| /dports/misc/ncnn/ncnn-20211208/src/layer/riscv/ |
| H A D | convolution_3x3_pack1ton.h | 64 vfloat32m1_t _sum0 = vle32_v_f32m1(outptr0, vl); in conv3x3s1_pack1ton_rvv() local
165 vfloat32m1_t _sum0 = vle32_v_f32m1(outptr0, vl); in conv3x3s1_pack1ton_rvv() local
222 vfloat32m1_t _sum0 = vle32_v_f32m1(outptr0, vl); in conv3x3s1_pack1ton_rvv() local
257 vfloat32m1_t _sum0 = vle32_v_f32m1(outptr0, vl); in conv3x3s1_pack1ton_rvv() local
342 vfloat32m1_t _sum0 = vle32_v_f32m1(outptr0, vl); in conv3x3s2_pack1ton_rvv() local
443 vfloat32m1_t _sum0 = vle32_v_f32m1(outptr0, vl); in conv3x3s2_pack1ton_rvv() local
500 vfloat32m1_t _sum0 = vle32_v_f32m1(outptr0, vl); in conv3x3s2_pack1ton_rvv() local
535 vfloat32m1_t _sum0 = vle32_v_f32m1(outptr0, vl); in conv3x3s2_pack1ton_rvv() local
|
| H A D | convolution_3x3_pack1ton_fp16s.h | 64 vfloat16m1_t _sum0 = vle16_v_f16m1(outptr0, vl); in conv3x3s1_pack1ton_fp16sa_rvv() local
165 vfloat16m1_t _sum0 = vle16_v_f16m1(outptr0, vl); in conv3x3s1_pack1ton_fp16sa_rvv() local
222 vfloat16m1_t _sum0 = vle16_v_f16m1(outptr0, vl); in conv3x3s1_pack1ton_fp16sa_rvv() local
257 vfloat16m1_t _sum0 = vle16_v_f16m1(outptr0, vl); in conv3x3s1_pack1ton_fp16sa_rvv() local
342 vfloat16m1_t _sum0 = vle16_v_f16m1(outptr0, vl); in conv3x3s2_pack1ton_fp16sa_rvv() local
443 vfloat16m1_t _sum0 = vle16_v_f16m1(outptr0, vl); in conv3x3s2_pack1ton_fp16sa_rvv() local
500 vfloat16m1_t _sum0 = vle16_v_f16m1(outptr0, vl); in conv3x3s2_pack1ton_fp16sa_rvv() local
535 vfloat16m1_t _sum0 = vle16_v_f16m1(outptr0, vl); in conv3x3s2_pack1ton_fp16sa_rvv() local
|
| H A D | convolution_sgemm_packnto1.h | 211 vfloat32m1_t _sum0 = vle32_v_f32m1(biasptr, vl); in im2col_sgemm_packnto1_rvv() local
264 vfloat32m1_t _sum0 = vle32_v_f32m1(biasptr, vl); in im2col_sgemm_packnto1_rvv() local
301 vfloat32m1_t _sum0 = vle32_v_f32m1(biasptr, vl); in im2col_sgemm_packnto1_rvv() local
371 vfloat32m1_t _sum0 = vfmv_v_f_f32m1(0.f, vl); in im2col_sgemm_packnto1_rvv() local
459 vfloat32m1_t _sum0 = vfmv_v_f_f32m1(0.f, vl); in im2col_sgemm_packnto1_rvv() local
517 vfloat32m1_t _sum0 = vfmv_v_f_f32m1(0.f, vl); in im2col_sgemm_packnto1_rvv() local
560 vfloat32m1_t _sum0 = vfmv_v_f_f32m1(0.f, vl); in im2col_sgemm_packnto1_rvv() local
|
| H A D | convolution_sgemm_packnto1_fp16s.h | 211 vfloat16m1_t _sum0 = vle16_v_f16m1(biasptr, vl); in im2col_sgemm_packnto1_fp16sa_rvv() local
264 vfloat16m1_t _sum0 = vle16_v_f16m1(biasptr, vl); in im2col_sgemm_packnto1_fp16sa_rvv() local
301 vfloat16m1_t _sum0 = vle16_v_f16m1(biasptr, vl); in im2col_sgemm_packnto1_fp16sa_rvv() local
371 vfloat16m1_t _sum0 = vfmv_v_f_f16m1(0.f, vl); in im2col_sgemm_packnto1_fp16sa_rvv() local
459 vfloat16m1_t _sum0 = vfmv_v_f_f16m1(0.f, vl); in im2col_sgemm_packnto1_fp16sa_rvv() local
517 vfloat16m1_t _sum0 = vfmv_v_f_f16m1(0.f, vl); in im2col_sgemm_packnto1_fp16sa_rvv() local
560 vfloat16m1_t _sum0 = vfmv_v_f_f16m1(0.f, vl); in im2col_sgemm_packnto1_fp16sa_rvv() local
|
| /dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
| H A D | convolution_sgemm_pack8to1_int8.h | 482 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
565 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
831 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1131 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1158 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1256 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1300 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1343 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1365 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1463 int32x2_t _sum0 = vdup_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
[all …]
|
| H A D | convolutiondepthwise_3x3_fp16s.h | 82 float16x8_t _sum0 = _bias0; in convdw3x3s1_fp16sa_neon() local
138 float16x4_t _sum0 = vget_low_f16(_bias0); in convdw3x3s1_fp16sa_neon() local
179 float16x4_t _sum0 = vmul_f16(_r0, _k012x); in convdw3x3s1_fp16sa_neon() local
230 float16x8_t _sum0 = _bias0; in convdw3x3s1_fp16sa_neon() local
269 float16x4_t _sum0 = vget_low_f16(_bias0); in convdw3x3s1_fp16sa_neon() local
|
| /dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/arm/ |
| H A D | convolution_sgemm_pack8to1_int8.h | 482 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
565 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
831 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1131 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1158 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1256 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1300 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1343 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1365 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1463 int32x2_t _sum0 = vdup_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
[all …]
|
| H A D | convolutiondepthwise_3x3_fp16s.h | 82 float16x8_t _sum0 = _bias0; in convdw3x3s1_fp16sa_neon() local
138 float16x4_t _sum0 = vget_low_f16(_bias0); in convdw3x3s1_fp16sa_neon() local
179 float16x4_t _sum0 = vmul_f16(_r0, _k012x); in convdw3x3s1_fp16sa_neon() local
230 float16x8_t _sum0 = _bias0; in convdw3x3s1_fp16sa_neon() local
269 float16x4_t _sum0 = vget_low_f16(_bias0); in convdw3x3s1_fp16sa_neon() local
|
| /dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
| H A D | convolution_sgemm_pack8to1_int8.h | 482 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
565 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
831 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1131 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1158 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1256 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1300 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1343 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1365 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1463 int32x2_t _sum0 = vdup_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
[all …]
|
| H A D | convolutiondepthwise_3x3_fp16s.h | 82 float16x8_t _sum0 = _bias0; in convdw3x3s1_fp16sa_neon() local
138 float16x4_t _sum0 = vget_low_f16(_bias0); in convdw3x3s1_fp16sa_neon() local
179 float16x4_t _sum0 = vmul_f16(_r0, _k012x); in convdw3x3s1_fp16sa_neon() local
230 float16x8_t _sum0 = _bias0; in convdw3x3s1_fp16sa_neon() local
269 float16x4_t _sum0 = vget_low_f16(_bias0); in convdw3x3s1_fp16sa_neon() local
|
| /dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
| H A D | convolution_sgemm_pack8to1_int8.h | 482 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
565 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
831 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1131 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1158 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1256 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1300 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1343 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1365 int32x4_t _sum0 = vdupq_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
1463 int32x2_t _sum0 = vdup_n_s32(0); in im2col_sgemm_pack8to1_int8_neon() local
[all …]
|
| H A D | convolutiondepthwise_3x3_fp16s.h | 82 float16x8_t _sum0 = _bias0; in convdw3x3s1_fp16sa_neon() local
138 float16x4_t _sum0 = vget_low_f16(_bias0); in convdw3x3s1_fp16sa_neon() local
179 float16x4_t _sum0 = vmul_f16(_r0, _k012x); in convdw3x3s1_fp16sa_neon() local
230 float16x8_t _sum0 = _bias0; in convdw3x3s1_fp16sa_neon() local
269 float16x4_t _sum0 = vget_low_f16(_bias0); in convdw3x3s1_fp16sa_neon() local
|
| H A D | innerproduct_arm.cpp | 274 float32x4_t _sum0 = vdupq_n_f32(0.f); in forward() local
538 float32x4_t _sum0 = vdupq_n_f32(0.f); in forward_fp16s() local
933 float16x4_t _sum0 = vdup_n_f16(0.f); in forward_fp16sa() local
1082 float16x4_t _sum0 = vdup_n_f16(0.f); in forward_fp16sa() local
1249 float16x8_t _sum0 = vdupq_n_f16(0.f); in forward_fp16sa() local
1372 float16x4_t _sum0 = vdup_n_f16(0.f); in forward_fp16sa() local
1780 float32x4_t _sum0 = vdupq_n_f32(0.f); in forward_bf16s() local
2004 int32x4_t _sum0 = vdupq_n_s32(0); in forward_int8_arm() local
2110 int32x4_t _sum0 = vdupq_n_s32(0); in forward_int8_arm() local
2207 int32x4_t _sum0 = vdupq_n_s32(0); in forward_int8_arm() local
[all …]
|
| /dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
| H A D | convolutiondepthwise_3x3_pack8.h | 58 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
200 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
279 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
326 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
410 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
498 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
548 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
|
| H A D | convolutiondepthwise_3x3_pack8_fp16.h | 58 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
200 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
279 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
326 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
410 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
498 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
548 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
|
| /dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
| H A D | convolutiondepthwise_3x3_pack8_fp16.h | 58 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
200 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
279 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
326 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
410 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
498 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
548 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
|
| H A D | convolutiondepthwise_3x3_pack8.h | 58 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
200 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
279 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
326 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
410 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
498 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
548 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
|
| /dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
| H A D | convolutiondepthwise_3x3_pack4.h | 58 __m128 _sum0 = _bias0; in convdw3x3s1_pack4_sse() local
200 __m128 _sum0 = _bias0; in convdw3x3s1_pack4_sse() local
279 __m128 _sum0 = _bias0; in convdw3x3s1_pack4_sse() local
326 __m128 _sum0 = _bias0; in convdw3x3s1_pack4_sse() local
410 __m128 _sum0 = _bias0; in convdw3x3s2_pack4_sse() local
498 __m128 _sum0 = _bias0; in convdw3x3s2_pack4_sse() local
548 __m128 _sum0 = _bias0; in convdw3x3s2_pack4_sse() local
|
| H A D | convolutiondepthwise_3x3_pack8_fp16.h | 58 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
200 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
279 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
326 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
410 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
498 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
548 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
|
| H A D | convolutiondepthwise_3x3_pack8.h | 58 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
200 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
279 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
326 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
410 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
498 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
548 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
|
| /dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
| H A D | convolutiondepthwise_3x3_pack8.h | 58 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
200 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
279 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
326 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
410 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
498 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
548 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
|
| H A D | convolutiondepthwise_3x3_pack8_fp16.h | 58 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
200 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
279 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
326 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
410 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
498 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
548 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
|
| /dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
| H A D | convolutiondepthwise_3x3_pack8_fp16.h | 58 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
200 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
279 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
326 __m256 _sum0 = _bias0; in convdw3x3s1_fp16_pack8_avx() local
410 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
498 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
548 __m256 _sum0 = _bias0; in convdw3x3s2_fp16_pack8_avx() local
|
| H A D | convolutiondepthwise_3x3_pack8.h | 58 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
200 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
279 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
326 __m256 _sum0 = _bias0; in convdw3x3s1_pack8_avx() local
410 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
498 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
548 __m256 _sum0 = _bias0; in convdw3x3s2_pack8_avx() local
|
| /dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/arm/ |
| H A D | convolutiondepthwise_3x3_fp16s.h | 82 float16x8_t _sum0 = _bias0; in convdw3x3s1_fp16sa_neon() local
138 float16x4_t _sum0 = vget_low_f16(_bias0); in convdw3x3s1_fp16sa_neon() local
179 float16x4_t _sum0 = vmul_f16(_r0, _k012x); in convdw3x3s1_fp16sa_neon() local
230 float16x8_t _sum0 = _bias0; in convdw3x3s1_fp16sa_neon() local
269 float16x4_t _sum0 = vget_low_f16(_bias0); in convdw3x3s1_fp16sa_neon() local
|