/third_party/musl/src/string/aarch64/ |
H A D | memset.S | 53 str q0, [dstin] 55 str q0, [dstend, -16] 57 str q0, [dstin, 16] 58 str q0, [dstend, -32] 65 str q0, [dstin, 16] 66 stp q0, q0, [dstin, 32] 67 stp q0, q0, [dstend, -32] 74 str q0, [dsti [all...] |
/third_party/optimized-routines/string/aarch64/ |
H A D | memset.S | 55 str q0, [dstin] 57 str q0, [dstend, -16] 59 str q0, [dstin, 16] 60 str q0, [dstend, -32] 67 str q0, [dstin, 16] 68 stp q0, q0, [dstin, 32] 69 stp q0, q0, [dstend, -32] 76 str q0, [dsti [all...] |
/third_party/node/deps/openssl/config/archs/linux-armv4/asm/crypto/modes/ |
H A D | ghashv8-armx.S | 38 INST(0xa8,0x0e,0xa8,0xf2) @ pmull q0,q12,q12 43 vext.8 q9,q0,q2,#8 @ Karatsuba post-processing 44 veor q10,q0,q2 47 INST(0x26,0x4e,0xe0,0xf2) @ pmull q10,q0,q11 @ 1st phase 51 veor q0,q1,q10 53 vext.8 q10,q0,q0,#8 @ 2nd phase 54 INST(0x26,0x0e,0xa0,0xf2) @ pmull q0,q0,q11 56 veor q14,q0,q1 [all...] |
/third_party/node/deps/openssl/config/archs/linux-armv4/asm_avx2/crypto/modes/ |
H A D | ghashv8-armx.S | 38 INST(0xa8,0x0e,0xa8,0xf2) @ pmull q0,q12,q12 43 vext.8 q9,q0,q2,#8 @ Karatsuba post-processing 44 veor q10,q0,q2 47 INST(0x26,0x4e,0xe0,0xf2) @ pmull q10,q0,q11 @ 1st phase 51 veor q0,q1,q10 53 vext.8 q10,q0,q0,#8 @ 2nd phase 54 INST(0x26,0x0e,0xa0,0xf2) @ pmull q0,q0,q11 56 veor q14,q0,q1 [all...] |
/third_party/ffmpeg/libavcodec/arm/ |
H A D | h264pred_neon.S | 46 vmov.i8 q0, #128 52 vld1.8 {q0}, [r2,:128] 53 add16x8 q0, d0, d1, d0, d1 54 vrshrn.u16 d0, q0, #4 55 vdup.8 q0, d0[0] 63 add16x8 q0, d0, d1, d0, d1 64 vrshrn.u16 d0, q0, #4 65 vdup.8 q0, d0[0] 71 vld1.8 {q0}, [r2,:128] 75 vaddl.u8 q0, d [all...] |
H A D | vp9lpf_neon.S | 48 @ and q0-q7 are used as scratch registers. 49 @ p3 = q8, p0 = q11, q0 = q12, q3 = q15 61 vabd.u8 q5, q12, q13 @ abs(q0 - q1) 67 vabd.u8 q5, q11, q12 @ abs(p0 - q0) 69 vqadd.u8 q5, q5, q5 @ abs(p0 - q0) * 2 74 vqadd.u8 q5, q5, q7 @ abs(p0 - q0) * 2 + abs(p1 - q1) >> 1 75 vcle.u8 q5, q5, q0 87 vabd.u8 q4, q13, q12 @ abs(q1 - q0) 91 vmax.u8 q3, q3, q4 @ max(abs(p1 - p0), abs(q1 - q0)) 97 vsubl.u8 q6, d24, d22 @ q0 [all...] |
H A D | sbrdsp_neon.S | 31 vld1.32 {q0}, [r0,:128] 33 vadd.f32 q0, q0, q1 35 vadd.f32 q0, q0, q2 37 vadd.f32 q0, q0, q3 39 vadd.f32 q0, q0, q8 40 vst1.32 {q0}, [r [all...] |
H A D | ac3dsp_neon.S | 24 vmov.i16 q0, #0 30 vorr q0, q0, q1 34 vorr q0, q0, q2 49 vld1.8 {q0}, [r0,:128] 54 vmin.u8 q0, q0, q1 57 vst1.8 {q0}, [r0,:128]! 63 vdup.16 q0, r [all...] |
H A D | fmtconvert_neon.S | 27 VFP vdup.32 q0, d0[0] 29 NOVFP vdup.32 q0, r2 38 vmul.f32 q9, q3, q0 39 vmul.f32 q10, q8, q0 60 vld1.32 {q0-q1}, [r2,:128]! 64 vcvt.f32.s32 q0, q0 69 vmul.f32 q0, q0, q8 74 vst1.32 {q0 [all...] |
H A D | hpeldsp_neon.S | 28 1: vld1.8 {q0}, [r1], r2 38 vrhadd.u8 q0, q0, q8 47 vst1.64 {q0}, [r0,:128], r2 61 vext.8 q1, q0, q1, #1 62 avg q0, q0, q1 68 vrhadd.u8 q0, q0, q1 72 vst1.8 {q0}, [r [all...] |
H A D | hevcdsp_idct_neon.S | 44 vld1.16 {q0-q1}, [r1, :128] 52 vqadd.s16 q0, q0, q8 54 vqmovun.s16 d0, q0 65 vld1.16 {q0-q1}, [r1, :128] 69 vqadd.s16 q0, q2 74 clip10 q0, q1, q12, q13 90 vld1.16 {q0-q1}, [r1, :128]! 92 vqadd.s16 q0, q9 94 vqmovun.s16 d0, q0 [all...] |
H A D | vp9mc_16bpp_neon.S | 34 vld1.16 {q0, q1}, [r2]! 35 vst1.16 {q0, q1}, [r0, :128]! 55 vld1.16 {q0, q1}, [r0, :128]! 57 vrhadd.u16 q0, q0, q8 62 vst1.16 {q0, q1}, [lr, :128]! 87 vld1.16 {q0, q1}, [r0, :128]! 89 vrhadd.u16 q0, q0, q8 93 vst1.16 {q0, q [all...] |
/third_party/node/deps/openssl/config/archs/linux-armv4/asm_avx2/crypto/aes/ |
H A D | bsaes-armv7.S | 100 veor q10, q0, q9 @ xor with round0 key 139 vshr.u64 q11, q0, #1 149 veor q0, q0, q11 164 vshr.u64 q11, q0, #2 174 veor q0, q0, q11 188 vshr.u64 q11, q0, #4 198 veor q0, q0, q1 [all...] |
/third_party/node/deps/openssl/config/archs/linux-armv4/asm/crypto/aes/ |
H A D | bsaes-armv7.S | 100 veor q10, q0, q9 @ xor with round0 key 139 vshr.u64 q11, q0, #1 149 veor q0, q0, q11 164 vshr.u64 q11, q0, #2 174 veor q0, q0, q11 188 vshr.u64 q11, q0, #4 198 veor q0, q0, q1 [all...] |
/third_party/node/deps/openssl/config/archs/linux-armv4/asm_avx2/crypto/ |
H A D | armv4cpuid.S | 127 vorr q0,q0,q0 146 .byte 0xb0,0xff,0x00,0x03 @ aese.8 q0,q0 148 .byte 0x00,0x03,0xb0,0xf3 @ aese.8 q0,q0 157 .byte 0x00,0xef,0x40,0x0c @ sha1c.32 q0,q0,q0 [all...] |
/third_party/node/deps/openssl/config/archs/linux-armv4/asm/crypto/ |
H A D | armv4cpuid.S | 127 vorr q0,q0,q0 146 .byte 0xb0,0xff,0x00,0x03 @ aese.8 q0,q0 148 .byte 0x00,0x03,0xb0,0xf3 @ aese.8 q0,q0 157 .byte 0x00,0xef,0x40,0x0c @ sha1c.32 q0,q0,q0 [all...] |
/third_party/node/deps/openssl/openssl/crypto/ |
H A D | armv4cpuid.pl | 151 vorr q0,q0,q0 170 .byte 0xb0,0xff,0x00,0x03 @ aese.8 q0,q0 172 .byte 0x00,0x03,0xb0,0xf3 @ aese.8 q0,q0 181 .byte 0x00,0xef,0x40,0x0c @ sha1c.32 q0,q0,q0 [all...] |
/third_party/openssl/crypto/ |
H A D | armv4cpuid.pl | 151 vorr q0,q0,q0 170 .byte 0xb0,0xff,0x00,0x03 @ aese.8 q0,q0 172 .byte 0x00,0x03,0xb0,0xf3 @ aese.8 q0,q0 181 .byte 0x00,0xef,0x40,0x0c @ sha1c.32 q0,q0,q0 [all...] |
/third_party/ffmpeg/libavcodec/ |
H A D | h264dsp_template.c | 122 const int q0 = pix[0]; in h264_loop_filter_luma() local 126 if( FFABS( p0 - q0 ) < alpha && in h264_loop_filter_luma() 128 FFABS( q1 - q0 ) < beta ) { in h264_loop_filter_luma() 135 pix[-2*xstride] = p1 + av_clip( (( p2 + ( ( p0 + q0 + 1 ) >> 1 ) ) >> 1) - p1, -tc_orig, tc_orig ); in h264_loop_filter_luma() 138 if( FFABS( q2 - q0 ) < beta ) { in h264_loop_filter_luma() 140 pix[ xstride] = q1 + av_clip( (( q2 + ( ( p0 + q0 + 1 ) >> 1 ) ) >> 1) - q1, -tc_orig, tc_orig ); in h264_loop_filter_luma() 144 i_delta = av_clip( (((q0 - p0 ) * 4) + (p1 - q1) + 4) >> 3, -tc, tc ); in h264_loop_filter_luma() 146 pix[0] = av_clip_pixel( q0 - i_delta ); /* q0' */ in h264_loop_filter_luma() 178 const int q0 in h264_loop_filter_luma_intra() local 248 const int q0 = pix[0]; h264_loop_filter_chroma() local 296 const int q0 = pix[0]; h264_loop_filter_chroma_intra() local [all...] |
/third_party/ffmpeg/libavresample/arm/ |
H A D | audio_convert_neon.S | 26 vld1.32 {q0}, [r1,:128]! 27 vcvt.s32.f32 q8, q0, #31 35 vld1.32 {q0}, [r1,:128]! 36 vcvt.s32.f32 q0, q0, #31 40 vqrshrn.s32 d6, q0, #16 51 2: vld1.32 {q0}, [r1,:128]! 53 vcvt.s32.f32 q0, q0, #31 57 vqrshrn.s32 d6, q0, #1 [all...] |
/third_party/ffmpeg/libswresample/arm/ |
H A D | audio_convert_neon.S | 27 vld1.32 {q0}, [r1,:128]! 28 vcvt.s32.f32 q8, q0, #31 36 vld1.32 {q0}, [r1,:128]! 37 vcvt.s32.f32 q0, q0, #31 41 vqrshrn.s32 d6, q0, #16 52 2: vld1.32 {q0}, [r1,:128]! 54 vcvt.s32.f32 q0, q0, #31 58 vqrshrn.s32 d6, q0, #1 [all...] |
/third_party/ffmpeg/libavutil/arm/ |
H A D | float_dsp_neon.S | 29 vmul.f32 q8, q0, q2 37 vmul.f32 q10, q0, q2 44 vmul.f32 q8, q0, q2 55 vmul.f32 q8, q0, q2 74 vld1.32 {q0}, [r1,:128]! 78 1: vmla.f32 q8, q0, q15 90 vld1.32 {q0}, [r1,:128]! 102 3: vld1.32 {q0}, [r1,:128]! 104 vmla.f32 q8, q0, q15 119 vld1.32 {q0},[r [all...] |
/third_party/ffmpeg/libavcodec/mips/ |
H A D | vp8_lpf_msa.c | 25 #define VP8_SIMPLE_MASK(p1, p0, q0, q1, b_limit, mask) \ 29 p0_a_sub_q0 = __msa_asub_u_b(p0, q0); \ 142 #define VP8_MBFILTER(p2, p1, p0, q0, q1, q2, mask, hev) \ 155 q0_m = (v16i8) __msa_xori_b(q0, 0x80); \ 214 q0 = __msa_xori_b((v16u8) q0_m, 0x80); \ 301 v16u8 p3, p2, p1, p0, q3, q2, q1, q0; in ff_vp8_v_loop_filter16_msa() local 309 LD_UB8(temp_src, pitch, p3, p2, p1, p0, q0, q1, q2, q3); in ff_vp8_v_loop_filter16_msa() 310 LPF_MASK_HEV(p3, p2, p1, p0, q0, q1, q2, q3, limit, b_limit, thresh, in ff_vp8_v_loop_filter16_msa() 312 VP8_MBFILTER(p2, p1, p0, q0, q1, q2, mask, hev); in ff_vp8_v_loop_filter16_msa() 315 ST_UB4(p2, p1, p0, q0, temp_sr in ff_vp8_v_loop_filter16_msa() 326 v16u8 p3, p2, p1, p0, q3, q2, q1, q0; ff_vp8_v_loop_filter8uv_msa() local 378 v16u8 p3, p2, p1, p0, q3, q2, q1, q0; ff_vp8_h_loop_filter16_msa() local 443 v16u8 p3, p2, p1, p0, q3, q2, q1, q0; ff_vp8_h_loop_filter8uv_msa() local 508 v16u8 p1, p0, q1, q0; ff_vp8_v_loop_filter_simple_msa() local 523 v16u8 p1, p0, q1, q0; ff_vp8_h_loop_filter_simple_msa() local 552 v16u8 p3, p2, p1, p0, q3, q2, q1, q0; ff_vp8_v_loop_filter8uv_inner_msa() local 593 v16u8 p3, p2, p1, p0, q3, q2, q1, q0; ff_vp8_h_loop_filter8uv_inner_msa() local 628 v16u8 p3, p2, p1, p0, q3, q2, q1, q0; ff_vp8_v_loop_filter16_inner_msa() local 648 v16u8 p3, p2, p1, p0, q3, q2, q1, q0; ff_vp8_h_loop_filter16_inner_msa() local [all...] |
/third_party/skia/third_party/externals/libwebp/src/dsp/ |
H A D | dec_neon.c | 49 uint8x16_t* const q0, in Load4x16_NEON() 51 // row0 = p1[0..7]|p0[0..7]|q0[0..7]|q1[0..7] in Load4x16_NEON() 52 // row8 = p1[8..15]|p0[8..15]|q0[8..15]|q1[8..15] in Load4x16_NEON() 57 *q0 = vcombine_u8(row0.val[2], row8.val[2]); in Load4x16_NEON() 71 uint8x16_t* const q0, in Load4x16_NEON() 105 *q0 = vreinterpretq_u8_u16(row02.val[1]); in Load4x16_NEON() 116 uint8x16_t* const p0, uint8x16_t* const q0, uint8x16_t* const q1, in Load8x16_NEON() 119 Load4x16_NEON(src + 2, stride, q0, q1, q2, q3); in Load8x16_NEON() 125 uint8x16_t* const q0, in Load16x4_NEON() 129 *q0 in Load16x4_NEON() 46 Load4x16_NEON(const uint8_t* const src, int stride, uint8x16_t* const p1, uint8x16_t* const p0, uint8x16_t* const q0, uint8x16_t* const q1) Load4x16_NEON() argument 68 Load4x16_NEON(const uint8_t* src, int stride, uint8x16_t* const p1, uint8x16_t* const p0, uint8x16_t* const q0, uint8x16_t* const q1) Load4x16_NEON() argument 113 Load8x16_NEON( const uint8_t* const src, int stride, uint8x16_t* const p3, uint8x16_t* const p2, uint8x16_t* const p1, uint8x16_t* const p0, uint8x16_t* const q0, uint8x16_t* const q1, uint8x16_t* const q2, uint8x16_t* const q3) Load8x16_NEON() argument 122 Load16x4_NEON(const uint8_t* const src, int stride, uint8x16_t* const p1, uint8x16_t* const p0, uint8x16_t* const q0, uint8x16_t* const q1) Load16x4_NEON() argument 133 Load16x8_NEON( const uint8_t* const src, int stride, uint8x16_t* const p3, uint8x16_t* const p2, uint8x16_t* const p1, uint8x16_t* const p0, uint8x16_t* const q0, uint8x16_t* const q1, uint8x16_t* const q2, uint8x16_t* const q3) Load16x8_NEON() argument 142 Load8x8x2_NEON( const uint8_t* const u, const uint8_t* const v, int stride, uint8x16_t* const p3, uint8x16_t* const p2, uint8x16_t* const p1, uint8x16_t* const p0, uint8x16_t* const q0, uint8x16_t* const q1, uint8x16_t* const q2, uint8x16_t* const q3) Load8x8x2_NEON() argument 164 Load8x8x2T_NEON( const uint8_t* const u, const uint8_t* const v, int stride, uint8x16_t* const p3, uint8x16_t* const p2, uint8x16_t* const p1, uint8x16_t* const p0, uint8x16_t* const q0, uint8x16_t* const q1, uint8x16_t* const q2, uint8x16_t* const q3) Load8x8x2T_NEON() argument 235 Store2x16_NEON(const uint8x16_t p0, const uint8x16_t q0, uint8_t* const dst, int stride) Store2x16_NEON() argument 259 Store4x16_NEON(const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, uint8_t* const dst, int stride) Store4x16_NEON() argument 274 Store16x2_NEON(const uint8x16_t p0, const uint8x16_t q0, uint8_t* const dst, int stride) Store16x2_NEON() argument 280 Store16x4_NEON(const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, uint8_t* const dst, int stride) Store16x4_NEON() argument 287 Store8x2x2_NEON(const uint8x16_t p0, const uint8x16_t q0, uint8_t* const u, uint8_t* const v, int stride) Store8x2x2_NEON() argument 298 Store8x4x2_NEON(const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, uint8_t* const u, uint8_t* const v, int stride) Store8x4x2_NEON() argument 317 Store6x8x2_NEON( const uint8x16_t p2, const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, const uint8x16_t q2, uint8_t* u, uint8_t* v, int stride) Store6x8x2_NEON() argument 345 Store4x8x2_NEON(const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, uint8_t* const u, uint8_t* const v, int stride) Store4x8x2_NEON() argument 427 NeedsFilter_NEON(const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, int thresh) NeedsFilter_NEON() argument 450 GetBaseDelta_NEON(const int8x16_t p1, const int8x16_t p0, const int8x16_t q0, const int8x16_t q1) GetBaseDelta_NEON() argument 460 GetBaseDelta0_NEON(const int8x16_t p0, const int8x16_t q0) GetBaseDelta0_NEON() argument 500 DoFilter2_NEON(const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, const uint8x16_t mask, uint8x16_t* const op0, uint8x16_t* const oq0) DoFilter2_NEON() argument 514 uint8x16_t p1, p0, q0, q1, op0, oq0; SimpleVFilter16_NEON() local 524 uint8x16_t p1, p0, q0, q1, oq0, op0; SimpleHFilter16_NEON() local 675 NeedsHev_NEON(const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, int hev_thresh) NeedsHev_NEON() argument 686 NeedsFilter2_NEON(const uint8x16_t p3, const uint8x16_t p2, const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, const uint8x16_t q2, const uint8x16_t q3, int ithresh, int thresh) NeedsFilter2_NEON() argument 711 ApplyFilter4_NEON( const int8x16_t p1, const int8x16_t p0, const int8x16_t q0, const int8x16_t q1, const int8x16_t delta0, uint8x16_t* const op1, uint8x16_t* const op0, uint8x16_t* const oq0, uint8x16_t* const oq1) ApplyFilter4_NEON() argument 730 DoFilter4_NEON( const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, const uint8x16_t mask, const uint8x16_t hev_mask, uint8x16_t* const op1, uint8x16_t* const op0, uint8x16_t* const oq0, uint8x16_t* const oq1) DoFilter4_NEON() argument 764 ApplyFilter6_NEON( const int8x16_t p2, const int8x16_t p1, const int8x16_t p0, const int8x16_t q0, const int8x16_t q1, const int8x16_t q2, const int8x16_t delta, uint8x16_t* const op2, uint8x16_t* const op1, uint8x16_t* const op0, uint8x16_t* const oq0, uint8x16_t* const oq1, uint8x16_t* const oq2) ApplyFilter6_NEON() argument 801 DoFilter6_NEON( const uint8x16_t p2, const uint8x16_t p1, const uint8x16_t p0, const uint8x16_t q0, const uint8x16_t q1, const uint8x16_t q2, const uint8x16_t mask, const uint8x16_t hev_mask, uint8x16_t* const op2, uint8x16_t* const op1, uint8x16_t* const op0, uint8x16_t* const oq0, uint8x16_t* const oq1, uint8x16_t* const oq2) DoFilter6_NEON() argument 839 uint8x16_t p3, p2, p1, p0, q0, q1, q2, q3; VFilter16_NEON() local 856 uint8x16_t p3, p2, p1, p0, q0, q1, q2, q3; HFilter16_NEON() local 878 uint8x16_t q0, q1, q2, q3; VFilter16i_NEON() local 902 uint8x16_t q0, q1, q2, q3; HFilter16i_NEON() local 921 uint8x16_t p3, p2, p1, p0, q0, q1, q2, q3; VFilter8_NEON() local 937 uint8x16_t p3, p2, p1, p0, q0, q1, q2, q3; VFilter8i_NEON() local 954 uint8x16_t p3, p2, p1, p0, q0, q1, q2, q3; HFilter8_NEON() local 969 uint8x16_t p3, p2, p1, p0, q0, q1, q2, q3; HFilter8i_NEON() local [all...] |
/third_party/ffmpeg/libavcodec/x86/ |
H A D | vp9lpf_16bpp.asm | 83 psubw m4, m0 ; q4-q0 84 psubw m5, m0 ; q5-q0 85 psubw m6, m0 ; q6-q0 86 psubw m7, m0 ; q7-q0 87 ABS2 m4, m5, m2, m3 ; abs(q4-q0) | abs(q5-q0) 88 ABS2 m6, m7, m2, m3 ; abs(q6-q0) | abs(q7-q0) 89 pcmpgtw m4, reg_F ; abs(q4-q0) > F 90 pcmpgtw m5, reg_F ; abs(q5-q0) > [all...] |