/dports/math/blasfeo/blasfeo-0.1.2/kernel/avx2/ |
H A D | kernel_sgemm_8x8_lib8.S | 1359 vbroadcastss 0(%r11), %ymm13 1361 vbroadcastss 4(%r10), %ymm13 1363 vbroadcastss 8(%r10), %ymm13 1516 vbroadcastss %xmm13, %ymm13 1545 vbroadcastss %xmm13, %ymm13 1570 vbroadcastss %xmm13, %ymm13 1593 vbroadcastss %xmm13, %ymm13 1614 vbroadcastss %xmm13, %ymm13 1635 vbroadcastss %xmm13, %ymm13 1654 vbroadcastss %xmm13, %ymm13 [all …]
|
H A D | kernel_sgemm_8x4_lib8.S | 1342 vbroadcastss 0(%r12), %ymm12 1438 vbroadcastss 0(%rbx), %ymm12 1450 vbroadcastss 4(%rbx), %ymm12 1465 vbroadcastss 8(%rbx), %ymm12 1489 vbroadcastss 0(%rbx), %ymm12 1501 vbroadcastss 4(%rbx), %ymm12 1516 vbroadcastss 8(%rbx), %ymm12 1541 vbroadcastss 0(%rbx), %ymm12 1553 vbroadcastss 4(%rbx), %ymm12 1570 vbroadcastss 0(%rbx), %ymm12 [all …]
|
H A D | kernel_sgemm_16x4_lib8.S | 1569 vbroadcastss 0(%rbx), %ymm12 1582 vbroadcastss 4(%rbx), %ymm12 1598 vbroadcastss 8(%rbx), %ymm12 1623 vbroadcastss 0(%rbx), %ymm12 1636 vbroadcastss 4(%rbx), %ymm12 1652 vbroadcastss 8(%rbx), %ymm12 1678 vbroadcastss 0(%rbx), %ymm12 1691 vbroadcastss 4(%rbx), %ymm12 1709 vbroadcastss 0(%rbx), %ymm12 1734 vbroadcastss 0(%rbx), %ymm12 [all …]
|
H A D | kernel_sgemm_16x8_lib8.S | 314 vbroadcastss (0+0*32)(%r13), %ymm14 // B 319 vbroadcastss (4+0*32)(%r13), %ymm14 // B 323 vbroadcastss (8+0*32)(%r13), %ymm14 // B 355 vbroadcastss (0+1*32)(%r13), %ymm14 // B 360 vbroadcastss (4+1*32)(%r13), %ymm14 // B 364 vbroadcastss (8+1*32)(%r13), %ymm14 // B 396 vbroadcastss (0+2*32)(%r13), %ymm14 // B 401 vbroadcastss (4+2*32)(%r13), %ymm14 // B 405 vbroadcastss (8+2*32)(%r13), %ymm14 // B 1395 vbroadcastss 0(%r10), %ymm12 [all …]
|
H A D | kernel_sgemm_24x4_lib8.S | 1629 vbroadcastss 0(%rbx), %ymm12 1644 vbroadcastss 4(%rbx), %ymm12 1663 vbroadcastss 8(%rbx), %ymm12 1692 vbroadcastss 0(%rbx), %ymm12 1707 vbroadcastss 4(%rbx), %ymm12 1726 vbroadcastss 8(%rbx), %ymm12 1756 vbroadcastss 0(%rbx), %ymm12 1771 vbroadcastss 4(%rbx), %ymm12 1792 vbroadcastss 0(%rbx), %ymm12 1821 vbroadcastss 0(%rbx), %ymm12 [all …]
|
/dports/math/blis/blis-0.8.1/kernels/haswell/3/sup/s6x16/ |
H A D | bli_gemmsup_rv_haswell_asm_sMx2.c | 199 vbroadcastss(mem(rax ), xmm2) in GEMMSUP_KER_PROT() 200 vbroadcastss(mem(rax, r8, 1), xmm3) in GEMMSUP_KER_PROT() 204 vbroadcastss(mem(rax, r8, 2), xmm2) in GEMMSUP_KER_PROT() 205 vbroadcastss(mem(rax, r13, 1), xmm3) in GEMMSUP_KER_PROT() 209 vbroadcastss(mem(rax, r8, 4), xmm2) in GEMMSUP_KER_PROT() 210 vbroadcastss(mem(rax, r15, 1), xmm3) in GEMMSUP_KER_PROT() 225 vbroadcastss(mem(rax ), xmm2) in GEMMSUP_KER_PROT() 226 vbroadcastss(mem(rax, r8, 1), xmm3) in GEMMSUP_KER_PROT() 230 vbroadcastss(mem(rax, r8, 2), xmm2) in GEMMSUP_KER_PROT() 231 vbroadcastss(mem(rax, r13, 1), xmm3) in GEMMSUP_KER_PROT() [all …]
|
H A D | bli_gemmsup_rv_haswell_asm_sMx4.c | 201 vbroadcastss(mem(rax ), xmm2) in GEMMSUP_KER_PROT() 202 vbroadcastss(mem(rax, r8, 1), xmm3) in GEMMSUP_KER_PROT() 206 vbroadcastss(mem(rax, r8, 2), xmm2) in GEMMSUP_KER_PROT() 207 vbroadcastss(mem(rax, r13, 1), xmm3) in GEMMSUP_KER_PROT() 211 vbroadcastss(mem(rax, r8, 4), xmm2) in GEMMSUP_KER_PROT() 212 vbroadcastss(mem(rax, r15, 1), xmm3) in GEMMSUP_KER_PROT() 227 vbroadcastss(mem(rax ), xmm2) in GEMMSUP_KER_PROT() 228 vbroadcastss(mem(rax, r8, 1), xmm3) in GEMMSUP_KER_PROT() 232 vbroadcastss(mem(rax, r8, 2), xmm2) in GEMMSUP_KER_PROT() 233 vbroadcastss(mem(rax, r13, 1), xmm3) in GEMMSUP_KER_PROT() [all …]
|
H A D | bli_gemmsup_rv_haswell_asm_sMx8.c | 206 vbroadcastss(mem(rax ), ymm2) in GEMMSUP_KER_PROT() 207 vbroadcastss(mem(rax, r8, 1), ymm3) in GEMMSUP_KER_PROT() 211 vbroadcastss(mem(rax, r8, 2), ymm2) in GEMMSUP_KER_PROT() 212 vbroadcastss(mem(rax, r13, 1), ymm3) in GEMMSUP_KER_PROT() 216 vbroadcastss(mem(rax, r8, 4), ymm2) in GEMMSUP_KER_PROT() 217 vbroadcastss(mem(rax, r15, 1), ymm3) in GEMMSUP_KER_PROT() 232 vbroadcastss(mem(rax ), ymm2) in GEMMSUP_KER_PROT() 233 vbroadcastss(mem(rax, r8, 1), ymm3) in GEMMSUP_KER_PROT() 237 vbroadcastss(mem(rax, r8, 2), ymm2) in GEMMSUP_KER_PROT() 238 vbroadcastss(mem(rax, r13, 1), ymm3) in GEMMSUP_KER_PROT() [all …]
|
H A D | bli_gemmsup_rv_haswell_asm_sMx6.c | 206 vbroadcastss(mem(rax ), ymm2) in GEMMSUP_KER_PROT() 207 vbroadcastss(mem(rax, r8, 1), ymm3) in GEMMSUP_KER_PROT() 211 vbroadcastss(mem(rax, r8, 2), ymm2) in GEMMSUP_KER_PROT() 212 vbroadcastss(mem(rax, r13, 1), ymm3) in GEMMSUP_KER_PROT() 216 vbroadcastss(mem(rax, r8, 4), ymm2) in GEMMSUP_KER_PROT() 217 vbroadcastss(mem(rax, r15, 1), ymm3) in GEMMSUP_KER_PROT() 234 vbroadcastss(mem(rax ), ymm2) in GEMMSUP_KER_PROT() 235 vbroadcastss(mem(rax, r8, 1), ymm3) in GEMMSUP_KER_PROT() 239 vbroadcastss(mem(rax, r8, 2), ymm2) in GEMMSUP_KER_PROT() 240 vbroadcastss(mem(rax, r13, 1), ymm3) in GEMMSUP_KER_PROT() [all …]
|
H A D | bli_gemmsup_rv_haswell_asm_sMx12.c | 212 vbroadcastss(mem(rax ), ymm2) in GEMMSUP_KER_PROT() 213 vbroadcastss(mem(rax, r8, 1), ymm3) in GEMMSUP_KER_PROT() 219 vbroadcastss(mem(rax, r8, 2), ymm2) in GEMMSUP_KER_PROT() 220 vbroadcastss(mem(rax, r13, 1), ymm3) in GEMMSUP_KER_PROT() 226 vbroadcastss(mem(rax, r8, 4), ymm2) in GEMMSUP_KER_PROT() 227 vbroadcastss(mem(rax, r15, 1), ymm3) in GEMMSUP_KER_PROT() 245 vbroadcastss(mem(rax ), ymm2) in GEMMSUP_KER_PROT() 246 vbroadcastss(mem(rax, r8, 1), ymm3) in GEMMSUP_KER_PROT() 252 vbroadcastss(mem(rax, r8, 2), ymm2) in GEMMSUP_KER_PROT() 253 vbroadcastss(mem(rax, r13, 1), ymm3) in GEMMSUP_KER_PROT() [all …]
|
/dports/math/blis/blis-0.8.1/kernels/zen/3/sup/broken/ |
H A D | bli_gemmsup_rv_zen_asm_c3x8m.c | 284 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_3x8m() 316 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_3x8m() 348 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_3x8m() 381 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_3x8m() 897 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_3x4m() 922 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_3x4m() 948 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_3x4m() 975 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_3x4m() 1011 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_3x4m() 1386 vbroadcastss(mem(rax, 4), xmm3) in bli_cgemmsup_rv_zen_asm_3x2m() [all …]
|
H A D | bli_gemmsup_rv_zen_asm_c3x8.c | 193 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_2x8() 216 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_2x8() 240 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_2x8() 266 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_2x8() 300 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_2x8() 653 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_1x8() 669 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_1x8() 685 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_1x8() 703 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_1x8() 729 vbroadcastss(mem(rax, 4), ymm3) in bli_cgemmsup_rv_zen_asm_1x8() [all …]
|
/dports/misc/mnn/MNN-1.2.0/source/backend/cpu/x86_x64/avxfma/ |
H A D | _AVX_MNNGemmFloatUnitMainFMA_Fused.S | 47 vbroadcastss (%r15), %ymm4 48 vbroadcastss 4(%r15), %ymm7 49 vbroadcastss 8(%r15), %ymm10 50 vbroadcastss 12(%r15), %ymm13 73 vbroadcastss (%rdx), %ymm3 79 vbroadcastss 4(%rdx), %ymm3 85 vbroadcastss 8(%rdx), %ymm3 99 vbroadcastss (%rdx), %ymm3 104 vbroadcastss 4(%rdx), %ymm3 109 vbroadcastss 8(%rdx), %ymm3 [all …]
|
H A D | _AVX_MNNGemmFloatUnitMainFMA6x16.S | 63 vbroadcastss (%rdx), %ymm3 69 vbroadcastss 4(%rdx), %ymm3 75 vbroadcastss 8(%rdx), %ymm3 79 vbroadcastss 12(%rdx), %ymm3 89 vbroadcastss (%rdx), %ymm3 94 vbroadcastss 4(%rdx), %ymm3 99 vbroadcastss 8(%rdx), %ymm3 103 vbroadcastss 12(%rdx), %ymm3 123 vbroadcastss (%rdx), %ymm3 128 vbroadcastss 4(%rdx), %ymm3 [all …]
|
H A D | _AVX_MNNGemmFloatUnitMainFMA.S | 69 vbroadcastss (%rdx), %ymm3 75 vbroadcastss 4(%rdx), %ymm3 81 vbroadcastss 8(%rdx), %ymm3 85 vbroadcastss 12(%rdx), %ymm3 95 vbroadcastss (%rdx), %ymm3 100 vbroadcastss 4(%rdx), %ymm3 105 vbroadcastss 8(%rdx), %ymm3 109 vbroadcastss 12(%rdx), %ymm3 129 vbroadcastss (%rdx), %ymm3 134 vbroadcastss 4(%rdx), %ymm3 [all …]
|
/dports/math/openblas/OpenBLAS-0.3.18/kernel/x86_64/ |
H A D | cgemm_kernel_4x2_bulldozer.S | 756 vbroadcastss ALPHA_R, %xmm0 757 vbroadcastss ALPHA_I, %xmm1 978 vbroadcastss ALPHA_R, %xmm0 979 vbroadcastss ALPHA_I, %xmm1 1173 vbroadcastss ALPHA_R, %xmm0 1174 vbroadcastss ALPHA_I, %xmm1 1421 vbroadcastss ALPHA_R, %xmm0 1422 vbroadcastss ALPHA_I, %xmm1 1618 vbroadcastss ALPHA_R, %xmm0 1619 vbroadcastss ALPHA_I, %xmm1 [all …]
|
H A D | cgemm_kernel_4x2_piledriver.S | 780 vbroadcastss ALPHA_R, %xmm0 781 vbroadcastss ALPHA_I, %xmm1 1002 vbroadcastss ALPHA_R, %xmm0 1003 vbroadcastss ALPHA_I, %xmm1 1197 vbroadcastss ALPHA_R, %xmm0 1198 vbroadcastss ALPHA_I, %xmm1 1445 vbroadcastss ALPHA_R, %xmm0 1446 vbroadcastss ALPHA_I, %xmm1 1642 vbroadcastss ALPHA_R, %xmm0 1643 vbroadcastss ALPHA_I, %xmm1 [all …]
|
/dports/math/blasfeo/blasfeo-0.1.2/kernel/avx_x86/ |
H A D | kernel_sgemm_4x4_lib4.S | 350 vbroadcastss 0(%ecx), %xmm5 // B 365 vbroadcastss 4(%ecx), %xmm5 // B 380 vbroadcastss 8(%ecx), %xmm5 // B 423 vbroadcastss 0(%ecx), %xmm5 // B 438 vbroadcastss 4(%ecx), %xmm5 // B 453 vbroadcastss 8(%ecx), %xmm5 // B 499 vbroadcastss 0(%ecx), %xmm5 // B 646 vbroadcastss 0(%eax), %xmm7 654 vbroadcastss 0(%ebx), %xmm6 722 vbroadcastss 0(%eax), %xmm7 [all …]
|
/dports/math/blis/blis-0.8.1/kernels/zen/3/sup/other/ |
H A D | bli_gemmsup_rv_zen_asm_s6x16m.c | 314 vbroadcastss(mem(rax ), ymm2) in bli_sgemmsup_rv_zen_asm_6x16m() 315 vbroadcastss(mem(rax, r8, 1), ymm3) in bli_sgemmsup_rv_zen_asm_6x16m() 321 vbroadcastss(mem(rax, r8, 2), ymm2) in bli_sgemmsup_rv_zen_asm_6x16m() 322 vbroadcastss(mem(rax, r13, 1), ymm3) in bli_sgemmsup_rv_zen_asm_6x16m() 328 vbroadcastss(mem(rax, r8, 4), ymm2) in bli_sgemmsup_rv_zen_asm_6x16m() 329 vbroadcastss(mem(rax, r15, 1), ymm3) in bli_sgemmsup_rv_zen_asm_6x16m() 343 vbroadcastss(mem(rax ), ymm2) in bli_sgemmsup_rv_zen_asm_6x16m() 344 vbroadcastss(mem(rax, r8, 1), ymm3) in bli_sgemmsup_rv_zen_asm_6x16m() 350 vbroadcastss(mem(rax, r8, 2), ymm2) in bli_sgemmsup_rv_zen_asm_6x16m() 351 vbroadcastss(mem(rax, r13, 1), ymm3) in bli_sgemmsup_rv_zen_asm_6x16m() [all …]
|
H A D | bli_gemmsup_rv_zen_asm_s6x16.c | 193 vbroadcastss(mem(rax ), ymm2) in GEMMSUP_KER_PROT() 194 vbroadcastss(mem(rax, r8, 1), ymm3) in GEMMSUP_KER_PROT() 200 vbroadcastss(mem(rax, r8, 2), ymm2) in GEMMSUP_KER_PROT() 201 vbroadcastss(mem(rax, r13, 1), ymm3) in GEMMSUP_KER_PROT() 207 vbroadcastss(mem(rax, r8, 4), ymm2) in GEMMSUP_KER_PROT() 216 vbroadcastss(mem(rax ), ymm2) in GEMMSUP_KER_PROT() 217 vbroadcastss(mem(rax, r8, 1), ymm3) in GEMMSUP_KER_PROT() 223 vbroadcastss(mem(rax, r8, 2), ymm2) in GEMMSUP_KER_PROT() 224 vbroadcastss(mem(rax, r13, 1), ymm3) in GEMMSUP_KER_PROT() 230 vbroadcastss(mem(rax, r8, 4), ymm2) in GEMMSUP_KER_PROT() [all …]
|
/dports/math/blis/blis-0.8.1/kernels/haswell/3/sup/ |
H A D | bli_gemmsup_rv_haswell_asm_s6x16m.c | 397 vbroadcastss(mem(rax ), ymm2) in GEMMSUP_KER_PROT() 398 vbroadcastss(mem(rax, r8, 1), ymm3) in GEMMSUP_KER_PROT() 404 vbroadcastss(mem(rax, r8, 2), ymm2) in GEMMSUP_KER_PROT() 405 vbroadcastss(mem(rax, r13, 1), ymm3) in GEMMSUP_KER_PROT() 411 vbroadcastss(mem(rax, r8, 4), ymm2) in GEMMSUP_KER_PROT() 412 vbroadcastss(mem(rax, r15, 1), ymm3) in GEMMSUP_KER_PROT() 432 vbroadcastss(mem(rax ), ymm2) in GEMMSUP_KER_PROT() 433 vbroadcastss(mem(rax, r8, 1), ymm3) in GEMMSUP_KER_PROT() 439 vbroadcastss(mem(rax, r8, 2), ymm2) in GEMMSUP_KER_PROT() 440 vbroadcastss(mem(rax, r13, 1), ymm3) in GEMMSUP_KER_PROT() [all …]
|
/dports/math/blasfeo/blasfeo-0.1.2/kernel/avx/ |
H A D | kernel_sgemm_8x4_lib8.S | 1389 vbroadcastss 0(%r12), %ymm12 1496 vbroadcastss 0(%rbx), %ymm12 1508 vbroadcastss 4(%rbx), %ymm12 1523 vbroadcastss 8(%rbx), %ymm12 1547 vbroadcastss 0(%rbx), %ymm12 1559 vbroadcastss 4(%rbx), %ymm12 1574 vbroadcastss 8(%rbx), %ymm12 1599 vbroadcastss 0(%rbx), %ymm12 1611 vbroadcastss 4(%rbx), %ymm12 1628 vbroadcastss 0(%rbx), %ymm12 [all …]
|
H A D | kernel_sgemm_8x8_lib8.S | 1674 vbroadcastss 0(%r11), %ymm13 1676 vbroadcastss 4(%r10), %ymm13 1679 vbroadcastss 8(%r10), %ymm13 1698 vbroadcastss 4(%r11), %ymm13 1719 vbroadcastss 8(%r11), %ymm13 2169 vbroadcastss 0(%r10), %ymm11 2182 vbroadcastss 0(%r11), %ymm14 2291 vbroadcastss 0(%r10), %ymm11 2304 vbroadcastss 0(%r11), %ymm15 2475 vbroadcastss 0(%r10), %ymm11 [all …]
|
/dports/math/blis/blis-0.8.1/kernels/haswell/3/ |
H A D | bli_gemmtrsm_l_haswell_asm_d6x8.c | 124 vbroadcastss(mem(rax, 0*4), ymm2) in bli_sgemmtrsm_l_haswell_asm_6x16() 125 vbroadcastss(mem(rax, 1*4), ymm3) in bli_sgemmtrsm_l_haswell_asm_6x16() 131 vbroadcastss(mem(rax, 2*4), ymm2) in bli_sgemmtrsm_l_haswell_asm_6x16() 132 vbroadcastss(mem(rax, 3*4), ymm3) in bli_sgemmtrsm_l_haswell_asm_6x16() 138 vbroadcastss(mem(rax, 4*4), ymm2) in bli_sgemmtrsm_l_haswell_asm_6x16() 139 vbroadcastss(mem(rax, 5*4), ymm3) in bli_sgemmtrsm_l_haswell_asm_6x16() 149 vbroadcastss(mem(rax, 6*4), ymm2) in bli_sgemmtrsm_l_haswell_asm_6x16() 150 vbroadcastss(mem(rax, 7*4), ymm3) in bli_sgemmtrsm_l_haswell_asm_6x16() 156 vbroadcastss(mem(rax, 8*4), ymm2) in bli_sgemmtrsm_l_haswell_asm_6x16() 157 vbroadcastss(mem(rax, 9*4), ymm3) in bli_sgemmtrsm_l_haswell_asm_6x16() [all …]
|
H A D | bli_gemm_haswell_asm_d8x6.c | 143 vbroadcastss(mem(rbx, 0*4), ymm2) in bli_sgemm_haswell_asm_16x6() 144 vbroadcastss(mem(rbx, 1*4), ymm3) in bli_sgemm_haswell_asm_16x6() 150 vbroadcastss(mem(rbx, 2*4), ymm2) in bli_sgemm_haswell_asm_16x6() 151 vbroadcastss(mem(rbx, 3*4), ymm3) in bli_sgemm_haswell_asm_16x6() 157 vbroadcastss(mem(rbx, 4*4), ymm2) in bli_sgemm_haswell_asm_16x6() 158 vbroadcastss(mem(rbx, 5*4), ymm3) in bli_sgemm_haswell_asm_16x6() 168 vbroadcastss(mem(rbx, 6*4), ymm2) in bli_sgemm_haswell_asm_16x6() 169 vbroadcastss(mem(rbx, 7*4), ymm3) in bli_sgemm_haswell_asm_16x6() 175 vbroadcastss(mem(rbx, 8*4), ymm2) in bli_sgemm_haswell_asm_16x6() 176 vbroadcastss(mem(rbx, 9*4), ymm3) in bli_sgemm_haswell_asm_16x6() [all …]
|