❌

Normal view

There are new articles available, click to refresh the page.
Before yesterdayMain stream

Qualcomm’s HBC Stacks Compute Beneath DRAM To Smash The AI Memory Wall, Claiming 6x The Bandwidth Per Watt Of HBM

24 June 2026 at 21:15

A layered chip with gold-colored elements is shown above the text '200x capacity per watt vs. SRAM*'.

Qualcomm is unveiling its breakthrough for the AI data center market called HBC (High-Bandwidth Compute), to break the memory wall. Qualcomm's HBC Is A Memory Accelerator That Is Stacked Under DRAM, Offering A Major Boost Versus Standard SRAM & HBM Configurations At its Investors Day 2026, Qualcomm unveiled HBC under its Dragonfly brand, an innovative technology that aims to offer a major boost in memory capacity and bandwidth. The HBC architecture deploys a purpose-built & near-memory solution that bonds compute with boosted memory bandwidth in a 3D stacked chip design. With this, Qualcomm aims to solve the memory bottlenecks that […]

Read full article at https://wccftech.com/qualcomm-hbc-stacks-compute-beneath-dram-to-smash-the-ai-memory-wall/

SanDisk Bets on Stacking NAND and Compute on One Chip as HBM Shortages Choke the AI Boom

21 June 2026 at 23:45

HBF Memory Offers Higher Capacities Than HBM But NVIDIA Isn't Interested In It (Yet), Sampling This Year With Google A Key-Customer 1

SanDisk is looking for more innovative solutions to address memory limitations, such as stacking NAND Flash within chips. Memory Limitations Push DRAM/NAND Maker To Get More Innovative, SanDisk Proposes The Stacking of NAND Flash Within Chips The rapid rise of AI & the proportional demand for compute has led to the exposure of bottlenecks, which are pushing DRAM and NAND manufacturers into going with the out-of-the-box approach. In the past, chipmakers called it a day by introducing new memory technologies, and DRAM was the primary component. But the rise in costs, development/yield drawbacks, & increased power have led to a […]

Read full article at https://wccftech.com/sandisk-bets-on-stacking-nand-and-compute-on-one-chip/

Micron Doubles Down on AI Memory With 256 GB DDR5 RDIMMs Hitting 9200 MT/s, a 40% Leap Over Today’s Modules

12 May 2026 at 17:35

Micron Doubles Down on AI Memory With 256 GB DDR5 RDIMMs Hitting 9200 MT/s, a 40% Leap Over Today's Modules

Micron has started to ship its fastest DDR5 RDIMM memory modules, which feature 256 GB capacities & up to 9200 MT/s speeds. Micron Offers 40% Boost Vs Current "In-Volume" DDR5 RDIMM Memory Modules, Brings 256 GB Capacities With 9200 MT/s Speeds As Agentic AI requirements grow, memory makers are rolling out faster and higher-capacity memory kits to meet the demands of AI firms. JEDEC is also pushing the DDR5 MRDIMM standard up to 12,800 MT/s, and today, Micron has announced that it is sampling its 256 GB DDR5 RDIMM modules with up to 9200 MT/s speeds. The main highlights include: […]

Read full article at https://wccftech.com/micron-doubles-down-on-ai-memory-256-gb-ddr5-rdimms-hitting-9200-mtps/

❌
❌