Samsung patent boosts AI server memory efficiency without adding GPUs

T2Covered by 1 source · first reported by JP/KR/TW: Korea Herald / Taipei Times / DigiTimes at 22 Oct, 02:27 UTC

Samsung Electronics has disclosed a patent application targeting GPU memory shortages when multiple users simultaneously submit requests to AI servers. By calculating data-transfer costs between GPUs and CPUs and minimizing unnecessary transfers, the technology is designed to enable AI servers to…

hardware

Sources

• T2Samsung patent boosts AI server memory efficiency without adding GPUsJP/KR/TW: Korea Herald / Taipei Times / DigiTimes22 Oct, 02:27