Home
last modified time | relevance | path

Searched refs:v10 (Results 1 – 25 of 217) sorted by relevance

123456789

/external/libavc/common/armv8/
Dih264_inter_pred_luma_horz_qpel_vert_qpel_av8.s155 ld1 {v10.2s, v11.2s}, [x7], x2 // Vector load from src[5_0]
157 uaddl v24.8h, v0.8b, v10.8b
199 umlsl v16.8h, v10.8b, v31.8b
246 umlal v16.8h, v10.8b, v30.8b
292 umlal v0.8h, v10.8b, v30.8b
342 mov v2.16b, v10.16b
359 ld1 {v10.2s, v11.2s}, [x7], x2 // Vector load from src[9_0]
361 uaddl v24.8h, v0.8b, v10.8b
401 umlsl v16.8h, v10.8b, v31.8b
446 umlal v16.8h, v10.8b, v30.8b
[all …]
Dih264_deblk_chroma_av8.s102 uaddl v10.8h, v7.8b, v1.8b //Q4,Q5 = q0 + p1
111 umlal v10.8h, v3.8b, v31.8b //Q5,Q4 = (X2(q1U) + q0U + p1U)
125 rshrn v9.8b, v10.8h, #2 //Q4 = (X2(q1U) + q0U + p1U + 2) >> 2
128 rshrn v10.8b, v14.8h, #2 //
130 mov v10.d[1], v11.d[0]
132 bit v10.16b, v4.16b , v18.16b //
134 mov v11.d[0], v10.d[1]
136 st2 {v10.8b, v11.8b}, [x4], x1 //
208 mov v10.16b, v2.16b
211 mov v4.16b, v10.16b
[all …]
Dih264_weighted_bi_pred_av8.s174 ld1 {v10.s}[0], [x1], x4 //load row 3 in source 2
175 ld1 {v10.s}[1], [x1], x4 //load row 4 in source 2
177 uxtl v10.8h, v10.8b //converting rows 3,4 in source 2 to 16-bit
181 mla v8.8h, v10.8h , v2.h[2] //weight 2 mult. for rows 3,4
201 ld1 {v10.8b}, [x1], x4 //load row 2 in source 2
209 uxtl v10.8h, v10.8b //converting row 2 in source 2 to 16-bit
215 mla v8.8h, v10.8h , v2.h[2] //weight 2 mult. for row 2
247 ld1 {v10.8b, v11.8b}, [x1], x4 //load row 2 in source 2
259 uxtl v26.8h, v10.8b //converting row 2L in source 2 to 16-bit
263 uxtl v10.8h, v11.8b //converting row 2H in source 2 to 16-bit
[all …]
Dih264_weighted_pred_av8.s175 ld1 {v10.8b}, [x0], x2 //load row 4 in source
180 uxtl v10.8h, v10.8b //converting row 4 to 16-bit
183 mul v10.8h, v10.8h , v2.h[0] //weight mult. for row 4
189 srshl v10.8h, v10.8h , v0.8h //rounds off the weighted samples from row 4
194 saddw v10.8h, v10.8h , v3.8b //adding offset for row 4
197 sqxtun v10.8b, v10.8h //saturating row 4 to unsigned 8-bit
203 st1 {v10.8b}, [x1], x3 //store row 4 in destination
216 ld1 {v10.8b, v11.8b}, [x0], x2 //load row 4 in source
225 uxtl v24.8h, v10.8b //converting row 4L to 16-bit
253 sqxtun v10.8b, v24.8h //saturating row 4L to unsigned 8-bit
[all …]
Dih264_deblk_luma_av8.s100 ld1 {v10.8b, v11.8b}, [x0], x1 //p2 values are loaded into q5
108 mov v10.d[1], v11.d[0]
125 uabd v28.16b, v10.16b, v6.16b
157 uaddl v10.8h, v16.8b, v10.8b //Q14,Q5 = p2 + (p0+q0+1)>>1
165 sub v10.8h, v10.8h , v16.8h //
169 sqshrn v28.8b, v10.8h, #1 //Q14 = i_macro_p1
258 ld1 {v10.8b, v11.8b}, [x14] //load p1 to Q5
262 mov v10.d[1] , v11.d[0]
267 uabd v16.16b , v10.16b, v6.16b
291 uaddw v16.8h, v16.8h , v10.8b //2*(p0+q0+q1)+q2 +p1 L
[all …]
Dih264_inter_pred_filters_luma_vert_av8.s136 ld1 {v10.2s, v11.2s}, [x0], x2 // Vector load from src[5_0]
140 uaddl v14.8h, v0.8b, v10.8b // temp = src[0_0] + src[5_0]
151 uaddl v18.8h, v4.8b, v10.8b
163 uaddl v12.8h, v8.8b, v10.8b
178 uaddl v12.8h, v10.8b, v0.8b
195 uaddl v16.8h, v10.8b, v4.8b // temp2 = src[1_0] + src[4_0]
217 uaddl v14.8h, v8.8b, v10.8b
220 ld1 {v10.2s, v11.2s}, [x0], x2
234 uaddl v14.8h, v10.8b, v0.8b
246 uaddl v16.8h, v10.8b, v4.8b
[all …]
Dih264_inter_pred_luma_horz_hpel_vert_qpel_av8.s180 uaddl v10.8h, v2.8b, v3.8b
185 mla v8.8h, v10.8h , v22.8h
187 uaddl v10.8h, v1.8b, v4.8b
189 mls v8.8h, v10.8h , v24.8h
191 uaddl v10.8h, v0.8b, v5.8b
199 mla v10.8h, v12.8h , v22.8h
203 mls v10.8h, v12.8h , v24.8h
210 st1 {v10.4s}, [x9], x6 // store temp buffer 2
248 add v30.8h, v10.8h , v12.8h
276 add v28.8h, v10.8h , v16.8h
[all …]
Dih264_iquant_itrans_recon_av8.s181 add v10.4h, v4.4h , v7.4h // x0+x3
191 trn1 v4.4h, v10.4h, v11.4h
192 trn2 v5.4h, v10.4h, v11.4h
196 trn1 v10.2s, v4.2s, v6.2s // 0
205 add v14.4h, v10.4h, v12.4h // x0 = q0 + q2//
206 sub v15.4h, v10.4h, v12.4h // x1 = q0 - q2//
370 add v10.4h, v4.4h , v7.4h // x0+x3
382 trn1 v4.4h, v10.4h, v11.4h
383 trn2 v5.4h, v10.4h, v11.4h
387 trn1 v10.2s, v4.2s, v6.2s // 0
[all …]
Dih264_inter_pred_luma_vert_qpel_av8.s143 ld1 {v10.2s, v11.2s}, [x0], x2 // Vector load from src[5_0]
147 uaddl v14.8h, v0.8b, v10.8b // temp = src[0_0] + src[5_0]
158 uaddl v18.8h, v4.8b, v10.8b
173 uaddl v12.8h, v8.8b, v10.8b
187 uaddl v12.8h, v10.8b, v0.8b
209 uaddl v16.8h, v10.8b, v4.8b // temp2 = src[1_0] + src[4_0]
234 uaddl v14.8h, v8.8b, v10.8b
237 ld1 {v10.2s, v11.2s}, [x0], x2
256 uaddl v14.8h, v10.8b, v0.8b
268 uaddl v16.8h, v10.8b, v4.8b
[all …]
/external/libxaac/decoder/armv8/
Dixheaacd_cos_sin_mod_loop1.s72 sMULL v10.2d, v1.2s, v3.2s //qsub 1st
73 sshr v10.2d, v10.2d, #16
76 SQSUB v2.4s, v10.4s , v4.4s
109 sMULL v10.2d, v1.2s, v3.2s //qsub 1st
110 sshr v10.2d, v10.2d, #16
112 ADD v0.4s, v10.4s , v4.4s
145 sMULL v10.2d, v1.2s, v3.2s //qsub 1st
146 sshr v10.2d, v10.2d, #16
149 SQSUB v2.4s, v10.4s , v4.4s
182 sMULL v10.2d, v1.2s, v3.2s //qsub 1st
[all …]
Dixheaacd_cos_sin_mod_loop2.s109 sMULL v10.2d, v1.2s, v3.2s //qsub 1st
110 sshr v10.2d, v10.2d, #16
113 SQSUB v14.2d, v10.2d , v4.2d
114 SQSUB v16.2d, v4.2d , v10.2d
149 sMULL v10.2d, v1.2s, v3.2s //qsub 1st
150 sshr v10.2d, v10.2d, #16
153 SQSUB v14.2d, v4.2d , v10.2d
154 SQSUB v16.2d, v10.2d , v4.2d
188 sMULL v10.2d, v1.2s, v3.2s //qsub 1st
189 sshr v10.2d, v10.2d, #16
[all …]
Dixheaacd_inv_dit_fft_8pt.s60 SQADD v10.2s, v2.2s, v6.2s //a20_v = vqadd_s32(y1_3,y9_11);
70 SQADD v7.2s, v10.2s, v12.2s //x1_9 = vqadd_s32(a20_v,a30_v);
73 SQSUB v8.2s, v10.2s, v12.2s //x5_13 = vqsub_s32(a20_v,a30_v);
77 SQSUB v10.2s, v1.2s, v6.2s //x2_10 = vqsub_s32(a0_v,a1_v);
98 UZP1 v6.2s, v10.2s, v11.2s //x2_3
100 SQSUB v1.2s, v10.2s, v11.2s //tempr = vqsub_s32(x2_10,x3_11)
101 SQADD v5.2s, v10.2s, v11.2s //tempi = vqadd_s32(x2_10,x3_11)
104 SMULL v10.2d, v5.2s, v0.2s
107 SSHR v10.2d, v10.2d, #32 //tempi_q
110 SHL v10.4s, v10.4s, #1
[all …]
Dixheaacd_post_twiddle.s58 dup v10.4h, w4
65 dup v10.4h, w4
201 uMULL v0.4s, v26.4h, v10.4h
204 uMULL v2.4s, v24.4h, v10.4h
230 sMLAL v0.4s, v27.4h, v10.4h
236 sMLAL v2.4s, v25.4h, v10.4h
238 uMULL v4.4s, v18.4h, v10.4h
239 uMULL v6.4s, v16.4h, v10.4h
251 sMLAL v4.4s, v19.4h, v10.4h
253 sMLAL v6.4s, v17.4h, v10.4h
[all …]
/external/libhevc/common/arm64/
Dihevc_itrans_recon_32x32.s211 ld1 {v10.4h},[x0],x6
230 smull v20.4s, v10.4h, v0.h[0]
234 smull v22.4s, v10.4h, v0.h[0]
237 smull v16.4s, v10.4h, v0.h[0]
240 smull v18.4s, v10.4h, v0.h[0]
280 ld1 {v10.4h},[x0],x6
300 smlal v20.4s, v10.4h, v2.h[0]
304 smlal v22.4s, v10.4h, v6.h[0]
307 smlsl v16.4s, v10.4h, v6.h[0]
310 smlsl v18.4s, v10.4h, v2.h[0]
[all …]
Dihevc_intra_pred_luma_mode_27_to_33.s174 umull v10.8h, v23.8b, v30.8b //(i row)vmull_u8(ref_main_idx, dup_const_32_fract)
177 umlal v10.8h, v9.8b, v31.8b //(i row)vmull_u8(ref_main_idx_1, dup_const_fract)
192 rshrn v10.8b, v10.8h,#5 //(i row)shift_res = vrshrn_n_u16(add_res, 5)
206 st1 {v10.8b},[x2],#8 //(i row)
235 umull v10.8h, v23.8b, v30.8b //(v)vmull_u8(ref_main_idx, dup_const_32_fract)
238 umlal v10.8h, v9.8b, v31.8b //(v)vmull_u8(ref_main_idx_1, dup_const_fract)
258 rshrn v10.8b, v10.8h,#5 //(v)shift_res = vrshrn_n_u16(add_res, 5)
272 st1 {v10.8b},[x0],x3 //(v)
315 umull v10.8h, v23.8b, v30.8b //(i)vmull_u8(ref_main_idx, dup_const_32_fract)
319 umlal v10.8h, v9.8b, v31.8b //(i)vmull_u8(ref_main_idx_1, dup_const_fract)
[all …]
Dihevc_intra_pred_chroma_mode_27_to_33.s169 umull v10.8h, v23.8b, v30.8b //(i row)vmull_u8(ref_main_idx, dup_const_32_fract)
172 umlal v10.8h, v9.8b, v31.8b //(i row)vmull_u8(ref_main_idx_1, dup_const_fract)
187 rshrn v10.8b, v10.8h,#5 //(i row)shift_res = vrshrn_n_u16(add_res, 5)
201 st1 {v10.8b},[x2],#8 //(i row)
230 umull v10.8h, v23.8b, v30.8b //(v)vmull_u8(ref_main_idx, dup_const_32_fract)
233 umlal v10.8h, v9.8b, v31.8b //(v)vmull_u8(ref_main_idx_1, dup_const_fract)
253 rshrn v10.8b, v10.8h,#5 //(v)shift_res = vrshrn_n_u16(add_res, 5)
267 st1 {v10.8b},[x0],x3 //(v)
310 umull v10.8h, v23.8b, v30.8b //(i)vmull_u8(ref_main_idx, dup_const_32_fract)
314 umlal v10.8h, v9.8b, v31.8b //(i)vmull_u8(ref_main_idx_1, dup_const_fract)
[all …]
Dihevc_intra_pred_filters_luma_mode_19_to_25.s284 umull v10.8h, v23.8b, v30.8b //(i row)vmull_u8(ref_main_idx, dup_const_32_fract)
287 umlal v10.8h, v9.8b, v31.8b //(i row)vmull_u8(ref_main_idx_1, dup_const_fract)
301 rshrn v10.8b, v10.8h,#5 //(i row)shift_res = vrshrn_n_u16(add_res, 5)
315 st1 {v10.8b},[x2],#8 //(i row)
342 umull v10.8h, v23.8b, v30.8b //(v)vmull_u8(ref_main_idx, dup_const_32_fract)
345 umlal v10.8h, v9.8b, v31.8b //(v)vmull_u8(ref_main_idx_1, dup_const_fract)
364 rshrn v10.8b, v10.8h,#5 //(v)shift_res = vrshrn_n_u16(add_res, 5)
378 st1 {v10.8b},[x0],x3 //(v)
422 umull v10.8h, v23.8b, v30.8b //(i)vmull_u8(ref_main_idx, dup_const_32_fract)
425 umlal v10.8h, v9.8b, v31.8b //(i)vmull_u8(ref_main_idx_1, dup_const_fract)
[all …]
Dihevc_sao_band_offset_chroma.s163 LD1 {v10.8b},[x14],#8 //band_table_v.val[1]
223 …ADD v14.8b, v10.8b , v30.8b //band_table_v.val[1] = vadd_u8(band_table_v.val[1], band_…
235 …ADD v10.8b, v14.8b , v28.8b //band_table_v.val[1] = vadd_u8(band_table_v.val[1], vdup_…
266 cmhs v19.8b, v29.8b , v10.8b //vcle_u8(band_table.val[1], vdup_n_u8(16))
268 … ORR v10.8b, v10.8b , v19.8b //band_table.val[1] = vorr_u8(band_table.val[1], au1_cmp)
280 … AND v10.8b, v10.8b , v19.8b //band_table.val[1] = vand_u8(band_table.val[1], au1_cmp)
296 mov v9.d[1],v10.d[0]
297 mov v10.d[0],v11.d[0]
298 mov v10.d[1],v12.d[0]
324 …TBX v6.8b, {v9.16b- v10.16b},v8.8b //vtbx4_u8(au1_cur_row_deint.val[1], band_table_v, vsub…
[all …]
Dihevc_inter_pred_chroma_horz.s197 ld1 { v10.2s},[x4],x11 //vector load pu1_src
240 umull v22.8h, v10.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)//
295 ld1 { v10.2s},[x4],x11 //vector load pu1_src
354 umull v22.8h, v10.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)//
394 ld1 { v10.2s},[x4],x11 //vector load pu1_src
425 umull v22.8h, v10.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)//
499 umull v10.8h, v5.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)//
500 umlsl v10.8h, v4.8b, v24.8b //mul_res = vmlsl_u8(src[0_2], coeffabs_2)//
504 umlal v10.8h, v6.8b, v26.8b //mul_res = vmlsl_u8(src[0_0], coeffabs_0)//
505 umlsl v10.8h, v7.8b, v27.8b //mul_res = vmlal_u8(src[0_1], coeffabs_1)//
[all …]
Dihevc_inter_pred_filters_luma_horz.s246 umull v10.8h, v15.8b, v27.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)//
248 umlsl v10.8h, v14.8b, v26.8b //mul_res = vmlsl_u8(src[0_2], coeffabs_2)//
250 umlal v10.8h, v16.8b, v28.8b //mul_res = vmlal_u8(src[0_4], coeffabs_4)//
252 umlsl v10.8h, v17.8b, v29.8b //mul_res = vmlsl_u8(src[0_5], coeffabs_5)//
254 umlal v10.8h, v18.8b, v30.8b //mul_res = vmlal_u8(src[0_6], coeffabs_6)//
255 umlsl v10.8h, v19.8b, v31.8b //mul_res = vmlsl_u8(src[0_7], coeffabs_7)//
257 umlsl v10.8h, v12.8b, v24.8b //mul_res = vmlsl_u8(src[0_0], coeffabs_0)//
258 umlal v10.8h, v13.8b, v25.8b //mul_res = vmlal_u8(src[0_1], coeffabs_1)//
262 sqrshrun v8.8b, v10.8h,#6 //right shift and saturating narrow result 2
376 umull v10.8h, v2.8b, v25.8b //mul_res = vmlal_u8(src[0_1], coeffabs_1)//
[all …]
Dihevc_itrans_recon_16x16.s235 ld1 {v10.4h},[x0],x6
270 smull v12.4s, v10.4h, v0.h[0]
272 smull v14.4s, v10.4h, v0.h[0]
274 smull v16.4s, v10.4h, v0.h[0]
276 smull v18.4s, v10.4h, v0.h[0]
319 ld1 {v10.4h},[x0],x6
358 smlal v12.4s, v10.4h, v0.h[0]
366 smlsl v14.4s, v10.4h, v0.h[0]
372 smlsl v16.4s, v10.4h, v0.h[0]
378 smlal v18.4s, v10.4h, v0.h[0]
[all …]
/external/libmpeg2/common/armv8/
Dimpeg2_idct.s173 uaddw v10.8h, v30.8h , v1.8b
177 sqxtun v1.8b, v10.8h
241 sxtl v10.4s, v3.4h
243 raddhn2 v12.8h, v0.4s, v10.4s
251 sxtl v10.4s, v3.4h
253 raddhn2 v12.8h, v0.4s, v10.4s
261 sxtl v10.4s, v3.4h
263 raddhn2 v12.8h, v0.4s, v10.4s
271 sxtl v10.4s, v3.4h
273 raddhn2 v12.8h, v0.4s, v10.4s
[all …]
/external/libjpeg-turbo/simd/
Djsimd_arm64_neon.S221 st1 {v8.8b, v9.8b, v10.8b, v11.8b}, [x10], #32
237 and v10.16b, v16.16b, v26.16b
240 and v13.16b, v31.16b, v10.16b
244 shl v10.8h, v2.8h, #(PASS1_BITS)
251 dup v2.2d, v10.d[0]
252 dup v6.2d, v10.d[1]
331 smull v10.4s, v9.4h, XFIX_P_0_298 /* tmp0 = MULTIPLY(tmp0, FIX_0_298631336) */
347 add v10.4s, v10.4s, v18.4s /* tmp0 += z1 */
356 add v10.4s, v10.4s, v22.4s /* tmp0 += z3 */
378 add v14.4s, v6.4s, v10.4s /* tmp13 + tmp0 */
[all …]
/external/libavc/encoder/armv8/
Dih264e_evaluate_intra16x16_modes_av8.s133 dup v10.8h, w10
141 add v0.4h, v0.4h, v10.4h
162 ld1 {v10.8b}, [x6], #8
174 uabdl v16.8h, v0.8b, v10.8b
194 uabal v16.8h, v2.8b, v10.8b
210 uabal v16.8h, v4.8b, v10.8b
226 uabal v16.8h, v6.8b, v10.8b
243 uabal v16.8h, v0.8b, v10.8b
259 uabal v16.8h, v2.8b, v10.8b
275 uabal v16.8h, v4.8b, v10.8b
[all …]
/external/llvm/test/MC/AArch64/
Darm64-simd-ldst.s12 ld1.8b {v7, v8, v9, v10}, [x4]
103 ; CHECK: ld1.8b { v7, v8, v9, v10 }, [x4] ; encoding: [0x87,0x20,0x40,0x0c]
231 ld3.8b {v9, v10, v11}, [x9]
247 st3.8b {v10, v11, v12}, [x9]
264 ; CHECK: ld3.8b { v9, v10, v11 }, [x9] ; encoding: [0x29,0x41,0x40,0x0c]
280 ; CHECK: st3.8b { v10, v11, v12 }, [x9] ; encoding: [0x2a,0x41,0x00,0x0c]
1315 ld1 { v7.4h, v8.4h, v9.4h, v10.4h }, [x1]
1320 ld1 { v7.8h, v8.8h, v9.8h, v10.8h }, [x1]
1325 ld1 { v7.2s, v8.2s, v9.2s, v10.2s }, [x1]
1330 ld1 { v7.4s, v8.4s, v9.4s, v10.4s }, [x1]
[all …]

123456789