The Intel® Xeon Phi architecture from Intel Corporation features parallelism at the level of many x86-based cores, multiple threads per core, and vector processing units. Lattice Quantum Chromodynamics (LQCD) is of importance in studies of nuclear and high energy physics and MPI-HMMER is an open source MPI implementation of the HMMR protein analysis suite and important to life science research. Technical experts at Intel describe the process and experience with optimizing key kernels for the Intel® Xeon Phi™ coprocessor and to achieve performance on the applications with the addition of an Intel® Xeon Phi™ coprocessor over a Intel® Xeon E5 system.
Porting and Tuning of Lattice QCD & MPI-HMMER for Intel® Xeon® Processors & Intel® Xeon Phi™ Coprocessors
For more complete information about compiler optimizations, see our Optimization Notice.