Denis Demidov

MINRES implementation

2

See #144. An interesting discussion: - [minres vs gmres](https://lists.mcs.anl.gov/pipermail/petsc-users/2011-March/008101.html) Reference implementations: - [scipy](https://github.com/scipy/scipy/blob/v1.4.1/scipy/sparse/linalg/isolve/minres.py#L11-L343) - [petsc](https://www.mcs.anl.gov/petsc/petsc-current/src/ksp/ksp/impls/minres/minres.c.html)

Look into using nvrtc for just-in-time cuda compilation

2

NVRTC is a runtime compilation library for CUDA C++. It accepts CUDA C++ source code in character string form and creates handles that can be used to obtain the PTX:...

Dense matrix support

18

Providing dense matrix support for VexCL would probably be of use for many people, but currently it is unclear what is the best approach to do this. Options are: 1....

See gregvw/chebyshev-gpu#5.

Look into the possibility of unified design for different matrix storage schemes and inter-GPU transfers. It should also be possible to accept host matrices in formats other than CSR (e.g....

Sets of builtin functions are different for OpenCL and CUDA.

See discussion in #49

Unit tests for universal API

2

See the head of the discussion here: https://github.com/ddemidov/ev3dev-lang-python-1/commit/92828ecf6061b8e5f0a65664eb86082874b5ee89#commitcomment-14064704. To keep the issue self contained: @ddemidov: > Note that I did not actually test this on ev3. Creating a Device on...