/dports/science/PETSc/petsc-3.14.1/src/mat/impls/baij/seq/ |
H A D | dgefa4.c | 197 SSE_SHUFFLE(XMM7,XMM7,0xB1) in PetscKernel_A_gets_inverse_A_4_SSE() 205 SSE_SHUFFLE(XMM7,XMM7,0x4E) in PetscKernel_A_gets_inverse_A_4_SSE() 212 SSE_SUB_PS(XMM7,XMM2) in PetscKernel_A_gets_inverse_A_4_SSE() 214 SSE_SHUFFLE(XMM7,XMM7,0x4E) in PetscKernel_A_gets_inverse_A_4_SSE() 238 SSE_SUB_PS(XMM0,XMM7) in PetscKernel_A_gets_inverse_A_4_SSE() 249 SSE_SHUFFLE(XMM7,XMM7,0xB1) in PetscKernel_A_gets_inverse_A_4_SSE() 260 SSE_SHUFFLE(XMM7,XMM7,0x4E) in PetscKernel_A_gets_inverse_A_4_SSE() 268 SSE_SUB_PS(XMM7,XMM2) in PetscKernel_A_gets_inverse_A_4_SSE() 270 SSE_SHUFFLE(XMM7,XMM7,0x4E) in PetscKernel_A_gets_inverse_A_4_SSE() 281 SSE_ADD_PS(XMM0,XMM7) in PetscKernel_A_gets_inverse_A_4_SSE() [all …]
|
H A D | baijfact11.c | 594 XOR_PS(XMM7,XMM7); in MatLUFactorNumeric_SeqBAIJ_4_NaturalOrdering_SSE() 718 SSE_SHUFFLE(XMM7,XMM7,0x00) in MatLUFactorNumeric_SeqBAIJ_4_NaturalOrdering_SSE() 736 SSE_SHUFFLE(XMM7,XMM7,0x00) in MatLUFactorNumeric_SeqBAIJ_4_NaturalOrdering_SSE() 756 SSE_SHUFFLE(XMM7,XMM7,0x00) in MatLUFactorNumeric_SeqBAIJ_4_NaturalOrdering_SSE() 761 SSE_SHUFFLE(XMM7,XMM7,0x00) in MatLUFactorNumeric_SeqBAIJ_4_NaturalOrdering_SSE() 766 SSE_SHUFFLE(XMM7,XMM7,0x00) in MatLUFactorNumeric_SeqBAIJ_4_NaturalOrdering_SSE() 776 SSE_SHUFFLE(XMM7,XMM7,0x00) in MatLUFactorNumeric_SeqBAIJ_4_NaturalOrdering_SSE() 780 SSE_SHUFFLE(XMM7,XMM7,0x00) in MatLUFactorNumeric_SeqBAIJ_4_NaturalOrdering_SSE() 790 SSE_SHUFFLE(XMM7,XMM7,0x00) in MatLUFactorNumeric_SeqBAIJ_4_NaturalOrdering_SSE() 1038 XOR_PS(XMM7,XMM7); in MatLUFactorNumeric_SeqBAIJ_4_NaturalOrdering_SSE_usj_Inplace() [all …]
|
H A D | baijsolvnat4.c | 301 LOAD_PS(&t[idx],XMM7); in MatSolve_SeqBAIJ_4_NaturalOrdering_SSE_Demotion_usj() 355 LOAD_PS(&t[idt],XMM7); in MatSolve_SeqBAIJ_4_NaturalOrdering_SSE_Demotion_usj() 402 SSE_COPY_PS(XMM0,XMM7) in MatSolve_SeqBAIJ_4_NaturalOrdering_SSE_Demotion_usj() 407 SSE_COPY_PS(XMM1,XMM7) in MatSolve_SeqBAIJ_4_NaturalOrdering_SSE_Demotion_usj() 415 SSE_COPY_PS(XMM2,XMM7) in MatSolve_SeqBAIJ_4_NaturalOrdering_SSE_Demotion_usj() 421 SSE_COPY_PS(XMM3,XMM7) in MatSolve_SeqBAIJ_4_NaturalOrdering_SSE_Demotion_usj() 496 LOAD_PS(&t[idx],XMM7); in MatSolve_SeqBAIJ_4_NaturalOrdering_SSE_Demotion() 551 LOAD_PS(&t[idt],XMM7); in MatSolve_SeqBAIJ_4_NaturalOrdering_SSE_Demotion() 599 SSE_COPY_PS(XMM0,XMM7) in MatSolve_SeqBAIJ_4_NaturalOrdering_SSE_Demotion() 604 SSE_COPY_PS(XMM1,XMM7) in MatSolve_SeqBAIJ_4_NaturalOrdering_SSE_Demotion() [all …]
|
/dports/audio/aften/aften-0.0.8/libaften/x86/ |
H A D | x86_sse_mdct_common.c | 119 XMM7 = _mm_load_ps(PFV3); in mdct_butterfly_16() 123 XMM5 = _mm_mul_ps(XMM5, XMM7); in mdct_butterfly_16() 161 XMM7 = XMM3; in mdct_butterfly_32() 170 XMM7 = _mm_add_ps(XMM7, PM128(x+12)); in mdct_butterfly_32() 174 _mm_store_ps(x+28, XMM7); in mdct_butterfly_32() 181 XMM7 = XMM3; in mdct_butterfly_32() 186 XMM7 = XMM3; in mdct_butterfly_32() 196 XMM7 = _mm_shuffle_ps(XMM7, XMM7, _MM_SHUFFLE(3,2,1,1)); in mdct_butterfly_32() 204 XMM7 = _mm_mul_ps(XMM7, PM128(PFV7)); in mdct_butterfly_32() 443 XMM7 = _mm_lddqu_ps(x3); in mdct_bitreverse() [all …]
|
/dports/math/igraph/igraph-0.9.5/vendor/plfit/ |
H A D | arithmetic_sse_double.h | 110 __m128d XMM7 = _mm_load_pd((x)+i+6); \ 114 XMM3 = _mm_sub_pd(XMM3, XMM7); \ 125 __m128d XMM7 = _mm_set1_pd(c); \ 131 XMM0 = _mm_mul_pd(XMM0, XMM7); \ 132 XMM1 = _mm_mul_pd(XMM1, XMM7); \ 155 XMM3 = _mm_sub_pd(XMM3, XMM7); \ 166 __m128d XMM7 = _mm_set1_pd(c); \ 170 XMM0 = _mm_mul_pd(XMM0, XMM7); \ 171 XMM1 = _mm_mul_pd(XMM1, XMM7); \ 192 XMM7 = _mm_mul_pd(XMM7, XMM3); \ [all …]
|
H A D | arithmetic_sse_float.h | 115 __m128 XMM7 = _mm_set_ps1(c); \ 121 XMM0 = _mm_mul_ps(XMM0, XMM7); \ 122 XMM1 = _mm_mul_ps(XMM1, XMM7); \ 141 __m128 XMM7 = _mm_load_ps((y)+i+12); \ 145 XMM3 = _mm_sub_ps(XMM3, XMM7); \ 156 __m128 XMM7 = _mm_set_ps1(c); \ 160 XMM0 = _mm_mul_ps(XMM0, XMM7); \ 161 XMM1 = _mm_mul_ps(XMM1, XMM7); \ 178 __m128 XMM7 = _mm_load_ps((y)+i+12); \ 182 XMM7 = _mm_mul_ps(XMM7, XMM3); \ [all …]
|
/dports/science/InsightToolkit/ITK-5.0.1/Modules/ThirdParty/libLBFGS/src/ |
H A D | arithmetic_sse_double.h | 110 __m128d XMM7 = _mm_load_pd((x)+i+6); \ 114 XMM3 = _mm_sub_pd(XMM3, XMM7); \ 125 __m128d XMM7 = _mm_set1_pd(c); \ 131 XMM0 = _mm_mul_pd(XMM0, XMM7); \ 132 XMM1 = _mm_mul_pd(XMM1, XMM7); \ 155 XMM3 = _mm_sub_pd(XMM3, XMM7); \ 166 __m128d XMM7 = _mm_set1_pd(c); \ 170 XMM0 = _mm_mul_pd(XMM0, XMM7); \ 171 XMM1 = _mm_mul_pd(XMM1, XMM7); \ 192 XMM7 = _mm_mul_pd(XMM7, XMM3); \ [all …]
|
H A D | arithmetic_sse_float.h | 122 __m128 XMM7 = _mm_set_ps1(c); \ 128 XMM0 = _mm_mul_ps(XMM0, XMM7); \ 129 XMM1 = _mm_mul_ps(XMM1, XMM7); \ 148 __m128 XMM7 = _mm_load_ps((y)+i+12); \ 152 XMM3 = _mm_sub_ps(XMM3, XMM7); \ 163 __m128 XMM7 = _mm_set_ps1(c); \ 167 XMM0 = _mm_mul_ps(XMM0, XMM7); \ 168 XMM1 = _mm_mul_ps(XMM1, XMM7); \ 185 __m128 XMM7 = _mm_load_ps((y)+i+12); \ 189 XMM7 = _mm_mul_ps(XMM7, XMM3); \ [all …]
|
/dports/math/R-cran-igraph/igraph/src/plfit/ |
H A D | arithmetic_sse_double.h | 110 __m128d XMM7 = _mm_load_pd((x)+i+6); \ 114 XMM3 = _mm_sub_pd(XMM3, XMM7); \ 125 __m128d XMM7 = _mm_set1_pd(c); \ 131 XMM0 = _mm_mul_pd(XMM0, XMM7); \ 132 XMM1 = _mm_mul_pd(XMM1, XMM7); \ 155 XMM3 = _mm_sub_pd(XMM3, XMM7); \ 166 __m128d XMM7 = _mm_set1_pd(c); \ 170 XMM0 = _mm_mul_pd(XMM0, XMM7); \ 171 XMM1 = _mm_mul_pd(XMM1, XMM7); \ 192 XMM7 = _mm_mul_pd(XMM7, XMM3); \ [all …]
|
H A D | arithmetic_sse_float.h | 115 __m128 XMM7 = _mm_set_ps1(c); \ 121 XMM0 = _mm_mul_ps(XMM0, XMM7); \ 122 XMM1 = _mm_mul_ps(XMM1, XMM7); \ 141 __m128 XMM7 = _mm_load_ps((y)+i+12); \ 145 XMM3 = _mm_sub_ps(XMM3, XMM7); \ 156 __m128 XMM7 = _mm_set_ps1(c); \ 160 XMM0 = _mm_mul_ps(XMM0, XMM7); \ 161 XMM1 = _mm_mul_ps(XMM1, XMM7); \ 178 __m128 XMM7 = _mm_load_ps((y)+i+12); \ 182 XMM7 = _mm_mul_ps(XMM7, XMM3); \ [all …]
|
/dports/multimedia/v4l-utils/linux-5.13-rc2/arch/x86/crypto/ |
H A D | aesni-intel_avx-x86_64.S | 1278 vpxor \T1, \XMM7, \XMM7 1294 vaesenc \T1, \XMM7, \XMM7 1304 vaesenc \T1, \XMM7, \XMM7 1327 vaesenc \T1, \XMM7, \XMM7 1350 vaesenc \T1, \XMM7, \XMM7 1375 vaesenc \T1, \XMM7, \XMM7 1398 vaesenc \T1, \XMM7, \XMM7 1422 vaesenc \T1, \XMM7, \XMM7 1446 vaesenc \T1, \XMM7, \XMM7 1502 vaesenc \T5, \XMM7, \XMM7 [all …]
|
/dports/multimedia/v4l_compat/linux-5.13-rc2/arch/x86/crypto/ |
H A D | aesni-intel_avx-x86_64.S | 1278 vpxor \T1, \XMM7, \XMM7 1294 vaesenc \T1, \XMM7, \XMM7 1304 vaesenc \T1, \XMM7, \XMM7 1327 vaesenc \T1, \XMM7, \XMM7 1350 vaesenc \T1, \XMM7, \XMM7 1375 vaesenc \T1, \XMM7, \XMM7 1398 vaesenc \T1, \XMM7, \XMM7 1422 vaesenc \T1, \XMM7, \XMM7 1446 vaesenc \T1, \XMM7, \XMM7 1502 vaesenc \T5, \XMM7, \XMM7 [all …]
|
/dports/multimedia/libv4l/linux-5.13-rc2/arch/x86/crypto/ |
H A D | aesni-intel_avx-x86_64.S | 1278 vpxor \T1, \XMM7, \XMM7 1294 vaesenc \T1, \XMM7, \XMM7 1304 vaesenc \T1, \XMM7, \XMM7 1327 vaesenc \T1, \XMM7, \XMM7 1350 vaesenc \T1, \XMM7, \XMM7 1375 vaesenc \T1, \XMM7, \XMM7 1398 vaesenc \T1, \XMM7, \XMM7 1422 vaesenc \T1, \XMM7, \XMM7 1446 vaesenc \T1, \XMM7, \XMM7 1502 vaesenc \T5, \XMM7, \XMM7 [all …]
|
/dports/graphics/libosmesa-gallium/mesa-21.3.6/src/mesa/x86/ |
H A D | sse_xform4.S | 74 MOVAPS( MAT(12), XMM7 ) /* m15 | m14 | m13 | m12 */ 93 MULPS( XMM7, XMM3 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 163 MOVSS( SRC(3), XMM7 ) /* ow */ 164 SHUFPS( CONST(0x0), XMM7, XMM7 ) /* ow | ow | ow | ow */ 165 MULPS( XMM3, XMM7 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 169 ADDPS( XMM7, XMM4 ) /* ox*m3+oy*m7+oz*m11+ow*m15 | ... */
|
/dports/lang/clover/mesa-21.3.6/src/mesa/x86/ |
H A D | sse_xform4.S | 74 MOVAPS( MAT(12), XMM7 ) /* m15 | m14 | m13 | m12 */ 93 MULPS( XMM7, XMM3 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 163 MOVSS( SRC(3), XMM7 ) /* ow */ 164 SHUFPS( CONST(0x0), XMM7, XMM7 ) /* ow | ow | ow | ow */ 165 MULPS( XMM3, XMM7 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 169 ADDPS( XMM7, XMM4 ) /* ox*m3+oy*m7+oz*m11+ow*m15 | ... */
|
/dports/graphics/libosmesa/mesa-21.3.6/src/mesa/x86/ |
H A D | sse_xform4.S | 74 MOVAPS( MAT(12), XMM7 ) /* m15 | m14 | m13 | m12 */ 93 MULPS( XMM7, XMM3 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 163 MOVSS( SRC(3), XMM7 ) /* ow */ 164 SHUFPS( CONST(0x0), XMM7, XMM7 ) /* ow | ow | ow | ow */ 165 MULPS( XMM3, XMM7 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 169 ADDPS( XMM7, XMM4 ) /* ox*m3+oy*m7+oz*m11+ow*m15 | ... */
|
/dports/graphics/mesa-libs/mesa-21.3.6/src/mesa/x86/ |
H A D | sse_xform4.S | 74 MOVAPS( MAT(12), XMM7 ) /* m15 | m14 | m13 | m12 */ 93 MULPS( XMM7, XMM3 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 163 MOVSS( SRC(3), XMM7 ) /* ow */ 164 SHUFPS( CONST(0x0), XMM7, XMM7 ) /* ow | ow | ow | ow */ 165 MULPS( XMM3, XMM7 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 169 ADDPS( XMM7, XMM4 ) /* ox*m3+oy*m7+oz*m11+ow*m15 | ... */
|
/dports/graphics/mesa-dri-gallium/mesa-21.3.6/src/mesa/x86/ |
H A D | sse_xform4.S | 74 MOVAPS( MAT(12), XMM7 ) /* m15 | m14 | m13 | m12 */ 93 MULPS( XMM7, XMM3 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 163 MOVSS( SRC(3), XMM7 ) /* ow */ 164 SHUFPS( CONST(0x0), XMM7, XMM7 ) /* ow | ow | ow | ow */ 165 MULPS( XMM3, XMM7 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 169 ADDPS( XMM7, XMM4 ) /* ox*m3+oy*m7+oz*m11+ow*m15 | ... */
|
/dports/graphics/mesa-dri-classic/mesa-20.2.3/src/mesa/x86/ |
H A D | sse_xform4.S | 74 MOVAPS( MAT(12), XMM7 ) /* m15 | m14 | m13 | m12 */ 93 MULPS( XMM7, XMM3 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 163 MOVSS( SRC(3), XMM7 ) /* ow */ 164 SHUFPS( CONST(0x0), XMM7, XMM7 ) /* ow | ow | ow | ow */ 165 MULPS( XMM3, XMM7 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 169 ADDPS( XMM7, XMM4 ) /* ox*m3+oy*m7+oz*m11+ow*m15 | ... */
|
/dports/graphics/mesa-gallium-va/mesa-21.3.6/src/mesa/x86/ |
H A D | sse_xform4.S | 74 MOVAPS( MAT(12), XMM7 ) /* m15 | m14 | m13 | m12 */ 93 MULPS( XMM7, XMM3 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 163 MOVSS( SRC(3), XMM7 ) /* ow */ 164 SHUFPS( CONST(0x0), XMM7, XMM7 ) /* ow | ow | ow | ow */ 165 MULPS( XMM3, XMM7 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 169 ADDPS( XMM7, XMM4 ) /* ox*m3+oy*m7+oz*m11+ow*m15 | ... */
|
/dports/graphics/mesa-gallium-vdpau/mesa-21.3.6/src/mesa/x86/ |
H A D | sse_xform4.S | 74 MOVAPS( MAT(12), XMM7 ) /* m15 | m14 | m13 | m12 */ 93 MULPS( XMM7, XMM3 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 163 MOVSS( SRC(3), XMM7 ) /* ow */ 164 SHUFPS( CONST(0x0), XMM7, XMM7 ) /* ow | ow | ow | ow */ 165 MULPS( XMM3, XMM7 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 169 ADDPS( XMM7, XMM4 ) /* ox*m3+oy*m7+oz*m11+ow*m15 | ... */
|
/dports/graphics/mesa-gallium-xa/mesa-21.3.6/src/mesa/x86/ |
H A D | sse_xform4.S | 74 MOVAPS( MAT(12), XMM7 ) /* m15 | m14 | m13 | m12 */ 93 MULPS( XMM7, XMM3 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 163 MOVSS( SRC(3), XMM7 ) /* ow */ 164 SHUFPS( CONST(0x0), XMM7, XMM7 ) /* ow | ow | ow | ow */ 165 MULPS( XMM3, XMM7 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 169 ADDPS( XMM7, XMM4 ) /* ox*m3+oy*m7+oz*m11+ow*m15 | ... */
|
/dports/graphics/mesa-dri/mesa-21.3.6/src/mesa/x86/ |
H A D | sse_xform4.S | 74 MOVAPS( MAT(12), XMM7 ) /* m15 | m14 | m13 | m12 */ 93 MULPS( XMM7, XMM3 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 163 MOVSS( SRC(3), XMM7 ) /* ow */ 164 SHUFPS( CONST(0x0), XMM7, XMM7 ) /* ow | ow | ow | ow */ 165 MULPS( XMM3, XMM7 ) /* ow*m15 | ow*m14 | ow*m13 | ow*m12 */ 169 ADDPS( XMM7, XMM4 ) /* ox*m3+oy*m7+oz*m11+ow*m15 | ... */
|
/dports/lang/fpc-source/fpc-3.2.2/tests/test/ |
H A D | taes1.pp | 67 MOVDQU XMM4, [R8+$40]; MOVDQU XMM5, [R8+$50]; MOVDQU XMM6, [R8+$60]; MOVDQU XMM7, [R8+$70] 71 AESIMC XMM5, XMM5; AESIMC XMM6, XMM6; AESIMC XMM7, XMM7; AESIMC XMM8, XMM8 75 MOVDQU [R8+$140], XMM4; MOVDQU [R8+$150], XMM5; MOVDQU [R8+$160], XMM6; MOVDQU [R8+$170], XMM7 98 MOVDQU XMM7, [R9+16*7] 117 AESENC XMM15, XMM7 146 MOVDQU XMM7, [R9+16*7] 165 AESDEC XMM15, XMM7
|
/dports/math/openblas/OpenBLAS-0.3.18/kernel/x86_64/ |
H A D | dgemm_kernel_6x4_piledriver.S | 247 VXOR1282(XMM7,XMM7,XMM7); 275 VMA1282(XMM13,XMM15,XMM7,XMM7); 295 VMA1282(XMM13,XMM15,XMM7,XMM7); 315 VMA1282(XMM13,XMM15,XMM7,XMM7); 335 VMA1282(XMM13,XMM15,XMM7,XMM7); 366 VMA1282(XMM13,XMM15,XMM7,XMM7); 386 VMA1282(XMM13,XMM15,XMM7,XMM7); 413 VMA1282(XMM13,XMM15,XMM7,XMM7); 478 VXOR1282(XMM7,XMM7,XMM7); 502 VMA1282(XMM14,XMM15,XMM7,XMM7); [all …]
|