“Hybrid cloud is not a temporary destination,
it is the destination.”
— Ginni Rometty, IBM Chairman, President and CEO
IBM Systems and Linux: 20+ years of innovation
More than 20
Number of years IBM Systems' servers have run on Red Hat Enterprise Linux.
Up to 84%
reduction in app development time and 75% reduction in operational expenses by using IBM and Red Hat Enterprise Linux.6
Lower latency for DevOps and database workloads on IBM Storage for Red Hat OpenShift container platform versus compared systems.11
Higher data throughput for IBM Storage for Red Hat OpenShift container platform running machine learning workloads than alternative systems with scalability to 120GB/s.12
1 Red Hat client data and Fortune 500 list, June 2018, https://www.redhat.com/en/about/company
5 IDC Whitepaper sponsored by RedHat, “The Value of Standardizing on Red Hat Infrastructure Solutions,” November 2017
8 Based on an IBM customer's data, 42 x86 servers (1,512 cores total) can be consolidated into 2 IBM LinuxONE Emperor II servers (135 cores total), yielding an 11:1 core consolidation ratio and 41% lower Total Cost of Ownership (TCO) over 5 years. Disclaimer: The x86 servers contained Intel Xeon E5-2697v4 18-core 2.3 GHz processors.
10 Results are based IBM Internal Measurements running 1000 iterations of Enlarged GoogleNet model (mini-batch size=5) on Enlarged Imagenet Dataset (2240x2240) . Power AC922; 40 cores (2 x 20c chips), POWER9 with NVLink 2.0; 2.25 GHz, 1024 GB memory, 4xTesla V100 GPU ; Red Hat Enterprise Linux 7.4 for Power Little Endian (POWER9) with CUDA 9.1/ CUDNN 7;. Competitive stack: 2x Xeon E5-2640 v4; 20 cores (2 x 10c chips) / 40 threads; Intel Xeon E5-2640 v4; 2.4 GHz; 1024 GB memory, 4xTesla V100 GPU, Ubuntu 16.04. with CUDA .9.0/ CUDNN 7 . Software: IBM Caffe with LMS Source code.
11 A fully populated IBM FlashSystem 9150 with FlashCore modules (FCM), delivers a minimum latency of 100μs measured in a performance test, benchmark application (workload generator), vs a competitor's system.
12 Alternative systems of 26GB/s to 19.9GB/s as sourced on http://jtekds.com/dell-emc-and-nvidia-expand-collaboration-to-deliver-flexible-deployment-options-for-artificial-intelligence-use-cases/ and https://www.theregister.co.uk/2018/06/07/pure_beats_netapp_at_ai/