Home
last modified time | relevance | path

Searched refs:CeedRunKernelDimShared_Cuda (Results 1 – 5 of 5) sorted by relevance

/libCEED/backends/cuda-shared/
H A Dceed-cuda-shared-basis.c67 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, apply_add ? data->InterpTransposeAdd : data->Int… in CeedBasisApplyTensorCore_Cuda_shared()
70 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, data->Interp, NULL, grid, thread_1d, 1, elems_pe… in CeedBasisApplyTensorCore_Cuda_shared()
80 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, apply_add ? data->InterpTransposeAdd : data->Int… in CeedBasisApplyTensorCore_Cuda_shared()
83 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, data->Interp, NULL, grid, thread_1d, thread_1d, … in CeedBasisApplyTensorCore_Cuda_shared()
92 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, apply_add ? data->InterpTransposeAdd : data->Int… in CeedBasisApplyTensorCore_Cuda_shared()
95 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, data->Interp, NULL, grid, thread_1d, thread_1d, … in CeedBasisApplyTensorCore_Cuda_shared()
121 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, apply_add ? data->GradTransposeAdd : data->GradT… in CeedBasisApplyTensorCore_Cuda_shared()
124 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, data->Grad, NULL, grid, thread_1d, 1, elems_per_… in CeedBasisApplyTensorCore_Cuda_shared()
134 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, apply_add ? data->GradTransposeAdd : data->GradT… in CeedBasisApplyTensorCore_Cuda_shared()
137 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, data->Grad, NULL, grid, thread_1d, thread_1d, el… in CeedBasisApplyTensorCore_Cuda_shared()
[all …]
/libCEED/backends/cuda/
H A Dceed-cuda-compile.h26 CEED_INTERN int CeedRunKernelDimShared_Cuda(Ceed ceed, CUfunction kernel, CUstream stream, int grid…
H A Dceed-cuda-compile.cpp455 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, kernel, NULL, grid_size, block_size, 1, 1, 0, ar… in CeedRunKernel_Cuda()
464 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, kernel, NULL, grid_size, block_size_x, block_siz… in CeedRunKernelDim_Cuda()
502 int CeedRunKernelDimShared_Cuda(Ceed ceed, CUfunction kernel, CUstream stream, const int grid_size,… in CeedRunKernelDimShared_Cuda() function
/libCEED/backends/magma/
H A Dceed-magma.h43 #define CeedRunKernelDimSharedMagma CeedRunKernelDimShared_Cuda
/libCEED/backends/cuda-ref/
H A Dceed-cuda-ref-operator.c1788 …CeedCallBackend(CeedRunKernelDimShared_Cuda(ceed, asmb->LinearAssemble, NULL, grid, asmb->block_si… in CeedOperatorAssembleSingle_Cuda()