# Optimizing Xeon Phi for Interactive Data Analysis

## TL;DR

This paper evaluates how to optimize Xeon Phi for interactive data analysis by tuning settings like OpenMP and memory modes, achieving up to 66% of peak performance in matrix operations.

## Contribution

It provides detailed performance results and tuning guidelines for Xeon Phi in data analysis environments like Matlab and Octave.

## Key findings

- Achieved 66% of practical peak performance in matrix multiplication.
- Optimal settings include KMP_AFFINITY, taskset pinning, and all2all cache mode.
- Performance improvements enabled real-world application success.

## Abstract

The Intel Xeon Phi manycore processor is designed to provide high performance matrix computations of the type often performed in data analysis. Common data analysis environments include Matlab, GNU Octave, Julia, Python, and R. Achieving optimal performance of matrix operations within data analysis environments requires tuning the Xeon Phi OpenMP settings, process pinning, and memory modes. This paper describes matrix multiplication performance results for Matlab and GNU Octave over a variety of combinations of process counts and OpenMP threads and Xeon Phi memory modes. These results indicate that using KMP_AFFINITY=granlarity=fine, taskset pinning, and all2all cache memory mode allows both Matlab and GNU Octave to achieve 66% of the practical peak performance for process counts ranging from 1 to 64 and OpenMP threads ranging from 1 to 64. These settings have resulted in generally improved performance across a range of applications and has enabled our Xeon Phi system to deliver significant results in a number of real-world applications.