24   data.t_id_z = threadIdx.z;  in Interp()
25   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in Interp()
37 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Interp()
63   data.t_id_z = threadIdx.z;  in InterpCollocated()
64   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in InterpCollocated()
70 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpCollocated()
93   data.t_id_z = threadIdx.z;  in InterpTranspose()
94   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in InterpTranspose()
106 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpTranspose()
132   data.t_id_z = threadIdx.z;  in InterpCollocatedTranspose()
133   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in InterpCollocatedTranspose()
139 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpCollocatedTranspose()
162   data.t_id_z = threadIdx.z;  in InterpTransposeAdd()
163   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in InterpTransposeAdd()
175 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpTransposeAdd()
201   data.t_id_z = threadIdx.z;  in InterpCollocatedTransposeAdd()
202   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in InterpCollocatedTransposeAdd()
208 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpCollocatedTransposeAdd()
234   data.t_id_z = threadIdx.z;  in Grad()
235   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in Grad()
249 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Grad()
277   data.t_id_z = threadIdx.z;  in GradCollocated()
278   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in GradCollocated()
290 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradCollocated()
317   data.t_id_z = threadIdx.z;  in GradTranspose()
318   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in GradTranspose()
332 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradTranspose()
360   data.t_id_z = threadIdx.z;  in GradCollocatedTranspose()
361   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in GradCollocatedTranspose()
373 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradCollocatedTranspose()
400   data.t_id_z = threadIdx.z;  in GradTransposeAdd()
401   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in GradTransposeAdd()
415 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradTransposeAdd()
443   data.t_id_z = threadIdx.z;  in GradCollocatedTransposeAdd()
444   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in GradCollocatedTransposeAdd()
456 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradCollocatedTransposeAdd()
485   data.t_id_z = threadIdx.z;  in Weight()
486   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in Weight()
492 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Weight()