AMD Core Math Library - optimized and threaded math routines for compute-intensive applications.

ACML End of Life Notice: We have transitioned our math libraries from a proprietary, closed source codebase (ACML) to open source solutions, providing developers with a set of open source libraries targeted to those who want to  accelerate computations on GPUs, APUs and CPUs. Please visit GPUOpen.com to learn more.

AMD Core Math Library, or ACML, provides a free set of thoroughly optimized and threaded math routines for HPC, scientific, engineering and related compute-intensive applications. ACML is ideal for weather modeling, computational fluid dynamics, financial analysis, oil and gas applications and more. ACML consists of the following main components:

1) A full implementation of Level 1, 2 and 3 Basic Linear Algebra Subroutines (BLAS), with key routines optimized for high performance on AMD Opteron™ processors.  The BLAS level 3 routines will take advantage of heterogeneous computing through OpenCL if detected.

2) A full suite of Linear Algebra (LAPACK) routines. As well as taking advantage of the highly-tuned BLAS kernels, a key set of LAPACK routines has been further optimized to achieve considerably higher performance than standard LAPACK implementations.

3) Beginning version 6 of ACML, a subset of FFTW interfaces are supported for Fourier transform functionality. Heterogeneous compute with GPU/APU and OpenCL is supported through the FFTW interfaces. A comprehensive set of FFTs through ACML specific API (found in version 5 and older) continues to be available in version 6.

4) Random Number Generators in both single- and double-precision.