memory bandwidth

Microsoft’s Maia 200 announcement marks a decisive escalation in the hyperscaler silicon arms race: an inference‑first accelerator built on TSMC’s 3 nm process that Microsoft says is already in Azure racks and is explicitly tuned to lower the per‑token cost of running large language models like...

Microsoft’s Maia 200 is a deliberate, high‑stakes response to the economics of modern generative AI: a second‑generation, inference‑first accelerator built on TSMC’s 3 nm process, designed to cut per‑token cost and tail latency for Azure and Microsoft’s Copilot and OpenAI‑hosted services...

High performance computing (HPC) sits at the engine room of modern science and industry, and the current vendor landscape reflects a rapid re‑ordering driven by AI, exascale ambitions, and cloud-first delivery models. The industry is anchored by a handful of hardware and software leaders — AMD...

Microsoft’s Azure Cobalt 200 arrives as a radical second act in its custom‑silicon playbook: a chipletized Arm-based server SoC that packs 132 Arm Neoverse V3 cores, a 12‑channel DDR5 memory interface, built on TSMC’s 3 nm process, and a set of on‑SoC accelerators and per‑core power controls...

Microsoft Azure’s HBv5 virtual machines have reached general availability, delivering a seismic shift in cloud HPC by pairing a custom AMD EPYC 9V64H processor with on‑package HBM3 memory and delivering nearly 7 TB/s of sustained memory bandwidth — a change that transforms which classes of HPC...

Microsoft and AMD’s co‑designed EPYC 9V64H — the custom CPU at the heart of Azure’s HBv5 virtual machines — rewrites the rules for memory‑bound HPC in the cloud by pairing Zen 4 compute chiplets with hundreds of gigabytes of on‑package HBM3 and delivering nearly an order‑of‑magnitude uplift in...

Nvidia’s journey into the AI-powered PC era reached a fresh milestone with the first public benchmarks of its GB10 Superchip, but the results spark more questions than answers for power users, IT pros, and PC enthusiasts evaluating hardware for next-gen AI workstations. According to Geekbench 6...

High-performance computing (HPC) often feels like a race car trying to navigate a traffic jam. It doesn’t matter how powerful the engine is if the road isn’t designed to support its speed. This sums up the ongoing challenge of memory-bound workloads in HPC. These workloads—think computational...

In a move that's likely to send ripples through the high-performance computing (HPC) landscape, Microsoft has unveiled its latest Azure HBv5 virtual machines, powered by a cutting-edge custom AMD CPU. This new CPU, which sports an impressive configuration, seems to be a rebirth of the...

:cool: