- Nov 26, 2019
-
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
Commented out checking for head and tail of warpList, as they don't contain values, they're just marks to the end of the list.
-
Lukas Cejka authored
-
Lukas Cejka authored
Preliminary templating of WarpInfo and WarpList. Preliminary fix of mistake where WarpList would loop infinitely. Added checkpoints. Committing for backup purposes.
-
Lukas Cejka authored
-
Lukas Cejka authored
addWarp( const int, const int, const int, const int * ) takes int, but in balanceLoad is given IndexType!! recast or rewrite warp list/info using IndexType?
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
Lukas Cejka authored
-
- Nov 08, 2019
-
-
Jakub Klinkovský authored
Closes #49
-
Jakub Klinkovský authored
They are not suitable for more than 2 devices/execution types; their design breaks the Open-Closed Principle. Instead, a type template "Self" was created, which allows to change any template parameter.
-
- Oct 25, 2019
-
-
Jakub Klinkovský authored
The usage of algorithms such as MemoryOperations or Reduction is not bound to a particular container. On the other hand, ArrayIO, ArrayAssignment, VectorAssignment and StaticArrayAssignment are just implementation details for the containers - moved into TNL/Containers/detail/ Also moved ParallelFor, StaticFor, StaticVectorFor, TemplateStaticFor into TNL/Algorithms/
-
Jakub Klinkovský authored
This will be necessary to avoid code bloat with more than 2 devices (execution types).
-
Jakub Klinkovský authored
Moved synchronization of smart pointers from Devices::Cuda into TNL::Pointers namespace as free functions synchronizeDevice() was renamed to synchronizeSmartPointersOnDevice() for clarity - there are many similarly named functions in CUDA (e.g. cudaDeviceSynchronize()).
-
Jakub Klinkovský authored
Moved (most of) static methods from TNL::Devices::Cuda as free functions into separate namespace TNL::Cuda The class TNL::Devices::Cuda was too bloated, breaking the Single Responsibility Principle. It should be used only for template specializations and other things common to all devices. The functions in MemoryHelpers.h are deprecated, smart pointers should be used instead. The functions in LaunchHelpers.h are temporary, more refactoring is needed with respect to execution policies and custom launch parameters.
-
- Oct 24, 2019
-
-
Jakub Klinkovský authored
Fixes #46
-
Jakub Klinkovský authored
-
Jakub Klinkovský authored
-
- Sep 03, 2019
-
-
Jakub Klinkovský authored
-
- Sep 02, 2019
-
-
Tomáš Oberhuber authored
-
- Aug 24, 2019
-
-
Jakub Klinkovský authored
-
- Aug 07, 2019
-
-
Jakub Klinkovský authored
-
- Aug 05, 2019
-
-
Jakub Klinkovský authored
-
- Aug 04, 2019
-
-
Jakub Klinkovský authored
getConstView should be always used for const operations, because explicit is better than implicit. Overloading one method for cases which have a completely different type (ConstViewType is *not* just a const-qualified ViewType) can be very unclear (or even ambiguous) in certain cases.
-
- Jul 27, 2019
-
-
Jakub Klinkovský authored
-
- Jul 26, 2019
-
-
Jakub Klinkovský authored
-
- Jul 11, 2019
-
-
Tomáš Oberhuber authored
-
- Jun 14, 2019
-
-
Tomáš Oberhuber authored
-
Tomáš Oberhuber authored
-