Frankfurt Germany, – 25th June, 2018 - Boston are pleased to announce the latest impressive benchmarks to come out of the renowned Boston Labs on the Boston Flash-IO Talyn solution powered by Excelero NVMesh. The solution delivered a sequential read of 44GB/s using 4MB blocks and a random read of 840k IOPS using 4k blocks.
Patrick O’Neill, HPC Systems Engineer, Boston Labs says “Using an NVIDIA® DGX-1™ as a client during testing we were able to achieve a throughput of 44GB/s for sequential reads and 840k IOPs for random reads. Both figures demonstrate the impressive performance that can be realised when using Flash-IO Talyn under varying workloads, even when only using a single client setup.”
The solution that was used consisted of four servers with each server including 4 NVMe drives – 16 in total.
Yaniv Romem, CTO for Excelero adds; “Modern GPUs used in AI and ML have an amazing appetite for data - up to 16GB/s per GPU. Starving that appetite...