artificial intelligence (AI) News - Page 104 of 121 - CNX Software

May 18, 2019 by Jean-Luc Aufranc (CNXSoft) - 4 Comments

Embedded Linux Conference & Open Source Summit 2019 Schedule

In the last few years, I covered the Embedded Linux Conference and IoT Summit schedules since both were happening at the same time and in the same location. But the Linux Foundation have recently announced the Embedded Linux Conference will combine with the Open Source Summit, so the IoT Summit appears to have been phased out. The full schedule for the events taking place on August 21 – 23, 2019 at the Hilton San Diego Bayfront, USA, has also been released, so I’ll create a virtual schedule with some of the sessions most relevant to this blog. Wednesday August 21, 2019 11:30 – 12:05 – What’s New with U-Boot? by Simon Glass, Google LLC U-Boot is a widely used bootloader in embedded systems. Many users are unaware of the wide feature-set of U-Boot, particularly features added in the last few years. This talk aims to bring users (and prospective users) […]

May 15, 2019 by Jean-Luc Aufranc (CNXSoft) - 12 Comments

ToyBrick RK3399Pro Board Shown to Outperform Jetson Nano SBC

NVIDIA created a lot of buzz when they released $99 Jetson Nano SBC featuring a 128-core Maxwell GPU, and said to deliver 472 GFLOPS of compute performance for running modern AI workloads with a power consumption of around 5 watts. But Jetson Nano is not the only low cost platform to deliver high performance at low power for AI workloads, as for example Rockchip RK3399Pro (RK1808 NPU) found in boards such as Toybrick RK3399Pro is said to deliver 3 TOPS for INT8, 300 GOPS for INT16, and 100 GOPS for FP16 inferences. Those operations per second numbers can be confusing and misleading, so it’s important to check out the performance of actual neural network models, and Rockchip did provide some RK3399Pro benchmarks last year for Inception V3, ResNet34 and VGG16 models comparing the results to Apple A11, Huawei Kirin 970, and NVIDIA Jetson TX2. However, ideally you’d want result from […]

May 10, 2019May 11, 2019 by Jean-Luc Aufranc (CNXSoft) - 15 Comments

Rockchip RK1808 AI Compute Stick Launched with Linux SDK

Rockchip RK1808 looks like a nifty and inexpensive little chip for artificial intelligence applications delivering up to 3.0 TOPS at low power, and the company has already released documentation and a Linux SDK with Caffe and Tensorflow framework support for the chip. So the main hurdle now is to get hardware to play with. Some people are selling (samples?) of the official RK1808-EVB on Taobao, but it costs close to $500 US. There’s still no RK1808 development board, but Rockchip has discreetly launched the RK1808 AI Compute Stick a few weeks ago. RK1808 AI Compute Stick specifications: SoC – Rockchip RK1808 dual core Cortex-A35 processor with NPU AI inference performance – 3 TOPS for INT8, 300 GOPS for INT16, 100 GOPS for FP16 Video – 1080p60 H.264 decoding, 1080p30 H.264 encoding Camera, ISP – 2MP camera support, ISP with BT.601/656/1120 support Host Interface – USB 3.0 port Power Supply – […]

May 5, 2019May 5, 2019 by Jean-Luc Aufranc (CNXSoft) - 1 Comment

Grove AI HAT Helps Raspberry Pi Run Edge Computing Workloads

Last year we wrote about Kendryte K210 dual core RISC-V processor specifically designed for for machine vision and machine hearing as well as the corresponding Kendryte KD233 which enables inference at the edge, e.g. tasks such as face recognition or object detection. Latter on we found the processor in Sipeed M1 module which went for as low as $5 in a crowdfunding campaign, and was fitted to some low cost boards now selling for $12.90 on Seeed Studio. The latter company has now designed Grove AI HAT that aims to assist Raspberry Pi in running the edge computing workloads previously described, as exposes 6 Grove interfaces to extend functionality with some of the Grove add-on modules. Grove AI HAT specifications: AI Module – Sipeed “MAIX” M1 with Kendryte K210 dual core RISC-V processor @ 600 MHz, KPU Convolutional Neural Network (CNN) hardware accelerator, APU audio hardware accelerator, 8 MB general […]

April 30, 2019April 30, 2019 by Jean-Luc Aufranc (CNXSoft) - 15 Comments

Rockchip RK1808 Datasheet, TRM, Schematics and Linux SDK Released

Rockchip RK1808 is the first chip from the company fully dedicated to artificial intelligence applications. The Neural Processing Unit (NPU) features an accelerator delivering up to 3.0 TOPS and is coupled with two low power Arm Cortex-A35 cores allowing it to run Linux. We’ve had the specifications for RK1808 for a while, but the company has recently posted hardware and software resources on their open source website. On the hardware side we’ve got: RK1808 Technical Reference Manual (TRM) RK1808 datasheet PDF Schematics for the company’s official RK1808-EVB On the software side we can get the Linux SDK from Github as explained in the Wiki:

git clone https://github.com/rockchip-linux/repo
mkdir linux
cd linux
../repo/repo init --repo-url=https://github.com/rockchip-linux/repo -u https://github.com/rockchip-linux/manifests -b master -m rk1808_linux_release.xml
../repo/repo sync

git clone https://github.com/rockchip-linux/repo

mkdir linux

cd linux

../repo/repo init --repo-url=https://github.com/rockchip-linux/repo -u https://github.com/rockchip-linux/manifests -b master -m rk1808_linux_release.xml

../repo/repo sync

Finally configure the build and start the build process:

sudo apt install liblz4-tool build-essential
source envsetup.sh rockchip_rk1808
./build.sh

sudo apt install liblz4-tool build-essential

source envsetup.sh rockchip_rk1808

./build.sh

After a while, or more accurately close to two hours on a Laptop with Ryzen 7 2700U processor, 8GB RAM, and hard drive, we’ll get U-boot, Linux, buildroot based rootfs, and firmware files and in […]

April 19, 2019 by Jean-Luc Aufranc (CNXSoft) - No Comments

Qualcomm Mesh Networking DevKit Supports Amazon AVS

Qualcomm Mesh Networking Devkit for Amazon AVS

The Qualcomm Mesh Networking Development Kit for Amazon AVS enables integration of Amazon Alexa Voice Services into mesh Wi-Fi systems. A somewhat recent blog post on Amazon Developer website explains the devkit is the first ever Amazon-qualified reference design for a mesh WiFi system with Alexa built-in. The reference platform is based on the Qualcomm IPQ4019 SoC, includes a rectangular 4-microphone array, far-field audio processing algorithms for noise suppression, acoustic echo cancellation, wake word engine, and the AVS Device SDK. Qualcomm Mesh Networking DevKit specifications: WiSoC – Qualcomm IPQ4019 quad core Arm Cortex-A7 processor @ 717 MHz with SIMD DSP, WiFi 5; 40 nm process technology System Memory – 1GB DDR3L RAM Storage – eMMC flash and microSD card Display I/F – LCD interface Connectivity WiFi Standards: 802.11ac Wave 2, 802.11ac, 802.11p, 802.11n Bands: 2.4 GHz, 5 GHz Peak speed: 1.733 Gbps Channel Utilization: 20/40/80 MHz, 5/10/20/40 MHz MIMO Configuration: […]

April 18, 2019 by Jean-Luc Aufranc (CNXSoft) - No Comments

MIPS Based TritonAI 64 AI IP Platform to Enable Inferencing & Training at the Edge

After announcing their first MIPS Open release a few weeks ago, Wave Computing is back in the news with the announcement of TritonAI 64, an artificial intelligence IP platform combining MIPS 64-bit + SIMD open instruction set architecture with the company’s WaveTensor subsystem for the execution of convolutional neural network (CNN) algorithms, and WaveFlow flexible, scalable fabric for more complex AI algorithms. TritonAI 64 can scale up to 8 TOPS/Watt, over 10 TOPS/mm2 using a standard 7nm process node, and eventually would allow both inference and training at the edge. The platform supports 1 to 6 cores with MIPS64r6 ISA boasting the following features: 128-bit SIMD/FPU 8/16/32/int, 32/64 FP datatype support Virtualization extensions Superscalar 9-stage pipeline w/SMT Caches (32KB-64KB), DSPRAM (0-64KB) Advanced branch predict and MMU Integrated L2 cache (0-8MB, opt ECC) Power management (F/V gating, per CPU) Interrupt control with virtualization 256b native AXI4 or ACE interface Here’s the […]

April 18, 2019 by Jean-Luc Aufranc (CNXSoft) - 3 Comments

$50 Anker Roav Bolt Car Charger is Optimized for Google Assistant

While it may be tempting to check your messages, make phone calls or checking something on your smartphone while driving, it’s never a good idea. But thanks to Anker Roav Bolt car charger with built-in Bluetooth connectivity and a microphone array, you can perform those tasks through Google Assistant while keeping your eyes on the road. Anker Roav Bolt key features and specifications: Voice Chip – Far-Field Voice Processor Audio 2x MEMS Microphones 3.5mm audio jack Noise cancellation, acoustic echo cancellation Connectivity – Bluetooth 4.2 Misc – 1x physical button used to trigger GVA (Google Voice Assistant), 4x RGB LED Power Input – 12V-24V cigarette lighter sockets USB Output – 24W, 5V/2.4A max per port, Anker PowerIQ Technology So you get to charge your phone, while it is connected to your car audio system over Bluetooth or the audio jack, and make calls, start listening to a podcast, or ask […]