Challenges for High-Performance Networking for Exascale Computing
Abstract not provided.
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.
Abstract not provided.
Abstract not provided.
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.
An approach to analyzing CFD knowledge-based systems is proposed which is based, in part, on the concept of knowledge-level analysis. Consideration is given to the expert cooling fan design system, the PAN AIR knowledge system, grid adaptation, and expert zonal grid generation. These AI/CFD systems demonstrate that current AI technology can be successfully applied to well-formulated problems that are solved by means of classification or selection of preenumerated solutions.
Explore the source record for details and available documents.
Two years ago, NASA was on the verge of dramatically increasing its HEC capability and capacity. With the 10,240-processor supercomputer, Columbia, now in production for 18 months, HEC has an even greater impact within the Agency and extending to partner institutions. Advanced science and engineering simulations in space exploration, shuttle operations, Earth sciences, and fundamental aeronautics research are occurring on Columbia, demonstrating its ability to accelerate NASA s exploration vision. This talk describes how the integrated production environment fostered at the NASA Advanced Supercomputing (NAS) facility at Ames Research Center is accelerating scientific discovery, achieving parametric analyses of multiple scenarios, and enhancing safety for NASA missions. We focus on Columbia s impact on two key engineering and science disciplines: Aerospace, and Climate. We also discuss future mission challenges and plans for NASA s next-generation HEC environment.
Abstract not provided.
Abstract not provided.
Sparse tensor contraction sequence has been widely employed in many fields, such as chemistry and physics. However, how to efficiently implement the sequence faces multiple challenges, such as redundant computations and memory operations, massive memory consumption, and inefficient utilization of hardware. To address the above challenges, we introduce Athena, a high-performance framework for SpTC sequences. Athena introduces new data structures, leverages emerging Optane-based heterogeneous memory (HM) architecture, and stage parallelism. In particular, Athena introduces shared hash table-represented sparse accumulator to eliminate unnecessary input processing and data migration; Athena uses a novel data-semantic guided dynamic migration solution to make the best use of the Optane-based HM for high performance; Athena also co-runs execution phases with different characteristics to enable high hardware utilization. Evaluating with 12 datasets, we show that Athena brings 327-7362× speedup over the state-of-the-art SpTC algorithm. With the dynamic data placement guided by data semantics, Athena brings performance improvement on Optane-based HM over a state-of-the-art software-based data management solution, a hardware-based data management solution, and PMM-only by 1.58×, 1.82×, and 2.34× respectively.
While many optimization and control methods for stochastic processes require gradient information from the process of interest, obtaining gradient information from experiments is prohibitively expensive and time-consuming. As a result, such information is often obtained from stochastic process simulations. Computing gradients efficiently and accurately from stochastic simulations is challenging, especially for simulations involving computationally expensive models with significant inherent noise. In this work, we analyze and characterize the applicability of two gradient estimation methods for kinetic Monte Carlo simulations: finite differencing and likelihood ratio. We developed a systematic method for choosing an optimal perturbation size for finite differencing and discuss, for both methods, important implementation issues such as scaling with respect to the number of elements in the gradient vector. Through a series of numerical experiments, the methods were compared across different time and size regimes to characterize the precision and accuracy associated with each method. We determined that the likelihood ratio method is appropriate for estimating gradients at short (transient) times or for systems with small population sizes, whereas finite differencing is better-suited for gradient estimation at long times (steady state) or for systems with large population sizes.
Multi-objective transmission switching (MO-TS) problems involve the strategic reconfiguration of network topology to simultaneously optimize multiple objectives. As the system scale increases, finding feasible solutions becomes increasingly challenging due to the problem's nonlinearity and high computational complexity. To address these challenges, this paper proposes a two-stage quantum reinforcement learning method that leverages potential quantum advantages for MO-TS. In the first stage, candidate switching lines are identified using a graph-theoretical approach to reduce the problem's dimensionality. The second stage introduces a quantum-classical reinforcement learning framework, where a learnable measurement-based CNN-ResVQC architecture is developed to effectively reduce the input dimension for quantum processing, mitigate vanishing gradients, and enhance trainability while improving the quantum circuit's flexibility in modeling complex decision policies for MO-TS. Numerical studies on IEEE 14-bus, 57-bus, and 118-bus systems demonstrate that the proposed algorithm achieves superior training stability and faster convergence with approximately 1% of the network parameters required by classical algorithms, highlighting its effectiveness, efficiency, and scalability. Furthermore, the practicality is validated through its stable convergence under three common quantum noise channels.
Whole-cell modeling is “the ultimate goal” of computational systems biology and “a grand challenge for 21st century”. These complex, highly detailed models account for the activity of every molecule in a cell and serve as comprehensive knowledgebases for the modeled system. Their scope and utility far surpass those of other systems models. In fact, whole-cell models (WCMs) are an amalgam of several types of “system” models. The models are simulated using a hybrid modeling method where the appropriate mathematical methods for each biological process are used to simulate their behavior. Given the complexity of the models, the process of developing and curating these models is labor-intensive and to date only a handful of these models have been developed. While whole-cell models provide valuable and novel biological insights, and to date have identified some novel biological phenomena, their most important contribution has been to highlight the discrepancy between available data and observations that are used for the parametrization and validation of complex biological models. Another realization has been that current whole-cell modeling simulators are slow and to run models that mimic more complex (e.g., multi-cellular) biosystems, those need to be executed in an accelerated fashion on high-performance computing platforms. In this manuscript, we review the progress of whole-cell modeling to date and discuss some of the ways that they can be improved.
Numerical solutions for fluid flow problems are challenging and have been focus of Computational Fluid Dynamics (CFD) research for past several decades. The advent of quantum computing promises exponential speedup in comparison to existing classical methods and alleviate computational constraints posed by CFD problems. Although solutions for most problems of interest in fluid dynamics using quantum computing are distant, recent advances in algorithms, software and hardware provide a path towards realizing this goal. Quantum linear solver algorithms (QLSA) such as Harrow–Hassidim–Lloyd (HHL) and Variational Quantum Linear Solver (VQLS) have been successfully implemented to solve for canonical problems such as Hele-Shaw flow. However, these algorithms still suffer to scale and address problems with ill-conditioned Jacobians. In the current paper, we alleviate these restrictions with a new quantum solver based on Singular Value Decomposition (SVD) and simulate flow past a 2D cylinder. The fidelity of the SVD based quantum solver in predicting the flow past 2D cylinder is computed along with an assessment of errors. Classical and quantum solutions for the flow are compared for different resolutions. Finally, we discuss variation in the solutions based on number of shots used.
Montage is an Earth Science Technology Office (ESTO) Computational Technologies (CT) Round III Grand Challenge investigation to deploy a portable, compute-intensive, custom astronomical image mosaicking service for the National Virtual Observatory (NVO). Although Montage is developing a compute- and data-intensive service for the astronomy community, we are also helping to address a problem that spans both Earth and Space science, namely how to efficiently access and process multi-terabyte, distributed datasets. In both communities, the datasets are massive, and are stored in distributed archives that are, in most cases, remote from the available Computational resources. Therefore, state of the art computational grid technologies are a key element of the Montage portal architecture. This paper describes the aspects of the Montage design that are applicable to both the Earth and Space science communities.
Julia is a relatively new computer language that aims to reduce the challenge for mathmodelers to develop fast computer tools and simulations. It potentially combines the ease-of-coding feature of scripting languages (like Python) with the performance of compiled languages (like C++). A key question for Julia application to the simulation domain is, “Can Julia, with its obvious coding simplicity, provide runtime speeds comparable to conventional compiled languages for flight simulation?” A unique combination of existing elements can be employed to address the previous question: Extensively documented object-oriented simulation architecture, Industry standard rocket flight simulation, Separate versions (C++, Java, and Python) already benchmarked.
Design of data structures for high performance computing (HPC) is one of the principal challenges facing researchers looking to utilize heterogeneous computing machinery. Heterogeneous systems derive cost, power, and speed efficiency by being composed of the appropriate hardware for the task. Yet, each type of processor requires a specific organization of the application state in order to achieve peak performance. Discovering this and refactoring the code can be a challenging and time-consuming task for the researcher, as the data structures and the computational model must be co-designed. We present a methodology that uses Python as the environment for which to explore tradeoffs in both the data structure design as well as the code executing on the computation accelerator. Our method enables multi-dimensional arrays to be used effectively in any target environment. We have chosen to focus on OpenMP and CUDA environments, thus exploring the development of optimized kernels for the two most common classes of computing hardware available today: multi-core CPU and GPU. Python s large palette of file and network access routines, its associative indexing syntax and support for common HPC environments makes it relevant for diverse hardware ranging from laptops through computing clusters to the highest performance supercomputers. Our work enables researchers to accelerate the development of their codes on the computing hardware of their choice.
The ability to solve our nation’s most challenging problems—whether it’s cleaning up the environment, finding alternative forms of energy or improving public health and safety—requires new scientific discoveries. High performance experimental and computational technologies from the past decade are helping to accelerate these scientific discoveries, but they introduce challenges of their own. The vastly increasing volumes and complexities of experimental and computational data pose significant challenges to traditional high-performance computing (HPC) platforms as terabytes to petabytes of data must be processed and analyzed. And the growing complexity of computer models that incorporate dynamic multiscale and multiphysics phenomena place enormous demands on high-performance computer architectures. Just as these new challenges are arising, the computer architecture world is experiencing a renaissance of innovation. The continuing march of Moore’s law has provided the opportunity to put more functionality on a chip, enabling the achievement of performance in new ways. Power limitations, however, will severely limit future growth in clock rates. The challenge will be to obtain greater utilization via some form of on-chip parallelism, but the complexities of emerging applications will require significant innovation in high-performance architectures. The Cray XMT, the successor to the Tera/Cray MTA, provides an alternative platform for addressing computations that stymie current HPC systems, holding the potential to substantially accelerate data analysis and predictive analytics for many complex challenges in energy, national security and fundamental science that traditional computing cannot do.