EC-Bench: Benchmarking Onload and Offload Erasure Coders on Modern Hardware Architectures
|
|
- Britton Russell
- 5 years ago
- Views:
Transcription
1 EC-Bench: Benchmarking Onload and Offload Erasure Coders on Modern Hardware Architectures Haiyang Shi, Xiaoyi Lu, and Dhabaleswar K. (DK) Panda {shi.876, lu.932, The Ohio State University Bench 218
2 Bench Outline Introduction EC-Bench Evaluation Conclusion and Future Work
3 Bench Fault Tolerance & Replication Fault tolerance is a critical requirement for distributed storages Availability: data is still accessible under failures Durability: no data corruptions under failures Traditional storage scheme to achieve fault tolerance is replication Common replication factors: 3-1 Replication factor = 3 D Original data Data used to maintain fault tolerance
4 Bench Booming of Data 1,4 Data Stored in Exabytes 1,2 1, ,327 36% CAGR Source: Cisco Global Cloud Index, The booming of data makes storage overhead of replication considerable
5 Bench Erasure Coding Erasure Coding is a promising redundancy storage scheme Minimize storage overhead by applying erasure encoding on data Deliver higher reliability with same storage overhead than replication Employed in Google, Microsoft, Facebook, Baidu, etc. v Microsoft Azure reduces storage overhead from 3x (3-way replication) to 1.33x - k = 4 - m = 2 (erasure coding) Data Chunks Parity Chunks D1 D2 D3 D4 P1 P2 Original data Data used to maintain fault tolerance
6 Bench Replication vs. Erasure Coding Replication Storage overhead = 2/1 = 2 D Replication factor = 3 Original data Data used to maintain fault tolerance Data Chunks Parity Chunks D1 D2 D3 D4 P1 P2 - k = 4 - m = 2 Erasure Coding Storage overhead = 2/4 =.5 Original data Data used to maintain fault tolerance
7 Bench Erasure Coding: Encoding Ø Takes in k data chunks and generates m parity chunks Ø Distributes (k + m) chunks to (k + m) independent nodes - k = 6 - m = 3 Data Chunks Parity Chunks D1 D2 D3 D4 D5 D6 P1 P2 P3
8 Bench Erasure Coding: Decoding Ø Any k of (k + m) chunks are sufficient to recover the original k data chunks - k = 6 - m = 3 Data Chunks Parity Chunks D1 D2 D3 D4 D5 D6 P1 P2 P3 Read Decode D1 D2 D3 D4 D5 D6
9 Bench Erasure Coding Pros: Low storage overhead with high fault tolerance Cons: High computation overhead introduced by encode and decode Ø High performance hardware-optimized erasure coding libraries to alleviate computation overhead Ø Intel CPUs -> Intel ISA-L Ø Nvidia GPUs -> Gibraltar Ø Mellanox InfiniBand -> Mellanox-EC
10 Bench Onload and Offload Erasure Coders Onload Erasure Coder Erasure coding operations are performed by host processors Jerasure and Intel ISA-L Onload Erasure Coders Jerasure CPU ISA-L Offload Erasure Coder Erasure coding operations are conducted by accelerators like Offload Erasure Coders GPU Gibraltar IB HCA Mellanox-EC GPUs and Mellanox InfiniBand HCAs Gibraltar and Mellanox-EC
11 Bench Our Contributions Ø EC-Bench: An unified benchmark suite to benchmark, measure, and characterize onload and offload erasure coders Performance Throughput Normalized Throughput Ø Evaluations on four popular open source erasure coders with EC-Bench Onload Offload CPU Cache Jerasure Intel ISA-L Heterogeneity Resource Utilization Gibraltar Mellanox-EC
12 Bench Outline Introduction EC-Bench Evaluation Conclusion and Future Work
13 Bench EC-Bench: Encoding Benchmark Data Buffer Big File 1. Read Chunk D1 Chunk D2 Chunk D3 Chunk D4 2. Encode Coding Buffer Chunk P1 Chunk P2 Chunk P3 - k = 6 - m = 3 Chunk D5 Chunk D6
14 Bench EC-Bench: Decoding Benchmark Big File 1. Read Data Buffer 2. Encode Coding Buffer D1 D2 D3 D4 D5 D6 P1 P2 P3 - k = 6 - m = 3 3. Decode
15 Bench EC-Bench: Parameter Space # Data Chunks # Parity Chunks D1 D2 D3 D4 Dk P1 Pm Chunk Size k the number of data chunks m the number of parity chunks c the size of each chunk
16 Bench EC-Bench: Metrics Ø Throughput!h# = % + ' ( ) * Ø Normalized Throughput o Enable to compare the performance across different configurations o Previous studies have demonstrated that optimal erasure codes take k 1 XOR operations to generate one byte!h# +,-. = % 1 ( ' ( ) * = % 1 ( ' % + ' (!h#
17 Bench EC-Bench: Metrics Ø CPU Utilization!"# #$%&%'($%)* =!"#!,-&./ $ Ø Cache Pressure!(-h. "1.//21. = 31!(-h. 5%//./ $
18 Bench Outline Introduction EC-Bench Evaluation Conclusion and Future Work
19 Bench Evaluation: Open Source Libraries Erasure Coder Specific Hardware Support Description Jerasure Intel ISA-L Gibraltar Mellanox-EC CPU CPU with SSE/AVX GPU IB NIC with EC Offload Jerasure is a CPU-based library released in 27 that supports a wide variety of erasure codes. Compiled without SSE support. Intel Intelligent Storage Acceleration Library (ISA-L) is a collection of optimized low-level functions including erasure coding. The erasure coding functions are optimized for Intel instructions, such as Intel SSE, vector and encryption instructions. Gibraltar is a GPU-based library for Reed- Solomon coding. Mellanox-EC proposed by Mellanox is an HCAbased library for Reed-Solomon coding.
20 Bench Evaluation: Experimental Setup 2.4 GHz Intel(R) Xeon(R) CPU E5-268 v4 o 28 cores, 32KB L1 cache, 256KB L2 cache, and 35MB L3 cache 128GB DRAM Nvidia K8 GPU Mellanox ConnectX-5 IB-EDR (1 Gbps) NIC Explored Configurations (RS(k, m)) o RS(3,2), RS(6,3), RS(1,4) and RS(17,3)
21 Bench Evaluation: Experimental Results Throughput (MB/sec) Jerasure ISA-L Mellanox-EC Gibraltar Chunk Size 512 8K 128K Throughput Performance with Varied Chunk Sizes for RS(3, 2) 2M 32M Normalized Throughput (MB/sec)
22 Bench Evaluation: Experimental Results Throughput (MB/sec) Jerasure ISA-L Mellanox-EC Gibraltar Chunk Size For small chunk sizes (< 32B), Jerasure performs better than Intel ISA-L 8K 128K Throughput Performance with Varied Chunk Sizes for RS(3, 2) 2M 32M Normalized Throughput (MB/sec)
23 Bench Evaluation: Experimental Results Throughput (MB/sec) Jerasure ISA-L Mellanox-EC Gibraltar Chunk Size 512 Chunk size = 2 KB 8K 128K 2M 32M Throughput Performance with Varied Chunk Sizes for RS(3, 2) For both onload coders, the best chunk size to carry out is 2 KB Normalized Throughput (MB/sec)
24 Evaluation: Experimental Results Throughput (MB/sec) Jerasure ISA-L Mellanox-EC Gibraltar Chunk Size Chunk size 512 KB 512 8K 128K 2M 32M Throughput Performance with Varied Chunk Sizes for RS(3, 2) For both offload coders, the best chunk size to carry out is 512 KB Because of data transformation overhead Bench Normalized Throughput (MB/sec)
25 Bench Evaluation: Experimental Results Normalized Throughput (MB/sec) Onload Coders 2KB RS(3, 2) RS(6, 3) RS(1, 4)RS(17, 3) RS(1, 4) is the best configuration for Intel ISA-L and Gibraltar Mellanox-EC performs the best with configuration RS(17, 3) Jerasure with RS(3, 2) outperforms other configurations slightly Offload Coders 512KB RS(3, 2) RS(6, 3) RS(1, 4)RS(17, 3) Jerasure ISA-L Mellanox-EC Gibraltar Normalized Throughput Performance of Onload and Offload Coders
26 Bench Evaluation: Experimental Results CPU Utilization (million cycles / sec) K 4K 16K 64K256K Chunk Size Jerasure ISA-L Mellanox-EC Gibraltar 1M 4M16M CPU Utilization with Varied Chunk Sizes for RS(6, 3) 64M
27 Bench Evaluation: Experimental Results CPU Utilization (million cycles / sec) Chunk size = 32 B K 4K 16K 64K256K Chunk Size Jerasure ISA-L Mellanox-EC Gibraltar 1M 4M16M CPU Utilization with Varied Chunk Sizes for RS(6, 3) 64M In Intel ISA-L, different approaches for < 32 bytes and 32 bytes (details in the function ec_encode_data_avx2)
28 Bench Evaluation: Experimental Results CPU Utilization (million cycles / sec) K 4K 16K 64K256K Chunk Size Jerasure ISA-L Mellanox-EC Gibraltar 1M 4M16M Offload coders make better use of CPU cycles, thus have less impact on applications computation o CPU Utilization with Varied Chunk Sizes for RS(6, 3) With chunk size = 64 MB,.41 million cycles by Mellanox-EC vs million cycles by ISA-L 64M
29 Bench Evaluation: Experimental Results L1 Cache Miss (millions / sec) Jerasure ISA-L Mellanox-EC Gibraltar K 4K 16K Chunk Size 64K 256K Cache Pressure with Varied Chunk Sizes for RS(1, 4) 1M 4M 16M 64M
30 Bench Evaluation: Experimental Results L1 Cache Miss (millions / sec) Jerasure ISA-L Mellanox-EC Gibraltar K 4K 16K Chunk Size 64K 256K Cache Pressure with Varied Chunk Sizes for RS(1, 4) 1M 4M 16M 64M Within onload coders, Intel ISA-L makes better use of L1 cache compared to Jerasure
31 Bench Evaluation: Experimental Results L1 Cache Miss (millions / sec) Jerasure ISA-L Mellanox-EC Gibraltar K 4K 16K Chunk Size 64K 256K Cache Pressure with Varied Chunk Sizes for RS(1, 4) 1M 4M 16M 64M In general, offload coders make less pressure on L1 cache, thus have less impact on applications cache usage
32 Bench Outline Introduction EC-Bench Evaluation Conclusion and Future Work
33 Bench Conclusion and Future Work Ø EC-Bench: An unified benchmark suite to benchmark, measure, and characterize onload and offload erasure coders Ø Evaluations on four popular open source erasure coders with EC-Bench Ø Advanced onload coders outperform offload coders Ø Offload coders make better use of CPU cycles and cache Ø Future work Ø Support more hardware-optimized erasure coders, e.g., FPGA-optimized erasure coders
34 Bench Thank You! {shi.876, lu.932, Network-Based Computing Laboratory The High-Performance Big Data Project
SR-IOV Support for Virtualization on InfiniBand Clusters: Early Experience
SR-IOV Support for Virtualization on InfiniBand Clusters: Early Experience Jithin Jose, Mingzhe Li, Xiaoyi Lu, Krishna Kandalla, Mark Arnold and Dhabaleswar K. (DK) Panda Network-Based Computing Laboratory
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 informationFast Erasure Coding for Data Storage: A Comprehensive Study of the Acceleration Techniques. Tianli Zhou & Chao Tian Texas A&M University
Fast Erasure Coding for Data Storage: A Comprehensive Study of the Acceleration Techniques Tianli Zhou & Chao Tian Texas A&M University 2 Contents Motivation Background and Review Evaluating Individual
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 informationImproving Application Performance and Predictability using Multiple Virtual Lanes in Modern Multi-Core InfiniBand Clusters
Improving Application Performance and Predictability using Multiple Virtual Lanes in Modern Multi-Core InfiniBand Clusters Hari Subramoni, Ping Lai, Sayantan Sur and Dhabhaleswar. K. Panda Department of
More informationMemory Scalability Evaluation of the Next-Generation Intel Bensley Platform with InfiniBand
Memory Scalability Evaluation of the Next-Generation Intel Bensley Platform with InfiniBand Matthew Koop, Wei Huang, Ahbinav Vishnu, Dhabaleswar K. Panda Network-Based Computing Laboratory Department of
More informationSoftware-defined Storage: Fast, Safe and Efficient
Software-defined Storage: Fast, Safe and Efficient TRY NOW Thanks to Blockchain and Intel Intelligent Storage Acceleration Library Every piece of data is required to be stored somewhere. We all know about
More informationImplementing Efficient and Scalable Flow Control Schemes in MPI over InfiniBand
Implementing Efficient and Scalable Flow Control Schemes in MPI over InfiniBand Jiuxing Liu and Dhabaleswar K. Panda Computer Science and Engineering The Ohio State University Presentation Outline Introduction
More informationHADOOP 3.0 is here! Dr. Sandeep Deshmukh Sadepach Labs Pvt. Ltd. - Let us grow together!
HADOOP 3.0 is here! Dr. Sandeep Deshmukh sandeep@sadepach.com Sadepach Labs Pvt. Ltd. - Let us grow together! About me BE from VNIT Nagpur, MTech+PhD from IIT Bombay Worked with Persistent Systems - Life
More informationApplication-Transparent Checkpoint/Restart for MPI Programs over InfiniBand
Application-Transparent Checkpoint/Restart for MPI Programs over InfiniBand Qi Gao, Weikuan Yu, Wei Huang, Dhabaleswar K. Panda Network-Based Computing Laboratory Department of Computer Science & Engineering
More informationA Plugin-based Approach to Exploit RDMA Benefits for Apache and Enterprise HDFS
A Plugin-based Approach to Exploit RDMA Benefits for Apache and Enterprise HDFS Adithya Bhat, Nusrat Islam, Xiaoyi Lu, Md. Wasi- ur- Rahman, Dip: Shankar, and Dhabaleswar K. (DK) Panda Network- Based Compu2ng
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 informationHigh-Performance Training for Deep Learning and Computer Vision HPC
High-Performance Training for Deep Learning and Computer Vision HPC Panel at CVPR-ECV 18 by Dhabaleswar K. (DK) Panda The Ohio State University E-mail: panda@cse.ohio-state.edu http://www.cse.ohio-state.edu/~panda
More informationAccelerating MPI Message Matching and Reduction Collectives For Multi-/Many-core Architectures Mohammadreza Bayatpour, Hari Subramoni, D. K.
Accelerating MPI Message Matching and Reduction Collectives For Multi-/Many-core Architectures Mohammadreza Bayatpour, Hari Subramoni, D. K. Panda Department of Computer Science and Engineering The Ohio
More informationReducing Network Contention with Mixed Workloads on Modern Multicore Clusters
Reducing Network Contention with Mixed Workloads on Modern Multicore Clusters Matthew Koop 1 Miao Luo D. K. Panda matthew.koop@nasa.gov {luom, panda}@cse.ohio-state.edu 1 NASA Center for Computational
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 informationExploiting Full Potential of GPU Clusters with InfiniBand using MVAPICH2-GDR
Exploiting Full Potential of GPU Clusters with InfiniBand using MVAPICH2-GDR Presentation at Mellanox Theater () Dhabaleswar K. (DK) Panda - The Ohio State University panda@cse.ohio-state.edu Outline Communication
More informationEfficient and Scalable Multi-Source Streaming Broadcast on GPU Clusters for Deep Learning
Efficient and Scalable Multi-Source Streaming Broadcast on Clusters for Deep Learning Ching-Hsiang Chu 1, Xiaoyi Lu 1, Ammar A. Awan 1, Hari Subramoni 1, Jahanzeb Hashmi 1, Bracy Elton 2 and Dhabaleswar
More informationDesigning Power-Aware Collective Communication Algorithms for InfiniBand Clusters
Designing Power-Aware Collective Communication Algorithms for InfiniBand Clusters Krishna Kandalla, Emilio P. Mancini, Sayantan Sur, and Dhabaleswar. K. Panda Department of Computer Science & Engineering,
More informationPerformance Analysis and Evaluation of Mellanox ConnectX InfiniBand Architecture with Multi-Core Platforms
Performance Analysis and Evaluation of Mellanox ConnectX InfiniBand Architecture with Multi-Core Platforms Sayantan Sur, Matt Koop, Lei Chai Dhabaleswar K. Panda Network Based Computing Lab, The Ohio State
More informationSupport for GPUs with GPUDirect RDMA in MVAPICH2 SC 13 NVIDIA Booth
Support for GPUs with GPUDirect RDMA in MVAPICH2 SC 13 NVIDIA Booth by D.K. Panda The Ohio State University E-mail: panda@cse.ohio-state.edu http://www.cse.ohio-state.edu/~panda Outline Overview of MVAPICH2-GPU
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 informationMELLANOX EDR UPDATE & GPUDIRECT MELLANOX SR. SE 정연구
MELLANOX EDR UPDATE & GPUDIRECT MELLANOX SR. SE 정연구 Leading Supplier of End-to-End Interconnect Solutions Analyze Enabling the Use of Data Store ICs Comprehensive End-to-End InfiniBand and Ethernet Portfolio
More informationCoupling GPUDirect RDMA and InfiniBand Hardware Multicast Technologies for Streaming Applications
Coupling GPUDirect RDMA and InfiniBand Hardware Multicast Technologies for Streaming Applications GPU Technology Conference GTC 2016 by Dhabaleswar K. (DK) Panda The Ohio State University E-mail: panda@cse.ohio-state.edu
More informationBuilding High Speed Erasure Coding Libraries for ARM and x86 Processors. Per Simonsen, CEO, MemoScale May 2017
Building High Speed Erasure Coding Libraries for ARM and x86 Processors Per Simonsen, CEO, MemoScale May 2017 Agenda MemoScale company and team Erasure coding - brief intro MemoScale erasure codes Performance
More informationPaving the Road to Exascale
Paving the Road to Exascale Gilad Shainer August 2015, MVAPICH User Group (MUG) Meeting The Ever Growing Demand for Performance Performance Terascale Petascale Exascale 1 st Roadrunner 2000 2005 2010 2015
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 informationOptimize Storage Efficiency & Performance with Erasure Coding Hardware Offload. Dror Goldenberg VP Software Architecture Mellanox Technologies
Optimize Storage Efficiency & Performance with Erasure Coding Hardware Offload Dror Goldenberg VP Software Architecture Mellanox Technologies SNIA Legal Notice The material contained in this tutorial is
More informationIn-Network Computing. Sebastian Kalcher, Senior System Engineer HPC. May 2017
In-Network Computing Sebastian Kalcher, Senior System Engineer HPC May 2017 Exponential Data Growth The Need for Intelligent and Faster Interconnect CPU-Centric (Onload) Data-Centric (Offload) Must Wait
More informationEfficient and Truly Passive MPI-3 RMA Synchronization Using InfiniBand Atomics
1 Efficient and Truly Passive MPI-3 RMA Synchronization Using InfiniBand Atomics Mingzhe Li Sreeram Potluri Khaled Hamidouche Jithin Jose Dhabaleswar K. Panda Network-Based Computing Laboratory Department
More informationOasis: An Active Storage Framework for Object Storage Platform
Oasis: An Active Storage Framework for Object Storage Platform Yulai Xie 1, Dan Feng 1, Darrell D. E. Long 2, Yan Li 2 1 School of Computer, Huazhong University of Science and Technology Wuhan National
More informationLatest Advances in MVAPICH2 MPI Library for NVIDIA GPU Clusters with InfiniBand
Latest Advances in MVAPICH2 MPI Library for NVIDIA GPU Clusters with InfiniBand Presentation at GTC 2014 by Dhabaleswar K. (DK) Panda The Ohio State University E-mail: panda@cse.ohio-state.edu http://www.cse.ohio-state.edu/~panda
More informationStudy. Dhabaleswar. K. Panda. The Ohio State University HPIDC '09
RDMA over Ethernet - A Preliminary Study Hari Subramoni, Miao Luo, Ping Lai and Dhabaleswar. K. Panda Computer Science & Engineering Department The Ohio State University Introduction Problem Statement
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 informationRepair Pipelining for Erasure-Coded Storage
Repair Pipelining for Erasure-Coded Storage Runhui Li, Xiaolu Li, Patrick P. C. Lee, Qun Huang The Chinese University of Hong Kong USENIX ATC 2017 1 Introduction Fault tolerance for distributed storage
More informationMulti-Threaded UPC Runtime for GPU to GPU communication over InfiniBand
Multi-Threaded UPC Runtime for GPU to GPU communication over InfiniBand Miao Luo, Hao Wang, & D. K. Panda Network- Based Compu2ng Laboratory Department of Computer Science and Engineering The Ohio State
More informationDesigning High Performance Communication Middleware with Emerging Multi-core Architectures
Designing High Performance Communication Middleware with Emerging Multi-core Architectures Dhabaleswar K. (DK) Panda Department of Computer Science and Engg. The Ohio State University E-mail: panda@cse.ohio-state.edu
More informationBig Data Meets HPC: Exploiting HPC Technologies for Accelerating Big Data Processing and Management
Big Data Meets HPC: Exploiting HPC Technologies for Accelerating Big Data Processing and Management SigHPC BigData BoF (SC 17) by Dhabaleswar K. (DK) Panda The Ohio State University E-mail: panda@cse.ohio-state.edu
More informationExploiting InfiniBand and GPUDirect Technology for High Performance Collectives on GPU Clusters
Exploiting InfiniBand and Direct Technology for High Performance Collectives on Clusters Ching-Hsiang Chu chu.368@osu.edu Department of Computer Science and Engineering The Ohio State University OSU Booth
More informationUnified Runtime for PGAS and MPI over OFED
Unified Runtime for PGAS and MPI over OFED D. K. Panda and Sayantan Sur Network-Based Computing Laboratory Department of Computer Science and Engineering The Ohio State University, USA Outline Introduction
More informationInfiniBand Networked Flash Storage
InfiniBand Networked Flash Storage Superior Performance, Efficiency and Scalability Motti Beck Director Enterprise Market Development, Mellanox Technologies Flash Memory Summit 2016 Santa Clara, CA 1 17PB
More informationAccelerating MPI Message Matching and Reduction Collectives For Multi-/Many-core Architectures
Accelerating MPI Message Matching and Reduction Collectives For Multi-/Many-core Architectures M. Bayatpour, S. Chakraborty, H. Subramoni, X. Lu, and D. K. Panda Department of Computer Science and Engineering
More informationMPI Alltoall Personalized Exchange on GPGPU Clusters: Design Alternatives and Benefits
MPI Alltoall Personalized Exchange on GPGPU Clusters: Design Alternatives and Benefits Ashish Kumar Singh, Sreeram Potluri, Hao Wang, Krishna Kandalla, Sayantan Sur, and Dhabaleswar K. Panda Network-Based
More informationCharacterizing and Benchmarking Deep Learning Systems on Modern Data Center Architectures
Characterizing and Benchmarking Deep Learning Systems on Modern Data Center Architectures Talk at Bench 2018 by Xiaoyi Lu The Ohio State University E-mail: luxi@cse.ohio-state.edu http://www.cse.ohio-state.edu/~luxi
More informationMeltdown and Spectre Interconnect Performance Evaluation Jan Mellanox Technologies
Meltdown and Spectre Interconnect Evaluation Jan 2018 1 Meltdown and Spectre - Background Most modern processors perform speculative execution This speculation can be measured, disclosing information about
More informationInterconnect Your Future
Interconnect Your Future Paving the Road to Exascale August 2017 Exponential Data Growth The Need for Intelligent and Faster Interconnect CPU-Centric (Onload) Data-Centric (Offload) Must Wait for the Data
More informationIn the multi-core age, How do larger, faster and cheaper and more responsive memory sub-systems affect data management? Dhabaleswar K.
In the multi-core age, How do larger, faster and cheaper and more responsive sub-systems affect data management? Panel at ADMS 211 Dhabaleswar K. (DK) Panda Network-Based Computing Laboratory Department
More informationApache Hadoop 3. Balazs Gaspar Sales Engineer CEE & CIS Cloudera, Inc. All rights reserved.
Apache Hadoop 3 Balazs Gaspar Sales Engineer CEE & CIS balazs@cloudera.com 1 We believe data can make what is impossible today, possible tomorrow 2 We empower people to transform complex data into clear
More informationDesigning High-Performance Non-Volatile Memory-aware RDMA Communication Protocols for Big Data Processing
Designing High-Performance Non-Volatile Memory-aware RDMA Communication Protocols for Big Data Processing Talk at Storage Developer Conference SNIA 2018 by Xiaoyi Lu The Ohio State University E-mail: luxi@cse.ohio-state.edu
More informationStorage. CS 3410 Computer System Organization & Programming
Storage CS 3410 Computer System Organization & Programming These slides are the product of many rounds of teaching CS 3410 by Deniz Altinbuke, Kevin Walsh, and Professors Weatherspoon, Bala, Bracy, and
More informationIn-Network Computing. Paving the Road to Exascale. 5th Annual MVAPICH User Group (MUG) Meeting, August 2017
In-Network Computing Paving the Road to Exascale 5th Annual MVAPICH User Group (MUG) Meeting, August 2017 Exponential Data Growth The Need for Intelligent and Faster Interconnect CPU-Centric (Onload) Data-Centric
More informationA Case for High Performance Computing with Virtual Machines
A Case for High Performance Computing with Virtual Machines Wei Huang*, Jiuxing Liu +, Bulent Abali +, and Dhabaleswar K. Panda* *The Ohio State University +IBM T. J. Waston Research Center Presentation
More informationSolutions for Scalable HPC
Solutions for Scalable HPC Scot Schultz, Director HPC/Technical Computing HPC Advisory Council Stanford Conference Feb 2014 Leading Supplier of End-to-End Interconnect Solutions Comprehensive End-to-End
More informationFPGA Implementation of Erasure Codes in NVMe based JBOFs
FPGA Implementation of Erasure Codes in NVMe based JBOFs Manoj Roge Director, Data Center Xilinx Inc. Santa Clara, CA 1 Acknowledgement Shre Shah Data Center Architect, Xilinx Santa Clara, CA 2 Agenda
More informationErasure coding and AONT algorithm selection for Secure Distributed Storage. Alem Abreha Sowmya Shetty
Erasure coding and AONT algorithm selection for Secure Distributed Storage Alem Abreha Sowmya Shetty Secure Distributed Storage AONT(All-Or-Nothing Transform) unkeyed transformation φ mapping a sequence
More informationAn Execution Strategy and Optimized Runtime Support for Parallelizing Irregular Reductions on Modern GPUs
An Execution Strategy and Optimized Runtime Support for Parallelizing Irregular Reductions on Modern GPUs Xin Huo, Vignesh T. Ravi, Wenjing Ma and Gagan Agrawal Department of Computer Science and Engineering
More informationUnifying UPC and MPI Runtimes: Experience with MVAPICH
Unifying UPC and MPI Runtimes: Experience with MVAPICH Jithin Jose Miao Luo Sayantan Sur D. K. Panda Network-Based Computing Laboratory Department of Computer Science and Engineering The Ohio State University,
More informationEvolving HPC Solutions Using Open Source Software & Industry-Standard Hardware
CLUSTER TO CLOUD Evolving HPC Solutions Using Open Source Software & Industry-Standard Hardware Carl Trieloff cctrieloff@redhat.com Red Hat, Technical Director Lee Fisher lee.fisher@hp.com Hewlett-Packard,
More informationHigh-Performance and Scalable Non-Blocking All-to-All with Collective Offload on InfiniBand Clusters: A study with Parallel 3DFFT
High-Performance and Scalable Non-Blocking All-to-All with Collective Offload on InfiniBand Clusters: A study with Parallel 3DFFT Krishna Kandalla (1), Hari Subramoni (1), Karen Tomko (2), Dmitry Pekurovsky
More informationIn-Network Computing. Paving the Road to Exascale. June 2017
In-Network Computing Paving the Road to Exascale June 2017 Exponential Data Growth The Need for Intelligent and Faster Interconnect -Centric (Onload) Data-Centric (Offload) Must Wait for the Data Creates
More informationHigh Performance Computing
High Performance Computing Dror Goldenberg, HPCAC Switzerland Conference March 2015 End-to-End Interconnect Solutions for All Platforms Highest Performance and Scalability for X86, Power, GPU, ARM and
More informationEvaluating the Impact of RDMA on Storage I/O over InfiniBand
Evaluating the Impact of RDMA on Storage I/O over InfiniBand J Liu, DK Panda and M Banikazemi Computer and Information Science IBM T J Watson Research Center The Ohio State University Presentation Outline
More informationSpark Over RDMA: Accelerate Big Data SC Asia 2018 Ido Shamay Mellanox Technologies
Spark Over RDMA: Accelerate Big Data SC Asia 2018 Ido Shamay 1 Apache Spark - Intro Spark within the Big Data ecosystem Data Sources Data Acquisition / ETL Data Storage Data Analysis / ML Serving 3 Apache
More informationWHITE PAPER SINGLE & MULTI CORE PERFORMANCE OF AN ERASURE CODING WORKLOAD ON AMD EPYC
WHITE PAPER SINGLE & MULTI CORE PERFORMANCE OF AN ERASURE CODING WORKLOAD ON AMD EPYC INTRODUCTION With the EPYC processor line, AMD is expected to take a strong position in the server market including
More informationImproving Cloud Storage Cost and Data Resiliency with Erasure Codes Michael Penick
Improving Cloud Storage Cost and Data Resiliency with Erasure Codes Michael Penick Commodity Storage Hosting storage FTP backup Goals Inexpensive (use commodity hardware) Resilient to failures Highly available
More informationDeep Learning Performance and Cost Evaluation
Micron 5210 ION Quad-Level Cell (QLC) SSDs vs 7200 RPM HDDs in Centralized NAS Storage Repositories A Technical White Paper Rene Meyer, Ph.D. AMAX Corporation Publish date: October 25, 2018 Abstract Introduction
More informationHigh Performance File System and I/O Middleware Design for Big Data on HPC Clusters
High Performance File System and I/O Middleware Design for Big Data on HPC Clusters by Nusrat Sharmin Islam Advisor: Dhabaleswar K. (DK) Panda Department of Computer Science and Engineering The Ohio State
More informationA Performance Evaluation of Open Source Erasure Codes for Storage Applications
A Performance Evaluation of Open Source Erasure Codes for Storage Applications James S. Plank Catherine D. Schuman (Tennessee) Jianqiang Luo Lihao Xu (Wayne State) Zooko Wilcox-O'Hearn Usenix FAST February
More informationFacilitating Magnetic Recording Technology Scaling for Data Center Hard Disk Drives through Filesystem-level Transparent Local Erasure Coding
Facilitating Magnetic Recording Technology Scaling for Data Center Hard Disk Drives through Filesystem-level Transparent Local Erasure Coding Yin Li, Hao Wang, Xuebin Zhang, Ning Zheng, Shafa Dahandeh,
More informationEnhancing Checkpoint Performance with Staging IO & SSD
Enhancing Checkpoint Performance with Staging IO & SSD Xiangyong Ouyang Sonya Marcarelli Dhabaleswar K. Panda Department of Computer Science & Engineering The Ohio State University Outline Motivation and
More informationExploration of Cache Coherent CPU- FPGA Heterogeneous System
Exploration of Cache Coherent CPU- FPGA Heterogeneous System Wei Zhang Department of Electronic and Computer Engineering Hong Kong University of Science and Technology 1 Outline ointroduction to FPGA-based
More informationOptimized Non-contiguous MPI Datatype Communication for GPU Clusters: Design, Implementation and Evaluation with MVAPICH2
Optimized Non-contiguous MPI Datatype Communication for GPU Clusters: Design, Implementation and Evaluation with MVAPICH2 H. Wang, S. Potluri, M. Luo, A. K. Singh, X. Ouyang, S. Sur, D. K. Panda Network-Based
More informationAccelerating String Matching Algorithms on Multicore Processors Cheng-Hung Lin
Accelerating String Matching Algorithms on Multicore Processors Cheng-Hung Lin Department of Electrical Engineering, National Taiwan Normal University, Taipei, Taiwan Abstract String matching is the most
More informationModern Erasure Codes for Distributed Storage Systems
Modern Erasure Codes for Distributed Storage Systems Storage Developer Conference, SNIA, Bangalore Srinivasan Narayanamurthy Advanced Technology Group, NetApp May 27 th 2016 1 Everything around us is changing!
More informationCooperative VM Migration for a virtualized HPC Cluster with VMM-bypass I/O devices
Cooperative VM Migration for a virtualized HPC Cluster with VMM-bypass I/O devices Ryousei Takano, Hidemoto Nakada, Takahiro Hirofuchi, Yoshio Tanaka, and Tomohiro Kudoh Information Technology Research
More informationAccelerating HPL on Heterogeneous GPU Clusters
Accelerating HPL on Heterogeneous GPU Clusters Presentation at GTC 2014 by Dhabaleswar K. (DK) Panda The Ohio State University E-mail: panda@cse.ohio-state.edu http://www.cse.ohio-state.edu/~panda Outline
More informationOptimizing MPI Communication on Multi-GPU Systems using CUDA Inter-Process Communication
Optimizing MPI Communication on Multi-GPU Systems using CUDA Inter-Process Communication Sreeram Potluri* Hao Wang* Devendar Bureddy* Ashish Kumar Singh* Carlos Rosales + Dhabaleswar K. Panda* *Network-Based
More informationLearning with Purpose
Network Measurement for 100Gbps Links Using Multicore Processors Xiaoban Wu, Dr. Peilong Li, Dr. Yongyi Ran, Prof. Yan Luo Department of Electrical and Computer Engineering University of Massachusetts
More informationFROM HPC TO THE CLOUD WITH AMQP AND OPEN SOURCE SOFTWARE
FROM HPC TO THE CLOUD WITH AMQP AND OPEN SOURCE SOFTWARE Carl Trieloff cctrieloff@redhat.com Red Hat Lee Fisher lee.fisher@hp.com Hewlett-Packard High Performance Computing on Wall Street conference 14
More informationHigh-Performance Broadcast for Streaming and Deep Learning
High-Performance Broadcast for Streaming and Deep Learning Ching-Hsiang Chu chu.368@osu.edu Department of Computer Science and Engineering The Ohio State University OSU Booth - SC17 2 Outline Introduction
More informationApplication Acceleration Beyond Flash Storage
Application Acceleration Beyond Flash Storage Session 303C Mellanox Technologies Flash Memory Summit July 2014 Accelerating Applications, Step-by-Step First Steps Make compute fast Moore s Law Make storage
More informationNotices and Disclaimers
Greg Tucker, Intel Notices and Disclaimers Intel technologies features and benefits depend on system configuration and may require enabled hardware, software or service activation. Learn more at intel.com,
More informationIntra-MIC MPI Communication using MVAPICH2: Early Experience
Intra-MIC MPI Communication using MVAPICH: Early Experience Sreeram Potluri, Karen Tomko, Devendar Bureddy, and Dhabaleswar K. Panda Department of Computer Science and Engineering Ohio State University
More informationInterconnect Your Future
Interconnect Your Future Gilad Shainer 2nd Annual MVAPICH User Group (MUG) Meeting, August 2014 Complete High-Performance Scalable Interconnect Infrastructure Comprehensive End-to-End Software Accelerators
More informationDesigning High Performance Heterogeneous Broadcast for Streaming Applications on GPU Clusters
Designing High Performance Heterogeneous Broadcast for Streaming Applications on Clusters 1 Ching-Hsiang Chu, 1 Khaled Hamidouche, 1 Hari Subramoni, 1 Akshay Venkatesh, 2 Bracy Elton and 1 Dhabaleswar
More informationX10 specific Optimization of CPU GPU Data transfer with Pinned Memory Management
X10 specific Optimization of CPU GPU Data transfer with Pinned Memory Management Hideyuki Shamoto, Tatsuhiro Chiba, Mikio Takeuchi Tokyo Institute of Technology IBM Research Tokyo Programming for large
More informationNFS/RDMA over 40Gbps iwarp Wael Noureddine Chelsio Communications
NFS/RDMA over 40Gbps iwarp Wael Noureddine Chelsio Communications Outline RDMA Motivating trends iwarp NFS over RDMA Overview Chelsio T5 support Performance results 2 Adoption Rate of 40GbE Source: Crehan
More informationDesigning High Performance DSM Systems using InfiniBand Features
Designing High Performance DSM Systems using InfiniBand Features Ranjit Noronha and Dhabaleswar K. Panda The Ohio State University NBC Outline Introduction Motivation Design and Implementation Results
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 informationInterconnect Your Future
Interconnect Your Future Smart Interconnect for Next Generation HPC Platforms Gilad Shainer, August 2016, 4th Annual MVAPICH User Group (MUG) Meeting Mellanox Connects the World s Fastest Supercomputer
More informationModern Erasure Codes for Distributed Storage Systems
Modern Erasure Codes for Distributed Storage Systems Srinivasan Narayanamurthy (Srini) NetApp Everything around us is changing! r The Data Deluge r Disk capacities and densities are increasing faster than
More informationDeep Learning Performance and Cost Evaluation
Micron 5210 ION Quad-Level Cell (QLC) SSDs vs 7200 RPM HDDs in Centralized NAS Storage Repositories A Technical White Paper Don Wang, Rene Meyer, Ph.D. info@ AMAX Corporation Publish date: October 25,
More informationEvaluation and Exploration of Next Generation Systems for Applicability and Performance Volodymyr Kindratenko Guochun Shi
Evaluation and Exploration of Next Generation Systems for Applicability and Performance Volodymyr Kindratenko Guochun Shi National Center for Supercomputing Applications University of Illinois at Urbana-Champaign
More informationThis Unit: Main Memory. Building a Memory System. First Memory System Design. An Example Memory System
This Unit: Main Memory Building a Memory System Application OS Compiler Firmware CPU I/O Memory Digital Circuits Gates & Transistors Memory hierarchy review DRAM technology A few more transistors Organization:
More informationS. Narravula, P. Balaji, K. Vaidyanathan, H.-W. Jin and D. K. Panda. The Ohio State University
Architecture for Caching Responses with Multiple Dynamic Dependencies in Multi-Tier Data- Centers over InfiniBand S. Narravula, P. Balaji, K. Vaidyanathan, H.-W. Jin and D. K. Panda The Ohio State University
More informationMATE-EC2: A Middleware for Processing Data with Amazon Web Services
MATE-EC2: A Middleware for Processing Data with Amazon Web Services Tekin Bicer David Chiu* and Gagan Agrawal Department of Compute Science and Engineering Ohio State University * School of Engineering
More informationGPU- Aware Design, Implementation, and Evaluation of Non- blocking Collective Benchmarks
GPU- Aware Design, Implementation, and Evaluation of Non- blocking Collective Benchmarks Presented By : Esthela Gallardo Ammar Ahmad Awan, Khaled Hamidouche, Akshay Venkatesh, Jonathan Perkins, Hari Subramoni,
More informationDesigning High-Performance MPI Collectives in MVAPICH2 for HPC and Deep Learning
5th ANNUAL WORKSHOP 209 Designing High-Performance MPI Collectives in MVAPICH2 for HPC and Deep Learning Hari Subramoni Dhabaleswar K. (DK) Panda The Ohio State University The Ohio State University E-mail:
More information10GE network tests with UDP. Janusz Szuba European XFEL
10GE network tests with UDP Janusz Szuba European XFEL Outline 2 Overview of initial DAQ architecture Slice test hardware specification Initial networking test results DAQ software UDP tests Summary 10GE
More informationIMPROVING ENERGY EFFICIENCY THROUGH PARALLELIZATION AND VECTORIZATION ON INTEL R CORE TM
IMPROVING ENERGY EFFICIENCY THROUGH PARALLELIZATION AND VECTORIZATION ON INTEL R CORE TM I5 AND I7 PROCESSORS Juan M. Cebrián 1 Lasse Natvig 1 Jan Christian Meyer 2 1 Depart. of Computer and Information
More information