/dports/misc/mxnet/incubator-mxnet-1.9.0/3rdparty/mkldnn/src/cpu/x64/gemm/bf16/ |
H A D | jit_avx512_core_s16_48x8_copy_an_kern_autogen.cpp | 142 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 148 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 154 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 160 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 166 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 172 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 179 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 185 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 191 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 197 vpunpcklwd(xmm2, xmm0, xmm1); in generate() [all …]
|
H A D | jit_avx512_core_s16_24x8_copy_an_kern_autogen.cpp | 136 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 142 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 148 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 155 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 161 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 167 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 182 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 188 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 194 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 237 vpunpcklwd(xmm2, xmm0, xmm1); in generate() [all …]
|
H A D | jit_avx512_core_s16_48x8_copy_bt_kern_autogen.cpp | 130 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 133 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 146 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 149 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 170 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 173 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 188 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 231 vpunpcklwd(xmm0, xmm0, xmm1); in generate() 232 vpunpcklwd(xmm2, xmm2, xmm3); in generate() 243 vpunpcklwd(xmm0, xmm0, xmm1); in generate() [all …]
|
H A D | jit_avx512_core_s16_24x8_copy_bt_kern_autogen.cpp | 130 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 133 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 146 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 149 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 170 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 173 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 188 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 231 vpunpcklwd(xmm0, xmm0, xmm1); in generate() 232 vpunpcklwd(xmm2, xmm2, xmm3); in generate() 243 vpunpcklwd(xmm0, xmm0, xmm1); in generate() [all …]
|
/dports/math/onednn/oneDNN-2.5.1/src/cpu/x64/gemm/bf16/ |
H A D | jit_avx512_core_s16_48x8_copy_an_kern_autogen.cpp | 142 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 148 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 154 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 160 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 166 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 172 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 179 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 185 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 191 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 197 vpunpcklwd(xmm2, xmm0, xmm1); in generate() [all …]
|
H A D | jit_avx512_core_s16_24x8_copy_an_kern_autogen.cpp | 136 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 142 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 148 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 155 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 161 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 167 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 182 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 188 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 194 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 237 vpunpcklwd(xmm2, xmm0, xmm1); in generate() [all …]
|
H A D | jit_avx512_core_s16_48x8_copy_bt_kern_autogen.cpp | 130 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 133 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 146 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 149 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 170 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 173 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 188 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 231 vpunpcklwd(xmm0, xmm0, xmm1); in generate() 232 vpunpcklwd(xmm2, xmm2, xmm3); in generate() 243 vpunpcklwd(xmm0, xmm0, xmm1); in generate() [all …]
|
H A D | jit_avx512_core_s16_24x8_copy_bt_kern_autogen.cpp | 130 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 133 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 146 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 149 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 170 vpunpcklwd(xmm4, xmm0, xmm1); in generate() 173 vpunpcklwd(xmm4, xmm2, xmm3); in generate() 188 vpunpcklwd(xmm2, xmm0, xmm1); in generate() 231 vpunpcklwd(xmm0, xmm0, xmm1); in generate() 232 vpunpcklwd(xmm2, xmm2, xmm3); in generate() 243 vpunpcklwd(xmm0, xmm0, xmm1); in generate() [all …]
|
/dports/devel/llvm10/llvm-10.0.1.src/test/tools/llvm-mca/X86/Generic/ |
H A D | resources-avx512bwvl.s | 172 vpunpcklwd %xmm16, %xmm17, %xmm19 label 173 vpunpcklwd (%rax), %xmm17, %xmm19 label 174 vpunpcklwd %xmm16, %xmm17, %xmm19 {k1} label 175 vpunpcklwd (%rax), %xmm17, %xmm19 {k1} label 176 vpunpcklwd %xmm16, %xmm17, %xmm19 {z}{k1} label 177 vpunpcklwd (%rax), %xmm17, %xmm19 {z}{k1} label 179 vpunpcklwd %ymm16, %ymm17, %ymm19 label 180 vpunpcklwd (%rax), %ymm17, %ymm19 label 181 vpunpcklwd %ymm16, %ymm17, %ymm19 {k1} label 182 vpunpcklwd (%rax), %ymm17, %ymm19 {k1} label [all …]
|
H A D | resources-avx512bw.s | 95 vpunpcklwd %zmm16, %zmm17, %zmm19 label 96 vpunpcklwd (%rax), %zmm17, %zmm19 label 97 vpunpcklwd %zmm16, %zmm17, %zmm19 {k1} label 98 vpunpcklwd (%rax), %zmm17, %zmm19 {k1} label 99 vpunpcklwd %zmm16, %zmm17, %zmm19 {z}{k1} label 100 vpunpcklwd (%rax), %zmm17, %zmm19 {z}{k1} label 189 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 190 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 191 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 {%k1} 192 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 {%k1} [all …]
|
/dports/devel/llvm10/llvm-10.0.1.src/test/tools/llvm-mca/X86/SkylakeServer/ |
H A D | resources-avx512bwvl.s | 172 vpunpcklwd %xmm16, %xmm17, %xmm19 label 173 vpunpcklwd (%rax), %xmm17, %xmm19 label 174 vpunpcklwd %xmm16, %xmm17, %xmm19 {k1} label 175 vpunpcklwd (%rax), %xmm17, %xmm19 {k1} label 176 vpunpcklwd %xmm16, %xmm17, %xmm19 {z}{k1} label 177 vpunpcklwd (%rax), %xmm17, %xmm19 {z}{k1} label 179 vpunpcklwd %ymm16, %ymm17, %ymm19 label 180 vpunpcklwd (%rax), %ymm17, %ymm19 label 181 vpunpcklwd %ymm16, %ymm17, %ymm19 {k1} label 182 vpunpcklwd (%rax), %ymm17, %ymm19 {k1} label [all …]
|
H A D | resources-avx512bw.s | 95 vpunpcklwd %zmm16, %zmm17, %zmm19 label 96 vpunpcklwd (%rax), %zmm17, %zmm19 label 97 vpunpcklwd %zmm16, %zmm17, %zmm19 {k1} label 98 vpunpcklwd (%rax), %zmm17, %zmm19 {k1} label 99 vpunpcklwd %zmm16, %zmm17, %zmm19 {z}{k1} label 100 vpunpcklwd (%rax), %zmm17, %zmm19 {z}{k1} label 189 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 190 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 191 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 {%k1} 192 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 {%k1} [all …]
|
/dports/devel/tinygo/tinygo-0.14.1/llvm-project/llvm/test/tools/llvm-mca/X86/Generic/ |
H A D | resources-avx512bwvl.s | 172 vpunpcklwd %xmm16, %xmm17, %xmm19 label 173 vpunpcklwd (%rax), %xmm17, %xmm19 label 174 vpunpcklwd %xmm16, %xmm17, %xmm19 {k1} label 175 vpunpcklwd (%rax), %xmm17, %xmm19 {k1} label 176 vpunpcklwd %xmm16, %xmm17, %xmm19 {z}{k1} label 177 vpunpcklwd (%rax), %xmm17, %xmm19 {z}{k1} label 179 vpunpcklwd %ymm16, %ymm17, %ymm19 label 180 vpunpcklwd (%rax), %ymm17, %ymm19 label 181 vpunpcklwd %ymm16, %ymm17, %ymm19 {k1} label 182 vpunpcklwd (%rax), %ymm17, %ymm19 {k1} label [all …]
|
H A D | resources-avx512bw.s | 95 vpunpcklwd %zmm16, %zmm17, %zmm19 label 96 vpunpcklwd (%rax), %zmm17, %zmm19 label 97 vpunpcklwd %zmm16, %zmm17, %zmm19 {k1} label 98 vpunpcklwd (%rax), %zmm17, %zmm19 {k1} label 99 vpunpcklwd %zmm16, %zmm17, %zmm19 {z}{k1} label 100 vpunpcklwd (%rax), %zmm17, %zmm19 {z}{k1} label 189 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 190 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 191 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 {%k1} 192 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 {%k1} [all …]
|
/dports/devel/llvm90/llvm-9.0.1.src/test/tools/llvm-mca/X86/SkylakeServer/ |
H A D | resources-avx512bwvl.s | 172 vpunpcklwd %xmm16, %xmm17, %xmm19 label 173 vpunpcklwd (%rax), %xmm17, %xmm19 label 174 vpunpcklwd %xmm16, %xmm17, %xmm19 {k1} label 175 vpunpcklwd (%rax), %xmm17, %xmm19 {k1} label 176 vpunpcklwd %xmm16, %xmm17, %xmm19 {z}{k1} label 177 vpunpcklwd (%rax), %xmm17, %xmm19 {z}{k1} label 179 vpunpcklwd %ymm16, %ymm17, %ymm19 label 180 vpunpcklwd (%rax), %ymm17, %ymm19 label 181 vpunpcklwd %ymm16, %ymm17, %ymm19 {k1} label 182 vpunpcklwd (%rax), %ymm17, %ymm19 {k1} label [all …]
|
H A D | resources-avx512bw.s | 95 vpunpcklwd %zmm16, %zmm17, %zmm19 label 96 vpunpcklwd (%rax), %zmm17, %zmm19 label 97 vpunpcklwd %zmm16, %zmm17, %zmm19 {k1} label 98 vpunpcklwd (%rax), %zmm17, %zmm19 {k1} label 99 vpunpcklwd %zmm16, %zmm17, %zmm19 {z}{k1} label 100 vpunpcklwd (%rax), %zmm17, %zmm19 {z}{k1} label 189 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 190 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 191 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 {%k1} 192 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 {%k1} [all …]
|
/dports/devel/llvm90/llvm-9.0.1.src/test/tools/llvm-mca/X86/Generic/ |
H A D | resources-avx512bwvl.s | 172 vpunpcklwd %xmm16, %xmm17, %xmm19 label 173 vpunpcklwd (%rax), %xmm17, %xmm19 label 174 vpunpcklwd %xmm16, %xmm17, %xmm19 {k1} label 175 vpunpcklwd (%rax), %xmm17, %xmm19 {k1} label 176 vpunpcklwd %xmm16, %xmm17, %xmm19 {z}{k1} label 177 vpunpcklwd (%rax), %xmm17, %xmm19 {z}{k1} label 179 vpunpcklwd %ymm16, %ymm17, %ymm19 label 180 vpunpcklwd (%rax), %ymm17, %ymm19 label 181 vpunpcklwd %ymm16, %ymm17, %ymm19 {k1} label 182 vpunpcklwd (%rax), %ymm17, %ymm19 {k1} label [all …]
|
H A D | resources-avx512bw.s | 95 vpunpcklwd %zmm16, %zmm17, %zmm19 label 96 vpunpcklwd (%rax), %zmm17, %zmm19 label 97 vpunpcklwd %zmm16, %zmm17, %zmm19 {k1} label 98 vpunpcklwd (%rax), %zmm17, %zmm19 {k1} label 99 vpunpcklwd %zmm16, %zmm17, %zmm19 {z}{k1} label 100 vpunpcklwd (%rax), %zmm17, %zmm19 {z}{k1} label 189 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 190 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 191 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 {%k1} 192 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 {%k1} [all …]
|
/dports/devel/tinygo/tinygo-0.14.1/llvm-project/llvm/test/tools/llvm-mca/X86/SkylakeServer/ |
H A D | resources-avx512bwvl.s | 172 vpunpcklwd %xmm16, %xmm17, %xmm19 label 173 vpunpcklwd (%rax), %xmm17, %xmm19 label 174 vpunpcklwd %xmm16, %xmm17, %xmm19 {k1} label 175 vpunpcklwd (%rax), %xmm17, %xmm19 {k1} label 176 vpunpcklwd %xmm16, %xmm17, %xmm19 {z}{k1} label 177 vpunpcklwd (%rax), %xmm17, %xmm19 {z}{k1} label 179 vpunpcklwd %ymm16, %ymm17, %ymm19 label 180 vpunpcklwd (%rax), %ymm17, %ymm19 label 181 vpunpcklwd %ymm16, %ymm17, %ymm19 {k1} label 182 vpunpcklwd (%rax), %ymm17, %ymm19 {k1} label [all …]
|
H A D | resources-avx512bw.s | 95 vpunpcklwd %zmm16, %zmm17, %zmm19 label 96 vpunpcklwd (%rax), %zmm17, %zmm19 label 97 vpunpcklwd %zmm16, %zmm17, %zmm19 {k1} label 98 vpunpcklwd (%rax), %zmm17, %zmm19 {k1} label 99 vpunpcklwd %zmm16, %zmm17, %zmm19 {z}{k1} label 100 vpunpcklwd (%rax), %zmm17, %zmm19 {z}{k1} label 189 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 190 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 191 # CHECK-NEXT: 1 1 1.00 vpunpcklwd %zmm16, %zmm17, %zmm19 {%k1} 192 # CHECK-NEXT: 2 8 1.00 * vpunpcklwd (%rax), %zmm17, %zmm19 {%k1} [all …]
|
/dports/devel/llvm90/llvm-9.0.1.src/test/CodeGen/X86/ |
H A D | vector-interleave.ll | 62 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm8 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],… 64 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],… 70 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],… 72 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm5 = xmm7[0],xmm6[0],xmm7[1],xmm6[1],xmm7[2],xmm6[2],xmm7[3],… 79 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],… 82 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],… 85 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],… 88 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm4 = xmm9[0],xmm7[0],xmm9[1],xmm7[1],xmm9[2],xmm7[2],xmm9[3],… 94 ; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm8 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],… 96 ; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],… [all …]
|
/dports/devel/llvm80/llvm-8.0.1.src/test/CodeGen/X86/ |
H A D | vector-interleave.ll | 62 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm8 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],… 64 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],… 70 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],… 72 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm5 = xmm7[0],xmm6[0],xmm7[1],xmm6[1],xmm7[2],xmm6[2],xmm7[3],… 79 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],… 82 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],… 85 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],… 88 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm4 = xmm9[0],xmm7[0],xmm9[1],xmm7[1],xmm9[2],xmm7[2],xmm9[3],… 94 ; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm8 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],… 96 ; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],… [all …]
|
/dports/devel/llvm70/llvm-7.0.1.src/test/CodeGen/X86/ |
H A D | vector-interleave.ll | 62 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm8 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],… 64 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],… 70 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],… 72 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm5 = xmm7[0],xmm6[0],xmm7[1],xmm6[1],xmm7[2],xmm6[2],xmm7[3],… 79 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],… 82 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],… 85 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],… 88 ; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm4 = xmm9[0],xmm7[0],xmm9[1],xmm7[1],xmm9[2],xmm7[2],xmm9[3],… 94 ; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm8 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],… 96 ; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],… [all …]
|
/dports/misc/mxnet/incubator-mxnet-1.9.0/3rdparty/mkldnn/src/cpu/x64/gemm/s8x8s32/ |
H A D | jit_avx_kernel_b0_c_gemm_s8u8s32_kern_autogen.cpp | 347 vpunpcklwd(xmm0, xmm1, xmm6); in generate() 350 vpunpcklwd(xmm2, xmm3, xmm6); in generate() 353 vpunpcklwd(xmm5, xmm5, xmm5); in generate() 391 vpunpcklwd(xmm0, xmm0, xmm6); in generate() 394 vpunpcklwd(xmm1, xmm1, xmm6); in generate() 397 vpunpcklwd(xmm2, xmm2, xmm6); in generate() 400 vpunpcklwd(xmm3, xmm3, xmm6); in generate() 403 vpunpcklwd(xmm5, xmm5, xmm5); in generate() 613 vpunpcklwd(xmm0, xmm1, xmm6); in generate() 616 vpunpcklwd(xmm2, xmm3, xmm6); in generate() [all …]
|
H A D | jit_avx_kernel_b0_r_gemm_s8u8s32_kern_autogen.cpp | 345 vpunpcklwd(xmm0, xmm1, xmm6); in generate() 348 vpunpcklwd(xmm2, xmm3, xmm6); in generate() 351 vpunpcklwd(xmm5, xmm5, xmm5); in generate() 389 vpunpcklwd(xmm0, xmm0, xmm6); in generate() 392 vpunpcklwd(xmm1, xmm1, xmm6); in generate() 395 vpunpcklwd(xmm2, xmm2, xmm6); in generate() 398 vpunpcklwd(xmm3, xmm3, xmm6); in generate() 401 vpunpcklwd(xmm5, xmm5, xmm5); in generate() 610 vpunpcklwd(xmm0, xmm1, xmm6); in generate() 613 vpunpcklwd(xmm2, xmm3, xmm6); in generate() [all …]
|