cevainc

Configurable sensor fusion software platform adds high-precision sensing to wearables

September 28, 2020 By Redding Traiger Leave a Comment

CEVA, Inc. introduced the Hillcrest Labs MotionEngine Hear, a sensor, and processor agnostic embedded software solution for hearable devices.

System-on-Chip (SoC) vendors, OEMs and ODMs can utilize MotionEngine Hear to deliver a frictionless user interface, gesture control, activity tracking and spatial audio for a range of smart personal audio devices, including true wireless stereo (TWS) earbuds, audio headsets, hearing aids, and AR glasses. The software is offered for the CEVA-BX1 and CEVA-BX2 DSPs, Arm Cortex-M series and RISC-V cores that are incorporated in a broad range of Bluetooth SoCs and MCUs targeted for hearable devices. MotionEngine Hear supports a broad range of commercial accelerometers, gyroscopes and proximity sensors from the leading sensor suppliers including STMicroelectronics, Bosch-Sensortec, TDK InvenSense, and others.

MotionEngine Hear offers a large portfolio of sensor-based user interface, gesture and activity tracking features, including tap, in-ear detection, step counter, walk/run/still activity classifiers and head-tracking to enable spatial audio applications. The software has been extensively stress-tested and was benchmarked against a leading OEM’s TWS earbuds, outperforming the incumbent solution for key features including tap and double-tap accuracy and in-ear detection.

The demand for TWS earbuds and other hearable devices continues to soar, with WiFore Wireless Consulting forecasting that more than 630 million devices are expected to ship by 2025. In Qualcomm’s recently published “State of Play Report 2020”, context awareness is identified as a key area of interest by consumers for wireless headphones and earbuds, enabling longer battery life and a better user experience through automatic adaptation to the current user activity or device state. The MotionEngine Hear software delivers sensor-based features that are essential to these context-aware devices, while requiring sub-milliamp level power draw for the whole system.

MotionEngine Hear is offered in two versions, both of which are flexible to meet customer requirements:

MotionEngine Hear Core
- Enables context awareness with activity classification, including walking, running and still
- Offers improved UI control with tap and double tap
- Controls playback and saves power with accelerometer-only in-ear detection
- Tracks fitness activity with step counter, activity detection, and distance and calorie estimates
- Sensor requirement: accelerometer-only

MotionEngine Hear Premium – includes all the features of Core version, in addition to:
- Essential support for spatial audio with highly accurate 3D head-tracking
- Advanced in-ear detection using accelerometer and/or proximity detection
- Sensor requirement: accelerometer, gyroscope and proximity sensor

MotionEngine Hear is available for licensing today.

Multistream decoder now supported and approved on audio DSP

July 28, 2020 By Aimee Kalnoskas Leave a Comment

CEVA, Inc. announced support for Dolby MS12 Multistream Decoder for the CEVA-BX2 audio DSP.

As smart TVs, over-the-top (OTT) content services and set-top-boxes evolve into multipurpose digital media receivers, the content is derived from numerous sources, utilizing a variety of audio codecs. Dolby MS12 is a comprehensive and cost-effective solution that reduces the complexity of integrating multiple audio technologies into these devices. It supports decoding of premium audio content including Dolby Atmos, which is used by many content service providers like Netflix, and Dolby AC-4 which is part of ATSC 3.0 and other next-gen audio standards around the globe.

CEVA’s optimized and approved implementation of Dolby MS12 on the CEVA-BX2 DSP will allow System-on-Chip (SoC) designers and device manufacturers the ability to incorporate Dolby technologies, including Dolby Atmos and Dolby AC-4 into their products. The powerful CEVA-BX2 DSP can also be used to run additional value-add software in the product, such as a multi-microphone voice user interface, supported by the ClearVox noise reduction and WhisPro speech recognition software packages.

CEVA-BX2 is a modern, high-performance audio/voice and AI capable DSP designed for intensive audio applications such as multichannel audio decode, far-field noise reduction, and Artificial Intelligence-based speech recognition and sound analytics. Targeted for high-performance audio devices such as Smart TVs and OTT/STB media devices, smart speakers, soundbars, and car infotainment systems, the CEVA-BX2 uses quad 32X32-bit MACs and octal 16X16-bit MACs, with enhanced capability for supporting 16×8-bit and 8×8-bit MAC operations. Its 11-stage pipeline and 5-way VLIW micro-architecture, support parallel processing with dual scalar compute engines, load/store and program control that reaches a speed of 2 GHz at a TSMC 7nm process node.

The CEVA-BX2 Instruction Set Architecture (ISA) incorporates support for Single Instruction Multiple Data (SIMD) as well as optional floating-point units for high accuracy algorithms. The CEVA-BX2 is accompanied by a comprehensive software development toolchain, including an advanced LLVM compiler, eclipse-based debugger, DSP and neural network compute libraries, neural network frameworks support and Real Time Operating Systems (RTOS). F

DSP architecture targets 5G Intelligent Radio Access Networks (RAN) and enterprise access points

March 4, 2020 By Aimee Kalnoskas Leave a Comment

CEVA, Inc. announced its powerful DSP architecture, the Gen4 CEVA-XC. This new architecture delivers unmatched performance for the most complex parallel processing workloads required for 5G endpoints and Radio Access Networks (RAN), enterprise access points and other multigigabit low latency applications.

The Gen4 CEVA-XC unifies the principles of scalar and vector processing in a powerful architecture, enabling two-times 8-way VLIW and up to an unprecedented 14,000 bits of data-level parallelism. It incorporates an advanced, deep pipeline architecture enabling operating speeds of 1.8 GHz at a 7nm process node using a unique physical design architecture for a fully synthesizable design flow, and an innovative multithreading design. This allows the processors to be dynamically reconfigured as either a wide SIMD machine or divided into smaller simultaneous SIMD threads. The Gen4 CEVA-XC architecture also features a novel memory subsystem, using 2048-bit memory bandwidth, with coherent, tightly-coupled memory to support efficient simultaneous multithreading and memory access.

The first processor based on the Gen4 CEVA-XC architecture is the multicore CEVA-XC16, the fastest DSP ever made. It is targeted for the rapid deployment of different form factors of 5G RAN architectures including Open RAN (O-RAN), Baseband Unit (BBU) aggregation as well as Wi-Fi and 5G enterprise access points. The CEVA-XC16 is also applicable to massive signal processing and AI workloads associated with base station operation.

The CEVA-XC16 has been specifically architected with the latest 3GPP release specifications in mind, building on the company’s extensive experience partnering with leading wireless infrastructure vendors for their cellular infrastructure ASICs. The previous generation CEVA-XC4500 and CEVA-XC12 DSPs are powering 4G and 5G cellular networks today, and the new CEVA-XC16 is already in design with a leading wireless vendor for their next-generation 5G ASIC.

The CEVA-XC16 offers high parallelism of up to 1,600 Giga Operations Per Second (GOPS) that can be reconfigured as two separate parallel threads. These can run simultaneously, sharing their L1 Data memory with cache coherency, which directly improves latency and performance efficiency for PHY control processing, without the need for an additional CPU. These new concepts boost the performance per square millimeter by 50% compared to a single-core/single-thread architecture when massive numbers of users are connected in a crowded area. This amounts to 35% die area savings for a large cluster of cores, as is typical for custom 5G base station silicon.

The CEVA-XC16 is available for general licensing starting in Q2 2020. For more information, visit https://www.ceva-dsp.com/product/ceva-xc16/.

Software handles low-power motion-based gesture control/3D motion tracking/pointing for consumer handhelds

December 22, 2019 By Aimee Kalnoskas Leave a Comment

CEVA, Inc. introduced a new generation of its Hillcrest Labs sensor fusion product family, with the launch of the MotionEngine Air software. This production-ready solution delivers low power, motion-based gesture control, 3D motion tracking and pointing for consumer handheld devices in high volume markets, among which are smartphone and PC stylus pens, smart TV and over-the-top (OTT) remote controls, game controllers, AR and VR controllers, and PC peripherals.

The global market for Bluetooth and other wireless handheld controllers is expanding rapidly with more than 500 million RF devices expected to ship in 2022. New advancements in low power inertial sensors and Bluetooth Low Energy along with the MotionEngine Air sensor fusion software yields sub-milliamp level power draw for the whole system. This enables the proliferation of precise, interactive and intuitive motion-control for always-on and always-aware user experiences.

MotionEngine Air software is a highly flexible, low power and small memory footprint solution that can run on a variety of processors, including Arm Cortex-M, RISC-V and CEVA-BX and CEVA-TeakLite families of DSPs. It can be delivered in multiple configurations – including a full-featured solution that requires an accelerometer plus gyroscope (IMU) and a gesture and motion event-based solution that requires only an accelerometer.

Software development kit focuses on Simultaneous Localization and Mapping apps

May 23, 2019 By Aimee Kalnoskas Leave a Comment

CEVA, Inc. announced the availability of its CEVA-SLAM software development kit, aimed at streamlining the development of Simultaneous Localization and Mapping (SLAM) enabled products, including mobile devices, AR/VR headsets, robots, autonomous vehicles and other camera-based devices. Available for the CEVA-XM family of intelligent vision DSPs and the NeuPro family of AI processors, CEVA-SLAM incorporates the hardware, software and interfaces required to significantly lower the entry barrier for companies looking to integrate efficient SLAM implementations into low-power embedded systems.

The CEVA-SLAM SDK accelerates SLAM based application development by incorporating the hardware, software and interfaces required to enable an efficient SLAM implementation into any embedded system. The SDK includes a detailed interface from a CPU to offload the heavy lifting SLAM blocks to the CEVA-XM DSP. These building blocks utilize the DSP efficiency to support both fixed point and floating point math and extend the device’s battery life.

The SDK building blocks include capabilities for image processing (including Feature Detection, Feature Descriptors, Feature Matching), Linear Algebra (including Matrix Manipulation, Linear Equation Solving), Fast Sparse Equation solving for Bundle Adjustment and more. Illustrating the low power capabilities of the CEVA-SLAM SDK, running a full SLAM tracking module on the CEVA-XM6 DSP at 60 frames per second consumes only 86mW. When deployed with a CEVA-XM DSPs or a NeuPro AI processor, customers can address a broad range of use cases and applications requiring SLAM, such as visual positioning, along with classical and Neural Network workloads for imaging and vision, all in a unified hardware platform that is easy to program.

The CEVA-SLAM SDK is available for licensing today, exclusively in conjunction with the CEVA-XM intelligent vision DSPs and NeuPro AI processors.

NB-IoT and GNSS SoC delivers low power, low cost for cellular IoT

February 20, 2019 By Aimee Kalnoskas Leave a Comment

CEVA, Inc. announced the introduction of Nurlink’s NK6010 3GPP Rel.14 eNB-IoT System-on-Chip (SoC) powered by the CEVA-Dragonfly NB2 IP solution.

NK6010 is a highly cost and power efficient NB-IoT SoC designed specifically to enable narrowband connectivity in massive IoT devices such as smart meters, wearables, asset trackers and industrial sensors. The SoC, built around the CEVA-Dragonfly NB2 solution, incorporates RF front-end, RF transceiver, cellular baseband, power management unit and application processor, all highly-integrated to minimize the size and cost of the solution. It supports all NB-IoT frequency bands and major global carriers, ensuring smooth and rapid certification of devices on any NB-IoT commercial network around the world. The SoC also includes an extremely low-power multi-GNSS subsystem, supporting GPS/Beidou/Galileo/GLONASS global navigation systems, to ensure highly-accurate device tracking and locating, worldwide.

Michael Boukaya, vice president and general manager of the wireless business unit at CEVA, stated: “NB-IoT has reached critical mass, with more than 60 operators around the world already supporting the standard and dozens more launching coverage imminently. Now the drive towards ultra-low cost NB-IoT chipsets and modules has begun and Nurlink, powered by our CEVA-Dragonfly NB2 IP solution, is one of the early entrants into this fast growing space. We applaud their efforts to reach the market so quickly and look forward to monitoring their success.”

The CEVA-Dragonfly NB2 IP solution is a modular technology, composed of the CEVA-X1 IoT processor, an optimized RF Transceiver, baseband, and a protocol stack to offer a complete Release 14 Cat-NB2 modem IP solution that significantly reduces time-to-market and lowers entry barriers. It is a fully software-configurable solution and can be extended with multi-constellation GNSS and sensor fusion functionality. The IP includes a reference silicon of the complete modem design, including an embedded CMOS RF transceiver and PA, an advanced digital front-end, physical layer firmware, and a protocol stack (MAC, RLC, PDCP, RRC, and NAS).

Hybrid DSP/controller architecture offers high-level programming for IoT devices

January 4, 2019 By Aimee Kalnoskas Leave a Comment

CEVA, Inc. announced today CEVA-BX, its new all-purpose, hybrid DSP / Controller architecture to address new algorithms of digital signal processing in voice, video, communication, sensing and digital signal control applications. Offering general purpose DSP capabilities required for motor control and electrification, the CEVA-BX architecture extends CEVA’s market reach into the burgeoning automotive and industrial markets currently underserved by legacy DSPs or MPU/MCUs with low performance DSP co-processing.

CEVA-BX offers a new breed of DSP architecture, combining the inherent low power requirements of DSP kernels with the high-level programming and compact code size requirements of a large control code base. Using an 11-stage pipeline and 5-way VLIW micro-architecture, it offers parallel processing with dual scalar compute engines, load/store and program control that reaches a speed of 2 GHz at TSMC 7nm process node using common standard cells and memory compilers. The CEVA-BX Instruction Set Architecture (ISA) incorporates support for Single Instruction Multiple Data (SIMD) widely used in neural network inference, noise reduction and echo cancellation, as well as half, single and double precision floating point units for high accuracy sensor fusion and positioning algorithms.

Mike Demler, Senior Analyst at The Linley Group commented: “Consumer, automotive, industrial and healthcare devices are increasingly integrating multiple sensors, such as cameras, microphones, environmental and motion detectors, which produce data that must be fused, interpreted, and processed on-device before being sent via a wireless link to the cloud. Processing these heavy-duty signal-processing workloads in edge devices requires an efficient combination of control and DSP capabilities. The CEVA-BX eliminates the need for separate CPUs and DSP coprocessors, employing a hybrid architecture that delivers excellent all-round performance for smart devices.”

CEVA-BX employs key architecture principles of advanced micro-processor architectures such as a large orthogonal general purpose register set for maximum C compiler efficiency, innovative Branch Target Buffer (BTB) for minimizing branch overhead, hardware loop buffer for reduced power consumption of code loops, fully cached memory subsystem, and native support for all standard C types. Its CoreMark/MHz score of 4.5 reflects the superior control capabilities of the architecture. CEVA-BX customers are able to add proprietary ISA into the architecture using the CEVA-Xtend, to accelerate proprietary algorithms and take advantage of CEVA’s automatic Queue and Buffer management mechanisms to integrate co-processors and create a cluster of CEVA-BX cores.

The CEVA-BX is initially offered in two configurations – the CEVA-BX1 with single 32X32-bit MAC and quad 16X16-bit MACs and the CEVA-BX2 with quad 32X32-bit MACs and octal 16X16-bit MACs, that are also capable of supporting 16×8-bit and 8×8-bit MAC operations. The CEVA-BX2 addresses intensive workloads such as 5G PHY control, multi-microphone beamforming and neural networks for speech recognition, with up to 16 GMACs per second. The CEVA-BX1 serves low to mid-range DSP workloads, such as cellular IoT, protocol stacks, and always-on sensor fusion, with up to 8 GMACs per second. Security is addressed using dedicated trusted execution modes to comply with the stringent safety standards.

The CEVA-BX cores are available now to lead customers and by end of Q1/2019 for general licensing.

BLE5 software integrated into SoCs for development of battery-free IoT device

December 7, 2018 By Aimee Kalnoskas Leave a Comment

CEVA, Inc. announced that Atmosic Technologies has integrated CEVA’s RivieraWaves Bluetooth 5 Low Energy (RW-BLE5) IP in its M2 and M3 Series IoT systems-on-chip (SoCs). The M2 and M3 SoCs target a diverse range of end markets for low power wireless applications, including wearables, personal and asset trackers, beacons, remotes, keyboards, mice, and more.

With its first products, Atmosic is tackling the real world battery-replacement challenge associated with installing and maintaining a plethora of IoT devices. To realize its vision, Atmosic developed a number of innovative RF CMOS technologies, including Lowest Power Radio, On-demand Wake-up, and Controlled Energy Harvesting.

The Atmosic M2 Series Bluetooth 5 SoC features Lowest Power Radio with On-demand Wake-up, radically enhancing battery life. The power consumption reduction is so substantial that it’s able to reach a technology inflection point where energy harvesting becomes a viable power source. The Atmosic M3 Series Bluetooth 5 SoC expands on the M2 with Controlled Energy Harvesting, which can provide forever battery life or even eliminate the need for battery power. The M2 and M3 Series will be demonstrated during the upcoming Consumer Electronics Show (CES) in Las Vegas from January 8-11, 2019.