| /hardware/intel/common/omx-components/videocodec/libvpx_internal/libvpx/vp8/common/arm/neon/ |
| vp8_subpixelvariance16x16_neon.asm | 47 vld1.s32 {d31}, [r2] ;load first_pass filter
52 vld1.u8 {d2, d3, d4}, [r0], r1 ;load src data
54 vld1.u8 {d5, d6, d7}, [r0], r1
57 vld1.u8 {d8, d9, d10}, [r0], r1
60 vld1.u8 {d11, d12, d13}, [r0], r1
109 vld1.u8 {d2, d3, d4}, [r0], r1 ;load src data
111 vld1.u8 {d5, d6, d7}, [r0], r1
114 vld1.u8 {d8, d9, d10}, [r0], r1
116 vld1.u8 {d11, d12, d13}, [r0], r1
121 vld1.u8 {d14, d15, d16}, [r0], r
[all...] |
| sixtappredict8x8_neon.asm | 51 vld1.s32 {q14, q15}, [r2] ;load first_pass filter
70 vld1.u8 {q3}, [r0], r1 ;load src data
72 vld1.u8 {q4}, [r0], r1
74 vld1.u8 {q5}, [r0], r1
76 vld1.u8 {q6}, [r0], r1
145 vld1.u8 {q3}, [r0], r1 ;load src data
153 vld1.u8 {q4}, [r0], r1
155 vld1.u8 {q5}, [r0], r1
157 vld1.u8 {q6}, [r0], r1
163 ;vld1.u8 {q3}, [r0], r1 ;load src dat
[all...] |
| sixtappredict4x4_neon.asm | 49 vld1.s32 {q14, q15}, [r2] ;load first_pass filter
60 vld1.u8 {q3}, [r0], r1 ;load first 4-line src data
62 vld1.u8 {q4}, [r0], r1
64 vld1.u8 {q5}, [r0], r1
66 vld1.u8 {q6}, [r0], r1
124 vld1.u8 {q3}, [r0], r1 ;load rest 5-line src data
125 vld1.u8 {q4}, [r0], r1
130 vld1.u8 {q5}, [r0], r1
131 vld1.u8 {q6}, [r0], r1
137 vld1.u8 {q11}, [r0], r
[all...] |
| /frameworks/rs/cpu_ref/ |
| rsCpuIntrinsics_neon_Convolve.S | 36 vld1.16 {q0, q1}, [r4]
46 vld1.8 {q13}, [r1], r5
47 vld1.8 {q14}, [r2], r5
48 vld1.8 {q15}, [r3], r5
132 vld1.16 {d0, d1, d2, d3}, [r6]!
133 vld1.16 {d4, d5, d6}, [r6]
145 vld1.8 {d24, d25, d26}, [r1], r7 @ y0 ( y - 2 )
146 vld1.8 {d27, d28, d29}, [r2], r7 @ y0 ( y - 1 )
191 vld1.8 {d24, d25, d26}, [r3], r7 @ y0 ( y )
192 vld1.8 {d27, d28, d29}, [r4], r7 @ y0 ( y + 1
[all...] |
| rsCpuIntrinsics_neon_ColorMatrix.S | 30 vld1.16 {q2}, [r2]!
31 vld1.16 {q3}, [r2]!
32 vld1.32 {d8[],d9[]}, [r2]!
33 vld1.32 {d10[],d11[]}, [r2]!
34 vld1.32 {d12[],d13[]}, [r2]!
35 vld1.32 {d14[],d15[]}, [r2]!
47 vld1.32 {q4}, [r2]!
48 vld1.32 {q5}, [r2]!
49 vld1.32 {q6}, [r2]!
50 vld1.32 {q7}, [r2]
[all...] |
| /external/libhevc/common/arm/ |
| ihevc_inter_pred_chroma_copy_w16out.s | 132 vld1.8 {d0},[r0] @vld1_u8(pu1_src_tmp)
138 vld1.8 {d22},[r5],r2 @vld1_u8(pu1_src_tmp)
143 vld1.8 {d24},[r5],r2 @vld1_u8(pu1_src_tmp)
148 vld1.8 {d26},[r5],r2 @vld1_u8(pu1_src_tmp)
173 vld1.8 {d0},[r0] @vld1_u8(pu1_src_tmp)
179 vld1.8 {d22},[r5],r2 @vld1_u8(pu1_src_tmp)
184 vld1.8 {d24},[r5],r2 @vld1_u8(pu1_src_tmp)
208 vld1.8 {d8},[r0]! @vld1_u8(pu1_src_tmp)
209 vld1.8 {d10},[r6],r2 @vld1_u8(pu1_src_tmp)
210 vld1.8 {d12},[r6],r2 @vld1_u8(pu1_src_tmp
[all...] |
| ihevc_itrans_recon_16x16.s | 147 vld1.16 {d0,d1,d2,d3},[r14] @//d0,d1 are used for storing the constant data
222 vld1.16 d10,[r0],r6
223 vld1.16 d11,[r9],r6
224 vld1.16 d6,[r0],r10
225 vld1.16 d7,[r9],r10
229 vld1.16 d4,[r0],r6
230 vld1.16 d5,[r9],r6
231 vld1.16 d8,[r0],r8
232 vld1.16 d9,[r9],r8
305 vld1.16 d10,[r0],r
[all...] |
| ihevc_itrans_recon_4x4.s | 140 vld1.16 d4,[r8] @loading first row of g_ai2_ihevc_trans_4_transpose
145 vld1.16 d1,[r9] @loading pi2_src 2nd row
146 vld1.16 d3,[r10] @loading pi2_src 4th row
147 vld1.16 d0,[r0],r4 @loading pi2_src 1st row
148 vld1.16 d2,[r0],r4 @loading pi2_src 3rd row
155 vld1.32 d22[0], [r2],r5
182 vld1.32 d22[1], [r2],r5
186 vld1.32 d23[0], [r2],r5
203 vld1.32 d23[1], [r2],r5
|
| ihevc_deblk_chroma_horz.s | 60 vld1.8 {d0},[r0]
66 vld1.8 {d2},[r12]
69 vld1.8 {d4},[r5]
71 vld1.8 {d16},[r6]
|
| ihevc_deblk_chroma_vert.s | 63 vld1.8 {d5},[r8],r1
65 vld1.8 {d17},[r8],r1
67 vld1.8 {d16},[r8],r1
69 vld1.8 {d4},[r8]
|
| ihevc_intra_pred_luma_dc.s | 149 vld1.s8 d0, [r6]! @load from src[nt]
151 vld1.s8 d1, [r8]! @load from src[2nt+1]
158 vld1.s8 d0, [r6]! @load from src[nt] (extra load for 8)
160 vld1.s8 d1, [r8]! @load from src[2nt+1] (extra load for 8)
180 vld1.s8 d0, [r6]! @load from src[nt] (extra load for 16)
183 vld1.s8 d1, [r8]! @load from src[2nt+1] (extra load for 16)
223 vld1.s8 d0, [r8]! @col 1::7 load (prol)
226 vld1.s8 d1, [r9] @row 7::1 (0 also) load (prol)
231 vld1.s8 d6, [r8] @col 8::15 load (prol extra)
295 vld1.s8 d1, [r9] @row 8::15 load (prol extra
[all...] |
| ihevc_itrans_recon_4x4_ttype1.s | 134 vld1.16 d0,[r0],r4 @loading pi2_src 1st row
136 vld1.16 d1,[r0],r4 @loading pi2_src 2nd row
138 vld1.16 d2,[r0],r4 @loading pi2_src 3rd row
140 vld1.16 d3,[r0],r4 @loading pi2_src 4th row
166 vld1.32 d18[0], [r2],r5
181 vld1.32 d18[1], [r2],r5
195 vld1.32 d19[0], [r2],r5
206 vld1.32 d19[1], [r2],r5
|
| /hardware/samsung_slsi/exynos5/libswconverter/ |
| csc_tiled_to_linear_y_neon.s | 86 vld1.8 {q0, q1}, [r8]!
87 vld1.8 {q2, q3}, [r8]!
89 vld1.8 {q4, q5}, [r8]!
90 vld1.8 {q6, q7}, [r8]!
93 vld1.8 {q8, q9}, [r8]!
95 vld1.8 {q10, q11}, [r8]!
98 vld1.8 {q12, q13}, [r8]!
99 vld1.8 {q14, q15}, [r8]!
177 vld1.8 {q0}, [r8]!
178 vld1.8 {q1}, [r8]
[all...] |
| /external/chromium_org/third_party/libvpx/source/libvpx/vp9/common/arm/neon/ |
| vp9_mb_lpf_neon.asm | 34 vld1.8 {d16[]}, [r2] ; load *blimit
35 vld1.8 {d17[]}, [r3] ; load *limit
36 vld1.8 {d18[]}, [r4] ; load *thresh
40 vld1.u8 {d0}, [r8@64], r1 ; p7
41 vld1.u8 {d1}, [r8@64], r1 ; p6
42 vld1.u8 {d2}, [r8@64], r1 ; p5
43 vld1.u8 {d3}, [r8@64], r1 ; p4
44 vld1.u8 {d4}, [r8@64], r1 ; p3
45 vld1.u8 {d5}, [r8@64], r1 ; p2
46 vld1.u8 {d6}, [r8@64], r1 ; p
[all...] |
| /external/libvpx/libvpx/vp8/common/arm/neon/ |
| sixtappredict8x8_neon.asm | 51 vld1.s32 {q14, q15}, [r2] ;load first_pass filter
70 vld1.u8 {q3}, [r0], r1 ;load src data
72 vld1.u8 {q4}, [r0], r1
74 vld1.u8 {q5}, [r0], r1
76 vld1.u8 {q6}, [r0], r1
145 vld1.u8 {q3}, [r0], r1 ;load src data
153 vld1.u8 {q4}, [r0], r1
155 vld1.u8 {q5}, [r0], r1
157 vld1.u8 {q6}, [r0], r1
163 ;vld1.u8 {q3}, [r0], r1 ;load src dat
[all...] |
| sixtappredict4x4_neon.asm | 49 vld1.s32 {q14, q15}, [r2] ;load first_pass filter
60 vld1.u8 {q3}, [r0], r1 ;load first 4-line src data
62 vld1.u8 {q4}, [r0], r1
64 vld1.u8 {q5}, [r0], r1
66 vld1.u8 {q6}, [r0], r1
124 vld1.u8 {q3}, [r0], r1 ;load rest 5-line src data
125 vld1.u8 {q4}, [r0], r1
130 vld1.u8 {q5}, [r0], r1
131 vld1.u8 {q6}, [r0], r1
137 vld1.u8 {q11}, [r0], r
[all...] |
| idct_dequant_full_2x_neon.asm | 25 vld1.16 {q0, q1}, [r1] ; dq (same l/r)
26 vld1.16 {q2, q3}, [r0] ; l q
28 vld1.16 {q4, q5}, [r0] ; r q
32 vld1.32 {d28[0]}, [r2], r3 ; l pre
33 vld1.32 {d28[1]}, [r12], r3 ; r pre
34 vld1.32 {d29[0]}, [r2], r3
35 vld1.32 {d29[1]}, [r12], r3
36 vld1.32 {d30[0]}, [r2], r3
37 vld1.32 {d30[1]}, [r12], r3
38 vld1.32 {d31[0]}, [r2], r
[all...] |
| /external/libvpx/libvpx/vp9/common/arm/neon/ |
| vp9_mb_lpf_neon.asm | 34 vld1.8 {d16[]}, [r2] ; load *blimit
35 vld1.8 {d17[]}, [r3] ; load *limit
36 vld1.8 {d18[]}, [r4] ; load *thresh
40 vld1.u8 {d0}, [r8@64], r1 ; p7
41 vld1.u8 {d1}, [r8@64], r1 ; p6
42 vld1.u8 {d2}, [r8@64], r1 ; p5
43 vld1.u8 {d3}, [r8@64], r1 ; p4
44 vld1.u8 {d4}, [r8@64], r1 ; p3
45 vld1.u8 {d5}, [r8@64], r1 ; p2
46 vld1.u8 {d6}, [r8@64], r1 ; p
[all...] |
| /hardware/intel/common/omx-components/videocodec/libvpx_internal/libvpx/vp9/common/arm/neon/ |
| vp9_mb_lpf_neon.asm | 34 vld1.8 {d16[]}, [r2] ; load *blimit
35 vld1.8 {d17[]}, [r3] ; load *limit
36 vld1.8 {d18[]}, [r4] ; load *thresh
40 vld1.u8 {d0}, [r8@64], r1 ; p7
41 vld1.u8 {d1}, [r8@64], r1 ; p6
42 vld1.u8 {d2}, [r8@64], r1 ; p5
43 vld1.u8 {d3}, [r8@64], r1 ; p4
44 vld1.u8 {d4}, [r8@64], r1 ; p3
45 vld1.u8 {d5}, [r8@64], r1 ; p2
46 vld1.u8 {d6}, [r8@64], r1 ; p
[all...] |
| /external/llvm/test/MC/ARM/ |
| neon-vld-vst-align.s | 5 vld1.8 {d0}, [r4]
6 vld1.8 {d0}, [r4:16]
7 vld1.8 {d0}, [r4:32]
8 vld1.8 {d0}, [r4:64]
9 vld1.8 {d0}, [r4:128]
10 vld1.8 {d0}, [r4:256]
12 @ CHECK: vld1.8 {d0}, [r4] @ encoding: [0x24,0xf9,0x0f,0x07]
14 @ CHECK-ERRORS: vld1.8 {d0}, [r4:16]
17 @ CHECK-ERRORS: vld1.8 {d0}, [r4:32]
19 @ CHECK: vld1.8 {d0}, [r4:64] @ encoding: [0x24,0xf9,0x1f,0x07
[all...] |
| /external/libvpx/libvpx/vp8/encoder/arm/neon/ |
| shortfdct_neon.asm | 35 vld1.16 {d0}, [r0@64], r2
37 vld1.16 {d1}, [r0@64], r2
38 vld1.16 {q8}, [r12@128]! ; d16=5352, d17=2217
39 vld1.16 {d2}, [r0@64], r2
40 vld1.32 {q9, q10}, [r12@128]! ; q9=14500, q10=7500
41 vld1.16 {d3}, [r0@64], r2
46 vld1.32 {q11,q12}, [r12@128] ; q11=12000, q12=51000
116 vld1.16 {q0}, [r0@128], r2
118 vld1.16 {q1}, [r0@128], r2
119 vld1.16 {q8}, [r12@128]! ; d16=5352, d17=221
[all...] |
| /external/openssl/crypto/modes/asm/ |
| ghashv8-armx.S | 10 vld1.64 {q9},[r1] @ load H
34 vld1.64 {q9},[r0] @ load Xi
36 vld1.64 {q12},[r1] @ load twisted H
54 vld1.64 {q0},[r0] @ load [rotated] Xi
58 vld1.64 {q12},[r1] @ load twisted H
62 vld1.64 {q9},[r2],r12 @ load [rotated] inp
89 vld1.64 {q9},[r2],r12 @ load [rotated] inp
|
| /hardware/intel/common/omx-components/videocodec/libvpx_internal/libvpx/vp8/encoder/arm/neon/ |
| shortfdct_neon.asm | 35 vld1.16 {d0}, [r0@64], r2
37 vld1.16 {d1}, [r0@64], r2
38 vld1.16 {q8}, [r12@128]! ; d16=5352, d17=2217
39 vld1.16 {d2}, [r0@64], r2
40 vld1.32 {q9, q10}, [r12@128]! ; q9=14500, q10=7500
41 vld1.16 {d3}, [r0@64], r2
46 vld1.32 {q11,q12}, [r12@128] ; q11=12000, q12=51000
116 vld1.16 {q0}, [r0@128], r2
118 vld1.16 {q1}, [r0@128], r2
119 vld1.16 {q8}, [r12@128]! ; d16=5352, d17=221
[all...] |
| /external/chromium_org/third_party/webrtc/common_audio/signal_processing/ |
| downsample_fast_neon.S | 63 @ move the pointer back to original after advancing 16 bytes by a vld1, and
92 vld1.16 {d2[], d3[]}, [r7], r4 @ coefficients[j]
93 vld1.16 d0[0], [r1], r5 @ data_in[i - j]
94 vld1.16 d0[1], [r1], r5 @ data_in[i + factor - j]
95 vld1.16 d0[2], [r1], r5 @ data_in[i + factor * 2 - j]
96 vld1.16 d0[3], [r1], r5 @ data_in[i + factor * 3 - j]
97 vld1.16 d1[0], [r1], r5 @ data_in[i + factor * 4 - j]
98 vld1.16 d1[1], [r1], r5 @ data_in[i + factor * 5 - j]
99 vld1.16 d1[2], [r1], r5 @ data_in[i + factor * 6 - j]
100 vld1.16 d1[3], [r1], r10 @ data_in[i + factor * 7 - j
[all...] |
| /external/chromium_org/third_party/libjpeg_turbo/simd/ |
| jsimd_arm_neon.S | 241 vld1.16 {d16, d17, d18, d19}, [COEF_BLOCK, :128]!
242 vld1.16 {d0, d1, d2, d3}, [DCT_TABLE, :128]!
243 vld1.16 {d20, d21, d22, d23}, [COEF_BLOCK, :128]!
245 vld1.16 {d4, d5, d6, d7}, [DCT_TABLE, :128]!
247 vld1.16 {d24, d25, d26, d27}, [COEF_BLOCK, :128]!
249 vld1.16 {d0, d1, d2, d3}, [DCT_TABLE, :128]!
251 vld1.16 {d28, d29, d30, d31}, [COEF_BLOCK, :128]
253 vld1.16 {d4, d5, d6, d7}, [DCT_TABLE, :128]!
256 vld1.16 {d0, d1, d2, d3}, [ip, :128] /* load constants */
335 vld1.s16 {d2}, [ip, :64] /* reload constants *
[all...] |
