Imagination Unveils PowerVR AX2185 and AX2145 Neural Network Accelerators (NNA)

PowerVR AX2185

Imagination Technologies introduced PowerVR Series2NX neural network accelerator (NNA) last year. At the time, the company claimed the NNA would deliver  twice the performance at half the bandwidth over existing competing solutions, and that it was the first dedicated hardware solution with flexible bit-depth support from 16-bit down to 4-bit. What they did not announce last September were any specific parts. But they’ve just done that today with PowerVR AX2185 and AX2145 NNAs “designed to enable high-performance computation of neural networks at very low power consumption in minimal silicon area”. PowerVR AX2185 PowerVR AX2185 is said to be the highest performing neural network accelerator per mm2 in the market with eight full-width compute engines delivering up to 4.1 TOPS (Tera Operations Per Second), or 2,048 MACs/clock. AX2185 NNA can deliver 3.5 times the performance compared to a desktop GPU. The NNA is best suited for high-end smartphones, smart surveillance and automotive markets. PowerVR AX2145 PowerVR AX2145 is a lower cost …

NVIDIA Introduces Jetson Xavier Devkit and Isaac Robotics Software

NVIDIA Jetson Xavier

NVIDIA Xavier was first unveiled in September 2016 as an artificial intelligence SoC with eight NVIDIA Custom 64-bit Arm cores, a 512-core Volta GPU,  8K video encoding and decoding, and a computer vision accelerator (CVA) now called NVDLA (NVIDIA Deep Learning Accelerator). Earlier this year, the company announced Xavier was sampling,  and DRIVE IX & DRIVE AR SDKs for the automotive market. On the eve of Computer 2018, NVIDIA has introduced Jetson Xavier development kit, as well as Isaac robotics software for autonomous machines. Jetson Xavier key specifications: SoC – NVIDIA Xavier with 8-core ARMv8.2 64-bit CPU, 8MB L2 + 4MB L3 512-core Volta GPU with Tensor Cores 2x NVDLA engines for deep learning 7-way VLIW Processor for vision acceleration VPU with dual 4Kp60 video decoding and encoding System Memory – 16GB 256-bit LPDDR4x | 137 GB/s Storage – 32GB eMMC 5.1 flash Display – 3x eDP/DP/HDMI at 4Kp60 | HDMI 2.0, DP HBR3 Camera 16x CSI-2 Lanes (40 Gbps …

Android 8.1 Firmware and SDK Released for Orange Pi 4G-IoT Board

Orange-Pi-4G-IoT-Android-8.1

When Orange Pi 4G-IoT board launched a few months ago, it shipped with a not so recent Android 6.0 operating system. But the good news is that Shenzhen Xunlong Software has now released Android 8.1 firmware for their Mediatek MT6737M quad core Cortex A53 LTE Cat 4 board, as well as the corresponding SDK. This makes it the cheapest Android 8.1 board with LTE connectivity available on the market so far as it goes for just under $50. The SDK is a large tarball (22.6 GB) split into 11 smaller files. It’s hosted on MEGA so download is fairly fast, but due to the size I had to install MEGA Sync software in order to download it easily. Once the download is complete, it’s not recognized in Nautilus, but you can extract the SDK as follows in a terminal:

This will take a while and extract over a million files for a total of 64.8 GB. We can now …

Sens’it Discovery is a Sigfox IoT Solution with 6 Sensors

Sigfox has just launched Sens’it Discovery, which they describe as a “end-to-end IoT solution, which aims to accelerate the adoption of the IoT (Internet of things) among business and technical professionals”. The solution is comprised for Sens’it 3 device with 6 sensors, sensit.io application, and Sigfox connectivity. Sens’it 3 hardware specifications: MCU – STM32 micro‑controller  Connectivity TI CC1125 radio transceiver Sigfox Ready class 0U Frequencies – 868 to 869.7 MHz, 902 to 908 MHz, or 923.2 MHz (TX) / 922.2 MHz (RX), or 920 to 925 MHz depending on region Transmit Power emission – 14 dBm ERP (RC1), 22 dBm ERP (RC2), 10 dBm ERP (RC3), 22 dBm ERP (RC4) Sensors Thermometer (HTS221) – -40 to 120°C / Accuracy ± 0.5°C Humidity (HTS221) –  0 to 100 / Accuracy ± 3.5% rH (20 to +80% rH) Accelerometer (FXOS8700) –  ±2, 4, 8 g / Accuracy 0.244, 0.488, 0.976 mg Magnetometer (FXOS8700) –  ±1200 μT / Sensitivity 0.1 μT/LSB Light (LTR329) –  …

Nordic Semiconductor nRF52840 Multiprotocol SoC Adds Support for Zigbee 3.0

Nordic Semiconductor nRF52840 was introduced in late 2016 as one of the first Bluetooth 5 ready SoC, and it’s the only  part from Nordic that fully supports Bluetooth 5 longer range. But the chip is actually a multiprotocol SoC and beside Bluetooth, 802.15.4, Ant, Thread and 2.4 GHz proprietary are also supported.  The company has now announced one more wireless protocol working on nRF52840: Zigbee 3.0. The company has released the first engineering release for Zigbee on nRF52840, but the production grade Zigbee 3.0 certified release is planed for H2 2018. The new protocol will be enabled in the S410 v6.0 SoftDevice release. Bluetooth and  Zigbee can run concurrently meaning for example you could create an nRF52840 gateway to control Zigbee smart lights from a smartphone connected over Bluetooth 5. The SDK includes examples for concurrent operation of Zigbee and Bluetooth 5 for a smart light bulb and switch. The company further explains raw data throughput rates of 250kbs can …

Qualcomm QCS603 / QCS605 “IoT” SoCs are Designed for AI and Computer Vision Applications

Qualcommn has unveiled the “Qualcomm Vision Intelligence Platform”, which aims at IoT devices with camera leveraging artificial intelligence and computer vision. The first SoCs part of the platform are QCS605 and QCS603 manufactured with a 10nm process, and equipped with an “advanced image signal processor” and the Qualcomm Artificial Intelligence (AI) Engine, as well Arm CPU cluster, Adreno GPU, and Hexagon DSP. QCS603 & QCS605 specifications: CPU QCS603 – 2x 1.6GHz Qualcomm Kryo 300 Gold cores, 6x 1.7GHz Qualcomm Kryo 300 Silver cores QCS605 – 2x 2.5GHz Qualcomm Kryo 300 Gold cores, 6x 1.7GHz Qualcomm Kryo 300 Silver cores Qualcomm Artificial Intelligence Engine DSP Qualcomm Hexagon 685 Vector Processor 2x Qualcomm Hexagon Vector eXtensions (HVX) GPU – Qualcomm Adreno 615 with OpenGL ES 3.2, Vulkan, OpenCL support Neural Processing – Qualcomm Snapdragon Neural Processing Engine programming interface with support for Tensorflow, Caffe/Caffe2, ONNE, Android NN; 2.1 TOPS @ 1w Memory I/F – 16-bit LPDDR4x @ up to 1866MHz Connectivity WiFi …

Espressif ESP-ADF Audio Development Framework for ESP32 Supports Baidu DuerOS, and Soon Amazon Alexa, Google Assistant, etc…

Espressif Systems have been working on audio applications like Smart Speakers based on ESP32 WiSoC with hardware development kits like ESP32-LyraTD-MSC Audio Mic HDK, and I could test it with Baidu DuerOS using Mandarin language. However, at the time (February 2018), there was not much else that could be done with the hardware kit, since no corresponding ESP32 audio software development kit had been made available. This has now changes since Espressif has just released ESP-ADF Audio Development Framework on Github. The framework will support the development of audio applications for the Espressif Systems ESP32 chip such as: Music player or recorder handling MP3, AAC, WAV, OGG, AMR, SPEEX … audio formats Play music from network (HTTP), storage (SD card), Bluetooth A2DP/HFP Integration with Media services such as DLNA, Wechat, etc.. Internet Radio Voice recognition and integration with voice services such as Alexa, DuerOS, Google Assistant As we can see from the diagram above, the first release supports Baidu DuerOS, …

PHYTEC Introduces phyCORE SoMs & Devkits Based on NXP i.MX8, i.MX 8M, or i.MX 8X Processors

PHYTEC, an embedded systems company headquartered in Germany with global offices, has updated their phyCORE systems-on-module family with 3 sub-families of modules based on NXP i.MX 8, i.MX 8X, or i.MX 8M dual or quad core processors for a total of 9 modules. phyCORE-i.MX 8 Specifications: SoC – NXP i.MX 8Quad,  i.MX 8QuadPlus or  i.MX 8QuadMax Arm Cortex-A72/A53/M4F processor @ up to 1.6 GHz with  Tensilica HiFi 4 DSP @ 666 MHz, 2x Vivante GC7000XSVX GPUs System Memory – 1  to 8GB LPDDR4 RAM Storage – 64MB to 256MB Octal SPI/DualSPI SPI NOR Flash, 4 GB to 128 GB eMMC flash, 4kB EEPROM Connectivity – 2x Gigabit Ethernet PHY 4x 120-pin Board-to-board connectors with: Display – 2x LVDS, 2x MIPI DSI, 1x HDMI Video Input / Camera – 1x HDMI, 2x MIPI CSI Audio – 2x ESAI, up to 4x SAI Networking – 2x 10/100/1000 Mbit/s Ethernet USB – 1x USB OTG,  1x USB 3.0 Serial – 1x UART, 2x …