GigaDevice Expands GD25UF Series Density Empowering AI Computing with 1.2V Ultra-Low Power Storage

2026-03-10 · Source: Big Data & AI News - EE Times · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Internet of Things (IoT) & Connected Devices · Depth: Intermediate, quick

Summary

GigaDevice announced on March 10, 2026, an expanded density range for its GD25UF series 1.2V ultra-low power SPI NOR Flash, now available from 8Mb to 256Mb. This expansion supports diverse applications, from high-performance AI computing to low-power battery-operated devices like wearables and medical devices, by enabling longer battery life and device miniaturization. The GD25UF series operates between 1.14V and 1.26V, aligning with the 1.2V operating voltage of modern SoCs and processors, eliminating the need for external level shifters and reducing BOM costs. It offers high data throughput up to 80MB/s, reduces power consumption by 50% to 70% compared to 1.8V Flash, and provides high reliability with 100,000 program/erase cycles and 20-year data retention across industrial and automotive temperature ranges.

Key takeaway

For AI Hardware Engineers designing next-generation edge AI devices or high-performance computing platforms, your selection of non-volatile storage should prioritize 1.2V compatibility and scalable density. The GigaDevice GD25UF series offers a direct path to reducing power conversion losses and BOM costs while supporting the increasing memory demands of larger AI models and ultra-compact form factors, directly impacting battery life and system complexity.

Key insights

GigaDevice's GD25UF series expands SPI NOR Flash density, enabling low-voltage AI and compact, power-efficient devices.

Principles

• Align memory voltage with SoC for efficiency.
• Higher density supports complex AI models.
• Ultra-compact packaging enables miniaturization.

Method

Integrate 1.2V SPI NOR Flash directly with 1.2V SoCs to eliminate level shifters, reduce BOM, and enhance energy efficiency.

In practice

• Use GD25UF for 1.2V AI ASIC platforms.
• Implement 8Mb WLCSP for IoT wearables.
• Reduce power in health monitoring devices.

Topics

• SPI NOR Flash
• Ultra-low Power
• Edge AI
• Semiconductor Memory
• GigaDevice

Best for: AI Hardware Engineer, AI Engineer, AI Product Manager

Related on AIssential

• H100 to B200: What Actually Changed — NVIDIA's Blackwell architecture, featuring the B200 GPU and GB200 NVL72 system, represents a fundamental shift from the H100, moving beyond individual GPU performance to datacenter-scale AI infrastructure.
• Samsung unveils UFS 5.0 storage for future Galaxy phones — Samsung's UFS 5.0 storage offers significantly faster speeds and greater efficiency for next-gen mobile devices and on-device AI.
• BREAKING: IBM's 0.7nm Chip Packs 100 Billion Transistors and Defies Physics — IBM's 0.7nm chip, packing 100 billion transistors, sets a new standard for semiconductor processing power and efficiency.
• Neutralizing the Gigascale Problem: How to Solve the Physical Power Paradox of Extreme AI Training Loads — Gigascale AI demands active, high-speed energy storage to stabilize power fluctuations, moving beyond passive backup.
• Micron Readies Client Storage for AI — Local AI on client devices is driving demand for high-performance, power-efficient storage solutions like PCIe Gen5 QLC SSDs.
• LPDDR6 Roadmap Leads to the Data Center — LPDDR6 is being extended with features like PIM and SOCAMM2 to meet the power-efficient, high-capacity demands of AI data centers.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Big Data & AI News - EE Times.