Lines Matching refs:data
28 SharedData_Hip data; in __launch_bounds__() local
29 data.t_id_x = threadIdx.x; in __launch_bounds__()
30 data.t_id_y = threadIdx.y; in __launch_bounds__()
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__()
33 data.slice = slice + data.t_id_z * BASIS_T_1D * (BASIS_DIM > 1 ? BASIS_T_1D : 1); in __launch_bounds__()
42 LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B); in __launch_bounds__()
49 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D,… in __launch_bounds__()
50 Interp1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_C); in __launch_bounds__()
52 …ReadElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem… in __launch_bounds__()
53 InterpTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_C); in __launch_bounds__()
55 …ReadElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_… in __launch_bounds__()
57 InterpTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_C); in __launch_bounds__()
66 …ReadPoint<BASIS_DIM, BASIS_NUM_PTS>(data, elem, p, BASIS_NUM_PTS, 1, num_elem * BASIS_NUM_PTS, BAS… in __launch_bounds__()
68 … InterpAtPoints1d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_C, r_X, r_V); in __launch_bounds__()
70 … InterpAtPoints2d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_C, r_X, r_V); in __launch_bounds__()
72 … InterpAtPoints3d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_C, r_X, r_V); in __launch_bounds__()
74 …WritePoint<BASIS_NUM_COMP, BASIS_NUM_PTS>(data, elem, p, BASIS_NUM_PTS, 1, num_elem * BASIS_NUM_PT… in __launch_bounds__()
84 SharedData_Hip data; in __launch_bounds__() local
85 data.t_id_x = threadIdx.x; in __launch_bounds__()
86 data.t_id_y = threadIdx.y; 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__()
89 data.slice = slice + data.t_id_z * BASIS_T_1D * (BASIS_DIM > 1 ? BASIS_T_1D : 1); in __launch_bounds__()
98 LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B); in __launch_bounds__()
109 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D… in __launch_bounds__()
111 …WriteElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_ele… in __launch_bounds__()
113 …WriteElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P… in __launch_bounds__()
123 …ReadPoint<BASIS_DIM, BASIS_NUM_PTS>(data, elem, p, BASIS_NUM_PTS, 1, num_elem * BASIS_NUM_PTS, BAS… in __launch_bounds__()
124 …ReadPoint<BASIS_NUM_COMP, BASIS_NUM_PTS>(data, elem, i, points_per_elem[elem], 1, num_elem * BASIS… in __launch_bounds__()
126 …InterpTransposeAtPoints1d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X… in __launch_bounds__()
128 …InterpTransposeAtPoints2d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X… in __launch_bounds__()
130 …InterpTransposeAtPoints3d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X… in __launch_bounds__()
136 InterpTranspose1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
137 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D, … in __launch_bounds__()
139 … InterpTransposeTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
140 …SumElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem,… in __launch_bounds__()
142 … InterpTransposeTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
143 …SumElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_1… in __launch_bounds__()
154 SharedData_Hip data; in __launch_bounds__() local
155 data.t_id_x = threadIdx.x; in __launch_bounds__()
156 data.t_id_y = threadIdx.y; 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__()
159 data.slice = slice + data.t_id_z * BASIS_T_1D * (BASIS_DIM > 1 ? BASIS_T_1D : 1); in __launch_bounds__()
168 LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B); in __launch_bounds__()
182 …ReadPoint<BASIS_DIM, BASIS_NUM_PTS>(data, elem, p, BASIS_NUM_PTS, 1, num_elem * BASIS_NUM_PTS, BAS… in __launch_bounds__()
183 …ReadPoint<BASIS_NUM_COMP, BASIS_NUM_PTS>(data, elem, i, points_per_elem[elem], 1, num_elem * BASIS… in __launch_bounds__()
185 …InterpTransposeAtPoints1d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X… in __launch_bounds__()
187 …InterpTransposeAtPoints2d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X… in __launch_bounds__()
189 …InterpTransposeAtPoints3d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X… in __launch_bounds__()
195 InterpTranspose1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
196 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D, … in __launch_bounds__()
198 … InterpTransposeTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
199 …SumElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem,… in __launch_bounds__()
201 … InterpTransposeTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
202 …SumElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_1… in __launch_bounds__()
216 SharedData_Hip data; in __launch_bounds__() local
217 data.t_id_x = threadIdx.x; in __launch_bounds__()
218 data.t_id_y = threadIdx.y; 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__()
221 data.slice = slice + data.t_id_z * BASIS_T_1D * (BASIS_DIM > 1 ? BASIS_T_1D : 1); in __launch_bounds__()
230 LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B); in __launch_bounds__()
237 …ReadElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D,… in __launch_bounds__()
238 Interp1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_C); in __launch_bounds__()
240 …ReadElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem… in __launch_bounds__()
241 InterpTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_C); in __launch_bounds__()
243 …ReadElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_… in __launch_bounds__()
245 InterpTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_U, s_B, r_C); in __launch_bounds__()
254 …ReadPoint<BASIS_DIM, BASIS_NUM_PTS>(data, elem, p, BASIS_NUM_PTS, 1, num_elem * BASIS_NUM_PTS, BAS… in __launch_bounds__()
256 … GradAtPoints1d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_C, r_X, r_V); in __launch_bounds__()
258 … GradAtPoints2d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_C, r_X, r_V); in __launch_bounds__()
260 … GradAtPoints3d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_C, r_X, r_V); in __launch_bounds__()
262 …WritePoint<BASIS_NUM_COMP * BASIS_DIM, BASIS_NUM_PTS>(data, elem, p, BASIS_NUM_PTS, 1, num_elem * … in __launch_bounds__()
272 SharedData_Hip data; in __launch_bounds__() local
273 data.t_id_x = threadIdx.x; in __launch_bounds__()
274 data.t_id_y = threadIdx.y; 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__()
277 data.slice = slice + data.t_id_z * BASIS_T_1D * (BASIS_DIM > 1 ? BASIS_T_1D : 1); in __launch_bounds__()
286 LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B); in __launch_bounds__()
297 …WriteElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D… in __launch_bounds__()
299 …WriteElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_ele… in __launch_bounds__()
301 …WriteElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P… in __launch_bounds__()
311 …ReadPoint<BASIS_DIM, BASIS_NUM_PTS>(data, elem, p, BASIS_NUM_PTS, 1, num_elem * BASIS_NUM_PTS, BAS… in __launch_bounds__()
312 …ReadPoint<BASIS_NUM_COMP * BASIS_DIM, BASIS_NUM_PTS>(data, elem, i, points_per_elem[elem], 1, num_… in __launch_bounds__()
315 …GradTransposeAtPoints1d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X, … in __launch_bounds__()
317 …GradTransposeAtPoints2d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X, … in __launch_bounds__()
319 …GradTransposeAtPoints3d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X, … in __launch_bounds__()
325 InterpTranspose1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
326 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D, … in __launch_bounds__()
328 … InterpTransposeTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
329 …SumElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem,… in __launch_bounds__()
331 … InterpTransposeTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
332 …SumElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_1… in __launch_bounds__()
343 SharedData_Hip data; in __launch_bounds__() local
344 data.t_id_x = threadIdx.x; in __launch_bounds__()
345 data.t_id_y = threadIdx.y; 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__()
348 data.slice = slice + data.t_id_z * BASIS_T_1D * (BASIS_DIM > 1 ? BASIS_T_1D : 1); in __launch_bounds__()
357 LoadMatrix<BASIS_P_1D, BASIS_Q_1D>(data, c_B, s_B); in __launch_bounds__()
371 …ReadPoint<BASIS_DIM, BASIS_NUM_PTS>(data, elem, p, BASIS_NUM_PTS, 1, num_elem * BASIS_NUM_PTS, BAS… in __launch_bounds__()
372 …ReadPoint<BASIS_NUM_COMP * BASIS_DIM, BASIS_NUM_PTS>(data, elem, i, points_per_elem[elem], 1, num_… in __launch_bounds__()
375 …GradTransposeAtPoints1d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X, … in __launch_bounds__()
377 …GradTransposeAtPoints2d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X, … in __launch_bounds__()
379 …GradTransposeAtPoints3d<BASIS_NUM_COMP, BASIS_NUM_PTS, BASIS_P_1D, BASIS_Q_1D>(data, i, r_U, r_X, … in __launch_bounds__()
385 InterpTranspose1d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
386 …SumElementStrided1d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * num_elem, BASIS_P_1D, … in __launch_bounds__()
388 … InterpTransposeTensor2d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
389 …SumElementStrided2d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * num_elem,… in __launch_bounds__()
391 … InterpTransposeTensor3d<BASIS_NUM_COMP, BASIS_P_1D, BASIS_Q_1D, BASIS_T_1D>(data, r_C, s_B, r_V); in __launch_bounds__()
392 …SumElementStrided3d<BASIS_NUM_COMP, BASIS_P_1D>(data, elem, 1, BASIS_P_1D * BASIS_P_1D * BASIS_P_1… in __launch_bounds__()