Optimizing parallel I/O performance of HPC applications

High Performance Computing (HPC);Parallel Computing;Parallel I/O;Big Data;Storage Performance Tuning;Autotuning

Behzad, Babak

关键词: High Performance Computing (HPC);    Parallel Computing;    Parallel I/O;    Big Data;    Storage Performance Tuning;    Autotuning;   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/89120/BEHZAD-DISSERTATION-2015.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

Parallel I/O is an essential component of modern High Performance Computing (HPC). Obtaining good I/O performance for a broad range of applications on diverse HPC platforms is a major challenge, in part because of complex inter-dependencies between I/O middleware and hardware. The parallel file system and I/O middleware layers all offer optimization parameters that can, in theory, result in better I/O performance. Unfortunately, the right combination of parameters is highly dependent on the application, HPC platform, and problem size/concurrency. Scientific application developers do not have the time or expertise to take on the substantial burden of identifying good parameters for each problem configuration. They resort to using system defaults, a choice that frequently results in poor I/O performance. We expect this problem to be compounded on exascale class machines, which will likely have a deeper software stack with hierarchically arranged hardware resources.We present a line of solution to this problem containing an autotuning system for optimizing I/O performance, I/O performance modeling, I/O tuning, I/O kernel generation, and I/O patterns. We demonstrate the value of these solution across platforms, applications, and at scale.