Modern HPC applications pose high demands on I/O performance and storage capability. The emerging non-volatile memory (NVM) techniques, such as Phase Change Memory and STT-RAM, offer low-latency, high bandwidth, and persistence for HPC applications. However, the existing I/O stack, including OS, high level library, I/O middleware, and applications, are designed and optimized based on an assumption of disk-based storage. To effectively use NVM, we must re-examine the existing I/O sub-system to properly integrate NVM into it. Using NVM as a fast storage, the previous assumption on the inferior performance of storage (e.g., hard drive) is not valid any more. The performance problem caused by slow storage may be mitigated; the existing mechanisms to narrow the performance gap between storage and CPU may be unnecessary and result in large overhead. Thus fully understanding of the impact of introducing NVM into the HPC software stack demands a thorough performance study.

In this paper, we analyze and model the performance of I/O intensive HPC applications with NVM as a block device. We study the performance from three perspectives: (1) the impact of NVM on the performance of traditional page caches; (2) a performance comparison between MPI individual I/O and POSIX I/O; and (3) the impact of NVM on the performance of collective I/O. We reveal the diminishing effects of page caches, ignorable performance difference between MPI individual I/O and POSIX I/O, and performance disadvantage of collective I/O on NVM due to unnecessary data shuffling. We model the performance of MPI collective I/O and study the complex interaction between data shuffling, storage performance, and I/O access patterns. Extensive experiments have been conducted to verify our analysis.

Keywords: NVM, page cache, MPI I/O, Collective I/O