/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack8_int8.h | 109 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 192 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 261 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 412 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s2_pack8_int8_neon() local
|
H A D | convolution_sgemm_pack8to4_int8.h | 766 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack8to4_int8_neon() local
|
H A D | convolution_sgemm_pack8to1_int8.h | 866 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
|
H A D | convolution_sgemm_pack1to4_int8.h | 1712 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack1to4_int8_neon() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack8_int8.h | 109 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 191 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 257 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 408 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s2_pack8_int8_neon() local
|
H A D | convolution_sgemm_pack8to4_int8.h | 766 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack8to4_int8_neon() local
|
H A D | convolution_sgemm_pack8to1_int8.h | 866 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
|
H A D | convolution_sgemm_pack1to4_int8.h | 1712 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack1to4_int8_neon() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack8_int8.h | 109 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 191 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 257 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 408 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s2_pack8_int8_neon() local
|
H A D | convolution_sgemm_pack8to4_int8.h | 766 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack8to4_int8_neon() local
|
H A D | convolution_sgemm_pack8to1_int8.h | 866 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
|
H A D | convolution_sgemm_pack1to4_int8.h | 1712 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack1to4_int8_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack8_int8.h | 109 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 192 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 261 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s1_pack8_int8_neon() local 412 int32x4_t _sum02 = vaddl_s16(vget_low_s16(_s02), vget_low_s16(_s03)); in convdw3x3s2_pack8_int8_neon() local
|
H A D | convolution_sgemm_pack8to4_int8.h | 766 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack8to4_int8_neon() local
|
H A D | convolution_sgemm_pack8to1_int8.h | 866 int32x4_t _sum02 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
H A D | convolution_3x3_pack1to8.h | 146 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s1_pack1to8_avx() local 683 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 956 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 1241 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 1419 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local
|
H A D | convolution_sgemm_pack8to4_int8.h | 92 __m128i _sum02 = _mm_setzero_si128(); in im2col_sgemm_pack8to4_int8_sse() local
|
/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
H A D | convolution_3x3_pack1to8.h | 146 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s1_pack1to8_avx() local 683 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 956 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 1241 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 1419 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local
|
H A D | convolution_sgemm_pack8to4_int8.h | 92 __m128i _sum02 = _mm_setzero_si128(); in im2col_sgemm_pack8to4_int8_sse() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolution_3x3_pack1to8.h | 146 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s1_pack1to8_avx() local 683 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 956 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 1241 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 1419 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local
|
H A D | convolution_sgemm_pack8to4_int8.h | 92 __m128i _sum02 = _mm_setzero_si128(); in im2col_sgemm_pack8to4_int8_sse() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolution_3x3_pack1to8.h | 146 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s1_pack1to8_avx() local 683 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 956 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 1241 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 1419 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local
|
H A D | convolution_3x3_pack1to4.h | 146 __m128 _sum02 = _mm_loadu_ps(outptr0 + 8); in conv3x3s1_pack1to4_sse() local 683 __m128 _sum02 = _mm_loadu_ps(outptr0 + 8); in conv3x3s2_pack1to4_sse() local 968 __m128 _sum02 = _mm_loadu_ps(outptr0 + 8); in conv3x3s2_pack1to4_sse() local 1147 __m128 _sum02 = _mm_loadu_ps(outptr0 + 8); in conv3x3s2_pack1to4_sse() local
|
H A D | convolution_sgemm_pack8to4_int8.h | 92 __m128i _sum02 = _mm_setzero_si128(); in im2col_sgemm_pack8to4_int8_sse() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
H A D | convolution_3x3_pack1to8.h | 146 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s1_pack1to8_avx() local 683 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 956 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 1241 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local 1419 __m256 _sum02 = _mm256_loadu_ps(outptr0 + 16); in conv3x3s2_pack1to8_avx() local
|