25   data.t_id_z = threadIdx.z;  in __launch_bounds__()
26   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
38 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
64   data.t_id_z = threadIdx.z;  in __launch_bounds__()
65   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
71 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
94   data.t_id_z = threadIdx.z;  in __launch_bounds__()
95   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
107 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
133   data.t_id_z = threadIdx.z;  in __launch_bounds__()
134   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
140 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
163   data.t_id_z = threadIdx.z;  in __launch_bounds__()
164   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
176 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
203   data.t_id_z = threadIdx.z;  in __launch_bounds__()
204   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
210 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
236   data.t_id_z = threadIdx.z;  in __launch_bounds__()
237   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
251 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
280   data.t_id_z = threadIdx.z;  in __launch_bounds__()
281   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
293 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
321   data.t_id_z = threadIdx.z;  in __launch_bounds__()
322   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
336 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
365   data.t_id_z = threadIdx.z;  in __launch_bounds__()
366   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
378 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
406   data.t_id_z = threadIdx.z;  in __launch_bounds__()
407   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
421 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
450   data.t_id_z = threadIdx.z;  in __launch_bounds__()
451   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
463 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()
493   data.t_id_z = threadIdx.z;  in __launch_bounds__()
494   data.t_id   = threadIdx.x + threadIdx.y * blockDim.x + threadIdx.z * blockDim.y * blockDim.x;  in __launch_bounds__()
499 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()