Kokkos Core Kernels Package
Version of the Day
|
Belos | |
Kokkos | |
Impl | ScopeGuard Some user scope issues have been identified with some Kokkos::finalize calls; ScopeGuard aims to correct these issues |
MemorySpaceAccess | Access relationship between DstMemorySpace and SrcMemorySpace |
FunctorPolicyExecutionSpace | Given a Functor and Execution Policy query an execution space |
ParallelFor | Implementation of the ParallelFor operator that has a partial specialization for the device |
ParallelReduce | Implementation detail of parallel_reduce |
ParallelScan | Implementation detail of parallel_scan |
ViewToDynRankViewTag | Assign compatible default mappings |
Experimental | |
Impl | |
ChunkedArrayManager | |
UniqueToken | Class to generate unique ids base on the required amount of concurrency |
UniqueToken< ExecutionSpace, UniqueTokenScope::Instance > | Instance scope UniqueToken allows for a max size other than execution_space().concurrency() |
AcquireUniqueToken | RAII helper for per-thread unique token values |
AcquireTeamUniqueToken | RAII helper for per-team unique token values |
DynamicView | Dynamic views are restricted to rank-one and no layout. Resize only occurs on host outside of parallel_regions. Subviews are not allowed |
hwloc | Minimal subset of logical 'hwloc' functionality available from http://www.open-mpi.org/projects/hwloc/ |
Tools | |
Experimental | |
Impl | |
ValueHierarchyNode | |
MapTypeConverter | |
ValueHierarchyConstructor | |
get_space_dimensionality | |
DimensionValueExtractor | |
GetMultidimensionalPoint | |
Array | Derived from the C++17 'std::array'. Dropping the iterator interface |
complex | Partial reimplementation of std::complex that works as the result of a Kokkos::parallel_reduce |
LaunchBounds | Specify Launch Bounds for CUDA execution |
SpaceAccessibility | Can AccessSpace access MemorySpace ? |
View | View to an array of data |
Crs | Compressed row storage array |
RangePolicy | Execution policy for work over a range of an integral type |
WorkRange | Subrange for a partition's rank and size |
TeamPolicy | Execution policy for parallel work over a league of teams of threads |
HostSpace | Memory management for host memory |
LayoutLeft | Memory layout tag indicating left-to-right (Fortran scheme) striding of multi-indices |
LayoutRight | Memory layout tag indicating right-to-left (C or lexigraphical scheme) striding of multi-indices |
LayoutStride | Memory layout tag indicated arbitrarily strided multi-index mapping into contiguous memory |
pair | Replacement for std::pair that works on CUDA devices |
ScratchMemorySpace | Scratch memory space associated with an execution space |
Timer | Time since construction |
ViewTraits | Traits class for accessing attributes of a View |
Bitset | A thread safe view to a bitset |
ConstBitset | |
GraphRowViewConst | View of a row of a sparse graph |
StaticCrsGraph | Compressed row storage array |
UnorderedMapInsertResult | First element of the return value of UnorderedMap::insert() |
UnorderedMapInsertOpTypes | Operations applied to the values array upon subsequent insertions |
UnorderedMap | Thread-safe, performance-portable lookup table |
Teuchos | |
MatrixMarket | |
Trilinos | |
Details |