Merge branch 'yohann/cuda-non-tensor' [PR #249]

* yohann/cuda-non-tensor:
ceed-cuda: resolve -Wsign-compare for CUresult (unsigned enum) in CeedError
make style.
namespace cuda backends functi

Merge branch 'yohann/cuda-non-tensor' [PR #249]

* yohann/cuda-non-tensor:
ceed-cuda: resolve -Wsign-compare for CUresult (unsigned enum) in CeedError
make style.
namespace cuda backends functions.
Minor: styling
Add CUDA_LIB_DIR_STUBS for systems that don't have CUDA drivers installed
make style
Remove useless function declaration.
Add a reference non-tensor BasisApply for cuda backends.

show more ...

Fix underinterpolation mode for /cpu/self backends

Makefile: add search for testing

The search argument works with make test, prove, and junit targets.

Remove "eval" code that was breaking parallel testing with -libceed_test.

Update t208-f to use offset

Add ElemRestrictionApplyBlock

Add a reference non-tensor BasisApply for cuda backends.

Add t110-vec, set vec from another vec

Add offset parameter in Fortran VecSetArray

Add juint exception

Add t109-vec-f

Adds a Vector unit test using CEED_MEM_DEVICE.

Restore t308-f

Modify t001 to remove clang warning

Add CeedGetPreferredMemType

junit.py: update test logic for skipped and intended-fail tests

junit.py: subprocess.run compatibility for python3.5

junit.py: avoid f-strings to support python3.5

Add junit target and report test results to Azure

junit-xml: avoid "six", which may not be installed

Merge commit '71c263ca3a3ce57731d1f7a04e93e4c31116f80b' as 'tests/junit-xml'

Simple Cuda backend using one thread per element (#195)

Thanks-to: Jeremy Thompson

* Take into account the compute capability of the GPU

* Add the cuda/reg backend and rename cuda to cuda/ref.

Simple Cuda backend using one thread per element (#195)

Thanks-to: Jeremy Thompson

* Take into account the compute capability of the GPU

* Add the cuda/reg backend and rename cuda to cuda/ref.

- cuda/reg uses a simple approach where each element is
processed by one thread. This approach is expected to be
efficient for 1D and 2D problems, but very ineficient
as soon as the kernels start to spill, which should arise
around Q1D=4 for 3D problems.

* Compilation takes into account the deviceId

* Make style

* Remove dead code in cuda qFunctions.

* Cuda-reg specialized Restriction.

* Split the Prolongation operator into Identity/not Identity.

* Remove "#pragma unroll" until further perf investigation.

* README update

* Add a description of cuda/reg.

* Add CompositeOperator msg to CUDA backends

show more ...

Operator Composition (#197)

* Composite Operator for cpu/self family of backends

* Remove small leak

* Improve C tests

* Add composite operator to Fortran interface and tests

* Fix Fortr

Operator Composition (#197)

* Composite Operator for cpu/self family of backends

* Remove small leak

* Improve C tests

* Add composite operator to Fortran interface and tests

* Fix Fortran test missing destroys

* Fortran test okl files, currently not used

* fix error in composite ' add' flag logic

* Switch composite op tests to f90

* Check for operator type on utility functions

* Documentation and test cleanup

* Make Style

show more ...

CeedBasisApply check (#208)

* Add check to verify input/ouput vector lengths compatibility with basis

* Added test for CeedBasisApply and updated tap.sh to pass failure

* Updated check and tap

CeedBasisApply check (#208)

* Add check to verify input/ouput vector lengths compatibility with basis

* Added test for CeedBasisApply and updated tap.sh to pass failure

* Updated check and tap.sh

show more ...

Add Nek to Travis (#169)

* Add test mode to Nek BP1 and BP3, improve Nek BPs

* Fix OCCA identity rst for multifield, minor NekBP1 fix

* Improve Nek run script

* Add Nek5K to prove-all

*

Add Nek to Travis (#169)

* Add test mode to Nek BP1 and BP3, improve Nek BPs

* Fix OCCA identity rst for multifield, minor NekBP1 fix

* Improve Nek run script

* Add Nek5K to prove-all

* Update travis yml for Nek5K

* Make style

* Adjust Travis yml

* Combine Nek run bash scripts

* Minor Nek script improvements

* Update to Nek 18.0 and reduce number of Nek compiler warnings

* Document required Nek5k version

* Remove stray command

* Remove extra file

* Adapt Nek for CUDA backend

* Fix Nek script string comparison

* Modify Nek script for better exit codes

* typo fix

* Modify the CU function names in nek/bp1.cu and nek/bp3.cu

* .cu file consistency

* Tidy Travis

* Tidy Travis

* Operator fixes

show more ...

Switch tests to .f90 extension