HADP Talk BlueDBM: An appliance for Big Data Analytics
|
|
- Roy Perry
- 5 years ago
- Views:
Transcription
1 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 Laboratory +Quanta Research Cambridge Presented by: Geethan Karunaratne Supervision: Gustavo Alonso 1
2 Big Data Success Stories Google predicts Flu outbreaks image: 2
3 Big Data Success Stories Amazon anticipatory shipment of products image: 3
4 Big Data Success Stories Genome analysis and personalized diagnostics image: 4
5 Big Data : Future Likely to be the biggest economic driver for the IT industry for the next decade. Predictive Analysis, Identify issues and or make recommendations Banking Business Finance Communication Health Data-as-a-Service Algorithm markets (Algorithmia, Data Xu, and Kaggle) Data in the range 5TB to 20 TB range: continue to grow Right appliance for big data processing? 5
6 Memory/Storage Technologies Power HDD Latency 5 us SSD Latency us Latency Cost per bit 6
7 A currently popular solution: RAM Cloud[1] Cluster of machines with large capacity and fast interconnect + Fastest as long as data fits in - Power hungry and expensive - Performance drops when data doesn t fit in What if enough isn t affordable? -based solutions a more appealing alternative + Faster than Disk, cheaper than + Lower power consumption than both - Legacy storage access interface is burdening - Slower than 7
8 Latency profile of distributed flash-based analytics Distributed processing involves many system components device access Storage software (OS, FTL, ) Network interface (10gE, Infiniband, ) Actual processing Access 75 μs Storage 100 μs Network 20 μs Processing 50~500 μs 100~1000 μs 20~1000 μs Latency is additive 8
9 Latency profile of distributed flash-based analytics Architectural modifications can remove unnecessary overhead Cross-layer optimization of flash management software Dedicated storage area network Near-storage processing accelerator Access 75 μs Storage Network Network Processing Processing 20 μs 20 μs 100 μs 50~100 μs <20μs 20~ ~1000 μs μs 20~1000 μs Processing 9
10 Latency profile of distributed flash-based analytics Architectural modifications can remove unnecessary overhead Access 75 μs Storage 100 μs 50~100 μs 100~1000 μs 1 Network 20 μs Processing 20~1000 μs 2 3 Access 75 μs 50~100 μs <20μs 10
11 Related work 1. Use of flash FusionIO, Purestorage, Moneta, Willow SSD for database buffer pool and metadata Zetascale Biscuit (ISCA 2016) Netezza [SIGMOD 2008], [IJCA 2013] 2. Networks QuickSAN [ISCA 2013] Hadoop/Spark on Infiniband RDMA [SC 2012] 3. Accelerators SmartSSD[SIGMOD 2013], Ibex[VLDB 2014] Catapult[ISCA 2014] Centaur [FCCM 2017] Biscuit (ISCA 2016) Netezza (IBM) GPUs 11
12 BlueDBM: Overall Architecture 1 of 2 Racks (10 Nodes) 12
13 Overall Architecture core Xeon Servers 20 1TB flash storage 20 Custom flash boards 20 Xilinx VC707 PCIe 1 Gen 10 Gbps controller network 13
14 Node Architecture 14
15 Node Architecture 15
16 Use of 16
17 ISP/Host HPC FMC PORT Custom flash card 512GB Cont. Bus 0 Bus 1 Bus 2 Bus 3 Network Ports 17
18 To VC707 HPC FMC PORT Custom flash card Limited program cycles in flash CPU for Artix 7 FPGA Bus 0 Bus 1 Bus 2 Bus 3 Network Ports Wear leveling Garbage collection Bit error correction Bad lock management In BlueDBM, these are offloaded to filesystem and block devices drivers 18
19 Custom flash card High Performance Access Handle out of order and Interleaved ( Server) Need for reorder buffer in host side Multi Agent access ( Interface Splitter) Local host Local in-store processor Remote in-store processor 19
20 Near Storage Processing 20
21 In-store Processing Engine User defined in-store processing engines Access to Interface Host Interface Network Interface Key in sending /receiving data to/from remote storage Implemented on Virtex 7 FPGA 21
22 Userspace Interface Hardware-assisted Applications Connectal Proxy Kernelspace File System Generated by Connectal* Block Device Driver FPGA Connectal (By Quanta) Ctrl HW Accelerator Connectal Wrapper Accelerator Manager Network Interface NAND BlueDBM provides a generic file system interface as well as an accelerator-specific interface (Aided by Connectal) 22
23 Networks 23
24 Integrated Storage Network Packet-switched mesh network connected by high performance serial links (SATA) 24
25 Integrated Storage Network Flow control and virtual channel Deterministic routing Network configuration file to populate the routing tables 25
26 Integrated Storage Network Virtex Artix Host Interface ISP Network Interface Aurora 4-Lanes 26Gbps 0.5us 4x GTX Transceivers 10Gbps, 0.5 us SATA Fanout 8 4x GTP Transceivers 6.6Gbps, 0.5 us Questions device selection Fanout 8 means upto 64 nodes reached within 2 hops 26
27 Evaluation 27
28 Evaluation FPGA resource utilization Module Name LUT Registers BRAM Module Name LUT Registers BRAM Bus s Interface SerDes Network Interface Total 56% 23% 50% Interface Host Interface Total 45% 22% 22% Artix 7 Virtex 7 28
29 Power Consumption Component Power (Watts) VC Board (x2) 10 Storage Device Total 40 Power Consumption: TeraData Aster 50x RamCloud 4x Component Power (Watts) Storage Device 40 Xeon Server 200+ Node Total
30 Access Bandwidth 3.3 GB/s 2.4 GB/s Int. Switch NIC In-store Proc PCI 1.6 GB/s 1 GB/s or 0.66 GB/s 30
31 Access Bandwidth 3.3 GB/s 2.4 GB/s Int. Switch In-store Proc NIC 1 GB/s or 0.66 GB/s PCI 1.6 GB/s 31
32 Access Bandwidth 3.3 GB/s 2.4 GB/s Int. Switch In-store Proc NIC 1 GB/s or 0.66 GB/s PCI 1.6 GB/s 32
33 Access Bandwidth 3.3 GB/s 2.4 GB/s Int. Switch In-store Proc NIC 1 GB/s or 0.66 GB/s PCI 1.6 GB/s 33
34 Latency Profile of a Node 0.5 us us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us 34
35 Remote Storage Access Latency From in-store processor to remote flash storage us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 35
36 Remote Storage Access Latency From host server to remote flash storage us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 36
37 Remote Storage Access Latency From host server to remote flash storage via its host server us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 37
38 Remote Storage Access Latency From host server to remote us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 38
39 Latency to different memories Near-uniform latency access? us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us (1%) us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us (1%) us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 39
40 Latency to different memories Near-uniform latency access? us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us (1%) us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 0.5 us (1%) us 0 us Int. Switch NIC In-store Proc 5 us PCI 50 us 40
41 Application Acceleration Nearest Neighbour Search 41
42 Application Acceleration Nearest Neighbour Search 42
43 Application Acceleration Nearest Neighbour Search 43
44 Application Acceleration Nearest Neighbour Search 44
45 Conclusion and Remarks Presents a complete end to end system More affordable and less-power consuming Demonstrated on hardware Several algorithms tested. Plans to test more. Broad range of contributions for a single paper 45
46 Conclusion and Remarks Near-uniform latency claim questionable Hardware selection could be improved (going for smaller single FPGA): To make small form factor Improve worst case network performance Reduce cost ASIC? 46
47 Thank you 47
48 References [1] [2] sh+memory+and+other+technologies 48
49 Big Data Success Stories Twitter (Social Media) reveal social upheavals image:
BlueDBM: 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 informationBlueDBM: An Appliance for Big Data Analytics
BlueDBM: An Appliance for Big Data Analytics Sang-Woo Jun Ming Liu Sungjin Lee Jamey Hicks John Ankcorn Myron King Shuotao Xu Arvind Department of Electrical Engineering and Computer Science Massachusetts
More informationGraFBoost: Using accelerated flash storage for external graph analytics
GraFBoost: Using accelerated flash storage for external graph analytics Sang-Woo Jun, Andy Wright, Sizhuo Zhang, Shuotao Xu and Arvind MIT CSAIL Funded by: 1 Large Graphs are Found Everywhere in Nature
More informationBig Data Analytics Using Hardware-Accelerated Flash Storage
Big Data Analytics Using Hardware-Accelerated Flash Storage Sang-Woo Jun University of California, Irvine (Work done while at MIT) Flash Memory Summit, 2018 A Big Data Application: Personalized Genome
More informationNOHOST: A New Storage Architecture for Distributed Storage Systems. Chanwoo Chung
NOHOST: A New Storage Architecture for Distributed Storage Systems by Chanwoo Chung B.S., Seoul National University (2014) Submitted to the Department of Electrical Engineering and Computer Science in
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 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 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 informationNVM Express Awakening a New Storage and Networking Titan Shaun Walsh G2M Research
NVM Express Awakening a New Storage and Networking Titan Shaun Walsh G2M Research Acronyms and Definition Check Point Term Definition NVMe Non-Volatile Memory Express NVMe-oF Non-Volatile Memory Express
More informationRealizing the Next Generation of Exabyte-scale Persistent Memory-Centric Architectures and Memory Fabrics
Realizing the Next Generation of Exabyte-scale Persistent Memory-Centric Architectures and Memory Fabrics Zvonimir Z. Bandic, Sr. Director, Next Generation Platform Technologies Western Digital Corporation
More informationNVM PCIe Networked Flash Storage
NVM PCIe Networked Flash Storage Peter Onufryk Microsemi Corporation Santa Clara, CA 1 PCI Express (PCIe) Mid-range/High-end Specification defined by PCI-SIG Software compatible with PCI and PCI-X Reliable,
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 informationReconfigurable 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 informationIndustry Collaboration and Innovation
Industry Collaboration and Innovation OpenCAPI Topics Industry Background Technology Overview Design Enablement OpenCAPI Consortium Industry Landscape Key changes occurring in our industry Historical microprocessor
More informationLightweight KV-based Distributed Store for Datacenters
Lightweight KV-based Distributed Store for Datacenters Chanwoo Chung, Jinhyung Koo*, Arvind, and Sungjin Lee Massachusetts Institute of Technology (MIT) Daegu Gyeongbuk Institute of Science & Technology
More informationImplementing Ultra Low Latency Data Center Services with Programmable Logic
Implementing Ultra Low Latency Data Center Services with Programmable Logic John W. Lockwood, CEO: Algo-Logic Systems, Inc. http://algo-logic.com Solutions@Algo-Logic.com (408) 707-3740 2255-D Martin Ave.,
More informationBlueGene/L. Computer Science, University of Warwick. Source: IBM
BlueGene/L Source: IBM 1 BlueGene/L networking BlueGene system employs various network types. Central is the torus interconnection network: 3D torus with wrap-around. Each node connects to six neighbours
More informationLessons from Post-processing Climate Data on Modern Flash-based HPC Systems
Lessons from Post-processing Climate Data on Modern Flash-based HPC Systems Adnan Haider 1, Sheri Mickelson 2, John Dennis 2 1 Illinois Institute of Technology, USA; 2 National Center of Atmospheric Research,
More informationScalable Multi-Access Flash Store for Big Data Analytics
Scalable Multi-Access Flash Store for Big Data Analytics Sang-Woo Jun, Ming Liu, Kermin Elliott Fleming, Arvind Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology
More informationCisco HyperFlex HX220c Edge M5
Data Sheet Cisco HyperFlex HX220c Edge M5 Hyperconvergence engineered on the fifth-generation Cisco UCS platform Rich digital experiences need always-on, local, high-performance computing that is close
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 informationMaximizing heterogeneous system performance with ARM interconnect and CCIX
Maximizing heterogeneous system performance with ARM interconnect and CCIX Neil Parris, Director of product marketing Systems and software group, ARM Teratec June 2017 Intelligent flexible cloud to enable
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 informationCOSMOS Architecture and Key Technologies. June 1 st, 2018 COSMOS Team
COSMOS Architecture and Key Technologies June 1 st, 2018 COSMOS Team COSMOS: System Architecture (2) System design based on three levels of SDR radio node (S,M,L) with M,L connected via fiber to optical
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 informationDDN About Us Solving Large Enterprise and Web Scale Challenges
1 DDN About Us Solving Large Enterprise and Web Scale Challenges History Founded in 98 World s Largest Private Storage Company Growing, Profitable, Self Funded Headquarters: Santa Clara and Chatsworth,
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 informationBenefits of 25, 40, and 50GbE Networks for Ceph and Hyper- Converged Infrastructure John F. Kim Mellanox Technologies
Benefits of 25, 40, and 50GbE Networks for Ceph and Hyper- Converged Infrastructure John F. Kim Mellanox Technologies Storage Transitions Change Network Needs Software Defined Storage Flash Storage Storage
More informationApplication-Managed Flash
Application-Managed Flash Sungjin Lee*, Ming Liu, Sangwoo Jun, Shuotao Xu, Jihong Kim and Arvind *Inha University Massachusetts Institute of Technology Seoul National University Operating System Support
More informationG2M Research Presentation Flash Memory Summit 2018
G2M Research Presentation Flash Memory Summit 2018 August 7, 2018 The Easy Facts about NVMe u NVMe SSDs will become ubiquitous over the next 1-2 years This will be true for the Cloud, Enterprise, and Consumer
More informationHardware NVMe implementation on cache and storage systems
Hardware NVMe implementation on cache and storage systems Jerome Gaysse, IP-Maker Santa Clara, CA 1 Agenda Hardware architecture NVMe for storage NVMe for cache/application accelerator NVMe for new NVM
More informationNVMe Takes It All, SCSI Has To Fall. Brave New Storage World. Lugano April Alexander Ruebensaal
Lugano April 2018 NVMe Takes It All, SCSI Has To Fall freely adapted from ABBA Brave New Storage World Alexander Ruebensaal 1 Design, Implementation, Support & Operating of optimized IT Infrastructures
More informationMessaging Overview. Introduction. Gen-Z Messaging
Page 1 of 6 Messaging Overview Introduction Gen-Z is a new data access technology that not only enhances memory and data storage solutions, but also provides a framework for both optimized and traditional
More informationScaling Internet TV Content Delivery ALEX GUTARIN DIRECTOR OF ENGINEERING, NETFLIX
Scaling Internet TV Content Delivery ALEX GUTARIN DIRECTOR OF ENGINEERING, NETFLIX Inventing Internet TV Available in more than 190 countries 104+ million subscribers Lots of Streaming == Lots of Traffic
More informationBig Compute, Big Net & Big Data: How to be big
> 2014 HPC Advisory Council Brazil Conference Big Compute, Big Net & Big Data: How to be big Luiz Monnerat PETROBRAS 26/05/2014 > Agenda Big Compute (HPC) Commodity HW, free software, parallel processing,
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 informationNext Generation Architecture for NVM Express SSD
Next Generation Architecture for NVM Express SSD Dan Mahoney CEO Fastor Systems Copyright 2014, PCI-SIG, All Rights Reserved 1 NVMExpress Key Characteristics Highest performance, lowest latency SSD interface
More informationIndustry Collaboration and Innovation
Industry Collaboration and Innovation Industry Landscape Key changes occurring in our industry Historical microprocessor technology continues to deliver far less than the historical rate of cost/performance
More informationSTORAGE NETWORKING TECHNOLOGY STEPS UP TO PERFORMANCE CHALLENGES
E-Guide STORAGE NETWORKING TECHNOLOGY STEPS UP TO PERFORMANCE CHALLENGES SearchStorage S torage network technology is changing and speed is the name of the game. To handle the burgeoning data growth, organizations
More informationReconstruyendo una Nube Privada con la Innovadora Hiper-Convergencia Infraestructura Huawei FusionCube Hiper-Convergente
Reconstruyendo una Nube Privada con la Innovadora Hiper-Convergencia Infraestructura Huawei FusionCube Hiper-Convergente Ronald Paz IT Product Director Huawei del Peru Contents 1 Huawei Corporation 2 IT
More informationNVMe Direct. Next-Generation Offload Technology. White Paper
NVMe Direct Next-Generation Offload Technology The market introduction of high-speed NVMe SSDs and 25/40/50/100Gb Ethernet creates exciting new opportunities for external storage NVMe Direct enables high-performance
More informationDDN. DDN Updates. DataDirect Neworks Japan, Inc Nobu Hashizume. DDN Storage 2018 DDN Storage 1
1 DDN DDN Updates DataDirect Neworks Japan, Inc Nobu Hashizume DDN Storage 2018 DDN Storage 1 2 DDN A Broad Range of Technologies to Best Address Your Needs Your Use Cases Research Big Data Enterprise
More informationZD-XL SQL Accelerator 1.6
ZD-XL SQL Accelerator 1.6 Integrated Flash Hardware & Software Acceleration Solution for SQL Server Features Supports Microsoft Hyper-V and VMware ESXi environments Accelerates SQL Server at a per database
More informationDDN. DDN Updates. Data DirectNeworks Japan, Inc Shuichi Ihara. DDN Storage 2017 DDN Storage
DDN DDN Updates Data DirectNeworks Japan, Inc Shuichi Ihara DDN A Broad Range of Technologies to Best Address Your Needs Protection Security Data Distribution and Lifecycle Management Open Monitoring Your
More informationNVMe: The Protocol for Future SSDs
When do you need NVMe? You might have heard that Non-Volatile Memory Express or NVM Express (NVMe) is the next must-have storage technology. Let s look at what NVMe delivers. NVMe is a communications protocol
More informationAn NVMe-based FPGA Storage Workload Accelerator
An NVMe-based FPGA Storage Workload Accelerator Dr. Sean Gibb, VP Software Eideticom Santa Clara, CA 1 PCIe Bus NVMe SSD NVMe SSD Acceleration Host CPU HDD RDMA NIC NoLoad Accel. Card TM Storage I/O Bandwidth
More informationNear-Data Processing for Differentiable Machine Learning Models
Near-Data Processing for Differentiable Machine Learning Models Hyeokjun Choe 1, Seil Lee 1, Hyunha Nam 1, Seongsik Park 1, Seijoon Kim 1, Eui-Young Chung 2 and Sungroh Yoon 1,3 1 Electrical and Computer
More informationSpartan-6 & Virtex-6 FPGA Connectivity Kit FAQ
1 P age Spartan-6 & Virtex-6 FPGA Connectivity Kit FAQ April 04, 2011 Getting Started 1. Where can I purchase a kit? A: You can purchase your Spartan-6 and Virtex-6 FPGA Connectivity kits online at: Spartan-6
More informationCommunication has significant impact on application performance. Interconnection networks therefore have a vital role in cluster systems.
Cluster Networks Introduction Communication has significant impact on application performance. Interconnection networks therefore have a vital role in cluster systems. As usual, the driver is performance
More informationThe Future of High Performance Interconnects
The Future of High Performance Interconnects Ashrut Ambastha HPC Advisory Council Perth, Australia :: August 2017 When Algorithms Go Rogue 2017 Mellanox Technologies 2 When Algorithms Go Rogue 2017 Mellanox
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 informationSSD Architecture Considerations for a Spectrum of Enterprise Applications. Alan Fitzgerald, VP and CTO SMART Modular Technologies
SSD Architecture Considerations for a Spectrum of Enterprise Applications Alan Fitzgerald, VP and CTO SMART Modular Technologies Introduction Today s SSD delivers form-fit-function compatible solid-state
More informationMass-Storage Structure
Operating Systems (Fall/Winter 2018) Mass-Storage Structure Yajin Zhou (http://yajin.org) Zhejiang University Acknowledgement: some pages are based on the slides from Zhi Wang(fsu). Review On-disk structure
More informationSOFTWARE-DEFINED BLOCK STORAGE FOR HYPERSCALE APPLICATIONS
SOFTWARE-DEFINED BLOCK STORAGE FOR HYPERSCALE APPLICATIONS SCALE-OUT SERVER SAN WITH DISTRIBUTED NVME, POWERED BY HIGH-PERFORMANCE NETWORK TECHNOLOGY INTRODUCTION The evolution in data-centric applications,
More informationSharing High-Performance Devices Across Multiple Virtual Machines
Sharing High-Performance Devices Across Multiple Virtual Machines Preamble What does sharing devices across multiple virtual machines in our title mean? How is it different from virtual networking / NSX,
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 informationOSSD: A Case for Object-based Solid State Drives
MSST 2013 2013/5/10 OSSD: A Case for Object-based Solid State Drives Young-Sik Lee Sang-Hoon Kim, Seungryoul Maeng, KAIST Jaesoo Lee, Chanik Park, Samsung Jin-Soo Kim, Sungkyunkwan Univ. SSD Desktop Laptop
More informationMemory Expansion Technology Using Software-Controlled SSD
Memory Expansion Technology Using Software-Controlled SSD S. Kazama*, S. Gokita*, S. Kuwamura*, E. Yoshida*, J. Ogawa*, Y. Honda** *Fujitsu Laboratories Ltd. **Fujitsu Ltd. Contact: sc-ssd-fms2017@ml.labs.fujitsu.com
More informationCisco HyperFlex HX220c M4 and HX220c M4 All Flash Nodes
Data Sheet Cisco HyperFlex HX220c M4 and HX220c M4 All Flash Nodes Fast and Flexible Hyperconverged Systems You need systems that can adapt to match the speed of your business. Cisco HyperFlex Systems
More informationGPUs and Emerging Architectures
GPUs and Emerging Architectures Mike Giles mike.giles@maths.ox.ac.uk Mathematical Institute, Oxford University e-infrastructure South Consortium Oxford e-research Centre Emerging Architectures p. 1 CPUs
More informationEI 338: Computer Systems Engineering (Operating Systems & Computer Architecture)
EI 338: Computer Systems Engineering (Operating Systems & Computer Architecture) Dept. of Computer Science & Engineering Chentao Wu wuct@cs.sjtu.edu.cn Download lectures ftp://public.sjtu.edu.cn User:
More informationFlash Trends: Challenges and Future
Flash Trends: Challenges and Future John D. Davis work done at Microsoft Researcher- Silicon Valley in collaboration with Laura Caulfield*, Steve Swanson*, UCSD* 1 My Research Areas of Interest Flash characteristics
More informationDell PowerEdge R730xd Servers with Samsung SM1715 NVMe Drives Powers the Aerospike Fraud Prevention Benchmark
Dell PowerEdge R730xd Servers with Samsung SM1715 NVMe Drives Powers the Aerospike Fraud Prevention Benchmark Testing validation report prepared under contract with Dell Introduction As innovation drives
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 informationBringing Intelligence to Enterprise Storage Drives
Bringing Intelligence to Enterprise Storage Drives Neil Werdmuller Director Storage Solutions Arm Santa Clara, CA 1 Who am I? 28 years experience in embedded Lead the storage solutions team Work closely
More informationAccelerating Enterprise Search with Fusion iomemory PCIe Application Accelerators
WHITE PAPER Accelerating Enterprise Search with Fusion iomemory PCIe Application Accelerators Western Digital Technologies, Inc. 951 SanDisk Drive, Milpitas, CA 95035 www.sandisk.com Table of Contents
More informationCisco HyperFlex HX220c M4 Node
Data Sheet Cisco HyperFlex HX220c M4 Node A New Generation of Hyperconverged Systems To keep pace with the market, you need systems that support rapid, agile development processes. Cisco HyperFlex Systems
More informationCan Parallel Replication Benefit Hadoop Distributed File System for High Performance Interconnects?
Can Parallel Replication Benefit Hadoop Distributed File System for High Performance Interconnects? N. S. Islam, X. Lu, M. W. Rahman, and D. K. Panda Network- Based Compu2ng Laboratory Department of Computer
More informationBuilding the Most Efficient Machine Learning System
Building the Most Efficient Machine Learning System Mellanox The Artificial Intelligence Interconnect Company June 2017 Mellanox Overview Company Headquarters Yokneam, Israel Sunnyvale, California Worldwide
More informationG2M Research Fall 2017 NVMe Market Sizing Webinar
G2M Research Fall 2017 NVMe Market Sizing Webinar October 24, 2017 G2M Research NVMe Market Report Agenda State of the NVMe Market and Key Predictions Use Cases, Drivers, and Hurdles for Various NVMe SSD
More informationAnnual Update on Flash Memory for Non-Technologists
Annual Update on Flash Memory for Non-Technologists Jay Kramer, Network Storage Advisors & George Crump, Storage Switzerland August 2017 1 Memory / Storage Hierarchy Flash Memory Summit 2017 2 NAND Flash
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 informationBrent Gorda. General Manager, High Performance Data Division
Brent Gorda General Manager, High Performance Data Division Legal Disclaimer Intel may make changes to specifications and product descriptions at any time, without notice. Designers must not rely on the
More informationNAND Interleaving & Performance
NAND Interleaving & Performance What You Need to Know Presented by: Keith Garvin Product Architect, Datalight August 2008 1 Overview What is interleaving, why do it? Bus Level Interleaving Interleaving
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 informationExtremely Fast Distributed Storage for Cloud Service Providers
Solution brief Intel Storage Builders StorPool Storage Intel SSD DC S3510 Series Intel Xeon Processor E3 and E5 Families Intel Ethernet Converged Network Adapter X710 Family Extremely Fast Distributed
More informationOpenCAPI and its Roadmap
OpenCAPI and its Roadmap Myron Slota, President OpenCAPI Speaker name, Consortium Title Company/Organization Name Join the Conversation #OpenPOWERSummit Industry Collaboration and Innovation OpenCAPI and
More informationKey Points. Rotational delay vs seek delay Disks are slow. Techniques for making disks faster. Flash and SSDs
IO 1 Today IO 2 Key Points CPU interface and interaction with IO IO devices The basic structure of the IO system (north bridge, south bridge, etc.) The key advantages of high speed serial lines. The benefits
More informationMaximum Performance. How to get it and how to avoid pitfalls. Christoph Lameter, PhD
Maximum Performance How to get it and how to avoid pitfalls Christoph Lameter, PhD cl@linux.com Performance Just push a button? Systems are optimized by default for good general performance in all areas.
More informationDecentralized Distributed Storage System for Big Data
Decentralized Distributed Storage System for Big Presenter: Wei Xie -Intensive Scalable Computing Laboratory(DISCL) Computer Science Department Texas Tech University Outline Trends in Big and Cloud Storage
More informationToward a Memory-centric Architecture
Toward a Memory-centric Architecture Martin Fink EVP & Chief Technology Officer Western Digital Corporation August 8, 2017 1 SAFE HARBOR DISCLAIMERS Forward-Looking Statements This presentation contains
More informationDesigning Next Generation FS for NVMe and NVMe-oF
Designing Next Generation FS for NVMe and NVMe-oF Liran Zvibel CTO, Co-founder Weka.IO @liranzvibel Santa Clara, CA 1 Designing Next Generation FS for NVMe and NVMe-oF Liran Zvibel CTO, Co-founder Weka.IO
More informationSATA-IP Introduction. Agenda
Introduction Ver1.3E Support Virtex-6/Spartan-6! Magician of the Storage! 2012/7/31 Design Gateway Page 1 Agenda SATA Overview Summary, Features and Trend Merit and Solution Introduction Summary Application
More information100% PACKET CAPTURE. Intelligent FPGA-based Host CPU Offload NIC s & Scalable Platforms. Up to 200Gbps
100% PACKET CAPTURE Intelligent FPGA-based Host CPU Offload NIC s & Scalable Platforms Up to 200Gbps Dual Port 100 GigE ANIC-200KFlex (QSFP28) The ANIC-200KFlex FPGA-based PCIe adapter/nic features dual
More informationWhen Hadoop-like Distributed Storage Meets NAND Flash: Challenge and Opportunity
When Hadoop-like Distributed Storage Meets NAND Flash: Challenge and Opportunity Jupyung Lee Intelligent Computing Lab Future IT Research Center Samsung Advanced Institute of Technology November 9, 2011
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 informationA Design for Networked Flash
A Design for Networked Flash (Clusters Of Raw Flash Units) Mahesh Balakrishnan, John Davis, Dahlia Malkhi, Vijayan Prabhakaran, Michael Wei*, Ted Wobber Microso- Research Silicon Valley * Graduate student
More informationNVMe-IP Introduction for Xilinx Ver1.8E
NVMe-IP Introduction for Xilinx Ver1.8E Direct connection between latest NVMe SSD and FPGA Optimal Solution for Data Recording Application! Page 1 NVMe SSD Overview Agenda SSD Trends Merit of NVMe SSD
More informationUnblinding the OS to Optimize User-Perceived Flash SSD Latency
Unblinding the OS to Optimize User-Perceived Flash SSD Latency Woong Shin *, Jaehyun Park **, Heon Y. Yeom * * Seoul National University ** Arizona State University USENIX HotStorage 2016 Jun. 21, 2016
More informationPreface. Fig. 1 Solid-State-Drive block diagram
Preface Solid-State-Drives (SSDs) gained a lot of popularity in the recent few years; compared to traditional HDDs, SSDs exhibit higher speed and reduced power, thus satisfying the tough needs of mobile
More informationNew HPE 3PAR StoreServ 8000 and series Optimized for Flash
New HPE 3PAR StoreServ 8000 and 20000 series Optimized for Flash AGENDA HPE 3PAR StoreServ architecture fundamentals HPE 3PAR Flash optimizations HPE 3PAR portfolio overview HPE 3PAR Flash example from
More informationMoneta: A High-Performance Storage Architecture for Next-generation, Non-volatile Memories
Moneta: A High-Performance Storage Architecture for Next-generation, Non-volatile Memories Adrian M. Caulfield Arup De, Joel Coburn, Todor I. Mollov, Rajesh K. Gupta, Steven Swanson Non-Volatile Systems
More informationNVMe over Universal RDMA Fabrics
NVMe over Universal RDMA Fabrics Build a Flexible Scale-Out NVMe Fabric with Concurrent RoCE and iwarp Acceleration Broad spectrum Ethernet connectivity Universal RDMA NVMe Direct End-to-end solutions
More informationEmerging Technologies for HPC Storage
Emerging Technologies for HPC Storage Dr. Wolfgang Mertz CTO EMEA Unstructured Data Solutions June 2018 The very definition of HPC is expanding Blazing Fast Speed Accessibility and flexibility 2 Traditional
More informationThe BioHPC Nucleus Cluster & Future Developments
1 The BioHPC Nucleus Cluster & Future Developments Overview Today we ll talk about the BioHPC Nucleus HPC cluster with some technical details for those interested! How is it designed? What hardware does
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 informationBuilding the Most Efficient Machine Learning System
Building the Most Efficient Machine Learning System Mellanox The Artificial Intelligence Interconnect Company June 2017 Mellanox Overview Company Headquarters Yokneam, Israel Sunnyvale, California Worldwide
More informationROM Status Update. U. Marconi, INFN Bologna
ROM Status Update U. Marconi, INFN Bologna Drift Chamber ~ 35 L1 processor EMC ~ 80 L1 processor? SVT L1 processor L3 to L5 ~15 Radiation wall Clk, L1, Sync Cmds Global Level1 Trigger (GLT) Raw L1 FCTS
More informationS2C K7 Prodigy Logic Module Series
S2C K7 Prodigy Logic Module Series Low-Cost Fifth Generation Rapid FPGA-based Prototyping Hardware The S2C K7 Prodigy Logic Module is equipped with one Xilinx Kintex-7 XC7K410T or XC7K325T FPGA device
More informationFlash Controller Solutions in Programmable Technology
Flash Controller Solutions in Programmable Technology David McIntyre Senior Business Unit Manager Computer and Storage Business Unit Altera Corp. dmcintyr@altera.com Flash Memory Summit 2012 Santa Clara,
More information