Publications of Torsten Hoefler

Torsten Hoefler:

A case for runtime recompilation in HPC

(Presentation - presented in New Orleans, Louisiana, USA, Nov. 2014)
The LLVM Compiler Infrastructure in HPC, Keynote Presentation

Abstract

Data packing before and after communication can make up as much as 90% of the communication time on modern computers. Despite MPI's well-defined datatype interface for non-contiguous data access, many codes use manual pack loops for performance reasons. Programmers write access-pattern specific pack loops (e.g., do manual unrolling) for which compilers emit optimized code. In contrast, MPI implementations in use today interpret datatypes at pack time, resulting in high overheads. In this work we explore the effectiveness of using runtime compilation techniques to generate efficient and optimized pack code for MPI datatypes at commit time. Thus, none of the overhead of datatype interpretation is incurred at pack time and pack setup is as fast as calling a function pointer. We have implemented a library called libpack that can be used to compile and (un)pack MPI datatypes. The library optimizes the datatype representation and uses the LLVM framework to produce vectorized machine code for each datatype at commit time. We show several examples of how MPI datatype pack functions benefit from runtime compilation and analyze the performance of compiled pack functions for the data access patterns in many applications. We show that the pack/unpack functions generated by our packing library are seven times faster than those of prevalent MPI implementations for 73% of the datatypes used in MILC and in many cases outperform manual pack loops.

Documents

download slides:

BibTeX

@misc{hoefler-llvm-keynote-sc14,
  author={Torsten Hoefler},
  title={{A case for runtime recompilation in HPC}},
  year={2014},
  month={Nov.},
  location={New Orleans, Louisiana, USA},
  source={http://www.unixer.de/~htor/publications/},
}


serving: 18.225.72.161:53060	© Torsten Hoefler