A Chinese AI company circumvented the U.S. ban on importing advanced AI chips by exporting its data instead.
Oracle Cloud Infrastructure will be the first major cloud provider to deploy AMD's Instinct MI350X GPUs and Pensando Pollara 400GbE Ultra Ethernet NICs as part of a massive zettascale AI cluster.
AMD launches ROCm 7 platform that boosts AI inference performance by up to 3.5X, adds support for FP4/FP6 formats and distributed workloads, and extends compatibility to Windows and Radeon GPUs on Ryzen systems.
A new air-gap attack dubbed 'SmartAttack' theorizes using a smartwatch to capture covert signals and steal information.
AMD’s Zen 6-based EPYC ‘Venice’ CPU pushes core count to 256, boosts performance by 70%, and features PCIe 6.0, 1.6 TB/s memory bandwidth, and a new SP7 packaging, according to AMD.
AMD plans to launch its second-generation rack-scale AI platform in 2027 with EPYC 'Verano' CPUs, Instinct MI500X GPUs, and Vulcano 800 GbE NICs, accelerating its roadmap to an annual cadence.
AMD unveiled its new MI350X and MI355X GPUs for AI workloads here at its Advancing AI 2025 event in San Jose, California, claiming the new accelerators offer a 3X performance boost over the prior-gen MI300X, positioning the company to improve its competitive footing against its market-leading rival, Nvidia.
The Nintendo Switch 2's powerful internals deliver a major upgrade to the Switch formula, but there's still some room for improvement.
AMD unveiled Helios, its first in-house rack-scale AI system built around upcoming EPYC 'Venice' CPUs and Instinct MI400-series GPUs, aiming to challenge Nvidia's dominance in AI. But while it is said to offer higher memory capacity and bandwidth than competing platforms, it is expected to trail in peak compute performance against Nvidia's future Rubin-based systems.