Can we boost more HPC performance? Integrate IBM POWER servers with GPUs to OpenStack Environment

Size: px
Start display at page:

Download "Can we boost more HPC performance? Integrate IBM POWER servers with GPUs to OpenStack Environment"

Transcription

1 Can we boost more HPC performance? Integrate IBM POWER servers with GPUs to OpenStack Environment Ankit Purohit, Takeaki Matsumoto Transform your business, transcend expectations with our technologically advanced solutions.

2 Self-Introduction Ankit Purohit Takeaki Matsumoto NTT Communications Technology Development NTT Communications Technology Development High Performance Computing GPU R&D for OpenStack Ops for Private Cloud 1

3 Previous talk at OpenPOWER Summit 2018 March 19, 2018 at Las Vegas OpenPOWER Summit Website: Co-speaker : Yutaka Kawai, IBM Japan Our Talk s Video: Topics * KVM on POWER * Many other Benchmarks 2

4 Agenda Background Our OpenStack GPU cloud Motivation for using POWER server Goal Can we boost more performance with POWER? Approach Unleash POWER s full performance as Baremetal server Integrate POWER server into OpenStack Cloud Conclusion Another choice: Kubernetes 3

5 Agenda Background Our OpenStack GPU cloud Motivation for using POWER server Goal Can we boost more performance with POWER? Approach Unleash POWER s full performance as Baremetal server Integrate POWER server into OpenStack Cloud Conclusion Another choice: Kubernetes 4

6 Background NTT Communications The largest Telecommunications company in Japan Subsidiaries and offices in over 110 cities worldwide Part of a Fortune Global 100 company Our team provide GPU cloud using OpenStack, for in-house users experimental usage. AI communication engine COTOHA Deep Learning training on customer data (time-series) etc. 5

7 Our OpenStack Environment Image source: x86 servers (as compute nodes) nvidia nvidia nvidia K10 GPU M60 GPU P100 GPU 6

8 Motivation to try IBM POWER system Even with same GPU card... different server architecture brings us better performance? Intel based system : DGX-1 IBM POWER8 system : Minsky - CPU and GPU are connected via PCle (32 GB/s) - CPU and GPU are connected via NVLink (80 GB/s) - Bandwidth between CPU sockets is 64 GB/s - Bandwidth between CPU sockets is 76.8 GB/s - Bandwidth between CPU and memory is 76.8 GB/s - Bandwidth between CPU and memory is 115 GB/s 76.8 GB/s 64 GB/s 76.8 GB/s 32 GB/s 76.8 GB/s 7

9 Goal How can we boost more performance with POWER? 8

10 Agenda Background Our OpenStack GPU cloud Motivation for using POWER server Goal Can we boost more performance with POWER? Approach Unleash POWER s full performance as Baremetal server Integrate POWER server into OpenStack Cloud Conclusion Another choice: Kubernetes 9

11 Benchmark program: nbody - nbody is kind of cuda sample program. This program can calculate single precision and double precision by using GPU and the results are displayed in GFLOPS. It can be also calculated by CPU only. $./nbody -benchmark -numbodies= numdevices=1 -benchmark : (run benchmark to measure performance) -numbodies : (number of bodies (>= 1) to run in simulation) (for GPU benchmark , for CPU benchmark 20480) -numdevice : (where i=(number of CUDA devices > 0) to use for simulation) -cpu : (run n-body simulation on the CPU)] -fp64 : (use double precision floating point values for simulation) 10

12 Benchmark program: nbody We use nbody to emulate memory intensive workflow In nbody, GPU directly access data from host memory (Main memory) many times NVLink(or PCle) Bottleneck? CPU GPU0 GPU1... Zero-copy Main Memory GPU Memory GPU Memory nbody data flow 11

13 Benchmark Result: POWER8 baremetal (1/2) With default server configuration Workload: numbodies= , FP32 on Minsky w/ RHEL7.3 1GPU 2GPU 2GPU 4GPU When using 4 GPUs, there is low performance than 2 GPUs because it is not scaled When using 2 GPUs, specifying different GPUs causes different performance. Why?! T. Kamenoue, M. Mitsugi, and Y. Kawai, "The optimization of nbody simulation on Multi-GPU environment in Proc. the 80th National Convention of Information Processing Society of Japan (IPSJ), Tokyo, Japan, Mar. 2018, pp. 1-25,26. 12

14 A Solution : Memory Interleave What memory Interleave actually does?? - It enables equally use of memories of all the node (CPU sockets) in round robin way. - I/O access can be balanced - it works well for the case of nbody benchmark (FP32) - How to execute? numactl -interleave=all./nbody Interleave disabled(default) OR numactl -i all./nbody... Interleave enabled T. Kamenoue, M. Mitsugi, and Y. Kawai, "The optimization of nbody simulation on Multi-GPU environment in Proc. the 80th National Convention of Information Processing Society of Japan (IPSJ), Tokyo, Japan, Mar. 2018, pp. 1-25,26. 13

15 What happens if Interleave is disabled? System Memory workload : FP32, numbodies= , 4GPU, Interleave disabled System Memory 115 GB/s 115 GB/s POWER8 GPU0 and GPU1 always reads from CLOSE Memory GPU2 and GPU3 always reads from FAR Memory - Elapsed Time Per 1 Iteration GPU 0 : Second GPU 1 : Second GPU 2 : Second GPU 3 : Second Benchmark Result : 8673 GFLOP/s POWER8 CPU1 CPU0 80 GB/s NVLink P100 GPU0 GPU Memory 80 GB/s NVLink P100 GPU1 P100 GPU2 GPU Memory GPU Memory 80 GB/s P100 GPU3 GPU Memory 1 Iteration T. Kamenoue, M. Mitsugi, and Y. Kawai, "The optimization of nbody simulation on Multi-GPU environment in Proc. the 80th National Convention of Information Processing Society of Japan (IPSJ), Tokyo, Japan, Mar. 2018, pp. 1-25,26. 14

16 What happens if Interleave is enabled? System Memory workload : FP32, numbodies= , 4GPU, Interleave enabled System Memory 115 GB/s 115 GB/s POWER8 GPU0 and GPU1 always reads 1/2 data from CLOSE Memory 1/2 data from FAR Memory All GPUs read same as above - Elapsed Time Per 1 Iteration GPU 0 : Second GPU 1 : Second GPU 2 : Second GPU 3 : Second Benchmark Result : GFLOP/s POWER8 CPU1 CPU0 80 GB/s NVLink P100 GPU0 GPU Memory 80 GB/s NVLink P100 GPU1 P100 GPU2 GPU Memory GPU Memory 80 GB/s P100 GPU3 GPU Memory 1 Iteration T. Kamenoue, M. Mitsugi, and Y. Kawai, "The optimization of nbody simulation on Multi-GPU environment in Proc. the 80th National Convention of Information Processing Society of Japan (IPSJ), Tokyo, Japan, Mar. 2018, pp. 1-25,26. 15

17 Benchmark Result: POWER8 baremetal (2/2) With memory interleave enabled Workload: numbodies= , FP32 on Minsky w/ RHEL7.3 1GPU 2GPU 2GPU 4GPU Now it is scaled. 4 GPU case has becomes faster than 2 GPU. T. Kamenoue, M. Mitsugi, and Y. Kawai, "The optimization of nbody simulation on Multi-GPU environment in Proc. the 80th National Convention of Information Processing Society of Japan (IPSJ), Tokyo, Japan, Mar. 2018, pp. 1-25,26. 16

18 Benchmark Result: POWER8 vs DGX-1 baremetal nbody result when increasing GPU number Workload: numbodies= , FP32 1GPU 2GPU 4GPU GFLOP/s POWER8 DGX-1 - Current Intel Architecture machine can not take benefit from Memory Interleave because of its narrow I/O bandwidth. 17

19 Agenda Background Our OpenStack GPU cloud Motivation for using POWER server Goal Can we boost more performance with POWER? Approach Unleash POWER s full performance as Baremetal server Integrate POWER server into OpenStack Cloud Conclusion Another choice: Kubernetes 18

20 How to integrate POWER8 to OpenStack nova-api nova-scheduler nova-conductor Controller (x86) nova-compute Compute (x86) nova-compute Compute (x86) nova-compute Compute (ppc64le) 19

21 How to integrate POWER8 to OpenStack Linux can run on POWER8 KVM can run on POWER8 OpenStack can run on POWER8 Cloud Archive repository available Basically, same procedure can be used as x86 20

22 How to integrate POWER8 to OpenStack For GPU, we need KVM PCI-Passthrough KVM support qemu (1:2.6.1+dfsg-0ubuntu2) xenial; urgency=medium Enable GPU Passthru for ppc64le IOMMU (like Intel VT-d) In POWER servers, IBM Translation Control Entry is available 21

23 How to integrate POWER8 to OpenStack Environment OpenPOWER IBM S822LC for HPC "Minsky" CPU: 20 cores (logical: 160 cores) MEM: 1TB GPU: NVIDIA P100 * 4 (with NVLink) OS Ubuntu (kernel: generic) Software KVM 2.11 Nova (Queens) 22

24 How to integrate POWER8 to OpenStack Configuration Kernel parameters Disable SMT vfio-pci.disable_idle_d3=1 $ ppc64_cpu --smt=off Disable nouveau driver $ cat /etc/modprobe.d/blacklist-nouveau.conf blacklist nouveau blacklist lbm-nouveau options nouveau modeset=0 alias nouveau off $ sudo update-initramfs -u $ reboot $ lsmod grep nouveau 23

25 How to integrate POWER8 to OpenStack Nova Configuration Compute node Ensure PCI device id nova.conf $ lspci -nn grep -i nvidia 0002:01:00.0 3D controller [0302]: NVIDIA Corporation Device [10de:15f9] (rev a1) [default] pci_passthrough_whitelist={"vendor_id":"10de","product_id":"15f9"} Controller node nova.conf [default] pci_alias= {"vendor_id":"10de", "product_id":"15f9", "name": "P100"} [filter_scheduler] enabled_filters =,PciPassthroughFilter 24

26 Our OpenStack Environment: After Integration Image source: x86 servers POWER8 servers nvidia nvidia nvidia nvidia K10 GPU M60 GPU P100 GPU P100 GPU 25

27 Benchmark of OpenStack-integrated VM Instance flavor vcpu: 16 Mem: 120GB Disk: 160GB Metadata: pci_passthrough:alias=p100:4 hw:mem_page_size=16384 hw:numa_nodes=2 GPU environment NVIDIA Driver: CUDA:

28 Benchmark of OpenStack-integrated VM nbody benchmark results $ numactl -i all./nbody -benchmark -numbodies= GPU 2GPU 4GPU 27

29 Benchmark of OpenStack-integrated VM CPU-GPU Memory bandwidth benchmark results $./bandwidthtest 28

30 Benchmark of OpenStack-integrated VM CPU-GPU Memory bandwidth benchmark results $./bandwidthtest Why? 29

31 Benchmark of OpenStack-integrated VM NVLink implementation Physical Linux recognize CPU NVLink (2.5x PCIe GPU PCI CPU NVLink Device NVLink Device GPU 30

32 Benchmark of OpenStack-integrated VM OpenStack attached only GPU VM PCI-Passthrough NVLink Device PCIe x8 NVLink Device GPU 31

33 Benchmark of OpenStack-integrated VM Passthrough 3 devices solve this issue? PCI-Passthrough VM NVLink Device NVLink Device GPU 32

34 Benchmark of OpenStack-integrated VM GPU loc-code $ lspci -d 10de:15f9 0002:01:00.0 3D controller: NVIDIA Corporation Device 15f9 (rev a1) 0003:01:00.0 3D controller: NVIDIA Corporation Device 15f9 (rev a1) 000a:01:00.0 3D controller: NVIDIA Corporation Device 15f9 (rev a1) 000b:01:00.0 3D controller: NVIDIA Corporation Device 15f9 (rev a1) $ cat /sys/bus/pci/devices/0002\:01\:00.0/of_node/ibm\,loc-code GPU1 $ cat /sys/bus/pci/devices/0003\:01\:00.0/of_node/ibm\,loc-code GPU2 $ cat /sys/bus/pci/devices/000a\:01\:00.0/of_node/ibm\,loc-code GPU3 $ cat /sys/bus/pci/devices/000b\:01\:00.0/of_node/ibm\,loc-code GPU4 33

35 Benchmark of OpenStack-integrated VM NVLink devices and its connection $ lspci -d 1014:04ea 0004:00:00.0 Bridge: IBM Device 04ea 0004:00:00.1 Bridge: IBM Device 04ea 0004:00:01.0 Bridge: IBM Device 04ea 0004:00:01.1 Bridge: IBM Device 04ea 0005:00:00.0 Bridge: IBM Device 04ea 0005:00:00.1 Bridge: IBM Device 04ea 0005:00:01.0 Bridge: IBM Device 04ea 0005:00:01.1 Bridge: IBM Device 04ea $ cat /sys/bus/pci/devices/0004\:00\:00.0/of_node/ibm\,loc-code GPU2 $ cat /sys/bus/pci/devices/0004\:00\:00.1/of_node/ibm\,loc-code GPU2 $ cat /sys/bus/pci/devices/0004\:00\:01.0/of_node/ibm\,loc-code GPU1 $ cat /sys/bus/pci/devices/0004\:00\:01.1/of_node/ibm\,loc-code GPU1 $ cat /sys/bus/pci/devices/0005\:00\:00.0/of_node/ibm\,loc-code GPU4 $ cat /sys/bus/pci/devices/0005\:00\:00.1/of_node/ibm\,loc-code GPU4 $ cat /sys/bus/pci/devices/0005\:00\:01.0/of_node/ibm\,loc-code GPU3 $ cat /sys/bus/pci/devices/0005\:00\:01.1/of_node/ibm\,loc-code GPU3 34

36 Benchmark of OpenStack-integrated VM Add NVLink devices (by hand) ~~~ <hostdev mode='subsystem' type='pci' managed='yes'> <source> <address domain='0x0002' bus='0x01' slot='0x00' function='0x0'/> </source> <address type='pci' domain='0x0000' bus='0x00' slot='0x8' function='0x0'/> </hostdev> instance xx.xml <hostdev mode='subsystem' type='pci' managed='yes'> <source> <address domain='0x0004' bus='0x00' slot='0x01' function='0x0'/> </source> <address type='pci' domain='0x0000' bus='0x00' slot='0x9' function='0x0' multifunction='on'/> </hostdev> <hostdev mode='subsystem' type='pci' managed='yes'> <source> <address domain='0x0004' bus='0x00' slot='0x01' function='0x1'/> </source> <address type='pci' domain='0x0000' bus='0x00' slot='0x9' function='0x1'/> </hostdev> ~~~ 35

37 Benchmark of OpenStack-integrated VM CPU-GPU Memory bandwidth benchmark results with NVLink device added 36

38 Benchmark of OpenStack-integrated VM nbody benchmark results with NVLink device with NVLink device added 1GPU 2GPU 4GPU 37

39 How can we manage NVLink devices? OpenStack doesn't care about device connection 1014:04ea pool 10de:15f9 pool NVLink Device GPU1 NVLink Device GPU1 NVLink Device GPU2 NVLink Device GPU2 NVLink Device GPU3 NVLink Device GPU3 NVLink Device GPU4 NVLink Device GPU4 GPU1 GPU2 GPU3 GPU4 Request P100:1,NVLink:2 38

40 How can we manage NVLink devices? In ideal device_set_p100 pool GPU1 NVLink Device GPU1 NVLink Device GPU1 GPU3 NVLink Device GPU3 NVLink Device GPU3 GPU2 NVLink Device GPU2 NVLink Device GPU2 GPU4 NVLink Device GPU4 NVLink Device GPU4 Request device_set_p100:1 39

41 How can we manage NVLink devices? Our solution Add simple script between libvirt and qemu Rename qemu-system-ppc64 to qemu-system-ppc64.orig Add the script as qemu-system-ppc64 Nova libvirt script qemu Add NVLink devices parameters Launch VM with P100 and NVLink devices Request P100 40

42 Agenda Background Our OpenStack GPU cloud Motivation for using POWER server Goal Can we boost more performance with POWER? Approach Unleash POWER s full performance as Baremetal server Integrate POWER server into OpenStack Cloud Conclusion Another choice: Kubernetes 41

43 Conclusion How can we boost more performance with POWER? Memory interleave may be required to get max performance Add POWER as compute node into OpenStack Specify GPU and its NVLink devices to passthrough to VM Power8 results better performance than x86 in some cases It has powerful NVLink CPU-GPU connection With OpenStack, some limitations exists SMT is no available NVLink requires extra device allocation OpenStack doesn't support now 42

44 Agenda Background Our OpenStack GPU cloud Motivation for using POWER server Goal Can we boost more performance with POWER? Approach Unleash POWER s full performance as Baremetal server Integrate POWER server into OpenStack Cloud Conclusion Another choice: Kubernetes 43

45 Another option How is the container? 44

46 Another option How to manage containers and GPUs 45

47 Another option Kubernetes schedules containers can integrate with OpenStack supports GPU scheduler requirements NVIDIA drivers ~= Device Plugin feature NVIDIA device plugin for Kubernetes nvidia-docker 46

48 Another option Device plugin feature NVIDIA device plugin for Kubernetes nvidia-docker NVIDIA Driver NVIDIA GPU 47

49 Another option Device Plugin feature Add kubelet exec parameter <= K8s version 1.9 "-feature-gates=deviceplugins=true" Example: deployed by kubeadm $ cat /etc/systemd/system/kubelet.service.d/10-kubeadm.conf grep KUBELET_EXTRA_ARGS= Environment="KUBELET_EXTRA_ARGS=--feature-gates=DevicePlugins=true" Device Plugins feature is Beta >= K8s version 1.10 Enabled by default Note: If you deploy k8s using kubeadm and the controller is x86, you have to do like $ docker tag gcr.io/google_containers/kube-proxy-ppc64le:v1.9.2 gcr.io/google_containers/kube-proxy:v

50 Another option NVIDIA device plugin for Kubernetes Build image for ppc64le $ docker build. -t nvidia/k8s-device-plugin:1.9 49

51 Another option nvidia-docker (2.0) supports NVLink devices ppc64le packages are not available yet nvidia-docker depends on following packages libnvidia-container nvidia-container-runtime can be installed using nvidia official repository now 50

52 Another option Change the default runtime $ cat /etc/docker/daemon.json $ sudo systemctl daemon-reload $ sudo systemctl restart kubelet Enable NVIDIA device plugin $ kubectl create -f 51

53 Another option Ensure GPU resource is available $ kubectl describe node 52

54 Another option Ensure GPU resource is available $ kubectl apply -f bandwidth-test.yml $ kubectl logs bwt-pod bandwidth-test.yml 53

55 Another option CPU-GPU Memory bandwidth benchmark results 54

56 Thank you! 55

57 References OpenStack Docs: Attaching physical PCI devices to guests Device Plugins - Kubernetes Feature Gates Kubernetes GitHub - NVIDIA/k8s-device-plugin GitHub - NVIDIA/nvidia-docker 56

Can we further boost HPC Performance? Integrate IBM Power System to OpenStack Environment (Part 1) Ankit Purohit, Research Engineer NTT

Can we further boost HPC Performance? Integrate IBM Power System to OpenStack Environment (Part 1) Ankit Purohit, Research Engineer NTT Can we further boost HPC Performance? Integrate IBM Power System to OpenStack Environment (Part 1) Ankit Purohit, Research Engineer NTT Communications 1 Agenda 1. Our Background 2. Providing GPU Resources:

More information

libvirt integration and testing for enterprise KVM/ARM Drew Jones, Eric Auger Linaro Connect Budapest 2017 (BUD17)

libvirt integration and testing for enterprise KVM/ARM Drew Jones, Eric Auger Linaro Connect Budapest 2017 (BUD17) libvirt integration and testing for enterprise KVM/ARM Drew Jones, Eric Auger Linaro Connect Budapest 2017 (BUD17) Overview Enterprise guest requirements QEMU/KVM enterprise guest management libvirt A

More information

How Container Runtimes matter in Kubernetes?

How Container Runtimes matter in Kubernetes? How Container Runtimes matter in Kubernetes? Kunal Kushwaha NTT OSS Center About me Works @ NTT Open Source Software Center Contributes to containerd and other related projects. Docker community leader,

More information

The Path to GPU as a Service in Kubernetes Renaud Gaubert Lead Kubernetes Engineer

The Path to GPU as a Service in Kubernetes Renaud Gaubert Lead Kubernetes Engineer The Path to GPU as a Service in Kubernetes Renaud Gaubert , Lead Kubernetes Engineer May 03, 2018 RUNNING A GPU APPLICATION Customers using DL DL Application RHEL 7.3 CUDA 8.0 Driver 375

More information

GPU on OpenStack for Science

GPU on OpenStack for Science GPU on OpenStack for Science Deployment and Performance Considerations Luca Cervigni Jeremy Phillips luca.cervigni@pawsey.org.au jeremy.phillips@pawsey.org.au Pawsey Supercomputing Centre Based in Perth,

More information

Optimizing Efficiency of Deep Learning Workloads through GPU Virtualization

Optimizing Efficiency of Deep Learning Workloads through GPU Virtualization Optimizing Efficiency of Deep Learning Workloads through GPU Virtualization Presenters: Tim Kaldewey Performance Architect, Watson Group Michael Gschwind Chief Engineer ML & DL, Systems Group David K.

More information

Installation and Maintenance Instructions for Intel(R) R-WPA VNF Package

Installation and Maintenance Instructions for Intel(R) R-WPA VNF Package Installation and Maintenance Instructions for Intel(R) R-WPA VNF Package Contents Contents 1 Table of Figures 2 Overview 3 Installation Steps 4 1 Host Setup 4 11 System BIOS settings 4 111 Virtualization

More information

OpenPOWER Performance

OpenPOWER Performance OpenPOWER Performance Alex Mericas Chief Engineer, OpenPOWER Performance IBM Delivering the Linux ecosystem for Power SOLUTIONS OpenPOWER IBM SOFTWARE LINUX ECOSYSTEM OPEN SOURCE Solutions with full stack

More information

Full Scalable Media Cloud Solution with Kubernetes Orchestration. Zhenyu Wang, Xin(Owen)Zhang

Full Scalable Media Cloud Solution with Kubernetes Orchestration. Zhenyu Wang, Xin(Owen)Zhang Full Scalable Media Cloud Solution with Kubernetes Orchestration Zhenyu Wang, Xin(Owen)Zhang Agenda Media in the Network and Cloud Intel Media Server Reference Software Stack Container with MSS enablement

More information

Infoblox Kubernetes1.0.0 IPAM Plugin

Infoblox Kubernetes1.0.0 IPAM Plugin 2h DEPLOYMENT GUIDE Infoblox Kubernetes1.0.0 IPAM Plugin NIOS version 8.X August 2018 2018 Infoblox Inc. All rights reserved. Infoblox Kubernetes 1.0.0 IPAM Deployment Guide August 2018 Page 1 of 18 Overview...

More information

IBM Power AC922 Server

IBM Power AC922 Server IBM Power AC922 Server The Best Server for Enterprise AI Highlights More accuracy - GPUs access system RAM for larger models Faster insights - significant deep learning speedups Rapid deployment - integrated

More information

IBM Deep Learning Solutions

IBM Deep Learning Solutions IBM Deep Learning Solutions Reference Architecture for Deep Learning on POWER8, P100, and NVLink October, 2016 How do you teach a computer to Perceive? 2 Deep Learning: teaching Siri to recognize a bicycle

More information

Using DC/OS for Continuous Delivery

Using DC/OS for Continuous Delivery Using DC/OS for Continuous Delivery DevPulseCon 2017 Elizabeth K. Joseph, @pleia2 Mesosphere 1 Elizabeth K. Joseph, Developer Advocate, Mesosphere 15+ years working in open source communities 10+ years

More information

Deep Insights: High Availability VMs via a Simple Host-to-Guest Interface OpenStack Masakari Greg Waines (Wind River Systems)

Deep Insights: High Availability VMs via a Simple Host-to-Guest Interface OpenStack Masakari Greg Waines (Wind River Systems) Deep Insights: High Availability VMs via a Simple Host-to-Guest Interface OpenStack Masakari Greg Waines (Wind River Systems) WHEN IT MATTERS, IT RUNS ON WIND RIVER. 2017 WIND RIVER. ALL RIGHTS RESERVED.

More information

Optimizing Out-of-Core Nearest Neighbor Problems on Multi-GPU Systems Using NVLink

Optimizing Out-of-Core Nearest Neighbor Problems on Multi-GPU Systems Using NVLink Optimizing Out-of-Core Nearest Neighbor Problems on Multi-GPU Systems Using NVLink Rajesh Bordawekar IBM T. J. Watson Research Center bordaw@us.ibm.com Pidad D Souza IBM Systems pidsouza@in.ibm.com 1 Outline

More information

PREPARING TO USE CONTAINERS

PREPARING TO USE CONTAINERS PREPARING TO USE CONTAINERS DU-08786-001_v001 May 2018 Getting Started Guide TABLE OF CONTENTS Chapter Introduction To Docker And Containers...1 Chapter 2. Preparing Your DGX System For Use With nvidia-docker...

More information

Onto Petaflops with Kubernetes

Onto Petaflops with Kubernetes Onto Petaflops with Kubernetes Vishnu Kannan Google Inc. vishh@google.com Key Takeaways Kubernetes can manage hardware accelerators at Scale Kubernetes provides a playground for ML ML journey with Kubernetes

More information

VIRTUAL GPU SOFTWARE. DU _v6.0 through 6.1 Revision 02 June User Guide

VIRTUAL GPU SOFTWARE. DU _v6.0 through 6.1 Revision 02 June User Guide VIRTUAL GPU SOFTWARE DU-69- _v6. through 6. Revision June User Guide TABLE OF CONTENTS Chapter. Introduction to NVIDIA vgpu Software..... How NVIDIA vgpu Software Is Used...... GPU Pass-Through.....3.

More information

IBM Power Advanced Compute (AC) AC922 Server

IBM Power Advanced Compute (AC) AC922 Server IBM Power Advanced Compute (AC) AC922 Server The Best Server for Enterprise AI Highlights IBM Power Systems Accelerated Compute (AC922) server is an acceleration superhighway to enterprise- class AI. A

More information

Kata Containers The way to run virtualized containers. Sebastien Boeuf, Linux Software Engineer Intel Corporation

Kata Containers The way to run virtualized containers. Sebastien Boeuf, Linux Software Engineer Intel Corporation Kata Containers The way to run virtualized containers Sebastien Boeuf, Linux Software Engineer Intel Corporation https://regmedia.co.uk/2017/09/11/shutterstock_containers_in_port.jpg Containers 101 Process

More information

Storage Performance Tuning for FAST! Virtual Machines

Storage Performance Tuning for FAST! Virtual Machines Storage Performance Tuning for FAST! Virtual Machines Fam Zheng Senior Software Engineer LC3-2018 Outline Virtual storage provisioning NUMA pinning VM configuration options Summary Appendix 2 Virtual storage

More information

Cisco UCS Manager VM-FEX for KVM CLI Configuration Guide, Release 3.2

Cisco UCS Manager VM-FEX for KVM CLI Configuration Guide, Release 3.2 Cisco UCS Manager VM-FEX for KVM CLI Configuration Guide, Release 3.2 First Published: 2017-08-18 Americas Headquarters Cisco Systems, Inc. 170 West Tasman Drive San Jose, CA 95134-1706 USA http://www.cisco.com

More information

INSTALLATION RUNBOOK FOR Triliodata + TrilioVault

INSTALLATION RUNBOOK FOR Triliodata + TrilioVault INSTALLATION RUNBOOK FOR Triliodata + TrilioVault Application Type: [Backup and disaster recovery] Application Version: [2.1] MOS Version: [7.0] OpenStack version: [Kilo] Content Document History 1 Introduction

More information

S INSIDE NVIDIA GPU CLOUD DEEP LEARNING FRAMEWORK CONTAINERS

S INSIDE NVIDIA GPU CLOUD DEEP LEARNING FRAMEWORK CONTAINERS S8497 - INSIDE NVIDIA GPU CLOUD DEEP LEARNING FRAMEWORK CONTAINERS Chris Lamb CUDA and NGC Engineering, NVIDIA John Barco NGC Product Management, NVIDIA NVIDIA GPU Cloud (NGC) overview AGENDA Using NGC

More information

Deploy the ASAv Using KVM

Deploy the ASAv Using KVM You can deploy the ASAv using the Kernel-based Virtual Machine (KVM). About ASAv Deployment Using KVM, on page 1 Prerequisites for the ASAv and KVM, on page 2 Prepare the Day 0 Configuration File, on page

More information

Convergence of VM and containers orchestration using KubeVirt. Chunfu Wen

Convergence of VM and containers orchestration using KubeVirt. Chunfu Wen Convergence of VM and containers orchestration using KubeVirt Chunfu Wen chwen@redhat.com Agenda Context Introduction What Is Kubevirt And How It Feel Kubevirt Architecture And Design Demo FIRST A LITTLE

More information

Building NVLink for Developers

Building NVLink for Developers Building NVLink for Developers Unleashing programmatic, architectural and performance capabilities for accelerated computing Why NVLink TM? Simpler, Better and Faster Simplified Programming No specialized

More information

INTEGRATING HPFS IN A CLOUD COMPUTING ENVIRONMENT

INTEGRATING HPFS IN A CLOUD COMPUTING ENVIRONMENT INTEGRATING HPFS IN A CLOUD COMPUTING ENVIRONMENT Abhisek Pan 2, J.P. Walters 1, Vijay S. Pai 1,2, David Kang 1, Stephen P. Crago 1 1 University of Southern California/Information Sciences Institute 2

More information

A comparison of performance between KVM and Docker instances in OpenStack

A comparison of performance between KVM and Docker instances in OpenStack A comparison of performance between KVM and Docker instances in OpenStack Wataru Takase High Energy Accelerator Research Organiza on (KEK), Japan HEPiX Fall 2015 Workshop at BNL 1 KEK site will become

More information

Singularity CRI User Documentation

Singularity CRI User Documentation Singularity CRI User Documentation Release 1.0 Sylabs Apr 02, 2019 CONTENTS 1 Installation 1 1.1 Overview................................................. 1 1.2 Before you begin.............................................

More information

OpenStack hypervisor, container and Baremetal servers performance comparison

OpenStack hypervisor, container and Baremetal servers performance comparison OpenStack hypervisor, container and Baremetal servers performance comparison Yoji Yamato a) Software Innovation Center, NTT Corporation, 3 9 11 Midori-cho, Musashino-shi, Tokyo 180 8585, Japan a) yamato.yoji@lab.ntt.co.jp

More information

MICROWAY S NVIDIA TESLA V100 GPU SOLUTIONS GUIDE

MICROWAY S NVIDIA TESLA V100 GPU SOLUTIONS GUIDE MICROWAY S NVIDIA TESLA V100 GPU SOLUTIONS GUIDE LEVERAGE OUR EXPERTISE sales@microway.com http://microway.com/tesla NUMBERSMASHER TESLA 4-GPU SERVER/WORKSTATION Flexible form factor 4 PCI-E GPUs + 3 additional

More information

DGX-1 DOCKER USER GUIDE Josh Park Senior Solutions Architect Contents created by Jack Han Solutions Architect

DGX-1 DOCKER USER GUIDE Josh Park Senior Solutions Architect Contents created by Jack Han Solutions Architect DGX-1 DOCKER USER GUIDE 17.08 Josh Park Senior Solutions Architect Contents created by Jack Han Solutions Architect AGENDA Introduction to Docker & DGX-1 SW Stack Docker basic & nvidia-docker Docker image

More information

Zoptymalizuj Swoje Centrum Danych z Red Hat Virtualization. Jacek Skórzyński Solution Architect/Red Hat

Zoptymalizuj Swoje Centrum Danych z Red Hat Virtualization. Jacek Skórzyński Solution Architect/Red Hat Zoptymalizuj Swoje Centrum Danych z Red Hat Virtualization Jacek Skórzyński Solution Architect/Red Hat AGENDA Red Hat Virtualization Overview RHV Architecture RHV Core Features Red Hat Virtualization Overview

More information

Configuring and Benchmarking Open vswitch, DPDK and vhost-user. Pei Zhang ( 张培 ) October 26, 2017

Configuring and Benchmarking Open vswitch, DPDK and vhost-user. Pei Zhang ( 张培 ) October 26, 2017 Configuring and Benchmarking Open vswitch, DPDK and vhost-user Pei Zhang ( 张培 ) pezhang@redhat.com October 26, 2017 Agenda 1. Background 2. Configure Open vswitch, DPDK and vhost-user 3. Improve network

More information

Effective Virtual CPU Configuration in Nova

Effective Virtual CPU Configuration in Nova Effective Virtual CPU Configuration in Nova Kashyap Chamarthy OpenStack Summit Berlin, 2018 1 / 39 Timeline of recent CPU flaws, 2018 (a) Jan 03 Spectre v1: Bounds Check Bypass Jan

More information

Deep Learning mit PowerAI - Ein Überblick

Deep Learning mit PowerAI - Ein Überblick Stephen Lutz Deep Learning mit PowerAI - Open Group Master Certified IT Specialist Technical Sales IBM Cognitive Infrastructure IBM Germany Ein Überblick Stephen.Lutz@de.ibm.com What s that? and what s

More information

Shifter: Fast and consistent HPC workflows using containers

Shifter: Fast and consistent HPC workflows using containers Shifter: Fast and consistent HPC workflows using containers CUG 2017, Redmond, Washington Lucas Benedicic, Felipe A. Cruz, Thomas C. Schulthess - CSCS May 11, 2017 Outline 1. Overview 2. Docker 3. Shifter

More information

Deploy the ExtraHop Discover Appliance on a Linux KVM

Deploy the ExtraHop Discover Appliance on a Linux KVM Deploy the ExtraHop Discover Appliance on a Linux KVM Published: 2018-07-16 The following procedure guides you through the deployment process of the ExtraHop Discover EDA 1000v or EDA 2000v virtual appliance

More information

CS-580K/480K Advanced Topics in Cloud Computing. OpenStack

CS-580K/480K Advanced Topics in Cloud Computing. OpenStack CS-580K/480K dvanced Topics in Cloud Computing OpenStack 1 Where we are 2 Virtualization Layer Operating System 1 2 3 4 Operating System 1 2 3 4 Operating System 1 2 3 4 VM1 VM2 VM3 Virtualization Layer

More information

Nested Virtualization and Server Consolidation

Nested Virtualization and Server Consolidation Nested Virtualization and Server Consolidation Vara Varavithya Department of Electrical Engineering, KMUTNB varavithya@gmail.com 1 Outline Virtualization & Background Nested Virtualization Hybrid-Nested

More information

VGPU ON KVM VFIO BASED MEDIATED DEVICE FRAMEWORK Neo Jia & Kirti Wankhede, 08/25/2016

VGPU ON KVM VFIO BASED MEDIATED DEVICE FRAMEWORK Neo Jia & Kirti Wankhede, 08/25/2016 V ON K BASED MEDIATED DEVICE FEWORK Neo Jia & Kirti Wankhede, 08/25/2016 Background / Motivation Framework Overview AGENDA Framework Deep-Dive Current Status Demo Future work 2 TODAY, HOW PRESENTED INSIDE

More information

Passthrough in QEMU/KVM on Linux

Passthrough in QEMU/KVM on Linux Passthrough in QEMU/KVM on Linux G. Lettieri 2 Nov. 2017 Let see how hardware passthrough can be used in practice, using the QEMU hypervisor with the KVM API on Linux. We assume Intel hardware throughout

More information

The configurations of each Dell R730:

The configurations of each Dell R730: Introduction The Mass Open Cloud (MOC) is a collaborative project between higher education, government, non-profit entities and industry. The mission of the MOC is To create a self-sustaining at-scale

More information

Live Migration with Mdev Device

Live Migration with Mdev Device Live Migration with Mdev Device Yulei Zhang yulei.zhang@intel.com 1 Background and Motivation Live Migration Desgin of Mediated Device vgpu Live Migration Implementation Current Status and Demo Future

More information

CONTAINERS AND MICROSERVICES WITH CONTRAIL

CONTAINERS AND MICROSERVICES WITH CONTRAIL CONTAINERS AND MICROSERVICES WITH CONTRAIL Scott Sneddon Sree Sarva DP Ayyadevara Sr. Director Sr. Director Director Cloud and SDN Contrail Solutions Product Line Management This statement of direction

More information

Conduire OpenStack Vers l Edge Computing Anthony Simonet Inria, École des Mines de Nantes, France

Conduire OpenStack Vers l Edge Computing Anthony Simonet Inria, École des Mines de Nantes, France Discovery Initiative Conduire OpenStack Vers l Edge Computing Anthony Simonet Inria, École des Mines de Nantes, France Fog/Edge Computing Infrastructures Leverage network backbones Extend any point of

More information

Deploy the ExtraHop Explore Appliance on a Linux KVM

Deploy the ExtraHop Explore Appliance on a Linux KVM Deploy the ExtraHop Explore Appliance on a Linux KVM Published: 2018-07-17 In this guide, you will learn how to deploy an ExtraHop Explore virtual appliance on a Linux kernel-based virtual machine (KVM)

More information

Deploy the ExtraHop Explore Appliance on a Linux KVM

Deploy the ExtraHop Explore Appliance on a Linux KVM Deploy the ExtraHop Explore Appliance on a Linux KVM Published: 2018-12-14 In this guide, you will learn how to deploy an ExtraHop Explore virtual appliance on a Linux kernel-based virtual machine (KVM)

More information

Welcome to Linux Foundation E-Learning Training

Welcome to Linux Foundation E-Learning Training Welcome to Linux Foundation E-Learning Training by The Linux Foundation 06/04/2018 Version 7.3. All rights reserved. Specific instructions for your course will be addressed in the Appendix. After reading

More information

Nova Scheduler: Optimizing, Configuring and Deploying NFV VNF's on OpenStack

Nova Scheduler: Optimizing, Configuring and Deploying NFV VNF's on OpenStack Nova Scheduler: Optimizing, Configuring and Deploying NFV VNF's on OpenStack Ian Jolliffe, Chris Friesen WHEN IT MATTERS, IT RUNS ON WIND RIVER. 2017 WIND RIVER. ALL RIGHTS RESERVED. Ian Jolliffe 2 2017

More information

INSTALLATION RUNBOOK FOR Netronome Agilio OvS. MOS Version: 8.0 OpenStack Version:

INSTALLATION RUNBOOK FOR Netronome Agilio OvS. MOS Version: 8.0 OpenStack Version: INSTALLATION RUNBOOK FOR Netronome Agilio OvS Product Name: Agilio OvS Driver Version: 2.2-r4603 MOS Version: 8.0 OpenStack Version: Liberty Product Type: Network Offload Driver 1. Introduction 1.1 Target

More information

Baremetal with Apache CloudStack

Baremetal with Apache CloudStack Baremetal with Apache CloudStack ApacheCon Europe 2016 Jaydeep Marfatia Cloud, IOT and Analytics Me Director of Product Management Cloud Products Accelerite Background Project lead for open source project

More information

CLOUD ARCHITECTURE & PERFORMANCE WORKLOADS. Field Activities

CLOUD ARCHITECTURE & PERFORMANCE WORKLOADS. Field Activities CLOUD ARCHITECTURE & PERFORMANCE WORKLOADS Field Activities Matt Smith Senior Solution Architect Red Hat, Inc @rhmjs Jeremy Eder Principal Performance Engineer Red Hat, Inc @jeremyeder CLOUD ARCHITECTURE

More information

IBM POWER SYSTEMS: YOUR UNFAIR ADVANTAGE

IBM POWER SYSTEMS: YOUR UNFAIR ADVANTAGE IBM POWER SYSTEMS: YOUR UNFAIR ADVANTAGE Choosing IT infrastructure is a crucial decision, and the right choice will position your organization for success. IBM Power Systems provides an innovative platform

More information

An Introduction to Kubernetes

An Introduction to Kubernetes 8.10.2016 An Introduction to Kubernetes Premys Kafka premysl.kafka@hpe.com kafkapre https://github.com/kafkapre { History }???? - Virtual Machines 2008 - Linux containers (LXC) 2013 - Docker 2013 - CoreOS

More information

BUILDING A GPU-FOCUSED CI SOLUTION

BUILDING A GPU-FOCUSED CI SOLUTION BUILDING A GPU-FOCUSED CI SOLUTION Mike Wendt @mike_wendt github.com/nvidia github.com/mike-wendt Need for CPU CI Challenges of GPU CI Methods to Implement GPU CI AGENDA Improving GPU CI Today Demo Lessons

More information

Welcome to Linux Foundation Virtual Training

Welcome to Linux Foundation Virtual Training Welcome to Linux Foundation Virtual Training by The Linux Foundation 06/04/2018 Version 7.3. All rights reserved. Connection information for class You will receive an email containing the specific login

More information

CafeGPI. Single-Sided Communication for Scalable Deep Learning

CafeGPI. Single-Sided Communication for Scalable Deep Learning CafeGPI Single-Sided Communication for Scalable Deep Learning Janis Keuper itwm.fraunhofer.de/ml Competence Center High Performance Computing Fraunhofer ITWM, Kaiserslautern, Germany Deep Neural Networks

More information

Using SR-IOV on OpenStack

Using SR-IOV on OpenStack Proceedings of NetDev 1.1: The Technical Conference on Linux Networking (February 10th-12th 2016. Seville, Spain) Using SR-IOV on OpenStack Alexander Duyck www.mirantis.com Agenda Proceedings of NetDev

More information

S8688 : INSIDE DGX-2. Glenn Dearth, Vyas Venkataraman Mar 28, 2018

S8688 : INSIDE DGX-2. Glenn Dearth, Vyas Venkataraman Mar 28, 2018 S8688 : INSIDE DGX-2 Glenn Dearth, Vyas Venkataraman Mar 28, 2018 Why was DGX-2 created Agenda DGX-2 internal architecture Software programming model Simple application Results 2 DEEP LEARNING TRENDS Application

More information

Containerizing GPU Applications with Docker for Scaling to the Cloud

Containerizing GPU Applications with Docker for Scaling to the Cloud Containerizing GPU Applications with Docker for Scaling to the Cloud SUBBU RAMA FUTURE OF PACKAGING APPLICATIONS Turns Discrete Computing Resources into a Virtual Supercomputer GPU Mem Mem GPU GPU Mem

More information

Xilinx Answer QDMA Linux Driver User Guide

Xilinx Answer QDMA Linux Driver User Guide Xilinx Answer 70928 QDMA Linux Driver User Guide Important Note: This downloadable PDF of an Answer Record is provided to enhance its usability and readability. It is important to note that Answer Records

More information

DEEP DIVE: OPENSTACK COMPUTE

DEEP DIVE: OPENSTACK COMPUTE DEEP DIVE: OPENSTACK COMPUTE Stephen Gordon Technical Product Manager, Red Hat @xsgordon AGENDA OpenStack architecture refresher Compute architecture Instance life cycle Scaling compute

More information

Red Hat Enterprise Linux 8.0 Beta

Red Hat Enterprise Linux 8.0 Beta Red Hat Enterprise Linux 8.0 Beta Configuring and managing virtualization A guide to managing virtualization on Red Hat Enterprise Linux 8.0 Beta Last Updated: 2018-11-30 Red Hat Enterprise Linux 8.0

More information

Virtualization. Santa Clara Valley Chapter of the IEEE Communication Society June 20, 2007 Scott Lurndal, 3Leaf Systems

Virtualization. Santa Clara Valley Chapter of the IEEE Communication Society June 20, 2007 Scott Lurndal, 3Leaf Systems Virtualization Santa Clara Valley Chapter of the IEEE Communication Society June 20, 2007 Scott Lurndal, 3Leaf Systems Agenda Virtualization Overview Application Virtualization Operating System Virtualization

More information

International Journal of Computer & Organization Trends Volume5 Issue3 May to June 2015

International Journal of Computer & Organization Trends Volume5 Issue3 May to June 2015 Performance Analysis of Various Guest Operating Systems on Ubuntu 14.04 Prof. (Dr.) Viabhakar Pathak 1, Pramod Kumar Ram 2 1 Computer Science and Engineering, Arya College of Engineering, Jaipur, India.

More information

S8765 Performance Optimization for Deep- Learning on the Latest POWER Systems

S8765 Performance Optimization for Deep- Learning on the Latest POWER Systems S8765 Performance Optimization for Deep- Learning on the Latest POWER Systems Khoa Huynh Senior Technical Staff Member (STSM), IBM Jonathan Samn Software Engineer, IBM Evolving from compute systems to

More information

RHOSP 12 Director Installation on MaxCore TM Platform

RHOSP 12 Director Installation on MaxCore TM Platform Configuration Note March, 2018 This configuration note describes the installation and configuration of Red Hat OpenStack Platform 12 director on MaxCore TM Platform with a SharpStreamer TM Pro PCIE-7211-2

More information

OPENSTACK + KUBERNETES + HYPERCONTAINER. The Container Platform for NFV

OPENSTACK + KUBERNETES + HYPERCONTAINER. The Container Platform for NFV OPENSTACK + KUBERNETES + HYPERCONTAINER The Container Platform for NFV ABOUT ME Harry Zhang ID: @resouer Coder, Author, Speaker Member of Hyper Feature Maintainer & Project Manager of Kubernetes sig-scheduling,

More information

VGA Assignment Using VFIO. Alex Williamson October 21 st, 2013

VGA Assignment Using VFIO. Alex Williamson October 21 st, 2013 VGA Assignment Using VFIO alex.williamson@redhat.com October 21 st, 2013 Agenda Introduction to PCI & PCIe IOMMUs VFIO VGA VFIO VGA support Quirks, quirks, quirks Status and future Performance 2 A brief

More information

Integrated Management of OpenPOWER Converged Infrastructures. Revolutionizing the Datacenter

Integrated Management of OpenPOWER Converged Infrastructures. Revolutionizing the Datacenter Integrated Management of OpenPOWER Converged Infrastructures Marcelo Perazolo, Architect IBM Systems Revolutionizing the Datacenter Join the Conversation #OpenPOWERSummit Converged Infrastructure Systems

More information

XEN and KVM in INFN production systems and a comparison between them. Riccardo Veraldi Andrea Chierici INFN - CNAF HEPiX Spring 2009

XEN and KVM in INFN production systems and a comparison between them. Riccardo Veraldi Andrea Chierici INFN - CNAF HEPiX Spring 2009 XEN and KVM in INFN production systems and a comparison between them Riccardo Veraldi Andrea Chierici INFN - CNAF HEPiX Spring 2009 Outline xen kvm Test description Benchmarks Conclusions Riccardo.Veraldi@cnaf.infn.it

More information

Using Docker in High Performance Computing in OpenPOWER Environment

Using Docker in High Performance Computing in OpenPOWER Environment Using Docker in High Performance Computing in OpenPOWER Environment Zhaohui Ding, Senior Product Architect Sam Sanjabi, Advisory Software Engineer IBM Platform Computing #OpenPOWERSummit Join the conversation

More information

IBM Leading High Performance Computing and Deep Learning Technologies

IBM Leading High Performance Computing and Deep Learning Technologies IBM Leading High Performance Computing and Deep Learning Technologies Yubo Li ( 李玉博 ) Chief Architect, on Cloud IBM Research -- China email: liyubobj@cn.ibm.com QQ: 395238640 GTC China 2016 Sept. 13, 2016

More information

GaaS Workload Characterization under NUMA Architecture for Virtualized GPU

GaaS Workload Characterization under NUMA Architecture for Virtualized GPU GaaS Workload Characterization under NUMA Architecture for Virtualized GPU Huixiang Chen, Meng Wang, Yang Hu, Mingcong Song, Tao Li Presented by Huixiang Chen ISPASS 2017 April 24, 2017, Santa Rosa, California

More information

VMware Integrated OpenStack with Kubernetes Getting Started Guide. VMware Integrated OpenStack 4.0

VMware Integrated OpenStack with Kubernetes Getting Started Guide. VMware Integrated OpenStack 4.0 VMware Integrated OpenStack with Kubernetes Getting Started Guide VMware Integrated OpenStack 4.0 VMware Integrated OpenStack with Kubernetes Getting Started Guide You can find the most up-to-date technical

More information

USING NGC WITH GOOGLE CLOUD PLATFORM

USING NGC WITH GOOGLE CLOUD PLATFORM USING NGC WITH GOOGLE CLOUD PLATFORM DU-08962-001 _v02 April 2018 Setup Guide TABLE OF CONTENTS Chapter 1. Introduction to... 1 Chapter 2. Deploying an NVIDIA GPU Cloud Image from the GCP Console...3 2.1.

More information

/ Cloud Computing. Recitation 5 September 26 th, 2017

/ Cloud Computing. Recitation 5 September 26 th, 2017 15-319 / 15-619 Cloud Computing Recitation 5 September 26 th, 2017 1 Overview Administrative issues Office Hours, Piazza guidelines Last week s reflection Project 2.1, OLI Unit 2 modules 5 and 6 This week

More information

Linuxboot continuous integration

Linuxboot continuous integration Open Firmware Linuxboot continuous integration Jean-Marie Verdun/ITRenew Guillaume Giamarchi/ITRenew Introduction This is Work In Progress, feel free to collaborate Linuxboot Continuous Integration platform

More information

OpenStack Magnum Hands-on. By Saulius Alisauskas and Bryan Havenstein

OpenStack Magnum Hands-on. By Saulius Alisauskas and Bryan Havenstein OpenStack Magnum Hands-on By Saulius Alisauskas and Bryan Havenstein Prerequisites & Expectations 8GB RAM minimum Expectations This will be very slow due to 2 layers of virtualization Things might fail

More information

Virtualization Device Emulator Testing Technology. Speaker: Qinghao Tang Title 360 Marvel Team Leader

Virtualization Device Emulator Testing Technology. Speaker: Qinghao Tang Title 360 Marvel Team Leader Virtualization Device Emulator Testing Technology Speaker: Qinghao Tang Title 360 Marvel Team Leader 1 360 Marvel Team Established in May 2015, the first professional could computing and virtualization

More information

Launching StarlingX. The Journey to Drive Compute to the Edge Pilot Project Supported by the OpenStack

Launching StarlingX. The Journey to Drive Compute to the Edge Pilot Project Supported by the OpenStack Launching StarlingX The Journey to Drive Compute to the Edge Pilot Project Supported by the OpenStack Foundation Ian Jolliffe, WIND RIVER SYSTEMS Director Engineering @ian_jolliffe Project Overview An

More information

Akraino & Starlingx: A Technical Overview

Akraino & Starlingx: A Technical Overview Akraino & Starlingx: A Technical Overview Agenda Why Edge Computing? What s Edge Computing? Akraino and Its Building Blocks StarlingX Technical Overview Collaboration in Akraino Community LC3 Beijing 2018

More information

The speed of containers, the security of VMs

The speed of containers, the security of VMs * The speed of containers, the security of VMs Xu Wang, Hyper Samuel Ortiz, Intel *Other names and brands may be claimed as the property of others. Contents Project

More information

Quick Start Guide to Compute Canada Cloud Service

Quick Start Guide to Compute Canada Cloud Service Quick Start Guide to Compute Canada Cloud Service Launching your first instance (VM) Login to the East or West cloud Dashboard SSH key pair Importing an existing key pair Creating a new key pair Launching

More information

Welcome to Linux Foundation E-Learning Training

Welcome to Linux Foundation E-Learning Training Welcome to Linux Foundation E-Learning Training by The Linux Foundation 08/26/2018 Version 7.6. All rights reserved. Specific instructions for your course will be addressed in the Appendix. After reading

More information

/ Cloud Computing. Recitation 5 February 14th, 2017

/ Cloud Computing. Recitation 5 February 14th, 2017 15-319 / 15-619 Cloud Computing Recitation 5 February 14th, 2017 1 Overview Administrative issues Office Hours, Piazza guidelines Last week s reflection Project 2.1, OLI Unit 2 modules 5 and 6 This week

More information

Democratizing Machine Learning on Kubernetes

Democratizing Machine Learning on Kubernetes Democratizing Machine Learning on Kubernetes Joy Qiao, Senior Solution Architect - AI and Research Group, Microsoft Lachlan Evenson - Principal Program Manager AKS/ACS, Microsoft Who are we? The Data Scientist

More information

Looking ahead with IBM i. 10+ year roadmap

Looking ahead with IBM i. 10+ year roadmap Looking ahead with IBM i 10+ year roadmap 1 Enterprises Trust IBM Power 80 of Fortune 100 have IBM Power Systems The top 10 banking firms have IBM Power Systems 9 of top 10 insurance companies have IBM

More information

Infoblox IPAM Driver for Kubernetes User's Guide

Infoblox IPAM Driver for Kubernetes User's Guide Infoblox IPAM Driver for Kubernetes User's Guide 1. Infoblox IPAM Driver for Kubernetes...................................................................... 3 1.1 Overview.......................................................................................

More information

RUNNING VIRTUAL MACHINES ON KUBERNETES. Roman Mohr & Fabian Deutsch, Red Hat, KVM Forum, 2017

RUNNING VIRTUAL MACHINES ON KUBERNETES. Roman Mohr & Fabian Deutsch, Red Hat, KVM Forum, 2017 RUNNING VIRTUAL MACHINES ON KUBERNETES Roman Mohr & Fabian Deutsch, Red Hat, KVM Forum, 2017 1 FABIAN DEUTSCH ROMAN MOHR Fedora user and former package maintainer ovirt and KubeVirt Contributor Working

More information

Container Orchestration on Amazon Web Services. Arun

Container Orchestration on Amazon Web Services. Arun Container Orchestration on Amazon Web Services Arun Gupta, @arungupta Docker Workflow Development using Docker Docker Community Edition Docker for Mac/Windows/Linux Monthly edge and quarterly stable

More information

Installing the Cisco IOS XRv 9000 Router in KVM Environments

Installing the Cisco IOS XRv 9000 Router in KVM Environments Installing the Cisco IOS XRv 9000 Router in KVM Environments These file types are needed to install Cisco IOS XRv 9000 Router on the KVM hypervisor:.qcow2 Used for booting the software image in KVM OpenStack

More information

IBM PowerKVM available with the Linux only scale-out servers IBM Redbooks Solution Guide

IBM PowerKVM available with the Linux only scale-out servers IBM Redbooks Solution Guide IBM PowerKVM available with the Linux only scale-out servers IBM Redbooks Solution Guide The IBM POWER8 processors are built for big data and open innovation. Now, Linux administrators and users can maximize

More information

Infoblox IPAM Driver for Kubernetes. Page 1

Infoblox IPAM Driver for Kubernetes. Page 1 Infoblox IPAM Driver for Kubernetes Page 1 1. CNI-Infoblox IPAM Driver for Kubernetes.................................................................. 3 1.1 Overview.......................................................................................

More information

19. prosince 2018 CIIRC Praha. Milan Král, IBM Radek Špimr

19. prosince 2018 CIIRC Praha. Milan Král, IBM Radek Špimr 19. prosince 2018 CIIRC Praha Milan Král, IBM Radek Špimr CORAL CORAL 2 CORAL Installation at ORNL CORAL Installation at LLNL Order of Magnitude Leap in Computational Power Real, Accelerated Science ACME

More information

Tooling Linux for the Future of Embedded Systems. Patrick Quairoli Director of Alliance and Embedded Technology SUSE /

Tooling Linux for the Future of Embedded Systems. Patrick Quairoli Director of Alliance and Embedded Technology SUSE / Tooling Linux for the Future of Embedded Systems Patrick Quairoli Director of Alliance and Embedded Technology SUSE / Patrick.Quairoli@suse.com With SUSE You Can Control Infrastructure Optimize Operations

More information

CUDA QUICK START GUIDE. DU _v9.1 January 2018

CUDA QUICK START GUIDE. DU _v9.1 January 2018 CUDA QUICK START GUIDE DU-05347-301_v9.1 January 2018 TABLE OF CONTENTS Chapter 1. Introduction...1 Chapter 2. Windows... 2 2.1. Network Installer... 2 2.2. Local Installer... 4 Chapter 3. Mac OSX...6

More information

Installation and setup guide of 1.1 demonstrator

Installation and setup guide of 1.1 demonstrator Installation and setup guide of 1.1 demonstrator version 2.0, last modified: 2015-09-23 This document explains how to set up the INAETICS demonstrator. For this, we use a Vagrant-based setup that boots

More information