Parallelizing doolittle algorithm using TBB

Abstract

This paper presents a different approach for parallelizing the Doolittle Algorithm with the help of Intel Threading Building Blocks (TBB) allowing the users to utilize the power of multiple cores present in the modern CPUs. Parallel Doolittle Algorithm (PDA) has been divided into 3 parts: Decomposing the data, Parallely processing the data, finally Composing the data. Using the PDA we can solve the linear system of equations in considerably lesser amount time as compare to Serial Doolittle Algorithm (SDA). The PDA has been implemented in C++ using TBB library which makes it highly efficient, cross-platform compatible, and scalable. The efficiency of PDA over SDA has been verified by comparing the running time on different order of matrices. Experiments proved that PDA outperformed SDA by utilizing all the cores present in the CPU.