Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “CRAY”

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 253 records · Page 14

Are we witnessing the spectre of an HPC meltdown?: Are We Witnessing the Spectre of an HPC Meltdown?

In this study, we measure and analyze the performance observed when running applications and benchmarks before and after the Meltdown and Spectre fixes have been applied to the Cray supercomputers and supporting systems at the Oak Ridge Leadership Computing Facility (OLCF). Of particular interest is the effect of these fixes on applications selected from the OLCF portfolio when running at scale. This comprehensive study presents results from experiments run on Titan, Eos, Cumulus, and Percival supercomputers at the OLCF. Lastly, the results from this study are useful for HPC users running on Cray supercomputers and serve to better understand the impact that these two vulnerabilities have on diverse HPC workloads at scale.

97 MATHEMATICS AND COMPUTING↗

Performance Tuning of Fock Matrix and Two-Electron Integral Calculations for NWChem on Leading HPC Platforms

Attaining performance in the evaluation of two-electron repulsion integrals and constructing the Fock matrix is of considerable importance to the computational chemistry community. Due to its numerical complexity improving the performance behavior across a variety of leading supercomputing platforms is an increasing challenge due to the significant diversity in high-performance computing architectures. In this paper, we present our successful tuning methodology for these important numerical methods on the Cray XE6, the Cray XC30, the IBM BG/Q, as well as the Intel Xeon Phi. Our optimization schemes leverage key architectural features including vectorization and simultaneous multithreading, and results in speedups of up to 2.5x compared with the original implementation.

Shan, Hongzhan↗

OpenSHMEM-UCX: Evaluation of UCX for Implementing OpenSHMEM Programming Model, In: OpenSHMEM 2016: OpenSHMEM and Related Technologies. Enhancing OpenSHMEM for Hybrid Environments

The OpenSHMEM reference implementation was developed towards the goal of developing an open source and high-performing OpenSHMEM implementation. To achieve portability and performance across various networks, the OpenSHMEM reference implementation uses GASNet and UCCS for network operations. Recently, new network layers have emerged with the promise of providing high-performance, scalability, and portability for HPC applications. In this paper, we implement the OpenSHMEM reference implementation to use the UCX framework for network operations. Then, we evaluate its performance and scalability on Cray XK systems to understand UCX’s suitability for developing the OpenSHMEM programming model. Further, we develop a benchmark called SHOMS for evaluating the OpenSHMEM implementation. Our experimental results show that OpenSHMEM-UCX outperforms the vendor supplied OpenSHMEM implementation in most cases on the Cray XK system by up to 40% with respect to message rate and up to 70% for the execution of application kernels.

Computer Science↗

Accelerating nuclear configuration interaction calculations through a preconditioned block iterative eigensolver

We describe a number of recently developed techniques for improving the performance of large-scalenuclear configuration interaction calculations on high performance parallel computers. We show thebenefit of using a preconditioned block iterative method to replace the Lanczos algorithm that hastraditionally been used to perform this type of computation. The rapid convergence of the block iterativemethod is achieved by a proper choice of starting guesses of the eigenvectors and the construction of aneffective preconditioner. These acceleration techniques take advantage of special structure of the nuclearconfiguration interaction problem which we discuss in detail. The use of a block method also allows usto improve the concurrency of the computation, and take advantage of the memory hierarchy of modernmicroprocessors to increase the arithmetic intensity of the computation relative to data movement. Wealso discuss the implementation details that are critical to achieving high performance on massivelyparallel multi-core supercomputers, and demonstrate that the new block iterative solver is two to threetimes faster than the Lanczos based algorithm for problems of moderate sizes on a Cray XC30 system.

Shao, Meiyue↗

A high-order discontinuous Galerkin method for wave propagation through coupled elastic-acoustic media

We introduce a high-order discontinuous Galerkin (dG) scheme for the numerical solution of three-dimensional (3D) wave propagation problems in coupled elastic-acoustic media. A velocity-strain formulation is used, which allows for the solution of the acoustic and elastic wave equations within the same unified framework. Careful attention is directed at the derivation of a numerical flux that preserves high-order accuracy in the presence of material discontinuities, including elastic-acoustic interfaces. Explicit expressions for the 3D upwind numerical flux, derived as an exact solution for the relevant Riemann problem, are provided. The method supports h-non-conforming meshes, which are particularly effective at allowing local adaptation of the mesh size to resolve strong contrasts in the local wavelength, as well as dynamic adaptivity to track solution features. The use of high-order elements controls numerical dispersion, enabling propagation over many wave periods. We prove consistency and stability of the proposed dG scheme. To study the numerical accuracy and convergence of the proposed method, we compare against analytical solutions for wave propagation problems with interfaces, including Rayleigh, Lamb, Scholte, and Stoneley waves as well as plane waves impinging on an elastic-acoustic interface. Spectral rates of convergence are demonstrated for these problems, which include a non-conforming mesh case. Finally, we present scalability results for a parallel implementation of the proposed high-order dG scheme for large-scale seismic wave propagation in a simplified earth model, demonstrating high parallel efficiency for strong scaling to the full size of the Jaguar Cray XT5 supercomputer.

97 MATHEMATICS AND COMPUTING↗

A case study of CUDA FORTRAN and OpenACC for an atmospheric climate kernel

The porting of a key kernel in the tracer advection routines of the Community Atmosphere Model – Spectral Element (CAM-SE) to use Graphics Processing Units (GPUs) using OpenACC is considered in comparison to an existing CUDA FORTRAN port. The development of the OpenACC kernel for GPUs was substantially simpler than that of the CUDA port. Also, OpenACC performance was about 1.5× slower than the optimized CUDA version. Particular focus is given to compiler maturity regarding OpenACC implementation for modern FORTRAN, and it is found that the Cray implementation is currently more mature than the PGI implementation. Still, for the case that ran successfully on PGI, the PGI OpenACC runtime was slightly faster than Cray. The results show encouraging performance for OpenACC implementation compared to CUDA while also exposing some issues that may be necessary before the implementations are suitable for porting all of CAM-SE. Furthermore, most notable are that GPU shared memory should be used by future OpenACC implementations and that derived type support should be expanded.

54 ENVIRONMENTAL SCIENCES↗

Cross-scale efficient tensor contractions for coupled cluster computations through multiple programming model backends

Coupled-cluster methods provide highly accurate models of molecular structure through explicit numerical calculation of tensors representing the correlation between electrons. These calculations are dominated by a sequence of tensor contractions, motivating the development of numerical libraries for such operations. While based on matrix–matrix multiplication, these libraries are specialized to exploit symmetries in the molecular structure and in electronic interactions, and thus reduce the size of the tensor representation and the complexity of contractions. The resulting algorithms are irregular and their parallelization has been previously achieved via the use of dynamic scheduling or specialized data decompositions. We introduce our efforts to extend the Libtensor framework to work in the distributed memory environment in a scalable and energy-efficient manner. We achieve up to 240× speedup compared with the optimized shared memory implementation of Libtensor. We attain scalability to hundreds of thousands of compute cores on three distributed-memory architectures (Cray XC30 and XC40, and IBM Blue Gene/Q), and on a heterogeneous GPU-CPU system (Cray XK7). As the bottlenecks shift from being compute-bound DGEMM's to communication-bound collectives as the size of the molecular system scales, we adopt two radically different parallelization approaches for handling load-imbalance, tasking and bulk synchronous models. Nevertheless, we preserve a unified interface to both programming models to maintain the productivity of computational quantum chemists.

97 MATHEMATICS AND COMPUTING↗

A communication-avoiding 3D algorithm for sparse LU factorization on heterogeneous systems

We propose a new algorithm to improve the strong scalability of right-looking sparse LU factorization on distributed memory systems. Our 3D algorithm for sparse LU uses a three-dimensional MPI process grid, exploits elimination tree parallelism, and trades off increased memory for reduced per-process communication. We also analyze the asymptotic improvements for planar graphs (e.g., those arising from 2D grid or mesh discretizations) and certain non-planar graphs (specifically for 3D grids and meshes). For a planar graph with $n$ vertices, our algorithm reduces communication volume asymptotically in $n$ by a factor of $\mathscr{O}$ $\Big(\sqrt{log \ n}\Big)$ and latency by a factor of $\mathscr{O}$ $(log \ n)$. For nonplanar cases, our algorithm can reduce the per-process communication volume by 3× and latency by $\mathscr{O}$ $\Big(n^\frac13\Big)$ times. In all cases, the memory needed to achieve these gains is a constant factor. We implemented our algorithm by extending the 2D data structure used in SuperLU_DIST. Our new 3D code achieves empirical speedups up to 27× for planar graphs and up to 3.3× for non-planar graphs over the baseline 2D SuperLU_DIST when run on 24,000 cores of a Cray XC30. We extend the 3D algorithm for heterogeneous architectures by adding the Highly Asynchronous Lazy Offload (Halo) algorithm for co-processor offload. On 4096 nodes of a Cray XK7 with 32,768 CPU cores and 4096 Nvidia K20x GPUs, the 3D algorithm achieves empirical speedups up to 24× for planar graphs and 3.5× for non-planar graphs over the baseline 2D SuperLU_DIST with co-processor acceleration.

97 MATHEMATICS AND COMPUTING↗

Parallel performance optimizations on unstructured mesh-based simulations

This paper addresses two key parallelization challenges the unstructured mesh-based ocean modeling code, MPAS-Ocean, which uses a mesh based on Voronoi tessellations: (1) load imbalance across processes, and (2) unstructured data access patterns, that inhibit intra- and inter-node performance. Our work analyzes the load imbalance due to naive partitioning of the mesh, and develops methods to generate mesh partitioning with better load balance and reduced communication. Furthermore, we present methods that minimize both inter- and intranode data movement and maximize data reuse. Our techniques include predictive ordering of data elements for higher cache efficiency, as well as communication reduction approaches. We present detailed performance data when running on thousands of cores using the Cray XC30 supercomputer and show that our optimization strategies can exceed the original performance by over 2×. Additionally, many of these solutions can be broadly applied to a wide variety of unstructured grid-based computations.

97 MATHEMATICS AND COMPUTING↗

High-performance finite-difference time-domain simulations of C-Mod and ITER RF antennas

Finite-difference time-domain methods have, in recent years, developed powerful capabilities for modeling realistic ICRF behavior in fusion plasmas [1, 2, 3, 4]. When coupled with the power of modern high-performance computing platforms, such techniques allow the behavior of antenna near and far fields, and the flow of RF power, to be studied in realistic experimental scenarios at previously inaccessible levels of resolution. In this talk, we present results and 3D animations from high-performance FDTD simulations on the Titan Cray XK7 supercomputer, modeling both Alcator C-Mod’s field-aligned ICRF antenna and the ITER antenna module. Much of this work focuses on scans over edge density, and tailored edge density profiles, to study dispersion and the physics of slow wave excitation in the immediate vicinity of the antenna hardware and SOL. An understanding of the role of the lower-hybrid resonance in low-density scenarios is emerging, and possible implications of this for the NSTX launcher and power balance are also discussed. In addition, we discuss ongoing work centered on using these simulations to estimate sputtering and impurity production, as driven by the self-consistent sheath potentials at antenna surfaces.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

An Approach to Selecting Thread + Process Mixes for Hybrid MPI + OpenMP Applications, In: 2015 IEEE International Conference on Cluster Computing

Hybrid MPI + OpenMP is a popular means of programming modern machines that feature substantial parallelism both off-node and on-node. Determining the right mix of the two programming models to use, however, is not as straightforward as simply using exclusively OpenMP on-node and limiting MPI to only inter-node communication. We present a step-by-step methodology to help make the decision of which mix of the two programming models to use. It starts with an estimate of the performance of a generic hybrid application on a given machine and incorporates additional available information about the specific application and the machine to provide guidance for selecting effective mixes of MPI processes and OpenMP threads to use when running that application on the machine in question. We validate our approach on four different applications on an IBM Blue Gene/Q, a Cray XK7, and a Cray XC30.

Computer Science↗

Parallel Reconstruction of Three Dimensional Magnetohydrodynamic Equilibria in Plasma Confinement Devices

Fast, accurate three dimensional reconstructions of plasma equilibria, crucial for physics interpretation of fusion data generated within confinement devices like stellarators/ tokamaks, are computationally very expensive and routinely require days, even weeks, to complete using serial approaches. Here, we present a parallel implementation of the three dimensional plasma reconstruction code, V3FIT. A formal analysis to identify the performance bottlenecks and scalability limits of this new parallel implementation, which combines both task and data parallelism, is presented. The theoretical findings are supported by empirical performance results on several thousands of processor cores of a Cray XC30 supercomputer. Parallel V3FIT is shown to deliver over 40X speedup, enabling fusion scientists to carry out three dimensional plasma equilibrium reconstructions at unprecedented scales in only a few hours (instead of in days/weeks) for the first time.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Scaling Linear Algebra Kernels using Remote Memory Access

This paper describes the scalability of linear algebra kernels based on remote memory access approach. The current approach differs from the other linear algebra algorithms by the explicit use of shared memory and remote memory access (RMA) communication rather than message passing. It is suitable for clusters and scalable shared memory systems. The experimental results on large scale systems (Linux-Infiniband cluster, Cray XT) demonstrate consistent performance advantages over ScaLAPACK suite, the leading implementation of parallel linear algebra algorithms used today. For example, on a Cray XT4 for a matrix size of 102400, our RMA-based matrix multiplication achieved over 55 teraflops while ScaLAPACK’s pdgemm measured close to 42 teraflops on 10000 processes.

99 GENERAL AND MISCELLANEOUS↗

UPC++: A High-Performance Communication Framework for Asynchronous Computation

© 2019 IEEE UPC++ is a C++ library that supports high-performance computation via an asynchronous communication framework. This paper describes a new incarnation that differs substantially from its predecessor, and we discuss the reasons for our design decisions. We present new design features, including future-based asynchrony management, distributed objects, and generalized Remote Procedure Call (RPC). We show microbenchmark performance results demonstrating that one-sided Remote Memory Access (RMA) in UPC++ is competitive with MPI-3 RMA; on a Cray XC40 UPC++ delivers up to a 25% improvement in the latency of blocking RMA put, and up to a 33% bandwidth improvement in an RMA throughput test. We showcase the benefits of UPC++ with irregular applications through a pair of application motifs, a distributed hash table and a sparse solver component. Our distributed hash table in UPC++ delivers near-linear weak scaling up to 34816 cores of a Cray XC40. Our UPC++ implementation of the sparse solver component shows robust strong scaling up to 2048 cores, where it outperforms variants communicating using MPI by up to 3.1x. UPC++ encourages the use of aggressive asynchrony in low-overhead RMA and RPC, improving programmer productivity and delivering high performance in irregular applications.

Bachan, John↗

Designing Next Generation Massively Multithreaded Architectures for Irregular Applications

Irregular applications, such as data mining or graph-based computations, show unpredictable memory/network access patterns and control structures. Massively multi-threaded architectures with large node count, like the Cray XMT, have been shown to address their requirements better than commodity clusters. In this paper we present the approaches that we are currently pursuing to design future generations of these architectures. First, we introduce the Cray XMT and compare it to other multithreaded architectures. We then propose an evolution of the architecture, integrating multiple cores per node and next generation network interconnect. We advocate the use of hardware support for remote memory reference aggregation to optimize network utilization. For this evaluation we developed a highly parallel, custom simulation infrastructure for multi-threaded systems. Our simulator executes unmodified XMT binaries with very large datasets, capturing effects due to contention and hot-spotting, while predicting execution times with greater than 90% accuracy. We also discuss the FPGA prototyping approach that we are employing to study efficient support for irregular applications in next generation manycore processors.

Tumeo, Antonino↗

ECP SOLLVE: Validation and Verification Testsuite Status Update and Compiler Insight for OpenMP

The OpenMP language continues to evolve with every new specification release, as does the need to validate and verify the new features that have been implemented by the different vendors. With the release of OpenMP 5.0 and OpenMP 5.1, new target offload and host-based features have been introduced to the programming model. While OpenMP continues to grow in maturity, there is an observable growth in the number of compiler and hardware vendors that support OpenMP. In this manuscript, the main focus is on evaluating the conformity and OpenMP implementation progress of various compiler vendors such as Cray, IBM, GNU, Clang/LLVM, NVIDIA, and Intel. More specifically, the 4.5, 5.0, and 5.1 versions of the OpenMP specification are analyzed. For our experimental setup, the Crusher and Summit computing systems hosted by Oak Ridge National Lab’s Computing Facilities are utilized. The effort of vendor agnostic analysis of these implementations is especially valuable for application developers who are using new OpenMP features to accelerate their scientific codes. Insights are presented into the current implementation status of various vendors, the progression of specific compiler’s support for OpenMP overtime, the subset of OpenMP 4.5, 5.0, and 5.1 that is supported by all compilers, and examples of how our test suite has influenced discussion regarding the correct interpretation of the OpenMP specification. By evaluating OpenMP conformity of pre-Exascale computing systems, the aim is to detail progress and status of AMD + Cray ecosystem before the system and their OpenMP implementation is used for mission critical applications when the first Exascale Computer Frontier is made available to applications.

Huber, Thomas↗

Global Data Re-allocation via Communication Aggregation in Chapel

Chapel is a parallel programming language designed to improve the productivity and ease of use of conventional and parallel computers. This language currently delivers sub optimal performance when executing codes that perform global data re-allocation operations on distributed memory architectures. This is mainly due to data communication that is done without aggregation (one message for each remote array element). In this work, we analyze Chapel's standard Block and Cyclic distribution modules and optimize the communication routines for array assignments by performing aggregation. Thanks to the expressive power of Chapel, the compiler and runtime have enough information to do communication aggregation without user intervention. The runtime relies on the low-level GAS Net networking layer, whose versions of one-sided bulk put/get routines that support strides are particularly useful for us. Experimental results conducted on Hector (a Cray XE6) and Jaguar (Cray XK6)reveal that the implemented techniques can lead to significant reductions in communication time.

Sanz, Alberto↗