Search NASA⌕ Search

SEARCH · Search NASA

Results for “Multicore”

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 199 records · Page 11

Accelerated Architectures Create Programming Opportunities

In the early 2000s, industry switched to multicore microprocessors to address semiconductors' speed and power limits. However, the change was unsuccessful, leading to dire claims that “Moore's law is ending.” In conclusion, this column suggests that while the approach was sound, it needed a deeper architectural transformation. Industry has since discovered a suitable architecture, but work remains on software to support it.

97 MATHEMATICS AND COMPUTING↗

Source-to-Source Automatic Differentiation of OpenMP Parallel Loops

This article presents our work toward correct and efficient automatic differentiation of OpenMP parallel worksharing loops in forward and reverse mode. Automatic differentiation is a method to obtain gradients of numerical programs, which are crucial in optimization, uncertainty quantification, and machine learning. The computational cost to compute gradients is a common bottleneck in practice. For applications that are parallelized for multicore CPUs or GPUs using OpenMP, one also wishes to compute the gradients in parallel. Here, we propose a framework to reason about the correctness of the generated derivative code, from which we justify our OpenMP extension to the differentiation model. We implement this model in the automatic differentiation tool Tapenade and present test cases that are differentiated following our extended differentiation procedure. Performance of the generated derivative programs in forward and reverse mode is better than sequential, although our reverse mode often scales worse than the input programs.

97 MATHEMATICS AND COMPUTING↗

Automatic Differentiation of C++ Codes on Emerging Manycore Architectures with Sacado

Automatic differentiation (AD) is a well-known technique for evaluating analytic derivatives of calculations implemented on a computer, with numerous software tools available for incorporating AD technology into complex applications. However, a growing challenge for AD is the efficient differentiation of parallel computations implemented on emerging manycore computing architectures such as multicore CPUs, GPUs, and accelerators as these devices become more pervasive. In this work, we explore forward mode, operator overloading-based differentiation of C++ codes on these architectures using the widely available Sacado AD software package. In particular, we leverage Kokkos, a C++ tool providing APIs for implementing parallel computations that is portable to a wide variety of emerging architectures. Here we describe the challenges that arise when differentiating code for these architectures using Kokkos, and two approaches for overcoming them that ensure optimal memory access patterns as well as expose additional dimensions of fine-grained parallelism in the derivative calculation. We describe the results of several computational experiments that demonstrate the performance of the approach on a few contemporary CPU and GPU architectures. We then conclude with applications of these techniques to the simulation of discretized systems of partial differential equations.

97 MATHEMATICS AND COMPUTING↗

A Generalized Framework for Auto-tuning Stencil Computations

This work introduces a generalized framework for automatically tuning stencil computations to achieve superior performance on a broad range of multicore architectures. Stencil (nearest-neighbor) based kernels constitute the core of many important scientific applications involving block-structured grids. Auto-tuning systems search over optimization strategies to find the combination of tunable parameters that maximizes computational efficiency for a given algorithmic kernel. Although the auto-tuning strategy has been successfully applied to libraries, generalized stencil kernels are not amenable to packaging as libraries. Studied kernels in this work include both memory-bound kernels as well as a computation-bound bilateral filtering kernel. We introduce a generalized stencil auto-tuning framework that takes a straightforward Fortran expression of a stencil kernel and automatically generates tuned implementations of the kernel in C or Fortran to achieve performance portability across diverse computer architectures.

97 MATHEMATICS AND COMPUTING↗

Achieving energy efficiency during collective communications

Energy consumption has become a major design constraint in modern computing systems. With the advent of petaflops architectures, power-efficient software stacks have become imperative for scalability. Techniques such as dynamic voltage and frequency scaling (called DVFS) and CPU clock modulation (called throttling) are often used to reduce the power consumption of the compute nodes. To avoid significant performance losses, these techniques should be used judiciously during parallel application execution. For example, its communication phases may be good candidates to apply the DVFS and CPU throttling without incurring a considerable performance loss. They are often considered as indivisible operations although little attention is being devoted to the energy saving potential of their algorithmic steps. In this work, two important collective communication operations, all-to-all and allgather, are investigated as to their augmentation with energy saving strategies on the per-call basis. The experiments prove the viability of such a fine-grain approach. They also validate a theoretical power consumption estimate for multicore nodes proposed here. While keeping the performance loss low, the obtained energy savings were always significantly higher than those achieved when DVFS or throttling were switched on across the entire application run

36 MATERIALS SCIENCE↗

A scalable approach to solving dense linear algebra problems on hybrid CPU-GPU systems

Aiming to fully exploit the computing power of all CPUs and all graphics processing units (GPUs) on hybrid CPU-GPU systems to solve dense linear algebra problems, in this paper we design a class of heterogeneous tile algorithms to maximize the degree of parallelism, to minimize the communication volume, and to accommodate the heterogeneity between CPUs and GPUs. The new heterogeneous tile algorithms are executed upon our decentralized dynamic scheduling runtime system, which schedules a task graph dynamically and transfers data between compute nodes automatically. The runtime system uses a new distributed task assignment protocol to solve data dependencies between tasks without any coordination between processing units. By overlapping computation and communication through dynamic scheduling, we are able to attain scalable performance for the double-precision Cholesky factorization and QR factorization. Finally, our approach demonstrates a performance comparable to Intel MKL on shared-memory multicore systems and better performance than both vendor (e.g., Intel MKL) and open source libraries (e.g., StarPU) in the following three environments: heterogeneous clusters with GPUs, conventional clusters without GPUs, and shared-memory systems with multiple GPUs.

97 MATHEMATICS AND COMPUTING↗

Roofline model toolkit: A practical tool for architectural and program analysis

We present preliminary results of the Roofline Toolkit for multicore, many core, and accelerated architectures. This paper focuses on the processor architecture characterization engine, a collection of portable instrumented micro benchmarks implemented with Message Passing Interface (MPI), and OpenMP used to express thread-level parallelism. These benchmarks are specialized to quantify the behavior of different architectural features. Compared to previous work on performance characterization, these microbenchmarks focus on capturing the performance of each level of the memory hierarchy, along with thread-level parallelism, instruction-level parallelism and explicit SIMD parallelism, measured in the context of the compilers and run-time environments. We also measure sustained PCIe throughput with four GPU memory managed mechanisms. By combining results from the architecture characterization with the Roofline model based solely on architectural specifications, this work offers insights for performance prediction of current and future architectures and their software systems. To that end, we instrument three applications and plot their resultant performance on the corresponding Roofline model when run on a Blue Gene/Q architecture.

97 MATHEMATICS AND COMPUTING↗

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↗

Reducing the Time to Tune Parallel Dense Linear Algebra Routines with Partial Execution and Performance Modeling

We present a modeling framework to accurately predict time to run dense linear algebra calculation. We report the framework’s accuracy in a number of varied computational environments such as shared memory multicore systems, clusters, and large supercomputing installations with tens of thousands of cores. We also test the accuracy for various algorithms, each of which having a different scaling properties and tolerance to low-bandwidth/high-latency interconnects. The predictive accuracy is very good and on the order of measurement accuracy which makes the method suitable for both dedicated and non-dedicated environments. We also present a practical application of our model to reduce the time required to tune and optimize large parallel runs whose time is dominated by linear algebra computations. We show practical examples of how to apply the methodology to avoid common pitfalls and reduce the influence of measurement errors and the inherent performance variability.

Linear systems↗

Graphics processing unit accelerated phase field dislocation dynamics: Application to bi-metallic interfaces

We present the first high-performance computing implementation of the meso-scale phase field dislocation dynamics (PFDD) model on a graphics processing unit (GPU)-based platform. The implementation takes advantage of the portable OpenACC standard directive pragmas along with Nvidia's compute unified device architecture (CUDA) fast Fourier transform (FFT) library called CUFFT to execute the FFT computations within the PFDD formulation on the same GPU platform. The overall implementation is termed ACCPFDD-CUFFT. The package is entirely performance portable due to the use of OPENACC-CUDA inter-operability, in which calls to CUDA functions are replaced with the OPENACC data regions for a host central processing unit (CPU) and device (GPU). A comprehensive benchmark study has been conducted, which compares a number of FFT routines, the Numerical Recipes FFT (FOURN), Fastest Fourier Transform in the West (FFTW), and the CUFFT. The last one exploits the advantages of the GPU hardware for FFT calculations. The novel ACCPFDD-CUFFT implementation is verified using the analytical solutions for the stress field around an infinite edge dislocation and subsequently applied to simulate the interaction and motion of dislocations through a bi-phase copper-nickel (Cu–Ni) interface. It is demonstrated that the ACCPFDD-CUFFT implementation on a single TESLA K80 GPU offers a 27.6X speedup relative to the serial version and a 5X speedup relative to the 22-multicore Intel Xeon CPU E5-2699 v4 @ 2.20 GHz version of the code.

97 MATHEMATICS AND COMPUTING↗

OpenMP and MPI implementations of an elasto-viscoplastic fast Fourier transform-based micromechanical solver for fast crystal plasticity modeling

Here, we explore several parallel implementations of an elasto-viscoplastic fast Fourier transform (EVPFFT) model using Message Passing Interface (MPI), OpenMP, and a hybrid of MPI and OpenMP to efficiently predict micromechanical response of polycrystals. Performance studies using EVPFFT are performed based on domain decomposition over voxels of a periodic cell, which is a representative volume element (RVE) of polycrystalline copper. We begin by parallelizing the computationally intensive Newton–Raphson (NR) single crystal solver within EVPFFT. Next, we compare the performance of the serial and parallel FFTW (Fastest Fourier Transform in the West) using OpenMP (OpenMP-FFTW) and MPI (MPI-FFTW) with the original Numerical Recipes-based FOURN routine within EVPFFT. In the parallel environment, we find that the FFT calculations are best performed using the MPI version of FFTW. Finally, the remainder of the code, except read/write subroutines, is parallelized. Significant speedups of the original EVPFFT model are achieved using MPI on shared memory multicore workstations. Furthermore, results achieved on a distributed memory Cray supercomputer show promising strong and weak scalability and in some cases even super scalability for the single crystal NR solver in EVPFFT. MPI-FFTW also scales perfectly for microstructure RVEs larger than 64 3 FFT voxels. For example, the MPI-EVPFFT parallel version of the code accelerates the simulations for approximately two orders of magnitude using 64 cores over the old serial code for an RVE size of 128 3 . Finally, the parallel EVPFFT code developed in this work can run massive voxel-based microstructural RVEs taking the advantages of thousands of logical cores provided by more advanced clusters.

42 ENGINEERING↗

The role of the spatial heterogeneity and correlation length of surface wettability on two-phase flow in a CO 2 -water-rock system

This study characterized and modeled heterogeneous surface wettability in sandstone and investigated the role of spatial heterogeneity and correlation length of surface wettability on relative permeability in a supercritical CO 2 (scCO 2 )-brine-rock system. Understanding the role of wettability heterogeneity on relative permeability is essential to geological CO 2 sequestration, oil and gas recovery, and contaminated groundwater remediation. Although numerous studies have attempted to understand the influences of surface wettability, capillary number (Ca), and viscosity ratio, the role of the spatial variation and correlation length of surface wettability on two-phase flow in three-dimensional (3D) porous media has not been unraveled due to the challenges in the measurement and representation of realistic rock surface wettability. In this work, we conducted in-situ measurements of surface contact angle (CA) in a Bentheimer sandstone after CO 2 flooding using micro-computed tomography (micro-CT), and found that the pore-scale CA distribution on rock surfaces followed a log-normal distribution associated with a spatial correlation length. Based on the statistical information from CT scanning, a Gaussian random field was used to model CA distributions that had desired standard deviations and spatial correlation lengths, which were then adjusted within a certain range of values for sensitivity analyses to study their combined effects on the two-phase flow in the porous medium using the lattice Boltzmann (LB) method. The LB two-phase flow simulation was accelerated using hybrid, multicore parallel computing to overcome the challenges in simulating multiphase flow in a large 3D domain having 800 × 800 × 600 nodes. The simulation results showed that the surface wettability heterogeneity (i.e., standard deviation of CA) had a lesser effect on the relative permeability of the wetting fluid (water) but a more significant impact on the relative permeability of the non-wetting fluid (scCO 2 ). The Corey model was used to fit the LB-simulated relative permeability curves of water and scCO 2 and showed that the variations in the relative permeability curves for both water and scCO 2 increased as the standard deviation and spatial correlation length of CA increased. This study illustrated that the assumption of homogeneous surface wettability may cause errors in multiphase flow simulations. Furthermore, the impacts of both the standard deviation and spatial correlation length of CAs should be accounted for. This is the first study that explored the spatial correlation lengths associated with CA distributions on sandstone surfaces and comprehensively investigated the roles of both spatial variation and correlation length of CA on two-phase flow properties in 3D porous media. The optimized LB multiphase flow model was proved a powerful tool to study the interplays and combined effects of these statistical parameters, which had critical applications in numerous natural and engineering processes that involved multiphase flow in porous media.

58 GEOSCIENCES↗

An OpenMP GPU-offload implementation of a non-equilibrium solidification cellular automata model for additive manufacturing

Here, in this paper, performance strategies on GPU-based HPC platforms of a cellular automata (CA) simulation code for non-equilibrium solidification, including nucleation, grain growth, solute partitioning and transport for the metal additive manufacturing (AM) process are investigated using OpenMP 4.5. To accurately report the speed-up for multicore CPUs and GPUs, a rigorous performance analysis employed optimizations appropriate for both CPU-only code (baseline) and GPU offload codes for an isothermal test problem. The performance results on Summit at the Oak Ridge Leadership Computing Facility indicate that using a precomputed list of interface cells significantly decreased the wall-clock time on GPUs. The speedup due to GPU acceleration was evaluated for a full Summit node and measured to be 1.8X when comparing a 6 MPI tasks run with 6 GPUs versus 36 MPI tasks on the CPU only. That speed-up was found to be 7.9X when comparing 6 MPI tasks with 6 GPUs versus the 6 MPI tasks running on the CPU only. Performance measurements showed that system total time is almost constant for runs with more than 96 MPI tasks (or GPUs), indicating that the GPU-accelerated code showed an excellent weak scaling performance. Finally, a rapid directional solidification problem was considered to demonstrate the CA code capability on Summit. It was found that a mesh size of at least 0.05 μm is recommended for the AM-like simulations in order to obtain accurate elongated grain microstructure and elongated subgrain features, which are in qualitative good agreement with experimental data. The results presented in this study indicate that the performance strategies on GPU-based HPC platforms for the CA code are appropriate for novel HPC exascale platforms.

36 MATERIALS SCIENCE↗

Parallel-vector algorithms for particle simulations on shared-memory multiprocessors

Over the last few decades, the computational demands of massive particle-based simulations for both scientific and industrial purposes have been continuously increasing. Hence, considerable efforts are being made to develop parallel computing techniques on various platforms. In such simulations, particles freely move within a given space, and so on a distributed-memory system, load balancing, i.e., assigning an equal number of particles to each processor, is not guaranteed. However, shared-memory systems achieve better load balancing for particle models, but suffer from the intrinsic drawback of memory access competition, particularly during (1) paring of contact candidates from among neighboring particles and (2) force summation for each particle. Here, novel algorithms are proposed to overcome these two problems. For the first problem, the key is a pre-conditioning process during which particle labels are sorted by a cell label in the domain to which the particles belong. Then, a list of contact candidates is constructed by pairing the sorted particle labels. For the latter problem, a table comprising the list indexes of the contact candidate pairs is created and used to sum the contact forces acting on each particle for all contacts according to Newton's third law. With just these methods, memory access competition is avoided without additional redundant procedures. The parallel efficiency and compatibility of these two algorithms were evaluated in discrete element method (DEM) simulations on four types of shared-memory parallel computers: a multicore multiprocessor computer, scalar supercomputer, vector supercomputer, and graphics processing unit. The computational efficiency of a DEM code was found to be drastically improved with our algorithms on all but the scalar supercomputer. Thus, the developed parallel algorithms are useful on shared-memory parallel computers with sufficient memory bandwidth.

97 MATHEMATICS AND COMPUTING↗

High-performance dynamic quantum clustering on graphics processors

Clustering methods in machine learning may benefit from borrowing metaphors from physics. Dynamic quantum clustering associates a Gaussian wave packet with the multidimensional data points and regards them as eigenfunctions of the Schroedinger equation. The clustering structure emerges by letting the system evolve and the visual nature of the algorithm has been shown to be useful in a range of applications. Furthermore, the method only uses matrix operations, which readily lend themselves to parallelization. In this paper, we develop an implementation on graphics hardware and investigate how this approach can accelerate the computations. We achieve a speedup of up to two magnitudes over a multicore CPU implementation, which proves that quantum-like methods and acceleration by graphics processing units have a great relevance to machine learning.

97 MATHEMATICS AND COMPUTING↗

Performance portability study for massively parallel computational fluid dynamics application on scalable heterogeneous architectures

Patient-specific hemodynamic simulations have the possibility to greatly improve both the diagnosis and treatment of a variety of vascular diseases. Portability will enable wider adoption of computational fluid dynamics (CFD) applications in the biomedical research community and targeting to platforms ideally suited to different vascular regions. Here, we introduce a case study in performance portability that assesses (1) the ease of porting an MPI application optimized for one specific architecture to new platforms using variants of hybrid MPI+X programming models; (2) performance portability seen when simulating blood flow in three different vascular regions on diverse heterogeneous architectures; (3) model-based performance prediction for future architectures; and (4) performance scaling of the hybrid MPI+X programming on parallel heterogeneous systems. We report on the lessons learned in porting HARVEY, a massively parallel CFD application, from traditional multicore CPUs to diverse heterogeneous architectures ranging from NVIDIA/AMD GPUs to Intel MICs and Altera FPGAs.

97 MATHEMATICS AND COMPUTING↗

Test suite for evaluating performance of multithreaded MPI communication.

As parallel systems are commonly being built out of increasingly large multicore chips, application programmers are exploring the use of hybrid programming models combining MPI across nodes and multithreading within a node. Many MPI implementations, however, are just starting to support multithreaded MPI communication, often focussing on correctness first and performance later. As a result, both users and implementers need some measure for evaluating the multithreaded performance of an MPI implementation. In this paper, we propose a number of performance tests that are motivated by typical application scenarios. These tests cover the overhead of providing the MPI-THREAD-MULTIPLE level of thread safety for user programs, the amount of concurrency in different threads making MPI calls, the ability to overlap communication with computation, and other features. We present performance results with this test suite on several platforms (Linux cluster, Sun and IBM SMPs) and MPI implementations (MPICH2, Open MPI, IBM, and Sun).

99 GENERAL AND MISCELLANEOUS↗