Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Exascale computing”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,189 records · Page 66

Optimizing I/O Performance of HPC Applications with Autotuning

Parallel Input output is an essential component of modern high-performance computing (HPC). Obtaining good I/O performance for a broad range of applications on diverse HPC platforms is a major challenge, in part, because of complex inter dependencies between I/O middleware and hardware. The parallel file system and I/O middleware layers all offer optimization parameters that can, in theory, result in better I/O performance. Unfortunately, the right combination of parameters is highly dependent on the application, HPC platform, problem size, and concurrency. Scientific application developers do not have the time or expertise to take on the substantial burden of identifying good parameters for each problem configuration. They resort to using system defaults, a choice that frequently results in poor I/O performance. We expect this problem to be compounded on exascale-class machines, which will likely have a deeper software stack with hierarchically arranged hardware resources. We present as a solution to this problem an autotuning system for optimizing I/O performance, I/O performance modeling, I/O tuning, and I/O patterns. We demonstrate the value of this framework across several HPC platforms and applications at scale.

Behzad, Babak↗

Programming Abstractions for Data Locality

The goal of the workshop and this report is to identify common themes and standardize concepts for locality-preserving abstractions for exascale programming models.

97 MATHEMATICS AND COMPUTING↗

Program Generators for Exascale and Beyond (Final Technical Report)

The major goals of this project were to devise programming models and supporting tools that simplify the construction of specialized high‐performance generators, leading to improvements over the state of the art along the various dimensions of portability, performance, and productivity. In particular, the project achieved these goals by focusing on domain‐specific languages (DSLs) as intermediate layers in a translation and optimization framework, on composability of program generators, on re‐targeting legacy code, and on fundamental methodologies such as stage polymorphism or "generic programming in time".

97 MATHEMATICS AND COMPUTING↗

Nanoporous Materials Genome Center Final Technical Report

Nanoporous materials (NPMs), including zeolites/zeotypes, metal-organic frameworks (MOFs), covalent organic frameworks, polymers with intrinsic microporosity, and molecular cages, possess enormous potential in diverse areas relevant to the DOE Office of Science Basic Energy Sciences (BES) mission and objectives. The Nanoporous Materials Genome Center (NMGC) has developed exascale-ready software, computational/theoretical chemistry methods, and data-driven science approaches that enable (i) the de-novo design of functional NPMs for chemical separation and catalysis tasks of increasing complexity, (ii) the discovery of the most promising functional NPMs from databases of synthesized and hypothetical adsorbent structures and the optimization of process conditions for specific applications, and (iii) the microscopic-level understanding of the fundamental interactions underlying the function of NPMs including hierarchical architectures, composite materials, responsive frameworks that may undergo phase transitions or post-synthetic modifications, and materials containing defects, partial disorder, or interfaces. A pivotal part of the NMGC project has been a tight collaboration between leading experimental groups for synthesis and characterization of NPMs and of computational groups that allowed for iterative feedback. The NMGC project has resulted in the publication of more than 290 research and review articles including more than 60 publications in high-impact journals and more than 15 journal covers. NMGC publications have already received more than 20,000 citations (with more than 3,000 citations per year in 2021, 2022, and 2023) and contribute to an h-index of more than 72. The NMGC award has supported collaborative research involving 28 research groups and contributed to the training of more than 40 postdocs, more than 60 graduate students, and more than 20 undergraduate students with broad expertise in data-driven science approaches, computational chemistry methods, and high-performance computing, in addition to the skills to thrive in an integrated experimental and computational research environment.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Milestone M7 Report: Reducing Excess Data Movement Part 2

This milestone evaluates techniques to measure and, if possible, reduce data movement across all levels of the memory hierarchy, focusing on CPU/GPU page level data movement and on intra-GPU memory hierarchy. We quantitatively evaluate the efficacy of the techniques in reducing data movement and measure how performance tracks data movement reduction. We study a small collection of benchmarks and proxy mini-apps that run on advanced pre-exascale GPUs and on the Accelsim GPU simulator. Our approach has two thrusts: to measure advanced data movement reduction directives and techniques on the newest available GPUs, and to evaluate our benchmark set on simulated GPUs configured with architectural refinements to reduce data movement. We primarily evaluated NVidia-based architectures due to the unavailability of AMD GPU hardware and tools until very recently.

97 MATHEMATICS AND COMPUTING↗

Reducing Concurrency Bottlenecks in Parallel I/O Workloads

To enable high performance parallel checkpointing we introduced the Parallel Log Structured File System (PLFS). PLFS is middleware interposed on the file system stack to transform concurrent writing of one application file into many non-concurrently written component files. The promising effectiveness of PLFS makes it important to examine its performance for workloads other than checkpoint capture, notably the different ways that state snapshots may be later read, to make the case for using PLFS in the Exascale I/O stack. Reading a PLFS file involved reading each of its component files. In this paper we identify performance limitations on broader workloads in an early version of PLFS, specifically the need to build and distribute an index for the overall file, and the pressure on the underlying parallel file system's metadata server, and show how PLFS's decomposed components architecture can be exploited to alleviate bottlenecks in the underlying parallel file system.

COMPUTER ARCHITECTURE↗

GEOS Atmospheric Model: Challenges at Exascale

The Goddard Earth Observing System (GEOS) model at NASA's Global Modeling and Assimilation Office (GMAO) is used to simulate the multi-scale variability of the Earth's weather and climate, and is used primarily to assimilate conventional and satellite-based observations for weather forecasting and reanalysis. In addition, assimilations coupled to an ocean model are used for longer-term forecasting (e.g., El Nino) on seasonal to interannual times-scales. The GMAO's research activities, including system development, focus on numerous time and space scales, as detailed on the GMAO website, where they are tabbed under five major themes: Weather Analysis and Prediction; Seasonal-Decadal Analysis and Prediction; Reanalysis; Global Mesoscale Modeling, and Observing System Science. A brief description of the GEOS systems can also be found at the GMAO website. GEOS executes as a collection of earth system components connected through the Earth System Modeling Framework (ESMF). The ESMF layer is supplemented with the MAPL (Modeling, Analysis, and Prediction Layer) software toolkit developed at the GMAO, which facilitates the organization of the computational components into a hierarchical architecture. GEOS systems run in parallel using a horizontal decomposition of the Earth's sphere into processing elements (PEs). Communication between PEs is primarily through a message passing framework, using the message passing interface (MPI), and through explicit use of node-level shared memory access via the SHMEM (Symmetric Hierarchical Memory access) protocol. Production GEOS weather prediction systems currently run at 12.5-kilometer horizontal resolution with 72 vertical levels decomposed into PEs associated with 5,400 MPI processes. Research GEOS systems run at resolutions as fine as 1.5 kilometers globally using as many as 30,000 MPI processes. Looking forward, these systems can be expected to see a 2 times increase in horizontal resolution every two to three years, as well as less frequent increases in vertical resolution. Coupling these resolution changes with increases in complexity, the computational demands on the GEOS production and research systems should easily increase 100-fold over the next five years. Currently, our 12.5 kilometer weather prediction system narrowly meets the time-to-solution demands of a near-real-time production system. Work is now in progress to take advantage of a hybrid MPI-OpenMP parallelism strategy, in an attempt to achieve a modest two-fold speed-up to accommodate an immediate demand due to increased scientific complexity and an increase in vertical resolution. Pursuing demands that require a 10- to 100-fold increases or more, however, would require a detailed exploration of the computational profile of GEOS, as well as targeted solutions using more advanced high-performance computing technologies. Increased computing demands of 100-fold will be required within five years based on anticipated changes in the GEOS production systems, increases of 1000-fold can be anticipated over the next ten years.

ESMF↗

Visualization and data analysis outbrief

Talk about Visualization and Data Analysis Current State and Exascale challenges. The goal is to update with colleagues our current status in our research. What challenges we need to face, and what future possibilities. Our goal is to propose to approach the problems with the visualization approach operating on the supercomputing platform. This presentation is about the L2 Milestone, we intend to discuss further possibilities of enhancing our results and optimizing our solutions.

97 MATHEMATICS AND COMPUTING↗

The fully coupled regionally refined model of E3SM version 2: overview of the atmosphere, land, and river results

Abstract. This paper provides an overview of the United States (US) Department of Energy's (DOE's) Energy Exascale Earth System Model version 2 (E3SMv2) fully coupled regionally refined model (RRM) and documents the overall atmosphere, land, and river results from the Coupled Model Intercomparison Project 6 (CMIP6) DECK (Diagnosis, Evaluation, and Characterization of Klima) and historical simulations – a first-of-its-kind set of climate production simulations using RRM. The North American (NA) RRM (NARRM) is developed as the high-resolution configuration of E3SMv2 with the primary goal of more explicitly addressing DOE's mission needs regarding impacts to the US energy sector facing Earth system changes. The NARRM features finer horizontal resolution grids centered over NA, consisting of 25→100 km atmosphere and land, a 0.125∘ river-routing model, and 14→60 km ocean and sea ice. By design, the computational cost of NARRM is ∼3× of the uniform low-resolution (LR) model at 100 km but only ∼ 10 %–20 % of a globally uniform high-resolution model at 25 km. A novel hybrid time step strategy for the atmosphere is key for NARRM to achieve improved climate simulation fidelity within the high-resolution patch without sacrificing the overall global performance. The global climate, including climatology, time series, sensitivity, and feedback, is confirmed to be largely identical between NARRM and LR as quantified with typical climate metrics. Over the refined NA area, NARRM is generally superior to LR, including for precipitation and clouds over the contiguous US (CONUS), summertime marine stratocumulus clouds off the coast of California, liquid and ice phase clouds near the North Pole region, extratropical cyclones, and spatial variability in land hydrological processes. The improvements over land are related to the better-resolved topography in NARRM, whereas those over ocean are attributable to the improved air–sea interactions with finer grids for both atmosphere and ocean and sea ice. Some features appear insensitive to the resolution change analyzed here, for instance the diurnal propagation of organized mesoscale convective systems over CONUS and the warm-season land–atmosphere coupling at the southern Great Plains. In summary, our study presents a realistically efficient approach to leverage the fully coupled RRM framework for a standard Earth system model release and high-resolution climate production simulations.

54 ENVIRONMENTAL SCIENCES↗

A graphics processing unit accelerated sparse direct solver and preconditioner with block low rank compression

We present the GPU implementation efforts and challenges of the sparse solver package STRUMPACK. The code is made publicly available on github with a permissive BSD license. STRUMPACK implements an approximate multifrontal solver, a sparse LU factorization which makes use of compression methods to accelerate time to solution and reduce memory usage. Multiple compression schemes based on rank-structured and hierarchical matrix approximations are supported, including hierarchically semi-separable, hierarchically off-diagonal butterfly, and block low rank. Here, in this paper, we present the GPU implementation of the block low rank (BLR) compression method within a multifrontal solver. Our GPU implementation relies on highly optimized vendor libraries such as cuBLAS and cuSOLVER for NVIDIA GPUs, rocBLAS and rocSOLVER for AMD GPUs and the Intel oneAPI Math Kernel Library (oneMKL) for Intel GPUs. Additionally, we rely on external open source libraries such as SLATE (Software for Linear Algebra Targeting Exascale), MAGMA (Matrix Algebra on GPU and Multi-core Architectures), and KBLAS (KAUST BLAS). SLATE is used as a GPU-capable ScaLAPACK replacement. From MAGMA we use variable sized batched dense linear algebra operations such as GEMM, TRSM and LU with partial pivoting. KBLAS provides efficient (batched) low rank matrix compression for NVIDIA GPUs using an adaptive randomized sampling scheme. The resulting sparse solver and preconditioner runs on NVIDIA, AMD and Intel GPUs. Interfaces are available from PETSc, Trilinos and MFEM, or the solver can be used directly in user code. We report results for a range of benchmark applications, using the Perlmutter system from NERSC, Frontier from ORNL, and Aurora from ALCF. For a high frequency wave equation on a regular mesh, using 32 Perlmutter compute nodes, the factorization phase of the exact GPU solver is about 6.5× faster compared to the CPU-only solver. The BLR-enabled GPU solver is about 13.8× faster than the CPU exact solver. For a collection of SuiteSparse matrices, the STRUMPACK exact factorization on a single GPU is on average 1.9× faster than NVIDIA’s cuDSS solver.

97 MATHEMATICS AND COMPUTING↗

Large-Scale Simulation of Nuclear Reactors: Issues and Perspectives

Numerical simulation has been an intrinsic part of nuclear engineering research since its inception. In recent years a transition is occurring toward predictive, first-principle-based tools such as computational fluid dynamics. Even with the advent of petascale computing, however, such tools still have significant limitations. In the present work some of these issues, and in particular the presence of massive multiscale separation, are discussed, as well as some of the research conducted to mitigate them. Petascale simulations at high fidelity (large eddy simulation/direct numerical simulation) were conducted with the massively parallel spectral element code Nek5000 on a series of representative problems. These simulations shed light on the requirements of several types of simulation: (1) axial flow around fuel rods, with particular attention to wall effects; (2) natural convection in the primary vessel; and (3) flow in a rod bundle in the presence of spacing devices. The focus of the work presented here is on the lessons learned and the requirements to perform these simulations at exascale. Additional physical insight gained from these simulations is also emphasized.

CFD↗

High performance sparse multifrontal solvers on modern GPUs

Here, we have ported the numerical factorization and triangular solve phases of the sparse direct solver STRUMPACK to GPU. STRUMPACK implements sparse LU factorization using the multifrontal algorithm, which performs most of its operations in dense linear algebra operations on so-called frontal matrices of various sizes. Our GPU implementation off-loads these dense linear algebra operations, as well as the sparse scatter–gather operations between frontal matrices. For the larger frontal matrices, our GPU implementation relies on vendor libraries such as cuBLAS and cuSOLVER for NVIDIA GPUs and rocBLAS and rocSOLVER for AMD GPUs. For the smaller frontal matrices we developed custom CUDA and HIP kernels to reduce kernel launch overhead. Overall, high performance is achieved by identifying submatrix factorizations corresponding to sub-trees of the multifrontal assembly tree which fit entirely in GPU memory. The multi-GPU setting uses SLATE (Software for Linear Algebra Targeting Exascale) as a modern GPU-aware replacement for ScaLAPACK. On 4 nodes of SUMMIT the code runs ~10X faster when using all 24 V100 GPUs compared to when it only uses the 168 POWER9 cores. On 8 SUMMIT nodes, using 48 V100 GPUs, the sparse solver reaches over 50TFlop/s. Compared to SuperLU, on a single V100, for a set of 17 matrices our implementation is faster for all but one matrix, and is on average 5X (median 4X) faster

97 MATHEMATICS AND COMPUTING↗

Preparing NERSC users for Cori, a Cray XC40 system with Intel many integrated cores

The newest NERSC supercomputer Cori is a Cray XC40 system consisting of 2,388 Intel Xeon Haswell nodes and 9,688 Intel Xeon-Phi “Knights Landing” (KNL) nodes. Compared to the Xeon-based clusters NERSC users are familiar with, optimal performance on Cori requires consideration of KNL mode settings; process, thread, and memory affinity; fine-grain parallelization; vectorization; and use of the high-bandwidth MCDRAM memory. This paper describes our efforts preparing NERSC users for KNL through the NERSC Exascale Science Application Program, Web documentation, and user training. We discuss how we configured the Cori system for usability and productivity, addressing programming concerns, batch system configurations, and default KNL cluster and memory modes. Here, system usage data, job completion analysis, programming and running jobs issues, and a few successful user stories on KNL are presented.

97 MATHEMATICS AND COMPUTING↗

Towards Exascale Astrophysics of Mergers and Supernovae (TEAMS)

The TEAMS project brought together cutting-edge simulations, theoretical insights, and collaborative efforts to deepen our understanding of some of the universe’s most extreme phenomena—supernovae, neutron star mergers, and the powerful signals they emit. Using one of the largest suites of 3D supernova simulations ever conducted, researchers uncovered new insights into how massive stars explode, how those explosions vary by stellar mass, and what conditions lead to the birth of neutron stars or black holes. They also studied the radiation and gravitational wave signals emitted during these events, revealing how future observations can be used to uncover what happens deep inside collapsing stars. The team developed improved tools for modeling how light and neutrinos behave in such explosive environments, enabling more accurate predictions of what astronomers might observe. Work also explored how the chemical composition and geometry of kilonovae—the visible explosions that follow neutron star mergers—influence their signals and can reveal the origins of heavy elements like gold. These efforts not only advanced scientific knowledge, but also trained a new generation of researchers at the intersection of astrophysics, computational science, and nuclear theory.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

ExaChem/exachem

Open Source Exascale Quantum Chemistry Software

Panyala, Ajay [Pacific Northwest National Laborato↗

Performance Understanding and Analysis for Exascale Data Management Workflows (Collaboration)

The general approach of the MONA project is depicted in Figure 1. The figure shows performance monitoring applied to an I/O workflow associated with a scientific simulation, with online measurements captured from this workflow informing methods for workflow reconfiguration and dynamic adjustment. The goal is to maintain suitable levels of Quality of Service for workflow execution, by understanding the underlying causes of workflow performance and behavior. One outcome will be workflow performance models able to characterize realistic workflows. Another outcome will be performance ‘mini-apps’ implementing such workflow behavior. Out of scope for this project are advanced methods for online workflow control.

97 MATHEMATICS AND COMPUTING↗

Performance-portable Binary Neutron Star Mergers with AthenaK

We introduce an extension to the AthenaK code for general-relativistic magnetohydrodynamics (GRMHD) in dynamical spacetimes using a 3+1 conservative Eulerian formulation. Like the fixed-spacetime GRMHD solver, we use standard finite-volume methods to evolve the fluid and a constrained-transport scheme to preserve the divergence-free constraint for the magnetic field. We also utilize a first-order flux correction (FOFC) scheme to reduce the need for an artificial atmosphere and optionally enforce a maximum principle to improve robustness. We demonstrate the accuracy of AthenaK using a set of standard tests in flat and curved spacetimes. Using a SANE accretion disk around a Kerr black hole, we compare the new solver to the existing solver for stationary spacetimes using the so-called "HARM-like" formulation. We find that both formulations converge to similar results. We also include the first published binary neutron star (BNS) mergers performed on graphical processing units (GPUs). Thanks to the FOFC scheme, our BNS mergers maintain a relative error of $\mathcal{O}$(10 –11 ) or better in baryon mass conservation up to collapse. Finally, we perform scaling tests of AthenaK on OLCF Frontier, where we show excellent weak scaling of ≥80% efficiency up to 32,768 GPUs and 74% up to 65,536 GPUs for a GRMHD problem in dynamical spacetimes with six levels of mesh refinement. AthenaK achieves an order-of-magnitude speedup using GPUs compared to CPUs, demonstrating that it is suitable for performing numerical relativity problems on modern exascale resources.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Optimizing fusion PIC code performance at scale on Cori Phase 2

In this paper we present the results of optimizing the performance of the gyrokinetic full-f fusion PIC code XGC1 on the Cori Phase Two Knights Landing system. The code has undergone substantial development to enable the use of vector instructions in its most expensive kernels within the NERSC Exascale Science Applications Program. We study the single-node performance of the code on an absolute scale using the roofline methodology to guide optimization efforts. We have obtained 2x speedups in single node performance due to enabling vectorization and performing memory layout optimizations. On multiple nodes, the code is shown to scale well up to 4000 nodes, near half the size of the machine. We discuss some communication bottlenecks that were identified and resolved during the work.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗