Portable performance optimizations based on a performance history of the fusion microturbulence code GYRO

ABSTRACT

We will show the performance history of the fusion code GYRO on two diverse architectures, namely a Cray XT3 and a Cray X1E. The history shows performance of selected versions of GYRO for two standard benchmarks. For this comparison, we choose one compiler version on each machine and keep it constant for all the tests and run the tests over a short time frame for consistency. We will present Cray X1E and Cray XT3 results; we expect to present dual-core XT3 results as well, time-permitting, following an upgrade this summer. The contribution of this work will be a summary of the performance enhancements that are portable to three classes of machines: vector, scalar, and multi-core scalar. Getting good performance on modern HPC systems is more than just finding the right compiler options. Knowing what performance optimizations are portable across a variety of machines is essential.

INDEX TERMS

Primary Classification:
  D. Software
  D.3 PROGRAMMING LANGUAGES
      D.3.4 Processors
          Subjects: Optimization

Additional Classification:
  C. Computer Systems Organization
  C.5 COMPUTER SYSTEM IMPLEMENTATION
      C.5.1 Large and Medium ("Mainframe") Computers

  D. Software
  D.3 PROGRAMMING LANGUAGES
      D.3.4 Processors
          Subjects: Compilers; Run-time environments

General Terms:
Design, Performance