CNX Software - Embedded Systems News

November 26, 2018November 26, 2018 by Jean-Luc Aufranc (CNXSoft) - 5 Comments

Facebook BOLT Speeds Up Large x86 & ARM64 Binaries by up to 15%

Compilers like GCC OR LLVM normally do a good job at optimizing your code when processing your source code into assembly, and then binary format, but there’s still room for improvement – at least for larger binaries -, and Facebook has just released BOLT (Binary Optimization and Layout Tool) that has been found to reduce CPU execution time by 2 percent to 15 percent. The tool is mostly useful for binaries built from a large code base, with binary size over 10MB which are often too large to fit in instruction cache. The hardware normally spends lots of processing time getting an instruction stream from memory to the CPU, sometimes up to 30% of execution time, and BOLT optimizes placement of instructions in memory – as illustrated below – in order to address this issue also known as “instruction starvation”. BOLT works with applications built by any compiler, including the […]

November 25, 2018 by Jean-Luc Aufranc (CNXSoft) - 22 Comments

An Attempt to Benchmark Entry-level x86 Boards against RK3399 & Exynos Arm Boards

Some Arm boards have become quite powerful, while hardware based on low power Intel processor has generally become cheaper with both architectures somewhat converging in terms of performance and price. Piotr Maliński got interested and purchased some low cost (<$150) Intel hardware to compare to mid-range Arm boards, throwing a Raspberry Pi 3 B+ into the mix as well for comparison. Those are the Intel test boards / computers: Qotom motherboard with Intel Atom Z3735F Bay Trail processor, 2GB RAM, 32GB flash – $74 + shipping on Aliexpress Piesia nano ITX board with Intel Celeron N2806 Bay Trail processor, DDR3 SO-DIMM socket, SATA / mSATA interfaces – Piotr found it for around $85 on Aliexpress, but the price now jumped to over $150 plus shipping, which does not make it very attractive Generic thin mini ITX motherboard based on Celeron N3160 “Braswell” processor, DDR3 SO-DIMM socket, SATA / mSATA interfaces. $62.68 […]

November 24, 2018November 29, 2018 by Jean-Luc Aufranc (CNXSoft) - 14 Comments

X96S Amlogic S905Y2 TV Stick Spotted for $39 and Up

Lacking Ethernet support, the latest Amlogic S905Y2 processor is designed for 4K HDMI TV dongles. However excluding Amlogic’s own TV stick reference design, we only had seen S905Y2 TV boxes so far, and no actual commercial product following the TV stick form factor. That has now changed since X96S TV stick powered by Amlogic S905Y2 processor has appeared on several Aliexpress stores with price starting at $38.76 including international shipping.X96S TV dongle specifications: SoC – Amlogic S905Y2 quad core ARM Cortex-A53 @ up to 2.0 GHz with Mali-G31 MP2 “Dvalin” GPU System Memory / Storage options 2GB LPDDR4, 16GB eMMC flash, micro SD card slot 4GB LPDDR4, 32GB eMMC flash, micro SD card slot Video & Audio Output – HDMI 2.1 output with HDR up to 4K UHD @ 75 Hz Video Codecs – VP9 Profile-2 up to 4K 60fps, 10-bit H.265 up to 4K 60fps, AVS2-P2 up to […]

November 23, 2018November 23, 2018 by Jean-Luc Aufranc (CNXSoft) - 1 Comment

Alfawise T1 Gemini Lake Mini PC Offered for $150 (Promo)

Gemini Lake mini PCs have been around for a while, but not quite at the price most expected, that is roughly the same as Apollo Lake, possibly due to shortages of Intel’s entry level processors. So for example, I had yet to see any Gemini Lake computers for under $150, with with Black Friday taking place now, GearBest decided to offer Alfawise T1 mini PC powered by an Intel Celeron N4100 quad core processor for just $149.99 with coupon GBJEAN. Alfawise T1 specifications: SoC – Intel Celeron N4100 quad core Gemini Lake processor up to 2.4 GHz with Intel UHD Graphics 600; 6W TDP System Memory – 4GB DDR4 Storage – 64GB eMMC flash, 2.5″ SATA bay, M.2 SSD slot, micro SD card Video Output – 2x HDMI 2.0 ports up to 4K @ 60 Hz Audio – Via HDMI, built-in microphone, 3.5mm audio jack Connectivity – Gigabit Ethernet, dual […]

November 23, 2018November 23, 2018 by Jean-Luc Aufranc (CNXSoft) - 2 Comments

ODROID-XU4 and ODROID-XU4Q Boards Going for $49 (Promo)

ODROID-XU4, and its fanless ODROID-XU4Q sibling, are neat little single board computer packing lots of power into a small form factor. I tested ODROID-XU4 with Ubuntu 18.04 recently and was relatively impressed by how well it worked considering it’s an Arm platform, as there were still admittedly some limitations. But as they say at $59 a board you can’t beat the price. Except you can actually do, as Hardkernel is offering both ODROID-XU4Q and ODROID-XU4 for just $49 during Black Friday here and there. If you’ve already forgotten about the board it is equipped with a Samsung Exynos 5422 octa-core Cortex A15/A7 processor, 2GB RAM, eMMC module support, Gigabit Ethernet, USB 3.0, HDMI 1.4, and more. You can read the full specifications here. The only difference between ODROID-XU4 and ODROID-XU4Q is the latter comes with a large heatsink, while the former is cooled by fan. If you are currently shopping […]

November 23, 2018 by Jean-Luc Aufranc (CNXSoft) - 17 Comments

HiSilicon Kirin 980 Benchmarks Show Cortex A76’s Impressive Performance & Efficiency Improvements

HiSilicon Kirin 980 was the first processor announced with Cortex A76 cores, which were said to deliver laptop-class performance, with 35% performance improvement over Cortex A75, and around twice the performance of Cortex A73 cores thanks to improvements, and a higher CPU frequency up to 3.0 GHz. But now that Huawei Mate 20 / Mate 20 Pro smartphones are out, various reviews have been published, and Anandtech was mostly able to confirm the claims. In most case, actual results were inline with expectation despite Kirin 980 clock speed being “limited” to 2.6 GHz. Looking at GeekBench 4 single-thread integer and floating-point scores, the Cortex A76 core based Kirin 980 is significantly faster than Cortex A73 powered Snapdragon 835 clocked @ 2.45 GHz. Precisely: 1.77x faster in the integer score,and 2.21x faster in the floating point score. SPECS2006 confirmed the good performance with 1.89x higher integer score, and 2.04x faster for […]

November 22, 2018 by Jean-Luc Aufranc (CNXSoft) - 3 Comments

Open Source Hardware SpiderSoM System-on-Module Features Intel MAX 10 FPGA

When embedded systems companies offer a system-on-module (SoM) and a baseboard, the later is usually open source hardware with all design files provided so that customers can leverage the work for their own baseboard, but files for the SoM are normally not released to customers. Intel MAX 10 FPGA based Aries SpiderSoM and SpiderBase change that, as the company has decided to release both the module and carrier board KiCAD designs under a CERN OHL v1.2 license. SpiderSoM system-on-module specifications: FPGA – Intel MAX 10 FPGA in F256 package from 10M04DC to 10M50DA System Memory – Optional 128/256/512MB DDR3 DRAM for 10M 16/25/40/50 FPGAs Storage – Optional 4 MB SPI NOR, optional 4 GB eMMC flash 230-pin MxM2 edge connector with 178x FPGA GPIO pins, including 13 LVDS transmitters and 54 receivers Misc – RTC with battery backup, programmable clock generator and PLL, with optional external reference input Power Supply […]

November 22, 2018June 4, 2019 by Jean-Luc Aufranc (CNXSoft) - 10 Comments

Orange Pi AI Stick 2801 Neural Compute Stick SDK & Documentation Released

We covered the launch of Orange Pi AI Stick 2801 neural compute stick a few days ago, the first easily available Gyralcon Lightspeeur based USB stick, and noted that while the hardware was there, we had no details about software development kit and documentation at the time. I’ve got some more information now. First, the company release an English presentation about the neural stick, and while it’s not technical documentation, it provides insights into what it is capable of, and an overview about the workflow. More importantly, Shenzhen Xunlong Software also released Orange Pi AI Stick SDK and user manual for x86 PC, as well as cat/dog data and pre-trained models to get started. However, if you want to perform training with your own data, you’ll need to purchase the stick plus PLAI model transformation and training tools sold on Aliexpress for $218 plus shipping, that’s $69 for the hardware, […]