KubeCon + CloudNativeCon Europe Virtual
Visit our booth HERE! (requires to be logged in the tool)
As CNCF’s flagship conference, KubeCon + CloudNativeCon Europe 2020 - Virtual will bring together more than 20,000 technologists from thriving open source communities to further education around cloud native computing. Maintainers and end-users of CNCF’s hosted projects – including Kubernetes, Prometheus, Envoy, CoreDNS, containerd, Fluentd, Jaeger, Vitess, TUF, OpenTracing, gRPC, CNI, Notary, NATS, Linkerd, Helm, Rook, Harbor, etcd, Open Policy Agent, CRI-O, TiKV, CloudEvents, Falco, Argo, and Dragonfly – along with other cloud-native technologies will gather virtually from August 17-20 – sharing insights around and encouraging participation in this fast-growing ecosystem.
Why is Intel here?
With more than 15,000 software engineers, Intel is committed to furthering open cloud innovation. We are in a unique position to bring together key industry players to address the complexity of building for diverse architectures and workloads and enable faster deployments of new innovations at cloud scale. Software is a key technology pillar for Intel to fully realize the advancements in architecture, process, memory, interconnect and security.
We are continuing to shape the development of Kubernetes by addressing the limitations for low-latency workloads, defining the architecture and requirements for accelerator device plugins, and enabling new features in networking applications.
Our goal at this event is to raise awareness of Intel’s contributions to open source projects, and to demonstrate the benefits of Intel® architecture across device, edge, and cloud.
-
Bring awareness and promote the innovative open source projects that Intel contributes to and optimizes for Intel architecture.
-
Show users new ways to use Intel accelerators in cloud services that provide better performance or enhanced security.
-
By helping Kubernetes and other open source projects fully leverage platform capabilities, Intel can drive innovation to support rapidly changing demands.
Sessions
Session Title |
Presenter |
Time (CEST) |
Time (PDT) |
Mikko Ylinen Ismo Puustinen |
Wednesday, August 19 13:45 – 14:20 |
Wednesday, August 19 4:45 – 5:20 AM |
|
Conor Nolan, Intel; Victor Pickard, Red Hat |
Wednesday, August 19 16:55 – 17:30 |
Wednesday, August 19 7:55 – 8:30 AM |
|
Srini Addepalli, Intel w. VMWare, Linux Foundation, Ericson, Vodafone |
Wednesday, August 19 17:40 – 18:15 |
Wednesday, August 19 8:40 – 9:15 AM |
|
Samuel Ortiz |
Thursday, August 20 13:00 – 13:35 |
Thursday, August 20 4:00 – 4:35 AM |
|
Killian Muldoon, Intel & Tom Golway, HP |
Thursday, August 20 14:30 – 15:05 |
Thursday, August 20 5:30 – 6:05 AM |
|
Marlow Weston, Intel w. Microsoft, Illumio, InGuardians |
Thursday, August 20 17:20 – 17:55 |
Thursday, August 20 8:20 – 8:55 AM |
Demos
Demo Title |
Keywords |
Abstract |
Intel® Omni-Path Architecture, Intel® Optane™ SSD, VROC |
Non-Volatile Memory Express over Fabrics (NVMeoF) is becoming one of the most disruptive technologies for data center storage, designed to deliver high throughput and low-latency NVMe SSD technology over a network fabric. This demo shows how to use Intel® Omni-Path Architecture and Intel® SSD Data Center Family with open-source projects for the NVMeoF in a cloud native environment using Kubernetes*, and demonstrates that near native performance can be achieved. |
|
Intel® Xeon® Scalable Processors, Intel® QuickAssist Technology, Intel GPU, OpenNESS, Edge Computing,Cloud Native |
During the edge transformation journey to cloud native, there are many challenges. We introduce the Integrated Cloud Native NFV and App Stack project, or ICN, what ICN is and the purpose of ICN. We will show you a SDEWAN ICN demo of latest release of ICN. The demo explains how ICN can resolve the challenges of getting edge applications to communicate with each other. |
|
DLRS, DARS, Intel® Advanced Vector Extensions 512 |
Intercranial Hemorrhage is diagnosed by examining CT-Scan images, looking for key markers of hemorrhage, which is a job very suited for an AI solution. We created an AI pipeline using the System Stacks for Linux* OS, a purpose-built collection of containers that provide integrated, optimized, and tuned AI frameworks. This demo is deployed as a secure cloud service accessed through a web interface, which enables upload of CT scan images from multiple endpoints. The training and inference is distributed and orchestrated by Kubernetes*. |
|
Intel® QuickAssist Technology, Kata Containers* |
This demo is an early preview of the work to offload HTTP Compression to an Intel® QuickAssist Technology card. The entire workload is secured with Kata Containers* and uses an Nginx* web server with an Envoy* sidecar proxy. The virtual functions of the Intel® QAT card are enabled and SR-IOV is used to more securely pass the vf's into the Kata Container. |
|
NFD, Intel® Advanced Vector Extensions 512, Intel® QuickAssist Technology, Intel® FPGA, Intel processor |
Node Feature Discovery (NFD) is a Kubernetes* add-on that detects and advertises hardware and software capabilities of each node that can be used to facilitate intelligent scheduling of a workload. This demo shows users how easy it is to use NFD to discover and schedule on advanced Intel processor features like Intel® Advanced Vector Extensions 512 or VNNI. Besides Intel processor features, NFD can help to schedule workloads on nodes with specific PCIe cards, SRIOV networking, SSD storage, NUMA topology, and much more. |
|
Intel® FPGA, Accelerators |
See how using the Intel® FPGA device plugin and FPGA Programmable Acceleration Card D5005 with OpenCL™ Matrix Multiplication bitstream design can accelerate an English letter recognition workload in a multi-node Kubernetes* cluster by x185 times. |
|
INTEL® Optane™ Persistent Memory, Storage |
Our PMEM-CSI (container storage interface) allows you to use Intel® Optane™ Persistent Memory for your Kubernetes* workloads, providing both non-volatile storage and fast data movement. In this demo, we explore how using PMEM-CSI can accelerate Redis* in a Kubernetes environment. |
|
Networking, 5G, OpenNESS |
Self-healing and Self-optimizing network infrastructures require a combination of fine-grained visibility and control of platform features to help ensure an optimum Quality of Service (QoS). One such automation use case is platform power monitoring and overload detection.This demo is built on container Bare Metal Reference Architecture – a standardized Kubernetes deployment that exposes platform features for increased and deterministic network performance. Platform telemetry insights are provided to detect a potential platform overload scenario when workloads are operating under compute intensive conditions. Automatic scaling combined with intelligent scheduling is triggered when overloaded nodes are identified, provisioning additional workloads and ensuring their placement on nodes with capacity for additional work. The audience will take away an understanding of the role of telemetry insights and orchestration in network platform automation and its necessity for infrastructure and service management. |
Take the 2-min survey using the link in our vitrual booth! Your input is very valuable to us!
------------------------------------------------------------------------------------------
*Other names and brands may be claimed as the property of others.