Research Notes

Research Note: UALink Consortium Expands Board, adds Apple, Alibaba Cloud & Synopsys

The Ultra Accelerator Link Consortium (UALink), an industry organization taking a collaborative approach to advance high-speed interconnect standards for next-generation AI workloads, announced an expansion to its Board of Directors, welcoming Alibaba Cloud, Apple, and Synopsys – joining existing member companies like AMD, AWS, Cisco, Google, HPE, Intel, Meta, and Microsoft.

Read More »

Research Note: Red Hat OpenShift Virtualization Engine

Red Hat announced the general availability of Red Hat OpenShift Virtualization Engine, a tailored version of its OpenShift orchestration platform for virtualization workloads.
The new offering utilizes the open-source KVM hypervisor and can run on-premises hardware with Red Hat Enterprise Linux and bare-metal cloud services.

Read More »

Research Note: Marvell Custom HBM for Cloud AI

Marvell recently announced a new custom high-bandwidth memory (HBM) compute architecture that addresses the scaling challenges of XPUs in AI workloads. The new architecture enables higher compute and memory density, reduced power consumption, and lower TCO for custom XPUs.

Read More »

Research Note: Enfabrica ACF-S Millennium

First detailed at Hot Chips 2024, Enbrica recently announced that its ACF-S “Millennium” chip, which addresses the limitations of traditional networking hardware for AI and accelerated computing workloads, will be available to customers in calendar Q1 2025.

Read More »