New memory architecture targets AI inference bottlenecks

Lightbits Labs Ltd. today is introducing a new architecture aimed at addressing one of the most stubborn bottlenecks in large-scale artificial intelligence inference: the growing mismatch between the ...
insideHPC

DDN Takes on GPU Waste with KV Cache Performance for AI Reasoning

CHATSWORTH, Calif. — July 18, 2025 DDN today unveiled performance benchmarks that the company said demonstrates how its AI-optimized DDN Infinia platform eliminates GPU waste and delivers the fastest ...
Gizmochina

Snapdragon 8 Gen 4 utilizes a new GPU architecture with improved cache and memory compression tech, claims tipster

Qualcomm‘s next flagship mobile processor, the Snapdragon 8 Gen 4, is expected to launch later this year, and rumors regarding its features are picking up steam. A new leak by Weibo tipster Digital ...
TweakTown

Intel's killed-off BMG-X3/X4 GPUs: 3D stacked die, up to 40 GPU cores, 512MB Adamantine cache

TL;DR: Intel's cancelled Battlemage GPUs featured innovative 3D-stacked Adamantine cache, promising enhanced performance similar to AMD's Infinity Cache. Despite ambitious designs with up to 40 Xe2 ...
XDA Developers on MSN

DirectStorage isn't magic, but it does change what SSD specs matter

DirectStorage could finally make Gen5 SSDs worth it for gaming ...
PCGamesN

New graphics card memory tech could boost performance by 12.5x

There's an exciting new graphics card memory technology on the horizon that could see huge gains in one of the most important aspects of GPUs: memory bandwidth. The new GPU SCM with DRAM tech can ...
HotHardware

Intel Core Ultra Meteor Lake CPU Breaks Cover With 128MB Cache And Alchemist GPU

Thanks to a mix of official, semi-official, and leaked data, aspects of Intel’s Meteor Lake (MTL) processors and architecture are coming into sharper focus. A case in point is a Sisoft Sandra sysinfo ...