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

AMD Goes Low Power with 6W Ryzen Embedded R1102G & 10W Ryzen Embedded R1305G Processors

AMD Ryzen R1305G Motherboard

If you’d like a relatively low cost (~$200) mini PC featuring a recent processor with a TDP less than 10W your only options up to this point were models with Intel Cherry Trail, Apollo Lake or Gemini Lake processors. AMD launched some 12W-25W processors with Ryzen Embedded V1000 series and Ryzen Embedded R1000 series for embedded systems over the course of the last two years. But the company is now providing lower cost and lower power versions of their Embedded R1000 family with Ryzen Embedded R1102G and Ryzen Embedded R1305G processors with a TDP of respectively 6W and 10W. Ryzen Embedded R1102G & R1305G Key Specs The new processors have many the same features as the previous R1505G & R1606G models but at a lower TDP and performance (frequencies): Ryzen Embedded R1102G – 2-core/2-thread @ 1.2 GHz / 2.6 GHz (Turbo); 3x CU Radeon Vega 3 graphics cores @ 1.0 GHz; 6W TDP Ryzen Embedded R1305G – 2-core/4-thread @ 1.5 …

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

Arm Introduces Cortex-M55 MCU Core, Arm Ethos-U55 microNPU for Cortex-M Microcontrollers

Arm Cortex M55

Artificial Intelligence and the Internet of Things often go hand in hand with AIoT being a new buzz word that came up last year or so. But for AIoT to scale we need ultra-low-cost, low-power solutions capable of doing inference at the sensor node level, and this is only possible with microcontrollers. To achieve this goal, Arm has just unveiled the Arm Cortex-M55 microcontroller core optimized for artificial intelligence workloads that delivers up to a 15x uplift in ML performance and a 5x uplift in DSP performance with greater efficiency, as well as Ethos-U55 microNPU designed for Cortex-M microcontrollers that need even more AI performance (up to 480 times faster), while consuming as little power as possible. Arm Cortex-M55 Key features and specifications: Architecture – Armv8.1-M Bus interface – AMBA 5 AXI5 64-bit master (compatible to AXI4 IPs) Pipeline – 4-stage (for main integer pipeline) Security – Arm TrustZone technology (optional) DSP extension – 32-bit DSP/SIMD extension M-Profile Vector Extension …

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

OmniVision OA805 4K Video Camera SoC Supports 100 ms Boot Time, 4K HEVC Encoding

OmniVision OA805 4K Video Processor

OmniVision OA805 Arm Cortex-A5 4K video camera processor is specifically designed for battery operated security and surveillance cameras, including video doorbells, with the ability to encode 4K30p video streams with HEVC/H.265 video codec at very low power consumption. The processor also has a very short boot-up time of just 100ms, meaning it can go from completely powered off to fully functional upon trigger by a motion detection sensor. That short boot time removes the need for standby or sleep mode further lowering the power consumption and allowing the camera to have up to two years of battery life (albeit no mention of battery capacity was made…). OmniVision OA805 specifications: CPU Main CPU – Arm Cortex-A5 processor with NEON, 32KB I-cache, 32KB D-cache Secondary CPU (SPU) – Arm Cortex-A5 processor with NEON, 32KB I-cache, 32KB D-cache Media Processing Unit (MPU) – 32-bit RISC MCU with 8KB I-cache, 8KB D-cache System Memory – 16-/32-bit LPDDR2, 16-/32-bit DDR3 and DDR3L Storage I/F 1x …

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

GreenWaves GAP9 IoT Application Processor Enables AI on Coin-cell Powered Devices

GAPuino Board

GreenWaves Technologies GAP8 multi-core RISC-V microcontroller was introduced last year for artificial intelligence (AI) at the edge at ultra-low power consumption. GAP8 AIoT SoC was shown to perform inference at 3.7mA against 60mA for the same workload on STM32F7 Arm Cortex-M7 MCU. The company has now expanded its GAP IoT application processor family with GAP9 that delivers five times lower power consumption compared to GAP8 microcontroller while enabling inference on neural networks 10 times larger. Greenwaves GAP9 will bring machine learning and signal processing capabilities to (coin cell) battery operated or energy harvesting devices such as IoT sensors in consumer and industrial markets, wearables, smart building, smart farming and so on. GAP9 is said to combine architectural enhancements with Global Foundries 22nm FDX process to achieve a peak cluster memory bandwidth of 41.6 GB/sec and up to 50 GOPS compute power while consuming only 50mW. The increased memory bandwidth (20x over GAP8) allows for greatly improved detection accuracy while analyzing …

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

Nordic Semi nRF5340 Dual Arm Cortex-M33 SoC Supports Bluetooth 5.1/Mesh, NFC, Thread & Zigbee

After introducing nRF52833 WiSoC with Bluetooth 5.1 direction-finding support last month, Nordic Semiconductors has now launched another multi-protocol wireless SoC with nRF5340 featuring two Arm Cortex-M33 cores and supporting Bluetooth 5.1, Bluetooth Mesh, NFC, Thread & Zigbee. One of the Cortex-M33 is an application core incorporating  1 MB Flash and 512 KB RAM, as well as Arm CryptoCell-312, Arm TrustZone technology, and Secure Key Storage for the highest level of security, and the other Cortex-M33 core is used for networking functions.  The company also announced nRF5340 PDK to get started with the new WiSoC. nRF5340 Dual-Core Multiprotocol SoC Key features and specifications: CPU Application core  – Arm Cortex-M33 @ 128/64 MHz with 1 MB Flash + 512 KB RAM, 8 KB 2-way set associative cache; CoreMark: 510/255; CoreMark/mA: 65/76 Network core –  Arm Cortex-M33 @ 64 MHz with 256 KB Flash + 64 KB RAM, 2 KB instruction cache; CoreMark: 238; CoreMark/mA: 101 Wireless Protocol support – Bluetooth 5.1 LE …

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

Intel Unveils Tremont Low-power x86 Architecture, Lakefield Hybrid Processor

Intel LakeField Processor

Intel Tremont microarchitecture was first leaked in April 2018 as a successor to Goldmont Plus used in Gemini Lake processors among others. But Intel has now made it official and revealed details about Tremont architecture at Linley Fall Processor Conference in Santa Clara, California. The new architecture is said to deliver significant IPC (instructions per cycle) gains compared with Intel’s prior low-power x86 architectures. Tremont-based processors will target client devices, IoT products, 5G networking, efficient datacenter servers, etc… Tremont Architecture Some of the highlights of Tremont architecture include: Intel Core class branch prediction with long history,32 bytes based, L1 predictor (no penalty) and large L2 predictor Out of order fetch – 32KB instruction cache, 32 bytes/cycle, up to 8 outstanding misses 6-wide out of order instruction decode Dual 3-wide clusters Wide decode without the area of a uop cache Optional single cluster mode based on product targets 4 wide allocation 10 execution ports Dual load/store pipelines 32KB data cache 1024 …

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

AAEON M.2 and mPCIe Cards for AIoT Acceleration Run Kneron KL520 AI SoC

The AAEON announcement of its AI Acceleration M.2 and mini-PCIe cards AAEON uses Kneron KL520 AI SoC dual Cortex-M4 on a series of new modules that are accelerating AI edge computing and that only need 0.5 Watt of power. The modules are M.2 and mini-PCIe AI acceleration cards, that offer a new way to come at AI acceleration. What AI Features are Enhanced The cards are meant to enhance and accelerate AI functions, like gesture detection, facial and object recognition, driver behavior in such AIoT areas as access control, automation, and security. History of the AAEON Development Previously AAEON has been offering the M.2 and mini-PCIe AI core modules for the Boxer computers that are based on the Intel Movidius Myriad 2 and Myriad X Vision Processing Units (VPU). Reporting was done on these previous releases in the articles on the UP AI core mini-PCIe card and the  AI Core XM2280 M.2 card, using two Myriad X VPUs. AAEON is …

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