/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 230 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 496 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 673 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 884 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1048 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1168 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1396 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local 1567 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local 1688 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1376 float16x8_t _k30 = vld1q_f16(k0); 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 | 230 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 496 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 673 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 884 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1048 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1168 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1396 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local 1567 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local 1688 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1376 float16x8_t _k30 = vld1q_f16(k0); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 230 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 496 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 673 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 884 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1048 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1168 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1396 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local 1567 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local 1688 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1376 float16x8_t _k30 = vld1q_f16(k0); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 230 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 496 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 673 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 884 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1048 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1168 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1396 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local 1567 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local 1688 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1376 float16x8_t _k30 = vld1q_f16(k0); 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 | 230 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 496 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 673 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 884 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1048 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1168 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s1_pack4_neon() local 1396 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local 1567 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local 1688 float32x4_t _k30 = vld1q_f32(k0); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1376 float16x8_t _k30 = vld1q_f16(k0); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/riscv/ |
H A D | convolution_7x7_pack1ton.h | 272 vfloat32m1_t _k30 = vle32_v_f32m1(kptr, vl); in conv7x7s2_pack1ton_rvv() local 683 vfloat32m1_t _k30 = vle32_v_f32m1(kptr, vl); in conv7x7s2_pack1ton_rvv() local 912 vfloat32m1_t _k30 = vle32_v_f32m1(kptr, vl); in conv7x7s2_pack1ton_rvv() local
|
H A D | convolution_7x7_pack1ton_fp16s.h | 272 vfloat16m1_t _k30 = vle16_v_f16m1(kptr, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 683 vfloat16m1_t _k30 = vle16_v_f16m1(kptr, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 912 vfloat16m1_t _k30 = vle16_v_f16m1(kptr, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local
|
H A D | convolutiondepthwise_5x5_packn.h | 140 vfloat32m1_t _k30 = vle32_v_f32m1(k0, vl); in convdw5x5s1_packn_rvv() local 284 vfloat32m1_t _k30 = vle32_v_f32m1(k0, vl); in convdw5x5s1_packn_rvv() local 442 vfloat32m1_t _k30 = vle32_v_f32m1(k0, vl); in convdw5x5s2_packn_rvv() local
|
H A D | convolutiondepthwise_5x5_packn_fp16s.h | 140 vfloat16m1_t _k30 = vle16_v_f16m1(k0, vl); in convdw5x5s1_packn_fp16sa_rvv() local 284 vfloat16m1_t _k30 = vle16_v_f16m1(k0, vl); in convdw5x5s1_packn_fp16sa_rvv() local 442 vfloat16m1_t _k30 = vle16_v_f16m1(k0, vl); in convdw5x5s2_packn_fp16sa_rvv() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/mips/ |
H A D | convolutiondepthwise_5x5_pack4.h | 146 v4f32 _k30 = (v4f32)__msa_ld_w(k0, 0); in convdw5x5s1_pack4_msa() local 298 v4f32 _k30 = (v4f32)__msa_ld_w(k0, 0); in convdw5x5s1_pack4_msa() local 461 v4f32 _k30 = (v4f32)__msa_ld_w(k0, 0); in convdw5x5s2_pack4_msa() local
|
H A D | convolution_7x7_pack1to4.h | 235 v4f32 _k30 = (v4f32)__msa_ld_w(kptr, 0); in conv7x7s2_pack1to4_msa() local 545 v4f32 _k30 = (v4f32)__msa_ld_w(kptr, 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 | 114 __m256 _k30 = _mm256_loadu_ps(k0); in convdw5x5s1_pack8_avx() local 268 __m256 _k30 = _mm256_loadu_ps(k0); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 188 __m256 _k30 = _mm256_loadu_ps(kptr); in conv3x3s1_pack8_avx() local 537 __m256 _k30 = _mm256_loadu_ps(kptr); 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 | 114 __m256 _k30 = _mm256_loadu_ps(k0); in convdw5x5s1_pack8_avx() local 268 __m256 _k30 = _mm256_loadu_ps(k0); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 188 __m256 _k30 = _mm256_loadu_ps(kptr); in conv3x3s1_pack8_avx() local 537 __m256 _k30 = _mm256_loadu_ps(kptr); in conv3x3s1_pack8_avx() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolutiondepthwise_5x5_pack8.h | 114 __m256 _k30 = _mm256_loadu_ps(k0); in convdw5x5s1_pack8_avx() local 268 __m256 _k30 = _mm256_loadu_ps(k0); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 188 __m256 _k30 = _mm256_loadu_ps(kptr); in conv3x3s1_pack8_avx() local 537 __m256 _k30 = _mm256_loadu_ps(kptr); in conv3x3s1_pack8_avx() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolutiondepthwise_5x5_pack8.h | 114 __m256 _k30 = _mm256_loadu_ps(k0); in convdw5x5s1_pack8_avx() local 268 __m256 _k30 = _mm256_loadu_ps(k0); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 188 __m256 _k30 = _mm256_loadu_ps(kptr); in conv3x3s1_pack8_avx() local 537 __m256 _k30 = _mm256_loadu_ps(kptr); 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 | 114 __m256 _k30 = _mm256_loadu_ps(k0); in convdw5x5s1_pack8_avx() local 268 __m256 _k30 = _mm256_loadu_ps(k0); in convdw5x5s2_pack8_avx() local
|