|
Neko 1.99.9
A portable framework for high-order spectral element flow simulations
|
Fortran CUDA interface.
Enumerations | |
| enum | { cudasuccess = 0 , cudaerrorinvalidvalue = 1 , cudaerrormemoryallocation = 2 , cudaerrorinitializationerror = 3 } |
| Enum cudaError. More... | |
| enum | { cudamemcpyhosttohost = 0 , cudamemcpyhosttodevice = 1 , cudamemcpydevicetohost = 2 , cudamemcpydevicetodevice = 3 , cudamemcpydefault = 4 } |
| Enum cudaMemcpyKind. More... | |
Functions/Subroutines | |
| subroutine | cuda_init (glb_cmd_queue, aux_cmd_queue, strm_high_prio, strm_low_prio) |
| subroutine | cuda_finalize (glb_cmd_queue, aux_cmd_queue) |
| subroutine | cuda_device_name (name) |
| integer function | cuda_device_count () |
| Return the number of avaialble CUDA devices. | |
| Enumerator | |
|---|---|
| cudasuccess | |
| cudaerrorinvalidvalue | |
| cudaerrormemoryallocation | |
| cudaerrorinitializationerror | |
Definition at line 43 of file cuda_intf.F90.
| Enumerator | |
|---|---|
| cudamemcpyhosttohost | |
| cudamemcpyhosttodevice | |
| cudamemcpydevicetohost | |
| cudamemcpydevicetodevice | |
| cudamemcpydefault | |
Definition at line 51 of file cuda_intf.F90.
Definition at line 365 of file cuda_intf.F90.


| subroutine cuda_intf::cuda_device_name | ( | character(len=*), intent(inout) | name | ) |
| subroutine cuda_intf::cuda_finalize | ( | type(c_ptr), intent(inout) | glb_cmd_queue, |
| type(c_ptr), intent(inout) | aux_cmd_queue | ||
| ) |