High-voltage half-bridge driver NSD2622N from NOVOSENSE: A high-reliability, high-integration solution tailored for E-mode GaN
Trade news

High-voltage half-bridge driver NSD2622N from NOVOSENSE: A high-reliability, high-integration solution tailored for E-mode GaN

　　NOVOSENSE has launched NSD2622N, a high-voltage half-bridge driver IC specifically designed for enhancement-mode GaN (E-mode GaN). This chip integrates positive/negative voltage regulation circuits, supports bootstrap supply, and provides high dv/dt immunity and robust driving capability. It significantly simplifies GaN driver circuit design while enhancing system reliability and reducing overall costs.　　Application background　　In recent years, gallium nitride high-electron-mobility transistors (GaN HEMTs) are gaining increasingly widespread adoption in high-voltage, high-power applications, such as AI data center power supplies, microinverters, and on-board chargers (OBCs). With significant advantages of high switching frequency and low switching losses, GaN HEMTs enable substantially improved power density in power supply systems, noticeably optimized energy efficiency, and significantly reduced system costs.　　However, GaN devices still face challenges in real-world applications. For instance, E-mode GaN devices exhibit low turn-on thresholds. In high-voltage and high-power applications, particularly in hard-switching operation mode, poorly designed driver circuits can lead to false triggering due to crosstalk during high-frequency high-speed switching. Additionally, the complexity of compatible driver circuit designs raises the barrier to GaN device adoption.　　To accelerate widespread GaN adoption, leading GaN manufacturers at home and abroad have introduced some power ICs with integrated drivers, especially MOSFET-LIKE GaN power devices in Si-MOSFET-compatible packages, which somewhat reduce GaN driver circuit design complexity. However, driver-integrated GaN solutions have limitations: they struggle to meet customized design requirements and are unsuitable for applications adopting multi-device parallel or bidirectional switching topologies. Therefore, discrete GaN devices with dedicated drivers remain essential for many applications. To address the above-mentioned limitations, NOVOSENSE has developed NSD2622N – a driver IC tailored to E-mode GaN, aiming to deliver high-performance, high-reliability, and cost-competitive driving solutions for high-voltage and high-power GaN applications.　　Product features　　NSD2622N is a high-voltage half-bridge driver IC specifically designed for E-mode GaN. It integrates a voltage regulation circuit capable of generating a configurable stable positive voltage from 5V to 6.5V to ensure reliable GaN driving, as well as a charge pump circuit that produces a fixed -2.5V negative voltage for reliable GaN turn-off. By integrating both positive and negative voltage regulation circuits, the chip supports high-side output with bootstrap supply.　　NSD2622N leverages NOVOSENSE’s proven capacitive isolation technology. Its high-side driver withstands a voltage range of -700V to +700V and a minimum SW dv/dt immunity of 200V/ns. Meanwhile, low propagation delay and tight delay matching between high-side and low-side outputs make it a perfect match for the high-frequency, high-speed switching requirements of GaN devices. Additionally, NSD2622N delivers 2A (source) and -4A (sink) peak drive currents on both high-side and low-side outputs, meeting the requirements of high-speed GaN driving and multi-device parallel configurations. The IC also includes an integrated 5V LDO that can power circuits like digital isolators in applications requiring isolation.　　Key specifications of NSD2622N　　SW voltage range: -700V to 700V　　SW dv/dt immunity: > 200V/ns　　Wide supply voltage range: 5V-15V　　Adjustable positive output voltage range: 5V-6.5V　　Built-in negative output voltage: -2.5V　　Peak drive current: 2A (source) / 4A (sink)　　Minimum input pulse width (typical): 10ns　　Input-to-output propagation delay (typical): 38ns　　Pulse width distortion (typical): 5ns　　Rise time (1nF load, typical): 6.5ns　　Fall time (1nF load, typical): 6.5ns　　Built-in dead time (typical): 20ns　　Bootstrap supply for high-side output　　Integrated 5V LDO for digital isolator supply　　Undervoltage lockout (UVLO) and overtemperature protection　　Operating temperature range: -40°C to +125°CFunctional block diagram of NSD2622N　　Eliminating false triggering risks and providing more stable drive voltage　　Compared to conventional Si MOSFET driver solutions, the key challenge in E-mode GaN driver circuit design lies in providing appropriate, stable and reliable positive/negative bias voltages. This is because that E-mode GaN typically requires a 5V-6V turn-on voltage, while its threshold voltage is as low as 1V, or even lower at high temperatures, necessitating negative turn-off voltage to prevent false triggering. To address this challenge, two common drive solutions are used for E-mode GaN: resistive-capacitive (RC) voltage division drive and direct drive.　　1. RC voltage division drive　　This approach utilizes standard Si MOSFET driver ICs. As shown in the diagram, during turn-on, the parallel combination of Cc and Ra is connected with Rb in series, dividing the driver supply voltage (e.g., 10V) to provide a 6V gate drive voltage for the GaN device, with Dz1 clamping the positive voltage. During turn-off, Cc discharges to provide negative turn-off voltage for the GaN device, with Dz2 clamping the negative voltage.RC voltage division drive solution　　Although the RC voltage division circuit does not require sophisticated driver ICs, it introduces additional parasitic inductance due to a large number of components involved, which can impact GaN’s switching performance at high frequencies. Moreover, since the negative turn-off voltage relies on discharge from capacitor Cc, the negative turn-off voltage proves unreliable.　　As shown in the half-bridge demo board test waveforms, during the startup phase (T1 in the waveform), the absence of initial charge on Cc results in failure to establish negative voltage and thus zero-voltage turn-off; during the negative turn-off period following the driver’s signal transmission (T2), the negative voltage amplitude fluctuates with capacitor discharge; and during the prolonged turn-off period (T3), the capacitor cannot sustain negative voltage, eventually discharging to zero. Consequently, RC voltage division circuits are generally limited to medium/low power applications with relatively lower reliability requirements, and are proved unsuitable for high-power systems.Waveform of E-mode GaN using RC voltage division drive circuit(CH2: Drive supply voltage; CH3: GaN gate-source voltage)　　2. Direct drive　　The direct drive solution requires selecting a driver IC with an appropriate undervoltage-lockout (UVLO) threshold, for example, NSI6602VD, which is specifically designed for E-mode GaN with a 4V UVLO threshold. When paired with an external positive/negative voltage regulation circuit, it can directly drive E-mode GaN devices. Below is a typical application circuit.NSI6602VD driver circuitPositive and negative voltage regulation circuits　　This direct drive solution can provide reliable negative turn-off voltage for GaN under all operating conditions, when the auxiliary power supply is functioning normally. As a result, this approach is widely adopted in various high-voltage, high-power GaN applications.　　The next-generation GaN driver NSD2622N from NOVOSENSE, integrates the positive/negative voltage regulation circuits directly into the chip. As shown in the half-bridge demo board test waveforms below, NSD2622N maintains consistent negative turn-off voltage amplitude and duration regardless of operating conditions. Specifically, during startup (T1 in the waveform), the negative voltage is established even before the driver sends signals; during GaN turn-off (T2), the negative voltage remains stable in amplitude; during extended periods without driver signals (T3), the negative voltage continues to stay reliably stable.Waveforms of E-mode GaN using NSD2622N driver circuit(CH2: Low-side GaN Vds, CH3: Low-side GaN Vgs)　　Simplified circuit design and reduced system costs　　NSD2622N can provide stable and reliable direct drive for GaN devices. More importantly, by integrating positive/negative voltage regulators, it significantly reduces external component count. By adopting the bootstrap supply architecture, NSD2622N greatly simplifies driver power circuit design and lowers overall system costs.　　Taking a 3kW power supply unit (PSU) as an example, assuming both phases of the interleaved TTP PFC and full-bridge LLC use GaN devices, a complexity comparison between two direct-drive solutions is given below:　　When using the NSI6602VD driver solution, each half-bridge high-side driver requires an independent isolated power supply in conjunction with corresponding isolation and positive/negative voltage regulation circuits. This means complex auxiliary power supply design for isolation. Given the high power quality requirements of GaN driving and the fact that the main power paths of the PFC and LLC stages are typically placed on separate boards, a two-stage auxiliary power architecture is often necessary. In this configuration, the first stage typically employs a device with wide input voltage range like flyback converter, to generate regulated voltage rails. The second stage may use an open-loop full-bridge topology to provide isolated power and further regulate the power to generate the required positive and negative supply voltages for NSI6602VD. Below is a typical power architecture for such a driver solution.Typical power architecture for NSI6602VD driver solution　　The NSD2622N driver solution significantly simplifies auxiliary power design through its bootstrap supply capability. Below is a typical power architecture for this approach.Typical power architecture for NSD2622N driver solution　　A detailed comparison of bill-of-materials (BOM) for driver and power supply circuits between the above-mentioned two GaN direct-drive solutions is provided in the table below. It can be seen that the NSD2622N solution utilizing bootstrap supply, dramatically reduces total component count compared to the NSI6602VD’s isolated power supply approach, resulting in substantially lower system costs. Even in applications requiring isolated power supply, NSD2622N maintains its competitive edge - its integrated positive/negative voltage regulators enable a more simplified peripheral circuit relative to the NSI6602VD solution, leading to fewer components and lower system costs.BOM comparison between two GaN direct drive solutions　　Versatile GaN compatibility and flexible drive voltage adjustment　　The E-mode GaN driver IC NSD2622N from NOVOSENSE delivers not only superior performance but also broad compatibility across various GaN devices from different brands, of different types (including both voltage-mode and current-mode), and at different voltage ratings. For instance, the output voltage of NSD2622N can be set between 5V to 6.5V by adjusting feedback resistors. This enables selection of the most appropriate driving voltage for any GaN device by simply adjusting the feedback resistors to match specific GaN characteristics, allowing GaN devices from different brands to operate at their individual peak performance points.　　In addition, NSD2622N features a minimum dv/dt immunity of 200V/ns on the switching node (SW), enhancing the upper limit of GaN switching speed. The adoption of a more compact QFN package and the design of independent turn-on and turn-off output pins further reduce the driver loop parasitic inductance. The over-temperature protection ensures safer GaN applications.　　NOVOSENSE also offers single-channel GaN driver IC NSD2012N. Featuring 3mm*3mm QFN package and adjustable negative voltage capability, it can meet more personalized application requirements.
Key word：
Release time：2025-08-07 14:08 reading：456 Continue reading>>
Renesas Introduces 64-bit RZ/G3E MPU for High-Performance HMI Systems Requiring <span style='color:red'>AI</span> Acceleration and Edge Computing
Trade news

Renesas Introduces 64-bit RZ/G3E MPU for High-Performance HMI Systems Requiring AI Acceleration and Edge Computing

　　Renesas Electronics Corporation (TSE:6723), a premier supplier of advanced semiconductor solutions, announced the launch of its new 64-bit RZ/G3E microprocessor (MPU), a general-purpose device optimized for high-performance Human Machine Interface (HMI) applications. Combining a quad-core Arm® Cortex®-A55 running at up to 1.8GHz with a Neural Processing Unit (NPU), the RZ/G3E brings high-performance edge computing with AI inference for faster, more efficient local processing. With Full HD graphics support and high-speed connectivity, the MPU targets HMI systems for industrial and consumer segments including factory equipment, medical monitors, retail terminals and building automation.　　High-Performance Edge Computing and HMI Capabilities　　At the heart of the RZ/G3E is a quad-core Arm Cortex-A55, a Cortex-M33 core, and the Ethos™-U55 NPU for AI tasks. This architecture efficiently runs AI applications such as image classification, object recognition, voice recognition and anomaly detection while minimizing CPU load. Designed for HMI applications, it delivers smooth Full HD (1920x1080) video at 60fps on two independent displays, with output interfaces including LVDS (dual-link), MIPI-DSI, and parallel RGB. A MIPI-CSI camera interface is also available for video input and sensing applications.　　“The RZ/G3E builds on the proven performance of the RZ/G series with the addition of an NPU to support AI processing,” said Daryl Khoo, Vice President of Embedded Processing at Renesas. “By using the same Ethos-U55 NPU as our recently announced RA8P1 microcontroller, we’re expanding our AI embedded processor portfolio and offering a scalable path forward for AI development. These advancements address the demands of next-generation HMI applications across vision, voice and real-time analytics with powerful AI capabilities.”　　The RZ/G3E is equipped with a range of high-speed communication interfaces essential for edge devices. These include PCI Express 3.0 (2 lanes) for up to 8Gbps, USB 3.2 Gen2 for fast 10Gbps data transfer, and dual-channel Gigabit Ethernet for seamless connectivity with cloud services, storage, and 5G modules.　　Low-Power Standby with Fast Linux Resume　　Starting with the third-generation RZ/G3S, the RZ/G series includes advanced power management features to significantly reduce standby power. The RZ/G3E maintains sub-CPU operation and peripheral functions while achieving low power consumption around 50mW and around 1mW in deep standby mode. It supports DDR self-refresh mode to retain memory data, enabling quick wake-up from deep standby for running Linux applications.　　Comprehensive Linux Software Support　　Renesas continues to offer the Verified Linux Package (VLP) based on the reliable Civil Infrastructure Platform, with over 10 years of maintenance support. For users requiring the latest versions, Renesas provides Linux BSP Plus, including support for the latest LTS Linux kernel and Yocto. Ubuntu by Canonical and Debian open-source OS are also available for server or desktop Linux environments.　　Key Features of RZ/G3E　　CPU: Quad-core Cortex-A55 (up to 1.8GHz), Cortex-M33　　NPU: Ethos-U55 (512 GOPS)　　HMI: Dual Full HD output, MIPI-DSI / Dual-link LVDS / Parallel RGB, 3D graphics, H.264/H.265 codec　　Memory Interface: 32-bit LPDDR4/LPDDR4X with ECC　　Connectivity for 5G Communication: PCIe 3.0 (2 lanes), USB 3.2 Gen2, USB 2.0 x2, Gigabit Ethernet x2, CAN-FD　　Operating Temperature: -40°C to 125°C　　Package Options: 15mm square 529-pin FCBGA, 21mm square 625-pin FCBGA　　Product Longevity: 15-year supply under Product Longevity Program (PLP)　　System-on-Module Solutions from Renesas and Ecosystem Partners　　Renesas has also introduced system-on-module (SoM) solutions featuring the RZ/G3E. A broad range of SoM solutions will be available from Renesas’ ecosystem partners such as a SMARC module from Tria, an OSM (Size-M) from ARIES Embedded, and an OSM (Size-L) from MXT.　　Winning Combinations　　Renesas combined the RZ/G3E with other compatible devices to develop Full HD Dual-Display HMI Platform and Digital Otoscope solutions. These Winning Combinations are technically vetted system architectures from mutually compatible devices that work together seamlessly to bring an optimized, low-risk design for faster time to market. Renesas offers more than 400 Winning Combinations with a wide range of products from the Renesas portfolio to enable customers to speed up the design process and bring their products to market more quickly. They can be found at renesas.com/win.　　Availability　　The RZ/G3E is available today, along with the Evaluation Board Kit. The kit includes a SMARC v2.1.1 module board and a carrier board.If you want to buy related products, you can contact AMEYA360's customer service.
Key word：
Release time：2025-07-30 15:09 reading：564 Continue reading>>
SIMCom Introduces SIM8668 & SIM8666 for Low-Power <span style='color:red'>AI</span> on the Edge
Trade news

SIMCom Introduces SIM8668 & SIM8666 for Low-Power AI on the Edge

　　AI has clearly become a key focusacross industries at MWC Shanghai 2025. While high-level and advanced-levelAI computing modules are alreadyadopted in applications like video conferencing, AR/VR, edge computing, and industrial PDAs, the growing diversity of edge applications has created strong demand for entry-level AI solutions that prioritize low power consumption, cost-efficiency, and fast deployment.　　To address the trends, and following the recent launches of its SIM9850 (high-level AI computing module) and SIM9630L-W (advanced-level AI module), SIMCom — a global leader in IoT communication solutions — has introduced two new entry-level AI computing modules: SIM8668 and SIM8666, designed to bring intelligent capabilities to lightweight, energy-efficient edge devices.　　Powered by the RK3568 and RK3566 platforms, both SIM8668 and SIM8666 deliver 1 TOPS of NPU performance and come equipped with a wide range of interfaces—including LVDS, MIPI-DSI, HDMI 2.0, CSI, USB, PCIe, UART, SPI, I2C, and more. These interfaces allow easy connection to cameras, displays, audio, and sensors, enabling rich data collection and smooth human-machine interaction. The integrated NPU supports INT8/INT16 hybrid operations and is compatible with popular AI frameworks such as TensorFlow, PyTorch, MXNet, and Caffe, offering flexibility for deploying a variety of deep learning models.　　These capabilities make SIM8668 and SIM8666 ideal for edge AI applications like like face recognition, license plate detection, seatbelt monitoring, people counting, helmet detection, e-bike identification, and safety alerts—all while maintaining low power consumption and cost efficiency for smart, connected devices.　　Specifically, the SIM8668 features a 2.0GHz CPU, ARM Mali-G52 GPU, and an 8M ISP with HDR support. It also supports dual independent displays, suitable for advanced multimedia and multitasking needs. The SIM8666, on the other hand, is designed for cost-sensitive AI applications with a 1.8GHz CPU, the same Mali-G52 GPU, and support for single or mirrored dual display output. It also includes a touchscreen interface (I2C TP), offering enhanced flexibility for HMI (Human Machine Interface) scenarios in both consumer and industrial devices.　　With their compact design and built-in connectivity, SIM8668 and SIM8666 help customers accelerate product development and reduce time-to-market.These modules are well suited for a variety of low-power edge AI applications, including home automation, self-service kiosks, digital signage, audio and video streaming devices, dashcams, and HMI systems.　　By launching the SIM8668 and SIM8666 during MWC Shanghai, SIMCom demonstrates its continued commitment to expanding the accessibility of AI—offering practical, scalable solutions to enable smarter edge devices across a wider range of industries.
Key word：
Release time：2025-07-21 14:49 reading：455 Continue reading>>
Fibocom Debuts 5G Module FG390 Powered by MediaTek T930 Platform, Accelerating FWA Innovation with the Convergence of 5G-A and <span style='color:red'>AI</span>
Trade news

Fibocom Debuts 5G Module FG390 Powered by MediaTek T930 Platform, Accelerating FWA Innovation with the Convergence of 5G-A and AI

　　Fibocom, a global leading provider of wireless communication modules and AI solutions, announces the launch of its 5G module FG390, developed on the advanced MediaTek T930 platform. Designed specifically for mobile broadband (MBB) terminal products focused on 5G Fixed Wireless Access (FWA), the FG390 series seeks to boost FWA industry growth across diverse applications such as CPEs, ODUs, mobile hotspot devices, enterprise gateways, and industrial gateways.　　FG390 is a highly integrated, high-performance 5G module built on MediaTek’s advanced T930 chipset, featuring cutting-edge 4nm process technology. It incorporates the MediaTek M90 5G modem alongside a quad-core ARM Cortex-A55 CPU, delivering robust functionality and full compliance with 3GPP Release 18 standards. Supporting downlink 6-carrier aggregation (6CC CA) and uplink 5-layer 3Tx transmission within the 5G NR Sub-6GHz spectrum, the FG390 achieves peak standalone (SA) downlink speeds of up to 10 Gbps and uplink speeds reaching 2.8 Gbps, providing an outstanding high-speed 5G experience. Furthermore, with 200MHz bandwidth and 8Rx technology, the module significantly enhances spectrum efficiency about 40% at cell edges, greatly extending signal coverage. Paired with a dedicated NPU chip, the FG390 powers AI-enabled gateway devices to offer advanced, intelligent network interaction capabilities.　　Amid the swift convergence of 5G-A and AI technologies, the FG390 series harnesses cutting-edge specifications, innovative features, and a comprehensive suite of peripherals to drive digital transformation and continuous innovation across both residential and enterprise applications. This breakthrough empowers telecom operators and the broader market to enhance investment efficiency and accelerate returns in the communications terminal sector.　　Leveraged by the MediaTek T930 platform, the FG390 seamlessly integrates robust 5G Release 18 protocol capabilities with exceptional cellular performance and AI-driven intelligence, setting a new benchmark for the next generation of mobile broadband terminals. Enhanced by a dedicated NPU for AI acceleration, this module empowers transformative applications across smart offices, smart homes, and smart cities. Fibocom remains dedicated to deepening the collaboration with MediaTek to drive continuous innovation in 5G technologies, products, and ecosystem development.
Key word：
Release time：2025-07-17 16:21 reading：495 Continue reading>>
Renesas Strengthens Power Leadership with New GaN FETs for High-Density Power Conversion in <span style='color:red'>AI</span> Data Centers, Industrial and Charging Systems
Trade news

Renesas Strengthens Power Leadership with New GaN FETs for High-Density Power Conversion in AI Data Centers, Industrial and Charging Systems

　　Renesas Electronics Corporation (TSE:6723), a premier supplier of advanced semiconductor solutions, introduced three new high-voltage 650V GaN FETs for AI data centers and server power supply systems including the new 800V HVDC architecture, E-mobility charging, UPS battery backup devices, battery energy storage and solar inverters. Designed for multi-kilowatt-class applications, these 4th-generation plus (Gen IV Plus) devices combine high-efficiency GaN technology with a silicon-compatible gate drive input, significantly reducing switching power loss while retaining the operating simplicity of silicon FETs. Offered in TOLT, TO-247 and TOLL package options, the devices give engineers the flexibility to customize their thermal management and board design for specific power architectures.　　The new TP65H030G4PRS, TP65H030G4PWS and TP65H030G4PQS devices leverage the robust SuperGaN® platform, a field-proven depletion mode (d-mode) normally-off architecture pioneered by Transphorm, which was acquired by Renesas in June 2024. Based on low-loss d-mode technology, the devices offer superior efficiency over silicon, silicon carbide (SiC), and other GaN offerings. Moreover, they minimize power loss with lower gate charge, output capacitance, crossover loss, and dynamic resistance impact, with a higher 4V threshold voltage, which is not achievable with today’s enhancement mode (e-mode) GaN devices.　　Built on a die that is 14 percent smaller than the previous Gen IV platform, the new Gen IV Plus products achieve a lower RDS(on) of 30 milliohms (mΩ), reducing on-resistance by 14 percent and delivering a 20 percent improvement in on-resistance output-capacitance-product figure of merit (FOM). The smaller die size reduces system costs and lowers output capacitance, which results in higher efficiency and power density. These advantages make the Gen IV Plus devices ideal for cost-conscious, thermally demanding applications where high performance, efficiency and small footprint are critical. They are fully compatible with existing designs for easy upgrades, while preserving existing engineering investments.　　Available in compact TOLT, TO-247 and TOLL packages, they provide one of the broadest packaging options to accommodate thermal performance and layout optimization for power systems ranging from 1kW to 10kW, and even higher with paralleling. The new surface-mount packages include bottom side (TOLL) and top-side (TOLT) thermal conduction paths for cooler case temperatures, allowing easier device paralleling when higher conduction currents are needed. Further, the commonly used TO-247 package provides customers with higher thermal capability to achieve higher power.　　“The rollout of Gen IV Plus GaN devices marks the first major new product milestone since Renesas’ acquisition of Transphorm last year,” said Primit Parikh, Vice President of the GaN Business Division at Renesas. “Future versions will combine the field-proven SuperGaN technology with our drivers and controllers to deliver complete power solutions. Whether used as standalone FETs or integrated into complete system solution designs with Renesas controllers or drivers, these devices will provide a clear path to designing products with higher power density, reduced footprint and better efficiency at a lower total system cost.”　　Unique d-mode Normally-off Design for Reliability and Easy Integration　　Like previous d-mode GaN products, the new Renesas devices use an integrated low-voltage silicon MOSFET – a unique configuration that achieves seamless normally-off operation while fully capturing the low loss, high efficiency switching benefits of the high- voltage GaN. As they use silicon FETs for the input stage, the SuperGaN FETs are easy to drive with standard off-the-shelf gate drivers rather than specialized drivers that are normally required for e-mode GaN. This compatibility simplifies design and lowers the barrier to GaN adaptation for system developers.　　GaN-based switching devices are quickly growing as key technologies for next-generation power semiconductors, fueled by demand from electric vehicles (EVs), inverters, AI data center servers, renewable energy, and industrial power conversion. Compared to SiC and silicon-based semiconductor switching devices, they provide superior efficiency, higher switching frequency and smaller footprints.　　Renesas is uniquely positioned in the GaN market with its comprehensive solutions, offering both high- and low-power GaN FETs, unlike many providers whose success in the field has been primarily limited to lower power devices. This diverse portfolio enables Renesas to serve a broader range of applications and customer needs. To date, Renesas has shipped over 20 million GaN devices for high- and low-power applications, representing more than 300 billion hours of field usage.
Key word：
Release time：2025-07-04 15:04 reading：546 Continue reading>>
Renesas Sets New MCU Performance Bar with 1-GHz RA8P1 Devices with <span style='color:red'>AI</span> Acceleration
Trade news

Renesas Sets New MCU Performance Bar with 1-GHz RA8P1 Devices with AI Acceleration

Unprecedented 7300+ CoreMarks1 with Dual Arm CPU coresTSMC 22ULL Process Delivers High Performance and Low Power ConsumptionEmbedded MRAM with Faster Write Speeds and Higher Endurance and RetentionDedicated Peripherals Optimized for Vision and Voice AI plus Real-Time AnalyticsNew AI Software Framework Eases Development and Enables Easy Migration with MPUsLeading-Edge Security Features Ensure Data Privacy　　Renesas Electronics Corporation (TSE:6723), a premier supplier of advanced semiconductor solutions, introduced the RA8P1 microcontroller (MCU) Group targeted at Artificial Intelligence (AI) and Machine Learning (ML) applications, as well as real-time analytics. The new MCUs establish a new performance level for MCUs by combining 1GHz Arm® Cortex®-M85 and 250MHz Cortex-M33 CPU cores with the Arm Ethos™-U55 Neural Processing Unit (NPU). This combination delivers the highest CPU performance of over 7300 CoreMarks and AI performance of 256 GOPS at 500 MHz.　　Designed for Edge/Endpoint AI　　The RA8P1 is optimized for edge and endpoint AI applications, using the Ethos-U55 NPU to offload the CPU for compute intensive operations in Convolutional and Recurrent Neural Networks (CNNs and RNNs) to deliver up to 256 MACs per cycle that yield 256 GOPS performance at 500 MHz. The new NPU supports most commonly used networks, including DS-CNN, ResNet, Mobilenet TinyYolo and more. Depending on the neural network used, the Ethos-U55 provides up to 35x more inferences per second than the Cortex-M85 processor on its own.　　Advanced Technology　　The RA8P1 MCUs are manufactured on the 22ULL (22nm ultra-low leakage) process from TSMC, enabling ultra-high performance with very low power consumption. This process also enables the use of embedded Magnetoresistive RAM (MRAM) in the new MCUs. MRAM offers faster write speeds along with higher endurance and retention compared with Flash.　　“There is explosive growth in demand for high-performance edge AIoT applications. We are thrilled to introduce what we believe are the best MCUs to address this trend,” said Daryl Khoo, Vice President of Embedded Processing Marketing Division at Renesas. “The RA8P1 devices showcase our technology and market expertise and highlight the strong partnerships we have built across the industry. Customers are eager to employ these new MCUs in multiple AI applications.”　　“The pace of innovation in the age of AI is faster than ever, and new edge use cases demand ever-improving performance and machine learning on-device,” said Paul Williamson, Senior Vice President and General Manager, IoT Line of Business at Arm. “By building on the advanced AI capabilities of the Arm compute platform, Renesas’ RA8P1 MCUs meet the demands of next generation voice and vision applications, helping to scale intelligent, context-aware AI experiences.”　　“It is gratifying to see Renesas harness the performance and reliability of TSMC 22ULL embedded MRAM technology to deliver outstanding results for its RA8P1 devices,” said Chien-Hsin Lee, Senior Director of Specialty Technology Business Development at TSMC. “As TSMC continues to advance our embedded non-volatile memory (eNVM) technologies, we look forward to strengthening our long-standing collaboration with Renesas to drive innovation in future groundbreaking devices.”　　Robust, Optimized Peripheral Set for AI　　Renesas has integrated dedicated peripherals, ample memory and advanced security to address Voice and Vision AI and Real-time Analytics applications. For vision AI, a 16-bit camera interface (CEU) is included that supports sensors up to 5 megapixels, enabling camera and demanding Vision AI applications. A separate MIPI CSI-2 interface offers a low pin-count interface with two lanes, each up to 720Mbps. In addition, multiple audio interfaces including I2S and PDM support microphone inputs for voice AI applications.　　The RA8P1 offers both on-chip and external memory options for efficient, low latency neural network processing. The MCU includes 2MB SRAM for storing intermediate activations or graphics framebuffers. 1MB of on-chip MRAM is also available for application code and storage of model weights or graphics assets. High-speed external memory interfaces are available for larger models. SIP options with 4 or 8 MB of external flash in a single package are also available for more demanding AI applications.　　New RUHMI Framework　　Along with the RA8P1 MCUs, Renesas has introduced RUHMI (Renesas Unified Heterogenous Model Integration), a comprehensive framework for MCUs and MPUs. RUHMI offers efficient AI deployment of the latest neural network models in a framework agnostic manner. It enables model optimization, quantization, graph compilation and conversion, and generates efficient source code. RUHMI provides native support for machine-learning AI frameworks such as TensorFlow Lite, Pytorch & ONNX. It also provides the necessary tools, APIs, code-generator, and runtime needed to deploy a pre-trained neural network, including ready-to-use application examples and models optimized for RA8P1. RUHMI is integrated with Renesas’s own e2Studio IDE to allow seamless AI development. This integration will facilitate a common development platform for MCUs and MPUs.　　Advanced Security Features　　The RA8P1 MCUs provide leading-edge security for critical applications. The new Renesas Security IP (RSIP-E50D) includes numerous cryptographic accelerators, including CHACHA20, Ed25519, NIST ECC curves up to 521 bits, enhanced RSA up to 4K, SHA2 and SHA3. In concert with Arm TrustZone®, this provides a comprehensive and fully integrated secure element-like functionality. The new MCUs also provides strong hardware Root-of-Trust and Secure Boot with First Stage Bootloader (FSBL) in immutable storage. XSPI interfaces with decryption-on-the-fly (DOTF) allow encrypted code images to be stored in external flash and decrypted on the fly as it is securely transferred to the MCU for execution.　　Ready to Use Solutions　　Renesas provides a wide range of easy-to-use tools and solutions for the RA8P1 MCUs, including the Flexible Software Package (FSP), evaluation kits and development tools. FreeRTOS and Azure RTOS are supported, as is Zephyr. Several Renesas software example projects and application notes are available to enable faster time to market. In addition, numerous partner solutions are available to support development with the RA8P1 MCUs, including a driver monitoring solution from Nota.AI and a traffic/pedestrian monitoring solution from Irida Labs. Other solutions can be found at the Renesas RA Partner Ecosystem Solutions Page.　　Key Features of the RA8P1 MCUs　　Processors: 1GHz Arm Cortex-M85, 500MHz Ethos-U55, 250 MHz Arm Cortex-M33 (Optional)　　Memory: 1MB/512KB On-chip MRAM, 4MB/8MB External Flash SIP Options, 2MB SRAM fully ECC protected, 32KB I/D caches per core　　Graphics Peripherals: Graphics LCD controller supporting resolutions up to WXGA (1280x800), parallel RGB and MIPI-DSI display interfaces, powerful 2D Drawing engine, parallel 16bit CEU and MIPI CSI-2 camera interfaces, 32bit external memory bus (SDRAM and CSC) interface　　Other Peripherals: Gigabit Ethernet and TSN Switch, XSPI (Octal SPI) with XIP and DOTF, SPI, I2C/I3C, SDHI, USBFS/HS, CAN-FD, PDM and SSI audio interfaces, 16bit ADC with S/H circuits, DAC, comparators, temperature sensor, timers　　Security: Advanced RSIP-E50D cryptographic engine, TrustZone, Immutable storage, secure boot, tamper resistance, DPA/SPA attack protection, secure debug, secure factory programming, Device Lifecycle management　　Packages: 224BGA, 289BGA
Key word：
Release time：2025-07-04 14:56 reading：557 Continue reading>>
ROHM Introduces a New MOSFET for <span style='color:red'>AI</span> Servers with Industry-Leading* SOA Performance and Low ON-Resistance
Trade news

ROHM Introduces a New MOSFET for AI Servers with Industry-Leading* SOA Performance and Low ON-Resistance

　　ROHM has released of a 100V power MOSFET - RY7P250BM - optimized for hot-swap circuits in 48V power systems used in AI servers and industrial power supplies requiring battery protection to the market.　　As AI technology rapidly advances, data centers are facing unprecedented processing demands and server power consumption continues to increase annually. In particular, the growing use of generative AI and high-performance GPUs has created a need to simultaneously improve power efficiency while supporting higher currents. To address these challenges, the industry is shifting from 12V systems to more efficient 48V power architectures. Furthermore, in hot-swap circuits used to safely replace modules while servers remain powered on, MOSFETs are required that offer both wide SOA (Safe Operating Area) and low ON-resistance to protect against inrush current and overloads.　　The RY7P250BM delivers these critical characteristics in a compact 8080-size package, helping to reduce power loss and cooling requirements in data centers while improving overall server reliability and energy efficiency. As the demand for 8080-size MOSFETs grows, this new product provides a drop-in replacement for existing designs. Notably, the RY7P250BM achieves wide SOA (VDS=48V, Pw=1ms/10ms) ideal for hot-swap operation. Power loss and heat generation are also minimized with an industry-leading low ON-resistance of 1.86mΩ (VGS=10V, ID=50A, Tj=25°C), approximately 18% lower than the typical 2.28mΩ of existing wide SOA 100V MOSFETs in the same size.　　Wide SOA tolerance is essential in hot-swap circuits, especially those in AI servers that experience large inrush currents. The RY7P250BM meets this demand, achieving 16A at 10ms and 50A at 1ms, enabling support for high-load conditions conventional MOSFETs struggle to handle.　　ROHM’s new product has also been certified as a recommended component by leading global cloud platform provider, where it is expected to gain widespread adoption in next-generation AI servers. Especially in server applications where reliability and energy efficiency are mission-critical, the combination of wide SOA and low RDS(on) has been highly evaluated for cloud infrastructure.　　Going forward, ROHM will continue to expand its lineup of 48V-compatible power solutions for servers and industrial equipment, contributing to the development of sustainable ICT infrastructure and greater energy savings through high-efficiency, high-reliability products.　　Application Examples　　• 48V AI server systems and power supply hot-swap circuits in data centers　　• 48V industrial equipment power systems (i.e. forklifts, power tools, robots, fan motors)　　• Battery-powered industrial equipment such as AGVs (Automated Guided Vehicles)　　• UPS and emergency power systems (battery backup units)　　Online Sales InformationSales Launch Date: May 2025　　Pricing: $5.50/unit (samples, excluding tax)　　Online Distributors: DigiKey™, Mouser™ and Farnell™　　The products will be offered at other online distributors as they become available.　　Applicable Part No: RY7P250BM　　EcoMOS™ BrandEcoMOS™ is ROHM's brand of silicon MOSFETs designed for energy-efficient applications in the power device sector.　　Widely utilized in applications such as home appliances, industrial equipment, and automotive systems, EcoMOS™ provides a diverse lineup that enables product selection based on key parameters such as noise performance and switching characteristics to meet specific requirements.　　TerminologyHot-Swap Circuit　　A circuit that enables components to be inserted or removed while the system remains powered on.　　It typically consists of MOSFETs, protection elements, and connectors, and is responsible for suppressing inrush current and protecting against overcurrent conditions, ensuring stable operation of the system and connected components.　　Power MOSFET　　A MOSFET designed for power conversion and switching applications. N-channel MOSFETs are the dominant type, turning on when a positive voltage is applied to the gate relative to the source. They offer lower ON-resistance and higher efficiency than P-channel variants. Due to their low conduction loss and high-speed switching performance, power MOSFETs are commonly used in power supplies, motor drives, and inverter circuits.　　SOA (Safe Operating Area)　　The defined range of voltage and current in which a device can operate reliably without risk of failure. Operating outside this boundary may result in thermal runaway or permanent damage. SOA is especially critical in applications exposed to inrush currents or overcurrent conditions.　　Low ON-resistance (RDS(on))　　The resistance value between the Drain and Source of a MOSFET during operation. A smaller RDS(on) reduces power loss during operation.　　Inrush Current　　A sudden surge of current that momentarily exceeds the rated value when an electronic device is powered on. Proper control of this current reduces stress on power circuit components, helping to prevent device damage and stabilize the system.
Key word：
Release time：2025-07-03 14:52 reading：374 Continue reading>>
Redefining Smart Living: Fibocom FG390 with MediaTek T930 Brings <span style='color:red'>AI</span> to the Heart of Homes and SMBs
Trade news

Redefining Smart Living: Fibocom FG390 with MediaTek T930 Brings AI to the Heart of Homes and SMBs

　　As AI technology rapidly advances and smart devices proliferate, households and small to medium-sized businesses (SMBs) are seeking intelligent, secure, and efficient “digital housekeepers”. These AI-powered ecosystems must enable seamless device coordination, centralized data management, and real-time decision-making across scenarios like smart security, remote work, and digital infrastructure management.　　To address the growing demand, Fibocom, in collaboration with MediaTek, introduces the FG390, a next-generation 5G module powered by the MediaTek T930 platform. Combining superior cellular connectivity, integrated AI capabilities, and deep insight into smart home and enterprise networking, FG390is set to become a key enabler in building AI-driven home ecosystems and intelligent control hubs. The module helps bridge data silos and optimize operational efficiency amid ongoing digital transformation.　　Exceptional Cellular Performance for Enhanced 5GExperience　　FG390 is powered by MediaTek’s advanced T930 platform, built on a 4nm process and integrating the MediaTek M90 5G modem with a quad-core ArmCortex-A55 CPU. Delivering exceptional cellular performance, it supports6-carrier downlink aggregation (6CC CA) and 5-layer 3Tx uplink over Sub-6GHz 5GNR, reaching peak speeds of 10 Gbps downlink and 2.8 Gbps uplink for ultra-fast, low-latency connectivity. Ideal for bandwidth-intensive applications such as multi-stream 8K video or immersive AR/VR experiences, FG390 also features 8Rx reception with 200MHz bandwidth to enhance spectral efficiency and ensure stable coverage, even at cell edges.　　Next-Gen Smart Home Hub with Advanced Personalization　　As 5G and AI technologies converge, the CPE (Customer Premises Equipment) is emerging as the central hub of the smart home. Powered by FG390, this hub gains advanced sensing capabilities, broad compatibility with smart devices—including support for the Matter protocol—and deeply integrated AI algorithms. Together, these features enable real-time adaptation to environmental changes and user behavior, delivering a more personalized, seamless, and comfortable smart living experience.　　AI Services Spark New Commercial Potential　　What truly differentiates the FG390 is its deep AI integration alongside exceptional connectivity. Equipped with a dedicated NPU, it functions as an intelligent in-home AI agent, delivering context-aware services to end users. Designed to support edge-cloud collaborative AI models, such as those from Open AI and DeepSeek, the FG390 empowers AI-enabled FWA (Fixed Wireless Access) solutions for both consumer and enterprise markets. Its intuitive AI SDK enables flexible service expansion for FWA users, while mobile operators can leverage it to unlock new AI-driven value-added services and monetization channels. Additionally, the module supports NAS integration for centralized data management and optimized AI resource allocation, enhancing productivity and setting the stage for next-generation smart applications.　　“We have a long history of working together with Fibocom to reach significant FWA milestones, and our collaboration on the next-generation T930 5G FWA platform will help to drive growth of the FWA ecosystem,” said Evan Su, General Manager of Wireless Communications at MediaTek. “With this partnership in mind, we are pushing forward by creating a higher focus on new products that are rich in features and innovative design, while delivering cutting-edge solutions and exceptional service to customers around the world.”　　“Designed to meet the evolving needs of the FWA market over the next 3–5 years, we’re pleased to collaborate with MediaTek to launch the FG390 5G FWA module,” Added Simon Tao, VP of MBB Product Management Dept, Head of MBB BU at Fibocom. “Powered by the full capabilities of the MediaTek T930 platform and 5G Release 18, FG390addresses the connectivity needs of large-scale smart home and SMB deployments with high gain, low latency, and multi-OS compatibility. Fibocom remains dedicated to advancing 5G eMBB modules with superior cellular and AI performance. Leveraging powerful NPUs, we’ll work closely with our partners to further enable AI-driven applications across smart homes, offices, and cities, fully embracing the AI era. Together with MediaTek, we’ll continue to innovate across products, technologies, and applications to shape a smarter future.”
Key word：
Release time：2025-06-30 15:02 reading：422 Continue reading>>
ROHM Builds the Future of <span style='color:red'>AI</span> with Optimized Solutions for NVIDIA 800V Architecture
Trade news

ROHM Builds the Future of AI with Optimized Solutions for NVIDIA 800V Architecture

　　As artificial intelligence continues to redefine the boundaries of computing, the infrastructure powering these advancements must evolve in parallel. A recognized leader in power semiconductor technology, ROHM is proud to be among the key silicon providers supporting NVIDIA’s new 800 V High Voltage Direct Current (HVDC) architecture. This marks a pivotal shift in data center design, enabling megawatt-scale AI factories that are more efficient, scalable, and sustainable.　　ROHM’s power device portfolio spans both silicon and wide bandgap technologies, including silicon carbide (SiC) and gallium nitride (GaN), offering a strategic path for data center designers. The company’s silicon MOSFETs are already widely adopted across automotive and industrial sectors, providing a cost-effective and reliable solution for today’s power conversion needs. These are ideal for applications where price, efficiency, and reliability must be balanced, making them a strong fit for transitional stages of AI infrastructure development.　　A standout example is the RY7P250BM, a 100V power MOSFET endorsed by major global cloud providers designed specifically for hot-swap circuits in 48V power systems—an essential component in AI servers. Key features include best-in-class SOA (Safe Operating Area) performance and ultra-low ON resistance (1.86 mΩ) in a compact 8080 package. These characteristics help reduce power loss and improve system reliability—crucial requirements in high-density, high-availability cloud platforms. As data centers transition from 12V to 48V and beyond, hot-swap capability becomes critical for maintaining uptime and protecting against inrush currents.　　Industrial-grade rectification with minimal losses is an area where ROHM’s SiC devices excel and align with NVIDIA’s plans to begin large-scale deployment of its 800V HVDC data center architecture to power 1 MW compute racks and beyond. At the heart of NVIDIA’s new infrastructure is the conversion of 13.8kV AC from the grid directly into 800V DC. The initiative is designed to address the inefficiencies of traditional 54V rack power systems, which are constrained by physical space, copper overload, and conversion losses.　　ROHM’s SiC MOSFETs deliver superior performance in high-voltage, high-power environments, offering higher efficiency through reduced switching and conduction losses, greater thermal stability for compact, high-density systems, and proven reliability in mission-critical applications. These characteristics align perfectly with the requirements of the NVIDIA 800 V HVDC architecture, which aims to reduce copper usage, minimize energy losses, and simplify power conversion across the data center.　　Complementing SiC, ROHM is advancing gallium nitride technologies under the EcoGaN™ brand. While SiC is best-suited for high voltage, high current applications, GaN offers exceptional performance in the 100V to 650V range, with superior breakdown field strength, low ON resistance, and ultra-fast switching. ROHM’s broad EcoGaNTM lineup includes 150V and 650V GaN HEMTs, gate drivers, and integrated power stage ICs. At the same time, proprietary Nano Pulse ControlTM technology further improves switching performance, reducing pulse widths to as low as 2ns. These innovations support the growing demand for smaller, more efficient power systems in AI data centers.　　Beyond discrete devices, ROHM offers a lineup of high-power SiC modules, including top-side cooling molded packages such as the HSDIP20, equipped with advanced 4th Gen SiC chips. These 1200V SiC modules are optimized for LLC topologies in AC-DC converters and primary-side applications in DC-DC converters. Engineered for high-efficiency, high-density power conversion, they are particularly well-suited for the centralized power systems envisioned in NVIDIA’s architecture. Their robust thermal performance and scalability make them ideal for 800 V busways and MW-scale rack configurations.　　The transition to an 800V HVDC infrastructure is a collaborative effort. ROHM is committed to working closely with industry leaders like NVIDIA as well as data center operators and power system designers to provide the foundational silicon technologies needed for this next generation of AI factories. Our expertise in power semiconductors, particularly in wide-bandgap materials like SiC and GaN, positions us as a key partner in developing solutions that are not only powerful but also contribute to a more sustainable and energy-efficient digital future.
Key word：
Release time：2025-06-13 16:52 reading：443 Continue reading>>
Fibocom Releases 5G <span style='color:red'>AI</span> Mobile Hotspot Solution, Unlocking Intelligent Future for Mobile Broadband Devices
Trade news

Fibocom Releases 5G AI Mobile Hotspot Solution, Unlocking Intelligent Future for Mobile Broadband Devices

　　As 5G and AI technologies continue to converge, demand is growing for stable, high-speed, and intelligent mobile networks across various scenarios—from business travel and outdoor operations to global connectivity. Fibocom’s latest 5G AI Mobile Hotspot solution redefines the mobile broadband experience with cutting-edge technology and forward-thinking design.　　Powered by Qualcomm’s advanced 4nm QCM4490 platform, the solution combines smartphone-grade ultra-low power consumption with precision circuit design. This results in a powerful yet energy-efficient platform that balances high performance with cost optimization.　　In terms of connectivity, the solution supports 3GPP Release 16 and NR 2CC 120MHz. It delivers a downlink speed of up to 2.3 Gbps in SA mode and 2.5 Gbps in NSA mode. Customers can flexibly configure the solution with either AX3600-based Wi-Fi 6E or BE5800-based Wi-Fi 7 options. It supports dual-band simultaneous (DBS) modes of 2.4GHz+5GHz or 2.4GHz+6GHz, as well as high-band simultaneous (HBS) mode of 5GHz+6GHz.　　Tailored for Mobile Hotspot applications, the solution runs an optimized Android 13 OS, significantly boosting system performance while reducing power consumption. With USB 3.1 support and a theoretical data transfer rate of up to 5 Gbps, it’s well-suited not only for 5G Mobile Hotspot devices but also for other mobile broadband terminals such as USB dongles.　　Crucially, the solution leverages the QCM4490’s heterogeneous computing architecture, featuring a robust 8-core CPU (2x Cortex-A78 @ 2.4GHz + 6x Cortex-A55 @ 2.0GHz) and integrated Adreno 613 GPU (@ 1010MHz). Compared to GPU-less solutions, this powerful combination enables efficient on-device AI processing, expanding the possibilities for more edge intelligence applications. Internal tests have demonstrated the successful deployment of large-scale open-source AI models such as Qwen-1.8 B-Chat.　　From business office to global travel these mobile broadband applied scenarios, Fibocom’s cost-effective 5G AI Mobile Hotspot solution—with optional Wi-Fi 7 support—paves the way for a new era of AI-enhanced mobile broadband.
Key word：
Release time：2025-06-06 15:38 reading：555 Continue reading>>

Turn to

/ 34

Popular categories
Semiconductors Circuit Protection Electromechanical Embedded Solutions Connectors, Interconnects Sensors, Transducers Optoelectronics Development Kits Test and Measurement Power Fans, Thermal Management Boxes, Enclosures, Racks Cables, Wires Passive Components Others
  • Week of hot material
  • Material in short supply seckilling
model brand Quote
TL431ACLPR Texas Instruments
CDZVT2R20B ROHM Semiconductor
MC33074DR2G onsemi
RB751G-40T2R ROHM Semiconductor
BD71847AMWV-E2 ROHM Semiconductor
model brand To snap up
STM32F429IGT6 STMicroelectronics
BP3621 ROHM Semiconductor
IPZ40N04S5L4R8ATMA1 Infineon Technologies
ESR03EZPJ151 ROHM Semiconductor
TPS63050YFFR Texas Instruments
BU33JA2MNVX-CTL ROHM Semiconductor
Hot labels
ROHM
IC
Averlogic
Intel
Samsung
IoT
AI
Sensor
Chip
Original authorized brand
More Licensed Brands>>
Information leaderboard
  • Week of ranking
  • Month ranking

About us

Qr code of ameya360 official account

Identify TWO-DIMENSIONAL code, you can pay attention to

AMEYA360 mall (www.ameya360.com) was launched in 2011. Now there are more than 3,500 high-quality suppliers, including 6 million product model data, and more than 1 million component stocks for purchase. Products cover MCU+ memory + power chip +IGBT+MOS tube + op amp + RF Bluetooth + sensor + resistor capacitance inductor + connector and other fields. main business of platform covers spot sales of electronic components, BOM distribution and product supporting materials, providing one-stop purchasing and sales services for our customers.

Please enter the verification code in the image below：

verification code