MaxLinear, a leader in high-performance analog, mixed-signal and connectivity semiconductor solutions, announced the expansion of its AI infrastructure portfolio with two new 16V high-current electronic fuse (eFuse) solutions, the MxL745950 and MxL745951P. AI infrastructure is driving unprecedented increases in rack power density, power-domain complexity, and serviceability requirements. The devices are designed to help hyperscalers, OEMs, ODMs, and networking equipment providers protect, monitor, and manage critical power paths across AI servers, accelerator trays, data center switches, fan trays, power shelves, plug-in modules, and rack-scale platforms.
As AI clusters scale from server-centric deployments to rack-scale systems, power-path protection is becoming a mission-critical element of platform reliability. MaxLinear’s new eFuse portfolio brings together integrated hot-swap protection, scalable high-current operation, compact implementation, and intelligent monitoring to help customers improve uptime, isolate faults, accelerate root-cause analysis, and gain deeper visibility into power-domain behavior across large-scale AI deployments.
Industry demand for AI infrastructure continues to accelerate. Market research estimates that data center semiconductor revenue will reach approximately $843 billion by 2030. Hyperscaler capital spending is also rising sharply as operators expand AI compute capacity to support training, inference, and emerging agentic workloads. These trends are increasing the need for highly reliable power protection, telemetry, and serviceability across servers, networking systems, accelerator platforms, and rack-level infrastructure. Industry estimates place the global eFuse market at approximately $1.0B today, with growth expected through 2030 as electronic systems require more intelligent, compact, resettable, and programmable power protection. When viewed together with adjacent hot-swap and intelligent power-path protection ICs used in data center, telecom, automotive, and industrial infrastructure, the broader opportunity expands into a multi-billion-dollar power-protection market.
Also Read: Silicon Motion Unveils MonTitan SSD Reference Design Kit for AI Infrastructure at FMS 2026
The MxL745950 is a 16V, 50A electronic fuse with 1mΩ on-resistance in a compact 5mm × 5mm LGA-32 package. It integrates current sensing, temperature monitoring, fault indication, programmable soft-start and parallel-operation capability for higher-current applications, such as servers, networking systems, and plug-in modules.
The MxL745951P is a 16V, 60A stackable eFuse with 0.79mΩ on-resistance, PMBus™/I²C interface support, high-precision telemetry, configurable protection thresholds, non-volatile fault recording, and active current balancing during start-up and steady-state operation. The device provides digital telemetry for input voltage, input current, input energy, output voltage, output current, input power, and output power, enabling platform designers to add more intelligent power monitoring and fault visibility in AI and high-performance computing infrastructure.
“As AI infrastructure scales, the opportunity is expanding beyond compute silicon into the control, power, and telemetry technologies required to operate dense racks reliably,” said Amit D. Bavisi, Ph.D., Senior Vice President and General Manager, Analog Mixed-Signal Business Unit at MaxLinear. “Our new eFuse solutions extend MaxLinear’s role across AI servers, accelerator trays, switches, fan trays, power shelves, and rack-level platforms by helping customers build more observable, serviceable, and resilient power architectures.”
Why AI Infrastructure Requires Intelligent Power Protection
- Rack-level fault isolation: Integrated protection and fault-management capabilities help isolate subsystem failures before they impact broader rack operation.
- Operational visibility: High-precision telemetry and fault recording help operators improve power-domain visibility and accelerate root-cause analysis.
- Scalable current handling: Parallel operation and active current balancing support increasingly dense AI platforms and higher-current accelerator deployments.
- Serviceability and uptime: Hot-swap and inrush-control capabilities help support maintenance and replacement workflows in live or service-sensitive infrastructure.
- Control-plane integration: Complements MaxLinear’s AI infrastructure portfolio spanning connectivity, monitoring, rack management, console access, telemetry, power management, and protection.
SOURCE: MaxLinear