Intel Xeon Phi coprocessors are the new family members of processors and platforms to the Intel family. Intel Xeon Phi is the first in the family of Intel MIC (Many Integrated Core) architecture. Software running on the coprocessor should leverage innumerable cores as well as make use of wide SIMD operation. Vectorization is the process of converting an algorithm from scalar implementation to vector. It is the form of parallel programming where the processors perform same operation simultaneously on N data elements of vector i.e. one dimensional array of scalar data objects such as floating point object , integers or double integers floating point. When the hardware is coupled with C/C++ compiler that supports it, developers have easier time delivering more efficient and better performing software.

Vectorization, Parallelism, High Performance Computing.

[1] S. Sawadsitang, K. Suankaewmanee, S. Kuo, B. Bhumiratne, “Interactive Computer Aided Code Vectorization”, 2012 Ninth International Joint conference on Computer Science and Software Engineering(JCSSE).
[2] Gil Raport, Ayal Zaks, Yosi Ben-Asher, “Streamlining Whole Function Vectorization in C using Higher Order Vector Semantics”, 2015 IEEE International Parallel and Distributed Processing Symposium Workshops.
[3] Xinmin Tian, Hideki Saito, Serguei V. Preis, Eric N. Garcia, Sergey S. Kozhukhov Matt Masten, Aleksei G. Cherkasov and Nikolay Panchenko ”Practical SIMD Vectorization Techniques for Intel Xeon Phi Coprocessors” 2013 IEEE 27th International Symposium on Parallel and Distributed Processing
[4] Juan M., Lasse Natvig, Jan C. Meyer,”Improving Energy Efficiency through Parallelization and Vectorization on Intel Core i5 and i7 processors”,SC Companion: High Performance Computing, Networking Storage and Analysis,2012.
[5] Hanbing Li,Isabelle Puaut, Erven Rohou ”Tracing Flow Information for Tighter WCET Estimation: Application to Vectorization” 2015 IEEE 21st International Conference on Embedded and Real-Time Computing Systems and Applications
[6] Ralf Karrenberg, Sebastian Hack “Whole-Function Vectorization” 978-1-61284-357-5/11/2011 IEEE
[7] O. Krzikalla1, K. Feldhoff1, R. Mller-Pfefferkorn1 andWolfgang E. Nagel1 Auto-Vectorization Techniques for modern SIMD architecture
[8] Ilan Baron,A Practical Parallel Algorithm for Solving Band Symmetric Positive Definite Systems of Linear Equations, ACM Transactions on Mathematical Software (TOMS), 323-332, Dec 1987.
[9] J. Jeffers and J. Reinders. Intel Xeon Phi Co-Processor High Performance Programming.
[10] P. Gavali, M. Shah, Gauri Kadam, Earthquake simulationof large scale structures using OpenSEES software on-grid and high performance computing in India,Earthquake simulation of large scale structures using OpenSEES software on Grid and high performance computing in India, Beijing, China,Oct 2008
[11] P. Gavali, M. Shah, Gauri Kadam, Kranti Meher, “Seismic response and simulations of reinforced concrete bridge using OpenSEES on high performance computing, CSI Transaction on ICT, Sep 2013.
[12] Chenggang Lal,Zhijun Hao,, Miaoquing Huang, Comparison of parallel programming Models on Intel MIC computer cluster, Parallel and Distributed Processing Symposium Workshop (IPDPSW),2014 IEEE International.
[13] https://software.intel.com/enus/articles/vectorizationessential
[14] https://software.intel.com/enus/articles/optimization-and- performance-tuning-for-intel-xeon-phi-coprocessors-part-1-optimization
[15] https://software.intel.com/en-us/articles/intel-xeonphi-coprocessors-performance-snapshot-on-cdac-cluster
[16] https://software.intel.com/enus/articles/theimportance-
of-vectorization-for-intel-many-integratedcore-architecture-intel-mic