Service Aggregated Linked Sequential Activities GOALS: Increasing number of cores accompanied by continued data deluge. Develop scalable parallel data.

Slides:



Advertisements
Similar presentations
Shanghai Many-Core Workshop March Judy Qiu Research.
Advertisements

Scalable High Performance Dimension Reduction
SALSA HPC Group School of Informatics and Computing Indiana University.
High Performance Dimension Reduction and Visualization for Large High-dimensional Data Analysis Jong Youl Choi, Seung-Hee Bae, Judy Qiu, and Geoffrey Fox.
OpenFOAM on a GPU-based Heterogeneous Cluster
SALSASALSASALSASALSA Large Scale DNA Sequence Analysis and Biomedical Computing using MapReduce, MPI and Threading Workshop on Enabling Data-Intensive.
Authors: Thilina Gunarathne, Tak-Lon Wu, Judy Qiu, Geoffrey Fox Publish: HPDC'10, June 20–25, 2010, Chicago, Illinois, USA ACM Speaker: Jia Bao Lin.
CUDA Programming Lei Zhou, Yafeng Yin, Yanzhi Ren, Hong Man, Yingying Chen.
Parallel Data Analysis from Multicore to Cloudy Grids Indiana University Geoffrey Fox, Xiaohong Qiu, Scott Beason, Seung-Hee.
Dimension Reduction and Visualization of Large High-Dimensional Data via Interpolation Seung-Hee Bae, Jong Youl Choi, Judy Qiu, and Geoffrey Fox School.
SALSASALSA Judy Qiu Research Computing UITS, Indiana University.
SALSASALSA Programming Abstractions for Multicore Clouds eScience 2008 Conference Workshop on Abstractions for Distributed Applications and Systems December.
Service Aggregated Linked Sequential Activities GOALS: Increasing number of cores accompanied by continued data deluge Develop scalable parallel data mining.
1 Multicore SALSA Parallel Computing and Web 2.0 for Cheminformatics and GIS Analysis 2007 Microsoft eScience Workshop at RENCI The Friday Center for Continuing.
PC08 Tutorial 1 CCR Multicore Performance ECMS Multiconference HPCS 2008 Nicosia Cyprus June Geoffrey Fox, Seung-Hee Bae, Neil Devadasan,
Exercise problems for students taking the Programming Parallel Computers course. Janusz Kowalik Piotr Arlukowicz Tadeusz Puzniakowski Informatics Institute.
Computer System Architectures Computer System Software
SALSASALSA Judy Qiu Assistant Director, Pervasive Technology Institute.
Chapter 4 Performance. Times User CPU time – Time that the CPU is executing the program System CPU time – time the CPU is executing OS routines for the.
1 Multicore Salsa Parallel Programming 2.0 SC07 Reno Nevada November Geoffrey Fox, Huapeng Yuan, Seung-Hee Bae Community Grids Laboratory, Indiana.
Science in Clouds SALSA Team salsaweb/salsa Community Grids Laboratory, Digital Science Center Pervasive Technology Institute Indiana University.
SALSASALSASALSASALSA Proposal Review Meeting with CTSI Translating Research Into Practice Project Development Team, July 8, 2009, IUPUI Gil Liu, Judy Qiu,
Generative Topographic Mapping in Life Science Jong Youl Choi School of Informatics and Computing Pervasive Technology Institute Indiana University
1 Multicore Salsa Parallel Programming 2.0 Peking University October Geoffrey Fox, Huapeng Yuan, Seung-Hee Bae Community Grids Laboratory, Indiana.
Applications and Runtime for multicore/manycore March Geoffrey Fox Community Grids Laboratory Indiana University 505 N Morton Suite 224 Bloomington.
Parallel and Distributed Systems Instructor: Xin Yuan Department of Computer Science Florida State University.
1 Performance of a Multi-Paradigm Messaging Runtime on Multicore Systems Poster at Grid 2007 Omni Austin Downtown Hotel Austin Texas September
SALSASALSA International Conference on Computational Science June Kraków, Poland Judy Qiu
SALSASALSASALSASALSA Cloud Technologies and Their Applications March 26, 2010 Indiana University Bloomington Judy Qiu
Chapter 3 Parallel Algorithm Design. Outline Task/channel model Task/channel model Algorithm design methodology Algorithm design methodology Case studies.
Generative Topographic Mapping by Deterministic Annealing Jong Youl Choi, Judy Qiu, Marlon Pierce, and Geoffrey Fox School of Informatics and Computing.
SALSASALSA Microsoft eScience Workshop December Indianapolis, Indiana Geoffrey Fox
1 Data Analysis from Cores to Clouds HPC 2008 High Performance Computing and Grids Cetraro Italy July Geoffrey Fox, Seung-Hee Bae,
Parallel Applications And Tools For Cloud Computing Environments Azure MapReduce Large-scale PageRank with Twister Twister BLAST Thilina Gunarathne, Stephen.
LATA: A Latency and Throughput- Aware Packet Processing System Author: Jilong Kuang and Laxmi Bhuyan Publisher: DAC 2010 Presenter: Chun-Sheng Hsueh Date:
S CALABLE H IGH P ERFORMANCE D IMENSION R EDUCTION Seung-Hee Bae.
SALSA HPC Group School of Informatics and Computing Indiana University.
MATRIX MULTIPLY WITH DRYAD B649 Course Project Introduction.
1 Performance Measurements of CCR and MPI on Multicore Systems Expanded from a Poster at Grid 2007 Austin Texas September Xiaohong Qiu Research.
Community Grids Lab. Indiana University, Bloomington Seung-Hee Bae.
Multidimensional Scaling by Deterministic Annealing with Iterative Majorization Algorithm Seung-Hee Bae, Judy Qiu, and Geoffrey Fox SALSA group in Pervasive.
1 Robust High Performance Optimization for Clustering, Multi-Dimensional Scaling and Mixture Models CGB Indiana University Lunchtime Talk January
1 High Performance Multi-Paradigm Messaging Runtime Integrating Grids and Multicore Systems e-Science 2007 Conference Bangalore India December
Service Aggregated Linked Sequential Activities: GOALS: Increasing number of cores accompanied by continued data deluge Develop scalable parallel data.
SALSASALSA Research Technologies Round Table, Indiana University, December Judy Qiu
SALSA Group’s Collaborations with Microsoft SALSA Group Principal Investigator Geoffrey Fox Project Lead Judy Qiu Scott Beason,
Shanghai Many-Core Workshop, March Judy Qiu Research.
1 Multicore for Science Multicore Panel at eScience 2008 December Geoffrey Fox Community Grids Laboratory, School of informatics Indiana University.
SALSASALSASALSASALSA Multicore and Cloud Technologies for Data Intensive Applications Ballantine Hall 006, Indiana University Bloomington October 23, 2009.
Linear Algebra Libraries: BLAS, LAPACK, ScaLAPACK, PLASMA, MAGMA
Cloud Computing Paradigms for Pleasingly Parallel Biomedical Applications Thilina Gunarathne, Tak-Lon Wu Judy Qiu, Geoffrey Fox School of Informatics,
SALSA Group Research Activities April 27, Research Overview  MapReduce Runtime  Twister  Azure MapReduce  Dryad and Parallel Applications 
Parallel Applications And Tools For Cloud Computing Environments CloudCom 2010 Indianapolis, Indiana, USA Nov 30 – Dec 3, 2010.
SALSASALSASALSASALSA Data Intensive Biomedical Computing Systems Statewide IT Conference October 1, 2009, Indianapolis Judy Qiu
Optimization Indiana University July Geoffrey Fox
1 High Performance Robust Datamining for Cheminformatics Division of Chemical Information Session: Cheminformatics: From Teaching to Research ACS Spring.
Background Computer System Architectures Computer System Software.
Lecture 13 Parallel Processing. 2 What is Parallel Computing? Traditionally software has been written for serial computation. Parallel computing is the.
1 Multicore Salsa Parallel Computing and Web 2.0 Open Grid Forum Web 2.0 Workshop OGF21, Seattle Washington October Geoffrey Fox, Huapeng Yuan,
Community Grids Laboratory
Service Aggregated Linked Sequential Activities
Our Objectives Explore the applicability of Microsoft technologies to real world scientific domains with a focus on data intensive applications Expect.
Geoffrey Fox, Huapeng Yuan, Seung-Hee Bae Xiaohong Qiu
Microsoft eScience Workshop December 2008 Geoffrey Fox
Biology MDS and Clustering Results
GCC2008 (Global Clouds and Cores 2008) October Geoffrey Fox
PHI Research in Digital Science Center
Clouds and Grids Multicore and all that
Presentation transcript:

Service Aggregated Linked Sequential Activities GOALS: Increasing number of cores accompanied by continued data deluge. Develop scalable parallel data mining algorithms with good multicore and cluster performance; understand software runtime and parallelization method. Use managed code (C#) and package algorithms as services to encourage broad use assuming experts parallelize core algorithms. CURRENT RESUTS: Microsoft CCR supports MPI, dynamic threading and via DSS a Service model of computing; detailed performance measurements. Speedups of 7.5 or above on 8-core systems for “large problems” with deterministic annealed (avoid local minima) algorithms for clustering, Gaussian Mixtures, GTM (dimensional reduction) etc. SALSA Team Geoffrey Fox Xiaohong Qiu Seung-Hee Bae Huapeng Yuan Indiana University Technology Collaboration George Chrysanthakopoulos Henrik Frystyk Nielsen Microsoft Application Collaboration Cheminformatics Rajarshi Guha David Wild Bioinformatics Haiku Tang Demographics (GIS) Neil Devadasan Indiana University and IUPUI SALSASALSA

SALSASALSA N data points E(x) in D dim. space and Minimize F by EM Deterministic Annealing Clustering (DAC)  a(x) = 1/N or generally p(x) with  p(x) =1  g(k)=1 and s(k)=0.5  T is annealing temperature varied down from  with final value of 1  Vary cluster center Y(k) but can calculate P k and  (k) (even for matrix  (k)) using IDENTICAL formulae for Gaussian mixtures  K starts at 1 and is incremented by algorithm

Deterministic Annealing Clustering of Indiana Census Data Decrease temperature (distance scale) to discover more clusters Distance Scale Temperature 0.5 SALSASALSA

Traditional Gaussian mixture models (GM)  As DAGM but set T=1 and fix K Deterministic Annealed Generative Topographic Mapping (DAGTM)  GTM has several natural annealing versions based on either DAC or DAGM: under investigation N data points E(x) in D dim. space and Minimize F by EM SALSASALSA

 We implement micro-parallelism using Microsoft CCR (Concurrency and Coordination Runtime) as it supports both MPI rendezvous and dynamic (spawned) threading style of parallelism  CCR Supports exchange of messages between threads using named ports and has primitives like:  FromHandler: Spawn threads without reading ports  Receive: Each handler reads one item from a single port  MultipleItemReceive: Each handler reads a prescribed number of items of a given type from a given port. Note items in a port can be general structures but all must have same type.  MultiplePortReceive: Each handler reads a one item of a given type from multiple ports.  CCR has fewer primitives than MPI but can implement MPI collectives efficiently  Use DSS (Decentralized System Services) built in terms of CCR for service model  DSS has ~35 µs and CCR a few µs overhead SALSASALSA

MPI Exchange Latency in µs (20-30 µs computation between messaging) MachineOSRuntimeGrainsParallelismMPI Latency Intel8c:gf12 (8 core 2.33 Ghz) (in 2 chips) RedhatMPJE(Java)Process8181 MPICH2 (C)Process840.0 MPICH2:FastProcess839.3 NemesisProcess84.21 Intel8c:gf20 (8 core 2.33 Ghz) FedoraMPJEProcess8157 mpiJavaProcess8111 MPICH2Process864.2 Intel8b (8 core 2.66 Ghz) VistaMPJEProcess8170 FedoraMPJEProcess8142 FedorampiJavaProcess8100 VistaCCR (C#)Thread820.2 AMD4 (4 core 2.19 Ghz) XPMPJEProcess4185 RedhatMPJEProcess4152 mpiJavaProcess499.4 MPICH2Process439.3 XPCCRThread416.3 Intel(4 core)XPCCRThread425.8 SALSASALSA Messaging CCR versus MPI C# v. C v. Java

Intel8b: 8 CoreNumber of Parallel Computations (μs) DynamicSpawn ed Threads Pipeline Shift Two Shifts Rendezvous MPI style Pipeline Shift Exchange As Two Shifts CCR Custom Exchange SALSASALSA

Speedup = Number of cores/(1+f) f = (Sum of Overheads)/(Computation per core) Computation  Grain Size n. # Clusters K Overheads are Synchronization: small with CCR Load Balance: good Memory Bandwidth Limit:  0 as K   Cache Use/Interference: Important Runtime Fluctuations: Dominant large n, K All our “real” problems have f ≤ 0.05 and speedups on 8 core systems greater than 7.6 SALSASALSA

2 Quadcore Processors Average of standard deviation of run time of the 8 threads between messaging synchronization points Number of Threads Standard Deviation/Run Time SALSASALSA

 Use Data Decomposition as in classic distributed memory but use shared memory for read variables. Each thread uses a “local” array for written variables to get good cache performance  Multicore and Cluster use same parallel algorithms but different runtime implementations; algorithms are  Accumulate matrix and vector elements in each process/thread  At iteration barrier, combine contributions (MPI_Reduce)  Linear Algebra (multiplication, equation solving, SVD) “Main Thread” and Memory M 1m11m1 0m00m0 2m22m2 3m33m3 4m44m4 5m55m5 6m66m6 7m77m7 Subsidiary threads t with memory m t MPI/CCR/DSS From other nodes MPI/CCR/DSS From other nodes SALSASALSA

SALSASALSA

SALSASALSA

GTM Projection of 2 clusters of 335 compounds in 155 dimensions GTM Projection of PubChem: 10,926,94 compounds in 166 dimension binary property space takes 4 days on 8 cores. 64X64 mesh of GTM clusters interpolates PubChem. Could usefully use 1024 cores! David Wild will use for GIS style 2D browsing interface to chemistry PCAGTM Linear PCA v. nonlinear GTM on 6 Gaussians in 3D PCA is Principal Component Analysis Parallel Generative Topographic Mapping GTM Reduce dimensionality preserving topology and perhaps distances Here project to 2D Working on: Random Projection Metric Embedding (Bourgain) and MDS Dimensional Scaling (EM like SMACOF) SALSASALSA

 Micro-parallelism uses low latency CCR threads or MPI processes  Services can be used where loose coupling natural  Input data  Algorithms  PCA  DAC GTM GM DAGM DAGTM – both for complete algorithm and for each iteration  Linear Algebra used inside or outside above  Metric embedding, MDS, HMM, SVM ….  User interface: GIS (Web map Service) or equivalent SALSASALSA

 This class of data mining does/will parallelize well on current/future multicore nodes  Several engineering issues for use in large applications  How to take CCR in multicore node to cluster (MPI or cross-cluster CCR?)  Need high performance linear algebra for C#  Access linear algebra services in a different language?  Need equivalent of Intel C Math Libraries for C# (vector arithmetic)  Service model to integrate modules  Need access to a ~ 128 node Windows cluster  Future work is more applications; refine current algorithms such as DAGTM  New parallel algorithms  Bourgain Random Projection for metric embedding  MDS Dimensional Scaling (SMACOF)  Support use of Newton’s Method (Marquardt’s method) as EM alternative  Later HMM and SVM  Need advice on quadratic programming SALSASALSA