-
Nexperia has expanded its portfolio of 650 V industrial-grade high-power gallium nitride (GaN) FETs, introducing new devices designed to address the growing demands of high-performance power conversion applications. The expanded portfolio includes 35 mΩ, 50 mΩ, and 70 mΩ variants available in industry-standard TO-247-3, TO-247-4, TOLL, and TOLT package options.
The extended product range is intended to provide power engineers with greater flexibility in optimizing efficiency, thermal performance, and power density across a variety of applications, including data center and telecommunications power supplies, renewable energy systems, battery energy storage systems (BESS), industrial drives, and factory automation equipment.
The increasing adoption of artificial intelligence is driving a significant rise in power requirements for server racks, with power supply capacities growing from below 3 kW toward the 5 kW to 12 kW range. At the same time, renewable energy deployment and industrial electrification continue to increase demand for higher switching frequencies and improved power conversion efficiency. As a result, wide-bandgap semiconductor technologies such as GaN are playing an increasingly important role in enabling higher efficiency, reduced system size, and enhanced thermal management in next-generation power architectures.
Andrea Bricconi, Vice President and Head of the GaN Product Group at Nexperia, said the transition toward wide-bandgap power semiconductors is accelerating across industrial, energy, and AI infrastructure applications. He noted that as efficiency, power density, and thermal performance requirements continue to rise, the company remains focused on making GaN technology more accessible and scalable for engineers developing high-power systems. He added that the expansion of the company’s 650 V GaN portfolio represents an important step in that strategy and forms part of its broader roadmap in wide-bandgap technologies.
At the system level, the new GaN devices enable designers to exceed the performance limitations of conventional silicon-based solutions by supporting higher switching frequencies while reducing both switching and conduction losses. Depending on system topology and operating conditions, engineers can achieve higher power density, improved energy efficiency, reduced cooling requirements, and lower overall system costs. The higher switching frequencies also allow for smaller passive components and reduced magnetic component size, supporting more compact and scalable power conversion architectures.
According to Nexperia, in high-power LLC converter stages commonly used in 10 kW to 12 kW AI server power supplies, GaN devices can deliver approximately 0.8% to 1.2% higher efficiency at full load compared with silicon-based alternatives. In addition, power density at the converter stage level can increase by approximately 40% to 70%, enabled by higher switching frequencies and smaller passive components.
For a typical 1 kW high-voltage motor drive, the company states that GaN technology can reduce inverter power losses by approximately 20% to 25%, resulting in efficiency improvements of around 1% to 1.5%. These benefits can also support smaller thermal management systems and higher overall power density.
The devices are built on Nexperia’s proprietary GaN technology platform and combine fast switching performance, low switching losses, controlled dynamic behavior, and robust thermal characteristics. The availability of multiple industry-standard package options allows engineers to optimize both electrical and mechanical design parameters while facilitating integration into existing power conversion systems.
The 35 mΩ and 70 mΩ devices are available immediately in TOLL, TOLT, TO-247-3, and TO-247-4 packages. Additional 50 mΩ variants are scheduled for release during the third quarter of 2026.
Original – Nexperia
-
onsemi has introduced GaNEXUS™, a new gallium nitride (GaN) power portfolio designed to deliver higher efficiency, increased power density, and improved thermal performance across a broad range of applications, including AI data centers, industrial automation, robotics, and energy infrastructure.
The initial GaNEXUS portfolio includes GaN FETs spanning voltage ranges from 40 V to 650 V, as well as 650 V GaNEXUS Smart devices that integrate protection features to simplify system design and improve reliability. These products are currently available for sampling.
The launch expands onsemi’s intelligent power portfolio and complements the company’s existing silicon and EliteSiC technologies. By offering multiple semiconductor technologies within a unified portfolio, onsemi aims to provide customers with greater flexibility in optimizing efficiency, thermal performance, system size, and total cost across a wide range of power conversion architectures.
The new portfolio targets applications with growing power requirements, including AI data center power delivery, 48 V power systems, robotics, industrial automation equipment, and energy infrastructure. As AI infrastructure, electrification, and industrial automation continue to accelerate, designers face increasing challenges related to energy consumption, cooling requirements, and system footprint. According to onsemi, AI data centers alone are expected to account for up to 9% of U.S. electricity generation by 2030, while power and cooling can represent up to 40% of total data center operating expenses.
GaNEXUS technology addresses these challenges through faster switching speeds, lower switching losses, higher power density, and improved thermal performance compared with conventional silicon-based solutions. These characteristics enable reductions in the size of magnetic components and cooling systems while improving overall efficiency and responsiveness and lowering system costs in applications ranging from AI data center power delivery and electric vehicle charging to robotics and industrial power systems.
Antoine Jalabert, Vice President of the GaN Division at onsemi, stated that the GaNEXUS portfolio is enabling new approaches to power system design by providing engineers with greater flexibility to address constraints that have traditionally limited conventional power architectures.
When combined with onsemi’s Treo platform for integrated sensing, control, protection, and power management, GaNEXUS devices can be deployed as part of complete system-level power solutions. This approach is intended to simplify design complexity, accelerate development and qualification cycles, reduce thermal and cooling requirements, and optimize performance throughout the power delivery chain.
In low- and medium-voltage applications, including AI server 48 V intermediate bus converters (IBCs), battery backup units (BBUs), and motor drives, GaNEXUS technology enables approximately 30% to 60% smaller magnetic components, 1.5x to 2x higher power density, and efficiency improvements ranging from 0.5% to 2%, depending on system topology. Additional benefits include reduced switching losses, enhanced thermal performance, and improved control stability.
For higher-voltage applications such as AI power shelves, high-voltage DC-DC conversion, power factor correction (PFC), and LLC power stages, GaNEXUS enables up to 60% reductions in magnetic component size in high-frequency AC-DC and resonant converter stages. The technology can also provide 1.5x to 2x higher power density and efficiency gains of approximately 0.5% to 1%, contributing to lower thermal stress and reduced operating costs in high-power systems. The integrated protection capabilities of GaNEXUS Smart devices further simplify power stage design and support faster qualification processes.
The GaNEXUS portfolio is offered in thermally enhanced package options with industry-standard footprints to support design flexibility and dual sourcing strategies. Available package formats include TOLL Bottom Cooling, TOLT Top Cooling, and dual-cooled 3.3 mm × 3.3 mm and 5 mm × 6 mm packages.
Original – onsemi
-
Efficient Power Conversion (EPC) has introduced the EPC91132, a compact three-phase brushless DC (BLDC) motor drive inverter reference design built around the company’s EPC33110 gallium nitride (GaN) three-phase power module. The new platform is designed to support next-generation motion control applications, including humanoid robot joints, robotic hands and wrists, and drone propulsion systems.
The EPC91132 features an ultra-compact design with a diameter of just 23 mm, making it suitable for space-constrained motor drive applications. At the core of the reference design is the EPC33110 GaN module, which leverages EPC’s monolithic GaN integrated circuit technology. The module integrates three half-bridges, gate drivers, bootstrap circuitry, and level shifters within a compact 6 mm × 6.5 mm QFN package.
Powered from a single 5 V supply, the EPC33110 supports operating voltages up to 80 V and offers a typical on-resistance of 11.7 mΩ. The module is compatible with both 3.3 V and 5 V logic inputs, providing flexibility for a variety of control architectures.
As robotic and drone systems continue to demand smaller, lighter, and more efficient power electronics, GaN technology is increasingly being adopted for motor drive applications. The ability to operate at switching frequencies above 100 kHz while minimizing both conduction and switching losses enables improved efficiency, faster dynamic response, higher control bandwidth, and reduced passive component size.
The EPC91132 supports a wide input voltage range from 10 V to 60 V DC and integrates all key functions required for a complete inverter system. These include an onboard microcontroller, regulated power supplies, DC bus voltage sensing, current sensing with integrated overcurrent protection, and a magnetic encoder for rotor position and speed control.
The monolithic architecture of the EPC33110 eliminates the need for discrete gate drivers, significantly reducing component count while simplifying PCB design and accelerating development. The platform can be programmed through a dedicated connector and supports real-time monitoring via an RS-485 communication interface.
To accommodate different application requirements, EPC designed the board with a flexible breakout-ring structure. When the outer ring is removed, the board maintains its 23 mm diameter, allowing direct integration into compact motor systems such as the Vertiq 23-06 drone motor platform.
Performance testing demonstrated that the EPC33110 module can deliver continuous phase currents of up to 11 ARMS in humanoid robotic joint applications operating at 48 V and switching frequencies up to 100 kHz. In drone motor evaluations, the system exhibited strong thermal performance, with only minimal temperature rise observed under airflow generated by the propeller.
According to EPC, the EPC91132 demonstrates how monolithic GaN integration can simplify inverter design while providing the switching speed, power density, efficiency, and thermal performance required by next-generation robotic and aerial mobility systems.
The new reference design is intended to provide engineers with a compact and highly integrated development platform for evaluating GaN-based motor drive architectures in advanced motion-control applications.
Original – Efficient Power Conversion
-
Efficient Power Conversion (EPC) has introduced four new evaluation boards—EPC91128, EPC91129, EPC91130, and EPC91131—designed to accelerate the development of next-generation three-phase brushless DC (BLDC) motor drive systems using gallium nitride (GaN) technology.
The compact, high-performance inverter platforms are built around EPC’s integrated EPC23108, EPC23109, EPC23110, and EPC23111 ePower™ Stage ICs. The boards support input voltages ranging from 10 V to 80 V and output currents up to 29 ARMS, providing developers with a flexible platform for rapid evaluation in applications such as robotics, industrial automation, e-mobility auxiliary systems, and battery-powered equipment.
The evaluation boards integrate key inverter functions including gate drivers, current sensing, voltage sensing, housekeeping power supplies, temperature monitoring, and protection features. This high level of integration enables engineers to quickly prototype high-efficiency motor drive systems while minimizing the need for additional external circuitry. The platforms are optimized to reduce torque ripple and acoustic noise while providing flexible dv/dt control for application-specific tuning.
All four evaluation boards support complementary PWM and single-PWM control schemes, depending on the selected variant. They are also compatible with controller platforms from Microchip, Texas Instruments, STMicroelectronics, and Renesas, allowing developers to integrate them easily into existing motor-control development environments.
A key feature of the EPC91128–EPC91131 platforms is their demonstrated performance in practical motor-drive testing. During validation using a 48 V DC bus and switching frequencies of up to 100 kHz, the EPC91128 and EPC91129 boards successfully drove a 3 kW BLDC motor while delivering 15 ARMS continuous phase current without a heatsink. With a heatsink and natural-convection cooling, continuous current capability increased to 20 ARMS. Under pulsed operating conditions, the boards supported peak currents of up to 29 ARMS, demonstrating the ability of the integrated ePower™ Stage IC architecture to manage demanding dynamic motor loads.
The EPC91130 and EPC91131 variants achieved 10 ARMS continuous operation without a heatsink and 15 ARMS with heatsink assistance. Under pulsed conditions, these boards supported peak currents of up to 18 ARMS. According to EPC, the test results demonstrate that the compact GaN-based inverter platforms can sustain meaningful power levels suitable for industrial-grade motor control evaluation while maintaining thermal performance and switching efficiency at elevated switching frequencies.
Alex Lidow, CEO of EPC, stated that the new inverter platforms are intended to make GaN technology more accessible for high-performance motor-drive applications. He noted that as designers increasingly pursue higher efficiency, faster switching frequencies, and more compact power electronics systems, the new evaluation boards can help accelerate the transition from silicon-based solutions to GaN across robotics, industrial automation, and battery-powered motion systems.
Marco Palma, Vice President of Motor Drive Marketing and System Engineering at EPC, highlighted that the new platforms provide engineers with ready-to-use environments for evaluating the latest ePower™ Stage ICs under real motor-drive operating conditions. He added that the integrated sensing, protection, and control features allow developers to focus on system optimization rather than spending time designing the underlying power stage.
To support product development, EPC provides complete design resources for the new evaluation boards, including schematics, bill of materials (BOM), and Gerber files.
Original – Efficient Power Conversion
-
Navitas Semiconductor announced its participation in NVIDIA’s Partner Ceremony held on May 29, 2026, at the Taipei Nangang Exhibition Center. The event brought together ecosystem partners supporting the NVIDIA AI Factory MGX™ platform, highlighting industry collaboration aimed at advancing next-generation AI data centers based on emerging 800 VDC rack architectures.
As part of the NVIDIA AI Factory MGX™ Ecosystem Showcase at COMPUTEX 2026 in Taipei, taking place from June 2–5, Navitas is demonstrating its 800 V-to-6 V DC-DC power delivery board (PDB). Powered by the company’s GaNFast™ technology, the PDB eliminates the need for a traditional 48 V intermediate bus converter (IBC) stage within compute server trays, enabling greater system efficiency, reliability, and board-space utilization.
The power delivery board incorporates sixteen 650 V, 11 mΩ GaNFast FETs in the company’s latest DFN8×8 dual-cooled package. The design targets 97.5% peak efficiency while operating at a switching frequency of 1 MHz and achieving a power density of 2,100 W/in³. The ultra-low-profile design is approximately 20% thinner than a mobile phone, allowing close integration with GPU boards to enhance transient response and improve power distribution efficiency.
“As AI workloads continue to scale and drive unprecedented demand for compute, power delivery has become one of the most critical challenges in enabling next-generation gigawatt AI factories,” said Chris Allexandre, President and CEO of Navitas. “Through our collaboration with NVIDIA within the MGX™ ecosystem, Navitas is delivering GaN and SiC power technologies that enable megawatt-scale AI server racks with higher power density, a smaller system footprint, and improved thermal performance, helping accelerate the transition to more efficient and scalable AI infrastructure.”
Navitas also highlighted its portfolio of wide-bandgap power technologies designed to support next-generation AI factory infrastructure. The company’s GeneSiC™ silicon carbide (SiC) solutions address power delivery requirements from the electrical grid to AI compute racks, supporting applications such as solid-state transformers (SSTs) with 2300 V and 3300 V SiC power modules, as well as high-power three-phase power supply units based on its fifth-generation 1200 V SiC MOSFET technology.
According to the company, these SiC technologies contribute to improved efficiency, increased power density, and enhanced system reliability in large-scale AI data center deployments.
Navitas’ GaNFast technology is designed to provide the high-frequency, high-efficiency DC-DC power conversion required to support increasing power demands from AI accelerators and GPUs. By leveraging the switching performance of gallium nitride devices, the company’s solutions enable MHz-frequency operation, higher power density, and faster transient response, facilitating more efficient power delivery from the rack level to the processor level.
Through its portfolio of GaN and SiC technologies, Navitas continues to collaborate with NVIDIA within the MGX ecosystem to support open and modular AI infrastructure architectures and contribute to the development of next-generation AI factory platforms.
Original – Navitas Semiconductor
-
Infineon Technologies AG has introduced two new system-level power solutions designed to address the evolving requirements of artificial intelligence (AI) data centers. The company unveiled an 18 kW three-phase power supply unit (PSU) reference design optimized for 50 V rack architectures and a 30 kW three-phase interleaved T-Type power factor correction (PFC) evaluation board developed for 800 VDC or ±400 VDC rack architectures with power sidecar configurations.
The two solutions are part of Infineon’s broader AI server power delivery portfolio and are intended to help server ODMs and OEMs accelerate development while achieving higher rack power, improved efficiency, and enhanced thermal performance.
As AI workloads continue to increase GPU power consumption and drive higher rack densities, data center power infrastructures are facing growing challenges. Infineon’s new designs are aimed at addressing these demands through advanced power conversion technologies and system-level integration.
The 18 kW PSU reference design incorporates a new integrated energy buffer concept that smooths power demand from the electrical grid during AI-related peak loads, eliminating the need for a separate capacitor bank unit. According to Infineon, this approach enables more efficient use of stored energy and reduces the required capacitor volume by up to 50%, lowering both component costs and system footprint.
The 30 kW PFC evaluation board utilizes Infineon’s CoolGaN™ semiconductor technology to achieve higher power density while reducing overall system cost, targeting data center operators expanding infrastructure to support increasing AI computing requirements.
The 18 kW PSU reference design achieves a peak efficiency of 97.5% through a combination of 650 V CoolSiC™ MOSFETs, 80 V CoolGaN™ switches, EiceDRIVER™ gate drivers, and a PSOC™ microcontroller. At the core of the system is a five-level active neutral-point clamped (ANPC) PFC topology, designed to deliver high efficiency across the full load range, particularly under low-to-medium load conditions, while reducing the size of magnetic components.
Infineon states that the ANPC topology provides a 0.2% higher peak efficiency at 50% load compared to a T-Type PFC design and a 0.4% improvement over a Vienna Rectifier topology.
The design also incorporates a novel integrated planar magnetic structure that enables a compact, modular, and scalable high-frequency transformer configuration. The integrated energy buffer provides a 20-millisecond hold-up time and supports GPU electrical data peak processing (EDPP) loads of up to 180%, meeting demanding AI load transient requirements.
The PSU accepts a wide three-phase input voltage range of 311 VAC to 528 VAC, allowing compatibility with global power grid standards. Thermal management has been engineered to support operation in ambient temperatures ranging from -5°C to 45°C.
Measuring 104 mm × 710 mm × 40 mm, the PSU is designed to fit standard 19-inch rack enclosures while delivering a power density of 100 W/in³.
The 30 kW T-Type PFC evaluation board combines 650 V CoolGaN™ bidirectional switches in the back-to-back switching path with 1200 V CoolSiC™ MOSFETs in the high-voltage power stage. The system achieves a peak efficiency exceeding 99%.
Power control is managed through the programmable power control accelerator (PPCA) integrated into the PSOC™ C3 microcontroller, enabling precise current and voltage regulation with fast dynamic response. The design maintains input current total harmonic distortion (iTHD) below 5% for loads above 30% and achieves a power factor greater than 0.99 across most operating conditions.
Current measurement is performed using the XENSIV™ TLE4978 isolated magnetic Hall plus Coil current sensor, which offers a bandwidth of 9 MHz, strong common-mode transient immunity (CMTI), and high measurement accuracy. These characteristics make the solution suitable for next-generation silicon carbide and gallium nitride-based power supply systems.
The modular platform is designed for integration into a 1U full-size PSU form factor and targets high-voltage DC data center applications requiring accurate voltage regulation and effective thermal management under the dynamic operating conditions associated with AI workloads.
Both designs are optimized for use with Infineon’s AI server power delivery portfolio, which spans the complete power chain from grid connection to processor core. The portfolio includes solid-state transformers, circuit breakers, power supply units, battery backup units, intermediate bus converters, and second-stage DC conversion power modules.
By combining silicon (Si), silicon carbide (SiC), and gallium nitride (GaN) technologies, Infineon provides a comprehensive platform for end-to-end power architectures supporting next-generation AI server infrastructure. The solutions are backed by scalable components, design resources, and system-level support aimed at accelerating deployment of advanced AI data center power systems.
Both the 18 kW three-phase PSU reference design and the 30 kW three-phase T-Type PFC evaluation board are expected to be available for evaluation in the near future.
Original – Infineon Technologies
-
Power Integrations has introduced two new ultra-slim auxiliary power supply reference designs developed for 800 VDC AI data center applications. The designs are optimized for NVIDIA’s Kyber liquid-cooled blade-rack architecture and are intended to reduce space requirements, simplify system design, and improve reliability in high-voltage AI infrastructure.
The first design is a single-output 15 W auxiliary power supply measuring just 30 mm × 30 mm with a profile height of 7 mm. The second is an isolated six-rail 35 W design measuring 80 mm × 60 mm with an 8 mm profile. According to Power Integrations, the compact solutions can free up approximately 30% of board space on densely populated main power distribution boards (PDBs) while reducing bill-of-materials (BOM) count by an estimated 30%, contributing to simplified designs and enhanced system reliability.
Both reference designs achieve efficiency levels of at least 88% across line and load conditions.
“As the only company offering single-HEMT 1700 V GaN devices, Power Integrations can design these best-in-class, highly efficient flyback converters with a low BOM count while maintaining wide safety margins on an 800 V bus,” said Jason Yan, Senior Training Manager at Power Integrations. “The only alternative solutions are discrete, costly silicon carbide (SiC) devices which require 30% more components and space to operate.”
The newly released design examples describe 35 W and 15 W flyback auxiliary power supplies intended for high-voltage AI data center environments. These compact power supply units provide power for internal system components such as microcontrollers, gate drivers, and operational amplifiers that perform essential control, monitoring, and housekeeping functions required for system safety, reliability, and efficiency.
Both designs are based on Power Integrations’ InnoMux™-2 ICs incorporating 1700 V-rated PowiGaN™ gallium nitride technology. The InnoMux-2 devices support nominal input voltages up to 1000 VDC in a flyback topology and can deliver up to 90% flat efficiency in discontinuous conduction mode (DCM) while maximizing power delivery performance.
Power Integrations has made both reference designs available for download:
• DER-1110 – a 35 W multi-output flyback auxiliary power supply based on the IMX2353F, designed for high-voltage AI data center applications.
• DER-1114 – a 15 W single-output flyback auxiliary power supply based on the IMX2353F, also targeted at high-voltage AI data center applications.
The new designs leverage Power Integrations’ 1700 V PowiGaN technology to deliver compact, low-profile auxiliary power solutions for emerging 800 VDC AI data center architectures.
Original – Power Integrations
-
Efficient Power Conversion (EPC) has released additional information on its EPC91123 evaluation board, a 6 kW isolated converter designed to convert 800 VDC to 12.5 VDC for next-generation AI data center power architectures.
As a contributor to the NVIDIA MGX™ AI Factory ecosystem, EPC is advancing gallium nitride (GaN)-based power conversion technologies intended to support emerging 800 VDC server architectures. The company’s solutions are designed to enable higher power density, improved efficiency, and scalable rack-level power delivery for future AI infrastructure.
The EPC91123 enables direct conversion to 12.5 V, eliminating the need for a traditional 48 V intermediate bus stage. According to EPC, this approach improves overall system efficiency by approximately 1–2%.
The converter is based on an input-series, output-parallel (ISOP) LLC topology and incorporates EPC’s Gen7 eGaN® devices, including the EPC2366, a 40 V device with 0.8 mΩ on-resistance in a compact 3.3 mm × 2.6 mm package, and the EPC2305, a 150 V device with 2.2 mΩ on-resistance.
The EPC91123 achieves a peak efficiency of 98.2% and a full-load efficiency of 97%. Designed for space-constrained AI server environments, the evaluation board delivers high power density within a compact 104 mm × 47 mm × 8 mm form factor.
“AI data centers consume tremendous amounts of power, making it critical to reduce power conversion stages to improve efficiency and power density, especially in 800 V architectures,” said Alejandro Pozo, Director of DC-DC System Engineering. “The ISOP topology is particularly well suited for high step-down-ratio power conversion, enabling improved transformer optimization and interleaved operation. It has been selected for our next 800VDC to 6VDC platform.”
The EPC91123 forms part of EPC’s broader strategy for 800 VDC AI power delivery systems. The company is developing conversion platforms spanning 800 VDC to 48 VDC, 12 VDC, and 6 VDC to address a range of system-level requirements in AI infrastructure.
By utilizing advanced GaN-based ISOP topologies and its latest Gen7 eGaN technology, EPC aims to provide scalable, high-density power conversion solutions that improve efficiency, reduce power distribution losses, and support next-generation accelerated computing platforms.
“NVIDIA MGX provides a modular foundation for scalable accelerated computing. A key element of NVIDIA’s strategy for AI infrastructure is the use of 800 VDC power architecture, helping address the growing demands for efficiency and power density as AI compute scales. We are pleased to contribute to the NVIDIA MGX AI Factory ecosystem with advanced multi-level GaN-based power conversion solutions designed to support emerging 800 VDC server architectures and next-generation AI infrastructure,” said Alex Lidow, CEO and Co-founder of EPC.
Additional information on the EPC91123 evaluation board, EPC’s Gen7 GaN technology, and the company’s portfolio of 800 VDC power conversion solutions for AI infrastructure is available from EPC.
Original – Efficient Power Conversion
-
Innoscience outlined its roadmap for enabling next-generation AI data center power delivery through an end-to-end “All-GaN” architecture aligned with the evolving NVIDIA MGX ecosystem and emerging 800 VDC power distribution standards.
As AI factories scale toward megawatt-level rack power, efficient power conversion has become a critical bottleneck. Innoscience positions gallium nitride (GaN) technology as a key enabler of future AI infrastructure, citing its ability to deliver higher switching frequencies, lower losses, improved thermal performance, and greater power density than conventional silicon solutions.
The company’s roadmap spans the entire AI power delivery chain, from 800 VDC rack distribution down to GPU core voltages. At the front-end conversion stage, Innoscience demonstrated a 12 kW 800 V-to-48 V all-GaN LLC converter utilizing 650 V and 100 V GaN devices, achieving approximately 99% peak efficiency and 98.2% full-load efficiency while operating at 1 MHz. The company has also introduced 150 V GaN devices that reduce secondary-side synchronous rectifier requirements by 50%, simplifying system design and improving power density.
Beyond the 48 V architecture, Innoscience is extending its portfolio to support emerging 800 V-to-12 V and 800 V-to-6 V conversion topologies that are gaining traction in next-generation AI server designs. These architectures aim to reduce conversion stages, lower distribution losses, and move power conversion closer to GPUs.
For intermediate bus conversion, the company highlighted its 100 V GaN portfolio for 48 V-to-12 V multiphase buck converters, targeting higher efficiency and power density in AI servers where even marginal efficiency gains can significantly reduce cooling and operating costs at data center scale.
At the point-of-load level, Innoscience is developing 15 V DrGaN technology for vertical power delivery (VPD) architectures. Operating at switching frequencies between 3 MHz and 5 MHz, these solutions are designed to support future GPU power requirements by reducing passive component size, improving transient response, and enabling power stages to be located closer to AI accelerators.
Original – Innoscience Technology
-
STMicroelectronics has expanded its STPOWER portfolio with a new family of 700 V gallium nitride (GaN) power transistors designed to improve efficiency and increase power density in medium- and high-power applications.
The new enhancement-mode PowerGaN HEMTs target rapidly growing markets including AI servers, robotics, industrial power supplies, smart-grid infrastructure, and advanced electrification systems. By extending GaN technology into higher power levels, ST aims to address increasing performance demands that are challenging the limits of conventional silicon-based power solutions.
The new portfolio consists of seven devices with current ratings ranging from 6 A to 29 A and typical RDS(on) values between 53 mΩ and 270 mΩ. The devices leverage the inherent advantages of GaN technology, including low conduction losses, extremely low switching losses at high frequencies, low gate charge, and zero reverse recovery characteristics.
These features enable operation at significantly higher switching frequencies, allowing reductions in the size of magnetic components and passive elements while increasing overall power density and lowering system operating temperatures.
From a packaging standpoint, the devices are available in DPAK, TO-LL, and PowerFLAT surface-mount packages. TO-LL and PowerFLAT versions include Kelvin source connections that improve noise immunity, enhance gate-driver performance, and support cleaner switching behavior.
Original – STMicroelectronics
