ECRC Activities at SC22! Nov 13, 00:00 - Nov 18, 00:00 Dallas TX USA HPC artificial intelligence HPC accelerates! This year's motto of the Supercomputing conference...
High-Performance Scientific Applications Using Mixed Precisions and Low-Rank Approximations Powered by Task-based Runtime Systems Rabab Alomairy, Postdoctoral Research Fellow, King Abdullah University of Science and Technology Jun 20, 11:00 - 13:00 B9 L4 R4223 Tile Low Rank Algorithmic redesign Task based Runtime Systems Scientific applications from diverse sources rely on dense matrix operations. These operations arise in: Schur complements, integral equations, covariances in spatial statistics, ridge regression, radial basis functions from unstructured meshes, and kernel matrices from machine learning, among others. This thesis demonstrates how to extend the problem sizes that may be treated and reduce their execution time. Sometimes, even forming the dense matrix can be a bottleneck – in computation or storage.
Heterogeneity in Hardware: Opportunities and Challenges for Software and Applications (SC21 Panel) Hatem Ltaief, Principal Research Scientist, Computer, Electrical and Mathematical Sciences and Engineering Nov 14, 00:05 - Nov 19, 23:55 SC21 Saint Louis MO USA HPC numerical linear algebra parallel numerical algorithms Parallel and Distributed Computing GPU Computing Mixed Precisions Heterogeneity in Hardware: Opportunities and Challenges for Software and Applications SC21 Panel Time: Tuesday, 16 November 2021, 10:30am - 12pm CST Location: 225-226 (America's Center, St. Louis, MO USA) Abstract With the end of Moore’s Law, the community has witnessed new hardware trends to increase performance. Today, it is not only the traditional x86 and accelerators that are part of computing systems, but also ARM, FPGAs and dedicated processors for DL workloads that equip now pioneering HPC systems. By the end of this decade, we are moving towards an era of extreme scale with “extreme
Hatem Ltaief, Principal Research Scientist, Computer, Electrical and Mathematical Sciences and Engineering
ISC21 Workshop: Numerical Algorithms and Libraries for Exascale (NAL-X) Hatem Ltaief, Principal Research Scientist, Computer, Electrical and Mathematical Sciences and Engineering Jul 2, 14:00 - 18:00 ISC21 KAUST Frankfurt Germany Time CET HPC numerical linear algebra parallel numerical algorithms Parallel and Distributed Computing GPU Computing Mixed Precisions 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
Hatem Ltaief, Principal Research Scientist, Computer, Electrical and Mathematical Sciences and Engineering
SIAM CSE21 (VIRTUAL) - Minisymposium on HPC Response to the COVID19 Pandemic Hatem Ltaief, Principal Research Scientist, Computer, Electrical and Mathematical Sciences and Engineering Mar 1, 09:00 - 18:00 KAUST HPC ML COVID-19 artificial intelligence Abstract This minisymposium brings together experts in numerical simulation that have developed HPC software tools toward a better understanding coronavirus and the global COVID19 pandemic. Their recent results highlight the importance of computational science as a guiding tool that helps in uncovering the structure and mechanics of the viral spread as well as drastically reduces the number of candidate treatments that need laborious laboratory testing. From transformative medical advances to drug discovery driven by massively parallel supercomputing, this minisymposium will span a range of
Hatem Ltaief, Principal Research Scientist, Computer, Electrical and Mathematical Sciences and Engineering
On The Coupling between HPC and Statistics: Challenges, Opportunities, and Future Trends of Emerging Techniques -- (Virtual SIAM CSE21 Minisymposium) Mar 1, 09:00 - 16:00 KAUST applied statistics big data Abstract Big data modeling/inference and large-scale simulations have followed largely independent paths to the high-performance computing (HPC) frontier, but important opportunities now arise that can be addressed by combining the strengths of each. HPC is becoming increasingly significant in scaling existing statistical methods to larger and more complex applications and developing novel methods that are amenable to scaling within the constraints that exist in modern HPC architectures. The purpose of this minisymposium is to bring together researchers in the area of statistics and HPC to
ExaGeoStat: Moving Towards Large-Scale Geostatistical Modeling on Manycore Systems Sameh Abdulah, Research Scientist, Hierarchical Computations on Manycore Architectures Oct 8, 12:00 - 13:00 KAUST Adaptive modeling We present Exascale GeoStatistics (ExaGeoStat) software, a high-performance library implemented on a wide variety of contemporary hybrid distributed-shared supercomputers whose primary target is climate and environmental prediction applications.
Maximizing I/O Bandwidth for Out-of-Core HPC Applications on Heterogeneous Large-Scale Systems Tariq Alturkestani, Ph.D. Student, Computer Science Jul 9, 16:00 - 17:00 KAUST Out-of-Core simulation systems often produce a massive amount of data that cannot fit on the aggregate fast memory of the compute nodes, and they also require to read back these data for computation. As a result, I/O data movement can be a bottleneck in large-scale simulations. Advances in memory architecture have made it feasible to integrate hierarchical storage media on large-scale systems, starting from the traditional Parallel File Systems to intermediate fast disk technologies (e.g., node-local and remote-shared NVMe and SSD-based Burst Buffers) and up to CPU’s main memory and GPU’s High Bandwidth Memory. However, while adding additional and faster storage media increases I/O bandwidth, it pressures the CPU, as it becomes responsible for managing and moving data between these layers of storage. Simulation systems are thus vulnerable to being blocked by I/O operations. The Multilayer Buffer System (MLBS) proposed in this research demonstrates a general method for overlapping I/O with computation that helps to ameliorate the strain on the processors through asynchronous access. The main idea consists in decoupling I/O operations from computational phases using dedicated hardware resources to perform expensive context switches. By continually prefetching up and down across all hardware layers of the memory/storage subsystems, MLBS transforms the original I/O-bound behavior of evaluated applications and shifts it closer to a memory-bound or compute-bound regime.
SLATE: Design of a Modern Distributed and Accelerated Dense Linear Algebra Library Dalal Sukkari, Ph.D., Applied Mathematics and Computational Sciences Dec 11, 16:00 - 17:00 B2 L5 R5220 The SLATE (Software for Linear Algebra Targeting Exascale) library is being developed to provide fundamental dense linear algebra capabilities for current and upcoming distributed high-performance systems, both accelerated CPU–GPU based and CPU based.
