37 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Interp()  local
38 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, d_U, r_U…  in Interp()
40 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS_Q, r_V, d_…  in Interp()
64 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpTranspose()  local
65 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS_Q, d_U, r_U…  in InterpTranspose()
67 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, r_V, d_…  in InterpTranspose()
91 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpTransposeAdd()  local
92 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS_Q, d_U, r_U…  in InterpTransposeAdd()
94 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, r_V, d_V);  in InterpTransposeAdd()
120 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Grad()  local
121 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, d_U, r_U…  in Grad()
123 …WriteElementStrided1d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASI…  in Grad()
147 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradTranspose()  local
148 …ReadElementStrided1d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS…  in GradTranspose()
150 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, r_V, d_…  in GradTranspose()
174 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradTransposeAdd()  local
175 …ReadElementStrided1d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS…  in GradTransposeAdd()
177 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, r_V, d_V);  in GradTransposeAdd()
196 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Weight()  local
198     WriteElementStrided1d<1, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS_Q, r_W, d_W);  in Weight()