未找到相关数据
Blk-Tune: Blocking Parameter Auto-Tuning to Minimize Input-Output Traffic for Flash-based Out-of-Core Stencil Computations
被引：3
|作者：
Midorikawa, Hiroko
[1
,2
]
机构：
[1] Seikei Univ, Dept Comp & Informat Sci, Tokyo, Japan
[2] JST CREST, Tokyo, Japan
来源：
关键词：
auto-tuning;
non-volatile memory;
flash memory;
memory hierarchy;
tiling;
temporal blocking;
stencil;
out-of-core;
asynchronous IO;
mmap;
block;
memory extension;
D O I：
10.1109/IPDPSW.2016.48
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper proposes the auto-tuning system designed for flash-based out-of-core stencil computations. Blk-Tune is a runtime blocking parameter auto-tuning system that enables the use of flash memory as an extension of main memory. It incorporates automatic hardware information retrieval using Portable Hardware Locality and minimizes the amount of data transferred between the flash device and DRAM, which is the most dominant factor affecting the performance of out-of-core algorithms using flash. The use of explicit highly parallel asynchronous I/O to a flash device together with this auto tuning system offers great advantages over the mmap method, in which a flash file is memory mapped. Blk-Tune allows users to easily achieve maximum performance of large-scale stencil computations in different hardware and application settings.
引用
收藏
页码：1516 / 1526
页数：11
相关论文