/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolution_3x3_pack1to4.h | 151 __m128 _r25 = _mm_set1_ps(*(r2 + 4)); in conv3x3s1_pack1to4_sse() local 421 __m128 _r25 = _mm_set1_ps(*(r2 + 4)); in conv3x3s1_pack1to4_sse() local 658 __m128 _r25 = _mm_set1_ps(*(r2 + 4)); in conv3x3s2_pack1to4_sse() local 801 __m128 _r25 = _mm_set1_ps(*(r2 + 4)); in conv3x3s2_pack1to4_sse() local 954 __m128 _r25 = _mm_set1_ps(*(r2 + 4)); in conv3x3s2_pack1to4_sse() local 1133 __m128 _r25 = _mm_set1_ps(*(r2 + 4)); in conv3x3s2_pack1to4_sse() local 1227 __m128 _r25 = _mm_set1_ps(*(r2 + 4)); in conv3x3s2_pack1to4_sse() local
|
H A D | convolution_3x3_pack1to8.h | 151 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s1_pack1to8_avx() local 421 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s1_pack1to8_avx() local 658 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 931 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1074 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1227 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1405 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1499 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local
|
H A D | convolutiondepthwise_3x3_pack4.h | 115 __m128 _r25 = _mm_loadu_ps(r2 + 20); in convdw3x3s1_pack4_sse() local 257 __m128 _r25 = _mm_loadu_ps(r2 + 20); in convdw3x3s1_pack4_sse() local 454 __m128 _r25 = _mm_loadu_ps(r2 + 20); in convdw3x3s2_pack4_sse() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16.h | 115 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_fp16_pack8_avx() local 257 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_fp16_pack8_avx() local 454 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s2_fp16_pack8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8.h | 115 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_pack8_avx() local 257 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_pack8_avx() local 454 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s2_pack8_avx() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
H A D | convolution_3x3_pack1to8.h | 151 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s1_pack1to8_avx() local 421 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s1_pack1to8_avx() local 658 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 931 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1074 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1227 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1405 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1499 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16.h | 115 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_fp16_pack8_avx() local 257 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_fp16_pack8_avx() local 454 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s2_fp16_pack8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8.h | 115 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_pack8_avx() local 257 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_pack8_avx() local 454 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s2_pack8_avx() local
|
H A D | pooling_3x3_pack8.h | 79 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in pooling3x3s2_max_pack8_avx() local
|
/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
H A D | convolution_3x3_pack1to8.h | 151 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s1_pack1to8_avx() local 421 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s1_pack1to8_avx() local 658 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 931 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1074 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1227 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1405 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1499 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8.h | 115 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_pack8_avx() local 257 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_pack8_avx() local 454 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s2_pack8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16.h | 115 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_fp16_pack8_avx() local 257 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_fp16_pack8_avx() local 454 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s2_fp16_pack8_avx() local
|
H A D | pooling_3x3_pack8.h | 79 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in pooling3x3s2_max_pack8_avx() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolution_3x3_pack1to8.h | 151 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s1_pack1to8_avx() local 421 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s1_pack1to8_avx() local 658 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 931 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1074 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1227 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1405 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1499 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8.h | 115 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_pack8_avx() local 257 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_pack8_avx() local 454 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s2_pack8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16.h | 115 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_fp16_pack8_avx() local 257 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_fp16_pack8_avx() local 454 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s2_fp16_pack8_avx() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
H A D | convolution_3x3_pack1to8.h | 151 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s1_pack1to8_avx() local 421 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s1_pack1to8_avx() local 658 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 931 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1074 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1227 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1405 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local 1499 __m256 _r25 = _mm256_broadcast_ss(r2 + 4); in conv3x3s2_pack1to8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16.h | 115 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_fp16_pack8_avx() local 257 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_fp16_pack8_avx() local 454 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s2_fp16_pack8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8.h | 115 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_pack8_avx() local 257 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s1_pack8_avx() local 454 __m256 _r25 = _mm256_loadu_ps(r2 + 40); in convdw3x3s2_pack8_avx() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/mips/ |
H A D | convolution_3x3_pack1to4.h | 159 v4f32 _r25 = (v4f32)__msa_splati_w(_r2n, 1); in conv3x3s1_pack1to4_msa() local 266 v4f32 _r25 = (v4f32)__msa_splati_w(_r2n, 1); in conv3x3s1_pack1to4_msa() local 559 v4f32 _r25 = (v4f32)__msa_splati_w(_r2n, 1); in conv3x3s2_pack1to4_msa() local 679 v4f32 _r25 = (v4f32)__msa_splati_w(_r2n, 1); in conv3x3s2_pack1to4_msa() local
|
/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 168 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 458 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 843 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 1021 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 1349 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s2_pack4_neon() local 1538 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s2_pack4_neon() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 168 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 458 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 843 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 1021 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 1349 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s2_pack4_neon() local 1538 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s2_pack4_neon() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 168 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 458 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 843 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 1021 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 1349 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s2_pack4_neon() local 1538 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s2_pack4_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 168 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 458 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 843 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 1021 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 1349 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s2_pack4_neon() local 1538 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s2_pack4_neon() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 168 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 458 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 843 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 1021 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s1_pack4_neon() local 1349 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s2_pack4_neon() local 1538 float32x4_t _r25 = vld1q_f32(r2 + 20); in convdw5x5s2_pack4_neon() local
|