19th December, 2016 - Boston Ltd. are attending the 23rd IEEE international conference on High Performance Computing, HiPC Hyderabad 2016, showcasing a selection of innovative HPC solutions including deep learning, cloud and Lustre* systems.
Boston Ltd. are on stand 4, and solutions exhibited include:
vScaler™
vScaler™ is a hyper converged solution for simplifying data center infrastructure, integrating and delivering server, storage, and networking resources at the click of a mouse. With a minimal deployment period of as little as 15 minutes, a variety of applications at any scale can be tested and deployed swiftly on this turnkey appliance. Powered by the OpenStack technology, the vScaler platform enables organizations to quickly deploy scalable and production-ready private cloud environments that can inter-operate with other public clouds.
Boston Venom 1501-0T (KNL Development Kit)
Keeping the requirements of developers in mind, Boston in partnership with Supermicro® designed the Boston Venom 1501-0T, KNL Development Kit. This kit comes integrated with an Intel® Xeon® Phi™ x200 Processor, supporting up to a staggering 72 cores* in a single socket, each performing at up to 1.7Ghz* (with Turbo boost). One such highly scalable processor could provide 3 trillion floating points operations a second. It also includes 16GB of high speed MCDRAM on package memory, which can act as cache or could be used in conjunction to legacy DDR4 DRAM enabling enhanced performance. Further capacity can be added by traditional DDR4 ECC LRDIMM’s, enabling a total of up to 384GB for memory hungry applications. An integrated liquid cooling solution and 6 low noise cooling fans, helps to keep the processor and other components at optimal temperature and your working environment quiet.
Boston ANNA Pascal (Artificial Neural Network Accelerator)
This latest deep learning platform from Boston Limited is an industry leading, latest-generation GPU based server and a masterclass of server design and innovation. NVIDIA® Tesla® P100 GPUs power the Boston ANNA Pascal to deliver the highest absolute performance for HPC and deep learning workloads with infinite computing needs.
The streamlined design eliminates complex cabling and GPU pre-heat for maximum airflow, cooling and the highest level of performance-per-watt. The high-density 1U server includes 2 x PCI-E Gen 3 slots for InfiniBand to enable strong RDMA performance and can support up to 4x GPUs, making it an optimal system for scalable GPU accelerator bound applications where density matters.
NVLink provides a high-speed 80Gb/s interconnect path wholly devoted to peer GPU-to-GPU connections. Combining this with RDMA via Infiniband or Omnipath provides the most powerful possible parallel computing environment. As shown below with the increase in performance compared to the previous generation K80 GPUs.
The reimagined appliance is crafted with innovation at each level from silicon to software, with over 5 ground-breaking technologies providing a dramatic jump in performance up to a 12X leap in neural network training, thus reducing training time from weeks to just hours.
Boston dataScaler-L SSF (Lustre* appliance)
The Boston dataScaler-L SFF appliance brings all the features of Intel Enterprise Lustre* into 4U form factor. This provides a lower cost / capacity entry point for Lustre* storage systems. The dataScaler-L SFF is optimized for the small or mid-sized clusters with capacities as low as 18TB (and scaling to 720TB).
The Boston dataScaler-L SFF has been developed and engineered in response to customer demands for higher performance HPC solutions at a more attractive price point.
Manoj Nayee, Managing Director, Boston Ltd says; "Attending HiPC is an opportunity for Boston to showcase and launch our newest solutions, in partnership with Supermicro®, to the HPC, data and analytics markets. All of the solutions on show are available immediately and have a variety of use-cases. I encourage attendees to visit our booth to discover more."