/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 234 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 500 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 677 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 888 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1052 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1172 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1400 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1571 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1692 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1380 float16x8_t _k34 = vld1q_f16(k0 + 32); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 234 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 500 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 677 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 888 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1052 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1172 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1400 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1571 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1692 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1380 float16x8_t _k34 = vld1q_f16(k0 + 32); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 234 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 500 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 677 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 888 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1052 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1172 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1400 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1571 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1692 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1380 float16x8_t _k34 = vld1q_f16(k0 + 32); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 234 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 500 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 677 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 888 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1052 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1172 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1400 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1571 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1692 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1380 float16x8_t _k34 = vld1q_f16(k0 + 32); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 234 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 500 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 677 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 888 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1052 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1172 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s1_pack4_neon() local 1400 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1571 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local 1692 float32x4_t _k34 = vld1q_f32(k0 + 16); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1380 float16x8_t _k34 = vld1q_f16(k0 + 32); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/riscv/ |
H A D | convolution_7x7_pack1ton.h | 276 vfloat32m1_t _k34 = vle32_v_f32m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_rvv() local 687 vfloat32m1_t _k34 = vle32_v_f32m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_rvv() local 916 vfloat32m1_t _k34 = vle32_v_f32m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_rvv() local
|
H A D | convolution_7x7_pack1ton_fp16s.h | 276 vfloat16m1_t _k34 = vle16_v_f16m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 687 vfloat16m1_t _k34 = vle16_v_f16m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 916 vfloat16m1_t _k34 = vle16_v_f16m1(kptr + packn * 4, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local
|
H A D | convolutiondepthwise_5x5_packn.h | 144 vfloat32m1_t _k34 = vle32_v_f32m1(k0 + packn * 4, vl); in convdw5x5s1_packn_rvv() local 288 vfloat32m1_t _k34 = vle32_v_f32m1(k0 + packn * 4, vl); in convdw5x5s1_packn_rvv() local 446 vfloat32m1_t _k34 = vle32_v_f32m1(k0 + packn * 4, vl); in convdw5x5s2_packn_rvv() local
|
H A D | convolutiondepthwise_5x5_packn_fp16s.h | 144 vfloat16m1_t _k34 = vle16_v_f16m1(k0 + packn * 4, vl); in convdw5x5s1_packn_fp16sa_rvv() local 288 vfloat16m1_t _k34 = vle16_v_f16m1(k0 + packn * 4, vl); in convdw5x5s1_packn_fp16sa_rvv() local 446 vfloat16m1_t _k34 = 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 | 150 v4f32 _k34 = (v4f32)__msa_ld_w(k0 + 4 * 4, 0); in convdw5x5s1_pack4_msa() local 302 v4f32 _k34 = (v4f32)__msa_ld_w(k0 + 4 * 4, 0); in convdw5x5s1_pack4_msa() local 465 v4f32 _k34 = (v4f32)__msa_ld_w(k0 + 4 * 4, 0); in convdw5x5s2_pack4_msa() local
|
H A D | convolution_7x7_pack1to4.h | 239 v4f32 _k34 = (v4f32)__msa_ld_w(kptr + 4 * 4, 0); in conv7x7s2_pack1to4_msa() local 549 v4f32 _k34 = (v4f32)__msa_ld_w(kptr + 4 * 4, 0); in conv7x7s2_pack1to4_msa() local
|
/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
H A D | convolutiondepthwise_5x5_pack8.h | 118 __m256 _k34 = _mm256_loadu_ps(k0 + 32); in convdw5x5s1_pack8_avx() local 272 __m256 _k34 = _mm256_loadu_ps(k0 + 32); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 192 __m256 _k34 = _mm256_loadu_ps(kptr + 32); in conv3x3s1_pack8_avx() local 541 __m256 _k34 = _mm256_loadu_ps(kptr + 32); in conv3x3s1_pack8_avx() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
H A D | convolutiondepthwise_5x5_pack8.h | 118 __m256 _k34 = _mm256_loadu_ps(k0 + 32); in convdw5x5s1_pack8_avx() local 272 __m256 _k34 = _mm256_loadu_ps(k0 + 32); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 192 __m256 _k34 = _mm256_loadu_ps(kptr + 32); in conv3x3s1_pack8_avx() local 541 __m256 _k34 = _mm256_loadu_ps(kptr + 32); in conv3x3s1_pack8_avx() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolutiondepthwise_5x5_pack8.h | 118 __m256 _k34 = _mm256_loadu_ps(k0 + 32); in convdw5x5s1_pack8_avx() local 272 __m256 _k34 = _mm256_loadu_ps(k0 + 32); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 192 __m256 _k34 = _mm256_loadu_ps(kptr + 32); in conv3x3s1_pack8_avx() local 541 __m256 _k34 = _mm256_loadu_ps(kptr + 32); in conv3x3s1_pack8_avx() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolutiondepthwise_5x5_pack8.h | 118 __m256 _k34 = _mm256_loadu_ps(k0 + 32); in convdw5x5s1_pack8_avx() local 272 __m256 _k34 = _mm256_loadu_ps(k0 + 32); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 192 __m256 _k34 = _mm256_loadu_ps(kptr + 32); in conv3x3s1_pack8_avx() local 541 __m256 _k34 = _mm256_loadu_ps(kptr + 32); in conv3x3s1_pack8_avx() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
H A D | convolutiondepthwise_5x5_pack8.h | 118 __m256 _k34 = _mm256_loadu_ps(k0 + 32); in convdw5x5s1_pack8_avx() local 272 __m256 _k34 = _mm256_loadu_ps(k0 + 32); in convdw5x5s2_pack8_avx() local
|