/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 168 __m256 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() local 174 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_pack8_avx() 194 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_pack8_avx() 210 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() 214 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_pack8_avx() 233 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_pack8_avx() 333 __m256 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() local 339 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_pack8_avx() 366 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() 370 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_pack8_avx()
|
H A D | convolution_2x2_pack8_fp16.h | 349 __m256 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() local 355 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_fp16_pack8_avx() 375 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_fp16_pack8_avx() 391 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() 395 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_fp16_pack8_avx() 414 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_fp16_pack8_avx() 514 __m256 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() local 520 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_fp16_pack8_avx() 547 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() 551 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_fp16_pack8_avx()
|
H A D | convolution_3x3_pack8.h | 108 __m256 _k15 = _mm256_loadu_ps(kptr + 40); in conv3x3s1_pack8_avx() local 119 _sum01 = _mm256_fmadd_ps(_r015, _k15, _sum01); in conv3x3s1_pack8_avx() 137 _sum11 = _mm256_fmadd_ps(_r025, _k15, _sum11); in conv3x3s1_pack8_avx() 484 __m256 _k15 = _mm256_loadu_ps(kptr + 40); in conv3x3s1_pack8_avx() local 495 _sum1 = _mm256_fmadd_ps(_r015, _k15, _sum1); in conv3x3s1_pack8_avx()
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 168 __m256 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() local 174 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_pack8_avx() 194 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_pack8_avx() 210 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() 214 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_pack8_avx() 233 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_pack8_avx() 333 __m256 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() local 339 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_pack8_avx() 366 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() 370 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_pack8_avx()
|
H A D | convolution_2x2_pack8_fp16.h | 349 __m256 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() local 355 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_fp16_pack8_avx() 375 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_fp16_pack8_avx() 391 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() 395 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_fp16_pack8_avx() 414 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_fp16_pack8_avx() 514 __m256 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() local 520 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_fp16_pack8_avx() 547 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() 551 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_fp16_pack8_avx()
|
H A D | convolution_3x3_pack8.h | 108 __m256 _k15 = _mm256_loadu_ps(kptr + 40); in conv3x3s1_pack8_avx() local 119 _sum01 = _mm256_fmadd_ps(_r015, _k15, _sum01); in conv3x3s1_pack8_avx() 137 _sum11 = _mm256_fmadd_ps(_r025, _k15, _sum11); in conv3x3s1_pack8_avx() 484 __m256 _k15 = _mm256_loadu_ps(kptr + 40); in conv3x3s1_pack8_avx() local 495 _sum1 = _mm256_fmadd_ps(_r015, _k15, _sum1); in conv3x3s1_pack8_avx()
|
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 168 __m256 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() local 174 _sum0 = _mm256_comp_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_pack8_avx() 194 _sum1 = _mm256_comp_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_pack8_avx() 210 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() 214 _sum0 = _mm256_comp_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_pack8_avx() 233 _sum1 = _mm256_comp_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_pack8_avx() 333 __m256 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() local 339 _sum = _mm256_comp_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_pack8_avx() 366 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() 370 _sum = _mm256_comp_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_pack8_avx()
|
H A D | convolution_2x2_pack8_fp16.h | 349 __m256 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() local 355 _sum0 = _mm256_comp_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_fp16_pack8_avx() 375 _sum1 = _mm256_comp_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_fp16_pack8_avx() 391 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() 395 _sum0 = _mm256_comp_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_fp16_pack8_avx() 414 _sum1 = _mm256_comp_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_fp16_pack8_avx() 514 __m256 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() local 520 _sum = _mm256_comp_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_fp16_pack8_avx() 547 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() 551 _sum = _mm256_comp_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_fp16_pack8_avx()
|
H A D | convolution_3x3_pack8.h | 108 __m256 _k15 = _mm256_loadu_ps(kptr + 40); in conv3x3s1_pack8_avx() local 119 _sum01 = _mm256_comp_fmadd_ps(_r015, _k15, _sum01); in conv3x3s1_pack8_avx() 137 _sum11 = _mm256_comp_fmadd_ps(_r025, _k15, _sum11); in conv3x3s1_pack8_avx() 484 __m256 _k15 = _mm256_loadu_ps(kptr + 40); in conv3x3s1_pack8_avx() local 495 _sum1 = _mm256_comp_fmadd_ps(_r015, _k15, _sum1); in conv3x3s1_pack8_avx()
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 168 __m256 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() local 174 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_pack8_avx() 194 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_pack8_avx() 210 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() 214 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_pack8_avx() 233 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_pack8_avx() 333 __m256 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() local 339 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_pack8_avx() 366 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() 370 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_pack8_avx()
|
H A D | convolution_2x2_pack8_fp16.h | 349 __m256 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() local 355 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_fp16_pack8_avx() 375 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_fp16_pack8_avx() 391 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() 395 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_fp16_pack8_avx() 414 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_fp16_pack8_avx() 514 __m256 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() local 520 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_fp16_pack8_avx() 547 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() 551 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_fp16_pack8_avx()
|
H A D | convolution_3x3_pack8.h | 108 __m256 _k15 = _mm256_loadu_ps(kptr + 40); in conv3x3s1_pack8_avx() local 119 _sum01 = _mm256_fmadd_ps(_r015, _k15, _sum01); in conv3x3s1_pack8_avx() 137 _sum11 = _mm256_fmadd_ps(_r025, _k15, _sum11); in conv3x3s1_pack8_avx() 484 __m256 _k15 = _mm256_loadu_ps(kptr + 40); in conv3x3s1_pack8_avx() local 495 _sum1 = _mm256_fmadd_ps(_r015, _k15, _sum1); in conv3x3s1_pack8_avx()
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 168 __m256 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() local 174 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_pack8_avx() 194 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_pack8_avx() 210 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() 214 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_pack8_avx() 233 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_pack8_avx() 333 __m256 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() local 339 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_pack8_avx() 366 _k15 = _mm256_loadu_ps(kptr + 8); in conv2x2s1_pack8_avx() 370 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_pack8_avx()
|
H A D | convolution_2x2_pack8_fp16.h | 349 __m256 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() local 355 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_fp16_pack8_avx() 375 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_fp16_pack8_avx() 391 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() 395 _sum0 = _mm256_fmadd_ps(_k15, _r15, _sum0); in conv2x2s1_fp16_pack8_avx() 414 _sum1 = _mm256_fmadd_ps(_k15, _r15, _sum1); in conv2x2s1_fp16_pack8_avx() 514 __m256 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() local 520 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_fp16_pack8_avx() 547 _k15 = loadfp16(kptr + 8); in conv2x2s1_fp16_pack8_avx() 551 _sum = _mm256_fmadd_ps(_k15, _r15, _sum); in conv2x2s1_fp16_pack8_avx()
|
/dports/misc/ncnn/ncnn-20211208/src/layer/riscv/ |
H A D | convolution_7x7_pack1ton.h | 188 _sum0 = vfmacc_vf_f32m1(_sum0, r1[5], _k15, vl); in conv7x7s2_pack1ton_rvv() 189 _sum1 = vfmacc_vf_f32m1(_sum1, r1[7], _k15, vl); in conv7x7s2_pack1ton_rvv() 190 _sum2 = vfmacc_vf_f32m1(_sum2, r1[9], _k15, vl); in conv7x7s2_pack1ton_rvv() 191 _sum3 = vfmacc_vf_f32m1(_sum3, r1[11], _k15, vl); in conv7x7s2_pack1ton_rvv() 192 _sum4 = vfmacc_vf_f32m1(_sum4, r1[13], _k15, vl); in conv7x7s2_pack1ton_rvv() 193 _sum5 = vfmacc_vf_f32m1(_sum5, r1[15], _k15, vl); in conv7x7s2_pack1ton_rvv() 194 _sum6 = vfmacc_vf_f32m1(_sum6, r1[17], _k15, vl); in conv7x7s2_pack1ton_rvv() 195 _sum7 = vfmacc_vf_f32m1(_sum7, r1[19], _k15, vl); in conv7x7s2_pack1ton_rvv() 635 _sum0 = vfmacc_vf_f32m1(_sum0, r1[5], _k15, vl); in conv7x7s2_pack1ton_rvv() 636 _sum1 = vfmacc_vf_f32m1(_sum1, r1[7], _k15, vl); in conv7x7s2_pack1ton_rvv() [all …]
|
H A D | convolution_7x7_pack1ton_fp16s.h | 188 _sum0 = vfmacc_vf_f16m1(_sum0, r1[5], _k15, vl); in conv7x7s2_pack1ton_fp16sa_rvv() 189 _sum1 = vfmacc_vf_f16m1(_sum1, r1[7], _k15, vl); in conv7x7s2_pack1ton_fp16sa_rvv() 190 _sum2 = vfmacc_vf_f16m1(_sum2, r1[9], _k15, vl); in conv7x7s2_pack1ton_fp16sa_rvv() 191 _sum3 = vfmacc_vf_f16m1(_sum3, r1[11], _k15, vl); in conv7x7s2_pack1ton_fp16sa_rvv() 192 _sum4 = vfmacc_vf_f16m1(_sum4, r1[13], _k15, vl); in conv7x7s2_pack1ton_fp16sa_rvv() 193 _sum5 = vfmacc_vf_f16m1(_sum5, r1[15], _k15, vl); in conv7x7s2_pack1ton_fp16sa_rvv() 194 _sum6 = vfmacc_vf_f16m1(_sum6, r1[17], _k15, vl); in conv7x7s2_pack1ton_fp16sa_rvv() 195 _sum7 = vfmacc_vf_f16m1(_sum7, r1[19], _k15, vl); in conv7x7s2_pack1ton_fp16sa_rvv() 635 _sum0 = vfmacc_vf_f16m1(_sum0, r1[5], _k15, vl); in conv7x7s2_pack1ton_fp16sa_rvv() 636 _sum1 = vfmacc_vf_f16m1(_sum1, r1[7], _k15, vl); in conv7x7s2_pack1ton_fp16sa_rvv() [all …]
|
/dports/misc/ncnn/ncnn-20211208/src/layer/mips/ |
H A D | convolution_7x7_pack1to4.h | 126 v4f32 _k15 = (v4f32)__msa_ld_w(kptr + 4 * 5, 0); in conv7x7s2_pack1to4_msa() local 169 _sum0 = __msa_fmadd_w(_sum0, _r15, _k15); in conv7x7s2_pack1to4_msa() 170 _sum1 = __msa_fmadd_w(_sum1, _r17, _k15); in conv7x7s2_pack1to4_msa() 171 _sum2 = __msa_fmadd_w(_sum2, _r19, _k15); in conv7x7s2_pack1to4_msa() 172 _sum3 = __msa_fmadd_w(_sum3, _r1b, _k15); in conv7x7s2_pack1to4_msa() 508 v4f32 _k15 = (v4f32)__msa_ld_w(kptr + 4 * 5, 0); in conv7x7s2_pack1to4_msa() local 521 _sum0 = __msa_fmadd_w(_sum0, (v4f32)__msa_splati_w(_r1n, 1), _k15); in conv7x7s2_pack1to4_msa()
|
/dports/devel/arm-none-eabi-gcc492/gcc-4.9.2/gcc/fortran/ |
H A D | intrinsic.texi | 10956 print *, huge(i15) >= 10_k15**15-1
|
/dports/lang/gcc48/gcc-4.8.5/gcc/fortran/ |
H A D | intrinsic.texi | 10956 print *, huge(i15) >= 10_k15**15-1
|
/dports/devel/mingw32-gcc/gcc-4.8.1/gcc/fortran/ |
H A D | intrinsic.texi | 10954 print *, huge(i15) >= 10_k15**15-1
|
/dports/lang/gnat_util/gcc-6-20180516/gcc/fortran/ |
H A D | intrinsic.texi | 11800 print *, huge(i15) >= 10_k15**15-1
|
/dports/lang/gcc6-aux/gcc-6-20180516/gcc/fortran/ |
H A D | intrinsic.texi | 11800 print *, huge(i15) >= 10_k15**15-1
|
/dports/devel/aarch64-none-elf-gcc/gcc-8.4.0/gcc/fortran/ |
H A D | intrinsic.texi | 12409 print *, huge(i15) >= 10_k15**15-1
|
/dports/lang/gcc12-devel/gcc-12-20211205/gcc/fortran/ |
H A D | intrinsic.texi | 12807 print *, huge(i15) >= 10_k15**15-1
|
/dports/devel/avr-gcc/gcc-10.2.0/gcc/fortran/ |
H A D | intrinsic.texi | 12852 print *, huge(i15) >= 10_k15**15-1
|