Android Things 1.0 Released with Support for NXP i.MX 8M, Qualcomm SDA212/SDA624 and Mediatek MT8516 SoMs

Innocomm-WB10AT

Brillo Project was renamed to Android Things with the release of a developer preview back in December 2014, and the operating system enabling developers and companies to build and maintain Internet of Things devices at scale. The OS has now graduated so-to-speak with the release of Android Things 1.0 with long-term support for production devices, and this was to be expected as several Android Things devices were announced earlier this year. The new release adds supports for new system-on-modules (SoMs) based on the NXP i.MX8M, Qualcomm SDA212, Qualcomm SDA624, and MediaTek MT8516 SoCs. These modules are certified for production use with guaranteed long-term support for 3 years, and development hardware and reference designs for these SoMs will be available in the coming months. The Raspberry Pi 3 Model B and NXP i.MX7D boards and system-on-modules are still supported, but support for NXP i.MX6UL devices will be deprecated. Check out the hardware page for a full list of supported platforms. Google …

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 …

Status of Embedded GPU Ecosystem – Linux/Mesa Upstream Support (ELC 2018 Video)

The Embedded Linux Confernce is on-going, and the Linux Foundation has been uploading videos about talks in a timely manner on YouTube. I checked out at RISC-V keynote yesterday, but today I’ve watched a talk by Robert Foss (his real name, not related to FOSS) from Collabora entitled “Progress in the Embedded GPU Ecosystem”, where he discusses open source software support in Linux/Mesa from companies and reverse-engineering support. The first part deals with the history of embedded GPU support, especially when it comes to company support. Intel was the first and offers very good support for their drivers, following by AMD who also is a good citizen. NVIDIA has the Nouveau driver but they did not really backed it up, and Tegra support is apparently sponsored by an aircraft supplier. Other companies have been slower to help, but Qualcomm has made progress since 2015 and now support all their hardware, Broadcom has a “one man team” handling VideoCore IV/V,  and …

Vulkan 1.1 and SPIR-V 1.3 Specifications Released

The Khronos Group released Vulkan 1.0 specifications in 2015 as a successor of OpenGL ES, compatible with OpenGL ES 3.1 or greater capable GPU, and taking less CPU resources thank to – for instance – better use of multi-core processors with support for multiple command buffers that can be created in parallel. A year later, we saw Vulkan efficiency in a demo, since then most vendors have implemented a Vulkan driver for their compatible hardware across multiple operating systems, including Imagination Technologies which recently released Vulkan drivers for Linux. The Khronos Group has now released Vulkan 1.1 and the associated SPIR-V 1.3 language specifications. New functionalities in Vulkan 1.1: Protected Content – Restrict access or copying from resources used for rendering and display, secure playback and display of protected multimedia content Subgroup Operations – Efficient mechanisms that enable parallel shader invocations to communicate, wide variety of parallel computation models supported Some Vulkan 1.0 extensions are now part of Vulkan 1.1 …

Snapdragon 700 Mobile Platform Series To Bring On-Device Artificial Intelligence to Mid-Range Smartphones

Qualcomm has announced a new family filling the gap between the mid-range Snapdragon 600 series, and the high-end Snapdragon 800 series, with Snapdragon 700 mobile platform series which will include on-device AI supported by the Qualcomm Artificial Intelligence (AI) Engine, as well as improvements to camera, device performance and power through Qualcomm Spectra ISP, Kyro CPU, Hexagon Vector Processor and Adreno Visual Processing subsystem (Yes, Qualcomm has a new name for everything, as GPU is now VPS). Snapdragon 700 Mobile Platform Series highlights: Artificial Intelligence – Multi-core Qualcomm AI Engine delivering up to 2x improvements for on-device AI applications compared to the Snapdragon 660 Mobile Platform. Camera – Qualcomm Spectra ISP will allow for better photos in different lighting conditions, slow motion capture, and improvements thanks to AI processing. Performance and Battery life – The new Qualcomm Spectra ISP, Kryo CPU and Adreno Visual Processing subsystem in 700 series will deliver up to 30% improvements in power efficiency, and better …

Qualcomm Snapdragon 820E Launched for the Embedded Market, DragonBoard 820c Board Selling for $199

Qualcomm Snapdragon processors are mainly used in smartphones manufactured in high volume, and in the past if you contacted the company to use their processor for your custom project with a target yearly production of a few thousands pieces, they’d just ignore you. This started to change in late 2016 with the launch of Snapdragon 410E and 600E processors based on mobile version of Snapdragon 410 and 600 processors minus the modem, but  instead targeting the embedded space and the Internet of Things, which anybody could purchase easily through Arrow Electronics, and offering a 10-year life cycle. Those are good if you are satisfied with entry-level or mid-range processor, but the company has now announced the launch of Snapdragon 820E for customers requiring better performance for their application. Snapdragon 820E specifications appears to be moslty the same as Snapdragon 820 except for the lack of X12 cellular modem: CPU – 4x Qualcomm 64-bit Kryo CPU cores @ up to 2.35 GHz GPU …

Qualcomm Snapdragon X24 LTE Cat 20 Modem Supports up to 2Gbps Download Speed (in Theory)

Qualcomm can already achieve peak download speed of 1.2 Gbps over 4G cellular network in Snapdragon 845 processor thanks to its Snapdragon X20 LTE modem, but the company has been working on an even faster modem with Snapdragon X24 modem support LTE Cat.20 download speed of up to 2 Gbps. That’s even faster than Gigabit Ethernet, at least in theory, as with all wireless technologies you can only achieve the maximum throughput in the lab, and upload speeds will be lower – but still decent – at up to 316 Mbps. You’d also have to find a Telco that can handle such speeds. Qualcomm X24 cellular modem specifications: LTE Category – 20 Downlink Features 7×20 MHz carrier aggregation Up to 4×4 MIMO on five carriers Maximum 20 spatial streams Full-Dimension MIMO (FD-MIMO) Up to 256-QAM Peak Download Speed – 2 Gbps Uplink Features Qualcomm Snapdragon Upload+ 3×20 MHz carrier aggregation Up to 2x 106Mbps LTE streams Up to 256-QAM Uplink …

Qualcomm Developer’s Guide to Artificial Intelligence (AI)

Qualcomm has many terms like ML (Machine Learning), DL (Deep Learning), CNN (Convolutional Neural Network),  ANN (Artificial Neural Networks), etc.. and is currently made possible via frameworks such as TensorFlow, Caffe2 or ONNX (Open Neural Network Exchange). If you have not looked into details, all those terms may be confusions, so Qualcomm Developer Network has released a 9-page e-Book entitled “A Developer’s Guide to Artificial Intelligence (AI)” that gives an overview of all the terms, what they mean, and how they differ. For example, they explain that a key difference between Machine Learning and Deep Learning is that with ML, the input features of the CNN are determined by humans, while DL requires less human intervention. The book also covers that AI is moving to the edge / on-device for low latency, and better reliability, instead of relying on the cloud. It also quickly go through the workflow using Snapdragon NPE SDK with a total of 4 steps including 3 …