Lines Matching refs:row
136 vld1.32 d4[0], [r0], r2 @load row 1 in source
137 vld1.32 d4[1], [r0], r2 @load row 2 in source
138 vld1.32 d6[0], [r0], r2 @load row 3 in source
139 vld1.32 d6[1], [r0], r2 @load row 4 in source
157 vst1.32 d4[0], [r1], r3 @store row 1 in destination
158 vst1.32 d4[1], [r1], r3 @store row 2 in destination
159 vst1.32 d6[0], [r1], r3 @store row 3 in destination
160 vst1.32 d6[1], [r1], r3 @store row 4 in destination
168 vld1.8 d4, [r0], r2 @load row 1 in source
169 vld1.8 d6, [r0], r2 @load row 2 in source
170 vld1.8 d8, [r0], r2 @load row 3 in source
171 vmovl.u8 q2, d4 @converting row 1 to 16-bit
172 vld1.8 d10, [r0], r2 @load row 4 in source
173 vmovl.u8 q3, d6 @converting row 2 to 16-bit
175 vmovl.u8 q4, d8 @converting row 3 to 16-bit
176 vmul.s16 q2, q2, d2[0] @weight mult. for row 1
177 vmovl.u8 q5, d10 @converting row 4 to 16-bit
178 vmul.s16 q3, q3, d2[0] @weight mult. for row 2
179 vmul.s16 q4, q4, d2[0] @weight mult. for row 3
180 vmul.s16 q5, q5, d2[0] @weight mult. for row 4
182 vrshl.s16 q2, q2, q0 @rounds off the weighted samples from row 1
183 vrshl.s16 q3, q3, q0 @rounds off the weighted samples from row 2
184 vrshl.s16 q4, q4, q0 @rounds off the weighted samples from row 3
185 vaddw.s8 q2, q2, d3 @adding offset for row 1
186 vrshl.s16 q5, q5, q0 @rounds off the weighted samples from row 4
187 vaddw.s8 q3, q3, d3 @adding offset for row 2
189 vaddw.s8 q4, q4, d3 @adding offset for row 3
190 vqmovun.s16 d4, q2 @saturating row 1 to unsigned 8-bit
191 vaddw.s8 q5, q5, d3 @adding offset for row 4
192 vqmovun.s16 d6, q3 @saturating row 2 to unsigned 8-bit
193 vqmovun.s16 d8, q4 @saturating row 3 to unsigned 8-bit
194 vqmovun.s16 d10, q5 @saturating row 4 to unsigned 8-bit
196 vst1.8 d4, [r1], r3 @store row 1 in destination
197 vst1.8 d6, [r1], r3 @store row 2 in destination
199 vst1.8 d8, [r1], r3 @store row 3 in destination
200 vst1.8 d10, [r1], r3 @store row 4 in destination
208 vld1.8 {q2}, [r0], r2 @load row 1 in source
209 vld1.8 {q3}, [r0], r2 @load row 2 in source
210 vmovl.u8 q6, d4 @converting row 1L to 16-bit
211 vld1.8 {q4}, [r0], r2 @load row 3 in source
212 vmovl.u8 q7, d5 @converting row 1H to 16-bit
213 vld1.8 {q5}, [r0], r2 @load row 4 in source
215 vmovl.u8 q8, d6 @converting row 2L to 16-bit
216 vmul.s16 q6, q6, d2[0] @weight mult. for row 1L
217 vmovl.u8 q9, d7 @converting row 2H to 16-bit
218 vmul.s16 q7, q7, d2[0] @weight mult. for row 1H
219 vmovl.u8 q10, d8 @converting row 3L to 16-bit
220 vmul.s16 q8, q8, d2[0] @weight mult. for row 2L
221 vmovl.u8 q11, d9 @converting row 3H to 16-bit
222 vmul.s16 q9, q9, d2[0] @weight mult. for row 2H
223 vmovl.u8 q12, d10 @converting row 4L to 16-bit
224 vmul.s16 q10, q10, d2[0] @weight mult. for row 3L
225 vmovl.u8 q13, d11 @converting row 4H to 16-bit
226 vmul.s16 q11, q11, d2[0] @weight mult. for row 3H
228 vmul.s16 q12, q12, d2[0] @weight mult. for row 4L
229 vrshl.s16 q6, q6, q0 @rounds off the weighted samples from row 1L
230 vmul.s16 q13, q13, d2[0] @weight mult. for row 4H
232 vrshl.s16 q7, q7, q0 @rounds off the weighted samples from row 1H
233 vrshl.s16 q8, q8, q0 @rounds off the weighted samples from row 2L
234 vaddw.s8 q6, q6, d3 @adding offset for row 1L
235 vrshl.s16 q9, q9, q0 @rounds off the weighted samples from row 2H
236 vaddw.s8 q7, q7, d3 @adding offset for row 1H
237 vqmovun.s16 d4, q6 @saturating row 1L to unsigned 8-bit
238 vrshl.s16 q10, q10, q0 @rounds off the weighted samples from row 3L
239 vaddw.s8 q8, q8, d3 @adding offset for row 2L
240 vqmovun.s16 d5, q7 @saturating row 1H to unsigned 8-bit
241 vrshl.s16 q11, q11, q0 @rounds off the weighted samples from row 3H
242 vaddw.s8 q9, q9, d3 @adding offset for row 2H
243 vqmovun.s16 d6, q8 @saturating row 2L to unsigned 8-bit
244 vrshl.s16 q12, q12, q0 @rounds off the weighted samples from row 4L
245 vaddw.s8 q10, q10, d3 @adding offset for row 3L
246 vqmovun.s16 d7, q9 @saturating row 2H to unsigned 8-bit
247 vrshl.s16 q13, q13, q0 @rounds off the weighted samples from row 4H
248 vaddw.s8 q11, q11, d3 @adding offset for row 3H
250 vqmovun.s16 d8, q10 @saturating row 3L to unsigned 8-bit
251 vaddw.s8 q12, q12, d3 @adding offset for row 4L
252 vqmovun.s16 d9, q11 @saturating row 3H to unsigned 8-bit
253 vaddw.s8 q13, q13, d3 @adding offset for row 4H
255 vqmovun.s16 d10, q12 @saturating row 4L to unsigned 8-bit
256 vst1.8 {q2}, [r1], r3 @store row 1 in destination
257 vqmovun.s16 d11, q13 @saturating row 4H to unsigned 8-bit
258 vst1.8 {q3}, [r1], r3 @store row 2 in destination
260 vst1.8 {q4}, [r1], r3 @store row 3 in destination
261 vst1.8 {q5}, [r1], r3 @store row 4 in destination
366 vld1.32 d6[0], [r0], r2 @load row 1 in source
367 vld1.32 d6[1], [r0], r2 @load row 2 in source
380 vst1.32 d6[0], [r1], r3 @store row 1 in destination
381 vst1.32 d6[1], [r1], r3 @store row 2 in destination
389 vld1.8 d6, [r0], r2 @load row 1 in source
390 vld1.8 d8, [r0], r2 @load row 2 in source
392 vmovl.u8 q3, d6 @converting row 1 to 16-bit
393 vmovl.u8 q4, d8 @converting row 2 to 16-bit
395 vmul.s16 q3, q3, q1 @weight mult. for row 1
396 vmul.s16 q4, q4, q1 @weight mult. for row 2
399 vrshl.s16 q3, q3, q0 @rounds off the weighted samples from row 1
400 vrshl.s16 q4, q4, q0 @rounds off the weighted samples from row 2
402 vaddw.s8 q3, q3, d4 @adding offset for row 1
403 vaddw.s8 q4, q4, d4 @adding offset for row 2
405 vqmovun.s16 d6, q3 @saturating row 1 to unsigned 8-bit
406 vqmovun.s16 d8, q4 @saturating row 2 to unsigned 8-bit
408 vst1.8 d6, [r1], r3 @store row 1 in destination
409 vst1.8 d8, [r1], r3 @store row 2 in destination
417 vld1.8 {q3}, [r0], r2 @load row 1 in source
418 vld1.8 {q4}, [r0], r2 @load row 2 in source
419 vmovl.u8 q7, d6 @converting row 1L to 16-bit
420 vld1.8 {q5}, [r0], r2 @load row 3 in source
421 vmovl.u8 q8, d7 @converting row 1H to 16-bit
422 vld1.8 {q6}, [r0], r2 @load row 4 in source
424 vmul.s16 q7, q7, q1 @weight mult. for row 1L
425 vmovl.u8 q9, d8 @converting row 2L to 16-bit
426 vmul.s16 q8, q8, q1 @weight mult. for row 1H
427 vmovl.u8 q10, d9 @converting row 2H to 16-bit
428 vmul.s16 q9, q9, q1 @weight mult. for row 2L
429 vmovl.u8 q11, d10 @converting row 3L to 16-bit
430 vmul.s16 q10, q10, q1 @weight mult. for row 2H
431 vmovl.u8 q12, d11 @converting row 3H to 16-bit
432 vmul.s16 q11, q11, q1 @weight mult. for row 3L
433 vmovl.u8 q13, d12 @converting row 4L to 16-bit
434 vmul.s16 q12, q12, q1 @weight mult. for row 3H
435 vmovl.u8 q14, d13 @converting row 4H to 16-bit
437 vmul.s16 q13, q13, q1 @weight mult. for row 4L
438 vrshl.s16 q7, q7, q0 @rounds off the weighted samples from row 1L
439 vmul.s16 q14, q14, q1 @weight mult. for row 4H
441 vrshl.s16 q8, q8, q0 @rounds off the weighted samples from row 1H
442 vrshl.s16 q9, q9, q0 @rounds off the weighted samples from row 2L
443 vaddw.s8 q7, q7, d4 @adding offset for row 1L
444 vrshl.s16 q10, q10, q0 @rounds off the weighted samples from row 2H
445 vaddw.s8 q8, q8, d4 @adding offset for row 1H
446 vqmovun.s16 d6, q7 @saturating row 1L to unsigned 8-bit
447 vrshl.s16 q11, q11, q0 @rounds off the weighted samples from row 3L
448 vaddw.s8 q9, q9, d4 @adding offset for row 2L
449 vqmovun.s16 d7, q8 @saturating row 1H to unsigned 8-bit
450 vrshl.s16 q12, q12, q0 @rounds off the weighted samples from row 3H
451 vaddw.s8 q10, q10, d4 @adding offset for row 2H
452 vqmovun.s16 d8, q9 @saturating row 2L to unsigned 8-bit
453 vrshl.s16 q13, q13, q0 @rounds off the weighted samples from row 4L
454 vaddw.s8 q11, q11, d4 @adding offset for row 3L
455 vqmovun.s16 d9, q10 @saturating row 2H to unsigned 8-bit
456 vrshl.s16 q14, q14, q0 @rounds off the weighted samples from row 4H
457 vaddw.s8 q12, q12, d4 @adding offset for row 3H
459 vqmovun.s16 d10, q11 @saturating row 3L to unsigned 8-bit
460 vaddw.s8 q13, q13, d4 @adding offset for row 4L
461 vqmovun.s16 d11, q12 @saturating row 3H to unsigned 8-bit
462 vaddw.s8 q14, q14, d4 @adding offset for row 4H
464 vqmovun.s16 d12, q13 @saturating row 4L to unsigned 8-bit
465 vst1.8 {q3}, [r1], r3 @store row 1 in destination
466 vqmovun.s16 d13, q14 @saturating row 4H to unsigned 8-bit
467 vst1.8 {q4}, [r1], r3 @store row 2 in destination
469 vst1.8 {q5}, [r1], r3 @store row 3 in destination
470 vst1.8 {q6}, [r1], r3 @store row 4 in destination