Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel computer architecture”

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 487 records · Page 27

GASNet-EX: A High-Performance, Portable Communication Library for Exascale

Partitioned Global Address Space (PGAS) models, typified by such languages as Unified Parallel C (UPC) and Co-Array Fortran, expose one-sided communication as a key building block for High Performance Computing (HPC) applications. Architectural trends in supercomputing make such programming models increasingly attractive, and newer, more sophisticated models such as UPC++, Legion and Chapel that rely upon similar communication paradigms are gaining popularity. GASNet-EX is a portable, open-source, high-performance communication library designed to efficiently support the networking requirements of PGAS runtime systems and other alternative models in future exascale machines. The library is an evolution of the popular GASNet communication system, building upon over 15 years of lessons learned. We describe and evaluate several features and enhancements that have been introduced to address the needs of modern client systems. Microbenchmark results demonstrate the RMA performance of GASNet-EX is competitive with several MPI-3 implementations on current HPC systems.

97 MATHEMATICS AND COMPUTING↗

The RAJA Portability Layer: Overview and Status

As computer architectures become increasingly complex and diverse, application developers face difficult challenges to achieve high performance while maintaining code portability. The problem is especially acute for large ASC multiphysics codes. Efficient parallel execution often requires tuning algorithms and data access to match processor and memory system constraints. Changing compiler directives and parallel programming model constructs on thousands of individual loops in a large code is disruptive and unwieldy. RAJA is a programming approach that we have been developing at Lawrence Livermore National Laboratory to encapsulate platform-specific concerns, related to both hardware and parallel programming models. The RAJA abstraction layer simplifies porting C/C++ codes to various programming models and architectures by reducing effort and developer disruption. In this report, we motivate and describe key aspects of RAJA. We also present a preliminary assessment of RAJA based on exploration in three ASC hydrodynamics codes at LLNL, which was one part of a three-part ASC Level 2 milestone, completed in September 2014.

97 MATHEMATICS AND COMPUTING↗

ExaTN

A challenging scientific problem that will benefit from exascale computing is predictive simulation of two- and three-dimensional quantum many-body Hamiltonians in condensed matter physics, together with the related strong entanglement problems in quantum chemistry and quantum computing. Efficient numerical simulations will require new insights into wavefunction compression algorithms that scale on extremely heterogeneous HPC architectures. To address this need, we propose to develop a scalable math library of parallel multi-linear algebraic numerical primitives for hierarchical tensor compression. Our library will subsequently be used for building an efficient, performance-portable HPC framework for simulating strongly correlated quantum systems. In particular, our will will be the first to deliver a massively parallel implementation of the multiscale entanglement renormalization ansatz (MERA), a hierarchical tensor decomposition quantum scheme capable of expressing local expectation values of strongly entangled higher-dimensional quantum systems efficiently. To address the extreme complexity and high computational cost of such schemes, we will automate their parallel implementation by delivering an integrated software framework, ExaTN (Exascale Tensor Networks), that will process hierarchical tensor representations on exascale HPC systems via an asymchronous task-based programming model. As a specific application, our framework will provide scientists with a capability of simulating strongly entangled quantum systems, thus positioning ORNL as a strategic leader in modeling of strongly correlated materials.

McCaskey, AlexanderJ↗

Rasterization with Data-Parallel Primitives

Parallel rasterization can suffer from race conditions during fragment generation, which is traditionally addressed by using specialized hardware accessible via vendor graphics APIs. Unfortunately, graphics APIs are increasingly problematic on high-performance computers, either because they are not provided or because of concerns about dependencies with in situ visualization. In response, we present a hardware-agnostic rasterization algorithm that handles race conditions using only data-parallel primitives (DPPs), enabling efficient rendering on HPC systems without graphics API dependencies and aligning with recent efforts to deliver visualization software with DPPs. Our evaluation consists of three phases: (1) evaluating portability across different CPU and GPU architectures, (2) evaluating competitiveness with a community standard, and (3) evaluating performance across varying workloads and available parallelism. The supporting experiments run on both AMD and NVIDIA GPUs, considering data sets as large as 460 million triangles and 160 million pixels. While performance generally falls short of graphics API baselines, it achieves interactive frame rates on most workloads. As a result, we conclude our approach is a viable solution for rasterization on high-performance computers since our approach is portably performant across different architectures without the need for specialized vendor support.

Buckley, Makani [University of Oregon] (ORCID:0009↗

Modeling of a chain of three plasma accelerator stages with the WarpX electromagnetic PIC code on GPUs

The fully electromagnetic particle-in-cell code WarpX is being developed by a team of the U.S. DOE Exascale Computing Project (with additional non-U.S. collaborators on part of the code) to enable the modeling of chains of tens to hundreds of plasma accelerator stages on exascale supercomputers, for future collider designs. The code is combining the latest algorithmic advances (e.g., Lorentz boosted frame and pseudo-spectral Maxwell solvers) with mesh refinement and runs on the latest computer processing unit and graphical processing unit (GPU) architectures. In this paper, we summarize the strategy that was adopted to port WarpX to GPUs, report on the weak parallel scaling of the pseudo-spectral electromagnetic solver, and then present solutions for decreasing the time spent in data exchanges from guard regions between subdomains. In Sec. IV, we demonstrate the simulations of a chain of three consecutive multi-GeV laser-driven plasma accelerator stages.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Towards performance-portability of the Albany Finite Element analysis code using the Kokkos library of Trilinos

Performance portability on heterogeneous high-performance computing (HPC) systems is a major challenge faced today by code developers: parallel code needs to execute correctly as well as with high performance on machines with different architectures, operating systems, and software libraries. The Finite Element Method (FEM) is a popular and flexible method for discretizing partial differential equations arising in a wide variety of scientific, engineering, and industry applications that require HPC. This paper presents some preliminary results pertaining to our development of a performance portable implementation of the FEM-based Albany code. Performance portability is achieved using the Kokkos library of Trilinos. We present performance results for two different physics simulations modules in Albany: the Aeras global atmosphere dynamical code and the FELIX land-ice solver. As a result, numerical experiments show that our single code implementation gives reasonable performance across two multi-core/many-core architectures: NVIDIA GPUs and multi-core CPUs.

97 MATHEMATICS AND COMPUTING↗

Parallel Programming Models and Systems for High Performance Computing. In: Emerging Research in Cloud Distributed Computing Systems

A parallel programming model is an abstraction of a parallel system that allows expression of both algorithms and shared data structures. To accommodate the diversity in parallel system architectures and user requirements, there are a variety of programming models including the models providing a shared memory view or a distributed memory view of the system. The programming models are implemented as libraries, language extensions, or compiler directives. This chapter provides a discussion on programming models and its implementations aimed at application developers, system software researchers, and hardware architects. The first part provides an overview of the programming models. The second part is an in-depth discussion on high-performance networking interface to implement the programming model. The last part of the chapter discusses implementation of a programming model with a case study. Each part of the chapter concludes with a discussion on current research trends and its impact on future architectures.

Venkata, Manjunath Gorentia↗

Exploring performance and energy tradeoffs for irregular applications: A case study on the Tilera many-core architecture

High performance, parallel applications with irregular data accesses are becoming a critical workload class for modern systems. In particular, the execution of such workloads on emerging many-core systems is expected to be a significant component of applications in data mining, machine learning, scientific computing and graph analytics. However, power and energy constraints limit the capabilities of individual cores, memory hierarchy and on-chip interconnect of such systems, thus leading to architectural and software trade-os that must be understood in the context of the intended application’s behavior. Irregular applications are notoriously hard to optimize given their data-dependent access patterns, lack of structured locality and complex data structures and code patterns. We have ported two irregular applications, graph community detection using the Louvain method (Grappolo) and high-performance conjugate gradient (HPCCG), to the Tilera many-core system and have conducted a detailed study of platform-independent and platform-specific optimizations that improve their performance as well as reduce their overall energy consumption. To conduct this study, we employ an auto-tuning based approach that explores the optimization design space along three dimensions - memory layout schemes, GCC compiler flag choices and OpenMP loop scheduling options. We leverage MIT’s OpenTuner auto-tuning framework to explore and recommend energy optimal choices for different combinations of parameters. We then conduct an in-depth architectural characterization to understand the memory behavior of the selected workloads. Finally, we perform a correlation study to demonstrate the interplay between the hardware behavior and application characteristics. Using auto-tuning, we demonstrate whole-node energy savings and performance improvements of up to 49:6% and 60% relative to a baseline instantiation, and up to 31% and 45:4% relative to manually optimized variants.

auto tuning↗

Graphics processing unit accelerated three-dimensional model for the simulation of pulsed low-temperature plasmas

A 3-dimensional particle-in-cell/Monte Carlo collision simulation that is fully implemented on a graphics processing unit (GPU) is described and used to determine low-temperature plasma characteristics at high reduced electric field, E/n, in nitrogen gas. Details of implementation on the GPU using the NVIDIA Compute Unified Device Architecture framework are discussed with respect to efficient code execution. The software is capable of tracking around 10 × 10{sup 6} particles with dynamic weighting and a total mesh size larger than 10{sup 8} cells. Verification of the simulation is performed by comparing the electron energy distribution function and plasma transport parameters to known Boltzmann Equation (BE) solvers. Under the assumption of a uniform electric field and neglecting the build-up of positive ion space charge, the simulation agrees well with the BE solvers. The model is utilized to calculate plasma characteristics of a pulsed, parallel plate discharge. A photoionization model provides the simulation with additional electrons after the initial seeded electron density has drifted towards the anode. Comparison of the performance benefits between the GPU-implementation versus a CPU-implementation is considered, and a speed-up factor of 13 for a 3D relaxation Poisson solver is obtained. Furthermore, a factor 60 speed-up is realized for parallelization of the electron processes.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Scalable Asynchronous Domain Decomposition Solvers

We discuss how parallel implementations of linear iterative solvers generally alternate between phases of data exchange and phases of local computation. Increasingly large problem sizes and more heterogeneous compute architectures make load balancing and the design of low latency network interconnects that are able to satisfy the communication requirements of linear solvers very challenging tasks. In particular, global communication patterns such as inner products become increasingly limiting at scale. We explore the use of asynchronous communication based on one-sided Message Passing Interface primitives in the context of domain decomposition solvers. In particular, a scalable asynchronous two-level Schwarz method is presented. We discuss practical issues encountered in the development of a scalable solver and show experimental results obtained on a state-of-the-art supercomputer system that illustrate the benefits of asynchronous solvers in load balanced as well as load imbalanced scenarios. Using the novel method, we can observe speedups of up to four times over its classical synchronous equivalent.

97 MATHEMATICS AND COMPUTING↗

Final Report: Migration Mechanisms for Large-scale Parallel Applications

Process migration is the ability to transfer a process from one machine to another. It is a useful facility in distributed computing environments, especially as computing devices become more pervasive and Internet access becomes more ubiquitous. The potential benefits of process migration, among others, are fault resilience by migrating processes off of faulty hosts, data access locality by migrating processes closer to the data, better system response time by migrating processes closer to users, dynamic load balancing by migrating processes to less loaded hosts, and improved service availability and administration by migrating processes before host maintenance so that applications can continue to run with minimal downtime. Although process migration provides substantial potential benefits and many approaches have been considered, achieving transparent process migration functionality has been difficult in practice. To address this problem, our work has designed, implemented, and evaluated new and powerful transparent process checkpoint-restart and migration mechanisms for desktop, server, and parallel applications that operate across heterogeneous cluster and mobile computing environments. A key aspect of this work has been to introduce lightweight operating system virtualization to provide processes with private, virtual namespaces that decouple and isolate processes from dependencies on the host operating system instance. This decoupling enables processes to be transparently checkpointed and migrated without modifying, recompiling, or relinking applications or the operating system. Building on this lightweight operating system virtualization approach, we have developed novel technologies that enable (1) coordinated, consistent checkpoint-restart and migration of multiple processes, (2) fast checkpointing of process and file system state to enable restart of multiple parallel execution environments and time travel, (3) process migration across heterogeneous software environments, (4) network checkpoint-restart and migration of distributed and parallel applications, (5) a utility computing infrastructure for mobile desktop cloud computing based on process checkpoint-restart and migration functionality, (6) a process migration security architecture for protecting applications and infrastructure from denial-of-service attacks, and (7) a checkpoint-restart mobile computing system using portable storage devices.

99 GENERAL AND MISCELLANEOUS↗

Experiences with string matching on the Fermi Architecture

String matching is at the core of many real-world applications, such as security, bioinformatic, data mining. All these applications requires the ability to match always growing data sets against large dictionaries effectively, fastly and possibly in real time. Unfortunately, string matching is a computationally intensive procedure which poses significant challenges on current software and hardware implementations. Graphic Processing Units (GPU) have become an interesting target for such high-throughput applications, but the algorithms and the data structures need to be redesigned to be parallelized and adapted to the underlining hardware, coping with the limitations imposed by these architectures. In this paper we present an efficient implementation of the Aho-Corasick string matching algorithm on GPU, showing how we progressively redesigned the algorithm and the data structures to fit on the architecture. We then evaluate the implementation on single and multiple Tesla C2050 (T20 ``Fermi'' based) boards, comparing them to the previous Tesla C1060 (T10 based) solutions and equivalent multicore implementations on x86 CPUs. We discuss the various tradeoffs of the different architectures.

99 GENERAL AND MISCELLANEOUS↗

HydraGNN_Predictive_GFM_2024 - Ensemble of predictive graph foundation models for ground state atomistic materials modeling

We provide the ensemble of fifteen pre-trained graph foundation models (GFMs) for atomistic materials modeling applications. Each one of the fifteen GFMs has been trained on five open-source datasets that (once aggregated) amount to over 154 million atomistic structures, which cover over two-thirds of the natural elements of the periodic table and that comprises a broad set of organic and inorganic compounds. This vast set of atomistic structures comprises ground state configurations that are dynamically stable (i.e., equilibrated structures with atomic forces approximately close to zero values) as well as dynamically unstable structures (i.e., non-equilibrium structures with non-negligible non-zero values of atomic forces). The ensemble of datasets aggregated does NOT include excited states. The datasets have been curated to remove atomistic structures with spectral norm of the force tensor above 100 eV/angstrom. Moreover, a linear term of the energy was computed for each dataset using a linear regression model that uses the chemical concentration of each natural element as regressor. The linear term predicted by the linear regression model has been subtracted from each original energy value to perform a re-alignment of the energy values across different electronic structures approximation theories performed to generate the diverse multi-source, multi-fidelity datasets. The folder "ADIOS_files" contains the set of pre-processed datasets in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used for the development and training of GFMs in this work. The "ADIOS_files" directory contains 6 sub-directories named as follows: - ANI1x-v3.bp - MPTrj-v3.bp - OC2020-20M-v3.bp - OC2020-v3.bp - OC2022-v3.bp - qm7x-v3.bp Each sub-directory contains the pre-processed datasets converted in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used to the development, training, and performance testing of the ensemble go predictive graph foundation models. Each GFM was developed using HydraGNN (https://github.com/ORNL/HydraGNN) as underlying graph neural network (GNN) architecture. The multi-task learning (MTL) capability of HydraGNN was used to simultaneously train the GFMs on labeled values for direct predictions of energy (a total system property of an atomistic structure that measures the chemical stability) and atomic forces (an atomic level property of an atomistic structure that measures the dynamical stability). The hyper parameters of the GFM have been tuned using scalable hyperparameter optimization (HPO) algorithms implemented in the software DeepHyper (https://github.com/deephyper/deephyper). The pre-training of each HPO trial was performed using distributed data parallelism (DDP) to scale the training across 128 compute nodes of the exascale OLCF supercomputer Frontier. Each HPO trial was trained only for 10 epochs and an early stopping was performed to avoid wasting significant computational resources on GNN architectures that were clearly underperforming. For each HPO trial, the 'omnistat' tool developed by (AMD Research - Advanced Micro Device) was used to measure the total energy consumption in kWh. The ensemble of GFMs was obtained by selecting the fifteen best performing HPO trials. Four models have been selected for their clear advantage in accuracy, and these are the GFMs with IDs 229, 156, 147, 260. Additional eleven models have been selected based on judicious balance between accuracy and energy consumption needed for training, and these are the GFMs with IDs 165, 78, 137, 1, 175, 171, 181, 67, 179, 167, 351. Each selected GFM of the ensemble was continued to cumulate a total of at most 30 epochs. In some cases, the total number of epochs actually performed was les than 30 due to two combined factors: (1) the size of the GFM (i.e., the number of model parameters to train) and (2) the total wall-clock time for which the computational resources could be allocated on OLCF-Frontier. The "Ensemble_of_models" directory contains 15 sub-directories named as follows: - gfm_0.229 - gfm_0.156 - gfm_0.147 - gfm_0.260 - gfm_0.165 - gfm_0.78 - gfm_0.137 - gfm_0.1 - gfm_0.175 - gfm_0.171 - gfm_0.181 - gfm_0.67 - gfm_0.179 - gfm_0.167 - gfm_0.351 Each one of these sub-directories refers to one of the fifteen HPO trials that have been selected to continue the pre-training with at most 30 epochs. With each sub-directory associated with a specific HPO trial, the following files can be found: - config.json: file for argument parsing to develop and train an HydraGNN architecture - gfm_0.ID_epoch_N.pk: file with model parameters for HPO ID trial after N epochs of training The ensemble of fifteen GFM architectures was used for (1) ensemble averaging to stabilize the predictions of energy and atomic forces after pre-training for post-processing analysis and (2) ensemble uncertainty quantification (UQ). The code used to develop, pre-train, and load the pre-trained models for post-processing analysis is available on the ORNL-GitHub at the following link: https://github.com/ORNL/HydraGNN/tree/Predictive_GFM_2024

36 MATERIALS SCIENCE↗

MetaStrider: Architectures for Scalable Memory-centric Reduction of Sparse Data Streams

Reduction is an operation performed on the values of two or more key-value pairs that share the same key. Reduction of sparse data streams finds application in a wide variety of domains such as data and graph analytics, cybersecurity, machine learning, and HPC applications. However, these applications exhibit low locality of reference, rendering traditional architectures and data representations inefficient. This article presents MetaStrider, a significant algorithmic and architectural enhancement to the state-of-the-art, SuperStrider. Furthermore, these enhancements enable a variety of parallel, memory-centric architectures that we propose, resulting in demonstrated performance that scales near-linearly with available memory-level parallelism.

97 MATHEMATICS AND COMPUTING↗

Partitioning Models for Scaling Parallel Sparse Matrix-Matrix Multiplication

We investigate outer-product--parallel, inner-product--parallel, and row-by-row-product--parallel formulations of sparse matrix-matrix multiplication (SpGEMM) on distributed memory architectures. For each of these three formulations, we propose a hypergraph model and a bipartite graph model for distributing SpGEMM computations based on one-dimensional (1D) partitioning of input matrices. Here, we also propose a communication hypergraph model for each formulation for distributing communication operations. The computational graph and hypergraph models adopted in the first phase aim at minimizing the total message volume and balancing the computational loads of processors, whereas the communication hypergraph models adopted in the second phase aim at minimizing the total message count and balancing the message volume loads of processors. That is, the computational partitioning models reduce the bandwidth cost and the communication hypergraph models reduce the latency cost. Our extensive parallel experiments on up to 2048 processors for a wide range of realistic SpGEMM instances show that although the outer-product--parallel formulation scales better, the row-by-row-product--parallel formulation is more viable due to its significantly lower partitioning overhead and competitive scalability. For computational partitioning models, our experimental findings indicate that the proposed bipartite graph models are attractive alternatives to their hypergraph counterparts because of their lower partitioning overhead. Finally, we show that by reducing the latency cost besides the bandwidth cost through using the communication hypergraph models, the parallel SpGEMM time can be further improved up to 32%.

97 MATHEMATICS AND COMPUTING↗

Porting AMG2013 to Heterogeneous CPU+GPU Nodes

LLNL's future advanced technology system SIERRA will feature heterogeneous compute nodes that consist of IBM PowerV9 CPUs and NVIDIA Volta GPUs. Conceptually, the motivation for such an architecture is quite straightforward: While GPUs are optimized for throughput on massively parallel workloads, CPUs strive to minimize latency for rather sequential operations. Yet, making optimal use of heterogeneous architectures raises new challenges for the development of scalable parallel software, e.g., with respect to work distribution. Porting LLNL's parallel numerical libraries to upcoming heterogeneous CPU+GPU architectures is therefore a critical factor for ensuring LLNL's future success in ful lling its national mission. One of these libraries, called HYPRE, provides parallel solvers and precondi- tioners for large, sparse linear systems of equations. In the context of this intern- ship project, I consider AMG2013 which is a proxy application for major parts of HYPRE that implements a benchmark for setting up and solving di erent systems of linear equations. In the following, I describe in detail how I ported multiple parts of AMG2013 to the GPU (Section 2) and present results for di erent experiments that demonstrate a successful parallel implementation on the heterogeneous ma- chines surface and ray (Section 3). In Section 4, I give guidelines on how my code should be used. Finally, I conclude and give an outlook for future work (Section 5).

97 MATHEMATICS AND COMPUTING↗

Argonne Leadership Computing Facility 2011 annual report: Shaping future supercomputing

The ALCF's Early Science Program aims to prepare key applications for the architecture and scale of Mira and to solidify libraries and infrastructure that will pave the way for other future production applications. Two billion core-hours have been allocated to 16 Early Science projects on Mira. The projects, in addition to promising delivery of exciting new science, are all based on state-of-the-art, petascale, parallel applications. The project teams, in collaboration with ALCF staff and IBM, have undertaken intensive efforts to adapt their software to take advantage of Mira's Blue Gene/Q architecture, which, in a number of ways, is a precursor to future high-performance-computing architecture. The Argonne Leadership Computing Facility (ALCF) enables transformative science that solves some of the most difficult challenges in biology, chemistry, energy, climate, materials, physics, and other scientific realms. Users partnering with ALCF staff have reached research milestones previously unattainable, due to the ALCF's world-class supercomputing resources and expertise in computation science. In 2011, the ALCF's commitment to providing outstanding science and leadership-class resources was honored with several prestigious awards. Research on multiscale brain blood flow simulations was named a Gordon Bell Prize finalist. Intrepid, the ALCF's BG/P system, ranked No. 1 on the Graph 500 list for the second consecutive year. The next-generation BG/Q prototype again topped the Green500 list. Skilled experts at the ALCF enable researchers to conduct breakthrough science on the Blue Gene system in key ways. The Catalyst Team matches project PIs with experienced computational scientists to maximize and accelerate research in their specific scientific domains. The Performance Engineering Team facilitates the effective use of applications on the Blue Gene system by assessing and improving the algorithms used by applications and the techniques used to implement those algorithms. The Data Analytics and Visualization Team lends expertise in tools and methods for high-performance, post-processing of large datasets, interactive data exploration, batch visualization, and production visualization. The Operations Team ensures that system hardware and software work reliably and optimally; system tools are matched to the unique system architectures and scale of ALCF resources; the entire system software stack works smoothly together; and I/O performance issues, bug fixes, and requests for system software are addressed. The User Services and Outreach Team offers frontline services and support to existing and potential ALCF users. The team also provides marketing and outreach to users, DOE, and the broader community.

99 GENERAL AND MISCELLANEOUS↗