/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
H A D | convolution_1x1_pack8.h | 402 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 405 _mm256_fmadd_ps4(_sum0, _w4, _w5, _w6, _w7, _val04, _val05, _val06, _val07); in conv1x1s1_sgemm_pack8_avx() 611 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 628 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 783 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 800 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 872 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 898 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx()
|
H A D | convolution_1x1_pack8_fp16.h | 398 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 415 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 646 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 663 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 818 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 835 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 907 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 933 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx()
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
H A D | convolution_1x1_pack8.h | 402 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 405 _mm256_fmadd_ps4(_sum0, _w4, _w5, _w6, _w7, _val04, _val05, _val06, _val07); in conv1x1s1_sgemm_pack8_avx() 611 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 628 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 783 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 800 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 872 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 898 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx()
|
H A D | convolution_1x1_pack8_fp16.h | 398 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 415 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 646 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 663 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 818 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 835 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 907 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 933 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx()
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolution_1x1_pack8.h | 402 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 405 _mm256_fmadd_ps4(_sum0, _w4, _w5, _w6, _w7, _val04, _val05, _val06, _val07); in conv1x1s1_sgemm_pack8_avx() 611 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 628 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 783 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 800 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 872 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 898 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx()
|
H A D | convolution_1x1_pack8_fp16.h | 398 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 415 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 646 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 663 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 818 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 835 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 907 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 933 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx()
|
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolution_1x1_pack8.h | 402 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 405 _mm256_comp_fmadd_ps4(_sum0, _w4, _w5, _w6, _w7, _val04, _val05, _val06, _val07); in conv1x1s1_sgemm_pack8_avx() 611 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 628 _sum0 = _mm256_comp_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 783 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 800 _sum0 = _mm256_comp_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 872 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 898 _sum0 = _mm256_comp_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx()
|
H A D | convolution_1x1_pack8_fp16.h | 398 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 415 _sum0 = _mm256_comp_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 646 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 663 _sum0 = _mm256_comp_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 818 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 835 _sum0 = _mm256_comp_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 907 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 933 _sum0 = _mm256_comp_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx()
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
H A D | convolution_1x1_pack8.h | 398 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 415 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 646 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 663 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 818 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 835 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx() 907 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_pack8_avx() local 933 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_pack8_avx()
|
H A D | convolution_1x1_pack8_fp16.h | 398 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 415 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 646 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 663 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 818 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 835 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx() 907 __m256 _val06 = _mm256_broadcast_ss(tmpptr + 6); in conv1x1s1_sgemm_fp16_pack8_avx() local 933 _sum0 = _mm256_fmadd_ps(_w6, _val06, _sum0); in conv1x1s1_sgemm_fp16_pack8_avx()
|