/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 74 __m256 _k04 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local 267 __m256 _k04 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local
|
H A D | convolutiondepthwise_5x5_pack8.h | 61 __m256 _k04 = _mm256_loadu_ps(k0 + 32); in convdw5x5s1_pack8_avx() local 215 __m256 _k04 = _mm256_loadu_ps(k0 + 32); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 255 __m256 _k04 = loadfp16(kptr); in conv2x2s1_fp16_pack8_avx() local 448 __m256 _k04 = loadfp16(kptr); in conv2x2s1_fp16_pack8_avx() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 74 __m256 _k04 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local 267 __m256 _k04 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local
|
H A D | convolutiondepthwise_5x5_pack8.h | 61 __m256 _k04 = _mm256_loadu_ps(k0 + 32); in convdw5x5s1_pack8_avx() local 215 __m256 _k04 = _mm256_loadu_ps(k0 + 32); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 255 __m256 _k04 = loadfp16(kptr); in conv2x2s1_fp16_pack8_avx() local 448 __m256 _k04 = loadfp16(kptr); in conv2x2s1_fp16_pack8_avx() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 74 __m256 _k04 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local 267 __m256 _k04 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local
|
H A D | convolutiondepthwise_5x5_pack8.h | 61 __m256 _k04 = _mm256_loadu_ps(k0 + 32); in convdw5x5s1_pack8_avx() local 215 __m256 _k04 = _mm256_loadu_ps(k0 + 32); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 255 __m256 _k04 = loadfp16(kptr); in conv2x2s1_fp16_pack8_avx() local 448 __m256 _k04 = loadfp16(kptr); in conv2x2s1_fp16_pack8_avx() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 74 __m256 _k04 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local 267 __m256 _k04 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local
|
H A D | convolutiondepthwise_5x5_pack8.h | 61 __m256 _k04 = _mm256_loadu_ps(k0 + 32); in convdw5x5s1_pack8_avx() local 215 __m256 _k04 = _mm256_loadu_ps(k0 + 32); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 255 __m256 _k04 = loadfp16(kptr); in conv2x2s1_fp16_pack8_avx() local 448 __m256 _k04 = loadfp16(kptr); in conv2x2s1_fp16_pack8_avx() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 74 __m256 _k04 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local 267 __m256 _k04 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local
|
H A D | convolutiondepthwise_5x5_pack8.h | 61 __m256 _k04 = _mm256_loadu_ps(k0 + 32); in convdw5x5s1_pack8_avx() local 215 __m256 _k04 = _mm256_loadu_ps(k0 + 32); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 255 __m256 _k04 = loadfp16(kptr); in conv2x2s1_fp16_pack8_avx() local 448 __m256 _k04 = loadfp16(kptr); in conv2x2s1_fp16_pack8_avx() local
|
/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 81 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 403 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 608 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 777 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 977 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1115 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1280 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1493 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1635 float32x4_t _k04 = vld1q_f32(k0 + 16); 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 | 81 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 403 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 608 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 777 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 977 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1115 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1280 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1493 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1635 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 81 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 403 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 608 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 777 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 977 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1115 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1280 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1493 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1635 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 81 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 403 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 608 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 777 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 977 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1115 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1280 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1493 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1635 float32x4_t _k04 = vld1q_f32(k0 + 16); 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 | 81 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 403 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 608 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 777 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 977 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1115 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1280 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1493 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1635 float32x4_t _k04 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/riscv/ |
H A D | convolution_7x7_pack1ton.h | 75 vfloat32m1_t _k04 = vle32_v_f32m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_rvv() local 570 vfloat32m1_t _k04 = vle32_v_f32m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_rvv() local 862 vfloat32m1_t _k04 = vle32_v_f32m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_rvv() local
|
H A D | convolution_7x7_pack1ton_fp16s.h | 75 vfloat16m1_t _k04 = vle16_v_f16m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 570 vfloat16m1_t _k04 = vle16_v_f16m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 862 vfloat16m1_t _k04 = vle16_v_f16m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local
|
H A D | convolutiondepthwise_5x5_packn.h | 69 vfloat32m1_t _k04 = vle32_v_f32m1(k0 + packn * 4, vl); in convdw5x5s1_packn_rvv() local 231 vfloat32m1_t _k04 = vle32_v_f32m1(k0 + packn * 4, vl); in convdw5x5s1_packn_rvv() local 389 vfloat32m1_t _k04 = vle32_v_f32m1(k0 + packn * 4, vl); in convdw5x5s2_packn_rvv() local
|
H A D | convolutiondepthwise_5x5_packn_fp16s.h | 69 vfloat16m1_t _k04 = vle16_v_f16m1(k0 + packn * 4, vl); in convdw5x5s1_packn_fp16sa_rvv() local 231 vfloat16m1_t _k04 = vle16_v_f16m1(k0 + packn * 4, vl); in convdw5x5s1_packn_fp16sa_rvv() local 389 vfloat16m1_t _k04 = vle16_v_f16m1(k0 + packn * 4, vl); in convdw5x5s2_packn_fp16sa_rvv() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/mips/ |
H A D | convolutiondepthwise_5x5_pack4.h | 75 v4f32 _k04 = (v4f32)__msa_ld_w(k0 + 4 * 4, 0); in convdw5x5s1_pack4_msa() local 245 v4f32 _k04 = (v4f32)__msa_ld_w(k0 + 4 * 4, 0); in convdw5x5s1_pack4_msa() local 408 v4f32 _k04 = (v4f32)__msa_ld_w(k0 + 4 * 4, 0); in convdw5x5s2_pack4_msa() local
|