Distributed Breadth-First Search (BFS) is fundamental to many large-scale graph applications, but its performance on parallel systems is often limited by high communication overhead. This paper presents \({\mathrm\small {CORE-BFS}}\), an extremely scalable GPU-based BFS implementation that introduces a unique rectangular 2D partitioning-based design for Frontier supercomputer. To further improve performance, we propose four key optimizations: (1) Rectangular 2D-partition specific data formats that use two compressed row and one compressed column status array bitmaps combined with a Double Compressed Sparse Row (DCSR) format per partition, reducing memory footprint and inter-rank traffic; (2) Adaptive frontier & communication strategy that unifies top-down and bottom-up traversal on the rectangular layout, uses lazy synchronization in top-down levels, and switches variants based on frontier size to minimize communication overhead; (3) Frontier-split degree-aware update that maps frontier vertices to thread-centric, wavefront-centric, and block-centric kernels based on their degree to improve GPU utilization and memory coalescing; (4) Row-reduction pipeline that overlaps bottom-up adjacency list processing with row-wise bitmap reduction to hide inter-rank latency. Together, these techniques increase parallelism while reducing memory and communication overhead. On the Graph500 benchmark, \({\mathrm\small {CORE-BFS}}\) scales up to 9,248 Frontier nodes with scale-42 graphs and reaches 160.845 TTEPS, delivering a 5.42 × speedup over our previous Frontier implementation.

Abstract The explosive demand for artificial intelligence (AI) workloads has led to a significant increase in silicon area dedicated to lower-precision computations on recent high-performance computing hardware designs. However, mixed-precision capabilities, which can achieve performance improvements of up to 8 $$\times$$ × compared to double-precision in extreme compute-intensive workloads, remain largely untapped in most scientific applications. A growing number of efforts have shown that mixed-precision algorithmic innovations can deliver superior performance without sacrificing accuracy. These developments should prompt computational scientists to seriously consider whether their scientific modeling and simulation applications could benefit from the acceleration offered by new hardware and mixed-precision algorithms. In this survey, we (1) review progress across diverse scientific domains—fluid dynamics, weather and climate, quantum chemistry, and computational genomics—that have begun adopting mixed-precision strategies; (2) examine state-of-the-art algorithmic techniques such as iterative refinement, splitting and emulation schemes, and adaptive precision solvers; (3) assess their implications for accuracy, performance, and resource utilization; and (4) survey the emerging software ecosystem that enables mixed-precision methods at scale. We conclude with perspectives and recommendations on cross-cutting opportunities, domain-specific challenges, and the role of co-design between application scientists, numerical analysts, and computer scientists. Collectively, this survey underscores that mixed-precision numerics can reshape computational science by aligning algorithms with the evolving landscape of hardware capabilities.

High performance LINPACK (HPL) remains the primary benchmark for evaluating supercomputing performance. It includes many parts with substantial internal complexity, and its performance is affected by a large number of parameters that interact in ways that are difficult to predict on large-scale heterogeneous supercomputer systems. We present a comprehensive performance analysis of HPL on Frontier, the world’s first exascale supercomputer, which achieved HPL performance of 1.35 exaflops. Through empirical parameter tuning, detailed modeling, and comparative evaluation, we uncover critical performance insights, share lessons learned, and outline best practices for effective parameter tuning on exascale systems. We introduce and evaluate two novel PDFACT strategies: a dedicated-thread (DT) variant and a GPU-based variant (GPUPDFACT) implementation using HIP cooperative groups, demonstrating that GPU-based factorization outperforms conventional CPU-based PDFACT on Frontier’s architecture. Our findings establish key performance factors for HPL on exascale systems and offer valuable guidance for future high-performance computing and benchmarking efforts.

Mixed-precision algorithms have been proposed as a way for scientific computing to benefit from some of the gains seen for artificial intelligence (AI) on recent high performance computing (HPC) platforms. A few applications dominated by dense matrix operations have seen substantial speedups by utilizing low precision formats such as FP16. However, a majority of scientific simulation applications are memory bandwidth limited. Beyond preliminary studies, the practical gain from using mixed-precision algorithms on a given HPC system is largely unclear.

The new reality of exascale computing faces many challenges in achieving optimal performance on large numbers of nodes. A key challenge is the efficient utilization of the message-passing interface (MPI), a critical component for process communication. This paper explores communication optimization strategies to harness the GPU-accelerated architectures of these supercomputers. We focus on MPI applications where processors form a two-dimensional process grid, a common arrangement in applications involving dense matrix operations. This configuration offers a unique opportunity to implement innovative strategies to improve performance and maintain effective load distribution. We study two applications— Dist-FW (Apsp:all-pair-shortest-path) and HPL-MxP (LU factorization with Mixed precision)—on two accelerated systems: Summit (IBM Power and NVIDIA V100) and Frontier (AMD EPYC and MI250X). These supercomputers are operated by the Oak Ridge Leadership Computing Facility (OLCF) and are currently ranked #1 and #5 on the Top500 list. We show how to scale up both applications to exascale levels and tackle the MPI challenges related to implementation, synchronization, and performance. We also compare the performance of several communication strategies at an unprecedented scale. Accurately predicting application performance becomes crucial for cost reduction as the computational scale grows. To address this, we suggest a hyperbolic model as a better alternative to the traditional one-sided asymptotic model for predicting future application performance at such large scales.

The rise of machine learning (ML) applications and their use of mixed precision to perform interesting science are driving forces behind AI for science on HPC. The convergence of ML and HPC with mixed precision offers the possibility of transformational changes in computational science. The HPL-AI benchmark is designed to measure the performance of mixed precision arithmetic as opposed to the HPL benchmark which measures double precision performance. Pushing the limits of systems at extreme scale is nontrivial -little public literature explores optimization of mixed precision computations at this scale. In this work, we demonstrate how to scale up the HPL-AI benchmark on the pre-exascale Summit and exascale Frontier systems at the Oak Ridge Leadership Computing Facility (OLCF) with a cross-platform design. We present the implementation, performance results, and a guideline of optimization strategies employed for delivering portable performance on both AMD and NVIDIA GPUs at extreme scale.

We consider the problem of low-rank approximation of massive dense nonnegative tensor data, for example, to discover latent patterns in video and imaging applications. As the size of data sets grows, single workstations are hitting bottlenecks in both computation time and available memory. We propose a distributed-memory parallel computing solution to handle massive data sets, loading the input data across the memories of multiple nodes, and performing efficient and scalable parallel algorithms to compute the low-rank approximation. We present a software package called Parallel Low-rank Approximation with Nonnegativity Constraints, which implements our solution and allows for extension in terms of data (dense or sparse, matrices or tensors of any order), algorithm (e.g., from multiplicative updating techniques to alternating direction method of multipliers), and architecture (we exploit GPUs to accelerate the computation in this work). We describe our parallel distributions and algorithms, which are careful to avoid unnecessary communication and computation, show how to extend the software to include new algorithms and/or constraints, and report efficiency and scalability results for both synthetic and real-world data sets.

In this paper, we pose and address some of the unique challenges in the analysis of scientific Big Data on supercomputing platforms. Our approach identifies, implements and scales numerical kernels that are critical to the instantiation of theory-inspired analytic workflows on modern computing architectures. We present the benefits of scalable kernels towards constructing algorithms such as principal component analysis and non-negative matrix factorization on an image-analysis use case at the Oak Ridge Leadership Computing Facility (OLCF). Based on experience with the use-case, we conclude that piecing scalable analytic kernels into user-defined analytic workflows are a flexible, modular and agile way to enable architecture-portable productivity for the data-intensive sciences.

Scaling-up scientific data analysis and machine learning algorithms for data-driven discovery is a grand challenge that we face today. Despite the growing need for analysis from science domains that are generating ‘Big Data’ from instruments and simulations, building high-performance analytical workflows of data-intensive algorithms have been daunting because: (i) the ‘Big Data’ hardware and software architecture landscape is constantly evolving, (ii) newer architectures impose new programming models, and (iii) data-parallel kernels of analysis algorithms and their performance facets on different architectures are poorly understood. To address these problems, we have: (i) identified scalable data-parallel kernels of popular data analysis algorithms, (ii) implemented ‘Mini-Apps’ of those kernels using different programming models (e.g. Map Reduce, MPI, etc.), (iii) benchmarked and validated the performance of the kernels in diverse architectures. In this paper, we discuss two of those Mini-Apps and show the execution of principal component analysis built as a workflow of the Mini-Apps. We show that Mini-Apps enable scientists to (i) write domain-specific data analysis code that scales on most HPC hardware and (ii) and offers the ability (most times with over a 10x speed-up) to analyze data sizes 100 times the size of what off-the-shelf desktop/workstations of today can handle.

Data driven science, accompanied by the explosion of petabytes of data, has called into need dedicated analytics computing resources. Dedicated analytics clusters require large capital outlays due to their expensive hardware requirements. Additionally, if such resources are located far from the data they analyze, they also incur substantial data transfer, which has both cost and latency implications. In this paper, we benchmark a variety of high-performance computing (HPC) architectures for classic data science algorithms, as well as conduct a cost analysis of these architectures. Additionally, we compare algorithms across analytic frameworks, as well as explore hidden costs in the form of queuing mechanisms. We observe that node architectures with large memory and high memory bandwidth are better suited for big data analytics on HPC hardware. We also conclude that cloud computing is more cost effective for small or experimental data workloads, but HPC is more cost effective at scale. Additionally, we quantify the hidden costs of queuing and how it relates to data science workloads. Finally, we observe that software developed for the cloud, such as Spark, performs significantly worse than pbdR when run in HPC environments.

In this paper, we propose strategies and objectives for immersive data visualization with applications in materials science using the Oculus Rift virtual reality headset. We provide background on currently available analysis tools for neutron scattering data and other large-scale materials science projects. In the context of the current challenges facing scientists, we discuss immersive virtual reality visualization as a potentially powerful solution. We introduce a prototype immersive visualization system, developed in conjunction with materials scientists at the Spallation Neutron Source, which we have used to explore large crystal structures and neutron scattering data. Finally, we offer our perspective on the greatest challenges that must be addressed to build effective and intuitive virtual reality analysis tools that will be useful for scientists in a wide range of fields.

A project in the field of computational electrocardiography which requires visualization of complex, three-dimensional geometry and electric potential and current fields is described. Starting from magnetic resonance images (MRIs) from a healthy subject, a multisurfaced model of the human thorax was constructed and used as the basis for computational studies relating potential distributions measured from the surface of the heart to potentials and currents throughout the volume of the thorax (a form of the forward problem in electrocardiography). Both interactive and batch-mode graphics programs were developed to view, manipulate, and interactively edit the model geometry. Results are presented.>