High-Performance Computation of the Number of Nested RNA Structures with 3D Parallel Tiled Code

Many current bioinformatics algorithms have been implemented in parallel programming code. Some of them already reached the limits imposed by Amdahl’s law, but many can still be improved. In our paper, we present an approach allowing us to generate a high-performance code for calculating number RNA pairs. The allows tiled maximal dimension tiles, which discussed algorithm is 3D. Experiments carried out on two modern multi-core computers, Intel(R) Xeon(R) Gold 6326 (2.90 GHz, 2 physical units, 32 cores, 64 threads, 24 MB Cache) and i7(11700KF (3.6 8 16 Cache), demonstrate significant increase performance scalability generated For i7, target speedup increases linearly with threads. An presented paper used programmers other codes whose dependence patterns are similar those implementing counting algorithm.