hipSOLVER Compatibility API#
Currently, this API document only provides the method signatures for the wrapper functions that are currently implemented in hipSOLVER. For a complete description of the functions’ behavior and arguments, see the corresponding backends’ documentation at cuSOLVER API and/or rocSOLVER API.
For ease of porting from existing cuSOLVER applications to hipSOLVER, functions in hipSOLVER’s compatibility API are designed to have method signatures that are consistent with the cusolverDn interface. However, performance issues may arise when using the rocSOLVER backend due to differing workspace requirements. Therefore, users interested in achieving the best performance with the rocSOLVER backend should consult the regular API documentation, and transition from the compatibility API to the regular API at the earliest convenience. Please refer to the user guide for additional considerations regarding the use of the regular API.
- Types
- Helper Functions
- Handle set-up and tear-down
- Stream manipulation
- Gesvdj parameter manipulation
- Syevj parameter manipulation
- LAPACK Auxiliary Functions
- Orthonormal matrices
- hipsolverDn<type>orgbr_bufferSize()
- hipsolverDn<type>orgbr()
- hipsolverDn<type>orgqr_bufferSize()
- hipsolverDn<type>orgqr()
- hipsolverDn<type>orgtr_bufferSize()
- hipsolverDn<type>orgtr()
- hipsolverDn<type>ormqr_bufferSize()
- hipsolverDn<type>ormqr()
- hipsolverDn<type>ormtr_bufferSize()
- hipsolverDn<type>ormtr()
- Unitary matrices
- hipsolverDn<type>ungbr_bufferSize()
- hipsolverDn<type>ungbr()
- hipsolverDn<type>ungqr_bufferSize()
- hipsolverDn<type>ungqr()
- hipsolverDn<type>ungtr_bufferSize()
- hipsolverDn<type>ungtr()
- hipsolverDn<type>unmqr_bufferSize()
- hipsolverDn<type>unmqr()
- hipsolverDn<type>unmtr_bufferSize()
- hipsolverDn<type>unmtr()
- Orthonormal matrices
- LAPACK Functions
- Triangular factorizations
- Orthogonal factorizations
- Problem and matrix reductions
- Linear-systems solvers
- Least-squares solvers
- Symmetric eigensolvers
- hipsolverDn<type>syevd_bufferSize()
- hipsolverDn<type>heevd_bufferSize()
- hipsolverDn<type>syevd()
- hipsolverDn<type>heevd()
- hipsolverDn<type>syevdx_bufferSize()
- hipsolverDn<type>heevdx_bufferSize()
- hipsolverDn<type>syevdx()
- hipsolverDn<type>heevdx()
- hipsolverDn<type>syevj_bufferSize()
- hipsolverDn<type>heevj_bufferSize()
- hipsolverDn<type>syevjBatched_bufferSize()
- hipsolverDn<type>heevjBatched_bufferSize()
- hipsolverDn<type>syevj()
- hipsolverDn<type>heevj()
- hipsolverDn<type>syevjBatched()
- hipsolverDn<type>heevjBatched()
- hipsolverDn<type>sygvd_bufferSize()
- hipsolverDn<type>hegvd_bufferSize()
- hipsolverDn<type>sygvd()
- hipsolverDn<type>hegvd()
- hipsolverDn<type>sygvdx_bufferSize()
- hipsolverDn<type>hegvdx_bufferSize()
- hipsolverDn<type>sygvdx()
- hipsolverDn<type>hegvdx()
- hipsolverDn<type>sygvj_bufferSize()
- hipsolverDn<type>hegvj_bufferSize()
- hipsolverDn<type>sygvj()
- hipsolverDn<type>hegvj()
- Singular value decomposition
- LAPACK-like Functions
- Symmetric eigensolvers
- hipsolverDn<type>syevdx_bufferSize()
- hipsolverDn<type>heevdx_bufferSize()
- hipsolverDn<type>syevdx()
- hipsolverDn<type>heevdx()
- hipsolverDn<type>syevj_bufferSize()
- hipsolverDn<type>heevj_bufferSize()
- hipsolverDn<type>syevjBatched_bufferSize()
- hipsolverDn<type>heevjBatched_bufferSize()
- hipsolverDn<type>syevj()
- hipsolverDn<type>heevj()
- hipsolverDn<type>syevjBatched()
- hipsolverDn<type>heevjBatched()
- hipsolverDn<type>sygvdx_bufferSize()
- hipsolverDn<type>hegvdx_bufferSize()
- hipsolverDn<type>sygvdx()
- hipsolverDn<type>hegvdx()
- hipsolverDn<type>sygvj_bufferSize()
- hipsolverDn<type>hegvj_bufferSize()
- hipsolverDn<type>sygvj()
- hipsolverDn<type>hegvj()
- Singular value decomposition
- Symmetric eigensolvers