Lines Matching refs:e
59 for (CeedSize e = start * block_size; e < stop * block_size; e += block_size) { in CeedElemRestrictionApplyStridedNoTranspose_Memcheck_Core() local
63 vv[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] = in CeedElemRestrictionApplyStridedNoTranspose_Memcheck_Core()
64 … uu[n * strides[0] + k * strides[1] + CeedIntMin(e + j, num_elem - 1) * (CeedSize)strides[2]]; in CeedElemRestrictionApplyStridedNoTranspose_Memcheck_Core()
80 for (CeedSize e = start * block_size; e < stop * block_size; e += block_size) { in CeedElemRestrictionApplyOffsetNoTranspose_Memcheck_Core() local
83 …vv[elem_size * (k * block_size + e * num_comp) + i - v_offset] = uu[impl->offsets[i + e * elem_siz… in CeedElemRestrictionApplyOffsetNoTranspose_Memcheck_Core()
98 for (CeedSize e = start * block_size; e < stop * block_size; e += block_size) { in CeedElemRestrictionApplyOrientedNoTranspose_Memcheck_Core() local
101 vv[elem_size * (k * block_size + e * num_comp) + i - v_offset] = in CeedElemRestrictionApplyOrientedNoTranspose_Memcheck_Core()
102 …uu[impl->offsets[i + e * elem_size] + k * comp_stride] * (impl->orients[i + e * elem_size] ? -1.0 … in CeedElemRestrictionApplyOrientedNoTranspose_Memcheck_Core()
117 for (CeedSize e = start * block_size; e < stop * block_size; e += block_size) { in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core() local
122 vv[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] = in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
123 uu[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
124 impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size] + in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
125 uu[impl->offsets[j + (n + 1) * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
126 impl->curl_orients[j + (3 * n + 2) * block_size + e * 3 * elem_size]; in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
130 vv[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] = in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
131 uu[impl->offsets[j + (n - 1) * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
132 impl->curl_orients[j + (3 * n + 0) * block_size + e * 3 * elem_size] + in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
133 uu[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
134 impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size] + in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
135 uu[impl->offsets[j + (n + 1) * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
136 impl->curl_orients[j + (3 * n + 2) * block_size + e * 3 * elem_size]; in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
140 vv[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] = in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
141 uu[impl->offsets[j + (n - 1) * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
142 impl->curl_orients[j + (3 * n + 0) * block_size + e * 3 * elem_size] + in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
143 uu[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
144 impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size]; in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
158 for (CeedSize e = start * block_size; e < stop * block_size; e += block_size) { in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core() local
163 vv[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] = in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
164 uu[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
165 abs(impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size]) + in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
166 uu[impl->offsets[j + (n + 1) * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
167 abs(impl->curl_orients[j + (3 * n + 2) * block_size + e * 3 * elem_size]); in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
171 vv[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] = in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
172 uu[impl->offsets[j + (n - 1) * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
173 abs(impl->curl_orients[j + (3 * n + 0) * block_size + e * 3 * elem_size]) + in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
174 uu[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
175 abs(impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size]) + in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
176 uu[impl->offsets[j + (n + 1) * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
177 abs(impl->curl_orients[j + (3 * n + 2) * block_size + e * 3 * elem_size]); in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
181 vv[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] = in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
182 uu[impl->offsets[j + (n - 1) * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
183 abs(impl->curl_orients[j + (3 * n + 0) * block_size + e * 3 * elem_size]) + in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
184 uu[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
185 abs(impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size]); in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
205 for (CeedSize e = start * block_size; e < stop * block_size; e += block_size) { in CeedElemRestrictionApplyStridedTranspose_Memcheck_Core() local
208 CeedPragmaSIMD for (CeedSize j = 0; j < CeedIntMin(block_size, num_elem - e); j++) { in CeedElemRestrictionApplyStridedTranspose_Memcheck_Core()
209 vv[n * strides[0] + k * strides[1] + (e + j) * strides[2]] += in CeedElemRestrictionApplyStridedTranspose_Memcheck_Core()
210 uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset]; in CeedElemRestrictionApplyStridedTranspose_Memcheck_Core()
226 for (CeedSize e = start * block_size; e < stop * block_size; e += block_size) { in CeedElemRestrictionApplyOffsetTranspose_Memcheck_Core() local
230 for (CeedSize j = i; j < i + CeedIntMin(block_size, num_elem - e); j++) { in CeedElemRestrictionApplyOffsetTranspose_Memcheck_Core()
233 vv_loc = uu[elem_size * (k * block_size + e * num_comp) + j - v_offset]; in CeedElemRestrictionApplyOffsetTranspose_Memcheck_Core()
234 CeedPragmaAtomic vv[impl->offsets[j + e * elem_size] + k * comp_stride] += vv_loc; in CeedElemRestrictionApplyOffsetTranspose_Memcheck_Core()
250 for (CeedSize e = start * block_size; e < stop * block_size; e += block_size) { in CeedElemRestrictionApplyOrientedTranspose_Memcheck_Core() local
254 for (CeedSize j = i; j < i + CeedIntMin(block_size, num_elem - e); j++) { in CeedElemRestrictionApplyOrientedTranspose_Memcheck_Core()
257 …vv_loc = uu[elem_size * (k * block_size + e * num_comp) + j - v_offset] * (impl->orients[j + e * e… in CeedElemRestrictionApplyOrientedTranspose_Memcheck_Core()
258 CeedPragmaAtomic vv[impl->offsets[j + e * elem_size] + k * comp_stride] += vv_loc; in CeedElemRestrictionApplyOrientedTranspose_Memcheck_Core()
275 for (CeedSize e = start * block_size; e < stop * block_size; e += block_size) { in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core() local
278 const CeedSize block_end = CeedIntMin(block_size, num_elem - e); in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
282 vv_loc[j] = uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
283 impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size] + in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
284 … uu[e * elem_size * num_comp + (k * elem_size + n + 1) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
285 impl->curl_orients[j + (3 * n + 3) * block_size + e * 3 * elem_size]; in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
288 …CeedPragmaAtomic vv[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] += vv_loc… in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
292 … vv_loc[j] = uu[e * elem_size * num_comp + (k * elem_size + n - 1) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
293 impl->curl_orients[j + (3 * n - 1) * block_size + e * 3 * elem_size] + in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
294 … uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
295 impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size] + in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
296 … uu[e * elem_size * num_comp + (k * elem_size + n + 1) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
297 impl->curl_orients[j + (3 * n + 3) * block_size + e * 3 * elem_size]; in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
300 …CeedPragmaAtomic vv[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] += vv_loc… in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
304 … vv_loc[j] = uu[e * elem_size * num_comp + (k * elem_size + n - 1) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
305 impl->curl_orients[j + (3 * n - 1) * block_size + e * 3 * elem_size] + in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
306 uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
307 impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size]; in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
310 …CeedPragmaAtomic vv[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] += vv_loc… in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core()
325 for (CeedSize e = start * block_size; e < stop * block_size; e += block_size) { in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core() local
328 const CeedSize block_end = CeedIntMin(block_size, num_elem - e); in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
332 vv_loc[j] = uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
333 abs(impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size]) + in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
334 … uu[e * elem_size * num_comp + (k * elem_size + n + 1) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
335 abs(impl->curl_orients[j + (3 * n + 3) * block_size + e * 3 * elem_size]); in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
338 …CeedPragmaAtomic vv[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] += vv_loc… in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
342 … vv_loc[j] = uu[e * elem_size * num_comp + (k * elem_size + n - 1) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
343 … abs(impl->curl_orients[j + (3 * n - 1) * block_size + e * 3 * elem_size]) + in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
344 … uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
345 … abs(impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size]) + in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
346 … uu[e * elem_size * num_comp + (k * elem_size + n + 1) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
347 abs(impl->curl_orients[j + (3 * n + 3) * block_size + e * 3 * elem_size]); in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
350 …CeedPragmaAtomic vv[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] += vv_loc… in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
354 … vv_loc[j] = uu[e * elem_size * num_comp + (k * elem_size + n - 1) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
355 abs(impl->curl_orients[j + (3 * n - 1) * block_size + e * 3 * elem_size]) + in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
356 uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
357 abs(impl->curl_orients[j + (3 * n + 1) * block_size + e * 3 * elem_size]); in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
360 …CeedPragmaAtomic vv[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] += vv_loc… in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core()
375 for (CeedSize e = start; e < stop; e++) { in CeedElemRestrictionApplyAtPointsInElement_Memcheck_Core() local
376 l_vec_offset = impl->offsets[e]; in CeedElemRestrictionApplyAtPointsInElement_Memcheck_Core()
377 CeedCallBackend(CeedElemRestrictionGetNumPointsInElement(rstr, e, &num_points)); in CeedElemRestrictionApplyAtPointsInElement_Memcheck_Core()