37 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Interp()  local
39 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D,…  in Interp()
41 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D…  in Interp()
43 …ReadElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem…  in Interp()
45 …WriteElementStrided2d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * num_ele…  in Interp()
47 …ReadElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_…  in Interp()
50 …WriteElementStrided3d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * BASIS_Q…  in Interp()
70 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpCollocated()  local
72 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D,…  in InterpCollocated()
73 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D…  in InterpCollocated()
75 …ReadElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem…  in InterpCollocated()
76 …WriteElementStrided2d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * num_ele…  in InterpCollocated()
78 …ReadElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_…  in InterpCollocated()
80 …WriteElementStrided3d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * BASIS_Q…  in InterpCollocated()
106 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpTranspose()  local
108 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D,…  in InterpTranspose()
110 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D…  in InterpTranspose()
112 …ReadElementStrided2d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * num_elem…  in InterpTranspose()
114 …WriteElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_ele…  in InterpTranspose()
116 …ReadElementStrided3d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * BASIS_Q_…  in InterpTranspose()
119 …WriteElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P…  in InterpTranspose()
139 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpCollocatedTranspose()  local
141 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D,…  in InterpCollocatedTranspose()
142 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D…  in InterpCollocatedTranspose()
144 …ReadElementStrided2d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * num_elem…  in InterpCollocatedTranspose()
145 …WriteElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_ele…  in InterpCollocatedTranspose()
147 …ReadElementStrided3d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * BASIS_Q_…  in InterpCollocatedTranspose()
149 …WriteElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P…  in InterpCollocatedTranspose()
175 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpTransposeAdd()  local
177 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D,…  in InterpTransposeAdd()
179 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D, …  in InterpTransposeAdd()
181 …ReadElementStrided2d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * num_elem…  in InterpTransposeAdd()
183 …SumElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem,…  in InterpTransposeAdd()
185 …ReadElementStrided3d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * BASIS_Q_…  in InterpTransposeAdd()
188 …SumElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_1…  in InterpTransposeAdd()
208 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in InterpCollocatedTransposeAdd()  local
210 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D,…  in InterpCollocatedTransposeAdd()
211 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D, …  in InterpCollocatedTransposeAdd()
213 …ReadElementStrided2d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * num_elem…  in InterpCollocatedTransposeAdd()
214 …SumElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem,…  in InterpCollocatedTransposeAdd()
216 …ReadElementStrided3d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * BASIS_Q_…  in InterpCollocatedTransposeAdd()
218 …SumElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_1…  in InterpCollocatedTransposeAdd()
249 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Grad()  local
251 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D,…  in Grad()
253 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D…  in Grad()
255 …ReadElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem…  in Grad()
257 …WriteElementStrided2d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_…  in Grad()
260 …ReadElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_…  in Grad()
264 …WriteElementStrided3d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_…  in Grad()
290 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradCollocated()  local
292 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D,…  in GradCollocated()
294 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D…  in GradCollocated()
296 …ReadElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem…  in GradCollocated()
298 …WriteElementStrided2d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_…  in GradCollocated()
301 …ReadElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_…  in GradCollocated()
304 …WriteElementStrided3d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_…  in GradCollocated()
332 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradTranspose()  local
334 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D,…  in GradTranspose()
336 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D…  in GradTranspose()
338 …ReadElementStrided2d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1…  in GradTranspose()
341 …WriteElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_ele…  in GradTranspose()
343 …ReadElementStrided3d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1…  in GradTranspose()
347 …WriteElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P…  in GradTranspose()
373 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradCollocatedTranspose()  local
375 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D,…  in GradCollocatedTranspose()
377 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D…  in GradCollocatedTranspose()
379 …ReadElementStrided2d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1…  in GradCollocatedTranspose()
382 …WriteElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_ele…  in GradCollocatedTranspose()
384 …ReadElementStrided3d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1…  in GradCollocatedTranspose()
387 …WriteElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P…  in GradCollocatedTranspose()
415 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradTransposeAdd()  local
417 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D,…  in GradTransposeAdd()
419 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D, …  in GradTransposeAdd()
421 …ReadElementStrided2d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1…  in GradTransposeAdd()
424 …SumElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem,…  in GradTransposeAdd()
426 …ReadElementStrided3d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1…  in GradTransposeAdd()
430 …SumElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_1…  in GradTransposeAdd()
456 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in GradCollocatedTransposeAdd()  local
458 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D,…  in GradCollocatedTransposeAdd()
460 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D, …  in GradCollocatedTransposeAdd()
462 …ReadElementStrided2d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1…  in GradCollocatedTransposeAdd()
465 …SumElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem,…  in GradCollocatedTransposeAdd()
467 …ReadElementStrided3d<BASIS_NUM_COMP * BASIS_DIM, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1…  in GradCollocatedTransposeAdd()
470 …SumElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_1…  in GradCollocatedTransposeAdd()
492 …for (CeedInt elem = blockIdx.x * blockDim.z + threadIdx.z; elem < num_elem; elem += gridDim.x * bl…  in Weight()  local
495 …  WriteElementStrided1d<1, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * num_elem, BASIS_Q_1D, r_W, d_W);  in Weight()
498 …WriteElementStrided2d<1, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * num_elem, BASIS_Q_1D…  in Weight()
501 …WriteElementStrided3d<1, BASIS_Q_1D>(data, elem, 1, BASIS_Q_1D * BASIS_Q_1D * BASIS_Q_1D * num_ele…  in Weight()