New-Tech Europe | Q3 2026 | Digital Edition

Co Components

New Products Automotive

IoT

IoT Computers Components Computers Electro Optic & Camera Packaging & Production Motion Automotive New Products for industrial, automotive, and high-performance computing applications, supporting the growing demand for secure and reliable infrastructure powering AI workloads. ■ Source: Infineon Technologies Microchip Introduces VectorBlox™ 3.0 SDK to Advance Edge AI on PolarFire FPGAs

Automotive

New Products

Electro Optic & Camera Packaging & Productio

Motion

Computers Communication

Motion

Communication

Motion Automotive

Infineon expands AI server portfolio with SEMPER™ NOR Flash

for next-generation BMC platforms

Infineon Technologies has announced that its SEMPER™ NOR Flash memory has been qualified for ASPEED Technology’s AST2700 Baseboard Management Controller (BMC) and added to the platform’s Approved Vendor List (AVL), providing server manufacturers with a validated memory solution for next generation AI and cloud data center systems. Designed to store the critical firmware used by the BMC, the SEMPER NOR Flash family supports secure server management, remote administration, firmware integrity verification, and system recovery. As AI, cloud, and enterprise computing infrastructures continue to scale, reliable firmware storage has become an essential element in ensuring server availability and resilience. The SEMPER NOR Flash family is engineered for high-endurance applications and combines fast SPI interface performance with built-in Error Correcting Code (ECC) and Cyclic Redundancy Check (CRC) technologies to help protect firmware integrity and improve system reliability. These capabilities make it well suited for data center environments where continuous operation and secure firmware management are critical. The qualification for ASPEED’s eighth-generation AST2700 BMC, built on a 12 nm process, enables server OEMs and hyperscale data center operators to simplify system design while reducing validation effort and integration risk. Infineon continues to expand its memory portfolio

Microchip Technology has announced the release of the VectorBlox™ 3.0 Accelerator Software Development Kit (SDK), designed to simplify AI implementation on FPGA-based platforms while improving performance and energy efficiency for edge AI applications. Available free of charge, the SDK provides an integrated development environment for optimizing, compiling and deploying convolutional neural network (CNN) models on PolarFire® FPGA and SoC devices. The platform enables developers to consolidate multiple vision and sensor-based AI workloads on a single low-power FPGA, helping reduce system complexity and accelerate time to market. A key enhancement in VectorBlox 3.0 is support for sparse neural networks, allowing the accelerator to skip zero-value operations during AI inference. This approach reduces computational and memory requirements while maintaining model accuracy, enabling faster inference and lower power consumption for always-on edge AI systems. Microchip also highlighted real-world deployments of the technology in space applications. Planetek Italia has used VectorBlox acceleration on PolarFire SoC devices to support onboard Earth observation processing, including object detection and semantic scene analysis aboard the AI-eXpress-1 satellite. The

44 l New-Tech Magazine Europe