
Optimise PPACK (#2067)

- pointers in `PPACK_IFACE_BLOCK` will be `__restrict__` - this is expected to produce better binary code for the _scalar_ case - for GPU we expect this to better utilise data caches as per CUDA docs - `ved_di` is not used anymore, gone and ABI bumped - GPU code never used the indexing structs, so remove from `PPACK_IFACE_BLOCK`
Showing
- arbor/backends/gpu/shared_state.cpp 0 additions, 1 deletionarbor/backends/gpu/shared_state.cpp
- arbor/backends/multicore/shared_state.cpp 0 additions, 1 deletionarbor/backends/multicore/shared_state.cpp
- arbor/include/arbor/mechanism_abi.h 2 additions, 3 deletionsarbor/include/arbor/mechanism_abi.h
- cmake/CompilerOptions.cmake 1 addition, 0 deletionscmake/CompilerOptions.cmake
- modcc/printer/cprinter.cpp 30 additions, 24 deletionsmodcc/printer/cprinter.cpp
- modcc/printer/gpuprinter.cpp 18 additions, 20 deletionsmodcc/printer/gpuprinter.cpp
Please register or sign in to comment