/dports/math/openblas/OpenBLAS-0.3.18/kernel/x86_64/ |
H A D | dgemm_ncopy_8_bulldozer.S | 173 vmovups %xmm0, %xmm8 176 vmovups %xmm2, %xmm9 188 vmovups %xmm4, %xmm10 219 vmovups %xmm0, %xmm8 221 vmovups %xmm2, %xmm9 261 vmovups %xmm0, %xmm8 263 vmovups %xmm2, %xmm9 302 vmovups %xmm0, %xmm8 304 vmovups %xmm2, %xmm9 358 vmovups %xmm0, %xmm8 [all …]
|
H A D | dgemm_tcopy_8_bulldozer.S | 151 vmovups %xmm0, -16 * SIZE(B0) 152 vmovups %xmm1, -14 * SIZE(B0) 153 vmovups %xmm2, -12 * SIZE(B0) 154 vmovups %xmm3, -10 * SIZE(B0) 163 vmovups %xmm0, -8 * SIZE(B0) 164 vmovups %xmm1, -6 * SIZE(B0) 165 vmovups %xmm2, -4 * SIZE(B0) 166 vmovups %xmm3, -2 * SIZE(B0) 176 vmovups %xmm0, 0 * SIZE(B0) 177 vmovups %xmm1, 2 * SIZE(B0) [all …]
|
H A D | gemm_tcopy_2_bulldozer.S | 104 vmovups %xmm6, 0(%rsp) 105 vmovups %xmm7, 16(%rsp) 106 vmovups %xmm8, 32(%rsp) 107 vmovups %xmm9, 48(%rsp) 108 vmovups %xmm10, 64(%rsp) 109 vmovups %xmm11, 80(%rsp) 110 vmovups %xmm12, 96(%rsp) 111 vmovups %xmm13, 112(%rsp) 112 vmovups %xmm14, 128(%rsp) 113 vmovups %xmm15, 144(%rsp) [all …]
|
H A D | dcopy_bulldozer.S | 96 vmovups -16 * SIZE(X), %xmm0 97 vmovups -14 * SIZE(X), %xmm1 98 vmovups -12 * SIZE(X), %xmm2 99 vmovups -10 * SIZE(X), %xmm3 100 vmovups -8 * SIZE(X), %xmm4 101 vmovups -6 * SIZE(X), %xmm5 102 vmovups -4 * SIZE(X), %xmm6 127 vmovups %xmm4, -8 * SIZE(Y) 128 vmovups %xmm5, -6 * SIZE(Y) 131 vmovups %xmm6, -4 * SIZE(Y) [all …]
|
/dports/misc/mxnet/incubator-mxnet-1.9.0/3rdparty/mkldnn/src/cpu/x64/gemm/f32/ |
H A D | jit_avx2_f32_copy_an_kern_autogen.cpp | 112 vmovups(yword[B], ymm0); in generate() 170 vmovups(yword[B], ymm0); in generate() 201 vmovups(yword[B], ymm0); in generate() 247 vmovups(yword[B], ymm0); in generate() 289 vmovups(yword[B], ymm0); in generate() 350 vmovups(yword[B], ymm0); in generate() 658 vmovups(yword[B], ymm0); in generate() 740 vmovups(yword[B], ymm0); in generate() 783 vmovups(yword[B], ymm0); in generate() 838 vmovups(yword[B], ymm0); in generate() [all …]
|
H A D | jit_avx512_core_f32_copy_an_kern_autogen.cpp | 106 vmovups(zmm0, zword[A1]); in generate() 107 vmovups(zword[B], zmm0); in generate() 130 vmovups(zmm0, zword[A2]); in generate() 164 vmovups(zmm0, zword[A1]); in generate() 165 vmovups(zword[B], zmm0); in generate() 195 vmovups(zmm0, zword[A1]); in generate() 196 vmovups(zword[B], zmm0); in generate() 215 vmovups(zword[B], zmm0); in generate() 242 vmovups(zword[B], zmm0); in generate() 284 vmovups(zword[B], zmm0); in generate() [all …]
|
H A D | jit_avx_f32_copy_an_kern_autogen.cpp | 103 vmovups(yword[B - 0x80], ymm0); in generate() 105 vmovups(yword[B - 0x60], ymm0); in generate() 111 vmovups(yword[B], ymm0); in generate() 153 vmovups(yword[B], ymm0); in generate() 216 vmovups(yword[B], ymm0); in generate() 524 vmovups(yword[B], ymm0); in generate() 582 vmovups(yword[B], ymm0); in generate() 659 vmovups(yword[B], ymm0); in generate() 1018 vmovups(yword[B], ymm0); in generate() 1076 vmovups(yword[B], ymm0); in generate() [all …]
|
H A D | jit_avx512_core_f32_copy_bt_kern_autogen.cpp | 103 vmovups(yword[B - 0x80], ymm0); in generate() 105 vmovups(yword[B - 0x60], ymm0); in generate() 107 vmovups(yword[B - 0x40], ymm0); in generate() 109 vmovups(yword[B - 0x20], ymm0); in generate() 111 vmovups(yword[B], ymm0); in generate() 113 vmovups(yword[B + 0x20], ymm0); in generate() 115 vmovups(yword[B + 0x40], ymm0); in generate() 117 vmovups(yword[B + 0x60], ymm0); in generate() 129 vmovups(yword[B - 0x80], ymm0); in generate() 421 vmovups(yword[B], ymm0); in generate() [all …]
|
/dports/math/onednn/oneDNN-2.5.1/src/cpu/x64/gemm/f32/ |
H A D | jit_avx2_f32_copy_an_kern_autogen.cpp | 112 vmovups(yword[B], ymm0); in generate() 170 vmovups(yword[B], ymm0); in generate() 201 vmovups(yword[B], ymm0); in generate() 247 vmovups(yword[B], ymm0); in generate() 289 vmovups(yword[B], ymm0); in generate() 350 vmovups(yword[B], ymm0); in generate() 658 vmovups(yword[B], ymm0); in generate() 740 vmovups(yword[B], ymm0); in generate() 783 vmovups(yword[B], ymm0); in generate() 838 vmovups(yword[B], ymm0); in generate() [all …]
|
H A D | jit_avx512_core_f32_copy_an_kern_autogen.cpp | 106 vmovups(zmm0, zword[A1]); in generate() 107 vmovups(zword[B], zmm0); in generate() 130 vmovups(zmm0, zword[A2]); in generate() 164 vmovups(zmm0, zword[A1]); in generate() 165 vmovups(zword[B], zmm0); in generate() 195 vmovups(zmm0, zword[A1]); in generate() 196 vmovups(zword[B], zmm0); in generate() 215 vmovups(zword[B], zmm0); in generate() 242 vmovups(zword[B], zmm0); in generate() 284 vmovups(zword[B], zmm0); in generate() [all …]
|
H A D | jit_avx_f32_copy_an_kern_autogen.cpp | 103 vmovups(yword[B - 0x80], ymm0); in generate() 105 vmovups(yword[B - 0x60], ymm0); in generate() 111 vmovups(yword[B], ymm0); in generate() 153 vmovups(yword[B], ymm0); in generate() 216 vmovups(yword[B], ymm0); in generate() 524 vmovups(yword[B], ymm0); in generate() 582 vmovups(yword[B], ymm0); in generate() 659 vmovups(yword[B], ymm0); in generate() 1018 vmovups(yword[B], ymm0); in generate() 1076 vmovups(yword[B], ymm0); in generate() [all …]
|
H A D | jit_avx512_core_f32_copy_bt_kern_autogen.cpp | 103 vmovups(yword[B - 0x80], ymm0); in generate() 105 vmovups(yword[B - 0x60], ymm0); in generate() 107 vmovups(yword[B - 0x40], ymm0); in generate() 109 vmovups(yword[B - 0x20], ymm0); in generate() 111 vmovups(yword[B], ymm0); in generate() 113 vmovups(yword[B + 0x20], ymm0); in generate() 115 vmovups(yword[B + 0x40], ymm0); in generate() 117 vmovups(yword[B + 0x60], ymm0); in generate() 129 vmovups(yword[B - 0x80], ymm0); in generate() 421 vmovups(yword[B], ymm0); in generate() [all …]
|
/dports/math/blis/blis-0.8.1/kernels/haswell/1m/ |
H A D | bli_packm_haswell_asm_s16xk.c | 420 vmovups(ymm0, mem(rbx, 0*64+ 0)) in PACKM_KER_PROT() 421 vmovups(ymm1, mem(rbx, 0*64+32)) in PACKM_KER_PROT() 425 vmovups(ymm2, mem(rbx, 1*64+ 0)) in PACKM_KER_PROT() 426 vmovups(ymm3, mem(rbx, 1*64+32)) in PACKM_KER_PROT() 430 vmovups(ymm4, mem(rbx, 2*64+ 0)) in PACKM_KER_PROT() 431 vmovups(ymm5, mem(rbx, 2*64+32)) in PACKM_KER_PROT() 435 vmovups(ymm6, mem(rbx, 3*64+ 0)) in PACKM_KER_PROT() 436 vmovups(ymm7, mem(rbx, 3*64+32)) in PACKM_KER_PROT() 440 vmovups(ymm8, mem(rbx, 4*64+ 0)) in PACKM_KER_PROT() 441 vmovups(ymm9, mem(rbx, 4*64+32)) in PACKM_KER_PROT() [all …]
|
/dports/devel/llvm-cheri/llvm-project-37c49ff00e3eadce5d8703fdc4497f28458c64a8/llvm/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/devel/llvm11/llvm-11.0.1.src/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/devel/llvm-devel/llvm-project-f05c95f10fc1d8171071735af8ad3a9e87633120/llvm/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/devel/wasi-libcxx/llvm-project-13.0.1.src/llvm/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/graphics/llvm-mesa/llvm-13.0.1.src/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/devel/llvm12/llvm-project-12.0.1.src/llvm/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/devel/llvm10/llvm-10.0.1.src/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/devel/wasi-compiler-rt13/llvm-project-13.0.1.src/llvm/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/devel/tinygo/tinygo-0.14.1/llvm-project/llvm/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/www/chromium-legacy/chromium-88.0.4324.182/third_party/llvm/llvm/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/devel/wasi-compiler-rt12/llvm-project-12.0.1.src/llvm/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|
/dports/devel/llvm13/llvm-project-13.0.1.src/llvm/test/CodeGen/X86/ |
H A D | musttail-fastcall.ll | 65 ; AVX-DAG: vmovups %ymm0, {{.*}} 66 ; AVX-DAG: vmovups %ymm1, {{.*}} 67 ; AVX-DAG: vmovups %ymm2, {{.*}} 68 ; AVX-DAG: vmovups %ymm3, {{.*}} 69 ; AVX-DAG: vmovups %ymm4, {{.*}} 70 ; AVX-DAG: vmovups %ymm5, {{.*}} 88 ; AVX-DAG: vmovups {{.*}}, %ymm0 89 ; AVX-DAG: vmovups {{.*}}, %ymm1 90 ; AVX-DAG: vmovups {{.*}}, %ymm2 91 ; AVX-DAG: vmovups {{.*}}, %ymm3 [all …]
|