| /frameworks/base/media/libstagefright/codecs/amrwbenc/src/asm/ARMV5E/ |
| Deemph_32_opt.s | 44 MOV r10, r6, LSL #16 @L_tmp = x_hi[0]<<16
47 ADD r12, r10, r7, LSL #4 @L_tmp += x_lo[0] << 4
48 MOV r10, r12, LSL #3 @L_tmp <<= 3
53 MOV r12, r10, LSL #1 @L_tmp = L_mac(L_tmp, *mem, fac)
58 MOV r10, r6, LSL #16
59 ADD r12, r10, r7, LSL #4
61 MOV r10, r12, LSL #3
64 MOV r12, r10, LSL #1
72 MOV r10, r6, LSL #16
73 ADD r12, r10, r7, LSL #
[all...] |
| cor_h_vec_opt.s | 41 ADD r7, r4, r2, LSL #5 @r7 --- p0 = rrixix[track]
49 ADD r9, r1, r2, LSL #1 @p2 = &vec[pos]
63 MOV r6, r6, LSL #2 @L_sum2 = (L_sum2 << 2)
66 MOV r5, r5, LSL #2 @L_sum1 = (L_sum1 << 2)
71 ADD r9, r3, r2, LSL #1 @address of sign[pos]
83 ADD r9, r9, r4, LSL #1
84 ADD r12, r12, r4, LSL #1
94 ADD r9, r1, r2, LSL #1 @p2 = &vec[pos]
109 MOV r6, r6, LSL #2 @L_sum2 = (L_sum2 << 2)
112 MOV r5, r5, LSL #2 @L_sum1 = (L_sum1 << 2
[all...] |
| /frameworks/base/media/libstagefright/codecs/amrwbenc/src/asm/ARMV7/ |
| Deemph_32_neon.s | 44 MOV r10, r6, LSL #16 @L_tmp = x_hi[0]<<16
47 ADD r12, r10, r7, LSL #4 @L_tmp += x_lo[0] << 4
48 MOV r10, r12, LSL #3 @L_tmp <<= 3
53 MOV r12, r10, LSL #1 @L_tmp = L_mac(L_tmp, *mem, fac)
58 MOV r10, r6, LSL #16
59 ADD r12, r10, r7, LSL #4
61 MOV r10, r12, LSL #3
64 MOV r12, r10, LSL #1
72 MOV r10, r6, LSL #16
73 ADD r12, r10, r7, LSL #
[all...] |
| cor_h_vec_neon.s | 41 ADD r7, r4, r2, LSL #5 @r7 --- p0 = rrixix[track]
50 ADD r9, r1, r2, LSL #1 @p2 = &vec[pos]
64 MOV r6, r6, LSL #2 @L_sum2 = (L_sum2 << 2)
67 MOV r5, r5, LSL #2 @L_sum1 = (L_sum1 << 2)
72 ADD r9, r3, r2, LSL #1 @address of sign[pos]
84 ADD r9, r9, r4, LSL #1
85 ADD r12, r12, r4, LSL #1
95 ADD r9, r1, r2, LSL #1 @p2 = &vec[pos]
110 MOV r6, r6, LSL #2 @L_sum2 = (L_sum2 << 2)
113 MOV r5, r5, LSL #2 @L_sum1 = (L_sum1 << 2
[all...] |
| /frameworks/base/media/libstagefright/codecs/on2/h264dec/omxdl/arm11/api/ |
| armCOMM_BitDec_s.h | 134 ORR $T2, $T2, $T1, LSL #8
135 ORR $BitBuffer, $T2, $BitBuffer, LSL #16
160 MOV $Symbol, $BitBuffer, LSL $BitCount
185 MOV $Symbol, $BitBuffer, LSL $BitCount
211 ORRCS $BitBuffer, $T1, $BitBuffer, LSL #8
236 MOVS $Symbol, $BitBuffer, LSL $BitCount
241 ORRCS $BitBuffer, $T1, $BitBuffer, LSL #8
272 MOVS $Symbol, $BitBuffer, LSL $BitCount
273 ORR $BitBuffer, $T1, $BitBuffer, LSL #8
278 ORRCS $BitBuffer, $T1, $BitBuffer, LSL #
[all...] |
| /frameworks/base/media/libstagefright/codecs/on2/h264dec/omxdl/arm_neon/api/ |
| armCOMM_BitDec_s.h | 134 ORR $T2, $T2, $T1, LSL #8
135 ORR $BitBuffer, $T2, $BitBuffer, LSL #16
160 MOV $Symbol, $BitBuffer, LSL $BitCount
185 MOV $Symbol, $BitBuffer, LSL $BitCount
211 ORRCS $BitBuffer, $T1, $BitBuffer, LSL #8
236 MOVS $Symbol, $BitBuffer, LSL $BitCount
241 ORRCS $BitBuffer, $T1, $BitBuffer, LSL #8
272 MOVS $Symbol, $BitBuffer, LSL $BitCount
273 ORR $BitBuffer, $T1, $BitBuffer, LSL #8
278 ORRCS $BitBuffer, $T1, $BitBuffer, LSL #
[all...] |
| /frameworks/base/media/libstagefright/codecs/on2/h264dec/omxdl/arm_neon/vc/m4p10/src_gcc/ |
| armVCM4P10_InterpolateLuma_Copy_unsafe_s.S | 19 ADD pc,pc,r12,LSL #2
41 ORR r4,r4,r5,LSL #24
44 ORR r8,r8,r9,LSL #24
51 ORR r4,r4,r5,LSL #24
54 ORR r8,r8,r9,LSL #24
63 ORR r4,r4,r5,LSL #16
66 ORR r8,r8,r9,LSL #16
73 ORR r4,r4,r5,LSL #16
76 ORR r8,r8,r9,LSL #16
85 ORR r4,r4,r5,LSL #
[all...] |
| armVCM4P10_InterpolateLuma_Align_unsafe_s.S | 19 ADD pc,pc,r7,LSL #2
37 ORR r7,r7,r10,LSL #24
39 ORR r10,r10,r11,LSL #24
49 ORR r7,r7,r10,LSL #16
51 ORR r10,r10,r11,LSL #16
61 ORR r7,r7,r10,LSL #8
63 ORR r10,r10,r11,LSL #8
78 ADD pc,pc,r7,LSL #2
94 LSL r10,r10,#24
103 LSL r10,r10,#1
[all...] |
| omxVCM4P10_InterpolateLuma_s.S | 23 ADD r6,r6,r7,LSL #2
29 ADD pc,pc,r6,LSL #2
48 ADD r12,r0,r1,LSL #1
53 ADD r12,r2,r3,LSL #1
67 ADD r12,r2,r3,LSL #1
77 ADD r12,r2,r3,LSL #1
91 ADD r12,r2,r3,LSL #1
99 SUB r0,r0,r1,LSL #1
105 ADD r12,r2,r3,LSL #1
114 SUB r0,r0,r1,LSL #
[all...] |
| armVCM4P10_InterpolateLuma_DiagCopy_unsafe_s.S | 37 ORR r11,r10,r11,LSL #8
38 ORR r10,r4,r5,LSL #8
71 ORR r11,r10,r11,LSL #8
72 ORR r10,r4,r5,LSL #8
73 PKHBT r4,r10,r11,LSL #16
93 ORR r11,r10,r11,LSL #8
94 ORR r10,r4,r5,LSL #8
95 PKHBT r4,r10,r11,LSL #16
|
| /frameworks/base/media/libstagefright/codecs/on2/h264dec/omxdl/arm11/vc/m4p10/src/ |
| armVCM4P10_Interpolate_Chroma_s.s | 121 ADD dxEightMinusdx, EightMinusdx, dx, LSL #16
122 ORR iWidth, iWidth, temp, LSL #16
153 ORR x01x00, x00, x01, LSL #16
155 ORR x02x01, x01, x02, LSL #16
157 ORR x11x10, x10, x11, LSL #16
158 ORR x12x11, x11, x12, LSL #16
173 RSB pSrc2, pSrc, pSrc1, LSL #1
180 ORR OutRow0100, OutRow00, OutRow01, LSL #8
190 ORR x21x20, x20, x21, LSL #16
191 ORR x22x21, x21, x22, LSL #16
[all...] |
| omxVCM4P10_DequantTransformResidualFromPairAndAdd_s.s | 83 ORR rowLuma01,rowLuma01,temp3,LSL #16 ;// rowLuma01 = [0b|0a]
92 ;// So we can shift the packed rowLuma values [0b|0a] with a single LSL operation
96 LSL rowLuma01,rowLuma01,shift
97 LSL rowLuma23,rowLuma23,shift
125 PKHBT SrcDst00,SrcDst00,temp1,LSL #16 ;// Pack the first two product values
132 PKHBT SrcDst02,SrcDst02,temp2,LSL #16 ;// Pack the next two product values
136 PKHBT SrcDst10,SrcDst10,temp1,LSL #16 ;// Pack the next two product values
144 PKHBT SrcDst12,SrcDst12,temp2,LSL #16 ;// Pack the next two product values
148 PKHBT SrcDst20,SrcDst20,temp1,LSL #16 ;// Pack the next two product values
160 PKHBT SrcDst22,SrcDst22,temp2,LSL #16 ;// Pack the remaining product value
[all...] |
| armVCM4P10_InterpolateLuma_HalfVer4x4_unsafe_s.s | 107 SUB pSrc, pSrc, srcStep, LSL #2
117 RSB ValCD0, ValEB0, ValCD0, LSL #2 ;// 4*(Off+C+D) - (Off+B+E)
119 LDR ValD, [pSrc, srcStep, LSL #1] ;// Load [d3 d2 d1 d0]
121 RSB ValCD1, ValEB1, ValCD1, LSL #2
126 LDR ValF, [pSrc, srcStep, LSL #2] ;// Load [f3 f2 f1 f0]
128 ADD ValCD0, ValCD0, ValCD0, LSL #2 ;// 5 * [4*(Off+C+D) - (Off+B+E)]
129 ADD ValCD1, ValCD1, ValCD1, LSL #2
132 RSB ValED1, ValCF1, ValED1, LSL #2
134 SUB ValA, pSrc, srcStep, LSL #1
136 RSB ValED0, ValCF0, ValED0, LSL #2 ;// 4*(Off+E+D) - (Off+C+F)
[all...] |
| armVCM4P10_InterpolateLuma_HalfHor4x4_unsafe_s.s | 96 PKHBT ValB, ValA, ValD, LSL #16 ;// [b1 a1 b0 a0]
100 PKHBT ValI, Temp1, Temp2, LSL #16 ;// [00 i1 00 i0]
101 PKHBT ValF, ValE, ValH, LSL #16 ;// [f1 e1 f0 e0]
109 RSB Temp1, Temp3, Temp1, LSL #2
111 ADD Temp1, Temp1, Temp1, LSL #2
118 RSB Temp1, Temp3, Temp1, LSL #2
120 ADD Temp1, Temp1, Temp1, LSL #2
139 ORR Acc0, Acc0, Acc1, LSL #8
140 RSB Temp5, Temp1, Temp2, LSL #2
142 ADD Temp5, Temp5, Temp5, LSL #2
[all...] |
| armVCM4P10_InterpolateLuma_HalfDiagHorVer4x4_unsafe_s.s | 120 PKHBT ValB, ValA, ValD, LSL #16 ;// [b1 a1 b0 a0]
124 PKHBT ValI, Temp1, Temp2, LSL #16 ;// [00 i1 00 i0]
125 PKHBT ValF, ValE, ValH, LSL #16 ;// [f1 e1 f0 e0]
133 RSB Temp1, Temp3, Temp1, LSL #2
135 ADD Temp1, Temp1, Temp1, LSL #2
142 RSB Temp1, Temp3, Temp1, LSL #2
144 ADD Temp1, Temp1, Temp1, LSL #2
157 RSB Temp1, Temp1, Temp2, LSL #2
159 ADD Temp1, Temp1, Temp1, LSL #2
165 RSB Temp1, Temp1, Temp2, LSL #
[all...] |
| armVCM4P10_InterpolateLuma_HalfDiagVerHor4x4_unsafe_s.s | 125 ADD Counter, Temp, Counter, LSL #8 ;// [0 0 H W]
136 SUB pSrc, pSrc, srcStep, LSL #2
145 RSB ValCD0, ValEB0, ValCD0, LSL #2 ;// 4*(Off+C+D) - (Off+B+E)
147 LDR ValD, [pSrc, srcStep, LSL #1] ;// Load [d3 d2 d1 d0]
149 RSB ValCD1, ValEB1, ValCD1, LSL #2
153 LDR ValF, [pSrc, srcStep, LSL #2] ;// Load [f3 f2 f1 f0]
155 ADD ValCD0, ValCD0, ValCD0, LSL #2 ;// 5 * [4*(Off+C+D) - (Off+B+E)]
156 ADD ValCD1, ValCD1, ValCD1, LSL #2
159 RSB ValED1, ValCF1, ValED1, LSL #2
161 SUB ValA, pSrc, srcStep, LSL #
[all...] |
| omxVCM4P10_TransformDequantLumaDCFromPair_s.s | 182 PKHBT trRow00,in00,in10,LSL #16 ;// [1 0] = [f4:f0]
192 PKHBT trRow20,in02,in12,LSL #16 ;// [9 8] = [6 2]
200 PKHBT trRow02,in20,in30,LSL #16 ;// [3 2] = [f12:f8]
213 PKHBT trRow22,in22,in32,LSL #16 ;// [11 10] = [14 10]
259 PKHBT trCol00,rowOp00,rowOp10,LSL #16 ;// [1 0] = [f4:f0]
269 PKHBT trCol20,rowOp02,rowOp12,LSL #16 ;// [9 8] = [6 2]
277 PKHBT trCol02,rowOp20,rowOp30,LSL #16 ;// [3 2] = [f12:f8]
290 PKHBT trCol22,rowOp22,rowOp32,LSL #16 ;// [11 10] = [14 10]
347 LSL Scale, Scale, Shift ;// Scale = Scale << Shift
358 PKHBT out00, temp1, temp2, LSL #14 ;// c0w0 = | Temp2 | Temp1
[all...] |
| omxVCM4P10_PredictIntra_16x16_s.s | 130 LDR pc, [pTable, predMode, LSL #2] ;// Branch to the case based on preMode
299 ORR sum, sum, sum, LSL #8 ;// sum replicated in two halfword
303 ORR tVal6, sum, sum, LSL #16 ;// sum replicated in all bytes
325 RSB tVal14, leftStep, leftStep, LSL #4 ;// tVal14 = 15*leftStep
335 MOV tVal2, tVal2, LSL #4 ;// tVal2 = a = 16 * (pSrcAbove[15] + pSrcLeft[15*leftStep])
337 MOV tVal11, tVal11, LSL #3 ;// 8*[15]-[-1]
341 RSB tVal8, tVal8, tVal8, LSL #3 ;// 7*[14]-[0]
347 ADD tVal8, tVal8, tVal8, LSL #1 ;// 6*[13]-[1]
352 ADD tVal8, tVal8, tVal8, LSL #2 ;// 5*[12]-[2]
357 ADD tVal11, tVal11, tVal8, LSL #2 ;// + 4*[11]-[3
[all...] |
| armVCM4P10_InterpolateLuma_Copy_unsafe_s.s | 78 ORR x0, x0, x1, LSL #24
81 ORR x2, x2, x3, LSL #24
88 ORR x0, x0, x1, LSL #24
91 ORR x2, x2, x3, LSL #24
101 ORR x0, x0, x1, LSL #16
104 ORR x2, x2, x3, LSL #16
112 ORR x0, x0, x1, LSL #16
115 ORR x2, x2, x3, LSL #16
125 ORR x0, x0, x1, LSL #8
128 ORR x2, x2, x3, LSL #
[all...] |
| /frameworks/base/media/libstagefright/codecs/on2/h264dec/source/arm11_asm/ |
| h264bsd_interpolate_ver_half.s | 138 ADD count, partW, partH, LSL #16 ;// |partH|partW|
147 ADD count, count, tmp1, LSL #24 ;// partWidth-1 to top byte
161 ADD tmpa, tmpa, tmpa, LSL #2 ;// 5(G+M)
164 ADD tmpa, plus16, tmpa, LSL #2 ;// 16+20(G+M)
168 ADD tmpb, tmpb, tmpb, LSL #2 ;// 5(C+R)
177 ADD tmpa, tmpa, tmpa, LSL #2 ;// 5(G+M)
179 ADD tmpa, plus16, tmpa, LSL #2 ;// 16+20(G+M)
184 ADD tmpb, tmpb, tmpb, LSL #2 ;// 5(C+R)
191 AND tmpa, tmpa, tmpb, LSL #3 ;// mask and divede by 32
206 ADD tmpa, tmpa, tmpa, LSL #2 ;// 5(G+M
[all...] |
| h264bsd_interpolate_chroma_hor_ver.s | 164 ADD count, count, tmp2, LSL #16 ;// chromaPartHeight-1
165 ADD count, count, tmp2, LSL #24 ;// loop_y
166 ADD count, count, tmp1, LSL #20 ;// chromaPartWidth-1
168 PKHBT valY, valY, yFrac, LSL #16 ;// |yFrac|valY |
182 LDRB tmp5, [ptrA, width, LSL #1]
184 PKHBT tmp1, tmp1, tmp3, LSL #16 ;// |t3|t1|
185 PKHBT tmp3, tmp3, tmp5, LSL #16 ;// |t5|t3|
190 ADD count, count, tmp2, LSL #8
195 LDRB tmp6, [ptrA, width, LSL #1]
197 PKHBT tmp2, tmp2, tmp4, LSL #16 ;// |t4|t2
[all...] |
| h264bsd_interpolate_ver_quarter.s | 137 ADD count, partW, partH, LSL #8 ;// |xx|xx|partH|partW|
139 RSB count, tmp5, count, LSL #8 ;// |xx|partH-1|partW-1|xx|
148 ADD count, count, tmp1, LSL #16 ;// partWidth-1 to top byte
162 ADD tmpa, tmpa, tmpa, LSL #2 ;// 5(G+M)
165 ADD tmpa, plus16, tmpa, LSL #2 ;// 16+20(G+M)
169 ADD tmpb, tmpb, tmpb, LSL #2 ;// 5(C+R)
178 ADD tmpa, tmpa, tmpa, LSL #2 ;// 5(G+M)
180 ADD tmpa, plus16, tmpa, LSL #2 ;// 16+20(G+M)
185 ADD tmpb, tmpb, tmpb, LSL #2 ;// 5(C+R)
189 MOVS tmp1, count, LSL #31 ;// update flags (verOffset
[all...] |
| h264bsd_interpolate_chroma_ver.s | 156 ADD count, count, tmp2, LSL #16 ;// chromaPartHeight-1
157 ADD count, count, tmp2, LSL #24 ;// loop_y
158 ADD count, count, tmp1, LSL #20 ;// chromaPartWidth-1
160 PKHBT valY, valY, yFrac, LSL #16 ;// |yFrac|valY |
161 MOV valY, valY, LSL #3 ;// multiply by 8 in advance
173 ADD count, count, tmp2, LSL #8
177 LDRB tmp3, [ptrA,width, LSL #1] ;// 3 row, 1 col
181 LDRB tmp6, [ptrA,width, LSL #1] ;// 3 row, 2 col
184 PKHBT tmp1, tmp1, tmp2, LSL #16 ;// |B|A|
185 PKHBT tmp2, tmp2, tmp3, LSL #16 ;// |C|B
[all...] |
| /frameworks/base/media/libstagefright/codecs/on2/h264dec/omxdl/arm_neon/vc/m4p10/src/ |
| omxVCM4P10_InterpolateLuma_s.s | 182 ADD index, idx, idy, LSL #2 ;// [index] = [idy][idx]
195 ADD pc, pc, index, LSL #2
219 ADD Temp, pSrc, srcStep, LSL #1
225 ADD Temp, pDst, dstStep, LSL #1
242 ADD Temp, pDst, dstStep, LSL #1
255 ADD Temp, pDst, dstStep, LSL #1
272 ADD Temp, pDst, dstStep, LSL #1
283 SUB pSrc, pSrc, srcStep, LSL #1
289 ADD Temp, pDst, dstStep, LSL #1
301 SUB pSrc, pSrc, srcStep, LSL #
[all...] |
| armVCM4P10_InterpolateLuma_Copy_unsafe_s.s | 78 ORR x0, x0, x1, LSL #24
81 ORR x2, x2, x3, LSL #24
88 ORR x0, x0, x1, LSL #24
91 ORR x2, x2, x3, LSL #24
101 ORR x0, x0, x1, LSL #16
104 ORR x2, x2, x3, LSL #16
112 ORR x0, x0, x1, LSL #16
115 ORR x2, x2, x3, LSL #16
125 ORR x0, x0, x1, LSL #8
128 ORR x2, x2, x3, LSL #
[all...] |
