Skip to content

Releases: saadrahim/rocSOLVER

rocSOLVER-3.12.0 for ROCm 4.2.0

10 May 23:13
124b3bc
Compare
Choose a tag to compare

Added

  • Multi-level logging functionality
  • Implementation of the Thin-SVD algorithm
  • Reductions of generalized symmetric- and hermitian-definite eigenproblems:
    • SYGS2, SYGST (with batched and strided_batched versions)
    • HEGS2, HEGST (with batched and strided_batched versions)
  • Symmetric and hermitian matrix eigensolvers:
    • SYEV (with batched and strided_batched versions)
    • HEEV (with batched and strided_batched versions)
  • Generalized symmetric- and hermitian-definite eigensolvers:
    • SYGV (with batched and strided_batched versions)
    • HEGV (with batched and strided_batched versions)

Optimizations

Changed

  • Sorting method in STERF as original quick-sort was failing for large sizes.

Removed

  • Removed hcc compiler support

Fixed

  • Fixed GELS overwriting B even when info != 0
  • Error when calling STEQR with n=1 from batched routines
  • Added roc::rocblas to the roc::rocsolver CMake usage requirements
  • Added rocblas to the dependency list of the rocsolver deb and rpm packages

Known Issues

  • Thin-SVD implementation is failing in some cases (in particular m=300, n=120) due to a possible bug in the gemm_batched routines of rocBLAS.

rocSOLVER-3.9.0 for ROCm 4.1.0

23 Mar 01:06
862b24e
Compare
Choose a tag to compare

Added

  • Eigensolver routines for symmetric/hermitian matrices:
    STERF, STEQR
  • Linear solvers for general non-square systems:
    GELS (API added with batched and strided_batched versions. Only the overdetermined non-transpose case is implemented in this release. Other cases will return rocblas_status_not_implemented status for now.)
  • Extended test coverage for functions returning info
  • Changelog file
  • Tridiagonalization routines for symmetric and hermitian matrices:
    LATRD
    SYTD2, SYTRD (with batched and strided_batched versions)
    HETD2, HETRD (with batched and strided_batched versions)
  • Sample code and unit test for unified memory model/Heterogeneous Memory Management (HMM)

Optimizations

  • Improved performance of LU factorization of small and mid-size matrices (n >= 2048)

Changed

  • Raised minimum requirement for building rocSOLVER from source to CMake 3.8
  • Switched to use semantic versioning for the library
  • Enabled automatic reallocation of memory workspace in rocsolver clients

Removed

  • Removed -DOPTIMAL from the roc::rocsolver CMake usage requirements. This is an internal rocSOLVER definition, and does not need to be defined by library users

Fixed

  • Fixed runtime errors in debug mode caused by incorrect kernel launch bounds
  • Fixed complex unit test bug caused by incorrect zaxpy function signature
  • Eliminated a small memory transfer that was being done on the default stream
  • Fixed GESVD right singular vectors for 1x1 matrices

Known Issues

  • None

rocSOLVER-3.9.0 for ROCm 4.1.0

23 Mar 00:54
862b24e
Compare
Choose a tag to compare

New Features
Added

  • Eigensolver routines for symmetric/hermitian matrices:
    STERF, STEQR
  • Linear solvers for general non-square systems:
    GELS (API added with batched and strided_batched versions. Only the overdetermined non-transpose case is implemented in this release. Other cases will return rocblas_status_not_implemented status for now.)
  • Extended test coverage for functions returning info
  • Changelog file
  • Tridiagonalization routines for symmetric and hermitian matrices:
    LATRD
    SYTD2, SYTRD (with batched and strided_batched versions)
    HETD2, HETRD (with batched and strided_batched versions)
  • Sample code and unit test for unified memory model/Heterogeneous Memory Management (HMM)

Optimizations

  • Improved performance of LU factorization of small and mid-size matrices (n > 2048)

Changed

  • Raised minimum requirement for building rocSOLVER from source to CMake 3.8
  • Switched to use semantic versioning for the library
  • Enabled automatic reallocation of memory workspace in rocsolver clients

Removed

  • Removed -DOPTIMAL from the roc::rocsolver CMake usage requirements. This is an internal rocSOLVER definition, and does not need to be defined by library users

Fixed

  • Fixed runtime errors in debug mode caused by incorrect kernel launch bounds
  • Fixed complex unit test bug caused by incorrect zaxpy function signature
  • Eliminated a small memory transfer that was being done on the default stream
  • Fixed GESVD right singular vectors for 1x1 matrices

Known Issues

  • None

rocSOLVER-3.9.0 for ROCm 3.9.0

27 Oct 20:05
c2cd214
Compare
Choose a tag to compare

New Features

  • Added Singular Value Decomposition (SVD)
  • Added QL factorization
  • Improved batch functionality by enabling use of rocBLAS bacthed functions
  • Improved unit test robustness
  • Added option to build documentation from source
  • Other improvements to code and library infrastructure

Known Issues

  • None

rocSOLVER-3.6.0 for ROCm 3.7.0

15 Aug 04:20
198e32e
Compare
Choose a tag to compare

New Features

  • bidiagonalization of general matrices
  • optimizations to LU factorization

Known Issues

  • None

rocSOLVER-3.6.0 for ROCm 3.7.0

15 Aug 04:17
198e32e
Compare
Choose a tag to compare

New Features

  • bidiagonalization of general matrices
  • optimizations to LU factorization

Known Issues

  • None

rocSOLVER-3.6.0 for ROCm 3.6.0

10 Jul 23:15
198e32e
Compare
Choose a tag to compare

New Features

  • bidiagonalization of general matrices
  • optimizations to LU factorization

Known Issues

  • None

rocSOLVER-3.6.0 for ROCm 3.6.0

10 Jul 23:13
198e32e
Compare
Choose a tag to compare

New Features

  • bidiagonalization of general matrices
  • optimizations to LU factorization

Known Issues

  • None

rocSOLVER-3.6.0 for ROCm 3.6.0

10 Jul 23:07
198e32e
Compare
Choose a tag to compare

New Features

  • bidiagonalization of general matrices
  • optimizations to LU factorization

Known Issues

  • None

rocSOLVER-3.6.0 for ROCm 3.6.0

10 Jul 23:03
198e32e
Compare
Choose a tag to compare

New Features

  • bidiagonalization of general matrices
  • optimizations to LU factorization

Known Issues

None