| /external/webrtc/webrtc/common_audio/resampler/ |
| sinc_resampler_sse.cc | 32 m_sums1 = _mm_add_ps(m_sums1, _mm_mul_ps(m_input, _mm_load_ps(k1 + i)));
33 m_sums2 = _mm_add_ps(m_sums2, _mm_mul_ps(m_input, _mm_load_ps(k2 + i)));
38 m_sums1 = _mm_add_ps(m_sums1, _mm_mul_ps(m_input, _mm_load_ps(k1 + i)));
39 m_sums2 = _mm_add_ps(m_sums2, _mm_mul_ps(m_input, _mm_load_ps(k2 + i)));
48 m_sums1 = _mm_add_ps(m_sums1, m_sums2);
52 m_sums2 = _mm_add_ps(_mm_movehl_ps(m_sums1, m_sums1), m_sums1);
|
| /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),
59 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0xaa),
61 xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0xff),y3));
65 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_load1_ps(x+j),_mm_loadu_ps(y+j)));
68 xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_load1_ps(x+j),_mm_loadu_ps(y+j)));
71 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_load1_ps(x+j),_mm_loadu_ps(y+j)));
75 _mm_storeu_ps(sum,_mm_add_ps(xsum1,xsum2));
91 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(xi, y1i));
92 xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(xi, y2i))
[all...] |
| vq_sse2.c | 75 sums = _mm_add_ps(sums, x4);
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)));
121 xy4 = _mm_add_ps(xy4, _mm_mul_ps(x4, y4));
122 yy4 = _mm_add_ps(yy4, _mm_mul_ps(y4, y4));
124 _mm_storeu_ps(&y[j], _mm_add_ps(y4, y4));
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)))
[all...] |
| /external/speex/libspeex/ |
| ltp_sse.h | 45 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+0), _mm_loadu_ps(b+0)));
46 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+4), _mm_loadu_ps(b+4)));
50 sum = _mm_add_ps(sum, _mm_movehl_ps(sum, sum));
82 sum = _mm_add_ps(sum, _mm_mul_ps(xx[0], yy[0]));
83 sum = _mm_add_ps(sum, _mm_mul_ps(xx[1], yy[1]));
87 sum = _mm_add_ps(sum, _mm_movehl_ps(sum, sum));
|
| resample_sse.h | 47 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+i), _mm_loadu_ps(b+i)));
48 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+i+4), _mm_loadu_ps(b+i+4)));
50 sum = _mm_add_ps(sum, _mm_movehl_ps(sum, sum));
64 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_load1_ps(a+i), _mm_loadu_ps(b+i*oversample)));
65 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_load1_ps(a+i+1), _mm_loadu_ps(b+(i+1)*oversample)));
68 sum = _mm_add_ps(sum, _mm_movehl_ps(sum, sum));
|
| cb_search_sse.h | 77 resj = _mm_add_ps(resj, _mm_mul_ps(shape[k],r[j-k]));
80 EE = _mm_add_ps(EE, _mm_mul_ps(resj, resj));
|
| filters_sse.h | 68 mem[0] = _mm_add_ps(mem[0], _mm_mul_ps(xx, num[0]));
74 mem[1] = _mm_add_ps(mem[1], _mm_mul_ps(xx, num[1]));
79 mem[2] = _mm_add_ps(mem[2], _mm_mul_ps(xx, num[2]));
118 mem[0] = _mm_add_ps(mem[0], _mm_mul_ps(xx, num[0]));
124 mem[1] = _mm_add_ps(mem[1], _mm_mul_ps(xx, num[1]));
271 mem[0] = _mm_add_ps(mem[0], _mm_mul_ps(xx, num[0]));
276 mem[1] = _mm_add_ps(mem[1], _mm_mul_ps(xx, num[1]));
280 mem[2] = _mm_add_ps(mem[2], _mm_mul_ps(xx, num[2]));
317 mem[0] = _mm_add_ps(mem[0], _mm_mul_ps(xx, num[0]));
322 mem[1] = _mm_add_ps(mem[1], _mm_mul_ps(xx, num[1]))
[all...] |
| vq_sse.h | 91 d = _mm_add_ps(d, _mm_mul_ps(in[j], *codebook++));
|
| /external/flac/libFLAC/ |
| lpc_intrin_sse.c | 73 sum0 = _mm_add_ps(sum0, _mm_mul_ps(d0, d));
85 sum0 = _mm_add_ps(sum0, _mm_mul_ps(d, d0));
111 sum0 = _mm_add_ps(sum0, _mm_mul_ps(d0, d));
112 sum1 = _mm_add_ps(sum1, _mm_mul_ps(d1, d));
127 sum1 = _mm_add_ps(sum1, _mm_mul_ps(d, d1));
128 sum0 = _mm_add_ps(sum0, _mm_mul_ps(d, d0));
157 sum0 = _mm_add_ps(sum0, _mm_mul_ps(d0, d));
158 sum1 = _mm_add_ps(sum1, _mm_mul_ps(d1, d));
159 sum2 = _mm_add_ps(sum2, _mm_mul_ps(d2, d));
177 sum2 = _mm_add_ps(sum2, _mm_mul_ps(d, d2))
[all...] |
| /frameworks/av/media/libaudioprocessing/ |
| AudioResamplerFirProcessSSE.h | 86 posCoef = _mm_add_ps(posCoef1, posCoef);
87 negCoef = _mm_add_ps(negCoef, negCoef1);
100 accL = _mm_add_ps(accL, posSamp);
101 accL = _mm_add_ps(accL, negSamp);
122 accL = _mm_add_ps(accL, posSampL);
123 accR = _mm_add_ps(accR, posSampR);
124 accL = _mm_add_ps(accL, negSampL);
125 accR = _mm_add_ps(accR, negSampR);
140 outAccum = _mm_add_ps(accL, _mm_movehl_ps(accL, accL));
141 outAccum = _mm_add_ps(outAccum, _mm_shuffle_ps(outAccum, outAccum, 0x11))
[all...] |
| /external/webrtc/webrtc/modules/audio_processing/aec/ |
| aec_core_sse2.c | 62 const __m128 f = _mm_add_ps(c, d);
63 const __m128 g = _mm_add_ps(y_fft_re, e);
64 const __m128 h = _mm_add_ps(y_fft_im, f);
101 const __m128 xPowPlus = _mm_add_ps(x_pow_local, k1e_10f);
106 const __m128 ef_sum2 = _mm_add_ps(ef_re2, ef_im2);
109 __m128 absEfPlus = _mm_add_ps(absEf, k1e_10f);
181 const __m128 e = _mm_add_ps(a, b);
223 wtBuf_re = _mm_add_ps(wtBuf_re, fft_re);
224 wtBuf_im = _mm_add_ps(wtBuf_im, fft_im);
295 const __m128 pol5_y_1 = _mm_add_ps(pol5_y_0, *((__m128*)C4))
[all...] |
| aec_rdft_sse2.c | 38 __m128 x0v = _mm_add_ps(a01v, a23v);
40 const __m128 x2v = _mm_add_ps(a45v, a67v);
43 a01v = _mm_add_ps(x0v, x2v);
49 a45v = _mm_add_ps(a45_0v, a45_1v);
55 x0v = _mm_add_ps(x1v, x3s);
59 a23v = _mm_add_ps(a23_0v, a23_1v);
67 a67v = _mm_add_ps(a67_0v, a67_1v);
98 __m128 x0r0_0i0_0r1_x0i1 = _mm_add_ps(a_00_32, a_08_40);
111 const __m128 x2r0_2i0_2r1_x2i1 = _mm_add_ps(a_16_48, a_24_56);
114 const __m128 xx0 = _mm_add_ps(x0r0_0i0_0r1_x0i1, x2r0_2i0_2r1_x2i1)
[all...] |
| /external/webrtc/webrtc/common_audio/ |
| fir_filter_sse.cc | 64 m_sum = _mm_add_ps(m_sum, _mm_mul_ps(m_in, _mm_load_ps(coef_ptr + j)));
69 m_sum = _mm_add_ps(m_sum, _mm_mul_ps(m_in, _mm_load_ps(coef_ptr + j)));
72 m_sum = _mm_add_ps(_mm_movehl_ps(m_sum, m_sum), m_sum);
|
| /external/swiftshader/src/Renderer/ |
| Surface.cpp | [all...] |
| /external/eigen/Eigen/src/Geometry/arch/ |
| Geometry_SSE.h | 36 _mm_add_ps(_mm_sub_ps(_mm_mul_ps(a,vec4f_swizzle1(b,3,3,3,3)),
39 _mm_xor_ps(mask,_mm_add_ps(s1,s2))));
|
| /external/eigen/Eigen/src/Core/arch/SSE/ |
| Complex.h | 55 template<> EIGEN_STRONG_INLINE Packet2cf padd<Packet2cf>(const Packet2cf& a, const Packet2cf& b) { return Packet2cf(_mm_add_ps(a.v,b.v)); }
79 return Packet2cf(_mm_add_ps(_mm_mul_ps(vec4f_swizzle1(a.v, 0, 0, 2, 2), b.v),
152 return pfirst(Packet2cf(_mm_add_ps(a.v, _mm_movehl_ps(a.v,a.v))));
157 return Packet2cf(_mm_add_ps(_mm_movelh_ps(vecs[0].v,vecs[1].v), _mm_movehl_ps(vecs[1].v,vecs[0].v)));
189 return Packet2cf(_mm_add_ps(_mm_xor_ps(_mm_mul_ps(vec4f_swizzle1(a.v, 0, 0, 2, 2), b.v), mask),
207 return Packet2cf(_mm_add_ps(_mm_mul_ps(vec4f_swizzle1(a.v, 0, 0, 2, 2), b.v),
255 return Packet2cf(_mm_div_ps(res.v,_mm_add_ps(s,_mm_castsi128_ps(_mm_shuffle_epi32(_mm_castps_si128(s), 0xb1)))));
|
| PacketMath.h | 194 template<> EIGEN_STRONG_INLINE Packet4f plset<Packet4f>(const float& a) { return _mm_add_ps(pset1<Packet4f>(a), _mm_set_ps(3,2,1,0)); }
198 template<> EIGEN_STRONG_INLINE Packet4f padd<Packet4f>(const Packet4f& a, const Packet4f& b) { return _mm_add_ps(a,b); }
520 tmp0 = _mm_add_ps(tmp0, tmp1);
522 tmp1 = _mm_add_ps(tmp1, tmp2);
525 return _mm_add_ps(tmp0, tmp2);
539 // Packet4f tmp = _mm_add_ps(a, vec4f_swizzle1(a,2,3,2,3));
542 Packet4f tmp = _mm_add_ps(a, _mm_movehl_ps(a,a));
[all...] |
| /external/mesa3d/src/gallium/drivers/swr/rasterizer/core/ |
| frontend.h | 194 vX = _mm_add_ps(vX, _mm_set1_ps(vpMatrix.m30));
197 vY = _mm_add_ps(vY, _mm_set1_ps(vpMatrix.m31));
200 vZ = _mm_add_ps(vZ, _mm_set1_ps(vpMatrix.m32));
|
| /prebuilts/gcc/linux-x86/host/x86_64-w64-mingw32-4.8/x86_64-w64-mingw32/include/ |
| fvec.h | 46 friend F32vec4 operator +(const F32vec4 &a,const F32vec4 &b) { return _mm_add_ps(a,b); }
52 F32vec4& operator +=(F32vec4 &a) { return *this = _mm_add_ps(vec,a); }
68 return _mm_sub_ps(_mm_add_ps(Ra0,Ra0),_mm_mul_ps(_mm_mul_ps(Ra0,a),Ra0));
|
| /external/pdfium/third_party/libopenjpeg20/ |
| mct.c | 408 vr = _mm_add_ps(vy, _mm_mul_ps(vv, vrv));
410 vb = _mm_add_ps(vy, _mm_mul_ps(vu, vbu));
421 vr = _mm_add_ps(vy, _mm_mul_ps(vv, vrv));
423 vb = _mm_add_ps(vy, _mm_mul_ps(vu, vbu));
|
| dwt.c | [all...] |
| /external/eigen/Eigen/src/LU/arch/ |
| Inverse_SSE.h | 109 iD = _mm_add_ps(iD,_mm_mul_ps(_mm_shuffle_ps(C,C,0xF5), _mm_movehl_ps(AB,AB)));
112 iA = _mm_add_ps(iA,_mm_mul_ps(_mm_shuffle_ps(B,B,0xF5), _mm_movehl_ps(DC,DC)));
115 d = _mm_add_ps(d, _mm_movehl_ps(d, d));
|
| /frameworks/rs/cpu_ref/ |
| rsCpuIntrinsics_x86.cpp | 328 bp0 = _mm_add_ps(bp0, _mm_mul_ps(pf0, x));
329 bp1 = _mm_add_ps(bp1, _mm_mul_ps(pf1, x));
363 pf = _mm_add_ps(pf, _mm_mul_ps(x, _mm_load_ps(pi + (r << 2))));
364 pf = _mm_add_ps(pf, _mm_mul_ps(y, _mm_load_ps(pi + (r << 2) + 4)));
395 pf = _mm_add_ps(pf, _mm_mul_ps(g0, p0));
397 pf = _mm_add_ps(pf, _mm_mul_ps(g1, _mm_alignr_epi8(p1, p0, 4)));
399 pf = _mm_add_ps(pf, _mm_mul_ps(g2, _mm_alignr_epi8(p1, p0, 8)));
401 pf = _mm_add_ps(pf, _mm_mul_ps(g3, _mm_alignr_epi8(p1, p0, 12)));
[all...] |
| /external/clang/test/CodeGen/ |
| sse-builtins.c | 13 return _mm_add_ps(A, B);
|
| /external/eigen/Eigen/src/Core/arch/AVX/ |
| PacketMath.h | 398 return predux(Packet4f(_mm_add_ps(_mm256_castps256_ps128(a),_mm256_extractf128_ps(a,1))));
407 return _mm_add_ps(_mm256_castps256_ps128(a),_mm256_extractf128_ps(a,1));
|
