Google joins the Arm server race with its Axion processor, promising better performance and efficiency than x86 chips for Google Cloud. Axion frees Google from reliance on AMD and Intel and could reduce costs, including energy expenses. As Arm’s ecosystem grows, cloud customers may also benefit. continue reading
Israeli startup Hailo unveiled the Hailo-10 edge-AI NPU. Rated at 40 TOPS, it offers 50% more peak performance than the earlier Hailo-8, purportedly to handle gen AI. continue reading
NeuReality, an Israeli startup, challenges the AI-processing landscape with the NR-1. Calling it a network-addressable processing unit (NAPU), the company aims to streamline AI inference by managing data flow, scheduling tasks, and potentially reducing reliance on CPUs. continue reading
Nvidia Blackwell promises performance leaps but at what cost? Are are the claims realistic, and can competitors keep up? Dive into the specs, anticipated release timing, competition, and potential impact on the AI hardware landscape. continue reading
A software developer turned hardware homebrewer, Dylan Barrie has developed his own GPU. continue reading
Altera AMD Ampere Apple Arm auto Broadcom Ceva Computex CPU data center DPU edge AI embedded Epyc FPGA Google GPU Imagination Immortalis Intel interconnect Marvell MCU MediaTek memory Meta Microchip Microsoft MLPerf NPU (AI accelerator) Nvidia NXP PC process tech Qualcomm RISC-V SambaNova Semidynamics smartphone SoftBank software Syntiant Tenstorrent Untether