NEXTGenIO Workshop on applications of NVRAM storage to exascale I/O

Improving data intensive workflows in modern supercomputers by any means possible continues to be a focus of both industry and academic research. And while big steps have been made, most have served to move the I/O bottleneck somewhere else and not actually solve it.
Putting NVRAM into computers, semi-shared burst buffers or even into storage servers to improve overall performance and reduce latency is great but can we afford to sacrifice resiliency and flexibility to achieve it. And what about the continued need for parallel file systems (or next gen object storage solutions) in this picture ??
Storage tiering may be the way to go but data movement between tiers is expensive.

This talk is intended to see the future of data intensive workflows from a storage point of view and how an end to end architecture could benefit from NVRAM and NVMe based technologies while still retaining a semblance of traditional storage subsystems.