James A. Ang

Abstract machine models and proxy architectures for exascale computing

To achieve exascale computing, fundamental hardware architectures must change. This will significantly impact scientific applications that run on current high performance computing (HPC) systems, many of which codify years of scientific domain knowledge and refinements for contemporary computer systems. To adapt to exascale architectures, developers must be able to reason about new hardware and determine what programming models and algorithms will provide the best blend of performance and energy efficiency in the future. An abstract machine model is designed to expose to the application developers and system software only the aspects of the machine that are important or relevant to performance and code structure. These models are intended as communication aids between application developers and hardware architects during the co-design process. A proxy architecture is a parameterized version of an abstract machine model, with parameters added to elucidate potential speeds and capacities of key hardware components. These more detailed architectural models enable discussion among the developers of analytic models and simulators and computer hardware architects and they allow for application performance analysis, system software development, and hardware optimization opportunities. In this paper, we present a set of abstract machine models and show how they might be used to help software developers prepare for exascale. We then apply parameters to one of these models to demonstrate how a proxy architecture can enable a more concrete exploration of how well application codes map onto future architectures.

Railgun performance with a two-stage light-gas gun injector

Results obtained with the HELEOS (hypervelocity experimental launcher for equation of state) railgun, which uses a two-stage light-gas gun (2SLGG) as an injector, are presented. The high-velocity 2SLGG injector preaccelerates projectiles up to approximately 7 km/s. The high injection velocity reduces the exposure duration of the railgun barrel to the passing high temperature plasma armature, thereby reducing the ablation and subsequent armature growth. The 2SLGG also provides a column of cool, high-pressure hydrogen gas to insulate the rails behind the projectile, thereby eliminating restrike. A means to form an armature behind the injected projectile has been developed. In preliminary tests, the third-stage railgun has successfully increased the projectile velocity by 1.35 km/s. Extensive diagnostics have been used to determine the behavior of the armature and track the launchers performance. Insome cases, velocity increases in the railgun section have been achieved, which are in close agreement with theoretical predictions, whereas in other experiments deviations from theoretical have been observed. The reasons for and implications of these results are addressed. Recent tests are reported. >

DOE Advanced Scientific Computing Advisory Subcommittee (ASCAC) Report: Top Ten Exascale Research Challenges

Exascale computing systems are essential for the scientific fields that will transform the 21st century global economy, including energy, biotechnology, nanotechnology, and materials science. Progress in these fields is predicated on the ability to perform advanced scientific and engineering simulations, and analyze the deluge of data. On July 29, 2013, ASCAC was charged by Patricia Dehmer, the Acting Director of the Office of Science, to assemble a subcommittee to provide advice on exascale computing. This subcommittee was directed to return a list of no more than ten technical approaches (hardware and software) that will enable the development of a system that achieves the Departments goals for exascale computing. Numerous reports over the past few years have documented the technical challenges and the non¬-viability of simply scaling existing computer designs to reach exascale. The technical challenges revolve around energy consumption, memory performance, resilience, extreme concurrency, and big data. Drawing from these reports and more recent experience, this ASCAC subcommittee has identified the top ten computing technology advancements that are critical to making a capable, economically viable, exascale system.

Pulsed holography for hypervelocity impact diagnostics

Pulsed holography is being developed to meet two principal objectives. The first objective is to quantify the three dimensional characteristics of hypervelocity impact events, and the second is to provide a diagnostic with the ability to capture high fidelity information for the validation of sophisticated three-dimensional hydrocodes. The holographic system uses a Q-switched, seeded, frequency-doubled Nd-YAG laser which produces 5 ns, 750 mJ, coherent pulses at 532 nm. Holographic images have been captured of the back-surface debris bubble from 4 km/s perforating impacts and crater ejecta from 2 km/s non-perforating impacts. A prototype holographic reconstruction and image analysis system has been assembled that provides the ability to measure the structure and individual particles produced in a hypervelocity impact event. The estimated image resolution of this system is 10 to 20 {mu}m; however, this level of performance has not yet been demonstrated.

Hypervelocity projectile design and fabrication

The authors present the design and fabrication techniques that have been used to increase the strength of the projectiles used in the STARFIRE Project. In addition, various diagnostics that have been used to guide the projectile development and monitor projectile integrity are reviewed. Stronger projectile designs have been fabricated with a concurrent reduction in precision machining time. The improvements in projectile strength have allowed increases in reliable projectile injection velocities from 6 km/s to 7 km/s. In addition, the molded projectile fabrication technique offers additional flexibility for the fabrication of complex projectile designs. One of these advanced projectile concepts which uses a base sealing design offers the potential for further increases in injection velocity. >

HYPERVELOCITY IMPACT JET FORMATION

The hypervelocity impact of a particle on a surface generates a jet of shocked material which is thrown from the impact site. A simple analytic model has been developed to obtain expressions for the evolution of this jet of ejecta. The analysis is based on applying the conservation equations of mass and momentum to the problem of a normal impact of a sphere against a semi-infinite flat target. Expressions are developed for the evolution of the jet velocity, jet release point and the locus of points which describe the ejecta envelope. These analytical ejecta profiles are compared with high speed photographs of impact jet evolution.

High Performance Computing Co-Design Strategies

The MEMSYS Call for Papers contains this passage: Many of the problems we see in the memory system are cross-disciplinary in nature -- their solution would likely require work at all levels, from applications to circuits. Thus, while the scope of the problem is memory, the scope of the solutions will be much wider. The Department of Energys (DOE) high performance computing (HPC) community is thinking about how to define, support and execute work at all levels for the development of future supercomputers to run our portfolio of mission applications. Borrowing a concept from embedded computing, the DOE HPC community is calling our work at all levels co-design [1]. Co-design for embedded computing is focused on hardware/software partitioning of activities to execute a well-defined task within specific constraints. Co-design for general-purpose HPC has many dimensions for both the work to be performed and the constraints, e.g. hardware designs, runtime software, applications and algorithms. The subject of this extended abstract is a description of two alternative DOE HPC co-design strategies. While DOE co-design efforts include more than the memory system, as noted in the MEMSYS call, the memory system impacts applications, circuits and all levels between.

The impact of acceleration on barrel/launch package design

The impact of launch acceleration on the design of electromagnetic launcher barrels and on the design of associated launch packages is discussed. This is of particular interest because launch package size and mass directly affect the overall armament system size and mass. A common design approach is to use as the peak launch acceleration the maximum acceleration which the projectile can be designed to withstand. While this approach will minimize barrel length, it may also yield an excessively large overall system size and mass, especially for the long, slender projectile configurations which are desired for high aero-thermal and terminal ballistics performance. An alternate design approach which balances the goals of reducing barrel length ad reducing launch package mass is described. Results illustrate the benefits of this balanced design approach on overall armament system size and mass. >