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:20260522T150119Z LOCATION:D161 DTSTART;TZID=America/Chicago:20181111T090000 DTEND;TZID=America/Chicago:20181111T173000 UID:submissions.supercomputing.org_SC18_sess156@linklings.com SUMMARY:The 3rd International Workshop on Post-Moore Era Supercomputing (P MES) DESCRIPTION:Session 1\n\nTranquility Amidst Turbulence: A Vision for Advan cing Scientific Discovery in the Era of Extreme Heterogeneity\n\nRapid cha nges in computing technology are driving ever-faster changes in the way sc ientific discoveries are made. Dr. Lucy Nowell will discuss the dimensions of heterogeneity that are expected to impact the software stack for compu tational and data-intensive in the 2025-2035 timeframe. In particular...\n \n\nLucy Nowell (US Department of Energy Office of Advanced Scientific Com puting Research)\n---------------------\nIntroduction - The 3rd Internatio nal Workshop on Post-Moore Era Supercomputing (PMES)\n\nThe 3rd Internatio nal Workshop on Post Moore's Era Supercomputing (PMES) follows the very su ccessful PMES workshops at SC16 and SC17. This interdisciplinary workshop is organized to explore the scientific issues, challenges, and opportuniti es for supercomputing beyond the scaling limits of Moore's L...\n\n\nJeffr ey S. Vetter (Oak Ridge National Laboratory) and Satoshi Matsuoka (Tokyo I nstitute of Technology)\n---------------------\nMemory-Efficient Quantum C ircuit Simulation by Using Lossy Data Compression\n\nIn order to evaluate, validate, and refine the design of new quantum algorithms or quantum comp uters, researchers and developers need methods to assess their correctness and fidelity. This requires the capabilities of quantum circuit simulatio ns. However, the number of quantum state amplitudes incre...\n\n\nXin-Chua n Wu (University of Chicago, Argonne National Laboratory); Sheng Di, Franc k Cappello, Hal Finkel, and Yuri Alexeev (Argonne National Laboratory); an d Frederic T. Chong (University of Chicago)\n---------------------\nHybrid Quantum-Classical Computing Architectures\n\nWe describe how classical su percomputing can aid unreliable quantum processors of intermediate size to solve large problem instances reliably. We advocate using a hybrid quantu m-classical architecture where larger quantum circuits are broken into sma ller sub-circuits that are evaluated separately, e...\n\n\nMartin Suchara and Yuri Alexeev (Argonne National Laboratory), Frederic Chong (University of Chicago), Hal Finkel (Argonne National Laboratory), Henry Hoffmann (Un iversity of Chicago), Jeffrey Larson and James Osborn (Argonne National La boratory), and Graeme Smith (University of Colorado)\n-------------------- -\nNon-Neural Network Applications for Spiking Neuromorphic Hardware\n\nIn creasing power costs for large-scale computing in a post-Moore’s Law syste m have forced the high-performance computing community to explore heteroge neous systems. Neuromorphic architectures, inspired by biological neural systems, have so far been relegated to auxiliary machine learning applicat io...\n\n\nJames B. Aimone (Sandia National Laboratories), Kathleen E. Ham ilton (Oak Ridge National Laboratory), Susan Mniszewski (Los Alamos Nation al Laboratory), Leah Reeder (Sandia National Laboratories), Catherine D. S chuman (Oak Ridge National Laboratory), and William M. Severa (Sandia Nati onal Laboratories)\n---------------------\nWorkshop Afternoon Break\n----- ----------------\nWorkshop Morning Break\n---------------------\nA Task-Ba sed Abstraction Layer for User Productivity and Performance Portability in Post-Moore’s Era Supercomputing\n\nThe proliferation of heterogeneous com puting architectures in current and future supercomputing systems dramatic ally increases the complexity of software development and exacerbates the divergence of software stacks. Currently, task-based runtimes attempt to a lleviate these impediments, however thei...\n\n\nSteve Petruzza, Attila Gy ulassy, and Valerio Pascucci (University of Utah) and Peer-Timo Bremer (La wrence Livermore National Laboratory)\n---------------------\nComparing De ep Learning with Quantum Inference on The D-Wave 2X\n\nWe used a quantum a nnealing D-Wave 2X computer to obtain solutions to NP-hard sparse coding p roblems for inferring representation of reduced dimensional MNIST images. For comparison, we implemented two deep neural network architectures. The first (AlexNet-like) approximately matched the architec...\n\n\nNga Ng uyen and Garrett Kenyon (Los Alamos National Laboratory)\n---------------- -----\nWorkshop Lunch (on your own)\n---------------------\nWorkshop Closi ng\n---------------------\nCommunity Detection Across Emerging Quantum Arc hitectures\n\nOne of the roadmap plans for quantum computers is an integra tion within HPC ecosystems assigning them a role of accelerators for a var iety of computationally hard tasks. However, in the near term, quantum har dware will be in a constant state of change. Heading towards solving real- world problems, we...\n\n\nRuslan Shaydulin, Hayato Ushijima-Mwesigwa, and Ilya Safro (Clemson University); Susan Mniszewski (Los Alamos National La boratory); and Yuri Alexeev (Argonne National Laboratory)\n--------------- ------\nStochastic Computing on Quantum Gates\n\nThe concept of Stochastic Computing is applied to Quantum Computing. A qubit in a superposition sta te is used to represent a probability as an input for Stochastic Computati on, instead of a random bit stream. Measuring the output qubit from the qu antum circuit produces zero or one with the probabili...\n\n\nYoshito Kana mori (University of Alaska, Anchorage)\n---------------------\nDomain-Spec ific System on Chips (DSSoC)\n\nThe invention of the digital computer came about as a proof of computable numbers, and so numerical processing was s olved by the Turing Machine that has led to the general purpose computer. These computers are good at solving multiple types of problems with a sing le machine. However, within the scop...\n\n\nTom Rondeau (Defense Advanced Research Projects Agency (DARPA), Domain-Specific System on Chip (DSSoC) Program)\n---------------------\nSpeaker Panel 1\n---------------------\nS peaker Panel 2\n---------------------\nDoing Moore with Less – Leapfroggin g Moore’s Law with Inexactness for Supercomputing\n\nWe investigate the us e of inexactness, to trade solution quality with energy savings to reduce power consumption in HPC systems, using commercial off-the-shelf processor s for lower-precision arithmetic. We implement an inexact Newton algorithm for solving nonlinear equations to show how to reinvest ...\n\n\nSven Ley ffer and Stefan M. Wild (Argonne National Laboratory), Mike Fagan (Rice Un iversity), Marc Snir (University of Illinois), Krishna Palem (Rice Univers ity), and Yoshii Kazutomo and Hal Finkel (Argonne National Laboratory)\n-- -------------------\nShortest Path and Neighborhood Subgraph Extraction on a Spiking Memristive Neuromorphic Implementation\n\nSpiking neuromorphic computers (SNCs) are promising as a post Moore's law technology because of their potential for very low power computation. SNCs have primarily been demonstrated on machine learning applications, but they can also be used for applications beyond machine learning. Here, we demon...\n\n\nCatherin e Schuman, Kathleen Hamilton, and Tiffany Mintz (Oak Ridge National Labora tory); Md Musabbir Adnan (University of Tennessee); Bon Woong Ku and Sung- Kyu Lim (Georgia Institute of Technology); and Garrett S. Rose (University of Tennessee)\n\nTag: Architectures, Heterogeneous Systems, Quantum Compu ting\n\nRegistration Category: Workshop Reg Pass\n\nSession Chair: Jeffrey S. Vetter (Oak Ridge National Laboratory (ORNL)) END:VEVENT END:VCALENDAR