The SciNet Consortium at the University of Toronto selected the NextIO vCORE Express 2070 systems because their research professors needed a powerful and flexible GPU system that would allow them to quickly solve rapidly growing and complex research problems. With the NextIO vCORE Express solution, researchers can obtain access to larger amounts of fast GPU memory than would be available in just a single GPU traditionally located in a system. This doubles their existing memory capabilities to run simulations, such as kinematic measurements of cosmic history, or predictions of combusting and multiphase flows encountered in aerospace propulsion systems.
"When it came to choosing a high-performance system to power the important research conducted at the University of Toronto, the NextIO vCORE GPU system was an obvious choice", stated Dr. Chris Loken, SciNet's Chief Technical Officer. "These systems certainly give us better density and more memory per dollar in addition to a tremendous amount of flexibility that can be leveraged in variables for different high compute problems."
NextIO's vCORE product family features NVIDIA's record-setting GPUs for both compute-intensive and data visualization requirements. The vCORE Express enhances NextIOs GPU consolidation product portfolio by introducing a simple, yet extremely powerful, solution for workstation and small cluster compute applications. vCORE Express is designed especially for parallel computing applications using NVIDIA Tesla 20-Series GPUs in cluster and datacenter deployments. With four massively parallel CUDA-enabled GPUs in a 1U system, vCORE Express brings economies of scale to GPU customers by delivering the same performance of a traditional CPU-based cluster - all at 10 percent of the cost and five percent of the power consumption.
The SciNet Consortium represents scientific researchers from the University of Toronto and the affiliated research hospitals and provides high-performance computing resources to the Canadian research community. Research professors who will utilize the NextIO GPUs to develop simulation codes for large-scale computing applications in science and engineering include: