Enterprise. Breadth-First Graph Traversal on GPUs. November 19th, 2015
|
|
- Luke Heath
- 5 years ago
- Views:
Transcription
1 Enterprise Breadth-First Graph Traversal on GPUs Hang Liu H. Howie Huang November 9th, 5
2 Graph is Ubiquitous
3 Breadth-First Search (BFS) is Important Wide Range of Applications Single Source Shortest Path (SSSP) Connectivity Detection Distance Oracle Reachability Problem Centrality Problems, e.g., Betweenness & Closeness Centralities
4 Graphics Processing Unit (GPU) Instruction Warp Cache Schedulers SMX SMX SMX n GPU Memory Hierarchy: core core core Register core core core core core core File core core core core core core L cache (KB), ~ cycles L cache (MB), ~ cycles Interconnect Network Shared Memory (L Cache) Global memory (GB), ~ cycles L Cache Thread Granularity: Thread -> Warp -> Block -> Grid Global Memory Threads ~5 Threads
5 Enterprise Innovations Streamlined GPU Thread Scheduling GPU Workload Balancing Hub Vertex based Optimization Rank No. in Graph5 with two GPUs No. in Green Graph5 Small Data Category for the last two year 5
6 Top-Down BFS 5 7 FQ Atomic operation NFQ Frontier Queue 9 SA F U U F U U U U U Vertex ID Status Array NSA F U U U F U U Vertex ID Status Array (SA) needs to assign threads to non-frontiers
7 Challenge #: Putting GPU Threads to Good Use 8 Frontier Percentage (%) FB FR HW KR KR KR KR KR LJ OR PK RM TW WK Average frontier ratio per level for all graphs is very low: ~ 9%. Need a more efficient way to use GPU threads 7
8 Bottom-Up BFS Level 9 Bottom-up: SA F F F F F Early Termination NSA F F From unvisited to visited Reduce workload by early termination Decide when to switch heuristically! 8
9 Technique #: Streamlined GPU Thread Scheduling Atomic Op Frontier Queue Enterprise Status Array Compact 9
10 Streamlined GPU Thread Scheduling Top-Down Workflow Thread Thread 5 SA F U U F U U U U U Thread Bin NFQ Current Level Next Level 7 Follow-up traversal Frontier Order Matters!
11 Streamlined GPU Thread Scheduling Direction-Switching Workflow Thread Thread 5 SA F F F F F Thread Bin NFQ Current Level Next Level 7 Follow-up traversal 5 8 9
12 Challenge #: Balancing Workload Between GPU Threads Out degree (log) out degree = 5 out degree =....8 Percentile of vertices Gowalla Out degree (log) out degree = 5 out degree =....8 Percentile of vertices Orkut Various graphs have different distribution of out-degrees Gowalla: 87% of vertices have less than edges, 99.5% have less than 5 edges Not every frontier is created equal.
13 Technique #: GPU Workload Balancing Status Array FQ Generation / Classification Frontier Queues Out-degree < F F F F (, 5) (5, 55) SmallQueue MiddleQueue LargeQueue ExtremeQueue Thread Warp CTA Grid Out-degree>55 Multiple Expansion / Inspections thread threads 5 threads 5,5 threads Two Steps: Classify frontiers when generate FQ from SA Assign different amount of threads for different frontiers
14 Facebook Execution Timeline CTA kernel 9ms CTA kernel. ms (a) Status array 9 ms 7 ms (b)streamlined GPU threads scheduling 8.5 ms FQ generation CTA kernel.5 ms Warp kernel Thread kernel 7.8 ms.5 ms 7 ms 5 (c) GPU workload balancing
15 Challenge #: Making Bottom-Up BFS GPU-Aware Bottom-up BFS: Direction-switching level is decided heuristically, where Large portion of status array is accessed CPUs have large LLC (e.g., 5MB Xeon-E5) GPUs have small cache/shared memory KB per SMX, but Manually controllable Have developed graph-ware, software controlled caching strategy 5
16 Challenge #: Making Bottom-up BFS GPU-aware (Cont'd) CDF of total edges.8... CDF of total edges.8... YouTube Kron-- Wiki-talk....8 Percentile of vertices Percentile of vertices Small amount of hub vertices contains considerable amount of edges YouTube: (.%) vertices à % edges Kron--: 77 (.5%) vertices à % edges Wiki-Talk: 9 (.%) vertices à % edges Hub vertices are super important in bottom-up BFS
17 Technique #: Graph-Aware, Software Controlled GPU Cache FQ s neighbor:, 5 and. s neighbor: 5 HubCache 7 Miss SA Vertex ID 5 F 7 F Steps: 5 8 Vertex ID of just visited Hub Vertex in shared mem. 9 Load frontier s neighbors in-core Check Neighbor ID == Cached Vertex ID? 7
18 Evaluation Hardware: C7 and K are from our own cluster M9 and K are from Keeneland and Stampede of XSEDE Metrics GTEPS: billion traversed edges per second Software g++..7, CUDA 5. NVIDIA profiler: nvprof, nvvp. Compilation flag: -O All results are reported with average of runs 8
19 Graph Datasets Edge Count (Million) 9 KR KR KR KR KR FR RM OR FB HW LJ TW PK WK Vertex Count (Million) 9
20 Different Optimizations TEPS (bilion, log scale) BaseLine (BL) BL+Thread Scheduling (TS) BL+TS+Workload Balance (WB) BL+TS+WB+HubCaching (HC) FB FR HW KR KR KR KR KR LJ OR PK RM TW WK TS improves x to 7.5x WB further increases x HC further improves upto 5% Overall Speedup: by.x (KR) to 5.5x (TW)
21 Scalability Weak-vertex scale Weak-edge scale Strong scalability TEPS (billion) GPU count
22 GPU Counter Analysis Power (W) 9 8 BL BL+TS BL+TS+WB BL+TS+WB+HC 7 FB FR HW LJ OR PK TW WK KR Power saving 8W -> 77W Contribution distribution: TS: W WB: W HC: W
23 Conclusion & Future Work Techniques Streamlined GPU Thread Scheduling GPU Thread Workload Balancing Hub Vertex Based Optimization Possible extensions Different Workload Balancing Heuristics Theoretical Support of Direction-Switching Based on Hub Vertex
24 Acknowledgements
25 Thank You {asherliu,
Enterprise: Breadth-First Graph Traversal on GPUs
Enterprise: Breadth-First Graph Traversal on GPUs Hang Liu H. Howie Huang Department of Electrical and Computer Engineering George Washington University ABSTRACT The Breadth-First Search (BFS) algorithm
More informationibfs: Concurrent Breadth-First Search on GPUs
ibfs: Concurrent Breadth-First Search on GPUs Hang Liu H. Howie Huang Yang Hu Department of Electrical and Computer Engineering George Washington University {asherliu, howie, huyang}@gwu.edu ABSTRACT Breadth-First
More informationHigh-Performance Graph Primitives on the GPU: Design and Implementation of Gunrock
High-Performance Graph Primitives on the GPU: Design and Implementation of Gunrock Yangzihao Wang University of California, Davis yzhwang@ucdavis.edu March 24, 2014 Yangzihao Wang (yzhwang@ucdavis.edu)
More informationTanuj Kr Aasawat, Tahsin Reza, Matei Ripeanu Networked Systems Laboratory (NetSysLab) University of British Columbia
How well do CPU, GPU and Hybrid Graph Processing Frameworks Perform? Tanuj Kr Aasawat, Tahsin Reza, Matei Ripeanu Networked Systems Laboratory (NetSysLab) University of British Columbia Networked Systems
More informationGPU Sparse Graph Traversal
GPU Sparse Graph Traversal Duane Merrill (NVIDIA) Michael Garland (NVIDIA) Andrew Grimshaw (Univ. of Virginia) UNIVERSITY of VIRGINIA Breadth-first search (BFS) 1. Pick a source node 2. Rank every vertex
More informationTowards Performance and Scalability Analysis of Distributed Memory Programs on Large-Scale Clusters
Towards Performance and Scalability Analysis of Distributed Memory Programs on Large-Scale Clusters 1 University of California, Santa Barbara, 2 Hewlett Packard Labs, and 3 Hewlett Packard Enterprise 1
More informationGPU Performance Nuggets
GPU Performance Nuggets Simon Garcia de Gonzalo & Carl Pearson PhD Students, IMPACT Research Group Advised by Professor Wen-mei Hwu Jun. 15, 2016 grcdgnz2@illinois.edu pearson@illinois.edu GPU Performance
More informationScalable GPU Graph Traversal!
Scalable GPU Graph Traversal Duane Merrill, Michael Garland, and Andrew Grimshaw PPoPP '12 Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming Benwen Zhang
More informationCoordinating More Than 3 Million CUDA Threads for Social Network Analysis. Adam McLaughlin
Coordinating More Than 3 Million CUDA Threads for Social Network Analysis Adam McLaughlin Applications of interest Computational biology Social network analysis Urban planning Epidemiology Hardware verification
More informationGPU Sparse Graph Traversal. Duane Merrill
GPU Sparse Graph Traversal Duane Merrill Breadth-first search of graphs (BFS) 1. Pick a source node 2. Rank every vertex by the length of shortest path from source Or label every vertex by its predecessor
More informationarxiv: v1 [cs.dc] 10 Dec 2018
SIMD-X: Programming and Processing of Graph Algorithms on GPUs arxiv:8.04070v [cs.dc] 0 Dec 08 Hang Liu University of Massachusetts Lowell Abstract With high computation power and memory bandwidth, graphics
More informationn N c CIni.o ewsrg.au
@NCInews NCI and Raijin National Computational Infrastructure 2 Our Partners General purpose, highly parallel processors High FLOPs/watt and FLOPs/$ Unit of execution Kernel Separate memory subsystem GPGPU
More informationCUDA PROGRAMMING MODEL Chaithanya Gadiyam Swapnil S Jadhav
CUDA PROGRAMMING MODEL Chaithanya Gadiyam Swapnil S Jadhav CMPE655 - Multiple Processor Systems Fall 2015 Rochester Institute of Technology Contents What is GPGPU? What s the need? CUDA-Capable GPU Architecture
More informationS WHAT THE PROFILER IS TELLING YOU: OPTIMIZING GPU KERNELS. Jakob Progsch, Mathias Wagner GTC 2018
S8630 - WHAT THE PROFILER IS TELLING YOU: OPTIMIZING GPU KERNELS Jakob Progsch, Mathias Wagner GTC 2018 1. Know your hardware BEFORE YOU START What are the target machines, how many nodes? Machine-specific
More informationDNA Interaction Network
Social Network Web Network Social Network DNA Interaction Network Follow Network User-Product Network Nonuniform network comm costs Contentiousness of the memory subsystems Nonuniform comp requirement
More informationImplementation of BFS on shared memory (CPU / GPU)
Kolganov A.S., MSU The BFS algorithm Graph500 && GGraph500 Implementation of BFS on shared memory (CPU / GPU) Predicted scalability 2 The BFS algorithm Graph500 && GGraph500 Implementation of BFS on shared
More informationKartik Lakhotia, Rajgopal Kannan, Viktor Prasanna USENIX ATC 18
Accelerating PageRank using Partition-Centric Processing Kartik Lakhotia, Rajgopal Kannan, Viktor Prasanna USENIX ATC 18 Outline Introduction Partition-centric Processing Methodology Analytical Evaluation
More informationIdentifying Performance Limiters Paulius Micikevicius NVIDIA August 23, 2011
Identifying Performance Limiters Paulius Micikevicius NVIDIA August 23, 2011 Performance Optimization Process Use appropriate performance metric for each kernel For example, Gflops/s don t make sense for
More informationGraph Partitioning for Scalable Distributed Graph Computations
Graph Partitioning for Scalable Distributed Graph Computations Aydın Buluç ABuluc@lbl.gov Kamesh Madduri madduri@cse.psu.edu 10 th DIMACS Implementation Challenge, Graph Partitioning and Graph Clustering
More informationNVGRAPH,FIREHOSE,PAGERANK GPU ACCELERATED ANALYTICS NOV Joe Eaton Ph.D.
NVGRAPH,FIREHOSE,PAGERANK GPU ACCELERATED ANALYTICS NOV 2016 Joe Eaton Ph.D. Agenda Accelerated Computing nvgraph New Features Coming Soon Dynamic Graphs GraphBLAS 2 ACCELERATED COMPUTING 10x Performance
More informationPortland State University ECE 588/688. Graphics Processors
Portland State University ECE 588/688 Graphics Processors Copyright by Alaa Alameldeen 2018 Why Graphics Processors? Graphics programs have different characteristics from general purpose programs Highly
More informationOn Fast Parallel Detection of Strongly Connected Components (SCC) in Small-World Graphs
On Fast Parallel Detection of Strongly Connected Components (SCC) in Small-World Graphs Sungpack Hong 2, Nicole C. Rodia 1, and Kunle Olukotun 1 1 Pervasive Parallelism Laboratory, Stanford University
More informationRESOLVING FALSE DEPENDENCE ON SHARED MEMORY. Patric Zhao
RESOLVING FALSE DEPENDENCE ON SHARED MEMORY Patric Zhao patricz@nvidia.com Agenda Background Programming Skeleton by Shared Memory False Dependence Issue Solutions to a real case Conclusions 1.Background
More informationGPU/CPU Heterogeneous Work Partitioning Riya Savla (rds), Ridhi Surana (rsurana), Jordan Tick (jrtick) Computer Architecture, Spring 18
ABSTRACT GPU/CPU Heterogeneous Work Partitioning Riya Savla (rds), Ridhi Surana (rsurana), Jordan Tick (jrtick) 15-740 Computer Architecture, Spring 18 With the death of Moore's Law, programmers can no
More informationPerformance Characterization, Prediction, and Optimization for Heterogeneous Systems with Multi-Level Memory Interference
The 2017 IEEE International Symposium on Workload Characterization Performance Characterization, Prediction, and Optimization for Heterogeneous Systems with Multi-Level Memory Interference Shin-Ying Lee
More informationCUDA. Matthew Joyner, Jeremy Williams
CUDA Matthew Joyner, Jeremy Williams Agenda What is CUDA? CUDA GPU Architecture CPU/GPU Communication Coding in CUDA Use cases of CUDA Comparison to OpenCL What is CUDA? What is CUDA? CUDA is a parallel
More informationA New Parallel Algorithm for Connected Components in Dynamic Graphs. Robert McColl Oded Green David Bader
A New Parallel Algorithm for Connected Components in Dynamic Graphs Robert McColl Oded Green David Bader Overview The Problem Target Datasets Prior Work Parent-Neighbor Subgraph Results Conclusions Problem
More informationEFFICIENT BREADTH FIRST SEARCH ON MULTI-GPU SYSTEMS USING GPU-CENTRIC OPENSHMEM
EFFICIENT BREADTH FIRST SEARCH ON MULTI-GPU SYSTEMS USING GPU-CENTRIC OPENSHMEM Sreeram Potluri, Anshuman Goswami NVIDIA Manjunath Gorentla Venkata, Neena Imam - ORNL SCOPE OF THE WORK Reliance on CPU
More informationA Comparative Study on Exact Triangle Counting Algorithms on the GPU
A Comparative Study on Exact Triangle Counting Algorithms on the GPU Leyuan Wang, Yangzihao Wang, Carl Yang, John D. Owens University of California, Davis, CA, USA 31 st May 2016 L. Wang, Y. Wang, C. Yang,
More informationGraph traversal and BFS
Graph traversal and BFS Fundamental building block Graph traversal is part of many important tasks Connected components Tree/Cycle detection Articulation vertex finding Real-world applications Peer-to-peer
More informationMulti Agent Navigation on GPU. Avi Bleiweiss
Multi Agent Navigation on GPU Avi Bleiweiss Reasoning Explicit Implicit Script, storytelling State machine, serial Compute intensive Fits SIMT architecture well Navigation planning Collision avoidance
More informationChallenges in large-scale graph processing on HPC platforms and the Graph500 benchmark. by Nkemdirim Dockery
Challenges in large-scale graph processing on HPC platforms and the Graph500 benchmark by Nkemdirim Dockery High Performance Computing Workloads Core-memory sized Floating point intensive Well-structured
More informationSTREAMER: a Distributed Framework for Incremental Closeness Centrality
STREAMER: a Distributed Framework for Incremental Closeness Centrality Computa@on A. Erdem Sarıyüce 1,2, Erik Saule 4, Kamer Kaya 1, Ümit V. Çatalyürek 1,3 1 Department of Biomedical InformaBcs 2 Department
More informationTesla GPU Computing A Revolution in High Performance Computing
Tesla GPU Computing A Revolution in High Performance Computing Gernot Ziegler, Developer Technology (Compute) (Material by Thomas Bradley) Agenda Tesla GPU Computing CUDA Fermi What is GPU Computing? Introduction
More informationMattan Erez. The University of Texas at Austin
EE382V (17325): Principles in Computer Architecture Parallelism and Locality Fall 2007 Lecture 12 GPU Architecture (NVIDIA G80) Mattan Erez The University of Texas at Austin Outline 3D graphics recap and
More informationOn Smart Query Routing: For Distributed Graph Querying with Decoupled Storage
On Smart Query Routing: For Distributed Graph Querying with Decoupled Storage Arijit Khan Nanyang Technological University (NTU), Singapore Gustavo Segovia ETH Zurich, Switzerland Donald Kossmann Microsoft
More informationCUDA Experiences: Over-Optimization and Future HPC
CUDA Experiences: Over-Optimization and Future HPC Carl Pearson 1, Simon Garcia De Gonzalo 2 Ph.D. candidates, Electrical and Computer Engineering 1 / Computer Science 2, University of Illinois Urbana-Champaign
More informationLocality-Aware Software Throttling for Sparse Matrix Operation on GPUs
Locality-Aware Software Throttling for Sparse Matrix Operation on GPUs Yanhao Chen 1, Ari B. Hayes 1, Chi Zhang 2, Timothy Salmon 1, Eddy Z. Zhang 1 1. Rutgers University 2. University of Pittsburgh Sparse
More informationNVIDIA Fermi Architecture
Administrivia NVIDIA Fermi Architecture Patrick Cozzi University of Pennsylvania CIS 565 - Spring 2011 Assignment 4 grades returned Project checkpoint on Monday Post an update on your blog beforehand Poster
More informationCUDA Development Using NVIDIA Nsight, Eclipse Edition. David Goodwin
CUDA Development Using NVIDIA Nsight, Eclipse Edition David Goodwin NVIDIA Nsight Eclipse Edition CUDA Integrated Development Environment Project Management Edit Build Debug Profile SC'12 2 Powered By
More informationAdvanced and parallel architectures. Part B. Prof. A. Massini. June 13, Exercise 1a (3 points) Exercise 1b (3 points) Exercise 2 (8 points)
Advanced and parallel architectures Prof. A. Massini June 13, 2017 Part B Exercise 1a (3 points) Exercise 1b (3 points) Exercise 2 (8 points) Student s Name Exercise 3 (4 points) Exercise 4 (3 points)
More informationProfiling GPU Code. Jeremy Appleyard, February 2016
Profiling GPU Code Jeremy Appleyard, February 2016 What is Profiling? Measuring Performance Measuring application performance Usually the aim is to reduce runtime Simple profiling: How long does an operation
More informationData Placement Optimization in GPU Memory Hierarchy Using Predictive Modeling
Data Placement Optimization in GPU Memory Hierarchy Using Predictive Modeling Larisa Stoltzfus*, Murali Emani, Pei-Hung Lin, Chunhua Liao *University of Edinburgh (UK), Lawrence Livermore National Laboratory
More informationScalable and High Performance Betweenness Centrality on the GPU
Scalable and High Performance Betweenness Centrality on the GPU Adam McLaughlin School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta, Georgia 30332 0250 Adam27X@gatech.edu
More informationDuane Merrill (NVIDIA) Michael Garland (NVIDIA)
Duane Merrill (NVIDIA) Michael Garland (NVIDIA) Agenda Sparse graphs Breadth-first search (BFS) Maximal independent set (MIS) 1 1 0 1 1 1 3 1 3 1 5 10 6 9 8 7 3 4 BFS MIS Sparse graphs Graph G(V, E) where
More informationdavidklee.net gplus.to/kleegeek linked.com/a/davidaklee
@kleegeek davidklee.net gplus.to/kleegeek linked.com/a/davidaklee Specialties / Focus Areas / Passions: Performance Tuning & Troubleshooting Virtualization Cloud Enablement Infrastructure Architecture
More informationFalcon: Scaling IO Performance in Multi-SSD Volumes. The George Washington University
Falcon: Scaling IO Performance in Multi-SSD Volumes Pradeep Kumar H Howie Huang The George Washington University SSDs in Big Data Applications Recent trends advocate using many SSDs for higher throughput
More informationLecture 13: Memory Consistency. + a Course-So-Far Review. Parallel Computer Architecture and Programming CMU , Spring 2013
Lecture 13: Memory Consistency + a Course-So-Far Review Parallel Computer Architecture and Programming Today: what you should know Understand the motivation for relaxed consistency models Understand the
More informationCSCI 402: Computer Architectures. Parallel Processors (2) Fengguang Song Department of Computer & Information Science IUPUI.
CSCI 402: Computer Architectures Parallel Processors (2) Fengguang Song Department of Computer & Information Science IUPUI 6.6 - End Today s Contents GPU Cluster and its network topology The Roofline performance
More informationIntroduction to parallel Computing
Introduction to parallel Computing VI-SEEM Training Paschalis Paschalis Korosoglou Korosoglou (pkoro@.gr) (pkoro@.gr) Outline Serial vs Parallel programming Hardware trends Why HPC matters HPC Concepts
More informationSimple Parallel Biconnectivity Algorithms for Multicore Platforms
Simple Parallel Biconnectivity Algorithms for Multicore Platforms George M. Slota Kamesh Madduri The Pennsylvania State University HiPC 2014 December 17-20, 2014 Code, presentation available at graphanalysis.info
More informationCS GPU and GPGPU Programming Lecture 8+9: GPU Architecture 7+8. Markus Hadwiger, KAUST
CS 380 - GPU and GPGPU Programming Lecture 8+9: GPU Architecture 7+8 Markus Hadwiger, KAUST Reading Assignment #5 (until March 12) Read (required): Programming Massively Parallel Processors book, Chapter
More informationBreadth First Search on Cost efficient Multi GPU Systems
Breadth First Search on Cost efficient Multi Systems Takuji Mitsuishi Keio University 3 14 1 Hiyoshi, Yokohama, 223 8522, Japan mits@am.ics.keio.ac.jp Masaki Kan NEC Corporation 1753, Shimonumabe, Nakahara
More informationDynamic Thread Block Launch: A Lightweight Execution Mechanism to Support Irregular Applications on GPUs
Dynamic Thread Block Launch: A Lightweight Execution Mechanism to Support Irregular Applications on GPUs Jin Wang* Norm Rubin Albert Sidelnik Sudhakar Yalamanchili* *Georgia Institute of Technology NVIDIA
More informationOptimizing Energy Consumption and Parallel Performance for Static and Dynamic Betweenness Centrality using GPUs Adam McLaughlin, Jason Riedy, and
Optimizing Energy Consumption and Parallel Performance for Static and Dynamic Betweenness Centrality using GPUs Adam McLaughlin, Jason Riedy, and David A. Bader Motivation Real world graphs are challenging
More informationAutomatic Compiler-Based Optimization of Graph Analytics for the GPU. Sreepathi Pai The University of Texas at Austin. May 8, 2017 NVIDIA GTC
Automatic Compiler-Based Optimization of Graph Analytics for the GPU Sreepathi Pai The University of Texas at Austin May 8, 2017 NVIDIA GTC Parallel Graph Processing is not easy 299ms HD-BFS 84ms USA Road
More informationExploiting GPU Caches in Sparse Matrix Vector Multiplication. Yusuke Nagasaka Tokyo Institute of Technology
Exploiting GPU Caches in Sparse Matrix Vector Multiplication Yusuke Nagasaka Tokyo Institute of Technology Sparse Matrix Generated by FEM, being as the graph data Often require solving sparse linear equation
More informationEE382N (20): Computer Architecture - Parallelism and Locality Spring 2015 Lecture 09 GPUs (II) Mattan Erez. The University of Texas at Austin
EE382 (20): Computer Architecture - ism and Locality Spring 2015 Lecture 09 GPUs (II) Mattan Erez The University of Texas at Austin 1 Recap 2 Streaming model 1. Use many slimmed down cores to run in parallel
More informationTowards Efficient Graph Traversal using a Multi- GPU Cluster
Towards Efficient Graph Traversal using a Multi- GPU Cluster Hina Hameed Systems Research Lab, Department of Computer Science, FAST National University of Computer and Emerging Sciences Karachi, Pakistan
More informationNUMA-aware Graph-structured Analytics
NUMA-aware Graph-structured Analytics Kaiyuan Zhang, Rong Chen, Haibo Chen Institute of Parallel and Distributed Systems Shanghai Jiao Tong University, China Big Data Everywhere 00 Million Tweets/day 1.11
More informationCSE 599 I Accelerated Computing - Programming GPUS. Parallel Patterns: Graph Search
CSE 599 I Accelerated Computing - Programming GPUS Parallel Patterns: Graph Search Objective Study graph search as a prototypical graph-based algorithm Learn techniques to mitigate the memory-bandwidth-centric
More informationProfiling & Tuning Applications. CUDA Course István Reguly
Profiling & Tuning Applications CUDA Course István Reguly Introduction Why is my application running slow? Work it out on paper Instrument code Profile it NVIDIA Visual Profiler Works with CUDA, needs
More informationGPU Programming. Lecture 1: Introduction. Miaoqing Huang University of Arkansas 1 / 27
1 / 27 GPU Programming Lecture 1: Introduction Miaoqing Huang University of Arkansas 2 / 27 Outline Course Introduction GPUs as Parallel Computers Trend and Design Philosophies Programming and Execution
More informationCopyright 2017 Intel Corporation
Agenda Intel Xeon Scalable Platform Overview Architectural Enhancements 2 Platform Overview 3x16 PCIe* Gen3 2 or 3 Intel UPI 3x16 PCIe Gen3 Capabilities Details 10GbE Skylake-SP CPU OPA DMI Intel C620
More informationarxiv: v2 [cs.dc] 27 Mar 2015
Gunrock: A High-Performance Graph Processing Library on the GPU Yangzihao Wang, Andrew Davidson, Yuechao Pan, Yuduo Wu, Andy Riffel, John D. Owens University of California, Davis {yzhwang, aaldavidson,
More informationVisual Analysis of Lagrangian Particle Data from Combustion Simulations
Visual Analysis of Lagrangian Particle Data from Combustion Simulations Hongfeng Yu Sandia National Laboratories, CA Ultrascale Visualization Workshop, SC11 Nov 13 2011, Seattle, WA Joint work with Jishang
More informationMulti-GPU Graph Analytics
Multi-GPU Graph Analytics Yuechao Pan, Yangzihao Wang, Yuduo Wu, Carl Yang, and John D. Owens University of California, Davis Email: {ychpan, yzhwang, yudwu, ctcyang, jowens@ucdavis.edu 1) Our mgpu graph
More informationIncreasing Performance for PowerCenter Sessions that Use Partitions
Increasing Performance for PowerCenter Sessions that Use Partitions 1993-2015 Informatica LLC. No part of this document may be reproduced or transmitted in any form, by any means (electronic, photocopying,
More informationGunrock: A Fast and Programmable Multi- GPU Graph Processing Library
Gunrock: A Fast and Programmable Multi- GPU Graph Processing Library Yangzihao Wang and Yuechao Pan with Andrew Davidson, Yuduo Wu, Carl Yang, Leyuan Wang, Andy Riffel and John D. Owens University of California,
More informationRUNTIME SUPPORT FOR ADAPTIVE SPATIAL PARTITIONING AND INTER-KERNEL COMMUNICATION ON GPUS
RUNTIME SUPPORT FOR ADAPTIVE SPATIAL PARTITIONING AND INTER-KERNEL COMMUNICATION ON GPUS Yash Ukidave, Perhaad Mistry, Charu Kalra, Dana Schaa and David Kaeli Department of Electrical and Computer Engineering
More informationCUDA Optimizations WS Intelligent Robotics Seminar. Universität Hamburg WS Intelligent Robotics Seminar Praveen Kulkarni
CUDA Optimizations WS 2014-15 Intelligent Robotics Seminar 1 Table of content 1 Background information 2 Optimizations 3 Summary 2 Table of content 1 Background information 2 Optimizations 3 Summary 3
More informationParallel Methods for Verifying the Consistency of Weakly-Ordered Architectures. Adam McLaughlin, Duane Merrill, Michael Garland, and David A.
Parallel Methods for Verifying the Consistency of Weakly-Ordered Architectures Adam McLaughlin, Duane Merrill, Michael Garland, and David A. Bader Challenges of Design Verification Contemporary hardware
More informationExploiting Inter-Warp Heterogeneity to Improve GPGPU Performance
Exploiting Inter-Warp Heterogeneity to Improve GPGPU Performance Rachata Ausavarungnirun Saugata Ghose, Onur Kayiran, Gabriel H. Loh Chita Das, Mahmut Kandemir, Onur Mutlu Overview of This Talk Problem:
More informationBillion-Scale Graph Analytics
Billion-Scale Graph Analytics Toyotaro Suzumura, Koji Ueno, Charuwat Houngkaew, Masaru Watanabe, Hidefumi Ogata, Miyuru Dayarathna, ScaleGraph Team Tokyo Institute of Technology / JST CREST IBM Research
More informationMulti-GPU Graph Analytics
2017 IEEE International Parallel and Distributed Processing Symposium Multi-GPU Graph Analytics Yuechao Pan, Yangzihao Wang, Yuduo Wu, Carl Yang, and John D. Owens University of California, Davis Email:
More informationHARNESSING IRREGULAR PARALLELISM: A CASE STUDY ON UNSTRUCTURED MESHES. Cliff Woolley, NVIDIA
HARNESSING IRREGULAR PARALLELISM: A CASE STUDY ON UNSTRUCTURED MESHES Cliff Woolley, NVIDIA PREFACE This talk presents a case study of extracting parallelism in the UMT2013 benchmark for 3D unstructured-mesh
More informationEE382N (20): Computer Architecture - Parallelism and Locality Fall 2011 Lecture 18 GPUs (III)
EE382 (20): Computer Architecture - Parallelism and Locality Fall 2011 Lecture 18 GPUs (III) Mattan Erez The University of Texas at Austin EE382: Principles of Computer Architecture, Fall 2011 -- Lecture
More informationHiPANQ Overview of NVIDIA GPU Architecture and Introduction to CUDA/OpenCL Programming, and Parallelization of LDPC codes.
HiPANQ Overview of NVIDIA GPU Architecture and Introduction to CUDA/OpenCL Programming, and Parallelization of LDPC codes Ian Glendinning Outline NVIDIA GPU cards CUDA & OpenCL Parallel Implementation
More informationPersistent RNNs. (stashing recurrent weights on-chip) Gregory Diamos. April 7, Baidu SVAIL
(stashing recurrent weights on-chip) Baidu SVAIL April 7, 2016 SVAIL Think hard AI. Goal Develop hard AI technologies that impact 100 million users. Deep Learning at SVAIL 100 GFLOP/s 1 laptop 6 TFLOP/s
More information7 DAYS AND 8 NIGHTS WITH THE CARMA DEV KIT
7 DAYS AND 8 NIGHTS WITH THE CARMA DEV KIT Draft Printed for SECO Murex S.A.S 2012 all rights reserved Murex Analytics Only global vendor of trading, risk management and processing systems focusing also
More informationGeneral Purpose GPU Computing in Partial Wave Analysis
JLAB at 12 GeV - INT General Purpose GPU Computing in Partial Wave Analysis Hrayr Matevosyan - NTC, Indiana University November 18/2009 COmputationAL Challenges IN PWA Rapid Increase in Available Data
More informationBoosting the Performance of FPGA-based Graph Processor using Hybrid Memory Cube: A Case for Breadth First Search
Boosting the Performance of FPGA-based Graph Processor using Hybrid Memory Cube: A Case for Breadth First Search Jialiang Zhang, Soroosh Khoram and Jing Li 1 Outline Background Big graph analytics Hybrid
More informationFast Parallel Detection of Strongly Connected Components (SCC) in Small-World Graphs
Fast Parallel Detection of Strongly Connected Components (SCC) in Small-World Graphs Sungpack Hong 2, Nicole C. Rodia 1, and Kunle Olukotun 1 1 Pervasive Parallelism Laboratory, Stanford University 2 Oracle
More informationS8873 GBM INFERENCING ON GPU. Shankara Rao Thejaswi Nanditale, Vinay Deshpande
S8873 GBM INFERENCING ON GPU Shankara Rao Thejaswi Nanditale, Vinay Deshpande Introduction AGENDA Objective Experimental Results Implementation Details Conclusion 2 INTRODUCTION 3 BOOSTING What is it?
More informationLecture 8: GPU Programming. CSE599G1: Spring 2017
Lecture 8: GPU Programming CSE599G1: Spring 2017 Announcements Project proposal due on Thursday (4/28) 5pm. Assignment 2 will be out today, due in two weeks. Implement GPU kernels and use cublas library
More informationSnowpack: Efficient Parameter Choice for GPU Kernels via Static Analysis and Statistical Prediction ScalA 17, Denver, CO, USA, November 13, 2017
Snowpack: Efficient Parameter Choice for GPU Kernels via Static Analysis and Statistical Prediction ScalA 17, Denver, CO, USA, November 13, 2017 Ignacio Laguna Ranvijay Singh, Paul Wood, Ravi Gupta, Saurabh
More informationCUDA Tools for Debugging and Profiling. Jiri Kraus (NVIDIA)
Mitglied der Helmholtz-Gemeinschaft CUDA Tools for Debugging and Profiling Jiri Kraus (NVIDIA) GPU Programming with CUDA@Jülich Supercomputing Centre Jülich 25-27 April 2016 What you will learn How to
More informationNew Approach for Graph Algorithms on GPU using CUDA
New Approach for Graph Algorithms on GPU using CUDA 1 Gunjan Singla, 2 Amrita Tiwari, 3 Dhirendra Pratap Singh Department of Computer Science and Engineering Maulana Azad National Institute of Technology
More informationExtreme-scale Graph Analysis on Blue Waters
Extreme-scale Graph Analysis on Blue Waters 2016 Blue Waters Symposium George M. Slota 1,2, Siva Rajamanickam 1, Kamesh Madduri 2, Karen Devine 1 1 Sandia National Laboratories a 2 The Pennsylvania State
More informationMaximizing Face Detection Performance
Maximizing Face Detection Performance Paulius Micikevicius Developer Technology Engineer, NVIDIA GTC 2015 1 Outline Very brief review of cascaded-classifiers Parallelization choices Reducing the amount
More informationGAIL The Graph Algorithm Iron Law
GAIL The Graph Algorithm Iron Law Scott Beamer, Krste Asanović, David Patterson GAP Berkeley Electrical Engineering & Computer Sciences gap.cs.berkeley.edu Graph Applications Social Network Analysis Recommendations
More informationCSCI-GA Graphics Processing Units (GPUs): Architecture and Programming Lecture 2: Hardware Perspective of GPUs
CSCI-GA.3033-004 Graphics Processing Units (GPUs): Architecture and Programming Lecture 2: Hardware Perspective of GPUs Mohamed Zahran (aka Z) mzahran@cs.nyu.edu http://www.mzahran.com History of GPUs
More informationUsing GPUs to Accelerate Synthetic Aperture Sonar Imaging via Backpropagation
Using GPUs to Accelerate Synthetic Aperture Sonar Imaging via Backpropagation GPU Technology Conference 2012 May 15, 2012 Thomas M. Benson, Daniel P. Campbell, Daniel A. Cook thomas.benson@gtri.gatech.edu
More informationPerformance analysis of -stepping algorithm on CPU and GPU
Performance analysis of -stepping algorithm on CPU and GPU Dmitry Lesnikov 1 dslesnikov@gmail.com Mikhail Chernoskutov 1,2 mach@imm.uran.ru 1 Ural Federal University (Yekaterinburg, Russia) 2 Krasovskii
More informationGPU Fundamentals Jeff Larkin November 14, 2016
GPU Fundamentals Jeff Larkin , November 4, 206 Who Am I? 2002 B.S. Computer Science Furman University 2005 M.S. Computer Science UT Knoxville 2002 Graduate Teaching Assistant 2005 Graduate
More informationNext-Generation Cloud Platform
Next-Generation Cloud Platform Jangwoo Kim Jun 24, 2013 E-mail: jangwoo@postech.ac.kr High Performance Computing Lab Department of Computer Science & Engineering Pohang University of Science and Technology
More informationThe Stampede is Coming: A New Petascale Resource for the Open Science Community
The Stampede is Coming: A New Petascale Resource for the Open Science Community Jay Boisseau Texas Advanced Computing Center boisseau@tacc.utexas.edu Stampede: Solicitation US National Science Foundation
More informationSharePoint 2010 Technical Case Study: Microsoft SharePoint Server 2010 Social Environment
SharePoint 2010 Technical Case Study: Microsoft SharePoint Server 2010 Social Environment This document is provided as-is. Information and views expressed in this document, including URL and other Internet
More informationGPU Concurrency: Weak Behaviours and Programming Assumptions
GPU Concurrency: Weak Behaviours and Programming Assumptions Jyh-Jing Hwang, Yiren(Max) Lu 03/02/2017 Outline 1. Introduction 2. Weak behaviors examples 3. Test methodology 4. Proposed memory model 5.
More informationParallel graph traversal for FPGA
LETTER IEICE Electronics Express, Vol.11, No.7, 1 6 Parallel graph traversal for FPGA Shice Ni a), Yong Dou, Dan Zou, Rongchun Li, and Qiang Wang National Laboratory for Parallel and Distributed Processing,
More information