We recently received Supermicro’s dual-socket Turin-based A+ Server AS-2126HS-TN for review. It’s a 2U platform designed to support extremely high-core-count workloads and to provide flexible PCIe expansion. Built around and supporting dual AMD EPYC 9005 (Turin) and 9004 (Genoa) series processors, the system targets a broad range of enterprise and data center use cases, including
At CES 2026, NVIDIA unveiled the Rubin platform, anchored by the Vera Rubin NVL72 rack-scale system. This is NVIDIA’s third-generation rack-scale architecture, combining six co-designed chips into a single unified system. The platform will be available from partners in the second half of 2026, with all six chips already back from fabrication and currently undergoing
The Lenovo ThinkSystem SR650 V4 is a flexible and powerful 2-socket, 2U rack server designed to meet the needs of industries such as cloud services, telecommunications, and high-performance computing (HPC). Whether optimizing for scale-out workloads or future-proofing your data center with high-density compute, the SR650 V4 offers meaningful upgrades over its predecessor, the SR650 V3.
At the SC25 event in St. Louis, Brian caught up with his long-time friend Mark Klarzynski, founder and acting CTO at PEAK:AIO. If you have been following StorageReview, then you may be familiar with our coverage of PEAK:AIO, from regular news coverage to medical AI to animal conservation. As Mark explains, he has “spent
Supermicro announced the latest addition to the AMD-based Instinct MI350 series GPU-optimized solutions. The updates are expected to deliver greater performance, maximum scalability, and power efficiency. Supermicro has designed this new system for organizations that need the high-end performance of AMD Instinct MI355X GPUs but require an air-cooled environment. Vik Malyala, SVP of Technology and
Some servers extend what already exists, while others reset expectations. The Dell PowerEdge R7725xd belongs to the second category. In our recent testing, configured with 24 Micron 9550 PRO PCIe Gen5 NVMe SSDs and four 2x 200GbE NICs, this 2U server achieved higher raw storage throughput than any system we have measured before. Internally, the
Dell Technologies has announced a series of enhancements to the Dell AI Factory to simplify and accelerate the enterprise AI journey. The expanded offerings focus on enhancing performance and automation for AI tasks while addressing common challenges through integrated, reliable on-premises infrastructure that provides greater control and more predictable operations. This timing aligns with a
HPE expanded Cray supercomputing solutions center on multi-vendor, multi-workload blade architecture, unified management, and high-performance interconnected fabric.
The benefits of immersion extend beyond temperature control. With stable thermal conditions, GPUs can maintain peak boost clocks without throttling, CPUs operate with lower variability, and storage devices deliver consistent I/O throughput.
HPE ProLiant DL380a Gen12 review: a 4U air-cooled AI server with dual Xeon 6, RTX PRO 6000 Server GPUs, E3.S NVMe, and iLO 7 for enterprise deployment.
Amazon