Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel optimization”

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 433 records · Page 24

Simulation-based Performance Analysis and Tuning for a Two-level Directly Connected System

Hardware and software co-design is becoming increasingly important due to complexities in supercomputing architectures. Simulating applications before there is access to the real hardware can assist machine architects in making better design decisions that can optimize application performance. At the same time, the application and runtime can be optimized and tuned beforehand. BigSim is a simulation-based performance prediction framework designed for these purposes. It can be used to perform packet-level network simulations of parallel applications using existing parallel machines. In this paper, we demonstrate the utility of BigSim in analyzing and optimizing parallel application performance for future systems based on the PERCS network. We present simulation studies using benchmarks and real applications expected to run on future supercomputers. Future petascale systems will have more than 100,000 cores, and we present simulations at that scale.

97 MATHEMATICS AND COMPUTING↗

SCORPIO: A Scalable Two-Phase Parallel I/O Library With Application To A Large Scale Subsurface Simulator

Inefficient parallel I/O is known to be a major bottleneck among scientific applications employed on supercomputers as the number of processor cores grows into the thousands. Our prior experience indicated that parallel I/O libraries such as HDF5 that rely on MPI-IO do not scale well beyond 10K processor cores, especially on parallel file systems (like Lustre) with single point of resource contention. Our previous optimization efforts for a massively parallel multi-phase and multi-component subsurface simulator (PFLOTRAN) led to a two-phase I/O approach at the application level where a set of designated processes participate in the I/O process by splitting the I/O operation into a communication phase and a disk I/O phase. The designated I/O processes are created by splitting the MPI global communicator into multiple sub-communicators. The root process in each sub-communicator is responsible for performing the I/O operations for the entire group and then distributing the data to rest of the group. This approach resulted in over 25X speedup in HDF I/O read performance and 3X speedup in write performance for PFLOTRAN at over 100K processor cores on the ORNL Jaguar supercomputer. This research describes the design and development of a general purpose parallel I/O library, SCORPIO (SCalable block-ORiented Parallel I/O) that incorporates our optimized two-phase I/O approach. The library provides a simplified higher level abstraction to the user, sitting atop existing parallel I/O libraries (such as HDF5) and implements optimized I/O access patterns that can scale on larger number of processors. Performance results with standard benchmark problems and PFLOTRAN indicate that our library is able to maintain the same speedups as before with the added flexibility of being applicable to a wider range of I/O intensive applications.

High Performance Computing↗

Optimizing Irregular Applications for Energy and Performance on the Tilera Many-core Architecture

Optimizing applications simultaneously for energy and performance is a complex problem. High performance, parallel, irregular applications are notoriously hard to optimize due to their data-dependent memory accesses, lack of structured locality and complex data structures and code patterns. Irregular kernels are growing in importance in applications such as machine learning, graph analytics and combinatorial scientific computing. Performance- and energy-efficient implementation of these kernels on modern, energy efficient, multicore and many-core platforms is therefore an important and challenging problem. We present results from optimizing two irregular applications { the Louvain method for community detection (Grappolo), and high-performance conjugate gradient (HPCCG) { on the Tilera many-core system. We have significantly extended MIT's OpenTuner auto-tuning framework to conduct a detailed study of platform-independent and platform-specific optimizations to improve performance as well as reduce total energy consumption. We explore the optimization design space along three dimensions: memory layout schemes, compiler-based code transformations, and optimization of parallel loop schedules. Using auto-tuning, we demonstrate whole node energy savings of up to 41% relative to a baseline instantiation, and up to 31% relative to manually optimized variants.

irregular applications, energy opttimization, many↗

Scheduling error correction operations for a quantum computer.

In a (future) quantum computer a single logical quantum bit (qubit) will be made of multiple physical qubits. These extra physical qubits implement mandatory extensive error checking. The efficiency of error correction will fundamentally influence the performance of a future quantum computer, both in latency/speed and in error threshold (the worst error tolerated for an individual gate). Executing this quantum error correction requires scheduling the individual operations subject to architectural constraints. Since our last talk on this subject, a team of researchers at Sandia National Labortories has designed a logical qubit architecture that considers all relevant architectural issues including layout, the effects of supporting classical electronics, and the types of gates that the underlying physical qubit implementation supports most naturally. This is a two-dimensional system where 2-qubit operations occur locally, so there is no need to calculate more complex qubit/information transportation. Using integer programming, we found a schedule of qubit operations that obeys the hardware constraints, implements the local-check code in the native gate set, and minimizes qubit idle periods. Even with an optimal schedule, however, parallel Monte Carlo simulation shows that there is no finite error probability for the native gates such that the error-correction system would be benecial. However, by adding dynamic decoupling, a series of timed pulses that can reverse some errors, we found that there may be a threshold. Thus finding optimal schedules for increasingly-refined scheduling problems has proven critical for the overall design of the logical qubit system. We describe the evolving scheduling problems and the ideas behind the integer programming-based solution methods. This talk assumes no prior knowledge of quantum computing.

99 GENERAL AND MISCELLANEOUS↗

A Domain Decomposition Parallelization of the Fast Marching Method

In this paper, the first domain decomposition parallelization of the Fast Marching Method for level sets has been presented. Parallel speedup has been demonstrated in both the optimal and non-optimal domain decomposition case. The parallel performance of the proposed method is strongly dependent on load balancing separately the number of nodes on each side of the interface. A load imbalance of nodes on either side of the domain leads to an increase in communication and rollback operations. Furthermore, the amount of inter-domain communication can be reduced by aligning the inter-domain boundaries with the interface normal vectors. In the case of optimal load balancing and aligned inter-domain boundaries, the proposed parallel FMM algorithm is highly efficient, reaching efficiency factors of up to 0.98. Future work will focus on the extension of the proposed parallel algorithm to higher order accuracy. Also, to further enhance parallel performance, the coupling of the domain decomposition parallelization to the G(sub 0)-based parallelization will be investigated.

Herrmann, M.↗

Approximate Weighted Matching On Emerging Manycore and Multithreaded Architectures

Graph matching is a prototypical combinatorial problem with many applications in computer science and scientific computing, but algorithms for computing optimal matchings are challenging to parallelize. Approximate matching algorithms provide an alternate route for parallelization, and in many contexts compute near-optimal matchings for large-scale graphs. We present sharedmemory parallel implementations for computing half-approximate weighted matching on state-of-the-art multicore (Intel Nehalem and AMD Magny-Cours), manycore (Nvidia Tesla and Nvidia Fermi) and massively multithreaded (Cray XMT) platforms. We provide two implementations: the first implementation uses shared work queues, and is suited to all these platforms; the second implementation is based on dataflow principles, and exploits the architectural features of the Cray XMT. Using a carefully chosen dataset that exhibits characteristics from a wide range of real-world applications, we show scalable performance across different platforms. In particular, for one instance of the input, an R-MAT graph (RMAT-G), we show speedups of: about 32 on 48 cores of an AMD Magny-Cours; 7 on 8 cores of Intel Nehalem; 3 on Nvidia Tesla and 10 on Nvidia Fermi relative to one core of Intel Nehalem; and 60 on 128 processors of Cray XMT. We demonstrate good weak and strong scaling for graphs with up to a billion edges using up to 12, 800 threads. Given the breadth of this work, we focus on simplicity and portability of software rather than excessive fine-tuning for each platform. To the best of our knowledge, this is the first such large-scale study of the half-approximate weighted matching problem on shared-memory platforms. Driven by the critical enabling role of combinatorial algorithms such as matching in scientific computing and the emergence of informatics applications, there is a growing demand to support irregular computations on current and future computing platforms. In this context, we evaluate the capability of emerging multithreaded platforms to tolerate latency induced by irregular memory access patterns, and to support fine-grained parallelism via light-weight synchronization mechanisms. By contrasting the architectural features of these platforms against the Cray XMT, which is specifically designed to support irregular memory-intensive applications, we delineate the impact of these choices on performance.

Halappanavar, Mahantesh↗

Optimization of rotor blades for combined structural, performance, and aeroelastic characteristics

The strategies whereby helicopter rotor blades can be optimized for combined structural, inertial, dynamic, aeroelastic, and aerodynamic performance characteristics are outlined. There are three key ingredients in the successful execution of such an interdisciplinary optimization. The first is the definition of a satisfactory performance index that combines all aspects of the problem without too many constraints. The second element is the judicious choice of computationally efficient analysis tools for the various quantitative components in both the cost functional and constraints. The third element is an effective strategy for combining the various disciplines either in parallel or sequential optimizations.

Peters, David A.↗

OpenACC acceleration of the Nek5000 spectral element code

We present a case study of porting NekBone, a skeleton version of the Nek5000 code, to a parallel GPU-accelerated system. Nek5000 is a computational fluid dynamics code based on the spectral element method used for the simulation of incompressible flow. The original NekBone Fortran source code has been used as the base and enhanced by OpenACC directives. The profiling of NekBone provided an assessment of the suitability of the code for GPU systems, and indicated possible kernel optimizations. To port NekBone to GPU systems required little effort and a small number of additional lines of code (approximately one OpenACC directive per 1000 lines of code). The naïve implementation using OpenACC leads to little performance improvement: on a single node, from 16 Gflops obtained with the version without OpenACC, we reached 20 Gflops with the naïve OpenACC implementation. An optimized NekBone version leads to a 43 Gflop performance on a single node. In addition, we ported and optimized NekBone to parallel GPU systems, reaching a parallel efficiency of 79.9% on 1024 GPUs of the Titan XK7 supercomputer at the Oak Ridge National Laboratory.

Computer Science↗

Scalable molecular dynamics on CPU and GPU architectures with NAMD

NAMD is a molecular dynamics program designed for high-performance simulations of very large biological objects on CPU- and GPU-based architectures. NAMD offers scalable performance on petascale parallel supercomputers consisting of hundreds of thousands of cores, as well as on inexpensive commodity clusters commonly found in academic environments. It is written in C++ and leans on Charm++ parallel objects for optimal performance on low-latency architectures. NAMD is a versatile, multipurpose code that gathers state-of-the-art algorithms to carry out simulations in apt thermodynamic ensembles, using the widely popular CHARMM, AMBER, OPLS, and GROMOS biomolecular force fields. Here, we review the main features of NAMD that allow both equilibrium and enhanced-sampling molecular dynamics simulations with numerical efficiency. We describe the underlying concepts utilized by NAMD and their implementation, most notably for handling long-range electrostatics; controlling the temperature, pressure, and pH; applying external potentials on tailored grids; leveraging massively parallel resources in multiple-copy simulations; and hybrid quantum-mechanical/molecular-mechanical descriptions. We detail the variety of options offered by NAMD for enhanced-sampling simulations aimed at determining free-energy differences of either alchemical or geometrical transformations and outline their applicability to specific problems. Last, we discuss the roadmap for the development of NAMD and our current efforts toward achieving optimal performance on GPU-based architectures, for pushing back the limitations that have prevented biologically realistic billion-atom objects to be fruitfully simulated, and for making large-scale simulations less expensive and easier to set up, run, and analyze. NAMD is distributed free of charge with its source code at www.ks.uiuc.edu.

high-performance computing↗

Femtosecond all-optical parallel logic gates based on tunable saturable to reverse saturable absorption in graphene-oxide thin films

A detailed theoretical analysis of ultrafast transition from saturable absorption (SA) to reverse saturable absorption (RSA) has been presented in graphene-oxide thin films with femtosecond laser pulses at 800 nm. Increase in pulse intensity leads to switching from SA to RSA with increased contrast due to two-photon absorption induced excited-state absorption. Theoretical results are in good agreement with reported experimental results. Interestingly, it is also shown that increase in concentration results in RSA to SA transition. The switching has been optimized to design parallel all-optical femtosecond NOT, AND, OR, XOR, and the universal NAND and NOR logic gates.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

High Performance Fortran for Aerospace Applications

This paper focuses on the use of High Performance Fortran (HPF) for important classes of algorithms employed in aerospace applications. HPF is a set of Fortran extensions designed to provide users with a high-level interface for programming data parallel scientific applications, while delegating to the compiler/runtime system the task of generating explicitly parallel message-passing programs. We begin by providing a short overview of the HPF language. This is followed by a detailed discussion of the efficient use of HPF for applications involving multiple structured grids such as multiblock and adaptive mesh refinement (AMR) codes as well as unstructured grid codes. We focus on the data structures and computational structures used in these codes and on the high-level strategies that can be expressed in HPF to optimally exploit the parallelism in these algorithms.

Mehrotra, Piyush↗

Aerodynamic Shape Optimization Using A Combined Distributed/Shared Memory Paradigm

Current parallel computational approaches involve distributed and shared memory paradigms. In the distributed memory paradigm, each processor has its own independent memory. Message passing typically uses a function library such as MPI or PVM. In the shared memory paradigm, such as that used on the SGI Origin 2000 machine, compiler directives are used to instruct the compiler to schedule multiple threads to perform calculations. In this paradigm, it must be assured that processors (threads) do not simultaneously access regions of memory in such away that errors would occur. This paper utilizes the latest version of the SGI MPI function library to combine the two parallelization paradigms to perform aerodynamic shape optimization of a generic wing/body.

Cheung, Samson↗

Parallel processing and expert systems

Whether it be monitoring the thermal subsystem of Space Station Freedom, or controlling the navigation of the autonomous rover on Mars, NASA missions in the 1990s cannot enjoy an increased level of autonomy without the efficient implementation of expert systems. Merely increasing the computational speed of uniprocessors may not be able to guarantee that real-time demands are met for larger systems. Speedup via parallel processing must be pursued alongside the optimization of sequential implementations. Prototypes of parallel expert systems have been built at universities and industrial laboratories in the U.S. and Japan. The state-of-the-art research in progress related to parallel execution of expert systems is surveyed. The survey discusses multiprocessors for expert systems, parallel languages for symbolic computations, and mapping expert systems to multiprocessors. Results to date indicate that the parallelism achieved for these systems is small. The main reasons are (1) the body of knowledge applicable in any given situation and the amount of computation executed by each rule firing are small, (2) dividing the problem solving process into relatively independent partitions is difficult, and (3) implementation decisions that enable expert systems to be incrementally refined hamper compile-time optimization. In order to obtain greater speedups, data parallelism and application parallelism must be exploited.

Lau, Sonie↗

Efficient Machine Learning Approach for Optimizing Scientific Computing Applications on Emerging HPC Architectures

Efficient parallel implementations of scientific applications on multi-core CPUs with accelerators such as GPUs and Xeon Phis is challenging. This requires - exploiting the data parallel architecture of the accelerator along with the vector pipelines of modern x86 CPU architectures, load balancing, and efficient memory transfer between different devices. It is relatively easy to meet these requirements for highly structured scientific applications. In contrast, a number of scientific and engineering applications are unstructured. Getting performance on accelerators for these applications is extremely challenging because many of these applications employ irregular algorithms which exhibit data-dependent control-ow and irregular memory accesses. Furthermore, these applications are often iterative with dependency between steps, and thus making it hard to parallelize across steps. As a result, parallelism in these applications is often limited to a single step. Numerical simulation of charged particles beam dynamics is one such application where the distribution of work and memory access pattern at each time step is irregular. Applications with these properties tend to present significant branch and memory divergence, load imbalance between different processor cores, and poor compute and memory utilization. Prior research on parallelizing such irregular applications have been focused around optimizing the irregular, data-dependent memory accesses and control-ow during a single step of the application independent of the other steps, with the assumption that these patterns are completely unpredictable. We observed that the structure of computation leading to control-ow divergence and irregular memory accesses in one step is similar to that in the next step. It is possible to predict this structure in the current step by observing the computation structure of previous steps. In this dissertation, we present novel machine learning based optimization techniques to address the parallel implementation challenges of such irregular applications on different HPC architectures. In particular, we use supervised learning to predict the computation structure and use it to address the control-ow and memory access irregularities in the parallel implementation of such applications on GPUs, Xeon Phis, and heterogeneous architectures composed of multi-core CPUs with GPUs or Xeon Phis. We use numerical simulation of charged particles beam dynamics simulation as a motivating example throughout the dissertation to present our new approach, though they should be equally applicable to a wide range of irregular applications. The machine learning approach presented here use predictive analytics and forecasting techniques to adaptively model and track the irregular memory access pattern at each time step of the simulation to anticipate the future memory access pattern. Access pattern forecasts can then be used to formulate optimization decisions during application execution which improves the performance of the application at a future time step based on the observations from earlier time steps. In heterogeneous architectures, forecasts can also be used to improve the memory performance and resource utilization of all the processing units to deliver a good aggregate performance. We used these optimization techniques and anticipation strategy to design a cache-aware, memory efficient parallel algorithm to address the irregularities in the parallel implementation of charged particles beam dynamics simulation on different HPC architectures. Experimental result using a diverse mix of HPC architectures shows that our approach in using anticipation strategy is effective in maximizing data reuse, ensuring workload balance, minimizing branch and memory divergence, and in improving resource utilization.

Arumugam, Kamesh↗

Hydrogen Energy Storage Integrated with a Combined Cycle Plant

A project is being developed that will build upon the existing infrastructure and resources at the Intermountain Power Project (IPP) site to provide reliable, dispatchable energy and to support the transmission of renewable energy resources while transitioning to an economical green energy future. The concept study depicted in this report outlines a techno-economic optimization to fulfill the demand for 30% vol hydrogen co-firing in the IPP 840 MW advanced class combined cycle power plant. In an initial step, a site assessment concluded the site has sufficient land available to co-locate a hydrogen production and storage facility. The team evaluated and defined a scalable concept that considered technology characteristics, including input and output models to be used for optimization purposes. The concept for the hydrogen production and storage system integrates multiple technologies, to determine system size and scalable approach, for each of the technologies evaluated, the team defined component and subcomponent sizes, minimum and maximum capacity, modularity, component utility consumption (electric, water), component flexibility and servicing, layout, and technology status, as well as technology alternatives. For hydrogen generation, the project considers Siemens Energy’s Silyzer-300 (S300) technology, a 17.5 MW modular Proton Exchange Membrane (PEM) electrolyzer. For the S300 configuration, the team determined that three S300 arrays, or approximately 1,000 kg/hr, per block would yield a compact block design. This configuration results in a fairly wide and flexible arrangement that fits well into the spaces available at the site. Therefore, the overall design approach is based on multiple identical blocks of 3 arrays to minimize engineering cost and optimize constructability. In parallel, a transmission screening study was conducted to determine any potential transmission constraints from the energy sources that could feed the hydrogen production equipment. The study results show that minimum transmission constraints would be encountered to deliver 400 MW renewable generation from southern California, or south-central Wyoming. At last, the techno-economic analysis concluded that a scenario that uses solar and wind power yields the lowest levelized cost of hydrogen (LCOH 2 ) production and the lowest cost per tonne of CO 2 reduced. In this optimized scenario, the hydrogen production plant was determined as 6,201 kg/hr and the hydrogen storage (underground cavern) was determined as 4,600 tonnes. The resulting capacity factor for the hydrogen production plant was 66.33% with 8,745 operating hours in one year. This techno-economic analysis provided various options for integrating hydrogen storage at the Intermountain Power Plant site to co-fire the CCPP units. The results provide insightful data about the magnitude of capacity needed and the economics of producing hydrogen and reducing CO 2 emissions.

08 HYDROGEN↗

Locality-Driven Dynamic GPU Cache Bypassing

This paper presents novel cache optimizations for massively parallel, throughput-oriented architectures like GPUs. Based on the reuse characteristics of GPU workloads, we propose a design that integrates such efficient locality filtering capability into the decoupled tag store of the existing L1 D-cache through simple and cost-effective hardware extensions.

architecture optimization↗

Identifying Redundant Flow Limits on Parallel Lines

Many power system optimization problems constrain line flows with limits specified in terms of the magnitudes of apparent power or current flows. The set of line-flow constraints may have redundancies (i.e., the feasible space may be unchanged upon removal of a subset of the line-flow constraints), which unnecessarily complicate optimization problems. This letter describes an algorithm for identifying redundant line-flow constraints corresponding to certain parallel lines. After formulating the constraints as ellipsoids in the voltage variables, redundancies are detected from the absence of intersections between pairs of ellipsoids corresponding to parallel lines. This algorithm is demonstrated using several large test cases.

Molzahn, Daniel K. (ORCID:0000000305835376)↗

Aligning parallel arrays to reduce communication

Axis and stride alignment is an important optimization in compiling data-parallel programs for distributed-memory machines. We previously developed an optimal algorithm for aligning array expressions. Here, we examine alignment for more general program graphs. We show that optimal alignment is NP-complete in this setting, so we study heuristic methods. This paper makes two contributions. First, we show how local graph transformations can reduce the size of the problem significantly without changing the best solution. This allows more complex and effective heuristics to be used. Second, we give a heuristic that can explore the space of possible solutions in a number of ways. We show that some of these strategies can give better solutions than a simple greedy approach proposed earlier. Our algorithms have been implemented; we present experimental results showing their effect on the performance of some example programs running on the CM-5.

Sheffler, Thomas J.↗