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:20181221T160907Z LOCATION:C2/3/4 Ballroom DTSTART;TZID=America/Chicago:20181115T083000 DTEND;TZID=America/Chicago:20181115T170000 UID:submissions.supercomputing.org_SC18_sess341@linklings.com SUMMARY:Exhibition of Doctoral Showcase Posters DESCRIPTION:Doctoral Showcase\nWorkshop Reg Pass, Tutorial Reg Pass, Tech Program Reg Pass, Exhibits Reg Pass, Exhibits - Exhibit Hall Only Reg Pass \n\nProductive Data Locality Optimizations in Distributed Memory\n\nKayrak lioglu, El-Ghazawi\n\nWith deepening memory hierarchies in HPC systems, th e challenge of managing data locality gains more importance. Coincidentall y, increasing ubiquity of HPC systems and wider range of disciplines utili zing HPC introduce more programmers to the HPC community. Given these two trends, it is imperative t...\n\n---------------------\nLinear Algebra Is the Right Way to Think About Graphs\n\nYang, Owens, Buluc\n\nGraph algorit hms are challenging to implement on new accelerators such as GPUs. To addr ess this problem, GraphBLAS is an innovative on-going effort by the graph analytics community to formulate graph algorithms as sparse linear algebra , so that they can be expressed in a performant, succinct and in ...\n\n-- -------------------\nDesigning High-Performance, Resilient, and Heterogene ity-Aware Key-Value Storage for Modern HPC Clusters\n\nShankar, Panda, Lu\ n\nDistributed key-value stores are being increasingly used to accelerate Big Data workloads on modern HPC clusters. The advances in HPC technologie s (e.g., RDMA, SSDs) has directed several efforts towards employing hybrid storage with RDMA, for designing high- performance key-value stores. With this a...\n\n---------------------\nEnabling Efficient Data Infrastructur e and Analytics on HPC Systems\n\nFu, Yu\n\nWe propose to leverage PGAS an d one-sided communication for building data infrastructure and analytics f rameworks on HPC systems. Specifically, we have developed SHMEMCache, a di stributed in-memory key-value store and SHMEMGraph, a balanced graph proce ssing framework. We have tackled unique challeng...\n\n------------------- --\nHardware Transactional Persistent Memory\n\nGiles, Varman\n\nThis rese arch solves the problem of creating durable transactions in byte-addressab le Non-Volatile Memory or Persistent Memory (PM) when using Hardware Trans actional Memory (HTM)-based concurrency control.  It shows how HTM tr ansactions can be ordered correctly and atomically into PM by the use...\n \n---------------------\nParallel and Scalable Combinatorial String and Gr aph Algorithms on Distributed Memory Systems\n\nFlick, Aluru\n\nMethods fo r processing and analyzing DNA and genomic data are built upon combinatori al graph and string algorithms. The advent of high-throughput DNA sequenci ng is enabling the generation of billions of reads per experiment. Classic al and sequential algorithms can no longer deal with these growing d...\n\ n---------------------\nScalable Methods for Genome Assembly\n\nGhosh, Kal yanaraman\n\nGenome assembly is a fundamental problem in the field of bioi nformatics wherein the goal lies in the reconstruction of an unknown genom e from short DNA fragments obtained from it. With the advent of high-throu ghput sequencing technologies, billions of reads can be generated in a few hours. My reseac...\n\n---------------------\nHigh Performance Middleware s for Next Generation Architectures: Challenges and Solutions\n\nChakrabor ty, Panda\n\nThe emergence of modern multi-/many-core architectures and hi gh-performance interconnects have fueled the growth of large-scale superco mputing clusters. Due to this unprecedented growth in scale and compute de nsity, high performance computing (HPC) middlewares now face a plethora of new challenges t...\n\n---------------------\nIn-Memory Accelerator Archi tectures for Machine Learning and Bioinformatics\n\nKaplan, Ginosar\n\nMos t contemporary accelerators are von Neumann machines. With the increasing sizes of gathered and then processed data,  memory bandwidth is the m ain limiting of performance. One approach to mitigate the bandwidth constr aint is to bring the processing units closer to the data. This approach is ...\n\n---------------------\nEfficient Deployment of Irregular Computati ons on Multi- and Many-Core Architectures\n\nWu, Becchi\n\nMulti- and many core processors have been advancing High Performance Computing with their high throughput and power efficiency. There has been an increasing interes t in accelerating irregular computations on these devices that offer massi ve parallelism. My thesis focuses on compiler techniques and co...\n\n---- -----------------\nUsing Integrated Processor Graphics to Accelerate Concu rrent Data and Index Structures\n\nFuentes, Scherson\n\nWith the advent of computing systems with on-die integrated processor graphics (iGPU), new p rogramming challenges have emerged from these heterogeneous systems. We pr oposed different data and index structure algorithms that can benefit from the Intel's iGPU architecture and the C for Media (CM) prog...\n\n------- --------------\nCompiler and Runtime Based Parallelization and Optimizatio n for GPUs\n\nOzen, Labarta, Ayguade\n\nThis thesis targets directive-base d 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 multiple GPUs in conjunction with t he heavily multithreaded capabilities in mul...\n\n---------------------\n The Algorithm and Framework Designs and Optimizations for Scalable Automat a Processing on HPC Platforms\n\nYu, Yao\n\nAutomata processing could perf orm as the core of many applications in the areas such as network security , text mining, and bioinformatics. Achieving high-speed and scalable autom ata processing is exceptionally challenging. For one thing, the classic DF A representation is memory-bandwidth efficient b...\n\n------------------- --\nPattern Matching on Massive Metadata Graphs at Scale\n\nReza, Ripeanu\ n\nPattern matching is a powerful graph analysis tool. Unfortunately, exis ting solutions have limited scalability, support only a limited set of pat terns, and/or focus on only a subset of the real-world problems associated with pattern matching. First, we present a new algorithmic pipeline based on gra...\n\n---------------------\nScalable Non-Blocking Krylov Solvers for Extreme-Scale Computing\n\nEller, Gropp\n\nThis study investigates pre conditioned conjugate gradient method variations designed to reduce commun ication costs by decreasing the number of allreduces and overlapping commu nication with computation using a non-blocking allreduce. Experiments show scalable PCG methods can outperform standard PCG a...\n\n---------------- -----\nFast and Generic Concurrent Message-Passing\n\nDang, Snir\n\nCommun ication hardware and software have a significant impact on the performance  of clusters and supercomputers. Message-passing model and the Messag e-Passing Interface (MPI) is a widely used model of communications in the High-Performance
Computing (HPC) community. However, MPI has r.. .\n END:VEVENT END:VCALENDAR