A Migration Method of MPI Program Combining Local Library Replacement and Instruction Translation

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Test cases</td><td class="align_center">Explanation</td><td class="align_center">Correctness</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">IMB-MPI1</td><td class="align_center">MPI-1 functions</td><td class="align_center">100%</td></tr><tr><td class="align_left">IMB-EXT</td><td class="align_center">One-way interaction capabilities in MPI-2</td><td class="align_center">100%</td></tr><tr><td class="align_left">IMB-NBC</td><td class="align_center">Interaction overlapping nonblocking MPI-3 functions</td><td class="align_center">100%</td></tr><tr><td class="align_left">IMB-RMA</td><td class="align_center">Remote memory access</td><td class="align_center">100%</td></tr><tr><td class="align_left">NPB-IS</td><td class="align_center">Two-dimensional large integer order base on the bucket sort</td><td class="align_center">100%</td></tr><tr><td class="align_left">NPB-CG</td><td class="align_center">The best feature of large sparse symmetric positive definite matrix approximation</td><td class="align_center">100%</td></tr><tr><td class="align_left">NPB-EP</td><td class="align_center">Test float computing</td><td class="align_center">100%</td></tr><tr><td class="align_left">NPB-FT</td><td class="align_center">Discrete Fourier transform 3D problem</td><td class="align_center">100%</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Test cases and the result of correctness test.

Mathematical Problems in Engineering

tab2

Table 2

Table 2: A Migration Method of MPI Program Combining Local Library Replacement and Instruction Translation 