| /frameworks/rs/cpu_ref/ |
| rsCpuIntrinsics_neon_Convolve.S | 70 vmlal.s16 q8, d5, d0[1]
71 vmlal.s16 q8, d6, d0[2]
72 vmlal.s16 q8, d8, d0[3]
73 vmlal.s16 q8, d9, d1[0]
74 vmlal.s16 q8, d10, d1[1]
75 vmlal.s16 q8, d12, d1[2]
76 vmlal.s16 q8, d13, d1[3]
77 vmlal.s16 q8, d14, d2[0]
80 vmlal.s16 q9, d6, d0[1]
81 vmlal.s16 q9, d7, d0[2
[all...] |
| rsCpuIntrinsics_neon_Blur.S | 128 vmlal.u16 q12, d20, \dreg
130 vmlal.u16 q13, d21, \dreg
131 vmlal.u16 q14, d22, \dreg
132 vmlal.u16 q15, d23, \dreg
154 vmlal.u16 q12, d20, \dreg
156 vmlal.u16 q13, d21, \dreg
158 vmlal.u16 q14, d22, \dreg
160 vmlal.u16 q15, d23, \dreg
285 108: vmlal.u16 q14, d16, d2[0]
286 vmlal.u16 q15, d17, d2[0
[all...] |
| /external/libhevc/common/arm/ |
| ihevc_itrans_recon_32x32.s | 222 vmlal.s16 q12,d9,d0[3] @// y1 * cos1 + y3 * cos3(part of b0)
223 vmlal.s16 q13,d9,d2[1] @// y1 * cos3 - y3 * sin1(part of b1)
224 vmlal.s16 q14,d9,d3[3] @// y1 * sin3 - y3 * cos1(part of b2)
225 vmlal.s16 q15,d9,d5[1] @// y1 * sin1 - y3 * sin3(part of b3)
232 vmlal.s16 q10,d11,d0[2]
236 vmlal.s16 q11,d11,d1[2]
239 vmlal.s16 q8,d11,d2[2]
242 vmlal.s16 q9,d11,d3[2]
257 vmlal.s16 q12,d14,d1[1]
258 vmlal.s16 q13,d14,d3[3
[all...] |
| ihevc_inter_pred_filters_luma_vert_w16inp.s | 155 vmlal.s16 q4,d0,d22 @mul_res1 = vmlal_u8(mul_res1, src_tmp1, coeffabs_0)@
157 vmlal.s16 q4,d2,d24 @mul_res1 = vmlal_u8(mul_res1, src_tmp3, coeffabs_2)@
159 vmlal.s16 q4,d3,d25 @mul_res1 = vmlal_u8(mul_res1, src_tmp4, coeffabs_3)@
161 vmlal.s16 q4,d4,d26 @mul_res1 = vmlal_u8(mul_res1, src_tmp1, coeffabs_4)@
163 vmlal.s16 q4,d5,d27 @mul_res1 = vmlal_u8(mul_res1, src_tmp2, coeffabs_5)@
164 vmlal.s16 q4,d6,d28 @mul_res1 = vmlal_u8(mul_res1, src_tmp3, coeffabs_6)@
165 vmlal.s16 q4,d7,d29 @mul_res1 = vmlal_u8(mul_res1, src_tmp4, coeffabs_7)@
171 vmlal.s16 q5,d1,d22 @mul_res2 = vmlal_u8(mul_res2, src_tmp2, coeffabs_0)@
173 vmlal.s16 q5,d3,d24 @mul_res2 = vmlal_u8(mul_res2, src_tmp4, coeffabs_2)@
175 vmlal.s16 q5,d4,d25 @mul_res2 = vmlal_u8(mul_res2, src_tmp1, coeffabs_3)
[all...] |
| ihevc_inter_pred_luma_vert_w16inp_w16out.s | 165 vmlal.s16 q4,d0,d22 @mul_res1 = vmlal_u8(mul_res1, src_tmp1, coeffabs_0)@
167 vmlal.s16 q4,d2,d24 @mul_res1 = vmlal_u8(mul_res1, src_tmp3, coeffabs_2)@
169 vmlal.s16 q4,d3,d25 @mul_res1 = vmlal_u8(mul_res1, src_tmp4, coeffabs_3)@
171 vmlal.s16 q4,d4,d26 @mul_res1 = vmlal_u8(mul_res1, src_tmp1, coeffabs_4)@
173 vmlal.s16 q4,d5,d27 @mul_res1 = vmlal_u8(mul_res1, src_tmp2, coeffabs_5)@
174 vmlal.s16 q4,d6,d28 @mul_res1 = vmlal_u8(mul_res1, src_tmp3, coeffabs_6)@
175 vmlal.s16 q4,d7,d29 @mul_res1 = vmlal_u8(mul_res1, src_tmp4, coeffabs_7)@
181 vmlal.s16 q5,d1,d22 @mul_res2 = vmlal_u8(mul_res2, src_tmp2, coeffabs_0)@
183 vmlal.s16 q5,d3,d24 @mul_res2 = vmlal_u8(mul_res2, src_tmp4, coeffabs_2)@
185 vmlal.s16 q5,d4,d25 @mul_res2 = vmlal_u8(mul_res2, src_tmp1, coeffabs_3)
[all...] |
| ihevc_intra_pred_luma_planar.s | 190 vmlal.u8 q6, d5, d0 @(1)(row+1) * src[nt-1]
193 vmlal.u8 q6, d8, d1 @(1)(col+1) * src[3nt+1]
196 vmlal.u8 q6, d6, d3 @(1)(nt-1-row) * src[2nt+1+col]
199 vmlal.u8 q6, d9, d20 @(1)(nt-1-col) * src[2nt-1-row]
207 vmlal.u8 q15, d5, d0 @(2)
210 vmlal.u8 q15, d8, d1 @(2)
212 vmlal.u8 q15, d6, d3 @(2)
213 vmlal.u8 q15, d9, d21 @(2)
221 vmlal.u8 q14, d5, d0 @(3)
224 vmlal.u8 q14, d8, d1 @(3
[all...] |
| ihevc_inter_pred_chroma_vert_w16inp.s | 150 vmlal.s16 q0,d2,d13
152 vmlal.s16 q4,d3,d13
155 vmlal.s16 q0,d3,d14
156 vmlal.s16 q4,d6,d14
157 vmlal.s16 q0,d6,d15
158 vmlal.s16 q4,d2,d15
195 vmlal.s16 q15,d1,d13
196 vmlal.s16 q15,d2,d14
198 vmlal.s16 q15,d3,d15
203 vmlal.s16 q14,d2,d1
[all...] |
| ihevc_inter_pred_chroma_vert_w16inp_w16out.s | 150 vmlal.s16 q0,d2,d13
152 vmlal.s16 q4,d3,d13
155 vmlal.s16 q0,d3,d14
156 vmlal.s16 q4,d6,d14
157 vmlal.s16 q0,d6,d15
158 vmlal.s16 q4,d2,d15
194 vmlal.s16 q15,d1,d13
195 vmlal.s16 q15,d2,d14
197 vmlal.s16 q15,d3,d15
203 vmlal.s16 q14,d2,d1
[all...] |
| ihevc_itrans_recon_16x16.s | 248 vmlal.s16 q12,d7,d0[3] @// y1 * cos1 + y3 * cos3(part of b0)
249 vmlal.s16 q13,d7,d2[1] @// y1 * cos3 - y3 * sin1(part of b1)
250 vmlal.s16 q14,d7,d3[3] @// y1 * sin3 - y3 * cos1(part of b2)
259 vmlal.s16 q6,d11,d0[2]
261 vmlal.s16 q7,d11,d1[2]
263 vmlal.s16 q8,d11,d2[2]
265 vmlal.s16 q9,d11,d3[2]
270 vmlal.s16 q12,d8,d1[1]
271 vmlal.s16 q13,d8,d3[3]
276 vmlal.s16 q12,d9,d1[3
[all...] |
| ihevc_intra_pred_chroma_planar.s | 185 vmlal.u8 q6, d6, d10 @(nt-1-row) * src[2nt+1+col]
187 vmlal.u8 q6, d8, d1 @(col+1) * src[3nt+1]
189 vmlal.u8 q6, d30, d4 @(nt-1-col) * src[2nt-1-row]
195 vmlal.u8 q14,d6,d11
199 vmlal.u8 q14,d31,d4
201 vmlal.u8 q14,d9,d1
206 vmlal.u8 q13, d19, d10 @(nt-1-row) * src[2nt+1+col]
208 vmlal.u8 q13, d8, d1 @(col+1) * src[3nt+1]
210 vmlal.u8 q13, d30, d3 @(nt-1-col) * src[2nt-1-row]
219 vmlal.u8 q12,d19,d1
[all...] |
| ihevc_itrans_recon_4x4_ttype1.s | 151 vmlal.s16 q3,d0,d4[0] @74 * pi2_src[1] + 29 * pi2_src[0]
152 vmlal.s16 q3,d3,d4[1] @74 * pi2_src[1] + 29 * pi2_src[0] + 55 * pi2_src[3]
153 vmlal.s16 q3,d2,d4[3] @pi2_out[0] = 29* pi2_src[0] + 74 * pi2_src[1] + 84* pi2_src[2] + 55 * pi2_src[3]
156 vmlal.s16 q4,d0,d4[1] @74 * pi2_src[1] + 55 * pi2_src[0]
162 vmlal.s16 q5,d3,d4[2] @pi2_out[2] = 74 * pi2_src[0] - 74 * pi2_src[2] + 74 * pi2_src[3]
167 vmlal.s16 q6,d0,d4[3] @pi2_out[3] = 84 * pi2_src[0] - 74 * pi2_src[1] + 55 * pi2_src[2] - 29 * pi2_src[3]
190 vmlal.s16 q3,d14,d4[0] @74 * pi2_src[1] + 29 * pi2_src[0]
191 vmlal.s16 q3,d17,d4[1] @74 * pi2_src[1] + 29 * pi2_src[0] + 55 * pi2_src[3]
192 vmlal.s16 q3,d16,d4[3] @pi2_out[0] = 29* pi2_src[0] + 74 * pi2_src[1] + 84* pi2_src[2] + 55 * pi2_src[3]
195 vmlal.s16 q4,d14,d4[1] @74 * pi2_src[1] + 55 * pi2_src[0
[all...] |
| ihevc_inter_pred_filters_luma_vert.s | 170 vmlal.u8 q4,d3,d25 @mul_res1 = vmlal_u8(mul_res1, src_tmp4, coeffabs_3)@
172 vmlal.u8 q4,d4,d26 @mul_res1 = vmlal_u8(mul_res1, src_tmp1, coeffabs_4)@
176 vmlal.u8 q4,d6,d28 @mul_res1 = vmlal_u8(mul_res1, src_tmp3, coeffabs_6)@
191 vmlal.u8 q5,d4,d25 @mul_res2 = vmlal_u8(mul_res2, src_tmp1, coeffabs_3)@
193 vmlal.u8 q5,d5,d26 @mul_res2 = vmlal_u8(mul_res2, src_tmp2, coeffabs_4)@
198 vmlal.u8 q5,d7,d28 @mul_res2 = vmlal_u8(mul_res2, src_tmp4, coeffabs_6)@
212 vmlal.u8 q6,d5,d25
213 vmlal.u8 q6,d6,d26
215 vmlal.u8 q6,d16,d28
226 vmlal.u8 q7,d6,d2
[all...] |
| /external/boringssl/ios-arm/crypto/fipsmodule/ |
| armv4-mont.S | 245 vmlal.u32 q6,d29,d4[0]
247 vmlal.u32 q7,d29,d4[1]
248 vmlal.u32 q8,d29,d5[0]
249 vmlal.u32 q9,d29,d5[1]
251 vmlal.u32 q10,d29,d6[0]
253 vmlal.u32 q11,d29,d6[1]
255 vmlal.u32 q12,d29,d7[0]
257 vmlal.u32 q13,d29,d7[1]
277 vmlal.u32 q6,d28,d0[0]
278 vmlal.u32 q7,d28,d0[1
[all...] |
| /external/boringssl/linux-arm/crypto/fipsmodule/ |
| armv4-mont.S | 242 vmlal.u32 q6,d29,d4[0]
244 vmlal.u32 q7,d29,d4[1]
245 vmlal.u32 q8,d29,d5[0]
246 vmlal.u32 q9,d29,d5[1]
248 vmlal.u32 q10,d29,d6[0]
250 vmlal.u32 q11,d29,d6[1]
252 vmlal.u32 q12,d29,d7[0]
254 vmlal.u32 q13,d29,d7[1]
274 vmlal.u32 q6,d28,d0[0]
275 vmlal.u32 q7,d28,d0[1
[all...] |
| /external/boringssl/src/crypto/curve25519/asm/ |
| x25519-asm-arm.S | 330 vmlal.s32 q12,d11,d1
331 vmlal.s32 q12,d12,d0
332 vmlal.s32 q12,d13,d23
333 vmlal.s32 q12,d16,d22
334 vmlal.s32 q12,d7,d21
336 vmlal.s32 q10,d4,d1
337 vmlal.s32 q10,d13,d0
338 vmlal.s32 q10,d6,d23
339 vmlal.s32 q10,d17,d22
341 vmlal.s32 q13,d11,d
[all...] |
| /external/libavc/encoder/arm/ |
| ih264e_half_pel.s | 119 vmlal.u8 q4, d31, d1 @// a0 + a5 + 20a2 (column1,row0)
121 vmlal.u8 q5, d30, d1 @// a0 + a5 + 20a2 (column2,row0)
123 vmlal.u8 q6, d29, d1 @// a0 + a5 + 20a2 (column3,row0)
125 vmlal.u8 q7, d28, d1 @// a0 + a5 + 20a2 (column1,row1)
128 vmlal.u8 q8, d27, d1 @// a0 + a5 + 20a2 (column2,row1)
130 vmlal.u8 q9, d26, d1 @// a0 + a5 + 20a2 (column3,row1)
132 vmlal.u8 q4, d31, d1 @// a0 + a5 + 20a2 + 20a3 (column1,row0)
134 vmlal.u8 q5, d30, d1 @// a0 + a5 + 20a2 + 20a3 (column2,row0)
136 vmlal.u8 q6, d29, d1 @// a0 + a5 + 20a2 + 20a3 (column3,row0)
138 vmlal.u8 q7, d28, d1 @// a0 + a5 + 20a2 + 20a3 (column1,row1
[all...] |
| /external/libavc/common/arm/ |
| ih264_inter_pred_chroma_a9q.s | 149 vmlal.u8 q5, d5, d30
150 vmlal.u8 q5, d3, d29
151 vmlal.u8 q5, d8, d31
157 vmlal.u8 q6, d1, d28
158 vmlal.u8 q6, d9, d31
159 vmlal.u8 q6, d4, d29
176 vmlal.u8 q5, d5, d30
177 vmlal.u8 q5, d3, d29
178 vmlal.u8 q5, d8, d31
182 vmlal.u8 q6, d1, d2
[all...] |
| ih264_inter_pred_filters_luma_horz_a9q.s | 135 vmlal.u8 q4, d31, d1 @// a0 + a5 + 20a2 (column1,row0)
137 vmlal.u8 q5, d30, d1 @// a0 + a5 + 20a2 (column2,row0)
139 vmlal.u8 q7, d28, d1 @// a0 + a5 + 20a2 (column1,row1)
141 vmlal.u8 q8, d27, d1 @// a0 + a5 + 20a2 (column2,row1)
143 vmlal.u8 q4, d31, d1 @// a0 + a5 + 20a2 + 20a3 (column1,row0)
145 vmlal.u8 q5, d30, d1 @// a0 + a5 + 20a2 + 20a3 (column2,row0)
147 vmlal.u8 q7, d28, d1 @// a0 + a5 + 20a2 + 20a3 (column1,row1)
149 vmlal.u8 q8, d27, d1 @// a0 + a5 + 20a2 + 20a3 (column2,row1)
190 vmlal.u8 q7, d25, d1 @// a0 + a5 + 20a2 (column1,row1)
191 vmlal.u8 q7, d24, d1 @// a0 + a5 + 20a2 + 20a3 (column1,row1
[all...] |
| ih264_inter_pred_luma_horz_qpel_a9q.s | 142 vmlal.u8 q4, d31, d1 @// a0 + a5 + 20a2 (column1,row0)
144 vmlal.u8 q5, d30, d1 @// a0 + a5 + 20a2 (column2,row0)
146 vmlal.u8 q7, d28, d1 @// a0 + a5 + 20a2 (column1,row1)
148 vmlal.u8 q8, d27, d1 @// a0 + a5 + 20a2 (column2,row1)
150 vmlal.u8 q4, d31, d1 @// a0 + a5 + 20a2 + 20a3 (column1,row0)
152 vmlal.u8 q5, d30, d1 @// a0 + a5 + 20a2 + 20a3 (column2,row0)
154 vmlal.u8 q7, d28, d1 @// a0 + a5 + 20a2 + 20a3 (column1,row1)
156 vmlal.u8 q8, d27, d1 @// a0 + a5 + 20a2 + 20a3 (column2,row1)
202 vmlal.u8 q7, d25, d1 @// a0 + a5 + 20a2 (column1,row1)
203 vmlal.u8 q7, d24, d1 @// a0 + a5 + 20a2 + 20a3 (column1,row1
[all...] |
| ih264_inter_pred_luma_horz_hpel_vert_hpel_a9q.s | 166 vmlal.s16 q1, d22, d0[0] @// a0 + a5 + 20a2 (column1)
167 vmlal.s16 q15, d23, d0[0] @// a0 + a5 + 20a2 (column1)
172 vmlal.s16 q1, d20, d0[0] @// a0 + a5 + 20a2 + 20a3 (column1)
173 vmlal.s16 q15, d21, d0[0] @// a0 + a5 + 20a2 + 20a3 (column1)
185 vmlal.s16 q1, d22, d0[0] @// a0 + a5 + 20a2 (column2)
186 vmlal.s16 q15, d23, d0[0] @// a0 + a5 + 20a2 (column2)
189 vmlal.s16 q1, d20, d0[0] @// a0 + a5 + 20a2 + 20a3 (column2)
190 vmlal.s16 q15, d21, d0[0] @// a0 + a5 + 20a2 + 20a3 (column2)
225 vmlal.s16 q3, d22, d0[0] @// a0 + a5 + 20a2 (column1)
226 vmlal.s16 q15, d23, d0[0] @// a0 + a5 + 20a2 (column1
[all...] |
| /external/boringssl/src/crypto/poly1305/ |
| poly1305_arm_asm.S | 463 # asm 1: vmlal.u32 <r4=reg128#16,<x01=reg128#9%bot,<z34=reg128#6%top
464 # asm 2: vmlal.u32 <r4=q15,<x01=d16,<z34=d11
465 vmlal.u32 q15,d16,d11
478 # asm 1: vmlal.u32 <r4=reg128#16,<x01=reg128#9%top,<z34=reg128#6%bot
479 # asm 2: vmlal.u32 <r4=q15,<x01=d17,<z34=d10
480 vmlal.u32 q15,d17,d10
493 # asm 1: vmlal.u32 <r4=reg128#16,<x23=reg128#10%bot,<z12=reg128#3%top
494 # asm 2: vmlal.u32 <r4=q15,<x23=d18,<z12=d5
495 vmlal.u32 q15,d18,d5
503 # asm 1: vmlal.u32 <r4=reg128#16,<x23=reg128#10%top,<z12=reg128#3%bo
[all...] |
| /external/llvm/test/MC/ARM/ |
| neon-mul-accum-encoding.s | 24 vmlal.s8 q8, d19, d18
25 vmlal.s16 q8, d19, d18
26 vmlal.s32 q8, d19, d18
27 vmlal.u8 q8, d19, d18
28 vmlal.u16 q8, d19, d18
29 vmlal.u32 q8, d19, d18
31 @ CHECK: vmlal.s8 q8, d19, d18 @ encoding: [0xa2,0x08,0xc3,0xf2]
32 @ CHECK: vmlal.s16 q8, d19, d18 @ encoding: [0xa2,0x08,0xd3,0xf2]
33 @ CHECK: vmlal.s32 q8, d19, d18 @ encoding: [0xa2,0x08,0xe3,0xf2]
34 @ CHECK: vmlal.u8 q8, d19, d18 @ encoding: [0xa2,0x08,0xc3,0xf3
[all...] |
| /external/swiftshader/third_party/LLVM/test/MC/ARM/ |
| neon-mul-accum-encoding.s | 19 @ CHECK: vmlal.s8 q8, d19, d18 @ encoding: [0xa2,0x08,0xc3,0xf2]
20 vmlal.s8 q8, d19, d18
21 @ CHECK: vmlal.s16 q8, d19, d18 @ encoding: [0xa2,0x08,0xd3,0xf2]
22 vmlal.s16 q8, d19, d18
23 @ CHECK: vmlal.s32 q8, d19, d18 @ encoding: [0xa2,0x08,0xe3,0xf2]
24 vmlal.s32 q8, d19, d18
25 @ CHECK: vmlal.u8 q8, d19, d18 @ encoding: [0xa2,0x08,0xc3,0xf3]
26 vmlal.u8 q8, d19, d18
27 @ CHECK: vmlal.u16 q8, d19, d18 @ encoding: [0xa2,0x08,0xd3,0xf3]
28 vmlal.u16 q8, d19, d1
[all...] |
| neon-mul-encoding.s | 22 vmlal.s8 q8, d19, d18
23 vmlal.s16 q8, d19, d18
24 vmlal.s32 q8, d19, d18
25 vmlal.u8 q8, d19, d18
26 vmlal.u16 q8, d19, d18
27 vmlal.u32 q8, d19, d18
29 @ CHECK: vmlal.s8 q8, d19, d18 @ encoding: [0xa2,0x08,0xc3,0xf2]
30 @ CHECK: vmlal.s16 q8, d19, d18 @ encoding: [0xa2,0x08,0xd3,0xf2]
31 @ CHECK: vmlal.s32 q8, d19, d18 @ encoding: [0xa2,0x08,0xe3,0xf2]
32 @ CHECK: vmlal.u8 q8, d19, d18 @ encoding: [0xa2,0x08,0xc3,0xf3
[all...] |
| neont2-mul-accum-encoding.s | 24 vmlal.s8 q8, d19, d18
25 vmlal.s16 q8, d19, d18
26 vmlal.s32 q8, d19, d18
27 vmlal.u8 q8, d19, d18
28 vmlal.u16 q8, d19, d18
29 vmlal.u32 q8, d19, d18
31 @ CHECK: vmlal.s8 q8, d19, d18 @ encoding: [0xc3,0xef,0xa2,0x08]
32 @ CHECK: vmlal.s16 q8, d19, d18 @ encoding: [0xd3,0xef,0xa2,0x08]
33 @ CHECK: vmlal.s32 q8, d19, d18 @ encoding: [0xe3,0xef,0xa2,0x08]
34 @ CHECK: vmlal.u8 q8, d19, d18 @ encoding: [0xc3,0xff,0xa2,0x08
[all...] |
