Copyright (C) 2025 Advanced Micro Devices, Inc. All rights reserved.

Copyright (C) 2014, The University of Texas at Austin

AOCL-LAPACK library - Release Notes - version 5.1.0
--------------------------------------------------------------------------------
AOCL-LAPACK is a high performant implementation of Linear Algebra PACKage 
(LAPACK). LAPACK provides routines for solving systems of linear equations, 
least-squares problems, eigenvalue problems, singular value problems, and the 
associated matrix factorizations. It is extensible, easy to use, and available 
under an open-source license. AOCL-LAPACK is a C-only implementation. 
Applications relying on standard Netlib LAPACK interfaces can utilize 
AOCL-LAPACK with virtually no changes to their source code.
In combination with the AOCL-BLAS library, which includes optimizations for the 
AMD “Zen”-based processors, AOCL-LAPACK enables running high performing LAPACK 
functionalities on AMD platforms. AOCL-LAPACK supports C, FORTRAN, and C++ 
template interfaces (for a subset of APIs) for the LAPACK APIs.

Highlights of AMD optimized AOCL-LAPACK 5.1.0
--------------------------------------------------------------------------------
• Improved performance of the following APIs.
  • Eigen Value and SVD(DSYEVD and DGESDD).
  • LU Factorization (DGETRF).
  • LU Banded matrix factorization(DGBTRF) and DORGQR.
  • Least Square solver(ZGELS).
• Upgraded to Netlib LAPACK 3.12.0 specification that includes 6 new APIs, bug 
  fixes, and improvements to the existing APIs.
• Updated CMake compiler flags and presets, and enhanced pkg-config for better 
  build configuration.
• Enhanced AOCL_ROOT variable usage for dependent library paths.
• Removed outdated netlib-test folders.
• Bug fixes.
  • Fixed windows build warnings and a corner case test failure in the 
    hetri_rook API.
  • Resolved precision error in AOCL LAPACK's dgels and fixed extreme value 
    test failure in DGESVD.
  • Addressed QZ convergence failure in DLARTG.
  • Fixed Tau value computation in SYTRD and accuracy issues in GEJSV.
  • Addressed build warnings.
• Test suite framework enhancements.
  • Support for C++ interface API tests.
  • 9 new test cases added including hetrf, GETRFNPI, sygvd and lange.
  • Improved test output display.

Please refer AOCL User Guide for supported Operating Systems and Compilers.

The package contains AOCL-LAPACK Library binaries which includes optimizations 
for the AMD EPYC and AMD Ryzen processor families, header files and examples.

Note: 
1. AOCL-LAPACK 4.1.0 has dependency on libstdc++ library. On Linux, user must 
   link libstdc++(-lstdc++) when AOCL-LAPACK library is used.
2. From 4.1.0 release onwards, AOCL-LAPACK depends on Python 3.x as a 
   prerequisite. Python 2.x is no longer supported.
3. The pre-built AOCL-LAPACK binaries are compiled with ENABLE_AOCL_BLAS 
   option. Hence applications must link with AOCL-BLAS when using prebuilt 
   AOCL-LAPACK library.

Known Issues
--------------------------------------------------------------------------------
1. Numerical failures in few Netlib LAPACK tests for complex datatype routines.
