HP Enterprise unveils their HPC optimized Cavium ThunderX2 ARM Powered High Performance Computing platforms, the Apollo 70 is a disruptive ARM HPC processor technology with maximum memory bandwidth, familiar management and performance tools, and the density and scalability required for large HPC cluster deployments. And then HPE Labs unveils The Machine which is also powered by a Cavium ThuderX2, it is HPE's vision for the future of computing as by 2020, one hundred billion connected devices will generate far more demand for computing than today's infrastructure can accommodate.
The Machine is a custom-built device made for the era of big data. HPE says it has created the world’s largest single-memory computer. The R&D program is the largest in the history of HPE, the former enterprise division of HP that split apart from the consumer-focused division. If the project works, it could be transformative for society. But it is no small effort, as it could require a whole new kind of software. HPE's prototype can accomodate up to 160 terabytes of memory, capable of simultaneously working with the data held in every book in the Library of Congress five times over — or approximately 160 million books. According to HPE, it has never been possible to hold and manipulate whole data sets of this size in a single-memory system, and this is just a glimpse of the immense potential of Memory-Driven Computing. Following the GenZ Consortium's vision, based on the current prototype, HPE expects the architecture can scale to an exabyte-scale single-memory system and, beyond that, to a nearly limitless pool of memory — 4,096 yottabytes. For context, that is 250,000 times the entire digital universe today. With that amount of memory, HPE said it will be possible to simultaneously work with every digital health record of every person on earth, every piece of data from Facebook, every trip of Google’s autonomous vehicles, and every data set from space exploration all at the same time — getting to answers and uncovering new opportunities at unprecedented speeds.
Filmed in 4K60 at Supercomputing 2017 in Denver using Panasonic GH5 ($1999 at Amazon.com) on firmware 2.1 (aperture priority, AF continuous tracking) with Leica 12mm f1.4 ($1297 at Amazon.com) with Sennheiser MKE440 stereo shotgun microphone ($325 at Amazon.com), get $25 off renting cameras and lenses with my referral link at https://share.lensrentals.com/x/wWbHqV
Cerevo is a company that was founded in 2008 that specializes in niche IOT products. Cerevo adds shoes to the virtual reality experience. The Shoes enable easier movement with VR applications. The shoes also enable a more tactile experience and can send sensations to your feet. The VR shoes should range from $800-$1200. The Cerevo Tipron projector is a Robot with a built in projector that moves around on wheals. The Projector robot costs $2299 and offers a display size of up to 80" with 1280x720 resolution. The lumigent is a robotic voice activated desk lamp. Lumigent technology is integrated into other devices such as cameras, bicycles and other IOT applications.
Daqri is a company which produces information technology for industrial uses. The Daqri Smart Helmet is a VR/AR helmet for industrial applications that uses 360-degree navigation cameras to analyze environments. Augmented reality can provide detailed information about work that is going on at a glance. The Smart helmet runs Ubuntu Linux and is based upon an Intel Core M7 processor, Intel realsense cameras, and offers 720p projection for each eye.
ARM Innovation Ecosystem Accelerator (“ARM Accelerator”) is an international global startup accelerator recruitment network in Mainland China, UK, U.S, Israel, Canada, France, Hong Kong, and Taiwan area, helping startups accelerate development in areas such as VR/AR, Robotics/AI, Smart Car, Smart Healthcare, Smart Home, Smart City. ARM Accelerator is an innovation and acceleration platform featured among ARM's ecosystem. ARM Accelerator focuses on smart hardware and IoT ecosystem. The core advantage of ARM Accelerator is to create an one-stop platform for China and overseas startups and integrates the world-leading IC design companies and scarce, high-value labs to provide the customers all kinds of incubation and acceleration services, such as professional technology consulting, design service, and global promotion and investment matchmaking.
Nvidia DRIVE PX Pegasus board for self-driving cars has 2 Octa-core ARM SoCs with 512-core CUDA GPU and 2 discreet GPUs for a total of 320 Billion calculations per second
Nvidia DRIVE PX Pegasus board is launched for self-driving cars which includes two ARM SoCs each feature Octa-core Nvidia Xavier Custom ARM processors with Volta 512-core CUDA GPU which supports up to 8K video encode and decode, 7Billion transistors each ARM SoC built on TSMC 16nm FinFET+ with also two next-generation discrete GPUs separately on the board with hardware created for accelerating deep learning and computer vision algorithms, the 4 chips on the board can compute 320 Billion calculations per second with an overall 1TB per second memory bandwidth.
Jon Masters says Moores Law may have come to an end and that single threaded performance is not defining the industry anymore because it's not increasing at the same rate that it used to. What is defining the future of the industry is machine learning, accelerators, lots of additional workload optimization that is happening outside of the core. Thus he believes ARM has an opportunity to get into the mainstream server space in the next 12-18 months with the newest powerful ARM Server solutions such as the Cavium ThunderX2 and the Qualcomm Centriq 2400. You can see some of my previous Jon Masters interviews over the past 5 years here.
I previously interviewed Paul McKenney at Linaro Connect 5 years ago in Hong Kong here, since then he has been working with a lot of things at IBM and this is the first time he's back at Linaro Connect since that initial interview. He says there might be 20 Billion Linux machines in the world, most of them running on ARM, all of them have Paul McKenney's Read-Copy Update (RCU) code in them.
Read-copy update (RCU) is a synchronization mechanism that was added to the Linux kernel in October of 2002. RCU achieves scalability improvements by allowing reads to occur concurrently with updates. In contrast with conventional locking primitives that ensure mutual exclusion among concurrent threads regardless of whether they be readers or updaters, or with reader-writer locks that allow concurrent reads but not in the presence of updates, RCU supports concurrency between a single updater and multiple readers. RCU ensures that reads are coherent by maintaining multiple versions of objects and ensuring that they are not freed up until all pre-existing read-side critical sections complete. RCU defines and uses efficient and scalable mechanisms for publishing and reading new versions of an object, and also for deferring the collection of old versions. These mechanisms distribute the work among read and update paths in such a way as to make read paths extremely fast. In some cases (non-preemptable kernels), RCU's read-side primitives have zero overhead.
Open Source Foundries is a spin off company off of Linaro, composed of a talented group of engineers to work more directly with companies, OEMs, ODMs, small, medium to large companies to bring new open source products and solutions more rapidly to the market. Leveraging all the work done by Linaro and speeding up the time to market, enable rapid product development, here demonstrating some of the open source IoT solutions provided based on Zephyr on ARM Cortex-M and Linux on ARM Cortex-A using the Linaro Technologies Division (LTD) microPlatforms system.
The lack of a secure IoT solution has the industry scrambling. The Open Source Foundries team believes that a world can exist in which all connected devices can be secured and updated in a timely fashion. In this demonstration shown at the Linaro Connect San Francisco 2017, the team showcases its secure end to end FOTA (firmware over the air) solution implementing the latest in connected technologies.
At Open Source Foundries, software is their passion, hacking hardware is their favorite past time, so they have created the OSLight project to convert off the shelf hardware into secure connected devices. They have inserted a Red Bear NRF52 BLE Nano 2 into these lamps, to allow them to communicate over BLE with various cloud services. In the first demo, they demonstrate creating a secure BLE mesh network with these lamps. They show the ability to securely pass messages through the mesh network to control the state of the LED lamp. The next demo shows a set of 96Boards Nitrogens sending temperature data to the SoftBank IoT Cloud with the ONEM2M protocol using 6lowpan over BLE. The third and final demo introduces a variant of the OSLight project, a fully 3D printed light bulb. Instead of a simple LED array it has a 12 LED WRGB NeoPixel which is powered by line voltage, stepped down to 5VDC.
For microcontrollers, they offer their Zephyr microplatform, an open source software reference based on Zephyr RTOS and MCUboot. This software stack implements secure boot, unified microkernel, and IP (TCP or UDP) using 6lowpan over BLE. At the protocol level they've embraced industry standards such as LWM2M/ONEM2M/HTTPS/MQTT to provide an array of options for their customers, whilst ensuring no vendor lock in. Open Source Foundries subscribers are offered continuous validated software updates throughout the life of their product for a fixed monthly subscription fee.
On the gateway, they offer their Linux microplatform, which is again, an open source reference based on the latest Linux kernel version, and a minimal Yocto based userspace with a container runtime (Docker). By isolated the OS from the containers, each can be updated independently while providing limitless potential for the applications it can run. For updates they again implement standards, and stay vendor neutral to allow their customers to choose the solution that is right for them. Continuous validated updates for the OS and containers are also offered for this platform for a reasonable fixed monthly fee.
Bero (Bernhard Rosenkränzer) from the Linaro Mobile Group set out this week as you can see in my previous video to build and bring up his ARM Desktop based on the Quad-core ARM Cortex-A72 Marvell MACCHIATObin development board with a Radeon or Nvidia GPU. Bero also built his own ARM Laptop based on the Dragonboard 820 running Open Mandriva Linux.