clearlinux.org: Clear Linux Project for Intel Architecture

clearlinux.org: Clear Linux Project for Intel Architecture

Clear Linux Project
for Intel® Architecture
The Clear Linux* Project for Intel® Architecture is a project that is building a Linux OS distribution for various cloud use cases. The goal of Clear Linux OS is to showcase the best of Intel Architecture technology, from low-level kernel features to more complex items that span across the entire operating system stack.

Autoproxy

Clear Linux* OS for Intel® Architecture is the first Linux distribution that supports auto proxy. This allows the OS to discover a Proxy Auto-Config (PAC) script and use it to automatically resolve what proxy is needed for a given connection. Autoproxy enables end users — both internal and external to Intel — to use Clear Linux OS for Intel Architecture inside any proxy…

Function Multiversioning (FMV)

Imagine that you are developing software that could work in multiple platforms. At the end of the day, it could be running anywhere, maybe on a server or a home computer. While Intel® architecture provides many powerful instruction set extensions, it is challenging for developers to generate code that takes advantage of these capabilities.Currently, developers have these choices:Write multiple…

Telemetry

In support of the goal to provide an agile Linux* distribution that rapidly detects and responds to quality issues in the field, Clear Linux for Intel® Architecture includes a telemetry solution, which notes events of interest and reports them back to the development team. The solution adheres to Intel’s privacy policies regarding the collection and use of Personally Identifiable Information (PII…

AutoFDO

For the longest time, compilers have been producing optimized binaries. However, in today’s world it can often be daunting to know exactly which optimizations — among the more than 80 options for basic optimizations — to choose, and which of those will really be of benefit to you. In the Clear Linux* Project for Intel® Architecture we use a lot of these optimizations, and one in particular…

Clear Containers

Containers are immensely popular in the cloud world. With Clear Containers we’re working on a way to improve security of containers by using Intel® Virtualization Technology (Intel® VT). We set out to build Clear Containers by leveraging the isolation of virtual-machine technology along with the deployment benefits of containers. As part of this, we let go of the “generic PC hardware”…

Stateless

You just made a mistake in configuring OpenStack* on your system, and out of frustration ran the following commands on your Linux distro as root: # rm -rf /etc /var # reboot What do you think would happen? How long would it take you to recover? Without backups? With Clear Linux* OS for Intel® Architecture, the system will boot correctly! In fact, this will effectively perform a “…

Software update

Linux*-based operating systems contain the code of several hundred, if not thousands, of open source projects. To make this manageable, distributions use a concept called “packages” to configure and compile the source code of these projects into binaries, which can then be logically installed.Many distributions then combine these compiled binaries into so-called packages, resolving dependencies…

All debug information, all the time

Debug information is generated when a program is compiled from source code into a binary. Programs like the GDB debugger use the information to map machine instructions back to the original source code. Developers can then debug and analyze their programs by stepping through original source code, rather than going through the much lower level (and harder to understand) CPU instructions one by…

Advertisements

Blog by Dan Luu

Blog by Dan Luu

I started out working on flash memory and optics, and then moved up one level to CPUs. I was lucky enough to land at Centaur, a small company that gave me a lot of freedom, and I ended up doing RTL, ucode, verification, bringup, test, and pretty much everything else you can do on a CPU. After that, I worked on hardware/software co-design to speed up a problem domain for Google. I’m off to start a new job soon, but I’m not big on announcing things in advance, so that’s all I’m going to say about that. If you’re so inclined, you can check out my github, linkedin, and resume, but that just has a bunch of details.

Intel® Xeon Phi™ Coprocessors

Intel® Xeon Phi™ Coprocessors

What is the Intel® Xeon Phi™ coprocessor?
Intel® Xeon Phi™ coprocessors are PCI Express* form factor add-in cards that work synergistically with Intel® Xeon® processors to enable dramatic performance gains for highly parallel code—up to 1.2 double-precision teraFLOPS (floating point operations per second) per coprocessor.

Manufactured using Intel’s industry-leading 22nm technology with 3-D Tri-Gate transistors, each coprocessor features more cores, more threads, and wider vector execution units than an Intel Xeon processor. The high degree of parallelism compensates for the lower speed of each core to deliver higher aggregate performance for highly parallel workloads.

What applications can benefit from the Intel Xeon Phi coprocessor?
While a majority of applications (80 to 90 percent) will continue to achieve maximum performance on Intel Xeon processors, certain highly parallel applications will benefit dramatically by using Intel Xeon Phi coprocessors. To take full advantage of Intel Xeon Phi coprocessors, an application must scale well to over 100 software threads and either make extensive use of vectors or efficiently use more local memory bandwidth than is available on an Intel Xeon processor. Examples of segments with highly parallel applications include: animation, energy, finance, life sciences, manufacturing, medical, public sector, weather, and more. Learn more about Intel® Many Integrated Core Architecture (Intel® MIC Architecture) development.

omgubuntu.co.uk: Intel ‘Compute Stick’ Is an $89 Chromecast-size PC That Runs Ubuntu

omgubuntu.co.uk: Intel ‘Compute Stick’ Is an $89 Chromecast-size PC That Runs Ubuntu

Intel Compute Stick PC Specifications

  • Quad-core Intel Atom Z3735F @ 1.33GHz (1.83GHz boost)
  • 2GB RAM (Windows), 1GB RAM (Ubuntu)
  • 32GB eMMC (Windows), 8GB eMMC (Ubuntu)
  • Full-sized HDMI Out
  • 1x USB 2.0
  • 1x MicroUSB
  • MicroSD Card Slot
  • Bluetooth 4.0
  • Wi-Fi

Other commonalities between both models include: on-board Wi-Fi 802.11b/g/n and Bluetooth 4.0, a microSD card slot for extra storage, a single USB 2.0 port and a microUSB port for power.

A full-size HDMI-out connector sits at the end of the stick to let you plug it in directly, though Intel includes a little extender wire should your monitor’s HDMI-in port be awkwardly placed.

The Ubuntu version of the Compute Stick will sell for $89. The Windows 8.1 version will sell for $149.

lotsofcores.com: High Performance Programming for Intel Xeon Phi Coprocessors | Intel Xeon Phi Coprocessor High Performance Programming

lotsofcores.com: High Performance Programming for Intel Xeon Phi Coprocessors | Intel Xeon Phi Coprocessor High Performance Programming
The world’s fastest computer, for the third time in a row on biannual Top500 list, uses Intel Xeon Phi coprocessors to make it possible. Intel Xeon Phi coprocessors are used in the #1, #7, #15, #39, #50, #51, #65, #92, #101, #102, #103, #134, #157, #186, #235, #251 and #451 systems. EXPLICIT VECTORIZATION – A TALK ABOUT THE NEED FOR THIS, GIVEN AT SGIUG ON APRIL 30, 2014

Linux.com: Install Fedora on Intel NUC: A Low-Power, x86-Ready Mini PC With Grunt

Linux.com: Install Fedora on Intel NUC: A Low-Power, x86-Ready Mini PC With Grunt
Some advantages the NUC has over many small form factor machines are the speed of the processor, the ability to have up to 16 GB of RAM, four USB 3.0 ports, and both a mini HDMI and mini DisplayPort connector. Being an Intel Core i3 CPU, if some code works on a regular x86 desktop machine then it shouldn’t require any por The Haswell NUC has an infrared receiver on the front of the unit. I thought getting that working would be a matter of starting lircd and probably telling it what remote I have at hand. Unfortunately there was no /dev/lirc0 device file. And my attempts to cajole a working one into existence were ineffective. I then found this post in an Intel Community Forum. I’ve repeated the commands from the above link below in case the link goes stale. The first command verifies that the IR driver didn’t load properly and the second block creates a state that allows the nuvoton-cir module to load properly. After doing that, the NUC could receive input from an IR remote control.

techrights.org: UEFI Booster Intel Could Not Even Bother Making GNU/Linux Bootable on NUC

techrights.org: UEFI Booster Intel Could Not Even Bother Making GNU/Linux Bootable on NUC
OVER THE PAST week or two there has been a lot of media hype about Intel NUC [1,2] (a lot of it was purely marketing), in part because Linux support was improved [3-5] (it was hard to install GNU/Linux on these machines) and there was a benchmark too [6]. One angle that was scarcely explored in the media should have included the simple question: why did Intel release a Linux-hostile machine in the first place? Let’s expand that question. Was it not properly tested? Does Intel not care about Linux? Recall how Microsoft fought Linux affinity at Intel. There’s a lot of food for thought here, especially now that Intel wants to impose UEFI on everyone (with security risks). For ethical computing with no surveillance, no back doors, and no monopoly abuse people should avoid everything from Intel (where possible). They should say NUC you to Intel.