We explore how NVIDIA NVSwitch technology is expanding NVLink topologies and enabling larger 16 GPU systems like the NVIDIA DGX-2 server with 16x NVIDIA Tesla V100 32GB GPUs
Doubling the amount of HBM2 memory on its flagship the NVIDIA Tesla V100 32GB is now available to the delight of deep learning and AI researchers
The new NVIDIA Quadro GV100 is a Volta-based monster for workstations designed for the workflows, and to attract, top-tier deep learning, AI, VR developers and digital artists.
We continue our benchmark every server CPU project with our Intel Xeon Gold 6132 benchmarks and review. We also have power consumption information along with our thoughts on market positioning
Preparing for the hard fork in April 2018 to make Monero more ASIC resistant, we have updated our Docker mining images. These new images are ready for the Monero and Aeon hardforks for cryptonight and cryptonight-lite POW changes.
We show you how to overclock a server and get faster memory speeds by running RAM at a higher than rated clock speed. This can ever so slightly increase your system performance and works on a variety of Intel-based servers
Microsoft Project Denali is a potential game-changer for flash storage at the scale Azure operates at. The company outlined how and why this is moving into production this year at OCP Summit 2018
Our Supermicro X11SDV-4C-TLN2F motherboard review with an Intel Xeon D-2123IT onboard. We also have some performance benchmarks, power consumption details and a comparison to other embedded platforms
Facebook shows off and donates its 100GbE central switching design. The Facebook Fabric Aggregator is a scalable architecture to handle massive traffic. It is also calling for the end of pluggable optics with the 400GbE generation
Just in time for OCP Summit 2018, Toshiba released new SSDs the Toshiba XD5, HK6-DC and CD5 and its KumoScale NVMeoF solutions.