38 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()  local
39 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, d_U, r_U…  in __launch_bounds__()
41 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS_Q, r_V, d_…  in __launch_bounds__()
65 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()  local
66 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS_Q, d_U, r_U…  in __launch_bounds__()
68 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, r_V, d_…  in __launch_bounds__()
92 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()  local
93 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS_Q, d_U, r_U…  in __launch_bounds__()
95 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, r_V, d_V);  in __launch_bounds__()
122 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()  local
123 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, d_U, r_U…  in __launch_bounds__()
125 …WriteElementStrided1d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASI…  in __launch_bounds__()
149 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()  local
150 …ReadElementStrided1d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS…  in __launch_bounds__()
152 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, r_V, d_…  in __launch_bounds__()
176 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()  local
177 …ReadElementStrided1d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS…  in __launch_bounds__()
179 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P>(data, elem, 1, BASIS_P * num_elem, BASIS_P, r_V, d_V);  in __launch_bounds__()
199 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in __launch_bounds__()  local
201     WriteElementStrided1d<1, BASIS_Q>(data, elem, 1, BASIS_Q * num_elem, BASIS_Q, r_W, d_W);  in __launch_bounds__()