Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Parallelism”

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 1,585 records · Page 88

Exploiting variability for energy optimization of parallel programs

Here in this paper we present optimizations that use DVFS mechanisms to reduce the total energy usage in scientific applications. Our main insight is that noise is intrinsic to large scale parallel executions and it appears whenever shared resources are contended. The presence of noise allows us to identify and manipulate any program regions amenable to DVFS. When compared to previous energy optimizations that make per core decisions using predictions of the running time, our scheme uses a qualitative approach to recognize the signature of executions amenable to DVFS. By recognizing the "shape of variability" we can optimize codes with highly dynamic behavior, which pose challenges to all existing DVFS techniques. We validate our approach using offline and online analyses for one-sided and two-sided communication paradigms. We have applied our methods to NWChem, and we show best case improvements in energy use of 12% at no loss in performance when using online optimizations running on 720 Haswell cores with one-sided communication. With NWChem on MPI two-sided and offline analysis, capturing the initialization, we find energy savings of up to 20%, with less than 1% performance cost.

97 MATHEMATICS AND COMPUTING↗

IMPACC: A Tightly Integrated MPI+OpenACC Framework Exploiting Shared Memory Parallelism

We propose IMPACC, an MPI+OpenACC framework for heterogeneous accelerator clusters. IMPACC tightly integrates MPI and OpenACC, while exploiting the shared memory parallelism in the target system. IMPACC dynamically adapts the input MPI+OpenACC applications on the target heterogeneous accelerator clusters to fully exploit target system-specific features. IMPACC provides the programmers with the unified virtual address space, automatic NUMA-friendly task-device mapping, efficient integrated communication routines, seamless streamlining of asynchronous executions, and transparent memory sharing. We have implemented IMPACC and evaluated its performance using three heterogeneous accelerator systems, including Titan supercomputer. Results show that IMPACC can achieve easier programming, higher performance, and better scalability than the current MPI+OpenACC model.

Kim, Jungwon↗

Machine and Application Aware Partitioning for Adaptive Mesh Refinement Applications. In: HPDC '17 Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing

Load balancing and partitioning are critical when it comes to parallel computations. Popular partitioning strategies based on space filling curves focus on equally dividing work. The partitions produced are independent of the architecture or the application. Given the ever-increasing relative cost of data movement and increasing heterogeneity of our architectures, it is no longer sufficient to only consider an equal partitioning of work. Minimizing communication costs are equally if not more important. Our hypothesis is that an unequal partitioning that minimizes communication costs significantly can scale and perform better than conventional equal-work partitioning schemes. This tradeoff is dependent on the architecture as well as the application. We validate our hypothesis in the context of a finite-element computation utilizing adaptive mesh-refinement. Our central contribution is a new partitioning scheme that minimizes the overall runtime of subsequent computations by performing architecture and application-aware non-uniform work assignment in order to decrease time to solution, primarily by minimizing data-movement. We evaluate our algorithm by comparing it against standard space-filling curve based partitioning algorithms and observing time-to-solution as well as energy-to-solution for solving Finite Element computations on adaptively refined meshes. We demonstrate excellent scalability of our new partition algorithm up to $262,144$ cores on ORNL's Titan and demonstrate that the proposed partitioning scheme reduces overall energy as well as time-to-solution for application codes by up to 22.0%.

Fernando, Milinda↗

A 3D Parallel Algorithm for QR Decomposition

Interprocessor communication often dominates the runtime of large matrix computations. Here, we present a parallel algorithm for computing QR decompositions whose bandwidth cost (communication volume) can be decreased at the cost of increasing its latency cost (number of messages). By varying a parameter to navigate the bandwidth/latency tradeoff, we can tune this algorithm for machines with different communication costs.

97 MATHEMATICS AND COMPUTING↗

Island model for parallel evolutionary optimization of spiking neuromorphic computing

Parallel genetic algorithms (PGAs) can be used to accelerate optimization by exploiting large-scale computational resources. In this work, we describe a PGA framework for evolving spiking neural networks (SNNs) for neuromorphic hardware implementation. The PGA framework is based on an islands model with migration. We show that using this framework, better SNNs for neuromorphic systems can be evolved faster.

Schuman, Catherine↗

A massively parallel and scalable multi-CPU material point method

Harnessing the power of modern multi-GPU architectures, we present a massively parallel simulation system based on the Material Point Method (MPM) for simulating physical behaviors of materials undergoing complex topological changes, self-collision, and large deformations. Our system makes three critical contributions. First, we introduce a new particle data structure that promotes coalesced memory access patterns on the GPU and eliminates the need for complex atomic operations on the memory hierarchy when writing particle data to the grid. Second, we propose a kernel fusion approach using a new Grid-to-Particles-to-Grid (G2P2G) scheme, which efficiently reduces GPU kernel launches, improves latency, and significantly reduces the amount of global memory needed to store particle data. Finally, we introduce optimized algorithmic designs that allow for efficient sparse grids in a shared memory context, enabling us to best utilize modern multi-GPU computational platforms for hybrid Lagrangian-Eulerian computational patterns. We demonstrate the effectiveness of our method with extensive benchmarks, evaluations, and dynamic simulations with elastoplasticity, granular media, and fluid dynamics. In comparisons against an open-source and heavily optimized CPU-based MPM codebase [Fang et al. 2019] on an elastic sphere colliding scene with particle counts ranging from 5 to 40 million, our GPU MPM achieves over 100x per-time-step speedup on a workstation with an Intel 8086K CPU and a single Quadro P6000 GPU, exposing exciting possibilities for future MPM simulations in computer graphics and computational science. Moreover, compared to the state-of-the-art GPU MPM method [Hu et al. 2019a], we not only achieve 2x acceleration on a single GPU but our kernel fusion strategy and Array-of-Structs-of-Array (AoSoA) data structure design also generalizes to multi-GPU systems. Our multi-GPU MPM exhibits near-perfect weak and strong scaling with 4 GPUs, enabling performant and large-scale simulations on a 10243 grid with close to 100 million particles with less than 4 minutes per frame on a single 4-GPU workstation and 134 million particles with less than 1 minute per frame on an 8-GPU workstation.

Wang, Xinlei↗

CEAZ: Accelerating Parallel I/O Via Hardware-Algorithm Co-Designed Adaptive Lossy Compression

As supercomputers continue to grow to exa-scale, the amount of data that needs to be saved or transmitted is exploding. To this end, many previous works have studied using error-bounded lossy compressors to reduce the data size and improve the I/O performance. However, little work has been done for effectively offloading lossy compression onto FPGA-based SmartNICs to reduce the compression overhead. In this paper, we propose a hardware-algorithm co-design of efficient and adaptive lossy compressor for scientific data on FPGAs (called CEAZ) to accelerate parallel I/O. Our contribution is fourfold: (1) We propose an efficient Huffman coding approach that can adaptively update Huffman codewords online based on codewords generated offline (from a variety of representative scientific datasets). (2) We derive a theoretical analysis to support a precise control of compression ratio under an error-bounded compression mode, enabling accurate offline Huffman codewords generation. This also help us create a fixed-ratio compression mode for consistent throughput. (3) We develop an efficient compression pipeline by adopting cuSZ’s dual-quantization algorithm to our hardware use case. (4) We evaluate CEAC on five real-world datasets with both a single FPGA board and 256 nodes from Bridges2 supercomputer. Experiments show that CEAZ outperforms the second-best FPGA-based lossy compressor by 2× of throughput and 9.6× of compression ratio. It also improves MPI_File_write and MPI_Gather throughputs by up to 32.7× and 31.4×, respectively.

Zhang, Chengming↗

Accelerated Constrained Sparse Tensor Factorization on Massively Parallel Architectures

This study presents the first constrained sparse tensor factorization (cSTF) framework that optimizes and fully offloads computation to massively parallel GPU architectures, and the first performance characterization of cSTF on GPU architectures. In contrast to prior work on tensor factorization, where the matricized tensor times Khatri-Rao product (MTTKRP) is the primary performance bottleneck, our systematic analysis of the cSTF algorithm on GPUs reveals that adding constraints creates an additional bottleneck in the update operation for many real-world sparse tensors. While executing the update operation on the GPU brings significant speedup over its CPU counterpart, it remains a significant bottleneck. To further accelerate the update operation, we propose cuADMM, a new update algorithm that leverages algorithmic and code optimization strategies to minimize both computation and data movement on GPUs. As a result, our framework delivers significantly improved performance compared to prior state-of-the-art. On 10 real-world sparse tensors, our framework achieves geometric mean speedup of 5.1 × (max 41.59 ×) and 7.01 × (max 58.05 ×) on the NIVIDA A100 and H100 GPUs, respectively, over the state-of-the-art SPLATT library running on a 26-core Intel Ice Lake Xeon CPU.

Soh, Yongseok↗

Determining Levels of Detail for Simulators of Parallel and Distributed Computing Systems via Automated Calibration

There are two sources of inaccuracy when simulating parallel and distributed computing systems: (i) a simulator implemented at an insufficient level of detail; and (ii) incorrectly calibrated simulation parameter values. Increasing the simulator’s level of detail can improve accuracy, but at the cost of higher space, time, and/or software complexity. Furthermore, evaluating the intrinsic accuracy of a simulator requires that its parameters be well-calibrated. Making decisions regarding the level of detail is thus challenging. We propose a methodology for instantiating the simulation calibration process and a framework for automating this process, which makes it possible to pick appropriate levels of detail for any simulator. We demonstrate the usefulness of our approach via two case studies for two different domains.

McDonald, Jessie [University of Hawaii at Manoa, H↗

A Parallel Kinetic Model for Surface and Bulk Charge Storage in ε -MnO 2 Pseudocapacitors

Pseudocapacitive materials such as manganese dioxide (MnO 2 ) are attractive for energy storage applications due to their ability to combine the fast kinetics of capacitors with the higher energy density of battery-type systems. However, the electrochemical behavior of MnO 2 remains difficult to interpret mechanistically, in part because existing models often fail to distinguish between surface-based redox processes and bulk intercalation mechanisms. In this work, we develop a physics-based model that represents MnO 2 pseudocapacitance as a linear combination of two independent, parallel electrochemical processes: (i) the surface or near-surface redox storage and (ii) lithium ion intercalation into the bulk material. These two processes are treated with distinct kinetic and thermodynamic parameters and are assumed to proceed independently. The total measured current is assumed to be the sum of these two partial currents. We validate the model using rate-dependent cyclic voltammetry experiments, demonstrating that it captures key trends and provides physically interpretable parameters reflecting the relative contributions of surface and bulk processes. By enabling a clear separation between these mechanisms, the model offers a useful framework for analyzing pseudocapacitive materials and can guide the rational design of high-performance energy storage electrodes.

Energy - Storage↗

A Parallel Stochastic Framework for Reservoir Characterization and History Matching

The spatial distribution of parameters that characterize the subsurface is never known to any reasonable level of accuracy required to solve the governing PDEs of multiphase flow or species transport through porous media. This paper presents a numerically cheap, yet efficient, accurate and parallel framework to estimate reservoir parameters, for example, medium permeability, using sensor information from measurements of the solution variables such as phase pressures, phase concentrations, fluxes, and seismic and well log data. Numerical results are presented to demonstrate the method.

Thomas, Sunil G.↗

Large-Scale Modeling of Epileptic Seizures: Scaling Properties of Two Parallel Neuronal Network Simulation Algorithms

Our limited understanding of the relationship between the behavior of individual neurons and large neuronal networks is an important limitation in current epilepsy research and may be one of the main causes of our inadequate ability to treat it. Addressing this problem directly via experiments is impossibly complex; thus, we have been developing and studying medium-large-scale simulations of detailed neuronal networks to guide us. Flexibility in the connection schemas and a complete description of the cortical tissue seem necessary for this purpose. In this paper we examine some of the basic issues encountered in these multiscale simulations. We have determined the detailed behavior of two such simulators on parallel computer systems. The observed memory and computation-time scaling behavior for a distributed memory implementation were very good over the range studied, both in terms of network sizes (2,000 to 400,000 neurons) and processor pool sizes (1 to 256 processors). Our simulations required between a few megabytes and about 150 gigabytes of RAM and lasted between a few minutes and about a week, well within the capability of most multinode clusters. Therefore, simulations of epileptic seizures on networks with millions of cells should be feasible on current supercomputers.

59 BASIC BIOLOGICAL SCIENCES↗

Clock Agreement Among Parallel Supercomputer Nodes

This dataset presents measurements that quantify the clock synchronization time-agreement characteristics among several high performance computers including the current world's most powerful machine for open science, the U.S. Department of Energy's Titan machine sited at Oak Ridge National Laboratory. These ultra-fast machines derive much of their computational capability from extreme node counts (over 18000 nodes in the case of the Titan machine). Time-agreement is commonly utilized by parallel programming applications and tools, distributed programming application and tools, and system software. Our time-agreement measurements detail the degree of time variance between nodes and how that variance changes over time. The dataset includes empirical measurements and the accompanying spreadsheets.

97 MATHEMATICS AND COMPUTING↗

Parallel electron force balance and the L-H transition

In one popular description of the L-H transition, energy transfer to the mean flows directly depletes turbulence fluctuation energy, resulting in suppression of the turbulence and a corresponding transport bifurcation. However, electron parallel force balance couples nonzonal velocity fluctuations with electron pressure fluctuations on rapid timescales, comparable with the electron transit time. For this reason, energy in the nonzonal velocity stays in a fairly fixed ratio to the free energy in electron density fluctuations, at least for frequency scales much slower than electron transit. In order for direct depletion of the energy in turbulent fluctuations to cause the L-H transition, energy transfer via Reynolds stress must therefore drain enough energy to significantly reduce the sum of the free energy in nonzonal velocities and electron pressure fluctuations. At low k, the electron thermal free energy is much larger than the energy in nonzonal velocities, posing a stark challenge for this model of the L-H transition.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Parallel electron force balance and the L-H transition

In one popular description of the L-H transition, energy transfer to the mean flows directly depletes turbulence fluctuation energy, resulting in suppression of the turbulence and a corresponding transport bifurcation. However, electron parallel force balance couples nonzonal velocity fluctuations with electron pressure fluctuations on rapid timescales, comparable with the electron transit time. For this reason, energy in the nonzonal velocity stays in a fairly fixed ratio to the free energy in electron density fluctuations, at least for frequency scales much slower than electron transit. In order for direct depletion of the energy in turbulent fluctuations to cause the L-H transition, energy transfer via Reynolds stress must therefore drain enough energy to significantly reduce the sum of the free energy in nonzonal velocities and electron pressure fluctuations. At low k, the electron thermal free energy is much larger than the energy in nonzonal velocities, posing a stark challenge for this model of the L-H transition.

L-H transition↗

Parallel Environment for the Creation of Stochastics 1.0

PECOS is a computational library for creating and manipulating realizations of stochastic quantities, including scalar uncertain variables, random fields, and stochastic processes. It offers a unified interface to univariate and multivariate polynomial approximations using either orthogonal or interpolation polynomials; numerical integration drivers for Latin hypercube sampling, quadrature, cubature, and sparse grids; and fast Fourier transforms using third party libraries. The PECOS core also offers statistical utilities and transformations between various representations of stochastic uncertainty. PECOS provides a C++ API through which users can generate and transform realizations of stochastic quantities. It is currently used by Sandia's DAKOTA, Stokhos, and Encore software packages for uncertainty quantification and verification. PECOS generates random sample sets and multi-dimensional integration grids, typically used in forward propagation of scalar uncertainty in computational models (uncertainty quantification (UQ)). PECOS also generates samples of random fields (RFs) and stochastic processes (SPs) from a set of user-defined power spectral densities (PSDs). The RF/SP may be either Gaussian or non-Gaussian and either stationary or nonstationary, and the resulting sample is intended for run-time query by parallel finite element simulation codes. Finally, PECOS supports nonlinear transformations of random variables via the Nataf transformation and extensions.

Field Jr, Richard↗

Parallel Element Agglomeration Algebraic Multigrid and Upscaling Library

ParFELAG is a parallel distributed memory C++ library for numerical upscaling of finite element discretizations. It provides optimal complesity algorithms ro build multilevel hierarchies and solvers that can be used for solving a wide class of partial differential equations (elliptic, hyperbolic, saddle point problems) on general unstructured mesh (under the assumption that the topology of the agglomerated entities is correct). Additionally, a novel multilevel solver for saddle point problems with divergence constraint is implemented.

Source record↗

Communication Graph Generator for Parallel Programs

Graphator is a collection of relatively simple sequential programs that generate communication graphs/matrices for commonly occurring patterns in parallel programs. Currently, there is support for five communication patterns: two-dimensional 4-point stencil, four-dimensional 8-point stencil, all-to-alls over sub-communicators, random near-neighbor communication, and near-neighbor communication.

Source record↗