/dports/misc/ncnn/ncnn-20211208/src/layer/mips/ |
H A D | convolutiondepthwise_3x3_pack4.h | 72 v4f32 _r01 = (v4f32)__msa_ld_w(r0 + 4, 0); in convdw3x3s1_pack4_msa() local 155 v4f32 _r01 = (v4f32)__msa_ld_w(r0 + 4, 0); in convdw3x3s1_pack4_msa() local 225 v4f32 _r01 = (v4f32)__msa_ld_w(r0 + 4, 0); in convdw3x3s1_pack4_msa() local 278 v4f32 _r01 = (v4f32)__msa_ld_w(r0 + 4, 0); in convdw3x3s1_pack4_msa() local 371 v4f32 _r01 = (v4f32)__msa_ld_w(r0 + 4, 0); in convdw3x3s2_pack4_msa() local 427 v4f32 _r01 = (v4f32)__msa_ld_w(r0 + 4, 0); in convdw3x3s2_pack4_msa() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/riscv/ |
H A D | convolutiondepthwise_3x3_packn_fp16s.h | 70 vfloat16m1_t _r01 = vle16_v_f16m1(r0 + packn, vl); in convdw3x3s1_packn_fp16sa_rvv() local 148 vfloat16m1_t _r01 = vle16_v_f16m1(r0 + packn, vl); in convdw3x3s1_packn_fp16sa_rvv() local 214 vfloat16m1_t _r01 = vle16_v_f16m1(r0 + packn, vl); in convdw3x3s1_packn_fp16sa_rvv() local 263 vfloat16m1_t _r01 = vle16_v_f16m1(r0 + packn, vl); in convdw3x3s1_packn_fp16sa_rvv() local 355 vfloat16m1_t _r01 = vle16_v_f16m1(r0 + packn, vl); in convdw3x3s2_packn_fp16sa_rvv() local 407 vfloat16m1_t _r01 = vle16_v_f16m1(r0 + packn, vl); in convdw3x3s2_packn_fp16sa_rvv() local
|
H A D | convolutiondepthwise_3x3_packn.h | 70 vfloat32m1_t _r01 = vle32_v_f32m1(r0 + packn, vl); in convdw3x3s1_packn_rvv() local 148 vfloat32m1_t _r01 = vle32_v_f32m1(r0 + packn, vl); in convdw3x3s1_packn_rvv() local 214 vfloat32m1_t _r01 = vle32_v_f32m1(r0 + packn, vl); in convdw3x3s1_packn_rvv() local 263 vfloat32m1_t _r01 = vle32_v_f32m1(r0 + packn, vl); in convdw3x3s1_packn_rvv() local 355 vfloat32m1_t _r01 = vle32_v_f32m1(r0 + packn, vl); in convdw3x3s2_packn_rvv() local 407 vfloat32m1_t _r01 = vle32_v_f32m1(r0 + packn, vl); in convdw3x3s2_packn_rvv() local
|
/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
H A D | convolutiondepthwise_3x3_pack8.h | 61 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 203 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 282 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 329 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 413 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local 501 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local 551 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16.h | 61 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 203 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 282 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 329 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 413 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local 501 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local 551 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local
|
H A D | pooling_3x3_pack8.h | 41 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local 119 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local 164 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local
|
H A D | convolution_3x3_pack1to8.h | 83 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 218 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 293 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 382 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 461 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 508 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 617 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 890 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 1033 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 1110 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local [all …]
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
H A D | convolutiondepthwise_3x3_pack8_fp16.h | 61 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 203 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 282 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 329 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 413 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local 501 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local 551 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8.h | 61 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 203 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 282 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 329 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 413 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local 501 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local 551 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local
|
H A D | pooling_3x3_pack8.h | 41 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local 119 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local 164 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local
|
H A D | convolution_3x3_pack1to8.h | 83 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 218 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 293 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 382 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 461 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 508 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 617 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 890 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 1033 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 1110 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local [all …]
|
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolutiondepthwise_3x3_pack4.h | 61 __m128 _r01 = _mm_loadu_ps(r0 + 4); in convdw3x3s1_pack4_sse() local 203 __m128 _r01 = _mm_loadu_ps(r0 + 4); in convdw3x3s1_pack4_sse() local 282 __m128 _r01 = _mm_loadu_ps(r0 + 4); in convdw3x3s1_pack4_sse() local 329 __m128 _r01 = _mm_loadu_ps(r0 + 4); in convdw3x3s1_pack4_sse() local 413 __m128 _r01 = _mm_loadu_ps(r0 + 4); in convdw3x3s2_pack4_sse() local 501 __m128 _r01 = _mm_loadu_ps(r0 + 4); in convdw3x3s2_pack4_sse() local 551 __m128 _r01 = _mm_loadu_ps(r0 + 4); in convdw3x3s2_pack4_sse() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16.h | 61 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 203 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 282 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 329 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 413 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local 501 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local 551 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8.h | 61 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 203 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 282 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 329 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 413 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local 501 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local 551 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local
|
H A D | convolution_3x3_pack1to4.h | 83 __m128 _r01 = _mm_set1_ps(*(r0)); in conv3x3s1_pack1to4_sse() local 218 __m128 _r01 = _mm_set1_ps(*(r0)); in conv3x3s1_pack1to4_sse() local 293 __m128 _r01 = _mm_set1_ps(*(r0)); in conv3x3s1_pack1to4_sse() local 382 __m128 _r01 = _mm_set1_ps(*(r0)); in conv3x3s1_pack1to4_sse() local 461 __m128 _r01 = _mm_set1_ps(*(r0)); in conv3x3s1_pack1to4_sse() local 508 __m128 _r01 = _mm_set1_ps(*(r0)); in conv3x3s1_pack1to4_sse() local 617 __m128 _r01 = _mm_set1_ps(*(r0)); in conv3x3s2_pack1to4_sse() local 760 __m128 _r01 = _mm_set1_ps(*(r0)); in conv3x3s2_pack1to4_sse() local 837 __m128 _r01 = _mm_set1_ps(*(r0)); in conv3x3s2_pack1to4_sse() local 925 __m128 _r01 = _mm_set1_ps(*(r0)); in conv3x3s2_pack1to4_sse() local [all …]
|
H A D | pooling_3x3_pack8.h | 41 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local 119 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local 164 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local
|
H A D | convolution_3x3_pack1to8.h | 83 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 218 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 293 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 382 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 461 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 508 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 617 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 890 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 1033 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 1110 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local [all …]
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolutiondepthwise_3x3_pack8.h | 61 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 203 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 282 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 329 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 413 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local 501 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local 551 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16.h | 61 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 203 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 282 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 329 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 413 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local 501 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local 551 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local
|
H A D | pooling_3x3_pack8.h | 41 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local 119 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local 164 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local
|
H A D | convolution_3x3_pack1to8.h | 83 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 218 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 293 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 382 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 461 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 508 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 617 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 890 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 1033 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 1110 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local [all …]
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
H A D | convolutiondepthwise_3x3_pack8_fp16.h | 61 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 203 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 282 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 329 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_fp16_pack8_avx() local 413 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local 501 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local 551 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_fp16_pack8_avx() local
|
H A D | convolutiondepthwise_3x3_pack8.h | 61 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 203 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 282 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 329 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s1_pack8_avx() local 413 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local 501 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local 551 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in convdw3x3s2_pack8_avx() local
|
H A D | pooling_3x3_pack8.h | 41 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local 119 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local 164 __m256 _r01 = _mm256_loadu_ps(r0 + 8); in pooling3x3s2_max_pack8_avx() local
|
H A D | convolution_3x3_pack1to8.h | 83 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 218 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 293 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 382 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 461 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 508 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s1_pack1to8_avx() local 617 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 890 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 1033 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local 1110 __m256 _r01 = _mm256_broadcast_ss(r0); in conv3x3s2_pack1to8_avx() local [all …]
|