Publications

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Co-design has been identified as a key strategy for achieving Exascale computing in this decade. This paper describes the need for co-design in High Performance Computing related research in embedded computing the development of hardware/software co-simulation methods.

Achieving the next three orders of magnitude performance increase to move from petascale to exascale computing will require a significant advancements in several fundamental areas. Recent studies have outlined many of the challenges in hardware and software that will be needed. In this paper, we examine these challenges with respect to high-performance networking. We describe the repercussions of anticipated changes to computing and networking hardware and discuss the impact that alternative parallel programming models will have on the network software stack. We also present some ideas on possible approaches that address some of these challenges.

Abstract not provided.

Los Alamos and Sandia National Laboratories have formed a new high performance computing center, the Alliance for Computing at the Extreme Scale (ACES). The two labs will jointly architect, develop, procure and operate capability systems for DOE's Advanced Simulation and Computing Program. This presentation will discuss a petascale production capability system, Cielo, that will be deployed in late 2010, and a new partnership with Cray on advanced interconnect technologies.

Abstract not provided.

There is considerable interest in achieving a 1000 fold increase in supercomputing power in the next decade, but the challenges are formidable. In this paper, the authors discuss some of the driving science and security applications that require Exascale computing (a million, trillion operations per second). Key architectural challenges include power, memory, interconnection networks and resilience. The paper summarizes ongoing research aimed at overcoming these hurdles. Topics of interest are architecture aware and scalable algorithms, system simulation, 3D integration, new approaches to system-directed resilience and new benchmarks. Although significant progress is being made, a broader international program is needed.

Data mining and machine learning techniques can be applied to computer system design to aid in optimizing design decisions, improving system runtime performance. Data mining techniques have been investigated in the context of branch prediction. Specifically, a comparison of traditional branch predictor performance has been made to data mining algorithms. Additionally, the possiblity of whether additional features available within the architectural state might serve to further improve branch prediction has been evaluated. Results show that data mining techniques indicate potential for improved branch prediction, especially when register file contents are included as a feature set.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Field programmable gate arrays (FPGAs) have been used as alternative computational de-vices for over a decade; however, they have not been used for traditional scientific com-puting due to their perceived lack of floating-point performance. In recent years, there hasbeen a surge of interest in alternatives to traditional microprocessors for high performancecomputing. Sandia National Labs began two projects to determine whether FPGAs wouldbe a suitable alternative to microprocessors for high performance scientific computing and,if so, how they should be integrated into the system. We present results that indicate thatFPGAs could have a significant impact on future systems. FPGAs have thepotentialtohave order of magnitude levels of performance wins on several key algorithms; however,there are serious questions as to whether the system integration challenge can be met. Fur-thermore, there remain challenges in FPGA programming and system level reliability whenusing FPGA devices.4 AcknowledgmentArun Rodrigues provided valuable support and assistance in the use of the Structural Sim-ulation Toolkit within an FPGA context. Curtis Janssen and Steve Plimpton provided valu-able insights into the workings of two Sandia applications (MPQC and LAMMPS, respec-tively).5

Abstract not provided.

Advances in FPGA technology have led to dramatic improvements in double precision floating-point performance. Modern FPGAs boast several GigaFLOPs of raw computing power. Unfortunately, this computing power is distributed across 30 floating-point units with over 10 cycles of latency each. The user must find two orders of magnitude more parallelism than is typically exploited in a single microprocessor; thus, it is not clear that the computational power of FPGAs can be exploited across a wide range of algorithms. This paper explores three implementation alternatives for the Fast Fourier Transform (FFT) on FPGAs. The algorithms are compared in terms of sustained performance and memory requirements for various FFT sizes and FPGA sizes. The results indicate that FPGAs are competitive with microprocessors in terms of performance and that the "correct" FFT implementation varies based on the size of the transform and the size of the FPGA. © 2005 IEEE.

There have been many papers proposing the use of logarithmic numbers (LNS) as an alternative to floating point because of simpler multiplication, division and exponentiation computations [1,4-9,13]. However, this advantage comes at the cost of complicated, inexact addition and subtraction, as well as the need to convert between the formats. In this work, we created a parameterized LNS library of computational units and compared them to an existing floating point library. Specifically, we considered multiplication, division, addition, subtraction, and format conversion to determine when one format should be used over the other and when it is advantageous to change formats during a calculation. © 2005 IEEE.

The latency and throughput of MPI messages are critically important to a range of parallel scientific applications. In many modern networks, both of these performance characteristics are largely driven by the performance of a processor on the network interface. Because of the semantics of MPI, this embedded processor is forced to traverse a linked list of posted receives each time a message is received. As this list grows long, the latency of message reception grows and the throughput of MPI messages decreases. This paper presents a novel hardware feature to handle list management functions on a network interface. By moving functions such as list insertion, list traversal, and list deletion to the hardware unit, latencies are decreased by up to 20% in the zero length queue case with dramatic improvements in the presence of long queues. Similarly, the throughput is increased by up to 10% in the zero length queue case and by nearly 100% in the presence queues of 30 messages.