Finally the 1.0.0 is out!
The DPLASMA layer provided supports all basic datatypes (s,d,z,c) for the following kernels:
- Linear Systems of Equations: Cholesky, LU (inc. pivoting and partial pivotin), LDL (prototype)
- Least Squares: QR & LQ; -- Parameterized QR (all possible trees) (factorization / generation of Q)
- Symmetric Eigenvalue Problem: Reduction to Band (prototype)
- Level 3 Tile BLAS: GEMM, TRSM, TRMM, HEMM/SYMM, HERK/SYRK, HER2K/SYR2K
Release Notes:
- Please visit the project wiki for more information about the compilation, installation, howto and FAQ.
- the GPU supports is enabled, but use at your own risk
- parameterized QR only supports cases where N and M are multiple of the tile size.
- MPI is required for distributed runs, HWLOC is required for hardware-aware features
Download version 1.0.0