| /dports/net-im/libsignal-client/libsignal-client-0.9.6/cargo-crates/poly1305-0.7.1/src/backend/avx2/ |
| H A D | helpers.rs | 161 let xh = _mm256_permutevar8x32_epi32( in new()
224 let a_5 = _mm256_permutevar8x32_epi32( in from()
1351 _mm256_permutevar8x32_epi32(r1, ord), in mul()
1352 _mm256_permutevar8x32_epi32(v0, ord), in mul()
1357 _mm256_permutevar8x32_epi32(r1, ord), in mul()
1358 _mm256_permutevar8x32_epi32(v1, ord), in mul()
1368 _mm256_permutevar8x32_epi32(v0, ord), in mul()
1813 let t = _mm256_permutevar8x32_epi32( in add()
1849 _mm256_permutevar8x32_epi32( in add()
1873 let mask = _mm256_permutevar8x32_epi32( in add()
[all …]
|
| /dports/dns/doh-proxy/doh-proxy-0.9.2/cargo-crates/poly1305-0.6.2/src/backend/avx2/ |
| H A D | helpers.rs | 161 let xh = _mm256_permutevar8x32_epi32( in new()
224 let a_5 = _mm256_permutevar8x32_epi32( in from()
1351 _mm256_permutevar8x32_epi32(r1, ord), in mul()
1352 _mm256_permutevar8x32_epi32(v0, ord), in mul()
1357 _mm256_permutevar8x32_epi32(r1, ord), in mul()
1358 _mm256_permutevar8x32_epi32(v1, ord), in mul()
1368 _mm256_permutevar8x32_epi32(v0, ord), in mul()
1813 let t = _mm256_permutevar8x32_epi32( in add()
1849 _mm256_permutevar8x32_epi32( in add()
1873 let mask = _mm256_permutevar8x32_epi32( in add()
[all …]
|
| /dports/x11/eaglemode/eaglemode-0.95.0/src/emCore/ |
| H A D | emPainter_ScTlIntImg_AVX2.cpp | 494 __m256i v01=_mm256_permutevar8x32_epi32(vt,_mm256_set_epi32(4,3,2,1,3,2,1,0)); in CONCAT()
495 __m256i vff=_mm256_permutevar8x32_epi32(vt,_mm256_set_epi32(0,7,6,5,0,0,0,4)); in CONCAT()
504 __m256i vtb=_mm256_permutevar8x32_epi32(vta,_mm256_set_epi32(7,0,3,2,3,2,7,0)); in CONCAT()
529 vff=_mm256_permutevar8x32_epi32(vff,_mm256_set_epi32(1,7,6,5,0,3,2,4)); in CONCAT()
857 __m256i v02=_mm256_permutevar8x32_epi32(vt,_mm256_set_epi32(0,0,0,2,0,6,4,0)); in CONCAT()
858 __m256i v13=_mm256_permutevar8x32_epi32(vt,_mm256_set_epi32(0,0,0,3,0,7,5,1)); in CONCAT()
887 v13=_mm256_permutevar8x32_epi32(oldV02,_mm256_set_epi32(0,7,6,1,5,3,2,4)); in CONCAT()
1254 __m256i v02=_mm256_permutevar8x32_epi32(vt,_mm256_set_epi32(0,0,0,2,0,6,4,0)); in CONCAT()
1255 __m256i v13=_mm256_permutevar8x32_epi32(vt,_mm256_set_epi32(0,0,0,3,0,7,5,1)); in CONCAT()
1284 v13=_mm256_permutevar8x32_epi32(oldV02,_mm256_set_epi32(0,7,6,1,5,3,2,4)); in CONCAT()
[all …]
|
| /dports/x11/eaglemode/eaglemode-0.95.0/src/emAv/ |
| H A D | emAvImageConverter_AVX2.cpp | 131 br=_mm256_permutevar8x32_epi32(br,_mm256_set_epi32( in ConvertI420_AVX2()
134 bg=_mm256_permutevar8x32_epi32(bg,_mm256_set_epi32( in ConvertI420_AVX2()
137 bb=_mm256_permutevar8x32_epi32(bb,_mm256_set_epi32( in ConvertI420_AVX2()
176 ac=_mm256_permutevar8x32_epi32(ac,_mm256_set_epi32( in ConvertI420_AVX2()
|
| /dports/math/viennacl/ViennaCL-1.7.1/viennacl/linalg/host_based/ |
| H A D | spgemm_vector.hpp | 73 …__m256i avx_temp = _mm256_permutevar8x32_epi32(avx_index_min1, _mm256_set_epi32(3, 2, 1, 0, … in row_C_scan_symbolic_vector_AVX2()
417 … _mm256_permutevar8x32_epi32(avx_load_mask, _mm256_set_epi32(3, 7, 2, 6, 1, 5, 0, 4)), 8); // mask in row_C_scan_numeric_vector_AVX2()
422 … _mm256_permutevar8x32_epi32(avx_load_mask, _mm256_set_epi32(7, 3, 6, 2, 5, 1, 4, 0)), 8); // mask in row_C_scan_numeric_vector_AVX2()
440 … _mm256_permutevar8x32_epi32(avx_load_mask, _mm256_set_epi32(3, 7, 2, 6, 1, 5, 0, 4)), 8); // mask in row_C_scan_numeric_vector_AVX2()
445 … _mm256_permutevar8x32_epi32(avx_load_mask, _mm256_set_epi32(7, 3, 6, 2, 5, 1, 4, 0)), 8); // mask in row_C_scan_numeric_vector_AVX2()
453 …__m256i avx_temp = _mm256_permutevar8x32_epi32(avx_index_min1, _mm256_set_epi32(3, 2, 1, 0, … in row_C_scan_numeric_vector_AVX2()
502 … _mm256_permutevar8x32_epi32(avx_load_mask, _mm256_set_epi32(3, 7, 2, 6, 1, 5, 0, 4)), 8); // mask in row_C_scan_numeric_vector_AVX2()
508 … _mm256_permutevar8x32_epi32(avx_load_mask, _mm256_set_epi32(7, 3, 6, 2, 5, 1, 4, 0)), 8); // mask in row_C_scan_numeric_vector_AVX2()
|
| /dports/biology/gmap/gmap-2020-09-12/src/ |
| H A D | merge-uint4.c | 137 vTmp = _mm256_permutevar8x32_epi32(vMin, vRot); /* Rotate Min by ints */ in merge_8x8()
142 vTmp = _mm256_permutevar8x32_epi32(vMin, vRot); /* Rotate Min by ints */ in merge_8x8()
147 vTmp = _mm256_permutevar8x32_epi32(vMin, vRot); /* Rotate Min by ints */ in merge_8x8()
152 vTmp = _mm256_permutevar8x32_epi32(vMin, vRot); /* Rotate Min by ints */ in merge_8x8()
157 vTmp = _mm256_permutevar8x32_epi32(vMin, vRot); /* Rotate Min by ints */ in merge_8x8()
162 vTmp = _mm256_permutevar8x32_epi32(vMin, vRot); /* Rotate Min by ints */ in merge_8x8()
167 vTmp = _mm256_permutevar8x32_epi32(vMin, vRot); /* Rotate Min by ints */ in merge_8x8()
173 *vMergedA = _mm256_permutevar8x32_epi32(vMin, vRot); /* Rotate Min by ints */ in merge_8x8()
|
| /dports/misc/visp/visp-3.4.0/3rdparty/simdlib/Simd/ |
| H A D | SimdAvx2Deinterleave.cpp | 89 …Store<align>((__m256i*)(b + offset), _mm256_permutevar8x32_epi32(_mm256_unpacklo_epi64(bbgg0, bbgg… in DeinterleaveBgra()
90 …Store<align>((__m256i*)(g + offset), _mm256_permutevar8x32_epi32(_mm256_unpackhi_epi64(bbgg0, bbgg… in DeinterleaveBgra()
95 …Store<align>((__m256i*)(r + offset), _mm256_permutevar8x32_epi32(_mm256_unpacklo_epi64(rraa0, rraa… in DeinterleaveBgra()
96 …Store<align>((__m256i*)(a + offset), _mm256_permutevar8x32_epi32(_mm256_unpackhi_epi64(rraa0, rraa… in DeinterleaveBgra()
|
| H A D | SimdAvx2GrayToBgra.cpp | 58 … __m256i _gray = _mm256_permutevar8x32_epi32(Load<align>((__m256i*)(gray + col)), permuteOffsets); in GrayToBgra()
63 …__m256i _gray = _mm256_permutevar8x32_epi32(Load<false>((__m256i*)(gray + width - A)), permuteOffs… in GrayToBgra()
|
| /dports/graphics/openjph/OpenJPH-0.7.3/src/core/transform/ |
| H A D | ojph_transform_avx2.cpp | 117 d1 = _mm256_permutevar8x32_epi32(d1, mask); in avx2_rev_horz_wvlt_fwd_tx()
118 d2 = _mm256_permutevar8x32_epi32(d2, mask); in avx2_rev_horz_wvlt_fwd_tx()
139 d1 = _mm256_permutevar8x32_epi32(d1, mask); in avx2_rev_horz_wvlt_fwd_tx()
140 d2 = _mm256_permutevar8x32_epi32(d2, mask); in avx2_rev_horz_wvlt_fwd_tx()
|
| /dports/graphics/tesseract/tesseract-5.0.0/src/arch/ |
| H A D | intsimdmatrixavx2.cpp | 164 inputs = _mm256_permutevar8x32_epi32(inputs, shift_id); in PartialMatrixDotVector64()
205 inputs = _mm256_permutevar8x32_epi32(inputs, shift_id); in PartialMatrixDotVector32()
238 inputs = _mm256_permutevar8x32_epi32(inputs, shift_id); in PartialMatrixDotVector16()
267 inputs = _mm256_permutevar8x32_epi32(inputs, shift_id); in PartialMatrixDotVector8()
409 inputs = _mm256_permutevar8x32_epi32(inputs, shift_id); in PartialMatrixDotVector64()
450 inputs = _mm256_permutevar8x32_epi32(inputs, shift_id); in PartialMatrixDotVector32()
483 inputs = _mm256_permutevar8x32_epi32(inputs, shift_id); in PartialMatrixDotVector16()
512 inputs = _mm256_permutevar8x32_epi32(inputs, shift_id); in PartialMatrixDotVector8()
|
| /dports/multimedia/gstreamer1-plugins-svt-hevc/SVT-HEVC-1.5.1/Source/Lib/ASM_AVX2/ |
| H A D | EbCombinedAveragingSAD_Intrinsic_AVX2.c | 123 … ymm_blockMeanSquaredlow = _mm256_permutevar8x32_epi32(ymm_blockMeanSquaredlow,ymm_permute8/*8*/); in ComputeIntermVarFour8x8_AVX2_INTRIN()
124 ymm_blockMeanSquaredHi = _mm256_permutevar8x32_epi32(ymm_blockMeanSquaredHi,ymm_permute8); in ComputeIntermVarFour8x8_AVX2_INTRIN()
137 ymm_result = _mm256_permutevar8x32_epi32(ymm_result,ymm_permute8); in ComputeIntermVarFour8x8_AVX2_INTRIN()
|
| /dports/multimedia/svt-av1/SVT-AV1-3971c982311d49f9355dc8dccdcf8d21b70fa624/Source/Lib/Encoder/ASM_AVX2/ |
| H A D | EbCombinedAveragingSAD_Intrinsic_AVX2.c | 147 ymm_block_mean_squared_low = _mm256_permutevar8x32_epi32(ymm_block_mean_squared_low, in svt_compute_interm_var_four8x8_avx2_intrin()
149 ymm_block_mean_squared_high = _mm256_permutevar8x32_epi32(ymm_block_mean_squared_high, in svt_compute_interm_var_four8x8_avx2_intrin()
164 ymm_result = _mm256_permutevar8x32_epi32(ymm_result, ymm_permute8); in svt_compute_interm_var_four8x8_avx2_intrin()
|
| /dports/multimedia/svt-hevc/SVT-HEVC-1.5.1/Source/Lib/ASM_AVX2/ |
| H A D | EbCombinedAveragingSAD_Intrinsic_AVX2.c | 123 … ymm_blockMeanSquaredlow = _mm256_permutevar8x32_epi32(ymm_blockMeanSquaredlow,ymm_permute8/*8*/); in ComputeIntermVarFour8x8_AVX2_INTRIN()
124 ymm_blockMeanSquaredHi = _mm256_permutevar8x32_epi32(ymm_blockMeanSquaredHi,ymm_permute8); in ComputeIntermVarFour8x8_AVX2_INTRIN()
137 ymm_result = _mm256_permutevar8x32_epi32(ymm_result,ymm_permute8); in ComputeIntermVarFour8x8_AVX2_INTRIN()
|
| /dports/multimedia/gstreamer1-plugins-svt-av1/SVT-AV1-3971c982311d49f9355dc8dccdcf8d21b70fa624/Source/Lib/Encoder/ASM_AVX2/ |
| H A D | EbCombinedAveragingSAD_Intrinsic_AVX2.c | 147 ymm_block_mean_squared_low = _mm256_permutevar8x32_epi32(ymm_block_mean_squared_low, in svt_compute_interm_var_four8x8_avx2_intrin()
149 ymm_block_mean_squared_high = _mm256_permutevar8x32_epi32(ymm_block_mean_squared_high, in svt_compute_interm_var_four8x8_avx2_intrin()
164 ymm_result = _mm256_permutevar8x32_epi32(ymm_result, ymm_permute8); in svt_compute_interm_var_four8x8_avx2_intrin()
|
| /dports/databases/arrow/apache-arrow-6.0.1/cpp/src/arrow/compute/exec/ |
| H A D | key_hash_avx2.cc | 48 acc = _mm256_permutevar8x32_epi32(acc, _mm256_setr_epi32(0, 4, 0, 0, 0, 0, 0, 0)); in combine_accumulators_avx2()
125 v1 = _mm256_permutevar8x32_epi32(v1, _mm256_setr_epi32(0, 2, 4, 6, 1, 3, 5, 7)); in helper_tails_avx2()
126 v2 = _mm256_permutevar8x32_epi32(v2, _mm256_setr_epi32(0, 2, 4, 6, 1, 3, 5, 7)); in helper_tails_avx2()
228 _mm256_permutevar8x32_epi32(hash, _mm256_setr_epi32(0, 4, 1, 5, 2, 6, 3, 7))); in hash_varlen_avx2()
|
| /dports/devel/simde/simde-0.7.2/simde/x86/avx512/ |
| H A D | permutex2var.h | 691 ta = _mm256_permutevar8x32_epi32(a, idx2); in simde_mm256_permutex2var_epi16()
692 tb = _mm256_permutevar8x32_epi32(b, idx2); in simde_mm256_permutex2var_epi16()
699 ta = _mm256_permutevar8x32_epi32(a, idx2); in simde_mm256_permutex2var_epi16()
700 tb = _mm256_permutevar8x32_epi32(b, idx2); in simde_mm256_permutex2var_epi16()
784 ta = _mm256_permutevar8x32_epi32(a, idx); in simde_mm256_permutex2var_epi32()
785 tb = _mm256_permutevar8x32_epi32(b, idx); in simde_mm256_permutex2var_epi32()
1148 ta = _mm256_permutevar8x32_epi32(a_.m256i[0], idx2); in simde_mm512_permutex2var_epi16()
1149 tb = _mm256_permutevar8x32_epi32(b_.m256i[0], idx2); in simde_mm512_permutex2var_epi16()
1153 ta = _mm256_permutevar8x32_epi32(a_.m256i[1], idx2); in simde_mm512_permutex2var_epi16()
1166 ta = _mm256_permutevar8x32_epi32(a_.m256i[0], idx2); in simde_mm512_permutex2var_epi16()
[all …]
|
| /dports/biology/bowtie2/simde-no-tests-f6a0b3b/x86/avx512/ |
| H A D | permutex2var.h | 691 ta = _mm256_permutevar8x32_epi32(a, idx2); in simde_mm256_permutex2var_epi16()
692 tb = _mm256_permutevar8x32_epi32(b, idx2); in simde_mm256_permutex2var_epi16()
699 ta = _mm256_permutevar8x32_epi32(a, idx2); in simde_mm256_permutex2var_epi16()
700 tb = _mm256_permutevar8x32_epi32(b, idx2); in simde_mm256_permutex2var_epi16()
784 ta = _mm256_permutevar8x32_epi32(a, idx); in simde_mm256_permutex2var_epi32()
785 tb = _mm256_permutevar8x32_epi32(b, idx); in simde_mm256_permutex2var_epi32()
1148 ta = _mm256_permutevar8x32_epi32(a_.m256i[0], idx2); in simde_mm512_permutex2var_epi16()
1149 tb = _mm256_permutevar8x32_epi32(b_.m256i[0], idx2); in simde_mm512_permutex2var_epi16()
1153 ta = _mm256_permutevar8x32_epi32(a_.m256i[1], idx2); in simde_mm512_permutex2var_epi16()
1166 ta = _mm256_permutevar8x32_epi32(a_.m256i[0], idx2); in simde_mm512_permutex2var_epi16()
[all …]
|
| /dports/biology/mmseqs2/MMseqs2-13-45111/lib/simde/simde/x86/avx512/ |
| H A D | permutex2var.h | 691 ta = _mm256_permutevar8x32_epi32(a, idx2); in simde_mm256_permutex2var_epi16()
692 tb = _mm256_permutevar8x32_epi32(b, idx2); in simde_mm256_permutex2var_epi16()
699 ta = _mm256_permutevar8x32_epi32(a, idx2); in simde_mm256_permutex2var_epi16()
700 tb = _mm256_permutevar8x32_epi32(b, idx2); in simde_mm256_permutex2var_epi16()
784 ta = _mm256_permutevar8x32_epi32(a, idx); in simde_mm256_permutex2var_epi32()
785 tb = _mm256_permutevar8x32_epi32(b, idx); in simde_mm256_permutex2var_epi32()
1148 ta = _mm256_permutevar8x32_epi32(a_.m256i[0], idx2); in simde_mm512_permutex2var_epi16()
1149 tb = _mm256_permutevar8x32_epi32(b_.m256i[0], idx2); in simde_mm512_permutex2var_epi16()
1153 ta = _mm256_permutevar8x32_epi32(a_.m256i[1], idx2); in simde_mm512_permutex2var_epi16()
1166 ta = _mm256_permutevar8x32_epi32(a_.m256i[0], idx2); in simde_mm512_permutex2var_epi16()
[all …]
|
| /dports/lang/gcc6-aux/gcc-6-20180516/gcc/testsuite/gcc.target/i386/ |
| H A D | avx2-vpermd-1.c | 12 x = _mm256_permutevar8x32_epi32 (x, x); in avx2_test()
|
| /dports/lang/gcc10/gcc-10.3.0/gcc/testsuite/gcc.target/i386/ |
| H A D | avx2-vpermd-1.c | 12 x = _mm256_permutevar8x32_epi32 (x, x); in avx2_test()
|
| /dports/devel/riscv64-none-elf-gcc/gcc-8.4.0/gcc/testsuite/gcc.target/i386/ |
| H A D | avx2-vpermd-1.c | 12 x = _mm256_permutevar8x32_epi32 (x, x); in avx2_test()
|
| /dports/lang/gcc11-devel/gcc-11-20211009/gcc/testsuite/gcc.target/i386/ |
| H A D | avx2-vpermd-1.c | 12 x = _mm256_permutevar8x32_epi32 (x, x); in avx2_test()
|
| /dports/devel/arm-none-eabi-gcc/gcc-8.4.0/gcc/testsuite/gcc.target/i386/ |
| H A D | avx2-vpermd-1.c | 12 x = _mm256_permutevar8x32_epi32 (x, x); in avx2_test()
|
| /dports/devel/riscv32-unknown-elf-gcc/gcc-8.4.0/gcc/testsuite/gcc.target/i386/ |
| H A D | avx2-vpermd-1.c | 12 x = _mm256_permutevar8x32_epi32 (x, x); in avx2_test()
|
| /dports/devel/aarch64-none-elf-gcc/gcc-8.4.0/gcc/testsuite/gcc.target/i386/ |
| H A D | avx2-vpermd-1.c | 12 x = _mm256_permutevar8x32_epi32 (x, x); in avx2_test()
|