Training Discovery

NCSA's Center for AI Innovation invites you to join us on Zoom to hear from distinguished IBM Research Staff Member Peter Hofstee on "A Shared-Memory Approach to Big Data & Analytics." In this talk, Hofstee explores how technological advances that improve memory processing and sharing can change the way large systems & datasets are organized. 

Containers make it possible for scientists and engineers to easily use portable and reproducible software environments. However, if the desired application is not already available from a container registry, generating a custom container image from scratch can be challenging for users accustomed to a bare metal software environment. HPC Container Maker (HPCCM) is an open source project to address these challenges. HPCCM provides a high level, configurable Python recipe format for deploying HPC components into container images according to best practices. HPCCM recipes are more portable and powerful than native container specification formats, easier to create, and produce smaller, well-constructed container images.

8 am – 8:05 am: Welcome and C3.ai DTI Overview Shankar Sastry (C3.ai DTI Co-Director, University of California, Berkeley) and R. Srikant (C3.ai DTI Co-Director, University of Illinois at Urbana-Champaign)

8:05 am – 8:15 am: Opening Remarks (Thomas Siebel, Chairman and CEO, C3.ai)

The Colloquium on Digital Transformation is a series of weekly online talks on how artificial intelligence, machine learning, and big data can lead to scientific breakthroughs with large-scale societal benefit. The spring series focuses largely on COVID-19 mitigation research.
 

The DOE Exascale Computing Project (ECP) Software Technology focus area is developing an HPC software ecosystem that will enable the efficient and performant execution of exascale applications. Through the Extreme-scale Scientific Software Stack (E4S) [https://e4s.io], it is developing a comprehensive and coherent software stack that will enable application developers to productively write highly parallel applications that can portably target diverse exascale architectures. E4S provides both source builds through the Spack platform and a set of containers that feature a broad collection of HPC software packages. E4S exists to accelerate the development, deployment, and use of HPC software, lowering the barriers for HPC users. It provides container images, build manifests, and turn-key, from-source builds of popular HPC software packages developed as Software Development Kits (SDKs). This effort includes a broad range of areas including programming models and runtimes (MPICH, Kokkos, RAJA, OpenMPI), development tools (TAU, HPCToolkit, PAPI), math libraries (PETSc, Trilinos), data and visualization tools (Adios, HDF5, Paraview), and compilers (LLVM), all available through the Spack package manager. It will describe the community engagements and interactions that led to the many artifacts produced by E4S. It will introduce the E4S containers is installed on BlueWaters (NCSA) using Shifter and this talk will demonstrate its usage.

Spack is an open-source package manager for HPC. Its simple, templated Python DSL allows the same package to be built in many configurations, with different compilers, flags, dependencies, and dependency versions. Spack allows HPC end users to automatically build any of over 3,000 community-maintained packages, software developers to easily manage large applications with hundreds of dependencies, and HPC facility administrators to deploy software stacks for all of their users.

This talk will give a technical overview of Spack, as well as a brief rundown of recent developments, the longer-term Spack road map, and activities within the U.S. Exascale Computing Project (ECP).

Understanding and optimizing the runtime behavior of your code can be a challenging effort but is often rewarded with significant performance gains. NVIDIA Nsight Compute is a CUDA kernel profiler that provides detailed performance data and offers guidance for optimizing your CUDA kernels. You'll learn about how to collect a wide range of performance data for your CUDA kernels, how automatic rules help in detecting common performance pitfalls and offering guidance through the profile reports, how to quickly compare profiling results to evaluate the effects of your code changes, and how to customize the tool to fit best to your optimization workflow.

The affordability of computing today, progress in nanomaterials and sensing devices, the increasing availability of data, and the emergence of low power wireless networks have made this an opportune time for cyberphysical sensor networks for agriculture, water, and the environment. I will discuss our work from two projects in this context. In the first, I will discuss results from a three year study that we have undertaken in India to develop techniques for geospatial mapping of water quality in Indian rivers. I will describe the technology, and our experiences in placing the technology within the larger context of developing regulations and water policy, and impact of water quality on socioeconomic aspects of the people living near the rivers. In the second, I will describe our work in deploying and studying two subterranean wireless sensor networks for soil measurement and agriculture at locations at U Chicago and Argonne over the past few years. In both cases I will also talk about the “real life” experiences from such networks and the role/importance of data curation from the physical scientist rather than the computer scientist’s point of view.

The Open Storage Network (OSN) Team invites you to join the January Webinar  Thursday, January 21, 2021 – 9AM Pacific Time/5PM UTC. A review of the OSN project, key features, and ways to leverage it in your research. Alex Szalay, Brian Mohr, Kevin Coakley, Jim Culbert, Melissa Cragin, Jim Glasgow, John Goodhue, Register here for this look into the future of data storage on a global scale.