Service Aggregated Linked Sequential Activities 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 IU Bloomington and IUPUI 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 N data points E(x) in D dim. space and Minimize F by EM N N x 1 x 1 2 2 F T ) ln{ g ( k ) exp[ 0.5( E ( x ) Y ( k ))/ T/](Ts(k ))] F aT( x p( x) ln{ exp[ ( E ( x ) Y ( k )) k 1 k 1 K K 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 centerY(k) • K starts at 1 and is incremented by algorithm • My 4th most cited article but little used; probably as no good software compared to simple K-means SALSA Deterministic Annealing Clustering of Indiana Census Data Decrease temperature (distance scale) to discover more clusters Distance Scale Temperature0.5 N data points E(x) in D dim. space and Minimize F by EM N F T a ( x) ln{ k 1 g (k ) exp[ 0.5( E ( x) Y (k )) 2 / (Ts(k ))] K x 1 Deterministic Generative Traditional Topographic Annealing Gaussian Clustering Mapping (GTM) (DAC) Deterministic Annealing Gaussian mixture models GM models (DAGM) • a(x) = 1/NMixture or generally p(x) D/2 with p(x) =1 • a(x) = 1 and g(k) = (1/K)(/2) •and Ass(k)=0.5 DAGM but set T=1 and fix K •• g(k)=1 a(x) = 1 • s(k) = 1/ and T = 1 • T is annealing temperature 2)D/2}1/T varied down from M W/(2(k) •Y(k) •= g(k)={P m=1DAGTM: (X(k)) km m Deterministic Annealed with final value of 1 2 2/2 Gaussian) • s(k)= (k) (taking case of(X- spherical • Choose fixed (X) = exp( 0.5 ) ) m m Generative Topographic Mapping • Vary cluster centerY(k) but can calculate weight T misand annealing temperature varied down from • Vary•W but fix values of M and K a priori 2 • GTM has several natural annealing P and correlation matrix s(k) = (k) (even for space k with final value of 1 •Y(k) E(x)versions Wm are2 vectors in original high D dimension based on eitherformulae DAC orfor DAGM: matrix (k) ) using IDENTICAL • Vary Y(k) P and (k) • X(k) andunder m areinvestigation vectors in 2 dimensional mapped space k Gaussian • K startsmixtures at 1 and is incremented by algorithm •K starts at 1 and is incremented by algorithm SALSA We implement micro-parallelism using Microsoft CCR (Concurrency and Coordination Runtime) as it supports both MPI rendezvous and dynamic (spawned) threading style of parallelism http://msdn.microsoft.com/robotics/ 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 SALSA MPI Exchange Latency in µs (20-30 µs computation between messaging) Machine Intel8c:gf12 (8 core 2.33 Ghz) (in 2 chips) Intel8c:gf20 (8 core 2.33 Ghz) Intel8b (8 core 2.66 Ghz) AMD4 (4 core 2.19 Ghz) Intel(4 core) OS Runtime Grains Parallelism MPI Latency Redhat MPJE(Java) Process 8 181 MPICH2 (C) Process 8 40.0 MPICH2:Fast Process 8 39.3 Nemesis Process 8 4.21 MPJE Process 8 157 mpiJava Process 8 111 MPICH2 Process 8 64.2 Vista MPJE Process 8 170 Fedora MPJE Process 8 142 Fedora mpiJava Process 8 100 Vista CCR (C#) Thread 8 20.2 XP MPJE Process 4 185 Redhat MPJE Process 4 152 mpiJava Process 4 99.4 MPICH2 Process 4 39.3 XP CCR Thread 4 16.3 XP CCR Thread 4 25.8 Fedora Messaging CCR versus MPI C# v. C v. Java SALSA Intel8b: 8 Core (μs) 1 2 3 4 7 8 1.58 2.44 3 2.94 4.5 5.06 Shift 2.42 3.2 3.38 5.26 5.14 Two Shifts 4.94 5.9 6.84 14.32 19.44 3.96 4.52 5.78 6.82 7.18 Shift 4.46 6.42 5.86 10.86 11.74 Exchange As Two Shifts 7.4 11.64 14.16 31.86 35.62 6.94 11.22 13.3 18.78 20.16 Pipeline Dynamic Spawned Threads Pipeline Rendezvous MPI style Number of Parallel Computations CCR Custom Exchange 2.48 SALSA 30 Time Microseconds AMD Exch 25 AMD Exch as 2 Shifts AMD Shift 20 15 10 5 Stages (millions) 0 0 2 4 6 8 10 Overhead (latency) of AMD4 PC with 4 execution threads on MPI style Rendezvous Messaging for Shift and Exchange implemented either as two shifts or as custom CCR pattern 70 Time Microseconds 60 Intel Exch 50 Intel Exch as 2 Shifts Intel Shift 40 30 20 10 Stages (millions) 0 0 2 4 6 8 10 Overhead (latency) of Intel8b PC with 8 execution threads on MPI style Rendezvous Messaging for Shift and Exchange implemented either as two shifts or as custom CCR pattern 1.6 Scaled Intel 8b Vista C# CCR 1 Cluster 1.5 10,000 Runtime 1.4 500,000 1.3 Divide runtime by Grain Size n . # Clusters K 1.2 50,000 Datapoints per thread 1.1 1 a) 1 2 3 4 5 6 Number of Threads (one per core) 7 8 1 Scaled Runtime Intel 8b Vista C# CCR 80 Clusters 50,000 10,000 0.95 500,000 0.9 Datapoints per thread 0.85 0.8 b) 1 2 3 4 5 8 cores (threads) and 1 cluster show memory bandwidth effect 6 Number of Threads (one per core) 7 8 80 clusters show cache/memory bandwidth effect Multicore Matrix Multiplication (dominant linear algebra in GTM) Speedup = Number of cores/(1+f) f = (Sum of Overheads)/(Computation per core) 10,000.00 Execution Time Seconds 4096X4096 matrices 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 1 Core 1,000.00 Parallel Overhead 1% 8 Cores 100.00 Block Size 10.00 1 0.14 10 100 1000 10000 Parallel GTM Performance 0.12 Fractional Overhead f 0.1 0.08 0.06 4096 Interpolating Clusters 0.04 0.02 1/(Grain Size n) 0 0 0.002 n = 500 0.004 0.006 0.008 0.01 100 0.012 0.014 0.016 0.018 0.02 50 SALSA 0.1 Std Dev Intel 8a XP C# CCR Runtime 80 Clusters 0.075 500,000 10,000 0.05 50,000 0.025 Datapoints per thread 0 b) 0 1 2 3 4 5 6 7 Number of Threads (one per core) 8 synchronization 0.006 Std Dev Intel 8c Redhat C Locks Runtime 80 Clusters 10,000 0.004 50,000 500,000 0.002 Datapoints per thread 0 b) 1 2 3 4 5 6 Number of Threads (one per core) This is average of standard deviation of run time of the 8 threads between messaging 7 8 points Early implementations of our clustering algorithm showed large fluctuations due to the cache line interference effect (false sharing) We have one thread on each core each calculating a sum of same complexity storing result in a common array A with different cores using different array locations Thread i stores sum in A(i) is separation 1 – no memory access interference but cache line interference Thread i stores sum in A(X*i) is separation X Serious degradation if X < 8 (64 bytes) with Windows Note A is a double (8 bytes) Less interference effect with Linux – especially Red Hat Machine OS Run Time Intel8b Intel8b Intel8b Intel8b Intel8a Intel8a Intel8a Intel8c AMD4 AMD4 AMD4 AMD4 AMD4 AMD4 Vista Vista Vista Fedora XP CCR XP Locks XP Red Hat WinSrvr WinSrvr WinSrvr XP XP XP C# CCR C# Locks C C C# C# C C C# CCR C# Locks C C# CCR C# Locks C Time µs versus Thread Array Separation (unit is 8 bytes) 1 4 8 1024 Mean Std/ Mean Std/ Mean Std/ Mean Std/ Mean Mean Mean Mean 8.03 .029 3.04 .059 0.884 .0051 0.884 .0069 13.0 .0095 3.08 .0028 0.883 .0043 0.883 .0036 13.4 .0047 1.69 .0026 0.66 .029 0.659 .0057 1.50 .01 0.69 .21 0.307 .0045 0.307 .016 10.6 .033 4.16 .041 1.27 .051 1.43 .049 16.6 .016 4.31 .0067 1.27 .066 1.27 .054 16.9 .0016 2.27 .0042 0.946 .056 0.946 .058 0.441 .0035 0.423 .0031 0.423 .0030 0.423 .032 8.58 .0080 2.62 .081 0.839 .0031 0.838 .0031 8.72 .0036 2.42 0.01 0.836 .0016 0.836 .0013 5.65 .020 2.69 .0060 1.05 .0013 1.05 .0014 8.05 0.010 2.84 0.077 0.84 0.040 0.840 0.022 8.21 0.006 2.57 0.016 0.84 0.007 0.84 0.007 6.10 0.026 2.95 0.017 1.05 0.019 1.05 0.017 Note measurements at a separation X of 8 and X=1024 (and values between 8 and 1024 not shown) are essentially identical Measurements at 7 (not shown) are higher than that at 8 (except for Red Hat which shows essentially no enhancement at X<8) As effects due to co-location of thread variables in a 64 byte cache line, align the array with cache boundaries Parallel Generative Topographic Mapping GTM Reduce dimensionality preserving topology and perhaps distances Here project to 2D 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 PCA GTM Linear PCA v. nonlinear GTM on 6 Gaussians in 3D PCA is Principal Component Analysis GTM Projection of 2 clusters of 335 compounds in 155 SALSA dimensions “Main Thread” and Memory M MPI/CCR/DSS From other nodes MPI/CCR/DSS From other nodes 0 m0 1 m1 2 m2 3 m3 4 m4 5 m5 6 m6 7 m7 Subsidiary threads t with memory mt 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) SALSA 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, Bourgain, Quadratic Programming …. HMM, SVM …. User interface: GIS (Web map Service) or equivalent SALSA Average run time (microseconds) 350 DSS Service Measurements 300 250 200 150 100 50 0 1 10 100 1000 10000 Round trips Measurements of Axis 2 shows about 500 microseconds – DSS is 10 times better 20 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# (PLASMA from UTenn) Access linear algebra services in a different language? Need equivalent of Intel C Math Libraries for C# (vector arithmetic – level 1 BLAS) 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 Clustering with pairwise distances but no vectorspaces Bourgain Random Projection for metric embedding MDS Dimensional Scaling with EM-like SMACOF and deterministicannealing Support use of Newton’s Method (Marquardt’s method) as EM alternative Later HMM and SVM SALSA