Since receiving the powerful NVIDIA Jetson AGX Xavier with its ARMv8 Carmel cores on this Tegra194 SoC a while back, it's been quite a fun developer board for benchmarking and various Linux tests. One of the areas I was curious about was whether GCC or Clang would generate faster code for this high performance ARM SoC, so here are some benchmarks.
Back in November is when ARM Holdings posted their GCC compiler support for "Ares", their forthcoming new ARMv8 core design intended for HPC/server SoCs. Ares continues inching closer to launch while now the GNU Assembler has picked up support for recognizing Ares.
The ARM Linux developers continue working on Energy Aware Scheduling (EAS) for the mainline Linux kernel to better handle systems with asymmetric CPU topologies, namely SoCs like those with ARM big.LITTLE cores.
Esri has launched an Arm Linux version of its ArcGIS Runtime SDK for Qt aimed at GIS mapping and analytics applications such as in-vehicle fleet management.
It's been another busy week in compiler land for ARM. First up, the GCC compiler now officially supports the Cortex-A76. The A76 is the new Cortex processor announced back in May for yielding much better performance and efficiency, especially for AI and machine learning.
This is a non-sponsored guest post written by Marc Goodner: Principal Program Manager, Microsoft, and Jeremias Cordoba: Innovation Engineer, Toradex.
One of our major goals for Qt 5.9 LTS was to improve the performance and memory consumption compared to our previous long-term-support release Qt 5.6 LTS. In this blog post, I want to highlight the performance increase in modern embedded processors that support the 64-bit ARMv8 instruction set.
With the Linux 4.16 kernel release likely to happen this coming Sunday and that marking the opening of the Linux 4.17 merge window, many subsystem maintainers are preparing their "-next" trees of feature updates.
Herbert Xu has submitted the crypto subsystem updates for the Linux 4.16 kernel. This time around there are a number of ARM/ARM64 related improvements.
Kernel Page Table Isolation (KPTI) landed at the start of the year for x86/x86_64 systems for fending off the much talked about CPU attacks while the AMD64 / 64-bit ARM code is still a work-in-progress but looks like it will be squared away for the upcoming Linux 4.16 kernel cycle.
CentOS developers Karanbir Singh and Jim Perrin announced the release of the CentOS 7.4 operating system for supported architectures, a release that brings all the latest updates and security patches.
Canonical announced that it partnered with NEC Display Solutions Europe to collaborate on a new digital signage platform powered by the Ubuntu Core operating system for embedded and IoT devices.
What is the best way to save power consumption of your embedded Linux system? Is there any way to save max power and resume operation ? Yes. It is ‘hibernate’ mode, one of the Power Modes in Linux. This article talks about how we utilized this ‘hibernate mode’ in our Reference Platform Kit Meissa-I with eSOMiMX6-micro SOM.
Hardkernel is doing a good job at providing working images with GPU / VPU support, and documentation for their ODROID boards. But while Exynos based ODROID-XU4(Q) boards already get firmware images with a recent Linux 4.9 kernel, Amlogic S905 based ODROID-C2 board’s Ubuntu 16.04 images still rely on the Linux 3.14 kernel released by Amlogic, plus various patchsets.
Canonical's Simon Fels announced today that he's working on bringing the Snapd Snappy daemon to the Raspberry Pi Foundation's Raspbian operating system to allow the installation of Snaps.
Yesterday as I wrote about the Embedded Systems Conference 2017 schedule I came across a potentially interesting talk entitled “Building A Brain With Raspberry Pi and Zulu Embedded JVM” by Azul Systems that will explain how to build a brain emulator using a cluster of Raspberry Pi boards. I wanted to find more about it, but I have not been able to find any details about the project/demo at this stage.
GPU compute promises to deliver much better performance compared to CPU compute for application such a computer vision and machine learning, but the problem is that many developers may not have the right skills or time to leverage APIs such as OpenCL. So ARM decided to write their own ARM Compute library and has now released it under an MIT license.
Orange Pi 2G-IoT was unveiled at the start of the year as an ultra cheap ($10) Linux development board with 2G cellular connectivity. The board has just launched for $9.90 + shipping on Aliexpress.
Friends and fellows, we’re super glad to announce the outcome of a beautiful partnership with ARM University Program and Mouser: the Embedded Linux Education Kit. This is the ninth and latest Education Kit from ARM University and it’s beautiful to be part of such a great initiative.
The maker of Orange Pi boards, Shenzhen Xunlong Software, has partnered with Canonical to launch Orange Pi app store, allowing developers to gain a simple mechanism to share their applications, projects and scripts with the Orange Pi community.
Page 1 of 15