SEARCH · Search NASA
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.
Scientists studying the structure and behavior of the atomic nucleus require immense high-performance computing resources to gain scientific insights. Several nuclear physics codes are capable of scaling to more than 100,000 cores on Oak Ridge National Laboratory's petaflop Cray XT5 system, Jaguar. In this paper, we present our work on optimizing codes in the nuclear physics domain.
ne-sided communication is important to enable asynchronous communication and data movement for Global Address Space (GAS) programming models. Such communication is typically realized through direct messages between initiator and target processes. For petascale systems with 10,000s of nodes and 100,000s of cores, these direct messages require dedicated communication buffers and/or channels, which can lead to significant scalability challenges for GAS programming models. In this paper, we describe a network-friendly communication model, multinode cooperation, to enable indirect one-sided communication. Compute nodes work together to handle one-sided requests through (1) request forwarding in which one node can intercept a request and forward it to a target node, and (2) request aggregation in which one node can aggregate many requests to a target node. We have implemented multinode cooperation for a popular GAS runtime library, Aggregate Remote Memory Copy Interface (ARMCI). Our experimental results on a large-scale Cray XT5 system demonstrate that, multinode cooperation is able to greatly increase the memory scalability by reducing the number of communication buffers. In addition, multinode cooperation improves the resiliency of GAS runtime system to network contention. Furthermore, multinode cooperation can benefit the performance of scientific applications. In one case, it reduces the total execution time of an NWChem application by 52%.
ne-sided communication is important to enable asynchronous communication and data movement for Global Address Space (GAS) programming models. Such communication is typically realized through direct messages between initiator and target processes. For petascale systems with 10,000s of nodes and 100,000s of cores, these direct messages require dedicated communication buffers and/or channels, which can lead to significant scalability challenges for GAS programming models. In this paper, we describe a network-friendly communication model, multinode cooperation, to enable indirect one-sided communication. Compute nodes work together to handle one-sided requests through (1) request forwarding in which one node can intercept a request and forward it to a target node, and (2) request aggregation in which one node can aggregate many requests to a target node. We have implemented multinode cooperation for a popular GAS runtime library, Aggregate Remote Memory Copy Interface (ARMCI). Our experimental results on a large-scale Cray XT5 system demonstrate that, multinode cooperation is able to greatly increase the memory scalability by reducing the number of communication buffers. In addition, multinode cooperation improves the resiliency of GAS runtime system to network contention. Furthermore, multinode cooperation can benefit the performance of scientific applications. In one case, it reduces the total execution time of an NWChem application by 52%.
No abstract prepared.
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.
Many scientific simulations, using the Message Passing Interface (MPI) programming model, are sensitive to the performance and scalability of reduction collective operations such as MPI_Allreduce and MPI_Reduce. These operations are the most widely used abstractions to perform mathematical operations over all processes that are part of the simulation. In this work, we propose a hierarchical design to implement the reduction operations on multicore systems. This design aims to improve the efficiency of reductions by 1) tailoring the algorithms and customizing the implementations for various communication mechanisms in the system 2) providing the ability to configure the depth of hierarchy to match the system architecture, and 3) providing the ability to independently progress each of this hierarchy. Using this design, we implement MPI_Allreduce and MPI_Reduce operations (and its nonblocking variants MPI_Iallreduce and MPI_Ireduce) for all message sizes, and evaluate on multiple architectures including InfiniBand and Cray XT5. We leverage and enhance our existing infrastructure, Cheetah, which is a framework for implementing hierarchical collective operations to implement these reductions. The experimental results show that the Cheetah reduction operations outperform the production-grade MPI implementations such as Open MPI default, Cray MPI, and MVAPICH2, demonstrating its efficiency, flexibility and portability. On Infini-Band systems, with a microbenchmark, a 512-process Cheetah nonblocking Allreduce and Reduce achieves a speedup of 23x and 10x, respectively, compared to the default Open MPI reductions. The blocking variants of the reduction operations also show similar performance benefits. A 512-process nonblocking Cheetah Allreduce achieves a speedup of 3x, compared to the default MVAPICH2 Allreduce implementation. On a Cray XT5 system, a 6144-process Cheetah Allreduce outperforms the Cray MPI by 145%. The evaluation with an application kernel, Conjugate Gradient solver, shows that the Cheetah reductions speeds up total time to solution by 195%, demonstrating the potential benefits for scientific simulations.
Achieving good scaling for fine-grained communication intensive applications on modern supercomputers remains challenging. In our previous work, we have shown that such an application -- NAMD -- scales well on the full Jaguar XT5 without long-range interactions; Yet, with them, the speedup falters beyond 64K cores. Although the new Gemini interconnect on Cray XK6 has improved network performance, the challenges remain, and are likely to remain for other such networks as well. We analyze communication bottlenecks in NAMD and its CHARM++ runtime, using the Projections performance analysis tool. Based on the analysis, we optimize the runtime, built on the uGNI library for Gemini. We present several techniques to improve the fine-grained communication. Consequently, the performance of running 92224-atom Apoa1 with GPUs on TitanDev is improved by 36%. For 100-million-atom STMV, we improve upon the prior Jaguar XT5 result of 26 ms/step to 13 ms/step using 298,992 cores on Jaguar XK6.
Achieving good scaling for fine-grained communication intensive applications on modern supercomputers remains challenging. In our previous work, we have shown that such an application NAMD scales well on the full Jaguar XT5 without long-range interactions; Yet, with them, the speedup falters beyond 64K cores. Although the new Gemini interconnect on Cray XK6 has improved network performance, the challenges remain, and are likely to remain for other such networks as well. We analyze communication bottlenecks in NAMD and its CHARM++ runtime, using the Projections performance analysis tool. Based on the analysis, we optimize the runtime, built on the uGNI library for Gemini. We present several techniques to improve the fine-grained communication. Consequently, the performance of running 92224-atom Apoa1 with GPUs on TitanDev is improved by 36%. For 100-million-atom STMV, we improve upon the prior Jaguar XT5 result of 26 ms/step to 13 ms/step using 298,992 cores on Jaguar XK6.
Many scientific simulations, using the Message Passing Interface (MPI) programming model, are sensitive to the performance and scalability of reduction collective operations such as MPI Allreduce and MPI Reduce. These operations are the most widely used abstractions to perform mathematical operations over all processes that are part of the simulation. In this work, we propose a hierarchical design to implement the reduction operations on multicore systems. This design aims to improve the efficiency of reductions by 1) tailoring the algorithms and customizing the implementations for various communication mechanisms in the system 2) providing the ability to configure the depth of hierarchy to match the system architecture, and 3) providing the ability to independently progress each of this hierarchy. Using this design, we implement MPI Allreduce and MPI Reduce operations (and its nonblocking variants MPI Iallreduce and MPI Ireduce) for all message sizes, and evaluate on multiple architectures including InfiniBand and Cray XT5. We leverage and enhance our existing infrastructure, Cheetah, which is a framework for implementing hierarchical collective operations to implement these reductions. The experimental results show that the Cheetah reduction operations outperform the production-grade MPI implementations such as Open MPI default, Cray MPI, and MVAPICH2, demonstrating its efficiency, flexibility and portability. On Infini- Band systems, with a microbenchmark, a 512-process Cheetah nonblocking Allreduce and Reduce achieves a speedup of 23x and 10x, respectively, compared to the default Open MPI reductions. The blocking variants of the reduction operations also show similar performance benefits. A 512-process nonblocking Cheetah Allreduce achieves a speedup of 3x, compared to the default MVAPICH2 Allreduce implementation. On a Cray XT5 system, a 6144-process Cheetah Allreduce outperforms the Cray MPI by 145%. The evaluation with an application kernel, Conjugate Gradient solver, shows that the Cheetah reductions speeds up total time to solution by 195%, demonstrating the potential benefits for scientific simulations.
Managing the large volumes of data produced by emerging scientific and engineering simulations running on leadership-class resources has become a critical challenge. The data have to be extracted off the computing nodes and transported to consumer nodes so that it can be processed, analyzed, visualized, archived, and so on. Several recent research efforts have addressed data-related challenges at different levels. One attractive approach is to offload expensive input/output operations to a smaller set of dedicated computing nodes known as a staging area. However, even using this approach, the data still have to be moved from the staging area to consumer nodes for processing, which continues to be a bottleneck. In this paper, we investigate an alternate approach, namely moving the data-processing code to the staging area instead of moving the data to the data-processing code. Specifically, we describe the ActiveSpaces framework, which provides (1) programming support for defining the data-processing routines to be downloaded to the staging area and (2) runtime mechanisms for transporting codes associated with these routines to the staging area, executing the routines on the nodes that are part of the staging area, and returning the results. We also present an experimental performance evaluation of ActiveSpaces using applications running on the Cray XT5 at Oak Ridge National Laboratory. Finally, we use a coupled fusion application workflow to explore the trade-offs between transporting data and transporting the code required for data processing during coupling, and we characterize sweet spots for each option.
Over the past decade, the trajectory to the petascale has been built on increased complexity and scale of the underlying parallel architectures. Meanwhile, software developers have struggled to provide tools that maintain the productivity of computational science teams using these new systems. In this regard, Global Address Space (GAS) programming models provide a straightforward and easy to use addressing model, which can lead to improved productivity. However, the scalability of GAS depends directly on the design and implementation of the runtime system on the target petascale distributed-memory architecture. In this paper, we describe the design, implementation, and optimization of the Aggregate Remote Memory Copy Interface (ARMCI) runtime library on the Cray XT5 2.3 PetaFLOPs computer at Oak Ridge National Laboratory. We optimized our implementation with the flow intimation technique that we have introduced in this paper. Our optimized ARMCI implementation improves scalability of both the Global Arrays programming model and a real-world chemistry application—NWChem—from small jobs up through 180,000 cores.
Massively parallel computers now permit the molecular dynamics (MD) simulation of multi-million atom systems on time scales up to the microsecond. However, the subsequent analysis of the resulting simulation trajectories has now become a high performance computing problem in itself. Here, we present software for calculating X-ray and neutron scattering intensities from MD simulation data that scales well on massively parallel supercomputers. The calculation and data staging schemes used maximize the degree of parallelism and minimize the IO bandwidth requirements. The strong scaling tested on the Jaguar Petaflop Cray XT5 at Oak Ridge National Laboratory exhibits virtually linear scaling up to 7000 cores for most benchmark systems. Since both MPI and thread parallelism is supported, the software is flexible enough to cover scaling demands for different types of scattering calculations. The result is a high performance tool capable of unifying large-scale supercomputing and a wide variety of neutron/synchrotron technology.
Emerging scientific application workflows are composed of heterogeneous coupled component applications that simulate different aspects of the physical phenomena being modeled, and that interact and exchange significant volumes of data at runtime. With the increasing performance gap between on-chip data sharing and off-chip data transfers in current systems based on multicore processors, moving large volumes of data using communication network fabric can significantly impact performance. As a result, minimizing the amount of inter-application data exchanges that are across compute nodes and use the network is critical to achieving overall application performance and system efficiency. In this paper, we investigate the in-situ execution of the coupled components of a scientific application workflow so as to maximize on-chip exchange of data. Specifically, we present a distributed data sharing and task execution framework that (1) employs data-centric task placement to map computations from the coupled applications onto processor cores so that a large portion of the data exchanges can be performed using the intra-node shared memory, (2) provides a shared space programming abstraction that supplements existing parallel programming models (e.g., message passing) with specialized one-sided asynchronous data access operators and can be used to express coordination and data exchanges between the coupled components. We also present the implementation of the framework and its experimental evaluation on the Jaguar Cray XT5 at Oak Ridge National Laboratory.
The logical structure of a forest of octrees can be used to create scalable algorithms for parallel adaptive mesh refinement (AMR), which has recently been demonstrated for several petascale applications. Among various frequently used octree-based mesh operations, including refinement, coarsening, partitioning, and enumerating nodes, ensuring a 2:1 size balance between neighboring elements has historically been the most expensive in terms of CPU time and communication volume. The 2:1 balance operation is thus a primary target to optimize. One important component of a parallel balance algorithm is the ability to determine whether any two given octants have a consistent distance/size relation. Based on new logical concepts we propose fast algorithms for making this decision for all types of 2:1 balance conditions in 2D and 3D. Since we are able to achieve this without constructing any parent nodes in the tree that would otherwise need to be sorted and communicated, we can significantly reduce the required memory and communication volume. In addition, we propose a lightweight collective algorithm for reversing the asymmetric communication pattern induced by non-local octant interactions. We have implemented our improvements as part of the opensource “p4est” software. Benchmarking this code with both synthetic and simulation-driven adapted meshes we are able to demonstrate much reduced runtime and excellent weak and strong scalability. On our largest benchmark problem with 5.13 × 10 11 octants the new 2:1 balance algorithm executes in less than 8 seconds on 112,128 CPU cores of the Jaguar Cray XT5 supercomputer.
Fourier and related transforms are a family of algorithms widely employed in diverse areas of computational science, notoriously difficult to scale on high-performance parallel computers with a large number of processing elements (cores). This paper introduces a popular software package called P3DFFT which implements fast Fourier transforms (FFTs) in three dimensions in a highly efficient and scalable way. It overcomes a well-known scalability bottleneck of three-dimensional (3D) FFT implementations by using two-dimensional domain decomposition. Designed for portable performance, P3DFFT achieves excellent timings for a number of systems and problem sizes. On a Cray XT5 system P3DFFT attains 45% efficiency in weak scaling from 128 to 65,536 computational cores. Library features include Fourier and Chebyshev transforms, Fortran and C interfaces, in- and out-of-place transforms, uneven data grids, and single and double precision. P3DFFT is available as open source at http://code.google.com/p/p3dfft/. This paper discusses P3DFFT implementation and performance in a way that helps guide the user in making optimal choices for parameters of their runs. Read More: https://epubs.siam.org/doi/10.1137/11082748X
Radio signal strength estimation is essential in many applications, including the design of military radio communications and industrial wireless installations. For scenarios with large or richly- featured geographical volumes, parallel processing is required to meet the memory and computa- tion time demands. Here, we present a scalable and efficient parallel execution of the sequential model for radio signal propagation recently developed by Nutaro et al. Starting with that model, we (a) provide a vector-based reformulation that has significantly lower computational overhead for event handling, (b) develop a parallel decomposition approach that is amenable to reversibility with minimal computational overheads, (c) present a framework for transparently mapping the conservative time-stepped model into an optimistic parallel discrete event execution, (d) present a new reversible method, along with its analysis and implementation, for inverting the vector-based event model to be executed in an optimistic parallel style of execution, and (e) present performance results from implementation on Cray XT platforms. We demonstrate scalability, with the largest runs tested on up to 127,500 cores of a Cray XT5, enabling simulation of larger scenarios and with faster execution than reported before on the radio propagation model. This also represents the first successful demonstration of the ability to efficiently map a conservative time-stepped model to an optimistic discrete-event execution.
We present a multi-dimensional, atomistic, quantum transport simulation approach to investigate the performances of realistic nanoscale transistors for various geometries and material systems. The central computation consists in solving the Schrödinger equation with open boundary conditions several thousand times. To do that, a Wave Function approach is used since it can be relatively easily parallelized. To further improve the computational efficiency, three additional levels of parallelization are identified, the work load is optimally balanced between the CPUs, computational interleaving is applied where possible, and a mixed precision scheme is introduced. Using two different device types, a high electron mobility and a band-to-band tunneling transistor, sustained performances up to 1.28 PFlop/s in double precision (55% of the peak performance) and 1.44 PFlop/s in mixed precision are reached on 221,400 cores on the CRAY-XT5 Jaguar at Oak Ridge National Lab.
The development of reliable tools for excited-state simulations is emerging as an extremely powerful computational chemistry tool for understanding complex processes in the broad class of light harvesting systems and optoelectronic devices. Over the last years we have been developing equation of motion coupled cluster (EOMCC) methods capable of tackling these problems. In this paper we discuss the parallel performance of EOMCC codes which provide accurate description of the excited-state correlation effects. Two aspects are discuss in details: (1) a new algorithm for the iterative EOMCC methods based on the novel task scheduling algorithms, and (2) parallel algorithms for the non-iterative methods describing the effect of triply excited configurations. We demonstrate that the most computationally intensive non-iterative part can take advantage of 210,000 cores of the Cray XT5 system at OLCF. In particular, we demonstrate the importance of non-iterative many-body methods for achieving experimental level of accuracy for several porphyrin-based system.