| e3fbde13 | 15-Jul-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - add macro to clean up cublasGetErrorName function |
| 58c385a5 | 15-Jul-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - separate CeedCudaGetCublasHandle logic as independent funtion |
| 48e4fcd3 | 02-Jul-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - add on device vector norms for CUDA backends |
| f323b5ac | 01-Jul-2020 |
Jeremy L Thompson <25011573+jeremylt@users.noreply.github.com> |
CUDA - add missing ierr =
Co-authored-by: Jed Brown <jed@jedbrown.org> |
| f4289877 | 30-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
Op - use CeedVectorTakeArray in backends to reset array access |
| 6a6c615b | 30-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
Vec - add CeedVectorTakeArray |
| af17f337 | 29-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - reorder backend priority, lower is better |
| e75c1c2d | 29-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
make tidy |
| 00fa3faa | 26-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - guard module unload for QFunctions |
| 1958eb7c | 26-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - fix small leaks |
| 3f1466f8 | 26-Jun-2020 |
Jeremy L Thompson <25011573+jeremylt@users.noreply.github.com> |
Merge pull request #561 from CEED/jeremy/is-deterministic
Ceed - add IsDeterministic |
| 5f67fade | 26-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
spellcheck |
| b6e6b856 | 24-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - use d_ and h_ prefix for diagonal assembly data arrays |
| 2cb544c1 | 23-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - convert diagonal assembly into device kernel |
| f2d44534 | 19-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - fix composite operator diagonal support |
| 868092e3 | 19-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - inital version of LinearAssemble* |
| 50dfd88a | 23-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - add some missing ierr = |
| 347d7e4c | 23-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - add small leak fix in QFunction JiT load |
| 7df94212 | 23-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - clean up includes |
| 73b3ccaf | 23-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
CUDA - clean up minor memory leak |
| 82253e48 | 15-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
make style |
| 80ac2e43 | 15-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
style - rename AssembleLinear* to LinearAssemble* |
| fd364f38 | 15-Jun-2020 |
Jeremy L Thompson <thompson.jeremy.luke@gmail.com> |
style - change Get*Status to Is* |
| b1d74153 | 12-Jun-2020 |
Jeremy L Thompson <25011573+jeremylt@users.noreply.github.com> |
CUDA/MAGMA - add AssembleLinearQFunction (#553)
* CUDA - refactor operator apply for CUDA assemble linear QF impl
* CUDA/MAGMA - add AssembleLinearQFunction
* make style
* CUDA - clean up a
CUDA/MAGMA - add AssembleLinearQFunction (#553)
* CUDA - refactor operator apply for CUDA assemble linear QF impl
* CUDA/MAGMA - add AssembleLinearQFunction
* make style
* CUDA - clean up assembleLinearQF after q/e layout refactor
* CUDA - fallback operator for cuda/gen to cuda/ref
* CUDA - use delegation for cuda/gen prefered memtype
show more ...
|
| 49fd234c | 12-Jun-2020 |
Jeremy L Thompson <25011573+jeremylt@users.noreply.github.com> |
Convert CUDA ref/reg/shared E-Layout (#554)
* tests - update tests for multiple e-layouts
* CUDA - convert ref and reg restrictions to Q-layout
* CUDA - ref/reg/shared use gen/magma E-Layout f
Convert CUDA ref/reg/shared E-Layout (#554)
* tests - update tests for multiple e-layouts
* CUDA - convert ref and reg restrictions to Q-layout
* CUDA - ref/reg/shared use gen/magma E-Layout for multi elememnt basis apply and operator apply
* CUDA/MAGMA - drop eandqdiffer and separate MAGMA operator code
* CUDA - update operator comment
* reg - clarify read/write dofs/quads
* CUDA - drop dead code
show more ...
|