BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:America/Chicago X-LIC-LOCATION:America/Chicago BEGIN:DAYLIGHT TZOFFSETFROM:-0600 TZOFFSETTO:-0500 TZNAME:CDT DTSTART:19700308T020000 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:-0500 TZOFFSETTO:-0600 TZNAME:CST DTSTART:19701101T020000 RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260522T150153Z LOCATION:C2/3/4 Ballroom DTSTART;TZID=America/Chicago:20181113T171500 DTEND;TZID=America/Chicago:20181113T190000 UID:submissions.supercomputing.org_SC18_sess343@linklings.com SUMMARY:Doctoral Showcase Posters Reception DESCRIPTION:Reception catering is available for Technical Program registra nts only.\n\nFast and Generic Concurrent Message-Passing\n\nCommunication hardware and software have a significant impact on the performance of clus ters and supercomputers. Message-passing model and the Message-Passing Int erface (MPI) is a widely used model of communications in the High-Performa nce
Computing (HPC) community. However, MPI has r...\n\n\nHoang-Vu Da ng and Marc Snir (University of Illinois)\n---------------------\nDesignin g High-Performance, Resilient, and Heterogeneity-Aware Key-Value Storage f or Modern HPC Clusters\n\nDistributed key-value stores are being increasin gly used to accelerate Big Data workloads on modern HPC clusters. The adva nces in HPC technologies (e.g., RDMA, SSDs) has directed several efforts t owards employing hybrid storage with RDMA, for designing high- performance key-value stores. With this a...\n\n\nDipti Shankar, Dhabaleswar K. Panda , and Xiaoyi Lu (Ohio State University)\n---------------------\nScalable N on-Blocking Krylov Solvers for Extreme-Scale Computing\n\nThis study inves tigates preconditioned conjugate gradient method variations designed to re duce communication costs by decreasing the number of allreduces and overla pping communication with computation using a non-blocking allreduce. Exper iments show scalable PCG methods can outperform standard PCG a...\n\n\nPau l R. Eller and William Gropp (University of Illinois)\n------------------- --\nParallel and Scalable Combinatorial String and Graph Algorithms on Dis tributed Memory Systems\n\nMethods for processing and analyzing DNA and ge nomic data are built upon combinatorial graph and string algorithms. The a dvent of high-throughput DNA sequencing is enabling the generation of bill ions of reads per experiment. Classical and sequential algorithms can no l onger deal with these growing d...\n\n\nPatrick Flick and Srinivas Aluru ( Georgia Institute of Technology)\n---------------------\nScalable Methods for Genome Assembly\n\nGenome assembly is a fundamental problem in the fie ld of bioinformatics wherein the goal lies in the reconstruction of an unk nown genome from short DNA fragments obtained from it. With the advent of high-throughput sequencing technologies, billions of reads can be generate d in a few hours. My reseac...\n\n\nPriyanka Ghosh and Ananth Kalyanaraman (Washington State University)\n---------------------\nHigh Performance Mi ddlewares for Next Generation Architectures: Challenges and Solutions\n\nT he emergence of modern multi-/many-core architectures and high-performance interconnects have fueled the growth of large-scale supercomputing cluste rs. Due to this unprecedented growth in scale and compute density, high pe rformance computing (HPC) middlewares now face a plethora of new challenge s t...\n\n\nSourav Chakraborty and Dhabaleswar K. Panda (Ohio State Univer sity)\n---------------------\nProductive Data Locality Optimizations in Di stributed Memory\n\nWith deepening memory hierarchies in HPC systems, the challenge of managing data locality gains more importance. Coincidentally, increasing ubiquity of HPC systems and wider range of disciplines utilizi ng HPC introduce more programmers to the HPC community. Given these two tr ends, it is imperative t...\n\n\nEngin Kayraklioglu and Tarek El-Ghazawi ( George Washington University)\n---------------------\nPattern Matching on Massive Metadata Graphs at Scale\n\nPattern matching is a powerful graph a nalysis tool. Unfortunately, existing solutions have limited scalability, support only a limited set of patterns, and/or focus on only a subset of t he real-world problems associated with pattern matching. First, we present a new algorithmic pipeline based on gra...\n\n\nTahsin Reza and Matei Rip eanu (University of British Columbia)\n---------------------\nEnabling Eff icient Data Infrastructure and Analytics on HPC Systems\n\nWe propose to l everage PGAS and one-sided communication for building data infrastructure and analytics frameworks on HPC systems. Specifically, we have developed S HMEMCache, a distributed in-memory key-value store and SHMEMGraph, a balan ced graph processing framework. We have tackled unique challeng...\n\n\nHu ansong Fu and Weikuan Yu (Florida State University)\n--------------------- \nUsing Integrated Processor Graphics to Accelerate Concurrent Data and In dex Structures\n\nWith the advent of computing systems with on-die integra ted processor graphics (iGPU), new programming challenges have emerged fro m these heterogeneous systems. We proposed different data and index struct ure algorithms that can benefit from the Intel's iGPU architecture and the C for Media (CM) prog...\n\n\nJoel Fuentes and Isaac Scherson (University of California, Irvine)\n---------------------\nIn-Memory Accelerator Arch itectures for Machine Learning and Bioinformatics\n\nMost contemporary acc elerators are von Neumann machines. With the increasing sizes of gathered and then processed data,  memory bandwidth is the main limiting of perform ance. One approach to mitigate the bandwidth constraint is to bring the pr ocessing units closer to the data. This approach is ...\n\n\nRoman Kaplan and Ran Ginosar (Israel Institute of Technology)\n---------------------\nL inear Algebra Is the Right Way to Think About Graphs\n\nGraph algorithms a re challenging to implement on new accelerators such as GPUs. To address t his problem, GraphBLAS is an innovative on-going effort by the graph analy tics community to formulate graph algorithms as sparse linear algebra, so that they can be expressed in a performant, succinct and in ...\n\n\nCarl Yang (University of California, Davis; Lawrence Berkeley National Laborato ry); John D. Owens (University of California, Davis); and Aydin Buluc (Law rence Berkeley National Laboratory; University of California, Berkeley)\n- --------------------\nThe Algorithm and Framework Designs and Optimization s for Scalable Automata Processing on HPC Platforms\n\nAutomata processing could perform as the core of many applications in the areas such as netwo rk security, text mining, and bioinformatics. Achieving high-speed and sca lable automata processing is exceptionally challenging. For one thing, the classic DFA representation is memory-bandwidth efficient b...\n\n\nXiaodo ng Yu and Danfeng Yao (Virginia Tech)\n---------------------\nHardware Tra nsactional Persistent Memory\n\nThis research solves the problem of creati ng durable transactions in byte-addressable Non-Volatile Memory or Persist ent Memory (PM) when using Hardware Transactional Memory (HTM)-based concu rrency control.  It shows how HTM transactions can be ordered correctly an d atomically into PM by the use...\n\n\nEllis Giles and Peter Varman (Rice University)\n---------------------\nEfficient Deployment of Irregular Com putations on Multi- and Many-Core Architectures\n\nMulti- and manycore pro cessors have been advancing High Performance Computing with their high thr oughput and power efficiency. There has been an increasing interest in acc elerating irregular computations on these devices that offer massive paral lelism. My thesis focuses on compiler techniques and co...\n\n\nHancheng W u and Michela Becchi (North Carolina State University)\n------------------ ---\nCompiler and Runtime Based Parallelization and Optimization for GPUs\ n\nThis thesis targets directive-based programming models to enhance their capability for GPU programming.  It introduces a new dialect model, which is a combination of OpenMP and OmpSs. The new model allows the use of mul tiple GPUs in conjunction with the heavily multithreaded capabilities in m ul...\n\n\nGuray Ozen, Jesus Labarta, and Eduard Ayguade (Barcelona Superc omputing Center, Polytechnic University of Catalonia)\n\nRegistration Cate gory: Workshop Reg Pass, Tutorial Reg Pass, Tech Program Reg Pass, Exhibit s Reg Pass, Exhibits - Exhibit Hall Only Reg Pass END:VEVENT END:VCALENDAR