/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 169 __m256 _k16 = _mm256_loadu_ps(kptr + 16); in conv2x2s1_pack8_avx() local 334 __m256 _k16 = _mm256_loadu_ps(kptr + 16); in conv2x2s1_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 350 __m256 _k16 = loadfp16(kptr + 16); in conv2x2s1_fp16_pack8_avx() local 515 __m256 _k16 = loadfp16(kptr + 16); in conv2x2s1_fp16_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 109 __m256 _k16 = _mm256_loadu_ps(kptr + 48); in conv3x3s1_pack8_avx() local 485 __m256 _k16 = _mm256_loadu_ps(kptr + 48); in conv3x3s1_pack8_avx() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 169 __m256 _k16 = _mm256_loadu_ps(kptr + 16); in conv2x2s1_pack8_avx() local 334 __m256 _k16 = _mm256_loadu_ps(kptr + 16); in conv2x2s1_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 350 __m256 _k16 = loadfp16(kptr + 16); in conv2x2s1_fp16_pack8_avx() local 515 __m256 _k16 = loadfp16(kptr + 16); in conv2x2s1_fp16_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 109 __m256 _k16 = _mm256_loadu_ps(kptr + 48); in conv3x3s1_pack8_avx() local 485 __m256 _k16 = _mm256_loadu_ps(kptr + 48); in conv3x3s1_pack8_avx() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 169 __m256 _k16 = _mm256_loadu_ps(kptr + 16); in conv2x2s1_pack8_avx() local 334 __m256 _k16 = _mm256_loadu_ps(kptr + 16); in conv2x2s1_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 350 __m256 _k16 = loadfp16(kptr + 16); in conv2x2s1_fp16_pack8_avx() local 515 __m256 _k16 = loadfp16(kptr + 16); in conv2x2s1_fp16_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 109 __m256 _k16 = _mm256_loadu_ps(kptr + 48); in conv3x3s1_pack8_avx() local 485 __m256 _k16 = _mm256_loadu_ps(kptr + 48); in conv3x3s1_pack8_avx() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 169 __m256 _k16 = _mm256_loadu_ps(kptr + 16); in conv2x2s1_pack8_avx() local 334 __m256 _k16 = _mm256_loadu_ps(kptr + 16); in conv2x2s1_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 350 __m256 _k16 = loadfp16(kptr + 16); in conv2x2s1_fp16_pack8_avx() local 515 __m256 _k16 = loadfp16(kptr + 16); in conv2x2s1_fp16_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 109 __m256 _k16 = _mm256_loadu_ps(kptr + 48); in conv3x3s1_pack8_avx() local 485 __m256 _k16 = _mm256_loadu_ps(kptr + 48); in conv3x3s1_pack8_avx() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 169 __m256 _k16 = _mm256_loadu_ps(kptr + 16); in conv2x2s1_pack8_avx() local 334 __m256 _k16 = _mm256_loadu_ps(kptr + 16); in conv2x2s1_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 350 __m256 _k16 = loadfp16(kptr + 16); in conv2x2s1_fp16_pack8_avx() local 515 __m256 _k16 = loadfp16(kptr + 16); in conv2x2s1_fp16_pack8_avx() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/riscv/ |
H A D | convolution_7x7_pack1ton.h | 144 vfloat32m1_t _k16 = vle32_v_f32m1(kptr + packn * 6, vl); in conv7x7s2_pack1ton_rvv() local 611 vfloat32m1_t _k16 = vle32_v_f32m1(kptr + packn * 6, vl); in conv7x7s2_pack1ton_rvv() local 882 vfloat32m1_t _k16 = vle32_v_f32m1(kptr + packn * 6, vl); in conv7x7s2_pack1ton_rvv() local
|
H A D | convolution_7x7_pack1ton_fp16s.h | 144 vfloat16m1_t _k16 = vle16_v_f16m1(kptr + packn * 6, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 611 vfloat16m1_t _k16 = vle16_v_f16m1(kptr + packn * 6, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 882 vfloat16m1_t _k16 = vle16_v_f16m1(kptr + packn * 6, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/mips/ |
H A D | convolution_7x7_pack1to4.h | 127 v4f32 _k16 = (v4f32)__msa_ld_w(kptr + 4 * 6, 0); in conv7x7s2_pack1to4_msa() local 509 v4f32 _k16 = (v4f32)__msa_ld_w(kptr + 4 * 6, 0); in conv7x7s2_pack1to4_msa() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/arm/ |
H A D | convolution_3x3.h | 68 float32x4_t _k16 = vld1q_f32(k1 + 6); in conv3x3s1_neon() local 8003 float32x4_t _k16 = vld1q_f32(k1 + 6); in conv3x3s2_neon() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
H A D | convolution_3x3.h | 68 float32x4_t _k16 = vld1q_f32(k1 + 6); in conv3x3s1_neon() local 8003 float32x4_t _k16 = vld1q_f32(k1 + 6); in conv3x3s2_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
H A D | convolution_3x3.h | 68 float32x4_t _k16 = vld1q_f32(k1 + 6); in conv3x3s1_neon() local 8003 float32x4_t _k16 = vld1q_f32(k1 + 6); in conv3x3s2_neon() local
|
/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
H A D | convolution_3x3.h | 68 float32x4_t _k16 = vld1q_f32(k1 + 6); in conv3x3s1_neon() local 8003 float32x4_t _k16 = vld1q_f32(k1 + 6); in conv3x3s2_neon() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/arm/ |
H A D | convolution_3x3.h | 68 float32x4_t _k16 = vld1q_f32(k1 + 6); in conv3x3s1_neon() local 8003 float32x4_t _k16 = vld1q_f32(k1 + 6); in conv3x3s2_neon() local
|