/dports/graphics/qt5-3d/kde-qt3d-5.15.2p39/src/core/transforms/ |
H A D | matrix4x4_avx2_p.h | 348 const __m128 v = _mm256_extractf128_ps(m_col12, 0); in m21() 354 const __m128 v = _mm256_extractf128_ps(m_col12, 1); in m22() 360 const __m128 v = _mm256_extractf128_ps(m_col34, 0); in m23() 366 const __m128 v = _mm256_extractf128_ps(m_col34, 1); in m24() 373 const __m128 v = _mm256_extractf128_ps(m_col12, 0); in m31() 446 c.m_xyzw = _mm256_extractf128_ps(m_col12, 0); in column() 449 c.m_xyzw = _mm256_extractf128_ps(m_col12, 1); in column() 452 c.m_xyzw = _mm256_extractf128_ps(m_col34, 0); in column() 455 c.m_xyzw = _mm256_extractf128_ps(m_col34, 1); in column() 526 …v.m_xyzw = _mm_hadd_ps(_mm256_extractf128_ps(shuffledSum, 0), _mm256_extractf128_ps(shuffledSum, 1… [all …]
|
/dports/misc/mnn/MNN-1.2.0/source/backend/cpu/x86_x64/avx/ |
H A D | GemmFunctionPackL.hpp | 78 STORE_4(C + 0, _mm_add_ps(_mm256_extractf128_ps(S00, 0), _mm256_extractf128_ps(S00, 1))); in _AVX_MNNPackedMatMul_3() 83 STORE_4(C + 4, _mm_add_ps(_mm256_extractf128_ps(S00, 0), _mm256_extractf128_ps(S00, 1))); in _AVX_MNNPackedMatMul_3() 88 STORE_4(C + 8, _mm_add_ps(_mm256_extractf128_ps(S00, 0), _mm256_extractf128_ps(S00, 1))); in _AVX_MNNPackedMatMul_3() 146 … STORE_4(C + 0, _mm_add_ps(_mm256_extractf128_ps(S00, 0), _mm256_extractf128_ps(S00, 1))); in _AVX_MNNPackednMatMulRemainCommon() 151 … STORE_4(C + 4, _mm_add_ps(_mm256_extractf128_ps(S00, 0), _mm256_extractf128_ps(S00, 1))); in _AVX_MNNPackednMatMulRemainCommon() 184 … STORE_4(C + 0, _mm_add_ps(_mm256_extractf128_ps(S00, 0), _mm256_extractf128_ps(S00, 1))); in _AVX_MNNPackednMatMulRemainCommon()
|
H A D | GemmFunction.hpp | 12 auto m0 = _mm256_extractf128_ps(z0, u); \ 13 auto m1 = _mm256_extractf128_ps(z3, u); \ 14 auto m2 = _mm256_extractf128_ps(z6, u); \ 15 auto m3 = _mm256_extractf128_ps(z9, u); \ 734 auto sum00 = _mm256_extractf128_ps(sumAvx00, 0); in _AVX_MNNPackednMatMulRemainCommon() 735 auto sum01 = _mm256_extractf128_ps(sumAvx00, 1); in _AVX_MNNPackednMatMulRemainCommon() 737 auto sum10 = _mm256_extractf128_ps(sumAvx10, 0); in _AVX_MNNPackednMatMulRemainCommon() 738 auto sum11 = _mm256_extractf128_ps(sumAvx10, 1); in _AVX_MNNPackednMatMulRemainCommon() 741 auto sum20 = _mm256_extractf128_ps(sumAvx20, 0); in _AVX_MNNPackednMatMulRemainCommon() 784 auto sum0 = _mm256_extractf128_ps(sumAvx0, 0); in _AVX_MNNPackednMatMulRemainCommon() [all …]
|
/dports/science/gromacs/gromacs-2021.4/src/gromacs/simd/impl_x86_avx_256/ |
H A D | impl_x86_avx_256_util_float.h | 60 _mm256_extractf128_ps(a.simdInternal_, 0x1)); in decrHsimd() 252 tE = _mm256_extractf128_ps(t7, 0x1); in transposeScatterIncrU() 253 tF = _mm256_extractf128_ps(t8, 0x1); in transposeScatterIncrU() 254 tG = _mm256_extractf128_ps(t9, 0x1); in transposeScatterIncrU() 255 tH = _mm256_extractf128_ps(t10, 0x1); in transposeScatterIncrU() 380 tE = _mm256_extractf128_ps(t7, 0x1); in transposeScatterDecrU() 381 tF = _mm256_extractf128_ps(t8, 0x1); in transposeScatterDecrU() 382 tG = _mm256_extractf128_ps(t9, 0x1); in transposeScatterDecrU() 383 tH = _mm256_extractf128_ps(t10, 0x1); in transposeScatterDecrU() 607 _mm_store_ps(m1, _mm256_extractf128_ps(a.simdInternal_, 0x1)); in storeDualHsimd() [all …]
|
/dports/multimedia/pipewire/pipewire-0.3.43/spa/plugins/audioconvert/ |
H A D | resample-native-avx.c | 45 sx[1] = _mm256_extractf128_ps(sy[0], 1); in inner_product_avx() 46 sx[0] = _mm256_extractf128_ps(sy[0], 0); in inner_product_avx() 75 sx[0] = _mm_add_ps(_mm256_extractf128_ps(sy[0], 0), _mm256_extractf128_ps(sy[0], 1)); in inner_product_ip_avx() 76 sx[1] = _mm_add_ps(_mm256_extractf128_ps(sy[1], 0), _mm256_extractf128_ps(sy[1], 1)); in inner_product_ip_avx()
|
/dports/net-im/tg_owt/tg_owt-d578c76/src/common_audio/resampler/ |
H A D | sinc_resampler_avx2.cc | 46 __m128 m128_sums1 = _mm_add_ps(_mm256_extractf128_ps(m_sums1, 0), in Convolve_AVX2() 47 _mm256_extractf128_ps(m_sums1, 1)); in Convolve_AVX2() 48 __m128 m128_sums2 = _mm_add_ps(_mm256_extractf128_ps(m_sums2, 0), in Convolve_AVX2() 49 _mm256_extractf128_ps(m_sums2, 1)); in Convolve_AVX2()
|
/dports/www/chromium-legacy/chromium-88.0.4324.182/third_party/webrtc/common_audio/resampler/ |
H A D | sinc_resampler_avx2.cc | 46 __m128 m128_sums1 = _mm_add_ps(_mm256_extractf128_ps(m_sums1, 0), in Convolve_AVX2() 47 _mm256_extractf128_ps(m_sums1, 1)); in Convolve_AVX2() 48 __m128 m128_sums2 = _mm_add_ps(_mm256_extractf128_ps(m_sums2, 0), in Convolve_AVX2() 49 _mm256_extractf128_ps(m_sums2, 1)); in Convolve_AVX2()
|
/dports/www/firefox/firefox-99.0/third_party/libwebrtc/common_audio/resampler/ |
H A D | sinc_resampler_avx2.cc | 46 __m128 m128_sums1 = _mm_add_ps(_mm256_extractf128_ps(m_sums1, 0), in Convolve_AVX2() 47 _mm256_extractf128_ps(m_sums1, 1)); in Convolve_AVX2() 48 __m128 m128_sums2 = _mm_add_ps(_mm256_extractf128_ps(m_sums2, 0), in Convolve_AVX2() 49 _mm256_extractf128_ps(m_sums2, 1)); in Convolve_AVX2()
|
/dports/audio/webrtc-audio-processing/webrtc-audio-processing-1.0/webrtc/common_audio/resampler/ |
H A D | sinc_resampler_avx2.cc | 46 __m128 m128_sums1 = _mm_add_ps(_mm256_extractf128_ps(m_sums1, 0), in Convolve_AVX2() 47 _mm256_extractf128_ps(m_sums1, 1)); in Convolve_AVX2() 48 __m128 m128_sums2 = _mm_add_ps(_mm256_extractf128_ps(m_sums2, 0), in Convolve_AVX2() 49 _mm256_extractf128_ps(m_sums2, 1)); in Convolve_AVX2()
|
/dports/graphics/avir/avir-3.0/ |
H A D | avir_float8_avx.h | 74 return( _mm_cvtss_f32( _mm256_extractf128_ps( value, 0 ))); 162 _mm_storeu_ps( p, _mm256_extractf128_ps( value, 0 )); in storeu() 163 v = _mm256_extractf128_ps( value, 1 ); in storeu() 169 v = _mm256_extractf128_ps( value, 0 ); in storeu() 247 __m128 v = _mm_add_ps( _mm256_extractf128_ps( value, 0 ), in hadd() 248 _mm256_extractf128_ps( value, 1 )); in hadd()
|
/dports/math/blis/blis-0.8.1/kernels/zen/3/sup/broken/ |
H A D | bli_gemmsup_rv_zen_asm_c3x8n.c | 271 _mm_storeu_ps((float *)(tC ) ,_mm256_extractf128_ps (ymm0,1)); in bli_cgemmsup_rv_zen_asm_3x8n() 275 _mm_storeu_ps((float *)(tC) ,_mm256_extractf128_ps (ymm1,1)); in bli_cgemmsup_rv_zen_asm_3x8n() 276 _mm_storeh_pi((__m64 *)(tC+2), _mm256_extractf128_ps(ymm12,1)); in bli_cgemmsup_rv_zen_asm_3x8n() 290 _mm_storeu_ps((float *)(tC ),_mm256_extractf128_ps (ymm0,1)); in bli_cgemmsup_rv_zen_asm_3x8n() 291 _mm_storel_pi((__m64 *)(tC+2), _mm256_extractf128_ps(ymm13,1)); in bli_cgemmsup_rv_zen_asm_3x8n() 294 _mm_storeu_ps((float *)(tC ),_mm256_extractf128_ps (ymm1,1)); in bli_cgemmsup_rv_zen_asm_3x8n() 350 _mm_storeu_ps((float *)(tC) ,_mm256_extractf128_ps (ymm0,1)); in bli_cgemmsup_rv_zen_asm_3x8n() 354 _mm_storeu_ps((float *)(tC ),_mm256_extractf128_ps (ymm3,1)); in bli_cgemmsup_rv_zen_asm_3x8n() 405 _mm_storeu_ps((float *)(tC ),_mm256_extractf128_ps (ymm0,1)); in bli_cgemmsup_rv_zen_asm_3x8n() 409 _mm_storeu_ps((float *)(tC ),_mm256_extractf128_ps (ymm3,1)); in bli_cgemmsup_rv_zen_asm_3x8n() [all …]
|
/dports/devel/volk/volk-2.2.1/kernels/volk/ |
H A D | volk_32f_64f_multiply_64f.h | 125 aVal1 = _mm256_extractf128_ps(aVal, 0); in volk_32f_64f_multiply_64f_u_avx() 126 aVal2 = _mm256_extractf128_ps(aVal, 1); in volk_32f_64f_multiply_64f_u_avx() 176 aVal1 = _mm256_extractf128_ps(aVal, 0); in volk_32f_64f_multiply_64f_a_avx() 177 aVal2 = _mm256_extractf128_ps(aVal, 1); in volk_32f_64f_multiply_64f_a_avx()
|
H A D | volk_32f_64f_add_64f.h | 164 aVal1 = _mm256_extractf128_ps(aVal, 0); in volk_32f_64f_add_64f_u_avx() 165 aVal2 = _mm256_extractf128_ps(aVal, 1); in volk_32f_64f_add_64f_u_avx() 216 aVal1 = _mm256_extractf128_ps(aVal, 0); in volk_32f_64f_add_64f_a_avx() 217 aVal2 = _mm256_extractf128_ps(aVal, 1); in volk_32f_64f_add_64f_a_avx()
|
/dports/graphics/openjph/OpenJPH-0.7.3/src/core/transform/ |
H A D | ojph_transform_avx.cpp | 109 __m128 t1 = _mm256_extractf128_ps(d1, 0); in avx_irrev_horz_wvlt_fwd_tx() 110 __m128 t2 = _mm256_extractf128_ps(d1, 1); in avx_irrev_horz_wvlt_fwd_tx() 127 __m128 t1 = _mm256_extractf128_ps(d1, 0); in avx_irrev_horz_wvlt_fwd_tx() 128 __m128 t2 = _mm256_extractf128_ps(d1, 1); in avx_irrev_horz_wvlt_fwd_tx() 290 __m128 a0 = _mm256_extractf128_ps(s1, 0); in avx_irrev_horz_wvlt_bwd_tx() 291 __m128 a1 = _mm256_extractf128_ps(s1, 1); in avx_irrev_horz_wvlt_bwd_tx() 292 __m128 a2 = _mm256_extractf128_ps(d, 0); in avx_irrev_horz_wvlt_bwd_tx() 293 __m128 a3 = _mm256_extractf128_ps(d, 1); in avx_irrev_horz_wvlt_bwd_tx()
|
/dports/devel/libflatarray/libflatarray-0.3.0/src/detail/ |
H A D | short_vec_avx_float_32.hpp | 92 _mm256_extractf128_ps(buf0, 0), in any() 93 _mm256_extractf128_ps(buf0, 1)); in any() 127 buf1 = _mm256_extractf128_ps(buf0, 0); in get() 403 tmp = _mm256_extractf128_ps(val1, 0); in scatter() 408 tmp = _mm256_extractf128_ps(val1, 1); in scatter() 413 tmp = _mm256_extractf128_ps(val2, 0); in scatter() 418 tmp = _mm256_extractf128_ps(val2, 1); in scatter() 423 tmp = _mm256_extractf128_ps(val3, 0); in scatter() 428 tmp = _mm256_extractf128_ps(val3, 1); in scatter() 433 tmp = _mm256_extractf128_ps(val4, 0); in scatter() [all …]
|
H A D | short_vec_avx_float_16.hpp | 86 _mm256_extractf128_ps(buf0, 0), in any() 87 _mm256_extractf128_ps(buf0, 1)); in any() 113 buf1 = _mm256_extractf128_ps(buf0, 0); in get() 115 buf1 = _mm256_extractf128_ps(buf0, 1); in get() 327 tmp = _mm256_extractf128_ps(val1, 0); in scatter() 332 tmp = _mm256_extractf128_ps(val1, 1); in scatter() 337 tmp = _mm256_extractf128_ps(val2, 0); in scatter() 342 tmp = _mm256_extractf128_ps(val2, 1); in scatter()
|
H A D | short_vec_avx_float_8.hpp | 85 _mm256_extractf128_ps(val1, 0), in any() 86 _mm256_extractf128_ps(val1, 1)); in any() 103 buf = _mm256_extractf128_ps(val1, 0); in get() 105 buf = _mm256_extractf128_ps(val1, 1); in get() 281 tmp = _mm256_extractf128_ps(val1, 0); in scatter() 286 tmp = _mm256_extractf128_ps(val1, 1); in scatter()
|
/dports/net-im/tg_owt/tg_owt-d578c76/src/modules/audio_processing/aec3/ |
H A D | matched_filter_avx2.cc | 76 __m128 x2_sum_128 = _mm_add_ps(_mm256_extractf128_ps(x2_sum_256, 0), in MatchedFilterCore_AVX2() 77 _mm256_extractf128_ps(x2_sum_256, 1)); in MatchedFilterCore_AVX2() 78 __m128 s_128 = _mm_add_ps(_mm256_extractf128_ps(s_256, 0), in MatchedFilterCore_AVX2() 79 _mm256_extractf128_ps(s_256, 1)); in MatchedFilterCore_AVX2()
|
/dports/www/chromium-legacy/chromium-88.0.4324.182/third_party/webrtc/modules/audio_processing/aec3/ |
H A D | matched_filter_avx2.cc | 76 __m128 x2_sum_128 = _mm_add_ps(_mm256_extractf128_ps(x2_sum_256, 0), in MatchedFilterCore_AVX2() 77 _mm256_extractf128_ps(x2_sum_256, 1)); in MatchedFilterCore_AVX2() 78 __m128 s_128 = _mm_add_ps(_mm256_extractf128_ps(s_256, 0), in MatchedFilterCore_AVX2() 79 _mm256_extractf128_ps(s_256, 1)); in MatchedFilterCore_AVX2()
|
/dports/www/firefox/firefox-99.0/third_party/libwebrtc/modules/audio_processing/aec3/ |
H A D | matched_filter_avx2.cc | 76 __m128 x2_sum_128 = _mm_add_ps(_mm256_extractf128_ps(x2_sum_256, 0), in MatchedFilterCore_AVX2() 77 _mm256_extractf128_ps(x2_sum_256, 1)); in MatchedFilterCore_AVX2() 78 __m128 s_128 = _mm_add_ps(_mm256_extractf128_ps(s_256, 0), in MatchedFilterCore_AVX2() 79 _mm256_extractf128_ps(s_256, 1)); in MatchedFilterCore_AVX2()
|
/dports/audio/webrtc-audio-processing/webrtc-audio-processing-1.0/webrtc/modules/audio_processing/aec3/ |
H A D | matched_filter_avx2.cc | 76 __m128 x2_sum_128 = _mm_add_ps(_mm256_extractf128_ps(x2_sum_256, 0), in MatchedFilterCore_AVX2() 77 _mm256_extractf128_ps(x2_sum_256, 1)); in MatchedFilterCore_AVX2() 78 __m128 s_128 = _mm_add_ps(_mm256_extractf128_ps(s_256, 0), in MatchedFilterCore_AVX2() 79 _mm256_extractf128_ps(s_256, 1)); in MatchedFilterCore_AVX2()
|
/dports/audio/supercollider/SuperCollider-3.11.0-Source/external_libraries/nova-simd/vec/ |
H A D | vec_int_avx.hpp | 61 __m128 lhs_hi = _mm256_extractf128_ps(lhs_data, 1); \ 63 __m128 rhs_hi = _mm256_extractf128_ps(rhs_data, 1); \ 101 __m128 arg_hi = _mm256_extractf128_ps(arg_data, 1); in slli() 116 __m128 arg_hi = _mm256_extractf128_ps(arg_data, 1); in srli()
|
/dports/audio/sc3-plugins/sc3-plugins-Version-3.9.0/external_libraries/nova-simd/vec/ |
H A D | vec_int_avx.hpp | 61 __m128 lhs_hi = _mm256_extractf128_ps(lhs_data, 1); \ 63 __m128 rhs_hi = _mm256_extractf128_ps(rhs_data, 1); \ 101 __m128 arg_hi = _mm256_extractf128_ps(arg_data, 1); in slli() 116 __m128 arg_hi = _mm256_extractf128_ps(arg_data, 1); in srli()
|
/dports/misc/mnn/MNN-1.2.0/source/backend/cpu/x86_x64/avx512/ |
H A D | Gemm48_8.hpp | 286 auto m0 = _mm256_extractf128_ps(z0, u); \ 287 auto m1 = _mm256_extractf128_ps(z3, u); \ 288 auto m2 = _mm256_extractf128_ps(z6, u); \ 289 auto m3 = _mm256_extractf128_ps(z9, u); \ 290 auto m4 = _mm256_extractf128_ps(z12, u); \ 291 auto m5 = _mm256_extractf128_ps(z15, u); \ 292 auto m6 = _mm256_extractf128_ps(z18, u); \ 293 auto m7 = _mm256_extractf128_ps(z21, u); \ 316 auto m0 = _mm256_extractf128_ps(z0, u); \ 317 auto m1 = _mm256_extractf128_ps(z3, u); \ [all …]
|
/dports/graphics/blender/blender-2.91.0/intern/cycles/util/ |
H A D | util_avxb.h | 156 __m128i a_lo = _mm_castps_si128(_mm256_extractf128_ps(a, 0)); 157 __m128i a_hi = _mm_castps_si128(_mm256_extractf128_ps(a, 1)); 158 __m128i b_lo = _mm_castps_si128(_mm256_extractf128_ps(b, 0)); 159 __m128i b_hi = _mm_castps_si128(_mm256_extractf128_ps(b, 1));
|