Latest News Archives - Page 420 of 576 - SmartCitiesElectronics.com

Senseeker claims DROIC is world’s first eight micron pitch, dual-band version

Tue, Feb 11, 2020

Claimed to be the first dual-band, infra red imaging digital read-out integrated circuit (DROIC) the Oxygen RD0092 is shipping now from Senseeker Engineering.

The specialist in digital infra red image sensing technology, says it is the first eight micron pitch dual-band DROIC, to be available in the industry. It supports a 1280 x 720 frame size at over 500 frames per second and dual-polarity inputs to provide compatibility with all industry-standard direct-injection detector materials. It was designed to optimise infra red imaging system performance through multiple operating modes.

The company’s custom products are used in proprietary designs, so it was a natural progression to create an off-the-shelf version, said Kenton Veeder, Senseeker Engineering’s president. “This allows infra red image system developers to get immediate access to the latest technology without the cost and risk associated with custom designs,” he added.

In infra red search and track systems, the global shutter mode and windowing capability enables an unlimited number of 32 x 32 windows at over 8,000 frames per second to detect and track multiple objects in real-time. This is particularly targeted at surveillance and reconnaissance applications.

For situation awareness applications, where threat detection is critical, high dynamic range (HDR), dual integration mode can expand the possible dynamic range over 110dB. This mode runs two integration times simultaneously on a checkerboard pattern of pixels to optimise range, resolution and detection sensitivity of the system.

The Oxygen RD0092 DROIC supports time of flight or range gated imaging, through asynchronous integration and only a propagation delay between clock input and pixel operation.

The operating modes or window sizes can be changed on-the-fly, and users can toggle detector polarity or checkerboard integration pattern between frames, “by flipping just a few bits,” explained Dr Thomas Poonnen, director of engineering at Senseeker.

Applications also include infra red search and track and infra red astronomy.

Senseeker Engineering is a US-owned transducer IC semiconductor company that specialises in the design of digital imaging sensors and read-out integrated circuits for hybrid infra red image sensing arrays. Senseeker’s products and intellectual property (IP) are used by designers in a variety of infra red image sensing solutions.

http://www.senseeker.com

> Read More

Arm adds IP and processors to its to AI offering

Mon, Feb 10, 2020

For on-device intelligence for IoT applications, Arm has announced new IP and a neural processor to boost machine learning performance.

In a single announcement, the company introduced machine learning (ML) IP, the Arm Cortex-M55 processor and Arm Ethos-U55 neural processing unit (NPU).

The IP and supporting unified toolchain enable AI hardware and software developers what Arm describes as “unprecedented levels of on-device ML processing” for small, power-constrained IoT and embedded devices.

Explaining the need for AI, Dipti Vachani, senior vice president and general manager, Automotive and IoT Line of Business, Arm, said: “Enabling AI everywhere requires device makers and developers to deliver machine learning locally on billions, and ultimately trillions of devices”.

As the IoT intersects with AI advances and the rollout of 5G, more on-device intelligence means that smaller, cost-sensitive devices can be smarter and more capable while relying less on the cloud or internet for greater privacy and reliability.

Arm explains that this intelligence on microcontrollers designed securely from the ground up, reduces silicon and development costs and speeds up time to market for developers.

The Arm Cortex-M55 is described as Arm’s most AI-capable Cortex-M processor. It is the first to be based on the Armv8.1-M architecture with Arm Helium vector processing technology. Cortex-M55 delivers up to a 15-fold uplift in ML performance and a five-fold uplift in DSP performance, with greater efficiency, compared to previous Cortex-M generations, reports Arm.

Additionally, Arm Custom Instructions will be available to extend processor capabilities for specific workload optimisation.

The Ethos-U55 is Arm’s first microNPU (neural processing unit) for Cortex-M. It is designed to deliver a combined 480x leap in ML performance to microcontrollers.

Paired with the Cortex-M55, it can deliver a combined 480-fold increase in ML performance over existing Cortex-M processors.

The Ethos-U55 is highly configurable and specifically designed to accelerate ML inference in area-constrained embedded and IoT devices. Compression techniques save power and reduce ML model sizes significantly to enable execution of neural networks that previously only ran on larger systems.

The Cortex-M55 and Ethos-U55 are supported by Arm’s Cortex-M software tool chain. This ensures a unified development flow for traditional, DSP and ML workloads. There are specific integration and optimisations for leading machine learning frameworks (e.g. TensorFlow Lite Micro).

The processors and the accompanying Corstone reference design work with Arm TrustZone to ensure security can be more easily incorporated into the complete SoC.

Ecosystem partners, include Amazon, Alif Semiconductor, Bestechnic, Cypress, Dolby, Google, NXP, Samsung and STMicroelectronics.

http://www.arm.com

> Read More

Low-power DDR5 DRAM achieves data speeds for AI and 5G

Fri, Feb 07, 2020

Micro Technology is shipping what it claims is the first low-power DDR5 DRAM in mass production. The LPDDR5 DRAM will be used in Xiaomi’s the soon-to-be-released Mi 10 smartphone. Micron says that the LPDDR5 DRAM provides Xiaomi with power efficiency and fast data access speeds to meet consumer demand for artificial intelligence (AI) and 5G functionality in smartphones.

Dr. Raj Talluri, senior vice president and general manager of the Mobile Business Unit at Micron, said: “Micron’s LPDDR5 DRAM addresses [AI and 5G] requirements with a 50 per cent increase in data access speeds and more than 20 per cent power efficiency compared to previous generations.”

The LPDDR5 DRAM has been designed to address the growing demand for higher memory performance and lower energy consumption in automotive, client PCs and networking systems built for 5G and AI applications. LPDDR5 can provide more than a 20 per cent reduction in power use compared to LPDDR4x memory.

It delivers the speed and capacity needed to feed AI engines built directly into mobile processors. These processors rely on high data rates from Micron’s internal LPDDR5 memory to power their machine learning capabilities.

The next-generation LPDDR5 memory allows 5G smartphones to process data at peak speeds of up to 6.4Gbits per second, to prevent 5G data bottlenecks, explains Micron. Examples are autonomous vehicles that require a memory subsystem with a larger bandwidth to support real-time computing and data processing.

Micron is shipping LPDDR5 to customers in capacities of 6Gbyte, 8Gbyte and 12Gbyte and at data speeds of 5.5Gbits per second and 6.4Gbits per second.

The LPDDR5 in a multichip package will also provide longer battery life and higher bandwidth to enable high-performance image processing that was previously reserved for premier smartphones.

In the first half of 2020, the Micron LPDDR5 will also be available in a UFS-based multi-chip package (uMCP5) for use in mid- and high-tier smartphones.

http://www.micron.com

> Read More

Hailo-8 has processor architecture specifically for deep learning

Wed, Feb 05, 2020

Artificial intelligence (AI) chipmaker, Hailo, is sampling the Hailo-8 deep learning processor. The chip’s architecture enables edge devices to run sophisticated deep learning applications that could previously run only on the cloud. It can be used in multiple industries, but the company has a focus on automotive.

The Hailo-8 processor features up to 26 Tera operations per second (TOPS), to “significantly outperform” other edge processors in terms of area and power efficiency, says Hailo. The architecture design relies on the core properties of neural networks, so that edge devices can now run deep learning applications at full scale more efficiently, effectively, and sustainably than traditional solutions, while significantly lowering costs, explains the company.

Hailo is working with leading OEMs and Tier-1 automotive companies in advanced driver assistance systems (ADAS). The processor is also suitable for smarter edge and IoT devices which also require the use of high-performance cameras to perform tasks such as semantic segmentation and object detection in real-time. The Hailo-8 can perform these at full resolution, yet consuming only a few Watts. The processor’s heat dissipation removes the need for active cooling systems in the automotive industry, claims Hailo.

Hailo is an AI-focused Israel-based chipmaker. The company has developed a specialised deep learning processor that delivers the performance of a data centre-class computer to edge devices. Hailo’s AI processor is the product of a rethinking of traditional computer architecture, enabling smart devices to perform sophisticated deep learning tasks such as object detection and segmentation in real-time, with minimal power consumption, size, and cost. The deep learning processor is designed to fit into a multitude of smart machines and devices, including autonomous vehicles, smart cameras, smartphones, drones, AR/VR platforms, and wearables. The company was founded in 2017 by members of the Israel Defense Forces’ elite intelligence unit.

https://www.hailo.ai/

> Read More

Senseeker claims DROIC is world’s first eight micron pitch, dual-band version

Arm adds IP and processors to its to AI offering

Low-power DDR5 DRAM achieves data speeds for AI and 5G

Hailo-8 has processor architecture specifically for deep learning

About Smart Cities