MAXLINEAR, INC

Portfolio of connectivity, monitoring, control, and power-management solutions helps enable rack-level control-plane architectures for AI, cloud, enterprise, and edge infrastructure CARLSBAD, Calif.--(BUSINESS WIRE)-- MaxLinear, Inc. (NASDAQ: MXL), a leader in high-performance connectivity, mixed-signal, and power-management semiconductor solutions, today introduced RackCommander™, a portfolio of connectivity, monitoring, control, and power-management products that help enable modern rack-level control-plane architectures for AI, cloud, enterprise, and edge infrastructure. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260810436995/en/ MaxLinear's RackCommander™ portfolio brings together connectivity, monitoring, control, and power-management products that help enable modern rack-level control-plane architectures for AI infrastructure. Building on MaxLinear’s recently announced Coronado™ and Laguna™ USB-UART solutions for AI data center control-plane connectivity, RackCommander brings together products across the key functions needed to manage increasingly complex rack-scale infrastructure. With Full- and High-Speed USB UARTs, RS-485 transceivers, GPIO expanders, power management, and power protection technologies, MaxLinear offers a comprehensive silicon portfolio for rack management and console-port applications. These solutions are designed to support control-plane and console-access requirements for AI infrastructure, including Universal Baseboards (UBBs), multi-node systems, and rack-scale architectures. As AI infrastructure transitions from server-centric architectures to rack-scale systems, the management challenge is changing dramatically. A modern AI rack may include multiple compute trays, dozens of accelerators, power shelves, liquid-cooling subsystems, sensors, service processors, and multiple management controllers. Traditional server-centric management approaches were not designed to efficiently manage these increasingly complex rack-scale environments. Industry analysts project datacenter semiconductor revenue to reach approximately $843 billion by 2030. Independent market surveys also project sustained growth for rack-controller and rack-management infrastructure as operators deploy increasingly dense AI systems. Future AI racks require a control plane that spans console access, infrastructure communications, monitoring, telemetry, protection, and rack-level serviceability. RackCommander helps customers address these requirements with MaxLinear products that can support: Scalable console connectivity across compute, networking, and storage assets High-speed sideband connectivity for service access and infrastructure control Rack-level aggregation of management and telemetry signals Robust communications between power, cooling, sensors, and infrastructure systems Expanded monitoring and control across distributed rack resources Power visibility, protection, and resiliency for critical infrastructure Together, these technologies help customers: Accelerate deployment of rack-scale AI infrastructure Simplify console an

New MxL745950 and MxL745951P address growing hyperscaler demand for intelligent power protection and telemetry solutions and will be showcased at the OCP APAC 2026 Summit booth PL33 CARLSBAD, Calif.--(BUSINESS WIRE)-- MaxLinear, Inc. (NASDAQ: MXL), a leader in high-performance analog, mixed-signal and connectivity semiconductor solutions, today 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. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260810522477/en/ MaxLinear's MxL745950 and MxL745951P intelligent eFuse solutions help enable scalable power protection, telemetry, and fault isolation for next-generation AI infrastructure. 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. 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 f

Integrated high-speed console connectivity delivers up to 480Mbps USB bandwidth and UART performance up to 15Mbps per channel for low-latency AI infrastructure management CARLSBAD, Calif.--(BUSINESS WIRE)-- MaxLinear, Inc. (NASDAQ: MXL), a leader in high-performance analog, mixed-signal and connectivity semiconductor solutions, today announced Carmel™, MxL81434, a next-generation high-speed USB-to-UART product designed to support console access, system bring-up, monitoring, debugging, and infrastructure management in AI data centers and hyperscale cloud environments. Carmel™ combines 480Mbps High-Speed USB connectivity, four high-performance UART channels operating at up to 15 Mbps each, an integrated I²C master, and 32 GPIOs in a highly integrated device for modern server and rack-scale management designs. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260810065267/en/ MaxLinear's Carmel™ (MxL81434) high-speed USB-to-UART solution delivers 480 Mbps USB connectivity, four UART channels up to 15 Mbps each, integrated I²C, and 32 GPIOs for next-generation AI infrastructure console access. Carmel™ extends MaxLinear’s USB-to-UART portfolio with a high-speed connectivity and console-access building block for server, rack-scale, and AI infrastructure designs. We believe the market opportunity for USB-to-UART devices is substantial, with an estimated serviceable available market (SAM) of approximately 200 million units driven by AI data center deployments. Building on the success of Coronado™ and Laguna™, Carmel expands MaxLinear’s participation in this growing market by addressing higher-performance console-access, debug, monitoring, and infrastructure-management requirements for next-generation AI server and rack-scale platforms. Why Carmel Matters High-speed console access with up to 480Mbps High-Speed USB connectivity. Four independent UART channels supporting up to 15Mbps per channel. Integrated I²C and 32 GPIOs to consolidate management, monitoring, and debug functions. Large 1024-byte transmit and receive FIFOs to help sustain throughput and reduce host overhead. Robust ±15 kV HBM ESD protection for demanding server and data center environments. Low-latency console connectivity to support faster bring-up, recovery, diagnostics, and provisioning. Performance Leadership Featuring four UART channels operating at speeds up to 15 Mbps each, Carmel provides high-speed console connectivity for data-intensive debug, provisioning, diagnostics, and recovery workflows. The device integrates 1024-byte transmit and receive FIFOs, helping sustain high throughput while minimizing host processor overhead. An integrated I²C master and 32 GPIO channels allow designers to consolidate monitoring, reset management, debug access, and platform-management functions into a single device. Executive Quote “As AI infrastructure scales, the performance requirements for console access, debug, and platform management continue to increase,” said Amit D. Bavisi, Ph.D., Senior Vice President and General Manager of MaxLinear’s Analog Mix

Panther also recognized as an AI Infrastructure Award finalist, highlighting its broad impact across AI and data center infrastructure CARLSBAD, Calif.--(BUSINESS WIRE)-- MaxLinear, Inc. (NASDAQ: MXL), a leader in high-performance connectivity and data movement solutions, today announced that its Panther™ Storage Accelerator has been named the winner of the FMS 2026 Best of Show Award in the Servers & Networking category. Panther was also recognized as a finalist in the AI Infrastructure Award category, underscoring its ability to improve performance and efficiency across both AI and data center environments. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260806198207/en/ Panther Storage Accelerator was named the winner of the FMS 2026 Best of Show Award in the Servers & Networking category. The FMS Best of Show Awards recognize innovative technologies advancing the future of memory, storage, AI, and data center infrastructure. Panther earned top honors in the Servers & Networking category for its ability to improve server efficiency, reduce CPU bottlenecks, and accelerate high-performance data movement across modern data center architectures. Its AI Infrastructure finalist recognition reflects Panther's ability to help organizations scale AI inference, retrieval-augmented generation (RAG), vector database and KV cache workloads. The recognition comes as the AI inference market continues to expand rapidly, with sustained double-digit growth projected into the early 2030s, increasing demand for technologies that address data movement and infrastructure bottlenecks impacting AI and data center performance. "As AI workloads continue to grow, organizations need more efficient ways to move, protect, and process data across their infrastructure," said Vikas Choudhary, Executive Vice President of Connectivity & Storage at MaxLinear. "This recognition validates Panther's ability to accelerate the storage data path and help customers improve performance, efficiency, and resource utilization across both AI and data center environments." Panther is a hardware-accelerated storage and data movement platform designed to improve how data is stored, moved, protected, and processed across enterprise, hyperscale, AI, and high-performance computing environments. The platform combines hardware-accelerated compression, decompression, encryption, data protection, verification, and high-speed data movement in a single accelerator solution. By offloading these data-intensive services from host CPUs, Panther helps organizations improve infrastructure utilization, increase effective storage performance, expand usable storage capacity, reduce power consumption, and lower overall infrastructure costs. Recent demonstrations and deployments have highlighted Panther's ability to accelerate AI data movement, support large-scale AI inference workloads, improve storage efficiency, and enable hardware-accelerated OpenZFS implementations for enterprise and high-performance computing environments. In collaboration with Los Alamos National Laboratory, Panther-enabled OpenZFS implementations demonstrated approximately 39x faster write performance and 7x faster read performance while maintaining OpenZFS data protection capabilities. The du

CMS Integrates Panther Storage Accelerator and ZFlush™ to Enhance Compression, Encryption, and Deduplication Performance CARLSBAD, Calif.--(BUSINESS WIRE)-- MaxLinear, Inc. (NASDAQ: MXL), a leading provider of high-performance connectivity and data movement solutions, today announced that Core Micro Systems (CMS), a Japan-based technology innovator, has adopted the MaxLinear Panther platform (Panther V) as the foundation for its next-generation storage infrastructure. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260804882593/en/ Core Micro Systems (CMS) and MaxLinear are collaborating to deliver hardware-accelerated OpenZFS storage solutions based on the MaxLinear Panther platform for AI, cloud, hyperscale, and enterprise infrastructure. Through this adoption, CMS is integrating the MaxLinear Panther platform into its next-generation storage solutions and collaborating with MaxLinear to deliver hardware-accelerated OpenZFS capabilities that significantly improve storage performance, efficiency, and scalability for enterprise, cloud, hyperscale, and AI infrastructure environments. By combining the Panther Storage Accelerator with ZFlush™ hardware-accelerated OpenZFS, CMS will accelerate key data services including compression, encryption, and deduplication while reducing CPU utilization and lowering infrastructure costs. Executive Quotes "We selected the MaxLinear Panther platform to serve as the hardware acceleration foundation for our next-generation storage solutions. The Panther Storage Accelerator and ZFlush™ enable us to deliver enhanced OpenZFS performance across compression, encryption, and deduplication workloads while providing customers with a highly efficient and scalable storage architecture. We look forward to expanding our Panther-based offerings to meet the growing demands of data-intensive applications," said Shozo Takahashi, President and CEO of Core Micro Systems. "Our collaboration with Core Micro Systems marks an important step in expanding adoption of the MaxLinear Panther platform in high-performance storage environments. By combining Panther's hardware acceleration capabilities with CMS's deep system expertise, we are enabling customers to accelerate OpenZFS performance, reduce system complexity, and speed time to market for next-generation AI, cloud, hyperscale, and enterprise storage platforms," said Vikas Choudhary, Senior Vice President and General Manager of Connectivity & Storage at MaxLinear. Advancing OpenZFS Performance with Hardware Acceleration The solution leverages the MaxLinear Panther Storage Accelerator as the hardware acceleration engine for CMS's next-generation storage platforms. Combined with ZFlush™ hardware-accelerated OpenZFS, the platform accelerates compression, encryption, and deduplication workloads, enabling higher throughput, lower latency, and improved system efficiency while reducing CPU overhead. Key features of the solution include: Comprehensive Data Acceleration – ZFlush™ 1.3 supports compression/decompression, encryption/decryption, and SHA-256 processing

Live demonstrations and technology showcases highlight AI workload compression, OpenZFS acceleration, and peer-to-peer DMA for more efficient AI infrastructure CARLSBAD, Calif.--(BUSINESS WIRE)-- MaxLinear, Inc. (NASDAQ: MXL), a leading provider of high‑performance connectivity and data movement solutions, today announced it will showcase its Panther Storage Accelerator platform at Future of Memory and Storage (FMS) 2026, held August 4–6 in Santa Clara, California. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260729150347/en/ MaxLinear Panther Storage Accelerator helps organizations scale AI infrastructure by increasing effective storage capacity and enabling support for more AI agents through hardware-accelerated data services. As AI evolves from model-centric deployments to agentic AI architectures, infrastructure requirements are shifting from model performance to agent scalability. AI clusters are increasingly required to support millions of concurrent agents, driving exponential growth in memory capacity and bandwidth requirements. As agent populations grow, HBM and DDR resources become constrained, increasing memory pressure and reducing GPU and CPU efficiency. Panther addresses these challenges through hardware-accelerated compression, delivering up to a 3× compression ratio on AI data. This increased efficiency can enable up to 2.2× greater effective KV cache capacity, helping systems support up to 2.2× more AI agents within existing infrastructure. "As AI adoption accelerates, organizations are rethinking how they store, move, and manage data at scale," said Vikas Choudhary, Senior Vice President and General Manager of Connectivity and Storage at MaxLinear. "Panther helps address these challenges by enabling more efficient use of storage and compute resources, allowing customers to increase effective storage capacity for AI data while improving overall infrastructure efficiency. We're excited to showcase these capabilities at FMS and demonstrate how Panther can help organizations scale next-generation AI workloads more efficiently." Panther combines hardware-accelerated compression, encryption, erasure coding, data integrity services, and high-speed data movement in a single accelerator platform. By offloading these data-intensive functions from host CPUs, Panther helps organizations increase effective storage capacity, improve infrastructure utilization, reduce power consumption, and accelerate AI and storage workloads while lowering overall infrastructure costs. Panther Technology Showcases at FMS 2026 Live AI Workload Compression Demo — See Panther perform hardware-accelerated compression and decompression on AI datasets, reducing CPU overhead while maintaining the throughput required for modern AI environments. Live Peer-to-Peer DMA Demo — Experience direct PCIe endpoint-to-endpoint data movement enabled by Panther's peer-to-peer DMA architecture, reducing host CPU involvement and memory bandwidth consumption. OpenZFS Acceleration Showcase — Learn how Panther integrates with OpenZFS through the ZIA and DPUSM frameworks to enhance storage p

Pioneering Hardware-Accelerated ZFS to Improve Throughput, Efficiency, and Scalability in HPC Storage CARLSBAD, Calif. & LOS ALAMOS, N.M.--(BUSINESS WIRE)-- MaxLinear, Inc. (NASDAQ: MXL), a leading provider of high-performance storage accelerator SoCs, and Los Alamos National Laboratory (LANL) today announced a collaboration to enable hardware-accelerated OpenZFS File System storage for large scale, high-performance computing (HPC) environments. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260603338003/en/ MaxLinear and Los Alamos National Laboratory collaborate on hardware-accelerated OpenZFS storage using Panther™ Storage Accelerator SoCs for HPC environments. Los Alamos National Laboratory and MaxLinear have jointly developed a hardware-accelerated OpenZFS storage architecture designed to improve performance and storage capacity for next-generation NVMe flash-based storage infrastructure. “Los Alamos’ Direct I/O support and Z.I.A. (ZFS Interface for Accelerators) work were developed to accelerate performance for the ZFS-using community,” said Gary Grider, Senior Director for Computing Technologies at the Laboratory. “In this collaboration, MaxLinear demonstrated hardware-offloaded ZFS operations with reported speedups of approximately 39x for writes and 7x for reads. These results illustrate the potential for accelerator-based approaches to reduce host CPU involvement while maintaining the data-protection benefits associated with ZFS.” “Los Alamos National Laboratory has been at the forefront of advancing storage architectures for high-performance computing,” said Vikas Choudhary, Executive Vice President of Connectivity & Storage at MaxLinear. “By enabling hardware-accelerated ZFS with Panther™ Storage Accelerators, we deliver deep data compression, data protection services, and multi-hundred gigabit scalability—while preserving the data integrity guarantees that ZFS is known for.” LANL has decades of experience in operating ZFS at scale and has led to the development of key filesystem extensions, including Direct I/O support and ZIA (ZFS Interface for Accelerators)—a structured framework for introducing hardware acceleration into the ZFS data path without modifying core filesystem semantics. MaxLinear contributes the Panther™ family of Storage Accelerator SoCs and Storage Software Development Kits, providing high throughput, low latency execution of ZFS data path services using a domain-specific high-performance SoC architecture. Panther™ provides deep data compression, encryption, deduplication, and data protection services executed inline in hardware, delivering high throughput and low latency while significantly reducing host CPU overhead. Through this collaboration, Panther is integrated with ZFS as a Data Processing Unit Services Module (DPUSM) provider, enabling inline hardware acceleration of selected CPU‑intensive operations such as data compression and checksum generation to increase storage capacity, improve file I/O performance, and reduce host CPU utilization. This combined hardware‑software approach preserves ZFS ordering, consistency, and data integrity guarantees while enabling efficient compute offload and scalable acceleratio