| /external/webrtc/webrtc/modules/audio_processing/aec/ |
| aec_rdft_sse2.c | 27 __m128 a01v = _mm_shuffle_ps(a00v, a08v, _MM_SHUFFLE(1, 0, 1, 0));
28 __m128 a23v = _mm_shuffle_ps(a00v, a08v, _MM_SHUFFLE(3, 2, 3, 2));
29 __m128 a45v = _mm_shuffle_ps(a04v, a12v, _MM_SHUFFLE(1, 0, 1, 0));
30 __m128 a67v = _mm_shuffle_ps(a04v, a12v, _MM_SHUFFLE(3, 2, 3, 2));
45 x0w = _mm_shuffle_ps(x0v, x0v, _MM_SHUFFLE(2, 3, 0, 1));
53 const __m128 x3w = _mm_shuffle_ps(x3v, x3v, _MM_SHUFFLE(2, 3, 0, 1));
56 x0w = _mm_shuffle_ps(x0v, x0v, _MM_SHUFFLE(2, 3, 0, 1));
62 x0w = _mm_shuffle_ps(x0v, x0v, _MM_SHUFFLE(2, 3, 0, 1));
70 a00v = _mm_shuffle_ps(a01v, a23v, _MM_SHUFFLE(1, 0, 1, 0));
71 a04v = _mm_shuffle_ps(a45v, a67v, _MM_SHUFFLE(1, 0, 1, 0))
[all...] |
| aec_core_sse2.c | 220 _mm_shuffle_ps(fft0, fft4, _MM_SHUFFLE(2, 0, 2, 0));
222 _mm_shuffle_ps(fft0, fft4, _MM_SHUFFLE(3, 1, 3, 1));
437 sum = _mm_add_ps(sum, _mm_shuffle_ps(sum, sum, _MM_SHUFFLE(0, 0, 3, 2)));
439 sum = _mm_add_ps(sum, _mm_shuffle_ps(sum, sum, _MM_SHUFFLE(1, 1, 1, 1)));
533 __m128 vec_a = _mm_shuffle_ps(vec_3210, vec_7654,
535 __m128 vec_b = _mm_shuffle_ps(vec_3210, vec_7654,
554 __m128 vec_a = _mm_shuffle_ps(vec_3210, vec_7654,
556 __m128 vec_b = _mm_shuffle_ps(vec_3210, vec_7654,
632 _mm_shuffle_ps(vec_sqrtHanning_rev, vec_sqrtHanning_rev,
647 const __m128 vec_a = _mm_shuffle_ps(vec_fft0, vec_fft4
[all...] |
| /external/speex/libspeex/ |
| filters_sse.h | 62 yy = _mm_shuffle_ps(yy, yy, 0);
66 mem[0] = _mm_shuffle_ps(mem[0], mem[0], 0x39);
72 mem[1] = _mm_shuffle_ps(mem[1], mem[1], 0x39);
77 mem[2] = _mm_shuffle_ps(mem[2], mem[2], 0xfd);
86 mem[2] = _mm_shuffle_ps(mem[2], mem[2], 0x55);
112 yy = _mm_shuffle_ps(yy, yy, 0);
116 mem[0] = _mm_shuffle_ps(mem[0], mem[0], 0x39);
122 mem[1] = _mm_shuffle_ps(mem[1], mem[1], 0x39);
167 yy = _mm_shuffle_ps(yy, yy, 0);
171 mem[0] = _mm_shuffle_ps(mem[0], mem[0], 0x39)
[all...] |
| ltp_sse.h | 51 sum = _mm_add_ss(sum, _mm_shuffle_ps(sum, sum, 0x55));
88 sum = _mm_add_ss(sum, _mm_shuffle_ps(sum, sum, 0x55));
|
| resample_sse.h | 51 sum = _mm_add_ss(sum, _mm_shuffle_ps(sum, sum, 0x55));
69 sum = _mm_add_ss(sum, _mm_shuffle_ps(sum, sum, 0x55));
|
| /external/flac/libFLAC/ |
| lpc_intrin_sse.c | 72 d = d0; d = _mm_shuffle_ps(d, d, 0);
82 d = _mm_load_ss(data+i); d = _mm_shuffle_ps(d, d, 0);
83 d0 = _mm_shuffle_ps(d0, d0, _MM_SHUFFLE(2,1,0,3));
110 d = d0; d = _mm_shuffle_ps(d, d, 0);
122 d = _mm_load_ss(data+i); d = _mm_shuffle_ps(d, d, 0);
123 d1 = _mm_shuffle_ps(d1, d1, _MM_SHUFFLE(2,1,0,3));
124 d0 = _mm_shuffle_ps(d0, d0, _MM_SHUFFLE(2,1,0,3));
156 d = d0; d = _mm_shuffle_ps(d, d, 0);
170 d = _mm_load_ss(data+i); d = _mm_shuffle_ps(d, d, 0);
171 d2 = _mm_shuffle_ps(d2, d2, _MM_SHUFFLE(2,1,0,3))
[all...] |
| /external/eigen/Eigen/src/LU/arch/ |
| Inverse_SSE.h | 84 AB = _mm_mul_ps(_mm_shuffle_ps(A,A,0x0F), B);
85 AB = _mm_sub_ps(AB,_mm_mul_ps(_mm_shuffle_ps(A,A,0xA5), _mm_shuffle_ps(B,B,0x4E)));
87 DC = _mm_mul_ps(_mm_shuffle_ps(D,D,0x0F), C);
88 DC = _mm_sub_ps(DC,_mm_mul_ps(_mm_shuffle_ps(D,D,0xA5), _mm_shuffle_ps(C,C,0x4E)));
91 dA = _mm_mul_ps(_mm_shuffle_ps(A, A, 0x5F),A);
94 dB = _mm_mul_ps(_mm_shuffle_ps(B, B, 0x5F),B);
98 dC = _mm_mul_ps(_mm_shuffle_ps(C, C, 0x5F),C);
101 dD = _mm_mul_ps(_mm_shuffle_ps(D, D, 0x5F),D)
[all...] |
| /external/libopus/celt/x86/ |
| pitch_sse.c | 56 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x00),yj));
57 xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x55),
58 _mm_shuffle_ps(yj,y3,0x49)));
59 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0xaa),
60 _mm_shuffle_ps(yj,y3,0x9e)));
61 xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0xff),y3));
96 xsum1 = _mm_add_ss(xsum1, _mm_shuffle_ps(xsum1, xsum1, 0x55));
99 xsum2 = _mm_add_ss(xsum2, _mm_shuffle_ps(xsum2, xsum2, 0x55));
124 sum = _mm_add_ss(sum, _mm_shuffle_ps(sum, sum, 0x55));
155 x2v = _mm_shuffle_ps(x0v, x4v, 0x4e)
[all...] |
| vq_sse2.c | 82 sums = _mm_add_ps(sums, _mm_shuffle_ps(sums, sums, _MM_SHUFFLE(1, 0, 3, 2)));
83 sums = _mm_add_ps(sums, _mm_shuffle_ps(sums, sums, _MM_SHUFFLE(2, 3, 0, 1)));
129 xy4 = _mm_add_ps(xy4, _mm_shuffle_ps(xy4, xy4, _MM_SHUFFLE(1, 0, 3, 2)));
130 xy4 = _mm_add_ps(xy4, _mm_shuffle_ps(xy4, xy4, _MM_SHUFFLE(2, 3, 0, 1)));
132 yy4 = _mm_add_ps(yy4, _mm_shuffle_ps(yy4, yy4, _MM_SHUFFLE(1, 0, 3, 2)));
133 yy4 = _mm_add_ps(yy4, _mm_shuffle_ps(yy4, yy4, _MM_SHUFFLE(2, 3, 0, 1)));
183 max2 = _mm_max_ps(max, _mm_shuffle_ps(max, max, _MM_SHUFFLE(1, 0, 3, 2)));
184 max2 = _mm_max_ps(max2, _mm_shuffle_ps(max2, max2, _MM_SHUFFLE(2, 3, 0, 1)));
|
| /external/eigen/Eigen/src/Core/arch/SSE/ |
| TypeCasting.h | 55 return _mm_shuffle_ps(_mm_cvtpd_ps(a), _mm_cvtpd_ps(b), (1 << 2) | (1 << 6));
|
| PacketMath.h | 74 (_mm_shuffle_ps( (a), (b), ((s)<<6|(r)<<4|(q)<<2|(p))))
77 (_mm_castps_si128( (_mm_shuffle_ps( _mm_castsi128_ps(a), _mm_castsi128_ps(b), ((s)<<6|(r)<<4|(q)<<2|(p))))))
382 to[stride*1] = _mm_cvtss_f32(_mm_shuffle_ps(from, from, 1));
383 to[stride*2] = _mm_cvtss_f32(_mm_shuffle_ps(from, from, 2));
384 to[stride*3] = _mm_cvtss_f32(_mm_shuffle_ps(from, from, 3));
436 { return _mm_shuffle_ps(a,a,0x1B); }
543 return pfirst<Packet4f>(_mm_add_ss(tmp, _mm_shuffle_ps(tmp,tmp, 1)));
595 return pfirst<Packet4f>(_mm_mul_ss(tmp, _mm_shuffle_ps(tmp,tmp, 1)));
615 return pfirst<Packet4f>(_mm_min_ss(tmp, _mm_shuffle_ps(tmp,tmp, 1)));
641 return pfirst<Packet4f>(_mm_max_ss(tmp, _mm_shuffle_ps(tmp,tmp, 1)))
[all...] |
| Complex.h | 125 to[stride*0] = std::complex<float>(_mm_cvtss_f32(_mm_shuffle_ps(from.v, from.v, 0)),
126 _mm_cvtss_f32(_mm_shuffle_ps(from.v, from.v, 1)));
127 to[stride*1] = std::complex<float>(_mm_cvtss_f32(_mm_shuffle_ps(from.v, from.v, 2)),
128 _mm_cvtss_f32(_mm_shuffle_ps(from.v, from.v, 3)));
|
| /frameworks/av/media/libaudioprocessing/ |
| AudioResamplerFirProcessSSE.h | 96 posSamp = _mm_shuffle_ps(posSamp, posSamp, 0x1B);
112 __m128 posSampL = _mm_shuffle_ps(posSamp1, posSamp0, 0x22);
113 __m128 posSampR = _mm_shuffle_ps(posSamp1, posSamp0, 0x77);
114 __m128 negSampL = _mm_shuffle_ps(negSamp0, negSamp1, 0x88);
115 __m128 negSampR = _mm_shuffle_ps(negSamp0, negSamp1, 0xDD);
141 outAccum = _mm_add_ps(outAccum, _mm_shuffle_ps(outAccum, outAccum, 0x11));
|
| /external/webrtc/webrtc/common_audio/resampler/ |
| sinc_resampler_sse.cc | 53 _mm_store_ss(&result, _mm_add_ss(m_sums2, _mm_shuffle_ps(
|
| /external/tensorflow/tensorflow/core/kernels/ |
| sparse_matmul_op.h | 234 return _mm_set1_ps(_mm_cvtss_f32(_mm_shuffle_ps(a, a, 1)));
240 return _mm_set1_ps(_mm_cvtss_f32(_mm_shuffle_ps(a, a, 2)));
246 return _mm_set1_ps(_mm_cvtss_f32(_mm_shuffle_ps(a, a, 3)));
262 return _mm512_broadcastss_ps(_mm_shuffle_ps(a, a, _MM_SHUFFLE(1, 1, 1, 1)));
268 return _mm512_broadcastss_ps(_mm_shuffle_ps(a, a, _MM_SHUFFLE(2, 2, 2, 2)));
274 return _mm512_broadcastss_ps(_mm_shuffle_ps(a, a, _MM_SHUFFLE(3, 3, 3, 3)));
|
| /external/python/cpython3/Modules/_blake2/impl/ |
| blake2s-load-sse41.h | 20 buf = TOI(_mm_shuffle_ps(TOF(m0), TOF(m1), _MM_SHUFFLE(2,0,2,0)));
23 buf = TOI(_mm_shuffle_ps(TOF(m0), TOF(m1), _MM_SHUFFLE(3,1,3,1)));
26 buf = TOI(_mm_shuffle_ps(TOF(m2), TOF(m3), _MM_SHUFFLE(2,0,2,0)));
29 buf = TOI(_mm_shuffle_ps(TOF(m2), TOF(m3), _MM_SHUFFLE(3,1,3,1)));
|
| /external/webrtc/webrtc/common_audio/ |
| fir_filter_sse.cc | 73 _mm_store_ss(out + i, _mm_add_ss(m_sum, _mm_shuffle_ps(m_sum, m_sum, 1)));
|
| /external/eigen/Eigen/src/Core/arch/AVX/ |
| Complex.h | 106 to[stride*0] = std::complex<float>(_mm_cvtss_f32(_mm_shuffle_ps(low, low, 0)),
107 _mm_cvtss_f32(_mm_shuffle_ps(low, low, 1)));
108 to[stride*1] = std::complex<float>(_mm_cvtss_f32(_mm_shuffle_ps(low, low, 2)),
109 _mm_cvtss_f32(_mm_shuffle_ps(low, low, 3)));
112 to[stride*2] = std::complex<float>(_mm_cvtss_f32(_mm_shuffle_ps(high, high, 0)),
113 _mm_cvtss_f32(_mm_shuffle_ps(high, high, 1)));
114 to[stride*3] = std::complex<float>(_mm_cvtss_f32(_mm_shuffle_ps(high, high, 2)),
115 _mm_cvtss_f32(_mm_shuffle_ps(high, high, 3)));
|
| PacketMath.h | 274 to[stride*1] = _mm_cvtss_f32(_mm_shuffle_ps(low, low, 1));
275 to[stride*2] = _mm_cvtss_f32(_mm_shuffle_ps(low, low, 2));
276 to[stride*3] = _mm_cvtss_f32(_mm_shuffle_ps(low, low, 3));
280 to[stride*5] = _mm_cvtss_f32(_mm_shuffle_ps(high, high, 1));
281 to[stride*6] = _mm_cvtss_f32(_mm_shuffle_ps(high, high, 2));
282 to[stride*7] = _mm_cvtss_f32(_mm_shuffle_ps(high, high, 3));
|
| /prebuilts/gcc/linux-x86/host/x86_64-w64-mingw32-4.8/x86_64-w64-mingw32/include/ |
| fvec.h | 60 F32vec4 ftemp = _mm_add_ss(a,_mm_add_ss(_mm_shuffle_ps(a,a,1),_mm_add_ss(_mm_shuffle_ps(a,a,2),_mm_shuffle_ps(a,a,3))));
|
| /external/mesa3d/src/gallium/drivers/swr/rasterizer/core/ |
| frontend.h | 45 __m128 vYsub = _mm_shuffle_ps(vY, vY, _MM_SHUFFLE(3, 0, 2, 1));
55 __m128 vXsub = _mm_shuffle_ps(vX, vX, _MM_SHUFFLE(3, 0, 2, 1));
|
| rasterizer.cpp | [all...] |
| /frameworks/rs/cpu_ref/ |
| rsCpuIntrinsics_x86.cpp | 320 x = _mm_shuffle_ps(x, x, _MM_SHUFFLE(0, 0, 0, 0));
352 x = _mm_shuffle_ps(x, x, _MM_SHUFFLE(0, 0, 0, 0));
360 x = _mm_shuffle_ps(x, x, _MM_SHUFFLE(0, 0, 0, 0));
361 y = _mm_shuffle_ps(y, y, _MM_SHUFFLE(0, 0, 0, 0));
384 g0 = _mm_shuffle_ps(g0, g0, _MM_SHUFFLE(0, 0, 0, 0));
394 g0 = _mm_shuffle_ps(gx, gx, _MM_SHUFFLE(0, 0, 0, 0));
396 g1 = _mm_shuffle_ps(gx, gx, _MM_SHUFFLE(1, 1, 1, 1));
398 g2 = _mm_shuffle_ps(gx, gx, _MM_SHUFFLE(2, 2, 2, 2));
400 g3 = _mm_shuffle_ps(gx, gx, _MM_SHUFFLE(3, 3, 3, 3));
[all...] |
| /external/clang/test/CodeGen/ |
| sse-builtins.c | 658 return _mm_shuffle_ps(A, B, 0);
|
| /system/keymaster/key_blob_utils/ |
| ocb.c | 430 v3 = _mm_castps_si128(_mm_shuffle_ps(_mm_castsi128_ps(v3), _mm_castsi128_ps(v1), 16)); \
432 v3 = _mm_castps_si128(_mm_shuffle_ps(_mm_castsi128_ps(v3), _mm_castsi128_ps(v1), 140)); \
441 kp[idx] = _mm_castps_si128(_mm_shuffle_ps(_mm_castsi128_ps(tmp), _mm_castsi128_ps(x0), 68)); \
443 _mm_castps_si128(_mm_shuffle_ps(_mm_castsi128_ps(x0), _mm_castsi128_ps(x3), 78)); \
[all...] |
