Difference between revisions of "GPU621/MKL"
(Created page with "= Intel Math Kernel Library = == Overview == This project aims to explore the Intel Math Kernel Library and find out how it functions, its efficiency, as well as its advant...") |
(→What is Math Kernel Library?) |
||
Line 12: | Line 12: | ||
- Linear algebra | - Linear algebra | ||
+ | |||
- Fast Fourier transformations | - Fast Fourier transformations | ||
+ | |||
- Vectorization and matrix operations | - Vectorization and matrix operations | ||
+ | |||
- Eigenvalue calculations | - Eigenvalue calculations | ||
+ | |||
- Random number generation | - Random number generation | ||
+ | |||
MKL has seen use in the real world by handling data sets from a wide range of sources resulting in benefits such as assisting in applying machine learning techniques to large data sets and reducing the usage of energy in office buildings. | MKL has seen use in the real world by handling data sets from a wide range of sources resulting in benefits such as assisting in applying machine learning techniques to large data sets and reducing the usage of energy in office buildings. | ||
− | |||
== Installation/Setup == | == Installation/Setup == |
Revision as of 14:25, 30 November 2022
Contents
Intel Math Kernel Library
Overview
This project aims to explore the Intel Math Kernel Library and find out how it functions, its efficiency, as well as its advantages and disadvantages when utlized in the real world. This will be accomplished through an examination of how to include and apply Math Kernel Library functionality to a program, and the resulting effect on computational efficiency.
What is Math Kernel Library?
Released on May 9, 2003, Intel's oneAPI Math Kernel Library, also known as Intel oneMKL or Intel MKL, is a library tailored towards the optimization of numerical computation in the fields such as science, engineering and finance. MKL functions by parallelizing computation routines processing on both the CPU and GPU. The library provides functionality improvements for calculations including:
- Linear algebra
- Fast Fourier transformations
- Vectorization and matrix operations
- Eigenvalue calculations
- Random number generation
MKL has seen use in the real world by handling data sets from a wide range of sources resulting in benefits such as assisting in applying machine learning techniques to large data sets and reducing the usage of energy in office buildings.
Installation/Setup
Follow the steps listed below in order to include Math Kernel Library functionality to a program. Alternatively Intel's MKL Get Started Guide can be referenced
In this case we will be using the online installer provided by Intel, support for offline installation and installation via packet managers is also available, for example NuGet Package Manager on Visual Studio.
1. Download MKL
2. Open installer
3. Follow installer instructions
4. Access project properties in VS
5. Enable usage of MKL
6. Include MKL header file "mkl.h"
Installing and compiling on Linux or macOS may require additional steps such as linking code.