/external/boringssl/src/crypto/bn/asm/ |
armv4-mont.pl | 291 vld1.32 {${Bi}[0]}, [$bptr,:32]! 293 vld1.32 {$A0-$A3}, [$aptr]! @ can't specify :32 :-( 295 vld1.32 {${M0}[0]}, [$n0,:32] 312 vld1.32 {$N0-$N3}, [$nptr]! 349 vld1.32 {${Bi}[0]}, [$bptr,:32]! 409 vld1.32 {$A0-$A3}, [$aptr]! 416 vld1.32 {$N0-$N1}, [$nptr]! 424 vld1.32 {$N2-$N3}, [$nptr]! 443 vld1.64 {$Temp}, [sp,:128] 451 vld1.64 {$A0xB}, [$tinptr, :128] [all...] |
/external/clang/test/CodeGen/ |
asm_arm.c | 28 // CHECK: call void asm sideeffect "vld1.32 {d8[],d9[]}, 30 "vld1.32 {d8[],d9[]}, [%1,:32] \n\t"
|
/external/libvpx/libvpx/third_party/libyuv/source/ |
compare_neon.cc | 33 "vld1.8 {q0}, [%0]! \n" 35 "vld1.8 {q1}, [%1]! \n"
|
scale_neon.cc | 53 "vld1.8 {q0, q1}, [%0]! \n" // load pixels and post inc 79 "vld1.8 {q0, q1}, [%0]! \n" // load row 1 and post inc 81 "vld1.8 {q2, q3}, [%1]! \n" // load row 2 and post inc 129 "vld1.8 {q0}, [%0]! \n" // load up 16x4 131 "vld1.8 {q1}, [%3]! \n" 133 "vld1.8 {q2}, [%4]! \n" 135 "vld1.8 {q3}, [%5]! \n" 302 "vld1.8 {q3}, [%3] \n" 306 "vld1.8 {d0, d1, d2, d3}, [%0]! \n" 331 "vld1.16 {q13}, [%5] \n [all...] |
/external/libyuv/files/source/ |
compare_neon.cc | 34 "vld1.8 {q0}, [%0]! \n" 36 "vld1.8 {q1}, [%1]! \n"
|
scale_neon.cc | 51 "vld1.8 {q0, q1}, [%0]! \n" // load pixels and post inc 76 "vld1.8 {q0, q1}, [%0]! \n" // load row 1 and post inc 78 "vld1.8 {q2, q3}, [%1]! \n" // load row 2 and post inc 124 "vld1.8 {q0}, [%0]! \n" // load up 16x4 126 "vld1.8 {q1}, [%3]! \n" 128 "vld1.8 {q2}, [%4]! \n" 130 "vld1.8 {q3}, [%5]! \n" 294 "vld1.8 {q3}, [%3] \n" 297 "vld1.8 {d0, d1, d2, d3}, [%0]! \n" 322 "vld1.16 {q13}, [%5] \n [all...] |
/external/llvm/test/CodeGen/ARM/ |
memcpy-inline.ll | 33 ; CHECK: vld1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1] 37 ; CHECK: vld1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1] 49 ; CHECK: vld1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]! 51 ; CHECK: vld1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1] 60 ; CHECK: vld1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]! 71 ; CHECK: vld1.64 {[[REG3:d[0-9]+]], [[REG4:d[0-9]+]]}, [r1] 104 ; CHECK: vld1.16 120 ; CHECK: vld1.32
|
no-fpu.ll | 10 ; NONEON-NOVFP-NOT: vld1.64 11 ; NONEON-NOT: vld1.64
|
2012-08-09-neon-extload.ll | 21 ; CHECK: vld1.16 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}:16] 35 ; CHECK: vld1.16 {d{{[0-9]+}}[0]}, [{{r[0-9]+}}:16] 53 ; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}:32] 68 ; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}:32] 82 ; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}:32] 97 ; CHECK: vld1.32 {d[[LOAD:[0-9]+]][0]}, [{{r[0-9]+}}:32]
|
unaligned_load_store_vector.ll | 13 ;CHECK: vld1.8 31 ;CHECK: vld1.8 49 ;CHECK: vld1.8 67 ;CHECK: vld1.8 85 ;CHECK: vld1.8 103 ;CHECK: vld1.8 121 ;CHECK: vld1.8 139 ;CHECK: vld1.8 157 ;CHECK: vld1.8 175 ;CHECK: vld1.1 [all...] |
/bionic/libc/arch-arm/cortex-a53/bionic/ |
memcpy_base.S | 91 vld1.8 {d0}, [r1]! 99 vld1.8 {d0 - d3}, [r1]! 100 vld1.8 {d4 - d7}, [r1]! 111 vld1.8 {d0 - d3}, [r1]! 119 vld1.8 {d0, d1}, [r1]! 126 vld1.8 {d0}, [r1]!
|
/frameworks/av/media/libstagefright/codecs/on2/h264dec/source/arm_neon_asm/ |
h264bsdFillRow7.s | 118 VLD1 {qTmp0, qTmp1}, [ref]! 124 VLD1 {dTmp0,dTmp1,dTmp2}, [ref]! 131 VLD1 {dTmp0,dTmp1,dTmp2}, [ref]! 136 VLD1 qTmp0, [ref]! 143 VLD1 qTmp0, [ref]! 148 VLD1 dTmp0, [ref]!
|
/frameworks/rs/cpu_ref/ |
rsCpuIntrinsics_neon_Blur.S | 86 vld1.8 {d30,d31}, [r1] 121 vld1.8 {d20,d21}, [r10], r2 122 vld1.8 {d22,d23}, [r11] 145 vld1.8 {d20,d21}, [r10] 146 vld1.8 {d22,d23}, [r11] 743 vld1.u16 {d24,d25}, [r12:128] 750 vld1.u16 {d24}, [r12:64]! 752 vld1.u16 {d25}, [r12:64] 759 vld1.u16 {d24,d25}, [r12:128] 766 vld1.u16 {d24}, [r12:64] [all...] |
/external/libvpx/libvpx/vpx_dsp/arm/ |
idct16x16_add_neon.asm | 611 vld1.s16 {q0}, [r2], r4 ; load data step2[0] 612 vld1.s16 {q1}, [r2], r4 ; load data step2[1] 613 vld1.s16 {q10}, [r2], r4 ; load data step2[2] 614 vld1.s16 {q11}, [r2], r4 ; load data step2[3] 615 vld1.64 {d12}, [r7], r8 ; load destinatoin data 616 vld1.64 {d13}, [r7], r8 ; load destinatoin data 629 vld1.64 {d12}, [r7], r8 ; load destinatoin data 630 vld1.64 {d13}, [r7], r8 ; load destinatoin data 643 vld1.s16 {q0}, [r2], r4 ; load data step2[4] 644 vld1.s16 {q1}, [r2], r4 ; load data step2[5 [all...] |
/hardware/intel/common/omx-components/videocodec/libvpx_internal/libvpx/vp9/common/arm/neon/ |
vp9_idct16x16_add_neon.asm | 611 vld1.s16 {q0}, [r2], r4 ; load data step2[0] 612 vld1.s16 {q1}, [r2], r4 ; load data step2[1] 613 vld1.s16 {q10}, [r2], r4 ; load data step2[2] 614 vld1.s16 {q11}, [r2], r4 ; load data step2[3] 615 vld1.64 {d12}, [r7], r8 ; load destinatoin data 616 vld1.64 {d13}, [r7], r8 ; load destinatoin data 629 vld1.64 {d12}, [r7], r8 ; load destinatoin data 630 vld1.64 {d13}, [r7], r8 ; load destinatoin data 643 vld1.s16 {q0}, [r2], r4 ; load data step2[4] 644 vld1.s16 {q1}, [r2], r4 ; load data step2[5 [all...] |
/external/boringssl/linux-arm/crypto/modes/ |
ghashv8-armx32.S | 11 vld1.64 {q9},[r1] @ load input H 61 vld1.64 {q9},[r0] @ load Xi 63 vld1.64 {q12,q13},[r1] @ load twisted H, ... 103 vld1.64 {q0},[r0] @ load [rotated] Xi 119 vld1.64 {q12,q13},[r1]! @ load twisted H, ..., H^2 121 vld1.64 {q14},[r1] 124 vld1.64 {q8},[r2]! @ load [rotated] I[0] 132 vld1.64 {q9},[r2],r12 @ load [rotated] I[1] 155 vld1.64 {q8},[r2],r12 @ load [rotated] I[i+2] 164 vld1.64 {q9},[r2],r12 @ load [rotated] I[i+3 [all...] |
/external/libavc/common/arm/ |
ih264_iquant_itrans_recon_a9.s | 167 vld1.32 d30[0], [r1], r3 @I row Load pu1_pred buffer 177 vld1.32 d30[1], [r1], r3 @II row Load pu1_pred buffer 184 vld1.32 d31[0], [r1], r3 @III row Load pu1_pred buf 203 vld1.32 d31[1], [r1], r3 @IV row Load pu1_pred buffer 393 vld1.u8 d0, [r2], r4 @Loading out buffer 16 coeffs 394 vld1.u8 d1, [r2], r4 395 vld1.u8 d2, [r2], r4 396 vld1.u8 d3, [r2], r4 501 vld1.32 {q13}, [r5]! @ Q13 = dequant values row 0 502 vld1.32 {q10}, [r6]! @ Q10 = scaling factors row [all...] |
ih264_weighted_bi_pred_a9q.s | 169 vld1.32 d4[0], [r0], r3 @load row 1 in source 1 170 vld1.32 d4[1], [r0], r3 @load row 2 in source 1 171 vld1.32 d6[0], [r1], r4 @load row 1 in source 2 172 vld1.32 d6[1], [r1], r4 @load row 2 in source 2 175 vld1.32 d8[0], [r0], r3 @load row 3 in source 1 176 vld1.32 d8[1], [r0], r3 @load row 4 in source 1 178 vld1.32 d10[0], [r1], r4 @load row 3 in source 2 179 vld1.32 d10[1], [r1], r4 @load row 4 in source 2 210 vld1.8 d4, [r0], r3 @load row 1 in source 1 211 vld1.8 d6, [r1], r4 @load row 1 in source [all...] |
ih264_intra_pred_luma_8x8_a9q.s | 108 vld1.u8 {q0}, [r0]! @ 109 vld1.u8 {q1}, [r0] 115 vld1.8 {d10[7]}, [r0] @ LOADING SRC[24] AGIN TO THE END FOR p'[ 15, -1 ] = ( p[ 14, -1 ] + 3 * p[ 15, -1 ] + 2 ) >> 2 199 vld1.8 d0, [r0] 271 vld1.u8 {d0}, [r0] 357 vld1.u8 {d0}, [r0] @BOTH LEFT AND TOP AVAILABLE 359 vld1.u8 {d1}, [r0] 373 vld1.u8 {d0}, [r0] 382 vld1.u8 {d0}, [r0] 464 vld1.8 {q0}, [r0 [all...] |
/external/libhevc/common/arm/ |
ihevc_intra_pred_chroma_horz.s | 119 vld1.16 {q0},[r12] @load 16 values. d1[7] will have the 1st value. 121 vld1.16 {q5},[r12] @load 16 values. d1[7] will have the 1st value. 195 @vld1.8 {q15},[r12] @pu1_ref[two_nt + 1 + col] 199 vld1.8 {q0},[r12] 202 vld1.8 {q15},[r12] 274 @vld1.8 {d30},[r12] @pu1_ref[two_nt + 1 + col] 277 vld1.8 {d0},[r12] 279 vld1.8 {d30},[r12] 318 vld1.8 {d30},[r12] @pu1_ref[two_nt + 1 + col] 321 vld1.8 {d0},[r12 [all...] |
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...] |
/external/boringssl/src/crypto/poly1305/ |
poly1305_arm_asm.S | 173 # asm 1: vld1.8 {<y0=reg128#1%bot},[<input_1=int32#2]! 174 # asm 2: vld1.8 {<y0=d0},[<input_1=r1]! 175 vld1.8 {d0},[r1]! 178 # asm 1: vld1.8 {>y12=reg128#2%bot->y12=reg128#2%top},[<input_1=int32#2]! 179 # asm 2: vld1.8 {>y12=d2->y12=d3},[<input_1=r1]! 180 vld1.8 {d2-d3},[r1]! 183 # asm 1: vld1.8 {>y34=reg128#3%bot->y34=reg128#3%top},[<input_1=int32#2]! 184 # asm 2: vld1.8 {>y34=d4->y34=d5},[<input_1=r1]! 185 vld1.8 {d4-d5},[r1]! 195 # asm 1: vld1.8 {<z0=reg128#4%bot},[<input_1=int32#2] [all...] |
/external/llvm/test/Transforms/LoopStrengthReduce/ARM/ |
ivchain-ARM.ll | 242 %12 = tail call <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8* %.05, i32 1) nounwind 244 %14 = tail call <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8* %13, i32 1) nounwind 250 %19 = tail call <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8* %18, i32 1) nounwind 252 %21 = tail call <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8* %20, i32 1) nounwind 258 %26 = tail call <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8* %25, i32 1) nounwind 260 %28 = tail call <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8* %27, i32 1) nounwind 266 %33 = tail call <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8* %32, i32 1) nounwind 268 %35 = tail call <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8* %34, i32 1) nounwind 293 declare <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8*, i32) nounwind readonly 301 ; A9: vld1.8 {d{{[0-9]+}}}, [[BASE:[r[0-9]+]]], [[INC:r[0-9]] [all...] |
/frameworks/av/media/libstagefright/codecs/on2/h264dec/omxdl/arm_neon/vc/m4p10/src/ |
armVCM4P10_InterpolateLuma_HalfDiagHorVer4x4_unsafe_s.s | 111 VLD1 qSrc01, [pSrc], srcStep ;// [a0 a1 a2 a3 ..] 124 VLD1 qSrc01, [pSrc], srcStep ;// [a0 a1 a2 a3 ..] 138 VLD1 qSrc01, [pSrc], srcStep ;// [a0 a1 a2 a3 ..] 155 VLD1 qSrc01, [pSrc], srcStep ;// [a0 a1 a2 a3 ..] 172 VLD1 qSrc01, [pSrc], srcStep ;// [a0 a1 a2 a3 ..] 189 VLD1 qSrc01, [pSrc], srcStep ;// [a0 a1 a2 a3 ..] 206 VLD1 qSrc01, [pSrc], srcStep ;// [a0 a1 a2 a3 ..] 223 VLD1 qSrc01, [pSrc], srcStep ;// [a0 a1 a2 a3 ..] 240 VLD1 qSrc01, [pSrc], srcStep ;// [a0 a1 a2 a3 ..]
|
/frameworks/av/services/audioflinger/ |
AudioResamplerFirProcessNeon.h | 55 "vld1.s32 {d2}, [%[vLR]:64] \n"/* (1) load volumes */\ 56 "vld1.s32 {d3}, %[out] \n"/* (2) unaligned load the output */\ 64 "vld1.s32 {d2}, [%[vLR]:64] \n"/* (1) load volumes*/\ 65 "vld1.s32 {d3}, %[out] \n"/* (2) unaligned load the output*/\ 546 "vld1.16 {q2}, [%[sP]] \n"// (2+0d) load 8 16-bits mono samples 547 "vld1.16 {q3}, [%[sN]]! \n"// (2) load 8 16-bits mono samples 548 "vld1.16 {q8}, [%[coefsP0]:128]! \n"// (1) load 8 16-bits coefs 549 "vld1.16 {q10}, [%[coefsN0]:128]! \n"// (1) load 8 16-bits coefs 606 "vld1.16 {q8}, [%[coefsP0]:128]! \n"// (1) load 8 16-bits coefs 607 "vld1.16 {q10}, [%[coefsN0]:128]! \n"// (1) load 8 16-bits coef [all...] |