Most NPUs are integrated units that excel at executing real-time AI tasks on edge devices such as smartphones and IoT systems with low power consumption. TPUs, on the other hand, are standalone processors designed for large-scale AI workloads in data centers, demonstrating exceptional performance in deep learning tasks. However, some manufacturers’ NPU chips are also … Read more
On Monday, Arm announced that CPUs based on its technology will be able to integrate with AI chips using Nvidia’s NVLink Fusion technology. This move will enable customers who prefer custom infrastructure—especially large-scale cloud service providers (such as hyperscale data centers)—to combine Arm-based Neoverse CPUs with Nvidia-dominated GPUs, simplifying the process of technological integration. This … Read more
Recently, the prices of storage chips have been continuously rising. Currently, the pressure of price increases is being transmitted from upstream to downstream. The CEO of SMIC recently stated at a performance briefing:“Due to the shortage of storage chip supply and rising prices, industries such as mobile phones and network communication equipment are being cautious … Read more
What is an ASIC chip? ASIC chips, short for Application-Specific Integrated Circuits, are integrated circuits designed and manufactured according to specific user requirements and the needs of particular electronic systems. Unlike general-purpose chips, ASICs are not aimed at multiple tasks but focus on specific applications, such as dedicated audio and video processors, as well as … Read more
Investment bank Bernstein recently released a research report on the lifespan of GPUs, addressing the growing controversy over depreciation and lifespan in the market. As the AI wave accelerates investment in computing across major enterprises, some investors question whether setting the GPU depreciation period at five to six years is overly optimistic, potentially leading to … Read more
Since 2022, the United States has begun to restrict our chip supply, initially prohibiting the purchase of high-end lithography machines and EDA software, and even directly banning the sale of NVIDIA’s A100 and H100 chips. At that time, domestic AI companies faced a sudden shortage of computing power, causing widespread concern. By 2023, they further … Read more
Click the blue text above to follow us On November 17, 2025, institutions such as the University of Hong Kong achieved a revolutionary breakthrough in the field of next-generation AI chip power consumption: an intelligent ruler created using the programmable characteristics of memristors reduced AI chip power consumption by 57.2%. This innovation signifies a leap … Read more
In the eye of the global AI computing power competition, Marvell, Broadcom, and Google are engaged in a covert battle using ASIC chips as their weapon, determining the technological hegemony for the next decade. This war, devoid of gunpowder, not only affects the strategic nerves of tech giants like NVIDIA, Microsoft, and Meta but also … Read more
1. Focus on November 6: Intensifying AI Chip Competition and Booming Storage Chip Market Google Challenges NVIDIA: Reports indicate that Google will launch a new generation of AI chip, TPU Ironwood, which is said to have a fourfold performance increase and has secured a large order from AI company Anthropic. This move directly targets the … Read more
