| /external/libopus/celt/x86/ |
| pitch_sse.h | 52 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x00),yj));
53 xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0x55),
55 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0xaa),
57 xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_shuffle_ps(x0,x0,0xff),y3));
61 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_load1_ps(x+j),_mm_loadu_ps(y+j)));
64 xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_load1_ps(x+j),_mm_loadu_ps(y+j)));
67 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_load1_ps(x+j),_mm_loadu_ps(y+j)));
71 _mm_storeu_ps(sum,_mm_add_ps(xsum1,xsum2));
87 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(xi, y1i));
88 xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(xi, y2i))
[all...] |
| /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/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));
|
| 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...] |
| 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));
|
| /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/vulkan-validation-layers/libs/glm/gtx/ |
| simd_mat4.inl | 132 this->Data[0].Data = _mm_add_ps(this->Data[0].Data, m[0].Data);
133 this->Data[1].Data = _mm_add_ps(this->Data[1].Data, m[1].Data);
134 this->Data[2].Data = _mm_add_ps(this->Data[2].Data, m[2].Data);
135 this->Data[3].Data = _mm_add_ps(this->Data[3].Data, m[3].Data);
178 this->Data[0].Data = _mm_add_ps(this->Data[0].Data, Operand);
179 this->Data[1].Data = _mm_add_ps(this->Data[1].Data, Operand);
180 this->Data[2].Data = _mm_add_ps(this->Data[2].Data, Operand);
181 this->Data[3].Data = _mm_add_ps(this->Data[3].Data, Operand);
226 this->Data[0].Data = _mm_add_ps(this->Data[0].Data, one);
227 this->Data[1].Data = _mm_add_ps(this->Data[1].Data, one)
[all...] |
| simd_quat.inl | 107 return fquatSIMD(_mm_add_ps(q1.Data, q2.Data));
135 __m128 add0 = _mm_add_ps(mul0, _mm_movehl_ps(mul0, mul0));
139 __m128 add1 = _mm_add_ps(mul1, _mm_movehl_ps(mul1, mul1));
143 __m128 add2 = _mm_add_ps(mul2, _mm_movehl_ps(mul2, mul2));
147 __m128 add3 = _mm_add_ps(mul3, _mm_movehl_ps(mul3, mul3));
192 return _mm_add_ps(v.Data, _mm_add_ps(uv, uuv));
336 __m128 _xyzw2 = _mm_add_ps(_xyzw, _xyzw);
344 _tmp1 = _mm_add_ps(_tmp1, _mm_mul_ps(_zxyw2, _wwww));
428 return _mm_add_ps(x.Data, _mm_mul_ps(_mm_set1_ps(a), _mm_sub_ps(y.Data, x.Data)))
[all...] |
| simd_vec4.inl | 103 this->Data = _mm_add_ps(Data, _mm_set_ps1(s));
109 this->Data = _mm_add_ps(this->Data , v.Data);
151 this->Data = _mm_add_ps(this->Data , glm::detail::one);
185 return fvec4SIMD(_mm_add_ps(v.Data, _mm_set1_ps(s)));
190 return fvec4SIMD(_mm_add_ps(_mm_set1_ps(s), v.Data));
195 return fvec4SIMD(_mm_add_ps(v1.Data, v2.Data));
262 return fvec4SIMD(_mm_add_ps(v.Data, glm::detail::one));
455 return _mm_add_ps(x.Data, Mul0);
531 return _mm_add_ps(_mm_mul_ps(a.Data, b.Data), c.Data);
|
| /external/opencv3/modules/imgproc/src/ |
| filter.cpp | [all...] |
| imgwarp.cpp | 568 x0 = _mm_add_ps(_mm_mul_ps(x0, b0), _mm_mul_ps(y0, b1));
569 x1 = _mm_add_ps(_mm_mul_ps(x1, b0), _mm_mul_ps(y1, b1));
579 x0 = _mm_add_ps(_mm_mul_ps(x0, b0), _mm_mul_ps(y0, b1));
580 x1 = _mm_add_ps(_mm_mul_ps(x1, b0), _mm_mul_ps(y1, b1));
598 x0 = _mm_add_ps(_mm_mul_ps(x0, b0), _mm_mul_ps(y0, b1));
599 x1 = _mm_add_ps(_mm_mul_ps(x1, b0), _mm_mul_ps(y1, b1));
609 x0 = _mm_add_ps(_mm_mul_ps(x0, b0), _mm_mul_ps(y0, b1));
610 x1 = _mm_add_ps(_mm_mul_ps(x1, b0), _mm_mul_ps(y1, b1));
626 x0 = _mm_add_ps(_mm_mul_ps(x0, b0), _mm_mul_ps(y0, b1));
663 x0 = _mm_add_ps(_mm_mul_ps(x0, b0), _mm_mul_ps(y0, b1))
[all...] |
| /external/vulkan-validation-layers/libs/glm/detail/ |
| intrinsic_matrix.inl | 52 out[0] = _mm_add_ps(in1[0], in2[0]);
53 out[1] = _mm_add_ps(in1[1], in2[1]);
54 out[2] = _mm_add_ps(in1[2], in2[2]);
55 out[3] = _mm_add_ps(in1[3], in2[3]);
81 __m128 a0 = _mm_add_ps(m0, m1);
82 __m128 a1 = _mm_add_ps(m2, m3);
83 __m128 a2 = _mm_add_ps(a0, a1);
102 __m128 a0 = _mm_add_ps(u0, u1);
106 __m128 a1 = _mm_add_ps(u2, u3);
110 __m128 f2 = _mm_add_ps(f0, f1)
[all...] |
| intrinsic_geometric.inl | 56 __m128 add0 = _mm_add_ps(mul0, swp0);
58 __m128 add1 = _mm_add_ps(add0, swp1);
68 __m128 add0 = _mm_add_ps(mov0, mul0);
137 __m128 add0 = _mm_add_ps(mul3, sqt0);
|
| intrinsic_common.inl | 195 __m128 add0 = _mm_add_ps(x, or0);
205 __m128 add0 = _mm_add_ps(x, or0);
215 __m128 add0 = _mm_add_ps(rnd0, and0);
260 __m128 add0 = _mm_add_ps(mul0, mul1);
|
| /external/opencv3/modules/core/src/ |
| convert.cpp | [all...] |
| /external/eigen/Eigen/src/Geometry/arch/ |
| Geometry_SSE.h | 32 _mm_add_ps(_mm_sub_ps(_mm_mul_ps(a,vec4f_swizzle1(b,3,3,3,3)),
35 _mm_add_ps(flip1,flip2)));
|
| /external/libgdx/extensions/gdx-bullet/jni/src/bullet/BulletDynamics/ConstraintSolver/ |
| btSequentialImpulseConstraintSolver.cpp | 112 return _mm_add_ps( btVecSplat( result, 0 ), _mm_add_ps( btVecSplat( result, 1 ), btVecSplat( result, 2 ) ) );
145 #define FMADD(a, b, c) _mm_add_ps(c, _mm_mul_ps(a, b))
158 __m128 deltaVel1Dotn = _mm_add_ps(btSimdDot3(c.m_contactNormal1.mVec128, body1.internalGetDeltaLinearVelocity().mVec128), btSimdDot3(c.m_relpos1CrossNormal.mVec128, body1.internalGetDeltaAngularVelocity().mVec128));
159 __m128 deltaVel2Dotn = _mm_add_ps(btSimdDot3(c.m_contactNormal2.mVec128, body2.internalGetDeltaLinearVelocity().mVec128), btSimdDot3(c.m_relpos2CrossNormal.mVec128, body2.internalGetDeltaAngularVelocity().mVec128));
162 btSimdScalar sum = _mm_add_ps(cpAppliedImp, deltaImpulse);
175 body1.internalGetDeltaLinearVelocity().mVec128 = _mm_add_ps(body1.internalGetDeltaLinearVelocity().mVec128, _mm_mul_ps(linearComponentA, impulseMagnitude));
176 body1.internalGetDeltaAngularVelocity().mVec128 = _mm_add_ps(body1.internalGetDeltaAngularVelocity().mVec128, _mm_mul_ps(c.m_angularComponentA.mVec128, impulseMagnitude));
177 body2.internalGetDeltaLinearVelocity().mVec128 = _mm_add_ps(body2.internalGetDeltaLinearVelocity().mVec128, _mm_mul_ps(linearComponentB, impulseMagnitude));
178 body2.internalGetDeltaAngularVelocity().mVec128 = _mm_add_ps(body2.internalGetDeltaAngularVelocity().mVec128, _mm_mul_ps(c.m_angularComponentB.mVec128, impulse (…)
[all...] |
| /external/eigen/Eigen/src/Core/arch/SSE/ |
| Complex.h | 48 template<> EIGEN_STRONG_INLINE Packet2cf padd<Packet2cf>(const Packet2cf& a, const Packet2cf& b) { return Packet2cf(_mm_add_ps(a.v,b.v)); }
73 return Packet2cf(_mm_add_ps(_mm_mul_ps(vec4f_swizzle1(a.v, 0, 0, 2, 2), b.v),
131 return pfirst(Packet2cf(_mm_add_ps(a.v, _mm_movehl_ps(a.v,a.v))));
136 return Packet2cf(_mm_add_ps(_mm_movelh_ps(vecs[0].v,vecs[1].v), _mm_movehl_ps(vecs[1].v,vecs[0].v)));
168 return Packet2cf(_mm_add_ps(_mm_xor_ps(_mm_mul_ps(vec4f_swizzle1(a.v, 0, 0, 2, 2), b.v), mask),
186 return Packet2cf(_mm_add_ps(_mm_mul_ps(vec4f_swizzle1(a.v, 0, 0, 2, 2), b.v),
234 return Packet2cf(_mm_div_ps(res.v,_mm_add_ps(s,_mm_castsi128_ps(_mm_shuffle_epi32(_mm_castps_si128(s), 0xb1)))));
|
| /external/libgdx/extensions/gdx-bullet/jni/src/bullet/LinearMath/ |
| btMatrix3x3.h | 810 rv00 = _mm_add_ps(rv00, rv01);
811 rv10 = _mm_add_ps(rv10, rv11);
812 rv20 = _mm_add_ps(rv20, rv21);
814 m_el[0].mVec128 = _mm_add_ps(rv00, rv02);
815 m_el[1].mVec128 = _mm_add_ps(rv10, rv12);
816 m_el[2].mVec128 = _mm_add_ps(rv20, rv22);
[all...] |
| /external/opencv3/modules/hal/src/ |
| stat.cpp | 195 d0 = _mm_add_ps(d0, _mm_mul_ps(t0, t0));
196 d1 = _mm_add_ps(d1, _mm_mul_ps(t1, t1));
198 _mm_store_ps(buf, _mm_add_ps(d0, d1));
231 d0 = _mm_add_ps(d0, _mm_and_ps(t0, absmask));
232 d1 = _mm_add_ps(d1, _mm_and_ps(t1, absmask));
234 _mm_store_ps(buf, _mm_add_ps(d0, d1));
|
| mathfuncs.cpp | 89 __m128 c = _mm_div_ps(tmin, _mm_add_ps(tmax, eps));
92 a = _mm_mul_ps(_mm_add_ps(a, p5), c2);
93 a = _mm_mul_ps(_mm_add_ps(a, p3), c2);
94 a = _mm_mul_ps(_mm_add_ps(a, p1), c);
536 __m128 zf0 = _mm_add_ps(xf0, mA1);
537 __m128 zf1 = _mm_add_ps(xf1, mA1);
539 zf0 = _mm_add_ps(_mm_mul_ps(zf0, xf0), mA2);
540 zf1 = _mm_add_ps(_mm_mul_ps(zf1, xf1), mA2);
542 zf0 = _mm_add_ps(_mm_mul_ps(zf0, xf0), mA3);
543 zf1 = _mm_add_ps(_mm_mul_ps(zf1, xf1), mA3)
[all...] |
| /external/opencv3/modules/video/src/ |
| optflowgf.cpp | 478 x0 = _mm_add_ps(_mm_loadu_ps(sptr0 + x), _mm_loadu_ps(sptr1 + x));
479 x1 = _mm_add_ps(_mm_loadu_ps(sptr0 + x + 4), _mm_loadu_ps(sptr1 + x + 4));
480 s0 = _mm_add_ps(s0, _mm_mul_ps(x0, g4));
481 s1 = _mm_add_ps(s1, _mm_mul_ps(x1, g4));
482 x0 = _mm_add_ps(_mm_loadu_ps(sptr0 + x + 8), _mm_loadu_ps(sptr1 + x + 8));
483 x1 = _mm_add_ps(_mm_loadu_ps(sptr0 + x + 12), _mm_loadu_ps(sptr1 + x + 12));
484 s2 = _mm_add_ps(s2, _mm_mul_ps(x0, g4));
485 s3 = _mm_add_ps(s3, _mm_mul_ps(x1, g4));
504 __m128 x0 = _mm_add_ps(_mm_loadu_ps(sptr0 + x), _mm_loadu_ps(sptr1 + x));
505 s0 = _mm_add_ps(s0, _mm_mul_ps(x0, g4))
[all...] |
