64         CeedInt shared_mem      = elems_per_block * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
77         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
89         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
118         CeedInt shared_mem      = elems_per_block * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
131         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
142         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyTensorCore_Cuda_shared()  local
328         CeedInt shared_mem      = elems_per_block * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
342         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
354         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
378         CeedInt shared_mem      = elems_per_block * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
391         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
403         CeedInt shared_mem      = elems_per_block * thread_1d * thread_1d * sizeof(CeedScalar);  in CeedBasisApplyAtPointsCore_Cuda_shared()  local
487         CeedInt shared_mem      = elems_per_block * thread * sizeof(CeedScalar);  in CeedBasisApplyNonTensorCore_Cuda_shared()  local
511         CeedInt shared_mem      = elems_per_block * thread * sizeof(CeedScalar);  in CeedBasisApplyNonTensorCore_Cuda_shared()  local