/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 232 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 498 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 675 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 886 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1050 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1170 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1398 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local 1569 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local 1690 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1378 float16x8_t _k32 = vld1q_f16(k0 + 16); 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 | 232 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 498 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 675 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 886 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1050 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1170 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1398 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local 1569 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local 1690 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1378 float16x8_t _k32 = vld1q_f16(k0 + 16); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 232 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 498 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 675 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 886 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1050 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1170 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1398 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local 1569 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local 1690 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1378 float16x8_t _k32 = vld1q_f16(k0 + 16); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 232 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 498 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 675 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 886 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1050 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1170 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1398 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local 1569 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local 1690 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1378 float16x8_t _k32 = vld1q_f16(k0 + 16); 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 | 232 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 498 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 675 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 886 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1050 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1170 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s1_pack4_neon() local 1398 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local 1569 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local 1690 float32x4_t _k32 = vld1q_f32(k0 + 8); in convdw5x5s2_pack4_neon() local
|
H A D | convolutiondepthwise_5x5_pack8_fp16s.h | 1378 float16x8_t _k32 = vld1q_f16(k0 + 16); in convdw5x5s2_pack8_fp16sa_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/riscv/ |
H A D | convolution_7x7_pack1ton.h | 274 vfloat32m1_t _k32 = vle32_v_f32m1(kptr + packn * 2, vl); in conv7x7s2_pack1ton_rvv() local 685 vfloat32m1_t _k32 = vle32_v_f32m1(kptr + packn * 2, vl); in conv7x7s2_pack1ton_rvv() local 914 vfloat32m1_t _k32 = vle32_v_f32m1(kptr + packn * 2, vl); in conv7x7s2_pack1ton_rvv() local
|
H A D | convolution_7x7_pack1ton_fp16s.h | 274 vfloat16m1_t _k32 = vle16_v_f16m1(kptr + packn * 2, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 685 vfloat16m1_t _k32 = vle16_v_f16m1(kptr + packn * 2, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 914 vfloat16m1_t _k32 = vle16_v_f16m1(kptr + packn * 2, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local
|
H A D | convolutiondepthwise_5x5_packn.h | 142 vfloat32m1_t _k32 = vle32_v_f32m1(k0 + packn * 2, vl); in convdw5x5s1_packn_rvv() local 286 vfloat32m1_t _k32 = vle32_v_f32m1(k0 + packn * 2, vl); in convdw5x5s1_packn_rvv() local 444 vfloat32m1_t _k32 = vle32_v_f32m1(k0 + packn * 2, vl); in convdw5x5s2_packn_rvv() local
|
H A D | convolutiondepthwise_5x5_packn_fp16s.h | 142 vfloat16m1_t _k32 = vle16_v_f16m1(k0 + packn * 2, vl); in convdw5x5s1_packn_fp16sa_rvv() local 286 vfloat16m1_t _k32 = vle16_v_f16m1(k0 + packn * 2, vl); in convdw5x5s1_packn_fp16sa_rvv() local 444 vfloat16m1_t _k32 = vle16_v_f16m1(k0 + packn * 2, vl); in convdw5x5s2_packn_fp16sa_rvv() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/mips/ |
H A D | convolutiondepthwise_5x5_pack4.h | 148 v4f32 _k32 = (v4f32)__msa_ld_w(k0 + 4 * 2, 0); in convdw5x5s1_pack4_msa() local 300 v4f32 _k32 = (v4f32)__msa_ld_w(k0 + 4 * 2, 0); in convdw5x5s1_pack4_msa() local 463 v4f32 _k32 = (v4f32)__msa_ld_w(k0 + 4 * 2, 0); in convdw5x5s2_pack4_msa() local
|
H A D | convolution_7x7_pack1to4.h | 237 v4f32 _k32 = (v4f32)__msa_ld_w(kptr + 4 * 2, 0); in conv7x7s2_pack1to4_msa() local 547 v4f32 _k32 = (v4f32)__msa_ld_w(kptr + 4 * 2, 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 | 116 __m256 _k32 = _mm256_loadu_ps(k0 + 16); in convdw5x5s1_pack8_avx() local 270 __m256 _k32 = _mm256_loadu_ps(k0 + 16); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 190 __m256 _k32 = _mm256_loadu_ps(kptr + 16); in conv3x3s1_pack8_avx() local 539 __m256 _k32 = _mm256_loadu_ps(kptr + 16); 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 | 116 __m256 _k32 = _mm256_loadu_ps(k0 + 16); in convdw5x5s1_pack8_avx() local 270 __m256 _k32 = _mm256_loadu_ps(k0 + 16); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 190 __m256 _k32 = _mm256_loadu_ps(kptr + 16); in conv3x3s1_pack8_avx() local 539 __m256 _k32 = _mm256_loadu_ps(kptr + 16); in conv3x3s1_pack8_avx() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolutiondepthwise_5x5_pack8.h | 116 __m256 _k32 = _mm256_loadu_ps(k0 + 16); in convdw5x5s1_pack8_avx() local 270 __m256 _k32 = _mm256_loadu_ps(k0 + 16); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 190 __m256 _k32 = _mm256_loadu_ps(kptr + 16); in conv3x3s1_pack8_avx() local 539 __m256 _k32 = _mm256_loadu_ps(kptr + 16); in conv3x3s1_pack8_avx() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolutiondepthwise_5x5_pack8.h | 116 __m256 _k32 = _mm256_loadu_ps(k0 + 16); in convdw5x5s1_pack8_avx() local 270 __m256 _k32 = _mm256_loadu_ps(k0 + 16); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_3x3_pack8.h | 190 __m256 _k32 = _mm256_loadu_ps(kptr + 16); in conv3x3s1_pack8_avx() local 539 __m256 _k32 = _mm256_loadu_ps(kptr + 16); 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 | 116 __m256 _k32 = _mm256_loadu_ps(k0 + 16); in convdw5x5s1_pack8_avx() local 270 __m256 _k32 = _mm256_loadu_ps(k0 + 16); in convdw5x5s2_pack8_avx() local
|