/external/libopus/celt/x86/ |
D | pitch_sse.h | 43 xsum1 = _mm_loadu_ps(sum); in xcorr_kernel() 48 __m128 x0 = _mm_loadu_ps(x+j); in xcorr_kernel() 49 __m128 yj = _mm_loadu_ps(y+j); in xcorr_kernel() 50 __m128 y3 = _mm_loadu_ps(y+j+3); in xcorr_kernel() 61 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_load1_ps(x+j),_mm_loadu_ps(y+j))); in xcorr_kernel() 64 xsum2 = _mm_add_ps(xsum2,_mm_mul_ps(_mm_load1_ps(x+j),_mm_loadu_ps(y+j))); in xcorr_kernel() 67 xsum1 = _mm_add_ps(xsum1,_mm_mul_ps(_mm_load1_ps(x+j),_mm_loadu_ps(y+j))); in xcorr_kernel() 84 __m128 xi = _mm_loadu_ps(x+i); in dual_inner_prod() 85 __m128 y1i = _mm_loadu_ps(y01+i); in dual_inner_prod() 86 __m128 y2i = _mm_loadu_ps(y02+i); in dual_inner_prod() [all …]
|
/external/speex/libspeex/ |
D | resample_sse.h | 47 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+i), _mm_loadu_ps(b+i))); in inner_product_single() 48 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+i+4), _mm_loadu_ps(b+i+4))); in inner_product_single() 61 __m128 f = _mm_loadu_ps(frac); in interpolate_product_single() 64 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_load1_ps(a+i), _mm_loadu_ps(b+i*oversample))); in interpolate_product_single() 65 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_load1_ps(a+i+1), _mm_loadu_ps(b+(i+1)*oversample))); in interpolate_product_single() 86 t = _mm_mul_ps(_mm_loadu_ps(a+i), _mm_loadu_ps(b+i)); in inner_product_double() 90 t = _mm_mul_ps(_mm_loadu_ps(a+i+4), _mm_loadu_ps(b+i+4)); in inner_product_double() 106 __m128 f = _mm_loadu_ps(frac); in interpolate_product_double() 112 t = _mm_mul_ps(_mm_load1_ps(a+i), _mm_loadu_ps(b+i*oversample)); in interpolate_product_double() 116 t = _mm_mul_ps(_mm_load1_ps(a+i+1), _mm_loadu_ps(b+(i+1)*oversample)); in interpolate_product_double()
|
D | filters_sse.h | 46 mem[i] = _mm_loadu_ps(_mem+4*i); in filter_mem16_10() 47 num[i] = _mm_loadu_ps(_num+4*i); in filter_mem16_10() 48 den[i] = _mm_loadu_ps(_den+4*i); in filter_mem16_10() 99 mem[i] = _mm_loadu_ps(_mem+4*i); in filter_mem16_8() 100 num[i] = _mm_loadu_ps(_num+4*i); in filter_mem16_8() 101 den[i] = _mm_loadu_ps(_den+4*i); in filter_mem16_8() 153 mem[i] = _mm_loadu_ps(_mem+4*i); in iir_mem16_10() 154 den[i] = _mm_loadu_ps(_den+4*i); in iir_mem16_10() 202 mem[i] = _mm_loadu_ps(_mem+4*i); in iir_mem16_8() 203 den[i] = _mm_loadu_ps(_den+4*i); in iir_mem16_8() [all …]
|
D | ltp_sse.h | 45 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+0), _mm_loadu_ps(b+0))); in inner_prod() 46 sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+4), _mm_loadu_ps(b+4))); in inner_prod() 68 x[i] = _mm_loadu_ps(_x+(i<<2)); in pitch_xcorr() 72 y[i] = _mm_loadu_ps(_y+(i<<2)+offset); in pitch_xcorr()
|
/external/webrtc/webrtc/modules/audio_processing/aec/ |
D | aec_core_sse2.c | 51 const __m128 x_fft_buf_re = _mm_loadu_ps(&x_fft_buf[0][xPos + j]); in FilterFarSSE2() 52 const __m128 x_fft_buf_im = _mm_loadu_ps(&x_fft_buf[1][xPos + j]); in FilterFarSSE2() 53 const __m128 h_fft_buf_re = _mm_loadu_ps(&h_fft_buf[0][pos + j]); in FilterFarSSE2() 54 const __m128 h_fft_buf_im = _mm_loadu_ps(&h_fft_buf[1][pos + j]); in FilterFarSSE2() 55 const __m128 y_fft_re = _mm_loadu_ps(&y_fft[0][j]); in FilterFarSSE2() 56 const __m128 y_fft_im = _mm_loadu_ps(&y_fft[1][j]); in FilterFarSSE2() 97 const __m128 x_pow_local = _mm_loadu_ps(&x_pow[i]); in ScaleErrorSignalSSE2() 98 const __m128 ef_re_base = _mm_loadu_ps(&ef[0][i]); in ScaleErrorSignalSSE2() 99 const __m128 ef_im_base = _mm_loadu_ps(&ef[1][i]); in ScaleErrorSignalSSE2() 170 const __m128 x_fft_buf_re = _mm_loadu_ps(&x_fft_buf[0][xPos + j]); in FilterAdaptationSSE2() [all …]
|
D | aec_rdft_sse2.c | 23 __m128 a00v = _mm_loadu_ps(&a[j + 0]); in cft1st_128_SSE2() 24 __m128 a04v = _mm_loadu_ps(&a[j + 4]); in cft1st_128_SSE2() 25 __m128 a08v = _mm_loadu_ps(&a[j + 8]); in cft1st_128_SSE2() 26 __m128 a12v = _mm_loadu_ps(&a[j + 12]); in cft1st_128_SSE2() 253 const __m128 c_j1 = _mm_loadu_ps(&c[j1]); // 1, 2, 3, 4, in rftfsub_128_SSE2() 254 const __m128 c_k1 = _mm_loadu_ps(&c[29 - j1]); // 28, 29, 30, 31, in rftfsub_128_SSE2() 260 const __m128 a_j2_0 = _mm_loadu_ps(&a[0 + j2]); // 2, 3, 4, 5, in rftfsub_128_SSE2() 261 const __m128 a_j2_4 = _mm_loadu_ps(&a[4 + j2]); // 6, 7, 8, 9, in rftfsub_128_SSE2() 262 const __m128 a_k2_0 = _mm_loadu_ps(&a[122 - j2]); // 120, 121, 122, 123, in rftfsub_128_SSE2() 263 const __m128 a_k2_4 = _mm_loadu_ps(&a[126 - j2]); // 124, 125, 126, 127, in rftfsub_128_SSE2() [all …]
|
/external/opencv3/modules/hal/src/ |
D | stat.cpp | 193 __m128 t0 = _mm_sub_ps(_mm_loadu_ps(a + j), _mm_loadu_ps(b + j)); in normL2Sqr_() 194 __m128 t1 = _mm_sub_ps(_mm_loadu_ps(a + j + 4), _mm_loadu_ps(b + j + 4)); in normL2Sqr_() 229 __m128 t0 = _mm_sub_ps(_mm_loadu_ps(a + j), _mm_loadu_ps(b + j)); in normL1_() 230 __m128 t1 = _mm_sub_ps(_mm_loadu_ps(a + j + 4), _mm_loadu_ps(b + j + 4)); in normL1_()
|
D | mathfuncs.cpp | 85 __m128 x = _mm_loadu_ps(X + i), y = _mm_loadu_ps(Y + i); in fastAtan2() 479 xf0 = _mm_loadu_ps(&x[i].f); in exp() 480 xf1 = _mm_loadu_ps(&x[i+4].f); in exp()
|
/external/opencv3/modules/imgproc/src/ |
D | corner.cpp | 75 __m128 t0 = _mm_loadu_ps(cov + j*3); // a0 b0 c0 x in calcMinEigenVal() 76 __m128 t1 = _mm_loadu_ps(cov + j*3 + 3); // a1 b1 c1 x in calcMinEigenVal() 77 __m128 t2 = _mm_loadu_ps(cov + j*3 + 6); // a2 b2 c2 x in calcMinEigenVal() 78 __m128 t3 = _mm_loadu_ps(cov + j*3 + 9); // a3 b3 c3 x in calcMinEigenVal() 145 __m128 t0 = _mm_loadu_ps(cov + j*3); // a0 b0 c0 x in calcHarris() 146 __m128 t1 = _mm_loadu_ps(cov + j*3 + 3); // a1 b1 c1 x in calcHarris() 147 __m128 t2 = _mm_loadu_ps(cov + j*3 + 6); // a2 b2 c2 x in calcHarris() 148 __m128 t3 = _mm_loadu_ps(cov + j*3 + 9); // a3 b3 c3 x in calcHarris() 330 __m128 v_dx_0 = _mm_loadu_ps(dxdata + j); in cornerEigenValsVecs() 331 __m128 v_dx_1 = _mm_loadu_ps(dxdata + j + 4); in cornerEigenValsVecs() [all …]
|
D | imgwarp.cpp | 593 x0 = _mm_loadu_ps(S0 + x); in operator ()() 594 x1 = _mm_loadu_ps(S0 + x + 4); in operator ()() 595 y0 = _mm_loadu_ps(S1 + x); in operator ()() 596 y1 = _mm_loadu_ps(S1 + x + 4); in operator ()() 604 x0 = _mm_loadu_ps(S0 + x + 8); in operator ()() 605 x1 = _mm_loadu_ps(S0 + x + 12); in operator ()() 606 y0 = _mm_loadu_ps(S1 + x + 8); in operator ()() 607 y1 = _mm_loadu_ps(S1 + x + 12); in operator ()() 623 x0 = _mm_loadu_ps(S0 + x); in operator ()() 624 y0 = _mm_loadu_ps(S1 + x); in operator ()() [all …]
|
D | filter.cpp | 1453 x0 = _mm_loadu_ps(src); in operator ()() 1454 x1 = _mm_loadu_ps(src + 4); in operator ()() 1538 x0 = _mm_loadu_ps(src - cn); in operator ()() 1539 x1 = _mm_loadu_ps(src); in operator ()() 1540 x2 = _mm_loadu_ps(src + cn); in operator ()() 1541 y0 = _mm_loadu_ps(src - cn + 4); in operator ()() 1542 y1 = _mm_loadu_ps(src + 4); in operator ()() 1543 y2 = _mm_loadu_ps(src + cn + 4); in operator ()() 1553 x0 = _mm_loadu_ps(src - cn); in operator ()() 1554 x1 = _mm_loadu_ps(src); in operator ()() [all …]
|
D | thresh.cpp | 730 v0 = _mm_loadu_ps( src + j ); in thresh_32f() 731 v1 = _mm_loadu_ps( src + j + 4 ); in thresh_32f() 768 v0 = _mm_loadu_ps( src + j ); in thresh_32f() 769 v1 = _mm_loadu_ps( src + j + 4 ); in thresh_32f() 806 v0 = _mm_loadu_ps( src + j ); in thresh_32f() 807 v1 = _mm_loadu_ps( src + j + 4 ); in thresh_32f() 837 v0 = _mm_loadu_ps( src + j ); in thresh_32f() 838 v1 = _mm_loadu_ps( src + j + 4 ); in thresh_32f() 876 v0 = _mm_loadu_ps( src + j ); in thresh_32f() 877 v1 = _mm_loadu_ps( src + j + 4 ); in thresh_32f()
|
D | morph.cpp | 155 __m128 s = _mm_loadu_ps((const float*)src + i); in operator ()() 158 __m128 x = _mm_loadu_ps((const float*)src + i + k); in operator ()() 469 __m128 s0 = _mm_loadu_ps(sptr); in operator ()() 470 __m128 s1 = _mm_loadu_ps(sptr + 4); in operator ()() 471 __m128 s2 = _mm_loadu_ps(sptr + 8); in operator ()() 472 __m128 s3 = _mm_loadu_ps(sptr + 12); in operator ()() 478 x0 = _mm_loadu_ps(sptr); in operator ()() 479 x1 = _mm_loadu_ps(sptr + 4); in operator ()() 480 x2 = _mm_loadu_ps(sptr + 8); in operator ()() 481 x3 = _mm_loadu_ps(sptr + 12); in operator ()() [all …]
|
D | color.cpp | 1618 __m128 v_r0 = _mm_loadu_ps(src); in operator ()() 1619 __m128 v_r1 = _mm_loadu_ps(src + 4); in operator ()() 1620 __m128 v_g0 = _mm_loadu_ps(src + 8); in operator ()() 1621 __m128 v_g1 = _mm_loadu_ps(src + 12); in operator ()() 1622 __m128 v_b0 = _mm_loadu_ps(src + 16); in operator ()() 1623 __m128 v_b1 = _mm_loadu_ps(src + 20); in operator ()() 1643 __m128 v_r0 = _mm_loadu_ps(src); in operator ()() 1644 __m128 v_r1 = _mm_loadu_ps(src + 4); in operator ()() 1645 __m128 v_g0 = _mm_loadu_ps(src + 8); in operator ()() 1646 __m128 v_g1 = _mm_loadu_ps(src + 12); in operator ()() [all …]
|
D | pyramids.cpp | 499 __m128 v_r0 = _mm_loadu_ps(row0 + x); in operator ()() 500 __m128 v_r1 = _mm_loadu_ps(row1 + x); in operator ()() 501 __m128 v_r2 = _mm_loadu_ps(row2 + x); in operator ()() 506 v_r0 = _mm_loadu_ps(row0 + x + 4); in operator ()() 507 v_r1 = _mm_loadu_ps(row1 + x + 4); in operator ()() 508 v_r2 = _mm_loadu_ps(row2 + x + 4); in operator ()()
|
D | smooth.cpp | 2283 arg_type load(const float* ptr) { return _mm_loadu_ps(ptr); } in load() 2805 __m128 _sw = _mm_loadu_ps(space_weight+k); in operator ()() 2869 __m128 _sw = _mm_loadu_ps(space_weight+k); in operator ()() 3181 __m128 _sw = _mm_loadu_ps(space_weight + k); in operator ()() 3242 __m128 _sw = _mm_loadu_ps(space_weight + k); in operator ()() 3249 __m128 _b = _mm_loadu_ps(sptr_k0); in operator ()() 3250 __m128 _g = _mm_loadu_ps(sptr_k1); in operator ()() 3251 __m128 _r = _mm_loadu_ps(sptr_k2); in operator ()() 3252 __m128 _z = _mm_loadu_ps(sptr_k3); in operator ()()
|
/external/opencv3/modules/video/src/ |
D | optflowgf.cpp | 468 s0 = _mm_mul_ps(_mm_loadu_ps(sptr0 + x), g4); in FarnebackUpdateFlow_GaussianBlur() 469 s1 = _mm_mul_ps(_mm_loadu_ps(sptr0 + x + 4), g4); in FarnebackUpdateFlow_GaussianBlur() 470 s2 = _mm_mul_ps(_mm_loadu_ps(sptr0 + x + 8), g4); in FarnebackUpdateFlow_GaussianBlur() 471 s3 = _mm_mul_ps(_mm_loadu_ps(sptr0 + x + 12), g4); in FarnebackUpdateFlow_GaussianBlur() 478 x0 = _mm_add_ps(_mm_loadu_ps(sptr0 + x), _mm_loadu_ps(sptr1 + x)); in FarnebackUpdateFlow_GaussianBlur() 479 x1 = _mm_add_ps(_mm_loadu_ps(sptr0 + x + 4), _mm_loadu_ps(sptr1 + x + 4)); in FarnebackUpdateFlow_GaussianBlur() 482 x0 = _mm_add_ps(_mm_loadu_ps(sptr0 + x + 8), _mm_loadu_ps(sptr1 + x + 8)); in FarnebackUpdateFlow_GaussianBlur() 483 x1 = _mm_add_ps(_mm_loadu_ps(sptr0 + x + 12), _mm_loadu_ps(sptr1 + x + 12)); in FarnebackUpdateFlow_GaussianBlur() 498 __m128 s0 = _mm_mul_ps(_mm_loadu_ps(sptr0 + x), g4); in FarnebackUpdateFlow_GaussianBlur() 504 __m128 x0 = _mm_add_ps(_mm_loadu_ps(sptr0 + x), _mm_loadu_ps(sptr1 + x)); in FarnebackUpdateFlow_GaussianBlur() [all …]
|
/external/clang/test/Sema/ |
D | uninit-variables-vectors.c | 6 __m128 _mm_loadu_ps(const float *p); 14 X = _mm_loadu_ps(&input[0]); in test1()
|
/external/webrtc/webrtc/common_audio/resampler/ |
D | sinc_resampler_sse.cc | 31 m_input = _mm_loadu_ps(input_ptr + i); in Convolve_SSE()
|
/external/opencv3/modules/objdetect/src/ |
D | hog.cpp | 421 __m128 _mag = _mm_loadu_ps(dbuf + x + (width << 1)); in computeGradient() 422 __m128 _angle = _mm_loadu_ps(dbuf + x + width * 3); in computeGradient() 826 __m128 _w = _mm_mul_ps(_mm_set1_ps(pk.gradWeight), _mm_loadu_ps(pk.histWeights)); in getBlock() 874 __m128 _w = _mm_mul_ps(_mm_set1_ps(pk.gradWeight), _mm_loadu_ps(pk.histWeights)); in getBlock() 967 __m128 p0 = _mm_loadu_ps(hist); in normalizeBlockHistogram() 972 p0 = _mm_loadu_ps(hist + i); in normalizeBlockHistogram() 1002 __m128 p = _mm_mul_ps(_scale, _mm_loadu_ps(hist)); in normalizeBlockHistogram() 1009 p = _mm_loadu_ps(hist + i); in normalizeBlockHistogram() 1048 __m128 t = _mm_mul_ps(_scale2, _mm_loadu_ps(hist + i)); in normalizeBlockHistogram() 1522 __m128 _vec = _mm_loadu_ps(vec); in detect() [all …]
|
/external/webrtc/webrtc/common_audio/ |
D | fir_filter_sse.cc | 63 m_in = _mm_loadu_ps(in_ptr + j); in Filter()
|
/external/eigen/Eigen/src/Core/arch/SSE/ |
D | PacketMath.h | 223 return _mm_loadu_ps(from); 259 return _mm_loadu_ps(from); 286 return _mm_loadu_ps(from);
|
/external/opencv3/modules/core/src/ |
D | mathfuncs.cpp | 280 __m128 v_src = _mm_loadu_ps(buf[0] + k); in phase() 417 __m128 v_src = _mm_loadu_ps(buf[0] + k); in cartToPolar() 510 __m128 v_angle = _mm_loadu_ps(angle + i); in SinCos_32f() 701 __m128 v_m = _mm_loadu_ps(mag + k); in polarToCart() 702 _mm_storeu_ps(x + k, _mm_mul_ps(_mm_loadu_ps(x + k), v_m)); in polarToCart() 703 _mm_storeu_ps(y + k, _mm_mul_ps(_mm_loadu_ps(y + k), v_m)); in polarToCart()
|
D | rand.cpp | 232 __m128 q0 = _mm_loadu_ps((const float*)(p + i)); in randf_32f() 233 __m128 q1 = _mm_loadu_ps((const float*)(p + i + 2)); in randf_32f() 241 _mm_storeu_ps(arr + i, _mm_add_ps(_mm_mul_ps(_mm_loadu_ps(f), p0), p1)); in randf_32f()
|
D | convert.cpp | 1651 __m128 v_dst = _mm_add_ps(_mm_mul_ps(_mm_loadu_ps(src + x), v_scale), v_shift); in operator ()() 3109 __m128 v_src = _mm_loadu_ps(src + x); in operator ()() 3112 v_src = _mm_loadu_ps(src + x + 4); in operator ()() 3139 __m128 v_src = _mm_loadu_ps(src + x); in operator ()() 3142 v_src = _mm_loadu_ps(src + x + 4); in operator ()() 3175 __m128 v_src = _mm_loadu_ps(src + x); in operator ()() 3178 v_src = _mm_loadu_ps(src + x + 4); in operator ()() 3208 __m128 v_src = _mm_loadu_ps(src + x); in operator ()() 3211 v_src = _mm_loadu_ps(src + x + 4); in operator ()() 3237 __m128 v_src = _mm_loadu_ps(src + x); in operator ()() [all …]
|