# AMD Core Math Library

> Mediated Wiki article. Canonical URL: https://mediated.wiki/source/AMD_Core_Math_Library
> Markdown URL: https://mediated.wiki/source/AMD_Core_Math_Library.md
> Source: https://en.wikipedia.org/wiki/AMD_Core_Math_Library
> Source revision: 1320410337
> License: Creative Commons Attribution-ShareAlike 4.0 International (https://creativecommons.org/licenses/by-sa/4.0/)

**AMD Core Math Library** (**ACML**) is an end-of-life[1] [software development](/source/Software_development) library released by [AMD](/source/AMD), replaced by many open source libraries, including AMD libm 4.0. This library provides mathematical routines optimized for AMD processors.

The successor to ACML is the **AMD Optimizing CPU Libraries** (**AOCL**), a set of mostly [open source](/source/Open_source) libraries compiled for [AMD64](/source/AMD64) processors. It includes optimized open source forks of various projects including [BLIS](/source/BLIS_(software)), [libFLAME](/source/LAPACK#Implementations), [ScaLAPACK](/source/ScaLAPACK), and [FFTW](/source/Fastest_Fourier_Transform_in_the_West). It also offers various new open source solutions including AOCL-Sparse which implements sparse linear algebra, the AOCL-LibM math library, and AOCL-LibMem which implements [memcpy](/source/Memcpy) and similar functions. The AOCL RNG random number generation library is closed source.[2]

## Features

ACML consists of the following main components:[3]

- A full implementation of Level 1, 2 and 3 [Basic Linear Algebra Subprograms](/source/Basic_Linear_Algebra_Subprograms) (BLAS), with optimizations for AMD Opteron processors.

- A full suite of [Linear Algebra](/source/Linear_Algebra) ([LAPACK](/source/LAPACK)) routines.

- A comprehensive suite of [Fast Fourier transform](/source/Fast_Fourier_transform) (FFTs) in single-, double-, single-complex and double-complex data types.

- Fast scalar, vector, and array math transcendental library routines

- [Random Number Generators](/source/Random_Number_Generator) in both single- and double-precision

## Supported platforms

AMD offers pre-compiled binaries for [Linux](/source/Linux), [Solaris](/source/Solaris_(operating_system)), and [Windows](/source/Microsoft_Windows) available for download. Supported compilers include [GNU Fortran](/source/GNU_Fortran), [Intel Fortran Compiler](/source/Intel_Fortran_Compiler), [Microsoft Visual Studio](/source/Microsoft_Visual_Studio), [NAG](/source/Numerical_Algorithms_Group), [PathScale](/source/PathScale), [PGI compiler](/source/PGI_compiler), and [Sun Studio](/source/Sun_Studio_(software)).[4]

## License

ACML has a proprietary [freeware](/source/Freeware) license. The library is distributed in binary form free of charge, but cannot be freely redistributed.[5][6]

## See also

- [GPUOpen](/source/GPUOpen) – Open-source software suite for visual effects, HPC, and GPGPU

- Framewave – formerly the AMD Performance Library

- [Open64](/source/Open64) – AMD has an Open64 compiler distribution that can be used with ACML

- [Math Kernel Library](/source/Math_Kernel_Library) (MKL)

## References

1. **[^](#cite_ref-1)** [AMD Core Math Library Product Features](https://developer.amd.com/tools-and-sdks/archive/acml-product-features/)[*[dead link](https://en.wikipedia.org/wiki/Wikipedia:Link_rot)*]

1. **[^](#cite_ref-2)** ["AMD Optimizing CPU Libraries (AOCL)"](https://developer.amd.com/amd-aocl/). *AMD*.

1. **[^](#cite_ref-AMD-Core-Math-Library-dotcom_3-0)** ["ACML"](https://web.archive.org/web/20141015020116/http://developer.amd.com/tools-and-sdks/cpu-development/amd-core-math-library-acml/). Archived from [the original](http://developer.amd.com/tools-and-sdks/cpu-development/amd-core-math-library-acml/) on 2014-10-15. Retrieved 2014-10-19.

1. **[^](#cite_ref-4)** [ACML Downloads & Resources](https://developer.amd.com/tools-and-sdks/archive/acml-downloads-resources/)[*[dead link](https://en.wikipedia.org/wiki/Wikipedia:Link_rot)*]

1. **[^](#cite_ref-5)** [Redistribution Agreements](http://developer.amd.com/tools-and-sdks/cpu-development/amd-core-math-library-acml/acml-redistribution-agreements/) [Archived](https://web.archive.org/web/20141015020107/http://developer.amd.com/tools-and-sdks/cpu-development/amd-core-math-library-acml/acml-redistribution-agreements/) 2014-10-15 at the [Wayback Machine](/source/Wayback_Machine), ACML Redistribution Agreements

1. **[^](#cite_ref-6)** [ACML EULA](http://amd-dev.wpengine.netdna-cdn.com/wordpress/media/2012/10/ACML-EULA.pdf) [Archived](https://web.archive.org/web/20141221090252/http://amd-dev.wpengine.netdna-cdn.com/wordpress/media/2012/10/ACML-EULA.pdf) 2014-12-21 at the [Wayback Machine](/source/Wayback_Machine), End-user license agreement

## External links

- [Streaming Computing (User Guide)](https://web.archive.org/web/20081010124022/http://ati.amd.com/technology/streamcomputing/Stream_Computing_User_Guide.pdf)

- Replacement: [AMD Math Library (LibM)](https://www.amd.com/en/developer/aocl/libm.html), [github](https://github.com/amd/aocl-libm-ose)

v t e Numerical linear algebra Key concepts Floating point Numerical stability Problems System of linear equations Matrix decompositions Matrix multiplication (algorithms) Matrix splitting Sparse problems Hardware CPU cache TLB Cache-oblivious algorithm SIMD Multiprocessing Software ATLAS MATLAB Basic Linear Algebra Subprograms (BLAS) LAPACK Specialized libraries

---
Adapted from the Wikipedia article [AMD Core Math Library](https://en.wikipedia.org/wiki/AMD_Core_Math_Library) by Wikipedia contributors ([contributor history](https://en.wikipedia.org/wiki/AMD_Core_Math_Library?action=history)). Available under [Creative Commons Attribution-ShareAlike 4.0 International](https://creativecommons.org/licenses/by-sa/4.0/). Changes may have been made.
