Search

The complexity of combustion simulations demands the latest high-performance computing tools to accelerate its time-to-solution results. A current trend on HPC systems is the utilization of CPUs with SIMD or vector extensions to exploit data parallelism. Our work proposes a strategy to improve the automatic vectorization of finite-element-based scientific codes. The approach applies a parametric configuration to the data structures to help the compiler detect the block of codes that can take advantage of vector computation while maintaining the code portable. A detailed analysis of the computational impact of this methodology on the different stages of a CFD solver is studied on the PRECCINSTA burner simulation. Our parametric implementation has proven to help the compiler generate more vector instructions in the assembly operation: this results in a reduction of up to 9. 39 × of the total executed instruction maintaining constant the Instructions Per Cycle and the CPU frequency. The proposed strategy improves the performance of the CFD case under study up to 4. 67 × on the MareNostrum 4 supercomputer. • A parametric configuration of the CFD data structures is presented for enabling auto-vectorization. • A detailed performance analysis using different compilers is applied to a real CFD case. • A reduction of up to 9.39 times of the total executed instruction is attained, maintaining constant the IPC and the CPU frequency. • The proposed strategy accelerates up to 4.67 the PRECCINSTA burner simulation on the Marenostrum4 nodes. [ABSTRACT FROM AUTHOR]

This paper presents a load balancing strategy for reaction rate evaluation and chemistry integration in reacting flow simulations. The large disparity in scales during combustion introduces stiffness in the numerical integration of the PDEs and generates load imbalance during the parallel execution. The strategy is based on the use of the DLB library to redistribute the computing resources at node level, lending additional CPU-cores to higher loaded MPI processes. This approach does not require explicit data transfer and is activated automatically at runtime. Two chemistry descriptions, detailed and reduced, are evaluated on two different configurations: laminar counterflow flame and a turbulent swirl-stabilized flame. For single-node calculations, speedups of 2.3x and 7x are obtained for the detailed and reduced chemistry, respectively. Results on multi-node runs also show that DLB improves the performance of the pure-MPI code similar to single node runs. It is shown DLB can get performance improvements in both detailed and reduced chemistry calculations. • A load balancing strategy for reaction rate and chemistry integration is presented. • It uses the DLB library to redistribute the computational resources at node level. • Code hybridization improves the performance over MPI-pure implementations. • Single-node and multi-node tests show speedups in reacting flow calculations. [ABSTRACT FROM AUTHOR]