21 extern "C" __global__ void Interp(const CeedInt num_elem, const CeedScalar *__restrict__ d_B, const…  in Interp()  argument
23 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Interp()
24 …IS_Q_COMP_INTERP, BASIS_P, BASIS_Q>(elem, BASIS_P, BASIS_Q, BASIS_P * num_elem, BASIS_Q * num_elem,  in Interp()
25 …                                               BASIS_NUM_COMP * BASIS_Q * num_elem, d_B, d_U, d_V);  in Interp()
29 extern "C" __global__ void InterpTranspose(const CeedInt num_elem, const CeedScalar *__restrict__ d…  in InterpTranspose()  argument
31 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpTranspose()
32 …IS_Q_COMP_INTERP, BASIS_P, BASIS_Q>(elem, BASIS_Q, BASIS_P, BASIS_Q * num_elem, BASIS_P * num_elem,  in InterpTranspose()
33 …                                               BASIS_NUM_COMP * BASIS_Q * num_elem, d_B, d_U, d_V);  in InterpTranspose()
40 extern "C" __global__ void Deriv(const CeedInt num_elem, const CeedScalar *__restrict__ d_B, const …  in Deriv()  argument
42 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Deriv()
43 …SIS_Q_COMP_DERIV, BASIS_P, BASIS_Q>(elem, BASIS_P, BASIS_Q, BASIS_P * num_elem, BASIS_Q * num_elem,  in Deriv()
44 …                                               BASIS_NUM_COMP * BASIS_Q * num_elem, d_B, d_U, d_V);  in Deriv()
48 extern "C" __global__ void DerivTranspose(const CeedInt num_elem, const CeedScalar *__restrict__ d_…  in DerivTranspose()  argument
50 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in DerivTranspose()
51 …SIS_Q_COMP_DERIV, BASIS_P, BASIS_Q>(elem, BASIS_Q, BASIS_P, BASIS_Q * num_elem, BASIS_P * num_elem,  in DerivTranspose()
52 …                                               BASIS_NUM_COMP * BASIS_Q * num_elem, d_B, d_U, d_V);  in DerivTranspose()
59 extern "C" __global__ void Weight(const CeedInt num_elem, const CeedScalar *__restrict__ q_weight, …  in Weight()  argument
63 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Weight()