| /external/libhevc/common/arm64/ |
| D | ihevc_intra_pred_chroma_ver.s | 121 ld2 {v22.8b, v23.8b}, [x6] //16 loads (col 16:31)
132 st2 {v22.8b, v23.8b}, [x2], x11
133 st2 {v22.8b, v23.8b}, [x5], x11
134 st2 {v22.8b, v23.8b}, [x8], x11
135 st2 {v22.8b, v23.8b}, [x10], x11
145 st2 {v22.8b, v23.8b}, [x2], x11
146 st2 {v22.8b, v23.8b}, [x5], x11
147 st2 {v22.8b, v23.8b}, [x8], x11
148 st2 {v22.8b, v23.8b}, [x10], x11
158 st2 {v22.8b, v23.8b}, [x2], x11
[all …]
|
| D | ihevc_intra_pred_luma_vert.s | 122 ld1 {v22.8b, v23.8b}, [x6] //16 loads (col 16:31)
131 st1 {v22.8b, v23.8b}, [x2], x11
132 st1 {v22.8b, v23.8b}, [x5], x11
133 st1 {v22.8b, v23.8b}, [x8], x11
134 st1 {v22.8b, v23.8b}, [x10], x11
144 st1 {v22.8b, v23.8b}, [x2], x11
145 st1 {v22.8b, v23.8b}, [x5], x11
146 st1 {v22.8b, v23.8b}, [x8], x11
147 st1 {v22.8b, v23.8b}, [x10], x11
156 st1 {v22.8b, v23.8b}, [x2], x11
[all …]
|
| D | ihevc_intra_pred_filters_chroma_mode_19_to_25.s | 281 umull v23.8h, v7.8b, v30.8b //(i row)vmull_u8(ref_main_idx, dup_const_32_fract)
284 umlal v23.8h, v19.8b, v31.8b //(i row)vmull_u8(ref_main_idx_1, dup_const_fract)
298 rshrn v23.8b, v23.8h,#5 //(i row)shift_res = vrshrn_n_u16(add_res, 5)
312 st1 {v23.8b},[x2],#8 //(i row)
339 umull v23.8h, v7.8b, v30.8b //(v)vmull_u8(ref_main_idx, dup_const_32_fract)
342 umlal v23.8h, v19.8b, v31.8b //(v)vmull_u8(ref_main_idx_1, dup_const_fract)
364 rshrn v23.8b, v23.8h,#5 //(v)shift_res = vrshrn_n_u16(add_res, 5)
378 st1 {v23.8b},[x0],x3 //(v)
423 umull v23.8h, v7.8b, v30.8b //(i)vmull_u8(ref_main_idx, dup_const_32_fract)
426 umlal v23.8h, v19.8b, v31.8b //(i)vmull_u8(ref_main_idx_1, dup_const_fract)
[all …]
|
| /external/llvm-project/libclc/amdgpu/lib/math/ |
| D | sqrt.cl | 53 double v23 = __clc_builtin_rsq(v01);
54 double v45 = v01 * v23;
55 v23 = v23 * 0.5;
57 double v67 = fma(-v23, v45, 0.5);
60 v23 = fma(v23, v67, v23);
61 v45 = fma(v89, v23, v45);
63 v23 = fma(v67, v23, v45);
65 v23 = ldexp(v23, exp1);
66 return ((x == __builtin_inf()) || (x == 0.0)) ? v01 : v23;
|
| /external/llvm-project/llvm/test/MC/AArch64/ |
| D | armv8.2a-crypto-error.s | 5 sm3tt1a v20.4s, v23.4s, v21.s[4]
6 sm3tt1b v20.4s, v23.4s, v21.s[4]
7 sm3tt2a v20.4s, v23.4s, v21.s[4]
8 sm3tt2b v20.4s, v23.4s, v21.s[4]
9 sm3tt2b v20.4s, v23.4s, v21.s[-1]
|
| D | armv8.2a-crypto-apple.s | 23 sm3ss1.4s v20, v23, v21, v22
24 sm3tt1a.4s v20, v23, v21[3]
25 sm3tt1b.4s v20, v23, v21[3]
26 sm3tt2a.4s v20, v23, v21[3]
27 sm3tt2b.4s v20, v23, v21[3]
|
| D | armv8.2a-crypto.s | 38 sm3ss1 v20.4s, v23.4s, v21.4s, v22.4s
39 sm3tt1a v20.4s, v23.4s, v21.s[3]
40 sm3tt1b v20.4s, v23.4s, v21.s[3]
41 sm3tt2a v20.4s, v23.4s, v21.s[3]
42 sm3tt2b v20.4s, v23.4s, v21.s[3]
|
| /external/llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/ |
| D | mul.ll | 1615 ; GFX7-NEXT: v_mul_lo_u32 v23, v1, v11
1649 ; GFX7-NEXT: v_add_i32_e32 v20, vcc, v20, v23
1650 ; GFX7-NEXT: v_mul_lo_u32 v23, v0, v12
1653 ; GFX7-NEXT: v_add_i32_e32 v20, vcc, v20, v23
1654 ; GFX7-NEXT: v_mul_hi_u32 v23, v3, v8
1657 ; GFX7-NEXT: v_add_i32_e32 v20, vcc, v20, v23
1658 ; GFX7-NEXT: v_mul_hi_u32 v23, v2, v9
1661 ; GFX7-NEXT: v_add_i32_e32 v20, vcc, v20, v23
1662 ; GFX7-NEXT: v_mul_hi_u32 v23, v1, v10
1665 ; GFX7-NEXT: v_add_i32_e32 v20, vcc, v20, v23
[all …]
|
| /external/llvm-project/llvm/test/MC/Hexagon/ |
| D | v60-permute.s | 8 #CHECK: 1fd7d7a2 { v2.ub = vpack(v23.h{{ *}},{{ *}}v23.h):sat }
9 v2.ub=vpack(v23.h,v23.h):sat
29 #CHECK: 1e01d256 { v23:22.h = vunpack(v18.b) }
30 v23:22.h=vunpack(v18.b)
38 #CHECK: 1e01d778 { v25:24.w = vunpack(v23.h) }
39 v25:24.w=vunpack(v23.h)
|
| /external/llvm/test/MC/Hexagon/ |
| D | v60-permute.s | 8 #CHECK: 1fd7d7a2 { v2.ub = vpack(v23.h{{ *}},{{ *}}v23.h):sat }
9 v2.ub=vpack(v23.h,v23.h):sat
29 #CHECK: 1e01d256 { v23:22.h = vunpack(v18.b) }
30 v23:22.h=vunpack(v18.b)
38 #CHECK: 1e01d778 { v25:24.w = vunpack(v23.h) }
39 v25:24.w=vunpack(v23.h)
|
| /external/libavc/encoder/armv8/ |
| D | ih264e_half_pel_av8.s | 177 …sqrshrun v23.8b, v14.8h, #5 //// (a0 + a5 + 20a2 + 20a3 - 5a1 - 5a4 + 16) >> 5 (column1…
183 st1 {v23.8b, v24.8b}, [x1], #16 ////Store dest row1
321 mov v23.d[0], v22.d[1]
338 ext v31.8b, v22.8b , v23.8b , #2
354 ext v31.8b, v23.8b , v24.8b , #2
363 ext v30.8b, v22.8b , v23.8b , #4
364 ext v29.8b, v22.8b , v23.8b , #6
367 ext v28.8b, v22.8b , v23.8b , #2
371 smlsl v2.4s, v23.4h, v0.h[0] //// a0 + a5 + 20a2 + 20a3 - 5a1 - 5a4 (set3)
375 ext v30.8b, v23.8b , v24.8b , #4
[all …]
|
| /external/openscreen/third_party/boringssl/ios-aarch64/crypto/fipsmodule/ |
| D | ghash-neon-armv8.S | 138 zip2 v23.2d, v18.2d, v19.2d
140 eor v22.16b, v22.16b, v23.16b
142 and v23.16b, v23.16b, v25.16b
144 eor v22.16b, v22.16b, v23.16b
146 zip1 v18.2d, v22.2d, v23.2d
148 zip2 v19.2d, v22.2d, v23.2d
207 zip2 v23.2d, v18.2d, v19.2d
209 eor v22.16b, v22.16b, v23.16b
211 and v23.16b, v23.16b, v25.16b
213 eor v22.16b, v22.16b, v23.16b
[all …]
|
| /external/openscreen/third_party/boringssl/win-aarch64/crypto/fipsmodule/ |
| D | ghash-neon-armv8.S | 145 zip2 v23.2d, v18.2d, v19.2d
147 eor v22.16b, v22.16b, v23.16b
149 and v23.16b, v23.16b, v25.16b
151 eor v22.16b, v22.16b, v23.16b
153 zip1 v18.2d, v22.2d, v23.2d
155 zip2 v19.2d, v22.2d, v23.2d
214 zip2 v23.2d, v18.2d, v19.2d
216 eor v22.16b, v22.16b, v23.16b
218 and v23.16b, v23.16b, v25.16b
220 eor v22.16b, v22.16b, v23.16b
[all …]
|
| /external/rust/crates/quiche/deps/boringssl/linux-aarch64/crypto/fipsmodule/ |
| D | ghash-neon-armv8.S | 134 zip2 v23.2d, v18.2d, v19.2d
136 eor v22.16b, v22.16b, v23.16b
138 and v23.16b, v23.16b, v25.16b
140 eor v22.16b, v22.16b, v23.16b
142 zip1 v18.2d, v22.2d, v23.2d
144 zip2 v19.2d, v22.2d, v23.2d
203 zip2 v23.2d, v18.2d, v19.2d
205 eor v22.16b, v22.16b, v23.16b
207 and v23.16b, v23.16b, v25.16b
209 eor v22.16b, v22.16b, v23.16b
[all …]
|
| /external/boringssl/ios-aarch64/crypto/fipsmodule/ |
| D | ghash-neon-armv8.S | 138 zip2 v23.2d, v18.2d, v19.2d
140 eor v22.16b, v22.16b, v23.16b
142 and v23.16b, v23.16b, v25.16b
144 eor v22.16b, v22.16b, v23.16b
146 zip1 v18.2d, v22.2d, v23.2d
148 zip2 v19.2d, v22.2d, v23.2d
207 zip2 v23.2d, v18.2d, v19.2d
209 eor v22.16b, v22.16b, v23.16b
211 and v23.16b, v23.16b, v25.16b
213 eor v22.16b, v22.16b, v23.16b
[all …]
|
| /external/openscreen/third_party/boringssl/linux-aarch64/crypto/fipsmodule/ |
| D | ghash-neon-armv8.S | 139 zip2 v23.2d, v18.2d, v19.2d
141 eor v22.16b, v22.16b, v23.16b
143 and v23.16b, v23.16b, v25.16b
145 eor v22.16b, v22.16b, v23.16b
147 zip1 v18.2d, v22.2d, v23.2d
149 zip2 v19.2d, v22.2d, v23.2d
208 zip2 v23.2d, v18.2d, v19.2d
210 eor v22.16b, v22.16b, v23.16b
212 and v23.16b, v23.16b, v25.16b
214 eor v22.16b, v22.16b, v23.16b
[all …]
|
| /external/rust/crates/ring/pregenerated/ |
| D | ghash-neon-armv8-linux64.S | 136 zip2 v23.2d, v18.2d, v19.2d
138 eor v22.16b, v22.16b, v23.16b
140 and v23.16b, v23.16b, v25.16b
142 eor v22.16b, v22.16b, v23.16b
144 zip1 v18.2d, v22.2d, v23.2d
146 zip2 v19.2d, v22.2d, v23.2d
205 zip2 v23.2d, v18.2d, v19.2d
207 eor v22.16b, v22.16b, v23.16b
209 and v23.16b, v23.16b, v25.16b
211 eor v22.16b, v22.16b, v23.16b
[all …]
|
| D | ghash-neon-armv8-ios64.S | 135 zip2 v23.2d, v18.2d, v19.2d
137 eor v22.16b, v22.16b, v23.16b
139 and v23.16b, v23.16b, v25.16b
141 eor v22.16b, v22.16b, v23.16b
143 zip1 v18.2d, v22.2d, v23.2d
145 zip2 v19.2d, v22.2d, v23.2d
204 zip2 v23.2d, v18.2d, v19.2d
206 eor v22.16b, v22.16b, v23.16b
208 and v23.16b, v23.16b, v25.16b
210 eor v22.16b, v22.16b, v23.16b
[all …]
|
| /external/rust/crates/quiche/deps/boringssl/ios-aarch64/crypto/fipsmodule/ |
| D | ghash-neon-armv8.S | 133 zip2 v23.2d, v18.2d, v19.2d
135 eor v22.16b, v22.16b, v23.16b
137 and v23.16b, v23.16b, v25.16b
139 eor v22.16b, v22.16b, v23.16b
141 zip1 v18.2d, v22.2d, v23.2d
143 zip2 v19.2d, v22.2d, v23.2d
202 zip2 v23.2d, v18.2d, v19.2d
204 eor v22.16b, v22.16b, v23.16b
206 and v23.16b, v23.16b, v25.16b
208 eor v22.16b, v22.16b, v23.16b
[all …]
|
| /external/boringssl/win-aarch64/crypto/fipsmodule/ |
| D | ghash-neon-armv8.S | 145 zip2 v23.2d, v18.2d, v19.2d
147 eor v22.16b, v22.16b, v23.16b
149 and v23.16b, v23.16b, v25.16b
151 eor v22.16b, v22.16b, v23.16b
153 zip1 v18.2d, v22.2d, v23.2d
155 zip2 v19.2d, v22.2d, v23.2d
214 zip2 v23.2d, v18.2d, v19.2d
216 eor v22.16b, v22.16b, v23.16b
218 and v23.16b, v23.16b, v25.16b
220 eor v22.16b, v22.16b, v23.16b
[all …]
|
| /external/boringssl/linux-aarch64/crypto/fipsmodule/ |
| D | ghash-neon-armv8.S | 139 zip2 v23.2d, v18.2d, v19.2d
141 eor v22.16b, v22.16b, v23.16b
143 and v23.16b, v23.16b, v25.16b
145 eor v22.16b, v22.16b, v23.16b
147 zip1 v18.2d, v22.2d, v23.2d
149 zip2 v19.2d, v22.2d, v23.2d
208 zip2 v23.2d, v18.2d, v19.2d
210 eor v22.16b, v22.16b, v23.16b
212 and v23.16b, v23.16b, v25.16b
214 eor v22.16b, v22.16b, v23.16b
[all …]
|
| /external/libavc/common/armv8/ |
| D | ih264_resi_trans_quant_av8.s | 146 shl v23.4h, v21.4h, #1 //u_shift(x3,1,shft)
152 add v25.4h, v23.4h , v20.4h //x6 = u_shift(x3,1,shft) + x2;
155 dup v23.4s, w8 //load round factor values
176 add v20.4s, v0.4s, v23.4s
177 add v21.4s, v1.4s, v23.4s
178 add v22.4s, v2.4s, v23.4s
179 add v23.4s, v3.4s, v23.4s
186 sshl v23.4s, v23.4s, v24.4s //shift row 4
191 xtn v23.4h, v23.4s //narrow row 4
196 neg v27.8h, v23.8h //get negative
[all …]
|
| D | ih264_iquant_itrans_recon_av8.s | 137 ld4 {v20.4h - v23.4h}, [x5] // load pu2_iscal_mat[i], i =0..15
145 mul v23.4h, v23.4h, v29.4h // x[i]=(scale[i] * dequant[i]) where i = 12..14
150 smull v6.4s, v19.4h, v23.4h // q3 = p[i] = (x[i] * trns_coeff[i]) where i = 12..15
216 sub v23.4h, v14.4h, v17.4h // x0 - x3
219 mov v22.d[1], v23.d[0]
330 ld4 {v20.4h - v23.4h}, [x5] // load pu2_iscal_mat[i], i =0..15
338 mul v23.4h, v23.4h, v29.4h // x[i]=(scale[i] * dequant[i]) where i = 12..14
343 smull v6.4s, v19.4h, v23.4h // q3 = p[i] = (x[i] * trns_coeff[i]) where i = 12..15
413 sub v23.4h, v14.4h, v17.4h // x0 - x3
418 srshr v23.4h, v23.4h, #6
[all …]
|
| D | ih264_inter_pred_filters_luma_horz_av8.s | 180 …sqrshrun v23.8b, v14.8h, #5 //// (a0 + a5 + 20a2 + 20a3 - 5a1 - 5a4 + 16) >> 5 (column1…
189 st1 {v23.8b, v24.8b}, [x1], x3 ////Store dest row1
233 …sqrshrun v23.8b, v14.8h, #5 //// (a0 + a5 + 20a2 + 20a3 - 5a1 - 5a4 + 16) >> 5 (column1…
241 st1 {v23.8b, v24.8b}, [x1], x3 ////Store dest row3
285 …sqrshrun v23.8b, v14.8h, #5 //// (a0 + a5 + 20a2 + 20a3 - 5a1 - 5a4 + 16) >> 5 (column1…
295 st1 {v23.8b, v24.8b}, [x1], x3 ////Store dest row5
335 …sqrshrun v23.8b, v14.8h, #5 //// (a0 + a5 + 20a2 + 20a3 - 5a1 - 5a4 + 16) >> 5 (column1…
339 st1 {v23.8b, v24.8b}, [x1], x3 ////Store dest row7
359 ext v23.8b, v5.8b , v6.8b, #1 ////extract a[1] (column1,row1)
365 umlsl v14.8h, v23.8b, v0.8b //// a0 + a5 + 20a2 + 20a3 - 5a1 (column1,row1)
[all …]
|
| /external/libhevc/decoder/arm64/ |
| D | ihevcd_fmt_conv_420sp_to_rgba8888.s | 242 movi v23.8b, #0
254 ZIP1 v27.8b, v22.8b, v23.8b
255 ZIP2 v23.8b, v22.8b, v23.8b
261 mov v22.d[1], v23.d[0]
308 movi v23.8b, #0
320 ZIP1 v27.8b, v22.8b, v23.8b
321 ZIP2 v23.8b, v22.8b, v23.8b
327 mov v22.d[1], v23.d[0]
405 movi v23.8b, #0
417 ZIP1 v27.8b, v22.8b, v23.8b
[all …]
|