/external/libhevc/common/arm64/ |
D | ihevc_intra_pred_chroma_planar.s | 173 mov v25.8b, v17.8b 174 zip1 v29.8b, v17.8b, v25.8b 175 zip2 v25.8b, v17.8b, v25.8b 178 sub v31.8b, v2.8b , v25.8b 207 umlal v28.8h, v25.8b, v1.8b 227 umlal v24.8h, v25.8b, v1.8b 253 umlal v20.8h, v25.8b, v1.8b 275 umlal v28.8h, v25.8b, v1.8b 327 mov v25.8b, v17.8b 328 zip1 v29.8b, v17.8b, v25.8b [all …]
|
D | ihevc_itrans_recon_8x8.s | 416 umov x15,v25.d[0] 418 trn1 v25.4h, v2.4h, v6.4h 426 trn1 v2.2s, v25.2s, v27.2s 427 trn2 v3.2s, v25.2s, v27.2s ////x0,x1,x2,x3 first qudrant transposing continued..... 430 trn1 v25.4h, v10.4h, v14.4h 436 trn1 v10.2s, v25.2s, v27.2s 437 trn2 v11.2s, v25.2s, v27.2s ////x4,x5,x6,x7 third qudrant transposing continued..... 441 mov v25.d[0],x15 497 umov x19,v25.d[0] 498 umov x20,v25.d[1] [all …]
|
D | ihevc_intra_pred_luma_planar.s | 220 dup v25.8h,w4 //(4) 232 umlal v25.8h, v5.8b, v0.8b //(4) 235 umlal v25.8h, v17.8b, v1.8b //(4) 238 umlal v25.8h, v6.8b, v3.8b //(4) 241 umlal v25.8h, v19.8b, v23.8b //(4) 260 sshl v25.8h, v25.8h, v29.8h //(4)shr 264 xtn v25.8b, v25.8h //(4) 273 st1 {v25.8b},[x2], x3 //(4)str 8 values 396 dup v25.8h,w4 //(4) 409 umlal v25.8h, v5.8b, v0.8b //(4) [all …]
|
D | ihevc_inter_pred_chroma_horz_w16out.s | 133 dup v25.8b, v2.b[1] //coeffabs_1 = vdup_lane_u8(coeffabs, 1) 206 umull v30.8h, v2.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 225 umull v28.8h, v3.8b, v25.8b 252 umull v22.8h, v10.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 287 umull v20.8h, v11.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 304 umull v30.8h, v2.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 318 umull v28.8h, v3.8b, v25.8b 347 umull v22.8h, v10.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 365 umull v20.8h, v11.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 384 umull v30.8h, v2.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// [all …]
|
D | ihevc_sao_edge_offset_class1_chroma.s | 235 TBL v25.8b, {v1.16b},v23.8b 236 ZIP1 v27.8b, v24.8b, v25.8b 237 ZIP2 v25.8b, v24.8b, v25.8b 249 …SADDW v28.8h, v28.8h , v25.8b //II pi2_tmp_cur_row.val[1] = vaddw_s8(pi2_tmp_cur_row.val… 288 TBL v25.8b, {v1.16b},v23.8b 289 ZIP1 v27.8b, v24.8b, v25.8b 290 ZIP2 v25.8b, v24.8b, v25.8b 301 …SADDW v28.8h, v28.8h , v25.8b //pi2_tmp_cur_row.val[1] = vaddw_s8(pi2_tmp_cur_row.val[1]… 398 TBL v25.8b, {v1.16b},v23.8b 399 ZIP1 v27.8b, v24.8b, v25.8b [all …]
|
D | ihevc_inter_pred_chroma_horz.s | 133 dup v25.8b, v2.b[1] //coeffabs_1 = vdup_lane_u8(coeffabs, 1) 191 umull v30.8h, v2.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 210 umull v28.8h, v3.8b, v25.8b 240 umull v22.8h, v10.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 277 umull v20.8h, v11.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 297 umull v30.8h, v2.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 316 umull v28.8h, v3.8b, v25.8b 354 umull v22.8h, v10.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 370 umull v20.8h, v11.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// 387 umull v30.8h, v2.8b, v25.8b //mul_res = vmull_u8(src[0_3], coeffabs_3)// [all …]
|
/external/llvm/test/MC/Hexagon/ |
D | v60-alu.s | 44 #CHECK: 1cbad95c { v29:28.h = vadd(v25.ub,{{ *}}v26.ub) } 45 v29:28.h=vadd(v25.ub,v26.ub) 50 #CHECK: 1c79c350 { v16.h = vsub(v3.h,{{ *}}v25.h):sat } 51 v16.h=vsub(v3.h,v25.h):sat 77 #CHECK: 1c76dc98 { v25:24.b = vadd(v29:28.b,{{ *}}v23:22.b) } 78 v25:24.b=vadd(v29:28.b,v23:22.b) 92 #CHECK: 1cdcd987 { v7.ub = vavg(v25.ub,{{ *}}v28.ub) } 93 v7.ub=vavg(v25.ub,v28.ub) 125 #CHECK: 1c9acab8 { v25:24.w = vsub(v11:10.w,{{ *}}v27:26.w) } 126 v25:24.w=vsub(v11:10.w,v27:26.w) [all …]
|
/external/llvm-project/llvm/test/MC/Hexagon/ |
D | v60-alu.s | 44 #CHECK: 1cbad95c { v29:28.h = vadd(v25.ub,{{ *}}v26.ub) } 45 v29:28.h=vadd(v25.ub,v26.ub) 50 #CHECK: 1c79c350 { v16.h = vsub(v3.h,{{ *}}v25.h):sat } 51 v16.h=vsub(v3.h,v25.h):sat 77 #CHECK: 1c76dc98 { v25:24.b = vadd(v29:28.b,{{ *}}v23:22.b) } 78 v25:24.b=vadd(v29:28.b,v23:22.b) 92 #CHECK: 1cdcd987 { v7.ub = vavg(v25.ub,{{ *}}v28.ub) } 93 v7.ub=vavg(v25.ub,v28.ub) 125 #CHECK: 1c9acab8 { v25:24.w = vsub(v11:10.w,{{ *}}v27:26.w) } 126 v25:24.w=vsub(v11:10.w,v27:26.w) [all …]
|
/external/llvm-project/llvm/test/CodeGen/RISCV/rvv/ |
D | load-add-store-8.ll | 11 ; CHECK-NEXT: vle8.v v25, (a1) 15 ; CHECK-NEXT: vadd.vv v25, v25, v26 17 ; CHECK-NEXT: vse8.v v25, (a0) 87 ; CHECK-NEXT: vle8.v v25, (a1) 91 ; CHECK-NEXT: vadd.vv v25, v25, v26 93 ; CHECK-NEXT: vse8.v v25, (a0) 106 ; CHECK-NEXT: vle8.v v25, (a1) 110 ; CHECK-NEXT: vadd.vv v25, v25, v26 112 ; CHECK-NEXT: vse8.v v25, (a0) 125 ; CHECK-NEXT: vle8.v v25, (a1) [all …]
|
D | load-add-store-16.ll | 11 ; CHECK-NEXT: vle16.v v25, (a1) 15 ; CHECK-NEXT: vadd.vv v25, v25, v26 17 ; CHECK-NEXT: vse16.v v25, (a0) 87 ; CHECK-NEXT: vle16.v v25, (a1) 91 ; CHECK-NEXT: vadd.vv v25, v25, v26 93 ; CHECK-NEXT: vse16.v v25, (a0) 106 ; CHECK-NEXT: vle16.v v25, (a1) 110 ; CHECK-NEXT: vadd.vv v25, v25, v26 112 ; CHECK-NEXT: vse16.v v25, (a0)
|
/external/libmpeg2/common/armv8/ |
D | impeg2_idct.s | 623 umov x15, v25.d[0] 625 trn1 v25.4h, v2.4h, v6.4h 633 trn1 v2.2s, v25.2s, v27.2s 634 trn2 v3.2s, v25.2s, v27.2s ////x0,x1,x2,x3 first qudrant transposing continued..... 637 trn1 v25.4h, v10.4h, v14.4h 643 trn1 v10.2s, v25.2s, v27.2s 644 trn2 v11.2s, v25.2s, v27.2s ////x4,x5,x6,x7 third qudrant transposing continued..... 648 mov v25.d[0], x15 704 umov x19, v25.d[0] 705 umov x20, v25.d[1] [all …]
|
/external/libavc/common/armv8/ |
D | ih264_resi_trans_quant_av8.s | 97 ld1 {v25.8b}, [x1] //load first 8 pix pred row 4 102 usubl v6.8h, v24.8b, v25.8b //find residue row 4 152 add v25.4h, v23.4h , v20.4h //x6 = u_shift(x3,1,shft) + x2; 162 abs v1.4h, v25.4h //abs val of row 2 167 cmgt v5.4h, v25.4h, #0 194 neg v25.8h, v21.8h //get negative 205 bsl v5.8b, v21.8b, v25.8b //restore sign of row 3 and 4 226 movi v25.8b, #16 //get max nnz 227 sub v26.8b, v25.8b , v0.8b //invert current nnz 287 ld1 {v25.8b}, [x1] //load first 8 pix pred row 4 [all …]
|
/external/libavc/encoder/armv8/ |
D | ih264e_half_pel_av8.s | 179 …sqrshrun v25.8b, v18.8h, #5 //// (a0 + a5 + 20a2 + 20a3 - 5a1 - 5a4 + 16) >> 5 (column3… 184 st1 {v25.h}[0], [x1], x3 330 mov v25.d[0], v24.d[1] 372 ext v31.8b, v24.8b , v25.8b , #2 381 ext v31.8b, v25.8b , v25.8b , #2 386 ext v30.8b, v24.8b , v25.8b , #4 389 ext v29.8b, v24.8b , v25.8b , #6 391 ext v31.8b, v24.8b , v25.8b , #2 398 smlsl v22.4s, v25.4h, v0.h[0] //// a0 + a5 + 20a2 + 20a3 - 5a1 - 5a4 (set5) 443 mov v25.d[0], v24.d[1] [all …]
|
/external/XNNPACK/src/f16-gemm/gen/ |
D | 8x8-minmax-aarch64-neonfp16arith-ld64.S | 57 # C v25 127 MOV v25.16b, v24.16b 154 FMLA v25.8h, v16.8h, v1.h[0] 165 FMLA v25.8h, v17.8h, v1.h[1] 174 FMLA v25.8h, v18.8h, v1.h[2] 183 FMLA v25.8h, v19.8h, v1.h[3] 199 FMUL v25.8h, v25.8h, v20.8h 209 FMAX v25.8h, v25.8h, v21.8h 218 FMIN v25.8h, v25.8h, v22.8h 231 ST1 {v25.16b}, [x16], x0 [all …]
|
/external/libxaac/decoder/armv8/ |
D | ixheaacd_post_twiddle.s | 180 mov v25.D[0], v28.D[1] 190 UZP1 v24.4h, v31.4h, v25.4h 191 UZP2 v25.4h, v31.4h, v25.4h 236 sMLAL v2.4s, v25.4h, v10.4h 272 MOV v25.16B, v24.16B 273 ST2 { v25.4s, v26.4s}, [x7], x8 309 mov v25.D[0], v28.D[1] 320 UZP1 v24.4h, v31.4h, v25.4h 321 UZP2 v25.4h, v31.4h, v25.4h 364 sMLAL v2.4s, v25.4h, v10.4h [all …]
|
/external/XNNPACK/src/f16-gemm/gen-inc/ |
D | 8x8inc-minmax-aarch64-neonfp16arith-ld64.S | 58 # C v25 151 FMLA v25.8h, v16.8h, v1.h[0] 162 FMLA v25.8h, v17.8h, v1.h[1] 171 FMLA v25.8h, v18.8h, v1.h[2] 180 FMLA v25.8h, v19.8h, v1.h[3] 196 FMUL v25.8h, v25.8h, v20.8h 206 FMAX v25.8h, v25.8h, v21.8h 215 FMIN v25.8h, v25.8h, v22.8h 238 ST1 {v25.16b}, [x16], x0 266 FMLA v25.8h, v16.8h, v1.h[0] [all …]
|
/external/XNNPACK/src/f16-gemm/ |
D | 8x8-aarch64-neonfp16arith-ld64.S.in | 57 # C v25 138 MOV v25.16b, v24.16b 165 FMLA v25.8h, v16.8h, v1.h[0] 176 FMLA v25.8h, v17.8h, v1.h[1] 185 FMLA v25.8h, v18.8h, v1.h[2] 194 FMLA v25.8h, v19.8h, v1.h[3] 210 FMUL v25.8h, v25.8h, v20.8h 220 FMAX v25.8h, v25.8h, v21.8h 229 FMIN v25.8h, v25.8h, v22.8h 253 ST1 {v25.16b}, [x16], x0 [all …]
|
/external/XNNPACK/src/qs8-gemm/ |
D | 4x16c4-aarch64-neondot-ld32.S | 29 # C1 x8 v17 v21 v25 v29 70 MOV v25.16b, v24.16b 98 SDOT v25.4s, v6.16b, v1.4b[0] 142 BIC v5.16b, v25.16b, v2.16b 147 SQRDMULH v25.4s, v25.4s, v0.4s 152 SSRA v25.4s, v5.4s, 31 180 SRSHL v25.4s, v25.4s, v1.4s 193 SQXTN v25.4h, v25.4s 203 SQXTN2 v25.8h, v29.4s 212 SQADD v25.8h, v25.8h, v2.8h [all …]
|
/external/XNNPACK/src/f32-igemm/gen/ |
D | 5x8-minmax-aarch64-neonfma-cortex-a57.S | 58 # C v24 v25 102 MOV v25.16b, v21.16b 162 FMLA v25.4s, v13.4s, v4.s[0] 176 FMLA v25.4s, v15.4s, v4.s[1] 190 FMLA v25.4s, v17.4s, v4.s[2] 203 FMLA v25.4s, v19.4s, v4.s[3] 218 FMLA v25.4s, v13.4s, v5.s[0] 232 FMLA v25.4s, v15.4s, v5.s[1] 245 FMLA v25.4s, v17.4s, v5.s[2] 258 FMLA v25.4s, v19.4s, v5.s[3] [all …]
|
D | 5x8-minmax-aarch64-neonfma-cortex-a75.S | 58 # C v24 v25 103 MOV v25.16b, v21.16b 168 FMLA v25.4s, v13.4s, v4.s[0] 182 FMLA v25.4s, v15.4s, v4.s[1] 196 FMLA v25.4s, v17.4s, v4.s[2] 209 FMLA v25.4s, v19.4s, v4.s[3] 224 FMLA v25.4s, v13.4s, v5.s[0] 238 FMLA v25.4s, v15.4s, v5.s[1] 251 FMLA v25.4s, v17.4s, v5.s[2] 264 FMLA v25.4s, v19.4s, v5.s[3] [all …]
|
/external/XNNPACK/src/f32-gemm/gen/ |
D | 5x8-minmax-aarch64-neonfma-cortex-a57.S | 56 # C v24 v25 103 MOV v25.16b, v21.16b 139 FMLA v25.4s, v13.4s, v4.s[0] 153 FMLA v25.4s, v15.4s, v4.s[1] 167 FMLA v25.4s, v17.4s, v4.s[2] 180 FMLA v25.4s, v19.4s, v4.s[3] 195 FMLA v25.4s, v13.4s, v5.s[0] 209 FMLA v25.4s, v15.4s, v5.s[1] 222 FMLA v25.4s, v17.4s, v5.s[2] 235 FMLA v25.4s, v19.4s, v5.s[3] [all …]
|
D | 5x8-minmax-aarch64-neonfma-cortex-a75.S | 56 # C v24 v25 106 MOV v25.16b, v21.16b 150 FMLA v25.4s, v13.4s, v4.s[0] 164 FMLA v25.4s, v15.4s, v4.s[1] 178 FMLA v25.4s, v17.4s, v4.s[2] 191 FMLA v25.4s, v19.4s, v4.s[3] 206 FMLA v25.4s, v13.4s, v5.s[0] 220 FMLA v25.4s, v15.4s, v5.s[1] 233 FMLA v25.4s, v17.4s, v5.s[2] 246 FMLA v25.4s, v19.4s, v5.s[3] [all …]
|
D | 4x8-minmax-aarch64-neonfma-cortex-a55.S | 50 # C v24 v25 106 MOV v25.16b, v21.16b 155 FMLA v25.4s, v17.4s, v1.s[0] 175 FMLA v25.4s, v19.4s, v1.s[1] 205 FMLA v25.4s, v13.4s, v4.s[0] 225 FMLA v25.4s, v15.4s, v4.s[1] 258 FMLA v25.4s, v17.4s, v1.s[0] 278 FMLA v25.4s, v19.4s, v1.s[1] 303 FMLA v25.4s, v13.4s, v4.s[0] 316 FMLA v25.4s, v15.4s, v4.s[1] [all …]
|
D | 4x8-minmax-aarch64-neonfma-cortex-a53.S | 50 # C v24 v25 106 MOV v25.16b, v21.16b 157 FMLA v25.4s, v17.4s, v1.s[0] 176 FMLA v25.4s, v19.4s, v1.s[1] 211 FMLA v25.4s, v13.4s, v4.s[0] 232 FMLA v25.4s, v15.4s, v4.s[1] 269 FMLA v25.4s, v17.4s, v1.s[0] 288 FMLA v25.4s, v19.4s, v1.s[1] 314 FMLA v25.4s, v13.4s, v4.s[0] 327 FMLA v25.4s, v15.4s, v4.s[1] [all …]
|
/external/XNNPACK/src/f32-gemm/gen-inc/ |
D | 5x8inc-minmax-aarch64-neonfma-cortex-a57.S | 57 # C v24 v25 138 FMLA v25.4s, v13.4s, v4.s[0] 152 FMLA v25.4s, v15.4s, v4.s[1] 166 FMLA v25.4s, v17.4s, v4.s[2] 179 FMLA v25.4s, v19.4s, v4.s[3] 194 FMLA v25.4s, v13.4s, v5.s[0] 208 FMLA v25.4s, v15.4s, v5.s[1] 221 FMLA v25.4s, v17.4s, v5.s[2] 234 FMLA v25.4s, v19.4s, v5.s[3] 252 FMLA v25.4s, v13.4s, v4.s[0] [all …]
|