Anna Wood, Editor at Electronic Specifier, picks her top 5 AI products released in August 2026.
KIOXIA announces KIOXIA GP1 series IOPS SSDs for AI applications
KIOXIA Europe announced the KIOXIA GP1 Series PCIe 6.0 NVMe SSDs, the first product in its KIOXIA GP Series of Super High IOPS SSDs optimised for GPU direct access. Building on the KIOXIA GP Series technology introduced earlier this year, the KIOXIA GP1 Series delivers up to 10 million random read IOPS using KIOXIA XL-FLASH generation 2 flash memory, enabling flash-based memory extension to help address the growing performance and memory demands of AI infrastructure. Evaluation samples will be available to select customers by the end of 2026.
The KIOXIA GP1 Series is designed to support emerging AI storage architectures, which extend High Bandwidth Memory (HBM) as a fast flash memory media-based tier. This approach lets AI systems access larger datasets at a significantly lower cost than adding more HBM, while improving GPU utilisation.
2200V GaN breakthrough to power next-gen AI data centres
Power Integrations announced that PowiGaN gallium nitride (GaN) technology is now rated at up to 2200V, far exceeding the voltage capabilities of all other commercially available GaN technologies.
This positions PowiGaN as one of the best technology solutions for high-voltage data centres, EVs, renewable energy, and HVDC infrastructure.
GaN power switches are steadily supplanting silicon transistors in a wide range of power conversion applications thanks to their higher efficiency and switching frequencies. However, GaN technology must keep pace with data centre, EV, renewables, and HVDC infrastructure roadmaps calling for higher voltages and greater power density. Alternatives include lower-frequency silicon carbide (SiC) or arrays of stacked, lower-voltage GaN devices that require compromises on power density, complexity and reliability.
Infineon SEMPER NOR Flash memory strengthens data centre server
Infineon Technologies announced that its SEMPER NOR Flash memory has been qualified for ASPEED Technology’s AST2700 Baseboard Management Controller (BMC) and is now included in the AST2700 Approved Vendor List (AVL). As firmware storage for the BMC, the SEMPER NOR Flash supports the server management infrastructure that enables resilient, secure operation and helps keep systems available and protected. For hyperscale’s and server OEMs, the qualification provides a validated, design‑ready memory solution for AST2700‑based systems, reducing design risk and simplifying bill‑of‑materials decisions.
As AI, Cloud, and enterprise workloads grow, reliable server operation depends on more than compute capacity. BMCs provide out‑of‑band management and operate independently of the host CPU, remaining active even when the server is powered off. They continuously monitor system health, manage power sequencing, support secure boot, and enable remote access, secure over-the-network firmware updates, and system recovery. The NOR Flash connected to the BMC stores the critical management firmware that enables these functions, verifies its integrity at every power cycle, and supports recovery mechanisms.
Evaluating ultra-low-power Edge AI: inside BrainChip’s new Akida Pico FPGA Cloud
BrainChip has launched its Akida Pico ultra-low-power neuromorphic core on the FPGA Cloud. This initiative allows developers to remotely evaluate, test, and deploy Edge AI models without physical hardware, significantly reducing time to market for microwatt-scale sensing applications.
The democratisation of microwatt-scale Edge AI has arrived. BrainChip has announced the immediate availability of its Akida Pico neuromorphic co-processor on the FPGA Cloud. This remote platform breaks down traditional hardware barriers, allowing global engineers to validate their AI models on live hardware without waiting for physical evaluation boards.
Emerson advances AI across software portfolio
Emerson has announced new NI Nigel AI enhancements, including author code generation capabilities, across its full software portfolio. This next phase of Nigel AI introduces prompt-based code generation within NI LabVIEW and automated sequence generation in NI TestStand, enabling engineers to move from design to validation more quickly while maintaining the rigor required in mission-critical applications.
Based on internal benchmarking across representative engineering workflows, these capabilities reduce the time and effort required to develop and deploy test systems by up to 50%, accelerating test engineering productivity across industries like automotive, electronics, aerospace and defence, and semiconductors.
For more AI product news, and the latest on the electronics industry, check out the other articles on the website.
