Edgeless EAI-Series Dual Arm Cortex-M4 MCU Features a 300 GOPS CNN-NPU

Edgeless EAI80 Development Board

Microcontrollers will have an important role to play in AIoT (AI + IoT) applications as they provide the lowest cost and power consumption. Performance is limited but we start seeing MCUs with AI accelerators such as GreenWaves GAP9 multi-core RISC-V microcontroller or Kendryte K210 RISC-V MCU with a KPU AI accelerator. Another option is by Edgeless Semiconductor Co. Ltd (零边界集成电路有限公司) based in Zhuhai, China, and more specifically its Edgeless EAI-Series dual-core Arm Cortex-M4 microcontrollers equipped with a 300 GOPS CNN NPU. Edgeless EAI specifications: CPU – Dual Arm Cortex-M4F @ up to 200Mhz, with DSP instructions, I/D cache for high performance; 500DMIPS/1.25DMIPS/MHz (Dhrystone2.1) AI Accelerator – CNN-NPU clocked at up to 300MHz with 300 GOPS peak throughput; 144MAC/cycle, EER up to 1TOPS/W, for image recognition scenario. Support major CNN Models including Resnet-18, Resnet-34, Vgg16, GoogleNet, Lenet, etc.. Support Convolutional kernel size 1~7 Support Channel/Feature No. up to 512 Support Max/Average pooling function Arithmetic Precision: 16-bit fixed-point Memory Up to 384KB …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

This is what HoneyComb LX2K 16-core Arm Workstation Looks Like (Video)

Arm Workstation

Back in February 2019, while referring to Arm server, Linus Torvalds famously said: I can pretty much guarantee that as long as everybody does cross-development, the platform won’t be all that stable. Or successful. … If you develop on x86, then you’re going to want to deploy on x86, because you’ll be able to run what you test “at home” (and by “at home” I don’t mean literally in your home, but in your work environment). … Which in turn means that cloud providers will end up making more money from their x86 side, which means that they’ll prioritize it, and any ARM offerings will be secondary and probably relegated to the mindless dregs (maybe front-end, maybe just static html, that kind of stuff). SolidRun had already worked on products with NXP LX2160A 16-core Arm Cortex A72 processor and found out it could be a match to make a powerful Arm workstation so that code could be developed natively on …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Linux 5.6 Release – Main Changes, Arm, MIPS & RISC-V Architectures

Linux 5.6 Changelog

Linus Torvalds has just announced the release of Linux 5.6 on the Linux Kernel Mailing List: So I’ll admit to vacillating between doing this 5.6 release and doing another -rc. This has a bit more changes than I’d like, but they are mostly from davem’s networking fixes pulls, and David feels comfy with them. And I looked over the diff, and none of it looks scary. It’s just slightly more than I’d have preferred at this stage – not doesn’t really seem worth delaying a release over. So about half the diff from the final week is network driver fixlets, and some minor core networking fixes. Another 20% is tooling – mostly bpf and netfilter selftests (but also some perf work). The rest is “misc” – mostly random drivers (gpio, rdma, input) and DTS files. With a smattering of fixes elsewhere (a couple of afs fixes, some vm fixes, etc). The shortlog is appended, nothing really looks all that exciting, …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

M5Stack ATOM is a Compact, Fully Integrated ESP32 Development Kit

M5Stack ATOM Lite

When working on a project you may need an MCU or MCU board, an external display, a breadboard, and other accessories like sensors and jumper cables. It does the job, but it can be messy. Recently, we wrote about M5Stack M5StickV AI camera, but the company is better known for its ESP32 IoT development kits enabling neater project thanks to hardware that integrates MCU, I/O headers, display, and sensors into an enclosure. Their latest offerings are ATOM series toolkits that come in two versions: ATOM Lite and ATOM Matrix. Let’s have a look at both. M5Stack ATOM Lite Specifications: SiP – ESP32-PICO-D4 system-in-package with ESP32 dual-core processor with WiFi 4 and Bluetooth 5.0/5.1 Storage – 4 MB flash Crystal oscillator and passive components USB – 1x USB Type-C port Expansion 9-pin header with 6 GPIOs compatible with jumper cables 4-pin PH2.0 connector with 2x GPIO, 5V and GND Misc – Reset button, user button, RGB LED, IR LED Dimensions – …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

ARM9 in 2020 – Meet Microchip SAM9X60 SoC & Evaluation Kit

SAM9X60-EK Evaluation Kit

In my first job, I wrote code for a MIPS processor for VoIP phones, then I switched to NEC/Renesas MCUs for CD and DVD players, before going back to Linux and my first experience with an Arm processor: Cirrus Logic EP9307 with a single ARM9  (ARM920T) core clocked at 200 MHz. That was in 2005, and according to Wikipedia various ARM9 cores were released between 1998 to 2006, and now such cores are not recommended for new IC designs with most companies now building their chips around Arm Cortex-A/M/R cores. At the end of last year, we wrote about Banana Pi BPI-F2S SBC based on Sunplus SP7021 “Plus1” quad-core Cortex-A7 processor with ARM9 and 8051 co-processor. Odd enough but at least the ARM9 core is not the main processor, however, while looking at the upcoming Linux 5.6 Linux kernel log I read an entry about a new SAM9X60 ARM926-based SoC from Microchip. Microchip SAM9X60 ARM9 Processor Quite surprising to have …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Arrow Embedded To Go Free Online Conference, and 3,000 Development Boards Giveaway

Arrow Embedded to Go

With the coronavirus outbreak on-going, many events are either canceled or moving online. Arrow Electronics has now announced what appears to be a completely new online event. Embedded To Go virtual technology exhibition for embedded systems will take place on April 1-3, 2020, and offer technical presentations, information on newly launched technology, and access to Arrow’s sales and engineering teams. The event will entirely free to attend, and you can register online today with a company’s email address. The event will start in about 10 days by so far the virtual “booth map”, “supplier guide” and “lecture area” are inaccessible. We only know what the event should consist of thanks to an article on EENew Embedded: Technical presentation webinars will be hosted by leading suppliers covering AI, IoT and Edge computing, precision measurement, high-performance computing, intelligent condition-based monitoring, and other technological subjects. Information will also be available in the form of videos and white papers on boards and applications. A …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

MikroElektronika Launches Fusion for ARM & EasyPic MCU Development Boards

fusion for arm

During Embedded World 2020 (EW2020), some companies withdraw their presence, while some were at the event. MikroElektronika presented several new boards and among them Fusion for ARM v8 and EasyPic v8 development boards. While we already wrote about Fusion fo TIVA, we haven’t covered any EasyPic board yet. Development boards from MikroElektronika allow rapid prototyping in the most efficient and effortless way. Fusion for ARM v8 Fusion for ARM v8 belongs to the Fusion family of development boards. It has integrated the world’s first embedded debugger/programmer over WiFi, while the CODEGRIP WiFi license is available as an add-on feature. The board is designed to be used in almost every environment retaining full debugging and programming access. The CODEGRIP currently supports more than 1600 microcontrollers from different vendors. The Fusion board integrates a new MCU card standard. It is a low profile standard where sockets consist of two connectors (male/female) which prevents the wrong insertion. The MCU card has standardized dimensions …

Support CNX Software – Donate via PayPal or become a Patron on Patreon

Omnichip Devkit 2 Features Nordic nRF52832 based zGlue ZiP Multichip Module

zGlue Omnichip Devkit

We first covered zGlue Integration Platform (ZiP) in 2018 when the company introduced its chip-stacking technology with a fitness tracker based on ZGZL1BA ZiP equipped with chips from Dialog Semiconductor, Analog Devices, Macronix, MCube and others. The concept is similar to SiP (System-in-Package), but zGlue claims the costs and lead times are much lower with the technology. Earlier this year, ZiP was back in the news thanks to Antmicro GEM custom RISC-V/Arm ASIC, and today, I was informed about zGlue Omnichip devkit 2 that is equipped with a ZiP of the same name, and that can be used to evaluate the technology. zGlue OmniChip ZiP zGlue OmniChip ZiP is a multichip module with the following ICs (aka Chiplets) and specifications: Nordic Semiconductor nRF52832 Cortex-M4F microcontroller with Bluetooth LE and NFC connectivity Texas Instruments BQ25120AYFPR battery charger, buck regulator Maxim Integrated MAX86140ENP+ optical pulse oximeter Texas Instruments TMP108AIYFFR temperature sensor Bosch Sensortec BMM150 magnetometer mCube MC3672 accelerometer SiTime SIT1552AC 32 kHz …

Support CNX Software – Donate via PayPal or become a Patron on Patreon