/dports/math/blasfeo/blasfeo-0.1.2/kernel/avx2/ |
H A D | kernel_dgetr_lib4.c | 93 …v0 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A0[0+bs*0] ) ), _mm_load_pd( &A0[… in kernel_dgetr_8_lib4() 94 …v1 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A0[0+bs*1] ) ), _mm_load_pd( &A0[… in kernel_dgetr_8_lib4() 95 …v2 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A0[2+bs*0] ) ), _mm_load_pd( &A0[… in kernel_dgetr_8_lib4() 96 …v3 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A0[2+bs*1] ) ), _mm_load_pd( &A0[… in kernel_dgetr_8_lib4() 113 …v0 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A1[0+bs*0] ) ), _mm_load_pd( &A1[… in kernel_dgetr_8_lib4() 114 …v1 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A1[0+bs*1] ) ), _mm_load_pd( &A1[… in kernel_dgetr_8_lib4() 115 …v2 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A1[2+bs*0] ) ), _mm_load_pd( &A1[… in kernel_dgetr_8_lib4() 320 …v0 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[0+bs*0] ) ), _mm_load_pd( &A[0+… in kernel_dgetr_4_lib4() 321 …v1 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[0+bs*1] ) ), _mm_load_pd( &A[0+… in kernel_dgetr_4_lib4() 322 …v2 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[2+bs*0] ) ), _mm_load_pd( &A[2+… in kernel_dgetr_4_lib4() [all …]
|
H A D | kernel_dgetrf_pivot_lib.c | 189 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib() 424 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib() 647 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib() 857 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib() 1055 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib() 1239 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib() 1410 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib() 1568 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib() 1715 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib() 1847 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib() [all …]
|
H A D | kernel_dgetrf_pivot_lib4.c | 209 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib4() 442 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib4() 663 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib4() 871 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib4() 1067 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib4() 1249 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib4() 1418 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib4() 1573 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib4() 1718 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib4() 1848 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_12_lib4() [all …]
|
/dports/multimedia/gstreamer1-plugins-rust/gst-plugins-rs-d0466b3eee114207f851b37cae0015c0e718f021/cargo-crates/rustfft-5.1.1/src/avx/ |
H A D | avx64_utils.rs | 37 _mm256_castpd128_pd256(rows0[1]), 38 _mm256_castpd128_pd256(rows0[2]), 57 _mm256_castpd128_pd256(rows0[0]), 58 _mm256_castpd128_pd256(rows0[1]), 62 _mm256_castpd128_pd256(rows0[2]), 63 _mm256_castpd128_pd256(rows0[3]), 95 _mm256_insertf128_pd(_mm256_castpd128_pd256(rows0[0]), rows0[1], 1), 100 _mm256_insertf128_pd(_mm256_castpd128_pd256(rows0[2]), rows0[3], 1), 105 _mm256_insertf128_pd(_mm256_castpd128_pd256(rows0[4]), rows0[5], 1), 145 _mm256_insertf128_pd(_mm256_castpd128_pd256(rows0[1]), rows0[2], 1),
|
/dports/math/blasfeo/blasfeo-0.1.2/experimental/giaf/blas/kernel/avx2/ |
H A D | kernel_dpatr_lib4.c | 62 …v0 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[0+bs*0] ) ), _mm_load_pd( &A[0+… in kernel_dpatr_tn_4_lib4() 63 …v1 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[0+bs*1] ) ), _mm_load_pd( &A[0+… in kernel_dpatr_tn_4_lib4() 64 …v2 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[2+bs*0] ) ), _mm_load_pd( &A[2+… in kernel_dpatr_tn_4_lib4() 65 …v3 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[2+bs*1] ) ), _mm_load_pd( &A[2+… in kernel_dpatr_tn_4_lib4() 311 …v0 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[0+lda*0] ) ), _mm_load_pd( &A[0… 312 …v1 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[0+lda*1] ) ), _mm_load_pd( &A[0… 313 …v2 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[2+lda*0] ) ), _mm_load_pd( &A[2… 314 …v3 = _mm256_insertf128_pd( _mm256_castpd128_pd256( _mm_load_pd( &A[2+lda*1] ) ), _mm_load_pd( &A[2…
|
/dports/math/blis/blis-0.8.1/kernels/zen/3/sup/broken/ |
H A D | bli_gemmsup_rv_zen_asm_z3x4n.c | 287 ymm0 = _mm256_insertf128_pd(_mm256_castpd128_pd256(xmm0), xmm3, 1) ; in bli_zgemmsup_rv_zen_asm_3x4n() 296 ymm0 = _mm256_insertf128_pd(_mm256_castpd128_pd256(xmm0), xmm3, 1) ; in bli_zgemmsup_rv_zen_asm_3x4n() 306 ymm0 = _mm256_insertf128_pd(_mm256_castpd128_pd256(xmm0), xmm3, 1) ; in bli_zgemmsup_rv_zen_asm_3x4n() 327 ymm0 = _mm256_insertf128_pd(_mm256_castpd128_pd256(xmm0), xmm3, 1) ; in bli_zgemmsup_rv_zen_asm_3x4n() 336 ymm0 = _mm256_insertf128_pd(_mm256_castpd128_pd256(xmm0), xmm3, 1) ; in bli_zgemmsup_rv_zen_asm_3x4n() 346 ymm0 = _mm256_insertf128_pd(_mm256_castpd128_pd256(xmm0), xmm3, 1) ; in bli_zgemmsup_rv_zen_asm_3x4n() 626 ymm0 = _mm256_insertf128_pd(_mm256_castpd128_pd256(xmm0), xmm3, 1) ; in bli_zgemmsup_rv_zen_asm_2x4n() 635 ymm0 = _mm256_insertf128_pd(_mm256_castpd128_pd256(xmm0), xmm3, 1) ; in bli_zgemmsup_rv_zen_asm_2x4n() 1125 ymm0 = _mm256_insertf128_pd(_mm256_castpd128_pd256(xmm0), xmm3, 1) ; in bli_zgemmsup_rv_zen_asm_3x2() 1134 ymm0 = _mm256_insertf128_pd(_mm256_castpd128_pd256(xmm0), xmm3, 1) ; in bli_zgemmsup_rv_zen_asm_3x2() [all …]
|
/dports/math/blasfeo/blasfeo-0.1.2/kernel/avx/ |
H A D | kernel_dgetrf_pivot_lib.c | 189 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib() 393 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib() 582 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib() 755 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib() 913 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib() 1054 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib() 1179 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib() 1288 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib() 1544 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_4_lib() 1684 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_4_lib() [all …]
|
H A D | kernel_dgetrf_pivot_lib4.c | 209 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib4() 411 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib4() 598 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib4() 769 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib4() 924 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib4() 1062 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib4() 1184 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib4() 1290 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_8_lib4() 1523 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_4_lib4() 1651 …scl = _mm256_permute2f128_pd( _mm256_castpd128_pd256( inv ), _mm256_castpd128_pd256( inv ), 0x00 ); in kernel_dgetrf_pivot_4_lib4() [all …]
|
/dports/science/gromacs/gromacs-2021.4/src/gromacs/simd/impl_x86_avx_256/ |
H A D | impl_x86_avx_256_util_double.h | 101 tA = _mm256_insertf128_pd(_mm256_castpd128_pd256(t1), t3, 0x1); in gatherLoadTranspose() 102 tB = _mm256_insertf128_pd(_mm256_castpd128_pd256(t2), t4, 0x1); in gatherLoadTranspose() 355 tA = _mm256_insertf128_pd(_mm256_castpd128_pd256(t1), t3, 0x1); in gatherLoadBySimdIntTranspose() 356 tB = _mm256_insertf128_pd(_mm256_castpd128_pd256(t2), t4, 0x1); in gatherLoadBySimdIntTranspose() 376 tA = _mm256_insertf128_pd(_mm256_castpd128_pd256(t1), t3, 0x1); in gatherLoadUBySimdIntTranspose() 377 tB = _mm256_insertf128_pd(_mm256_castpd128_pd256(t2), t4, 0x1); in gatherLoadUBySimdIntTranspose()
|
/dports/devel/vc/Vc-1.4.2/Vc/avx/ |
H A D | casts.h | 75 …template<> Vc_INTRINSIC __m256d avx_cast(__m128 v) { return _mm256_castpd128_pd256(_mm_castps_pd(… in avx_cast() 76 …template<> Vc_INTRINSIC __m256d avx_cast(__m128i v) { return _mm256_castpd128_pd256(_mm_castsi128_… in avx_cast() 77 template<> Vc_INTRINSIC __m256d avx_cast(__m128d v) { return _mm256_castpd128_pd256(v); } in avx_cast() 82 …xtend(__m128d v) { return _mm256_permute2f128_pd (_mm256_castpd128_pd256(v), _mm256_castpd128_pd… in zeroExtend() 86 static Vc_INTRINSIC Vc_CONST __m256d zeroExtend(__m128d v) { return _mm256_castpd128_pd256(v); } in zeroExtend()
|
/dports/lang/gcc6-aux/gcc-6-20180516/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/lang/gcc12-devel/gcc-12-20211205/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/lang/gcc8/gcc-8.5.0/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/lang/gcc9/gcc-9.4.0/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/lang/gcc10/gcc-10.3.0/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/devel/riscv64-none-elf-gcc/gcc-8.4.0/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/lang/gcc11-devel/gcc-11-20211009/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/devel/arm-none-eabi-gcc/gcc-8.4.0/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/devel/riscv32-unknown-elf-gcc/gcc-8.4.0/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/devel/aarch64-none-elf-gcc/gcc-8.4.0/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/lang/gcc9-aux/gcc-9.1.0/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/lang/gcc48/gcc-4.8.5/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/devel/arm-none-eabi-gcc492/gcc-4.9.2/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/lang/gcc9-devel/gcc-9-20211007/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|
/dports/devel/riscv64-gcc/gcc-8.3.0/gcc/testsuite/gcc.target/i386/ |
H A D | pr49002-2.c | 9 *to = _mm256_castpd128_pd256(from); in foo()
|