31   data.t_id_z = threadIdx.z;  in __launch_bounds__()
32   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
46 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
87   data.t_id_z = threadIdx.z;  in __launch_bounds__()
88   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
102 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
157   data.t_id_z = threadIdx.z;  in __launch_bounds__()
158   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
172 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
219   data.t_id_z = threadIdx.z;  in __launch_bounds__()
220   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
234 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
275   data.t_id_z = threadIdx.z;  in __launch_bounds__()
276   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
290 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
346   data.t_id_z = threadIdx.z;  in __launch_bounds__()
347   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
361 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()