Lines Matching refs:k
60 for (CeedSize k = 0; k < num_comp; k++) { 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()
81 for (CeedSize k = 0; k < num_comp; k++) { 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()
99 for (CeedSize k = 0; k < num_comp; k++) { 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()
118 for (CeedSize k = 0; k < num_comp; k++) { 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()
125 uu[impl->offsets[j + (n + 1) * block_size + e * elem_size] + k * comp_stride] * 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()
133 uu[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
135 uu[impl->offsets[j + (n + 1) * block_size + e * elem_size] + k * comp_stride] * 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()
143 uu[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedNoTranspose_Memcheck_Core()
159 for (CeedSize k = 0; k < num_comp; k++) { 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()
166 uu[impl->offsets[j + (n + 1) * block_size + e * elem_size] + k * comp_stride] * 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()
174 uu[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
176 uu[impl->offsets[j + (n + 1) * block_size + e * elem_size] + k * comp_stride] * 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()
184 uu[impl->offsets[j + n * block_size + e * elem_size] + k * comp_stride] * in CeedElemRestrictionApplyCurlOrientedUnsignedNoTranspose_Memcheck_Core()
206 for (CeedSize k = 0; k < num_comp; k++) { in CeedElemRestrictionApplyStridedTranspose_Memcheck_Core() local
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()
227 for (CeedSize k = 0; k < num_comp; k++) { in CeedElemRestrictionApplyOffsetTranspose_Memcheck_Core() local
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()
251 for (CeedSize k = 0; k < num_comp; k++) { in CeedElemRestrictionApplyOrientedTranspose_Memcheck_Core() local
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()
276 for (CeedSize k = 0; k < num_comp; k++) { in CeedElemRestrictionApplyCurlOrientedTranspose_Memcheck_Core() local
282 vv_loc[j] = uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * 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()
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()
294 … uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * 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()
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()
306 uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * 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()
326 for (CeedSize k = 0; k < num_comp; k++) { in CeedElemRestrictionApplyCurlOrientedUnsignedTranspose_Memcheck_Core() local
332 vv_loc[j] = uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * 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()
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()
344 … uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * 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()
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()
356 uu[e * elem_size * num_comp + (k * elem_size + n) * block_size + j - v_offset] * 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()