Data Processing on Emerging Hardware
|
|
- Randell Matthews
- 5 years ago
- Views:
Transcription
1 Data Processing on Emerging Hardware Gustavo Alonso Systems Group Department of Computer Science ETH Zurich, Switzerland 3 rd International Summer School on Big Data, Munich, Germany, 2017
2 Systems Group 6 faculty ~40 PhD ~12 postdocs Researching all aspects of system architecture, sw and hw
3 Take home message
4 Slide courtesy of Torsten Hoefler (Systems Group, ETH Zürich)
5 In a nutshell Hardware going crazy More transistors no longer means faster machines but more specialized Big data is the killer app Specialized hardware to support data processing Great opportunity
6 Future programming systems must allow the programmer to express their code in a high-level, target-independent manner and optimize the target-dependent decisions DATABASES of mapping available parallelism in time and space. Bill Dally, NVIDIA Chief Scientist (Keynote at HiPEAC 15)
7 Hardware as a problem
8 Joins in main memory, multicore Kim et al. PVLDB 09 Blanas et al. SIGMOD 11 Albutiu et al. PVLDB 12 Hash joins faster than sort merge joins Will change when SIMD wide enough Showed tuning to multicore, SIMD No need for tuning a has join No need for careful partitioning Hardware hides complexity Sort merge join better already No need to use SIMD
9 Join with small build table Workload A: 16M 256M, 16-byte tuples (256MiB 4096MiB) 1. Effective on-chip threading 2. Efficient sync. primitives (ldstub) 3. Larger page size
10 Join with large build table Workload B: Equal-sized tables, (977MiB 977MiB, 8-byte tuples) 50 cy/tpl 3.5X 14 cy/tpl 10
11 This study demonstrates that in main memory, where no time-consuming I/O can mask variations in implementation, implementation details are very important; the implementations of the data structures and algorithms are more important for the performance than the data structures and algorithms themselves. (Sidlauskas & Jensen, PVLDB 14, commenting on Sowell et al., PVLDB 13)
12 Scalability Workload B: Equal-sized tables, 977MiB 977MiB, 8-byte tuples 196 M/sec 14 cy/tpl 3.5X 55 M/sec Intel Sandy Bridge 2.7GHz, 8 cores/16 threads Fastest reported join performance to date! Balkesen et al., ICDE 2013 Balkesen et al., PVLDB 2014 Balkesen et al., IEEE TKDE 2015
13 Specialization as a solution
14 Airline reservations (Amadeus) Load SLAs Features High peak workloads High update rate spikes Stringent response time requirements Extensibility over time Predictability Accurate provisioning
15 CRESCANDO Scan Thread Scan Thread Input Queue (Operations) Split Scan Thread Scan Thread Merge Output Queue (Result Tuples)... Input Queue (Operations) Scan Thread Output Queue (Result Tuples) External Clients... Crescando Aggregation Layers Replication Groups... Unterbrunner et al, PVLDB 09
16 Specialized hardware as the way forward
17 If the data moves, do it efficiently Bumps in the wire(s)
18 IBEX (Woods, PVLDB 14; Woods, PVLDB 11) On programming FPGAs: we had to develop our own SATA 2 driver from the SATA specs!
19 A wide range of algorithms Sorting networks Selection, projection Group by, join Frequent item Skyline Complex Event Detection Hashing Helped us to learn what works, what does not work, and, most importantly, that new algorithms and data structures are needed to exploit an FPGA
20 Near-Data processing The goal is to be able to do this at all levels: Smart storage On the network switch (SDN like) On the network card (smart NIC) On the PCI express bus On the memory bus (active memory) On the memory (near data processing) Every element in the system (a node, a computer rack, a cluster) should be a processing component
21 Integrated accelerators From Oracle M7 documentation
22 Do not replace, enhance Help the CPU to do what it does not do well
23 Text search in databases Istvan et al, FCCM 16 INTEL HARP: This is an experimental system provided by Intel any results presented are generated using preproduction hardware and software, and may not reflect the performance of production or future systems.
24 100% processing on FPGA
25 Hybrid Processing CPU/FPGA
26 Inside a real database: DoppioDB Sidler et al., SIGMOD 17 Owaida et al., FCCM 17
27 Accelerating real engines
28 Huge potential for new functionality (Kara et al. FCCM 17 => demo at SIGMOD 17) Stochastic Gradient Descent => machine learning on the FPGA
29 Requires rethinking the original system Database suboperators (started from work with Oracle Labs on a project called RAPID): Accelerate the important parts of an operators, do not try to accelerate operators or entire query plans Database partitioning Kara&Giceva, SIGMOD 17
30 Integration of Partitioned Hash Joins QPI QPI Endpoint 96GB Main Memory ~30 GB/s 6.5 GB/s Mem. Controller QPI Caches QPI Endpoint R S Pointer Pointer 64B Cache Line Partitioner FPGA 64B Cache Line Intel Xeon CPU Accelerator Counts R Counts S Target Architecture: Intel Xeon+FPGA Altera Stratix V Counts R Partitioned R Padding Counts S Core 0 Core 1... Core 0 Core 1... Core 0 Core 1 Core 0 Core 1 Core 5 Core 6... Kaan et al. SIGMOD 2017 Partitioned S Memory Core 0 Core 1... Core 2 Core 3 Core 4 CPU Core 7 Core 8 Core 9
31 Plenty of opportunities to extend databases Many existing operators that today are not really integrated or available Spatial, time series, statistical operations, temporal,... Ability to deal with complex data types and formats Many new operators that significantly expand the scope of a DB Stochastic gradient descent Support Vector Machines Data mining and data cubes Model based machine learning (clustering, classification) Through the FPGA: gateway to a other machines (Catapult)
32 Disaggregated data center Efficient microservers [FPGAs as standalone nodes]
33 Exploiting the network 40 Mio tuples/relation/core 2x1024M Barthels et al., SIGMOD 15 Barthels et al., PVLDB 17
34 Consensus in a Box (Istvan et al, NSDI 16; Sidler, FPL 16) Xilinx VC709 Evaluation Board SW Clients / Other nodes SFP+ TCP FPGA Reads Other nodes Other nodes SFP+ SFP+ Direct Direct Networking Writes Atomic Broadcast Replicated key-value store SFP+ DRAM (8GB) 34
35 The system 3 FPGA cluster 10Gbps Switch Comm. over TCP/IP Clients X 12 Comm. over direct connections + Leader election + Recovery Drop-in replacement for memcached with Zookeeper s replication Standard tools for benchmarking (libmemcached) Simulating 100s of clients 35
36 Latency of puts in a KVS Direct connections ~3μs Consensus Memaslap (ixgbe) 15-35μs ~10μs TCP / 10Gbps Ethernet 36
37 Througput (consensus rounds/s) The benefit of specialization Specialized solutions x General purpose solutions FPGA (Direct) FPGA (TCP) DARE* (Infiniband) Libpaxos (TCP) Etcd (TCP) Zookeeper (TCP) Consensus latency (us) [1] Dragojevic et al. FaRM: Fast Remote Memory. In NSDI 14. [2] Poke et al. DARE: High-Performance State Machine Replication on RDMA Networks. In HPDC 15. *=We extrapolated from the 5 node setup for a 3 node setup. 37
38 Today: Caribou (Istvan et al. PVLDB 2017) Everything mentioned in the talk can be done on top of this key vale store without affecting performance: Selection, projection Regular expression matching String search Compression/Decompression Next steps: Exploring Catapult (Microsoft) Implementing RoCE, active RDMA In-network data processing
39 Our research agenda: Near Data processing The goal is to be able to process data at all levels and extend database functionality: Smart storage On the network switch (SDN like) On the network card (smart NIC) On the PCI express bus On the memory bus (active memory) On the memory (near data processing) Every element in the system (memory, bus, disk, cache, network card, network switch,...) should be a processing component
Reconfigurable hardware for big data. Gustavo Alonso Systems Group Department of Computer Science ETH Zurich, Switzerland
Reconfigurable hardware for big data Gustavo Alonso Systems Group Department of Computer Science ETH Zurich, Switzerland www.systems.ethz.ch Systems Group 7 faculty ~40 PhD ~8 postdocs Researching all
More informationAccelerating Data Science. Gustavo Alonso Systems Group Department of Computer Science ETH Zurich, Switzerland
Accelerating Data Science Gustavo Alonso Systems Group Department of Computer Science ETH Zurich, Switzerland Data processing today: Appliances (large machines) Data Centers (many machines) Databases are
More informationInexpensive Coordination in Hardware
Consensus in a Box Inexpensive Coordination in Hardware Zsolt István, David Sidler, Gustavo Alonso, Marko Vukolic * Systems Group, Department of Computer Science, ETH Zurich * Consensus IBM in Research,
More informationPerformance in the Multicore Era
Performance in the Multicore Era Gustavo Alonso Systems Group -- ETH Zurich, Switzerland Systems Group Enterprise Computing Center Performance in the multicore era 2 BACKGROUND - SWISSBOX SwissBox: An
More informationCrazy little thing called hardware GUSTAVO ALONSO SYSTEMS GROUP DEPT. OF COMPUTER SCIENCE ETH ZURICH
Crazy little thing called hardware GUSTAVO ALONSO SYSTEMS GROUP DEPT. OF COMPUTER SCIENCE ETH ZURICH HTDC 2014 Systems Group = www.systems.ethz.ch Enterprise Computing Center = www.ecc.ethz.ch Hardware
More informationCaribou: Intelligent Distributed Storage
: Intelligent Distributed Storage Zsolt István, David Sidler, Gustavo Alonso Systems Group, Department of Computer Science, ETH Zurich 1 Rack-scale thinking In the Cloud ToR Switch Compute Compute + Provisioning
More informationDATABASES AND THE CLOUD. Gustavo Alonso Systems Group / ECC Dept. of Computer Science ETH Zürich, Switzerland
DATABASES AND THE CLOUD Gustavo Alonso Systems Group / ECC Dept. of Computer Science ETH Zürich, Switzerland AVALOQ Conference Zürich June 2011 Systems Group www.systems.ethz.ch Enterprise Computing Center
More informationCrescando: Predictable Performance for Unpredictable Workloads
Crescando: Predictable Performance for Unpredictable Workloads G. Alonso, D. Fauser, G. Giannikis, D. Kossmann, J. Meyer, P. Unterbrunner Amadeus S.A. ETH Zurich, Systems Group (Funded by Enterprise Computing
More informationMULTICORE IN DATA APPLIANCES. Gustavo Alonso Systems Group Dept. of Computer Science ETH Zürich, Switzerland
MULTICORE IN DATA APPLIANCES Gustavo Alonso Systems Group Dept. of Computer Science ETH Zürich, Switzerland SwissBox CREST Workshop March 2012 Systems Group = www.systems.ethz.ch Enterprise Computing Center
More informationProviding Multi-tenant Services with FPGAs: Case Study on a Key-Value Store
Zsolt István *, Gustavo Alonso, Ankit Singla Systems Group, Computer Science Dept., ETH Zürich * Now at IMDEA Software Institute, Madrid Providing Multi-tenant Services with FPGAs: Case Study on a Key-Value
More informationRack-scale Data Processing System
Rack-scale Data Processing System Jana Giceva, Darko Makreshanski, Claude Barthels, Alessandro Dovis, Gustavo Alonso Systems Group, Department of Computer Science, ETH Zurich Rack-scale Data Processing
More informationHash Joins for Multi-core CPUs. Benjamin Wagner
Hash Joins for Multi-core CPUs Benjamin Wagner Joins fundamental operator in query processing variety of different algorithms many papers publishing different results main question: is tuning to modern
More informationHighly Scalable, Non-RDMA NVMe Fabric. Bob Hansen,, VP System Architecture
A Cost Effective,, High g Performance,, Highly Scalable, Non-RDMA NVMe Fabric Bob Hansen,, VP System Architecture bob@apeirondata.com Storage Developers Conference, September 2015 Agenda 3 rd Platform
More informationOptimized Distributed Data Sharing Substrate in Multi-Core Commodity Clusters: A Comprehensive Study with Applications
Optimized Distributed Data Sharing Substrate in Multi-Core Commodity Clusters: A Comprehensive Study with Applications K. Vaidyanathan, P. Lai, S. Narravula and D. K. Panda Network Based Computing Laboratory
More informationA Distributed Hash Table for Shared Memory
A Distributed Hash Table for Shared Memory Wytse Oortwijn Formal Methods and Tools, University of Twente August 31, 2015 Wytse Oortwijn (Formal Methods and Tools, AUniversity Distributed of Twente) Hash
More informationArchitecture of a Real-Time Operational DBMS
Architecture of a Real-Time Operational DBMS Srini V. Srinivasan Founder, Chief Development Officer Aerospike CMG India Keynote Thane December 3, 2016 [ CMGI Keynote, Thane, India. 2016 Aerospike Inc.
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 informationLegUp: Accelerating Memcached on Cloud FPGAs
0 LegUp: Accelerating Memcached on Cloud FPGAs Xilinx Developer Forum December 10, 2018 Andrew Canis & Ruolong Lian LegUp Computing Inc. 1 COMPUTE IS BECOMING SPECIALIZED 1 GPU Nvidia graphics cards are
More informationBe Fast, Cheap and in Control with SwitchKV. Xiaozhou Li
Be Fast, Cheap and in Control with SwitchKV Xiaozhou Li Goal: fast and cost-efficient key-value store Store, retrieve, manage key-value objects Get(key)/Put(key,value)/Delete(key) Target: cluster-level
More informationN V M e o v e r F a b r i c s -
N V M e o v e r F a b r i c s - H i g h p e r f o r m a n c e S S D s n e t w o r k e d f o r c o m p o s a b l e i n f r a s t r u c t u r e Rob Davis, VP Storage Technology, Mellanox OCP Evolution Server
More informationMain-Memory Databases 1 / 25
1 / 25 Motivation Hardware trends Huge main memory capacity with complex access characteristics (Caches, NUMA) Many-core CPUs SIMD support in CPUs New CPU features (HTM) Also: Graphic cards, FPGAs, low
More informationArchitecture-Conscious Database Systems
Architecture-Conscious Database Systems 2009 VLDB Summer School Shanghai Peter Boncz (CWI) Sources Thank You! l l l l Database Architectures for New Hardware VLDB 2004 tutorial, Anastassia Ailamaki Query
More informationCan Memory-Less Network Adapters Benefit Next-Generation InfiniBand Systems?
Can Memory-Less Network Adapters Benefit Next-Generation InfiniBand Systems? Sayantan Sur, Abhinav Vishnu, Hyun-Wook Jin, Wei Huang and D. K. Panda {surs, vishnu, jinhy, huanwei, panda}@cse.ohio-state.edu
More informationProgrammable NICs. Lecture 14, Computer Networks (198:552)
Programmable NICs Lecture 14, Computer Networks (198:552) Network Interface Cards (NICs) The physical interface between a machine and the wire Life of a transmitted packet Userspace application NIC Transport
More informationAccelerating Real-Time Big Data. Breaking the limitations of captive NVMe storage
Accelerating Real-Time Big Data Breaking the limitations of captive NVMe storage 18M IOPs in 2u Agenda Everything related to storage is changing! The 3rd Platform NVM Express architected for solid state
More informationArrakis: The Operating System is the Control Plane
Arrakis: The Operating System is the Control Plane Simon Peter, Jialin Li, Irene Zhang, Dan Ports, Doug Woos, Arvind Krishnamurthy, Tom Anderson University of Washington Timothy Roscoe ETH Zurich Building
More informationData Modeling and Databases Ch 10: Query Processing - Algorithms. Gustavo Alonso Systems Group Department of Computer Science ETH Zürich
Data Modeling and Databases Ch 10: Query Processing - Algorithms Gustavo Alonso Systems Group Department of Computer Science ETH Zürich Transactions (Locking, Logging) Metadata Mgmt (Schema, Stats) Application
More informationData Modeling and Databases Ch 9: Query Processing - Algorithms. Gustavo Alonso Systems Group Department of Computer Science ETH Zürich
Data Modeling and Databases Ch 9: Query Processing - Algorithms Gustavo Alonso Systems Group Department of Computer Science ETH Zürich Transactions (Locking, Logging) Metadata Mgmt (Schema, Stats) Application
More informationAccelerating Analytical Workloads
Accelerating Analytical Workloads Thomas Neumann Technische Universität München April 15, 2014 Scale Out in Big Data Analytics Big Data usually means data is distributed Scale out to process very large
More informationJignesh M. Patel. Blog:
Jignesh M. Patel Blog: http://bigfastdata.blogspot.com Go back to the design Query Cache from Processing for Conscious 98s Modern (at Algorithms Hardware least for Hash Joins) 995 24 2 Processor Processor
More informationPSAM, NEC PCIe SSD Appliance for Microsoft SQL Server (Reference Architecture) September 4 th, 2014 NEC Corporation
PSAM, NEC PCIe SSD Appliance for Microsoft SQL Server (Reference Architecture) September 4 th, 2014 NEC Corporation 1. Overview of NEC PCIe SSD Appliance for Microsoft SQL Server Page 2 NEC Corporation
More informationConsensus in a Box: Inexpensive Coordination in Hardware
Consensus in a Box: Inexpensive Coordination in Hardware Zsolt István, David Sidler, Gustavo Alonso Systems Group, Dept. of Computer Science, ETH Zürich Marko Vukolić IBM Research - Zürich Abstract Consensus
More informationDesigning Hybrid Data Processing Systems for Heterogeneous Servers
Designing Hybrid Data Processing Systems for Heterogeneous Servers Peter Pietzuch Large-Scale Distributed Systems (LSDS) Group Imperial College London http://lsds.doc.ic.ac.uk University
More informationOracle Performance on M5000 with F20 Flash Cache. Benchmark Report September 2011
Oracle Performance on M5000 with F20 Flash Cache Benchmark Report September 2011 Contents 1 About Benchware 2 Flash Cache Technology 3 Storage Performance Tests 4 Conclusion copyright 2011 by benchware.ch
More informationDCS-ctrl: A Fast and Flexible Device-Control Mechanism for Device-Centric Server Architecture
DCS-ctrl: A Fast and Flexible ice-control Mechanism for ice-centric Server Architecture Dongup Kwon 1, Jaehyung Ahn 2, Dongju Chae 2, Mohammadamin Ajdari 2, Jaewon Lee 1, Suheon Bae 1, Youngsok Kim 1,
More informationBig data, little time. Scale-out data serving. Scale-out data serving. Highly skewed key popularity
/7/6 Big data, little time Goal is to keep (hot) data in memory Requires scale-out approach Each server responsible for one chunk Fast access to local data The Case for RackOut Scalable Data Serving Using
More informationSurvey of ETSI NFV standardization documents BY ABHISHEK GUPTA FRIDAY GROUP MEETING FEBRUARY 26, 2016
Survey of ETSI NFV standardization documents BY ABHISHEK GUPTA FRIDAY GROUP MEETING FEBRUARY 26, 2016 VNFaaS (Virtual Network Function as a Service) In our present work, we consider the VNFaaS use-case
More informationExtending RDMA for Persistent Memory over Fabrics. Live Webcast October 25, 2018
Extending RDMA for Persistent Memory over Fabrics Live Webcast October 25, 2018 Today s Presenters John Kim SNIA NSF Chair Mellanox Tony Hurson Intel Rob Davis Mellanox SNIA-At-A-Glance 3 SNIA Legal Notice
More informationApplication Partitioning on FPGA Clusters: Inference over Decision Tree Ensembles
Application Partitioning on FPGA Clusters: Inference over Decision Tree Ensembles Muhsen Owaida, Gustavo Alonso Systems Group, Department of Computer Science, ETH Zurich {firstname.lastname}@inf.ethz.ch
More informationBlueDBM: An Appliance for Big Data Analytics*
BlueDBM: An Appliance for Big Data Analytics* Arvind *[ISCA, 2015] Sang-Woo Jun, Ming Liu, Sungjin Lee, Shuotao Xu, Arvind (MIT) and Jamey Hicks, John Ankcorn, Myron King(Quanta) BigData@CSAIL Annual Meeting
More informationIBM FlashSystem. IBM FLiP Tool Wie viel schneller kann Ihr IBM i Power Server mit IBM FlashSystem 900 / V9000 Storage sein?
FlashSystem Family 2015 IBM FlashSystem IBM FLiP Tool Wie viel schneller kann Ihr IBM i Power Server mit IBM FlashSystem 900 / V9000 Storage sein? PiRT - Power i Round Table 17 Sep. 2015 Daniel Gysin IBM
More informationOracle Exadata X7. Uwe Kirchhoff Oracle ACS - Delivery Senior Principal Service Delivery Engineer
Oracle Exadata X7 Uwe Kirchhoff Oracle ACS - Delivery Senior Principal Service Delivery Engineer 05.12.2017 Oracle Engineered Systems ZFS Backup Appliance Zero Data Loss Recovery Appliance Exadata Database
More informationScalable Inference of Decision Tree Ensembles: Flexible Design for CPU-FPGA Platforms
Scalable Inference of Decision Tree Ensembles: Flexible Design for CPU-FPGA Platforms Muhsen Owaida, Hantian Zhang, Ce Zhang, Gustavo Alonso Systems Group, Department of Computer Science, ETH Zurich {firstname.lastname}@inf.ethz.ch
More informationIsilon Performance. Name
1 Isilon Performance Name 2 Agenda Architecture Overview Next Generation Hardware Performance Caching Performance Streaming Reads Performance Tuning OneFS Architecture Overview Copyright 2014 EMC Corporation.
More informationMemory-Based Cloud Architectures
Memory-Based Cloud Architectures ( Or: Technical Challenges for OnDemand Business Software) Jan Schaffner Enterprise Platform and Integration Concepts Group Example: Enterprise Benchmarking -) *%'+,#$)
More informationAn Oracle White Paper September Oracle Utilities Meter Data Management Demonstrates Extreme Performance on Oracle Exadata/Exalogic
An Oracle White Paper September 2011 Oracle Utilities Meter Data Management 2.0.1 Demonstrates Extreme Performance on Oracle Exadata/Exalogic Introduction New utilities technologies are bringing with them
More informationToday s Data Centers. How can we improve efficiencies?
Today s Data Centers O(100K) servers/data center Tens of MegaWatts, difficult to power and cool Very noisy Security taken very seriously Incrementally upgraded 3 year server depreciation, upgraded quarterly
More informationDesigning Optimized MPI Broadcast and Allreduce for Many Integrated Core (MIC) InfiniBand Clusters
Designing Optimized MPI Broadcast and Allreduce for Many Integrated Core (MIC) InfiniBand Clusters K. Kandalla, A. Venkatesh, K. Hamidouche, S. Potluri, D. Bureddy and D. K. Panda Presented by Dr. Xiaoyi
More informationIntel Workstation Technology
Intel Workstation Technology Turning Imagination Into Reality November, 2008 1 Step up your Game Real Workstations Unleash your Potential 2 Yesterday s Super Computer Today s Workstation = = #1 Super Computer
More informationBig Data Systems on Future Hardware. Bingsheng He NUS Computing
Big Data Systems on Future Hardware Bingsheng He NUS Computing http://www.comp.nus.edu.sg/~hebs/ 1 Outline Challenges for Big Data Systems Why Hardware Matters? Open Challenges Summary 2 3 ANYs in Big
More informationHADP Talk BlueDBM: An appliance for Big Data Analytics
HADP Talk BlueDBM: An appliance for Big Data Analytics Sang-Woo Jun* Ming Liu* Sungjin Lee* Jamey Hicks+ John Ankcorn+ Myron King+ Shuotao Xu* Arvind* *MIT Computer Science and Artificial Intelligence
More informationOncilla - a Managed GAS Runtime for Accelerating Data Warehousing Queries
Oncilla - a Managed GAS Runtime for Accelerating Data Warehousing Queries Jeffrey Young, Alex Merritt, Se Hoon Shon Advisor: Sudhakar Yalamanchili 4/16/13 Sponsors: Intel, NVIDIA, NSF 2 The Problem Big
More informationAdapted from: TRENDS AND ATTRIBUTES OF HORIZONTAL AND VERTICAL COMPUTING ARCHITECTURES
Adapted from: TRENDS AND ATTRIBUTES OF HORIZONTAL AND VERTICAL COMPUTING ARCHITECTURES Tom Atwood Business Development Manager Sun Microsystems, Inc. Takeaways Understand the technical differences between
More informationWorkload Optimized Systems: The Wheel of Reincarnation. Michael Sporer, Netezza Appliance Hardware Architect 21 April 2013
Workload Optimized Systems: The Wheel of Reincarnation Michael Sporer, Netezza Appliance Hardware Architect 21 April 2013 Outline Definition Technology Minicomputers Prime Workstations Apollo Graphics
More informationIBM s Data Warehouse Appliance Offerings
IBM s Data Warehouse Appliance Offerings RChaitanya IBM India Software Labs Agenda 1 IBM Smart Analytics System (D5600) System Overview Technical Architecture Software / Hardware stack details 2 Netezza
More informationPhilippe Thierry Sr Staff Engineer Intel Corp.
HPC@Intel Philippe Thierry Sr Staff Engineer Intel Corp. IBM, April 8, 2009 1 Agenda CPU update: roadmap, micro-μ and performance Solid State Disk Impact What s next Q & A Tick Tock Model Perenity market
More informationSoftFlash: Programmable Storage in Future Data Centers Jae Do Researcher, Microsoft Research
SoftFlash: Programmable Storage in Future Data Centers Jae Do Researcher, Microsoft Research 1 The world s most valuable resource Data is everywhere! May. 2017 Values from Data! Need infrastructures for
More informationAdvanced Systems Lab (Intro and Administration) G. Alonso Systems Group
Advanced Systems Lab (Intro and Administration) G. Alonso Systems Group http://www.systems.ethz.ch Overview of the Course Focus on project Individual project during semester (3 milestones) This is a project
More informationLow-Overhead Flash Disaggregation via NVMe-over-Fabrics Vijay Balakrishnan Memory Solutions Lab. Samsung Semiconductor, Inc.
Low-Overhead Flash Disaggregation via NVMe-over-Fabrics Vijay Balakrishnan Memory Solutions Lab. Samsung Semiconductor, Inc. 1 DISCLAIMER This presentation and/or accompanying oral statements by Samsung
More informationTiny GPU Cluster for Big Spatial Data: A Preliminary Performance Evaluation
Tiny GPU Cluster for Big Spatial Data: A Preliminary Performance Evaluation Jianting Zhang 1,2 Simin You 2, Le Gruenwald 3 1 Depart of Computer Science, CUNY City College (CCNY) 2 Department of Computer
More informationAdvanced RDMA-based Admission Control for Modern Data-Centers
Advanced RDMA-based Admission Control for Modern Data-Centers Ping Lai Sundeep Narravula Karthikeyan Vaidyanathan Dhabaleswar. K. Panda Computer Science & Engineering Department Ohio State University Outline
More informationFAWN. A Fast Array of Wimpy Nodes. David Andersen, Jason Franklin, Michael Kaminsky*, Amar Phanishayee, Lawrence Tan, Vijay Vasudevan
FAWN A Fast Array of Wimpy Nodes David Andersen, Jason Franklin, Michael Kaminsky*, Amar Phanishayee, Lawrence Tan, Vijay Vasudevan Carnegie Mellon University *Intel Labs Pittsburgh Energy in computing
More informationNext Generation Computing Architectures for Cloud Scale Applications
Next Generation Computing Architectures for Cloud Scale Applications Steve McQuerry, CCIE #6108, Manager Technical Marketing #clmel Agenda Introduction Cloud Scale Architectures System Link Technology
More informationProtoFlex: FPGA-Accelerated Hybrid Simulator
ProtoFlex: FPGA-Accelerated Hybrid Simulator Eric S. Chung, Eriko Nurvitadhi James C. Hoe, Babak Falsafi, Ken Mai Computer Architecture Lab at Multiprocessor Simulation Simulating one processor in software
More informationComparing Memory Systems for Chip Multiprocessors
Comparing Memory Systems for Chip Multiprocessors Jacob Leverich Hideho Arakida, Alex Solomatnikov, Amin Firoozshahian, Mark Horowitz, Christos Kozyrakis Computer Systems Laboratory Stanford University
More information4 Myths about in-memory databases busted
4 Myths about in-memory databases busted Yiftach Shoolman Co-Founder & CTO @ Redis Labs @yiftachsh, @redislabsinc Background - Redis Created by Salvatore Sanfilippo (@antirez) OSS, in-memory NoSQL k/v
More informationIntroduction to Xeon Phi. Bill Barth January 11, 2013
Introduction to Xeon Phi Bill Barth January 11, 2013 What is it? Co-processor PCI Express card Stripped down Linux operating system Dense, simplified processor Many power-hungry operations removed Wider
More informationDynamic Partitioned Global Address Spaces for Power Efficient DRAM Virtualization
Dynamic Partitioned Global Address Spaces for Power Efficient DRAM Virtualization Jeffrey Young, Sudhakar Yalamanchili School of Electrical and Computer Engineering, Georgia Institute of Technology Talk
More informationSTORAGE CONSOLIDATION WITH IP STORAGE. David Dale, NetApp
STORAGE CONSOLIDATION WITH IP STORAGE David Dale, NetApp SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA. Member companies and individuals may use this material in
More informationLow-Overhead Flash Disaggregation via NVMe-over-Fabrics
Low-Overhead Flash Disaggregation via NVMe-over-Fabrics Vijay Balakrishnan Memory Solutions Lab. Samsung Semiconductor, Inc. August 2017 1 DISCLAIMER This presentation and/or accompanying oral statements
More informationRevolutionizing the Datacenter Join the Conversation #OpenPOWERSummit
Redis Labs on POWER8 Server: The Promise of OpenPOWER Value Jeffrey L. Leeds, Ph.D. Vice President, Alliances & Channels Revolutionizing the Datacenter Join the Conversation #OpenPOWERSummit Who We Are
More informationIntel Solid State Drive Data Center Family for PCIe* in Baidu s Data Center Environment
Intel Solid State Drive Data Center Family for PCIe* in Baidu s Data Center Environment Case Study Order Number: 334534-002US Ordering Information Contact your local Intel sales representative for ordering
More informationAccelerating Foreign-Key Joins using Asymmetric Memory Channels
Accelerating Foreign-Key Joins using Asymmetric Memory Channels Holger Pirk Stefan Manegold Martin Kersten holger@cwi.nl manegold@cwi.nl mk@cwi.nl Why? Trivia: Joins are important But: Many Joins are (Indexed)
More informationOracle Exadata: Strategy and Roadmap
Oracle Exadata: Strategy and Roadmap - New Technologies, Cloud, and On-Premises Juan Loaiza Senior Vice President, Database Systems Technologies, Oracle Safe Harbor Statement The following is intended
More informationReliable Distributed Messaging with HornetQ
Reliable Distributed Messaging with HornetQ Lin Zhao Software Engineer, Groupon lin@groupon.com Agenda Introduction MessageBus Design Client API Monitoring Comparison with HornetQ Cluster Future Work Introduction
More informationFaRM: Fast Remote Memory
FaRM: Fast Remote Memory Problem Context DRAM prices have decreased significantly Cost effective to build commodity servers w/hundreds of GBs E.g. - cluster with 100 machines can hold tens of TBs of main
More informationCloud Acceleration. Performance comparison of Cloud vendors. Tobias Deml DOAG2017
Performance comparison of Cloud vendors Tobias Deml Consultant @TobiasDemlDBA DOAG2017 About Consultant, Trivadis GmbH, Munich Since more than 9 years working in Oracle environment Focus areas Cloud Computing
More informationConcurrent execution of an analytical workload on a POWER8 server with K40 GPUs A Technology Demonstration
Concurrent execution of an analytical workload on a POWER8 server with K40 GPUs A Technology Demonstration Sina Meraji sinamera@ca.ibm.com Berni Schiefer schiefer@ca.ibm.com Tuesday March 17th at 12:00
More informationCommodity Converged Fabrics for Global Address Spaces in Accelerator Clouds
Commodity Converged Fabrics for Global Address Spaces in Accelerator Clouds Jeffrey Young, Sudhakar Yalamanchili School of Electrical and Computer Engineering, Georgia Institute of Technology Motivation
More informationTales of the Tail Hardware, OS, and Application-level Sources of Tail Latency
Tales of the Tail Hardware, OS, and Application-level Sources of Tail Latency Jialin Li, Naveen Kr. Sharma, Dan R. K. Ports and Steven D. Gribble February 2, 2015 1 Introduction What is Tail Latency? What
More informationFlexNIC: Rethinking Network DMA
FlexNIC: Rethinking Network DMA Antoine Kaufmann Simon Peter Tom Anderson Arvind Krishnamurthy University of Washington HotOS 2015 Networks: Fast and Growing Faster 1 T 400 GbE Ethernet Bandwidth [bits/s]
More informationRecent Innovations in Data Storage Technologies Dr Roger MacNicol Software Architect
Recent Innovations in Data Storage Technologies Dr Roger MacNicol Software Architect Copyright 2017, Oracle and/or its affiliates. All rights reserved. Safe Harbor Statement The following is intended to
More informationTrack Join. Distributed Joins with Minimal Network Traffic. Orestis Polychroniou! Rajkumar Sen! Kenneth A. Ross
Track Join Distributed Joins with Minimal Network Traffic Orestis Polychroniou Rajkumar Sen Kenneth A. Ross Local Joins Algorithms Hash Join Sort Merge Join Index Join Nested Loop Join Spilling to disk
More informationAdvanced Computer Networks. End Host Optimization
Oriana Riva, Department of Computer Science ETH Zürich 263 3501 00 End Host Optimization Patrick Stuedi Spring Semester 2017 1 Today End-host optimizations: NUMA-aware networking Kernel-bypass Remote Direct
More informationSoftware-Defined Data Infrastructure Essentials
Software-Defined Data Infrastructure Essentials Cloud, Converged, and Virtual Fundamental Server Storage I/O Tradecraft Greg Schulz Server StorageIO @StorageIO 1 of 13 Contents Preface Who Should Read
More informationCentaur: A Framework for Hybrid CPU-FPGA Databases
2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines Centaur: A Framework for Hybrid CPU-FPGA Databases Muhsen Owaida David Sidler Kaan Kara Gustavo Alonso Systems
More informationEvolving To The Big Data Warehouse
Evolving To The Big Data Warehouse Kevin Lancaster 1 Copyright Director, 2012, Oracle and/or its Engineered affiliates. All rights Insert Systems, Information Protection Policy Oracle Classification from
More informationProtoFlex: FPGA Accelerated Full System MP Simulation
ProtoFlex: FPGA Accelerated Full System MP Simulation Eric S. Chung, Eriko Nurvitadhi, James C. Hoe, Babak Falsafi, Ken Mai Computer Architecture Lab at Our work in this area has been supported in part
More informationFast packet processing in the cloud. Dániel Géhberger Ericsson Research
Fast packet processing in the cloud Dániel Géhberger Ericsson Research Outline Motivation Service chains Hardware related topics, acceleration Virtualization basics Software performance and acceleration
More informationHigh Performance Packet Processing with FlexNIC
High Performance Packet Processing with FlexNIC Antoine Kaufmann, Naveen Kr. Sharma Thomas Anderson, Arvind Krishnamurthy University of Washington Simon Peter The University of Texas at Austin Ethernet
More informationHybrid Memory Platform
Hybrid Memory Platform Kenneth Wright, Sr. Driector Rambus / Emerging Solutions Division Join the Conversation #OpenPOWERSummit 1 Outline The problem / The opportunity Project goals Roadmap - Sub-projects/Tracks
More informationMicrosoft SQL Server 2012 Fast Track Reference Configuration Using PowerEdge R720 and EqualLogic PS6110XV Arrays
Microsoft SQL Server 2012 Fast Track Reference Configuration Using PowerEdge R720 and EqualLogic PS6110XV Arrays This whitepaper describes Dell Microsoft SQL Server Fast Track reference architecture configurations
More informationHuge market -- essentially all high performance databases work this way
11/5/2017 Lecture 16 -- Parallel & Distributed Databases Parallel/distributed databases: goal provide exactly the same API (SQL) and abstractions (relational tables), but partition data across a bunch
More informationDistributed Binary Decision Diagrams for Symbolic Reachability
Distributed Binary Decision Diagrams for Symbolic Reachability Wytse Oortwijn Formal Methods and Tools, University of Twente November 1, 2015 Wytse Oortwijn (Formal Methods and Tools, Distributed University
More informationIsoStack Highly Efficient Network Processing on Dedicated Cores
IsoStack Highly Efficient Network Processing on Dedicated Cores Leah Shalev Eran Borovik, Julian Satran, Muli Ben-Yehuda Outline Motivation IsoStack architecture Prototype TCP/IP over 10GE on a single
More informationJoin Processing for Flash SSDs: Remembering Past Lessons
Join Processing for Flash SSDs: Remembering Past Lessons Jaeyoung Do, Jignesh M. Patel Department of Computer Sciences University of Wisconsin-Madison $/MB GB Flash Solid State Drives (SSDs) Benefits of
More informationOpenFlow Software Switch & Intel DPDK. performance analysis
OpenFlow Software Switch & Intel DPDK performance analysis Agenda Background Intel DPDK OpenFlow 1.3 implementation sketch Prototype design and setup Results Future work, optimization ideas OF 1.3 prototype
More informationNetChain: Scale-Free Sub-RTT Coordination
NetChain: Scale-Free Sub-RTT Coordination Xin Jin Xiaozhou Li, Haoyu Zhang, Robert Soulé, Jeongkeun Lee, Nate Foster, Changhoon Kim, Ion Stoica Conventional wisdom: avoid coordination NetChain: lightning
More informationMoneta: A High-performance Storage Array Architecture for Nextgeneration, Micro 2010
Moneta: A High-performance Storage Array Architecture for Nextgeneration, Non-volatile Memories Micro 2010 NVM-based SSD NVMs are replacing spinning-disks Performance of disks has lagged NAND flash showed
More informationRAMCloud and the Low- Latency Datacenter. John Ousterhout Stanford University
RAMCloud and the Low- Latency Datacenter John Ousterhout Stanford University Most important driver for innovation in computer systems: Rise of the datacenter Phase 1: large scale Phase 2: low latency Introduction
More information