomputing Center) Dr. Leonardo Bautista Gomez is a Senior Research Scientist at the Barcelona Supercomputing Center where he work on resilience and scalability for high-performance computing and machine learning. He was awarded the 2016 IEEE TCSC Award for Excellence in Scalable Computing (Early Career Researcher). Before moving to BSC he was a Postdoctoral researcher for 3 years at the Argonne National Laboratory, where he investigated data corruption detection techniques and error propagation. Prior to that, he did his PhD. in resilience for supercomputers at the Tokyo Institute of Technology. He developed a scalable multilevel checkpointing library called Fault Tolerance Interface (FTI) to guarantee application resilience at extreme scale. For this work, he was awarded the 2011 ACM/IEEE George Michael Memorial High-Performance Computing Ph.D. Fellow at Supercomputing Conference 2011 (SC11), Honorable Mention. Before moving to Tokyo Tech, he graduated in Master for Distributed Systems from the Paris 6 University. Wounter Klinj (Forschungszentrum Julich) Wouter Klijn completed a MSc in Artificial Intelligence from the University of Groningen in the Netherlands. His Master thesis was on the information content of cell species in a 3 layer model of a cortical micro-column. He currently is a software architect in the Simlab Neuroscience at the Forschungzentrum Jülich with a focus on in Artificial Intelligence, information theory of neural networks, big data real-time streaming systems and development of complex HPC processing pipelines. He is responsible for science and use case management in the Human Brain Project, an EU Flagship Project and ICEI, the Interactive Computing E-Infrastructure for the Human Brain Project. He is currently creating the science and software infrastructure architecture for the HBP. He also works with advanced HPC oriented AI solutions and multiple neural simulators. His modelling work is focused on self-organizing dynamics of extremely large neural networks with a 2d spatial structure. Charles Gueunet (Kitware) Charles Gueunet joined Kitware in February 2016. For the first three years, he worked on his PhD on the topic of “High Performance Level-set based Topological Data Analysis”, and became one of the main contributors of the Topology ToolKit (TTK). After defending in February 2019, Charles joined the Scientific Visualization team at Kitware. He now works on various projects involving parallel programming, discrete geometry and data analysis algorithms. Sai Narasimhamurthy
Achim Basermann (DLR) Dr Achim Basermann is head of the department “High-Performance Computing” at German Aerospace Center’s (DLR) Simulation and Software Technology institute and German Research Foundation (DFG) review board member in computer science, topic “Massively Parallel and Data Intensive Systems”. In 2019, he became chairman of the strategy commission for national high-performance computing (NHR) in Germany. He coordinated the application workpackage in the European Grid computing project NextGRID (2004-2007), the pre- and postprocessing activities in the European Exascale computing project CRESTA (2011-2014) and the algorithmic research in the Exascale computing projects ESSEX I and II (2013-2018) of DFG. In 1995, he obtained his Ph.D. in Electrical Engineering from RWTH Aachen followed by a postdoctoral position in Computer Science at Research Centre Jülich GmbH, Central Institute for Applied Mathematics. From 1997 to 2009 he led a team of HPC application experts at the C&C Research Laboratories, NEC Europe Ltd., in Sankt Augustin, Germany and contributed to the Japanese Earth Simulator project. Current research is focussed on massively parallel linear algebra algorithms, partitioning methods, optimization tools in the area of computational fluid dynamics for many-core architectures and GPGPU clusters, high-performance data analytics and quantum computing. Matthieu Dorier
Amal Gueroudji
Tiago Quintino (ECMWF) Dr Tiago Quintino is a Senior Analyst and Team Leader for Development of Production Services at ECMWF. He and his team develop high-throughput specialist software that supports ECMWF’s operational meteorological forecast model, systems for acquisition of incoming observations, management of direct model output, perpetual archival of weather observations and forecast data, and post-processing, generation and dissemination of meteorological products. His team also develops cloud meteorological and climate data provisioning services (Data-as-a-Service) in support of ECMWF’s cloud activities. Dr Quintino’s career spans 20 years researching numerical algorithms and developing high performance scientific software in the areas of Aerospace and Numerical Weather Prediction. Lately, his research focuses on scalable data handling algorithms for generation of meteorological forecast products, optimising their workloads and I/O of massive data-sets. Dirk Pleiter
Alejandro Ribes (EDF) Dr. Alejandro Ribés graduated in computer science (bachelor’s and master’s) from the Universitat Jaume I, Castelló (ES). He later graduated, from Université de Nice Sophia-Antipolis (FR), in a master in image processing and computer vision. Alejandro Ribés also holds a Ph.D. in multispectral imaging applied to fine art paintings, from the Ecole Nationale Supérieure des Télécommunications (FR). He later was a postdoctoral fellow at the CEA laboratory in Orsay (FR), working on parallel MRI reconstruction. During this postdoc he was appointed as a lecturer at the Computer Science Department of Ecole Polytechnique, Palaiseau, France, where he taught for two years. Alejandro also worked in MRI technology, during more than two years, as a visiting scholar at the National Yang-Ming University, Taipei, Taiwan. In 2009, Alejandro Ribés became a Research Scientist at the R&D department of EDF. In December 2016, he became Principal Research Scientist. He recently introduced AI based methods on the context of advanced numerical simulation, especially deep neural networks trained using GPU clusters. From 2013, Alejandro Ribés also collaborates with Sorbonne Université (FR). Virginie Grandgirard
Yuuichi Asahi
Abstract Abstract Exascale promises to support disruptive numerical experiments generating unprecedented quantity and quality of data. Only the latest advances in automated data analytics based on machine-learning or statistical analysis will make it possible to extract knowledge out of the data generated at this scale. It is thus critical to consider the numerical experiment as a whole, encompassing both its simulation (HPC) and data-analytics (HPDA) aspects. These two aspects need to be efficiently coupled to overcome the widening performance gap between compute and I/O. This also opens the road for innovative numerical patterns where the outcome of analytics is used to steer the simulation and greatly increase the scientific return of investment for numerical experiments. Workshop Website https://hpcda.github.io/ pdfFriday 2:00pm-6:00pm Workshop The Second Workshop on LLVM Compiler and Tools for HPC Johannes Doerfert (Argonne National Laboratory), Anja Gerbes (Center for Information Services and High Performance Computing), Sameer Shende (University of Oregon), Jeremy Bennett (Embecosm), Shintaro Iwasaki (Argonne National Laboratory), Ernesto Su and Xinmin Tian (Intel), Valentin Clement (Oak Ridge National Laboratory), Arnamoy Bhattacharyya (Huawei), Saiyedul Islam (Advanced Micro Devices (AMD)), Tobias Grosser (University of Edinburgh), and Jeffrey Sandoval (HPE) Biographies Biographies Johannes Doerfert (Argonne National Laboratory) Johannes Doerfert is a researcher in the Argonne Leadership Computing Facility at the Argonne National Laboratory. He develops LLVM and Clang enhancements that enable compiler optimization for parallel programs. Johannes is also part of several ongoing efforts to make compiler software ready for exascale computing. He is an active member of the OpenMP Language Committee and already organized various LLVM related workshops and conferences, including the LLVM Performance Workshops @ CGO, and the EuroLLVM in 2017. Johannes received his Ph.D. in Computer Science from Saarland University in 2018. Anja Gerbes (Center for Information Services and High Performance Computing) Anja works at the Center for Information Services and High Performance Computing at TU Dresden. A considerable part of her job role is to develop a range of courses and resources to enable users to work with the cluster. In addition, she is doing a PhD at the German Climate Research Center in Hamburg as an external member. The main topic is Compiler Optimization in High-Performance Computing with an aim to improve weather forecasting and climate modeling. The goal of her PhD is to study the compiler for deficits in terms of performance when translating HPC applications and to understand the limitations of compilers in making the necessary optimizations. These insights can then be incorporated into the compiler for future automatic compiler optimization. Automatic program transformation using source-to-source instrumentation of parallel programs will prepare HPC applications for future performance analysis. Sameer Shende
Jeremy Bennett (Embecosm) Jeremy Bennett founded in 2008 Embecosm. He is an expert on hardware modeling and embedded software development. Previously Dr Bennett was Vice President of ARC International plc, following their acquisition of Tenison Design where he had been CEO and CTO. Dr Bennett is author of the popular textbook, “Introduction to Compiling Techniques” (McGraw-Hill 1990, 1995, 2003) and holds an MA and PhD in Computer Science from Cambridge University. Shintaro Iwasaki
Ernesto Su
Xinmin Tian
Valentin Clement
Arnamoy Bhattacharyya (Huawei) Arnamoy received his PhD from University of Toronto and currently working in the Heterogeneous compiler lab in Huawei, Canada as a research engineer. He is broadly interested in the area of performance enhancement through compiler optimization, cloud computing and machine learning guided optimizations. He has been actively contributing in the LLVM Flang project (especially for the driver and semantic analysis for OpenMP). Saiyedul Islam
Tobias Grosser
Jeffrey Sandoval
Abstract Abstract The LLVM framework is a vast ecosystem surrounding a compiler core which enabled various advances in source-code tools, debuggers, linkers, and a whole host of programming-language and toolchain-related components. In addition to the open source components in the LLVM framework, e.g., Clang, Flang, MLIR, LLDB, etc., LLVM also serves as a foundation for a majority of vendor compilers and toolchains. As such, most current and future HPC system will come with LLVM components that are developed in large parts in the open source LLVM code base, a multi-company, multi-research institute, industry-academia, joint-venture. Workshop Website https://hps.vi4io.org/events/2021/llvm pdfFriday 2:00pm-6:00pm Workshop 7th Annual High Performance Container Workshop Christian Kniep (AWS); Shane Canon (Lawrence Berkeley National Labs); Andrew Younge (Sandia National Laboratories); Carlos Eduardo Arango Gutierrez (Red Hat); Abdulrahman Azab (University of Oslo, Partnership for Advanced Computing in Europe (PRACE)); Umesh Upadhyaya (HPC Nepal); Michael Kuhn (Otto von Guericke University Magdeburg); and Carsten Kutzner (Max Planck Institute for Biophysical Chemistry) Biographies Biographies Christian Kniep (AWS) Christian is a Specialist Solutions Architect with AWS. With a 10 year journey rooted in the HPC parts of the german automotive industry, Christian Kniep started to support CAE applications and VR installations. When told at a conference that HPC can not learn anything from the emerging Cloud and BigData companies, he became curious and was leading the containerization effort of the cloud-stack at Playstation Now followed by working at Docker Inc as a Technical Account Manager to help push the adoption forward and be part of the innovation instead of an external bystander. At AWS he is helping customers to adopt the cloud efficiently. Shane Canon (Lawrence Berkeley National Labs) Shane Canon joined NERSC in 2000 to serve as a system administrator for the PDSF cluster. While working with PDSF he gained experience in cluster administration, batch systems, parallel file systems and the Linux kernel. In 2005, Shane left LBNL to take a position as Group Leader at Oak Ridge National Laboratory. One of the more significant accomplishments while at ORNL was architecting the 10 petabyte Spider File System. In 2008, Shane returned to NERSC to lead the Data Systems Group. More recently Shane has focused on enabling data intensive applications on HPC platforms and engaging with bioinformatics applications. Shane joined the Data & Analytics Services group in 2016 to focus on these topics. Shane is involved in a number of projects outside of NERSC. He is the Production Lead on the KBase project which is developing a platform to enable predictive biology. Shane has a Ph.D in Physics from Duke University and B.S. in Physics from Auburn University. Andrew Younge (Sandia National Laboratories) Andrew J. Younge is a Senior Member of Technical Staff in the Scalable System Software department at Sandia National Laboratories. He currently serves as the Lead PI for the Supercontainers project under the DOE Exascale Computing Project and is a key contributor to the Astra system, the world's first supercomputer based on the Arm processor deployed under Sandia's Vanguard program. Prior to joining Sandia, Andrew held visiting positions at the MITRE Corporation, the University of Southern California's Information Sciences Institute, and the University of Maryland, College Park. He received his PhD in computer science from Indiana University in 2016. His research interests include high performance computing, virtualization, distributed systems, and energy efficient computing. The focus of his research is on improving the usability and efficiency of system software for supercomputing systems. Carlos Eduardo Arango Gutierrez (Red Hat) Eduardo is a performance engineer at Red Hat, working on the OpenShift performance & latency sensitive applications. Eduardo is also a Computer Science PhD student at Universidad del Valle, Cali, Colombia, working on containerized distributed systems for research computing, with high focus on automated workflows and DevOps. His research interests include High Performance Computing, Distributed systems, Dependency management, Linux containers and most recently, Container orchestration. Over the past 5 years Eduardo has focused on enabling researchers to build and deploy performance sensitive applications with containers on distributed environments. Abdulrahman Azab (University of Oslo, Partnership for Advanced Computing in Europe (PRACE)) Abdulrahman Azab works at the Department of Research Computing, University of Oslo, Norway. In addition he is a senior lecturer at the Department of Computer Engineering and Control Systems, Mansoura University, Egypt. He is leading the Containers-for-HPC service at PRACE (Partnership for Advanced Computing in Europe). Abdulrahman is also the Norwegian sub-project manager at NeIC/Tryggve (Collaboration on Sensitive Data in the Nordics). Abdulrahman is leading the sensitive data working group in both EOSC-hub and EOSC-Nordic (EOSC: European Open Science Cloud). His research interests are: High Performance Computing, High Throughput Computing, High Availability Computing, Linux Containers, Cloud Computing, Cyber Security, Control systems, and Bioinformatics. Umesh Upadhyaya
Michael Kuhn (Otto von Guericke University Magdeburg) Michael Kuhn is a junior professor for Parallel Computing and I/O at Otto von Guericke University Magdeburg. He conducts research in the area of high performance I/O with a special focus on I/O interfaces and data reduction techniques. Other interests of his include file systems and high performance computing in general. Michael is the principal investigator of the CoSEMoS project funded by the German Research Foundation (DFG). Moreover, he is the lead developer of the JULEA storage framework and received a 2019 R&D 100 award for his contributions to the Spack package manager. He regularly offers lectures and courses related to HPC and parallel I/O. Carsten Kutzner
Abstract Abstract Linux Containers have become an industry standard for sharing and distributing software. This workshop will create a space of interaction between field experts,end-users, and newcomers to discuss container technologies and their current and future challenges. Workshop Website https://hpcw.github.io pdf |