/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 66 __m256 _k03 = _mm256_loadu_ps(kptr + 24); in conv2x2s1_pack8_avx() local 259 __m256 _k03 = _mm256_loadu_ps(kptr + 24); in conv2x2s1_pack8_avx() local
|
H A D | convolutiondepthwise_5x5_pack8.h | 60 __m256 _k03 = _mm256_loadu_ps(k0 + 24); in convdw5x5s1_pack8_avx() local 214 __m256 _k03 = _mm256_loadu_ps(k0 + 24); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 247 __m256 _k03 = loadfp16(kptr + 24); in conv2x2s1_fp16_pack8_avx() local 440 __m256 _k03 = loadfp16(kptr + 24); in conv2x2s1_fp16_pack8_avx() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 66 __m256 _k03 = _mm256_loadu_ps(kptr + 24); in conv2x2s1_pack8_avx() local 259 __m256 _k03 = _mm256_loadu_ps(kptr + 24); in conv2x2s1_pack8_avx() local
|
H A D | convolutiondepthwise_5x5_pack8.h | 60 __m256 _k03 = _mm256_loadu_ps(k0 + 24); in convdw5x5s1_pack8_avx() local 214 __m256 _k03 = _mm256_loadu_ps(k0 + 24); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 247 __m256 _k03 = loadfp16(kptr + 24); in conv2x2s1_fp16_pack8_avx() local 440 __m256 _k03 = loadfp16(kptr + 24); in conv2x2s1_fp16_pack8_avx() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 66 __m256 _k03 = _mm256_loadu_ps(kptr + 24); in conv2x2s1_pack8_avx() local 259 __m256 _k03 = _mm256_loadu_ps(kptr + 24); in conv2x2s1_pack8_avx() local
|
H A D | convolutiondepthwise_5x5_pack8.h | 60 __m256 _k03 = _mm256_loadu_ps(k0 + 24); in convdw5x5s1_pack8_avx() local 214 __m256 _k03 = _mm256_loadu_ps(k0 + 24); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 247 __m256 _k03 = loadfp16(kptr + 24); in conv2x2s1_fp16_pack8_avx() local 440 __m256 _k03 = loadfp16(kptr + 24); in conv2x2s1_fp16_pack8_avx() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 66 __m256 _k03 = _mm256_loadu_ps(kptr + 24); in conv2x2s1_pack8_avx() local 259 __m256 _k03 = _mm256_loadu_ps(kptr + 24); in conv2x2s1_pack8_avx() local
|
H A D | convolutiondepthwise_5x5_pack8.h | 60 __m256 _k03 = _mm256_loadu_ps(k0 + 24); in convdw5x5s1_pack8_avx() local 214 __m256 _k03 = _mm256_loadu_ps(k0 + 24); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 247 __m256 _k03 = loadfp16(kptr + 24); in conv2x2s1_fp16_pack8_avx() local 440 __m256 _k03 = loadfp16(kptr + 24); in conv2x2s1_fp16_pack8_avx() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 66 __m256 _k03 = _mm256_loadu_ps(kptr + 24); in conv2x2s1_pack8_avx() local 259 __m256 _k03 = _mm256_loadu_ps(kptr + 24); in conv2x2s1_pack8_avx() local
|
H A D | convolutiondepthwise_5x5_pack8.h | 60 __m256 _k03 = _mm256_loadu_ps(k0 + 24); in convdw5x5s1_pack8_avx() local 214 __m256 _k03 = _mm256_loadu_ps(k0 + 24); in convdw5x5s2_pack8_avx() local
|
H A D | convolution_2x2_pack8_fp16.h | 247 __m256 _k03 = loadfp16(kptr + 24); in conv2x2s1_fp16_pack8_avx() local 440 __m256 _k03 = loadfp16(kptr + 24); in conv2x2s1_fp16_pack8_avx() local
|
/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 80 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 402 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 607 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 776 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 976 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 1114 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 1279 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local 1492 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local 1634 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 80 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 402 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 607 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 776 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 976 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 1114 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 1279 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local 1492 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local 1634 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 80 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 402 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 607 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 776 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 976 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 1114 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 1279 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local 1492 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local 1634 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 80 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 402 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 607 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 776 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 976 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 1114 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 1279 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local 1492 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local 1634 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_5x5_pack4.h | 80 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 402 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 607 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 776 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 976 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 1114 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s1_pack4_neon() local 1279 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local 1492 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local 1634 float32x4_t _k03 = vld1q_f32(k0 + 12); in convdw5x5s2_pack4_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/riscv/ |
H A D | convolution_7x7_pack1ton.h | 74 vfloat32m1_t _k03 = vle32_v_f32m1(kptr + packn * 3, vl); in conv7x7s2_pack1ton_rvv() local 569 vfloat32m1_t _k03 = vle32_v_f32m1(kptr + packn * 3, vl); in conv7x7s2_pack1ton_rvv() local 861 vfloat32m1_t _k03 = vle32_v_f32m1(kptr + packn * 3, vl); in conv7x7s2_pack1ton_rvv() local
|
H A D | convolution_7x7_pack1ton_fp16s.h | 74 vfloat16m1_t _k03 = vle16_v_f16m1(kptr + packn * 3, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 569 vfloat16m1_t _k03 = vle16_v_f16m1(kptr + packn * 3, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local 861 vfloat16m1_t _k03 = vle16_v_f16m1(kptr + packn * 3, vl); in conv7x7s2_pack1ton_fp16sa_rvv() local
|
H A D | convolutiondepthwise_5x5_packn.h | 68 vfloat32m1_t _k03 = vle32_v_f32m1(k0 + packn * 3, vl); in convdw5x5s1_packn_rvv() local 230 vfloat32m1_t _k03 = vle32_v_f32m1(k0 + packn * 3, vl); in convdw5x5s1_packn_rvv() local 388 vfloat32m1_t _k03 = vle32_v_f32m1(k0 + packn * 3, vl); in convdw5x5s2_packn_rvv() local
|
H A D | convolutiondepthwise_5x5_packn_fp16s.h | 68 vfloat16m1_t _k03 = vle16_v_f16m1(k0 + packn * 3, vl); in convdw5x5s1_packn_fp16sa_rvv() local 230 vfloat16m1_t _k03 = vle16_v_f16m1(k0 + packn * 3, vl); in convdw5x5s1_packn_fp16sa_rvv() local 388 vfloat16m1_t _k03 = vle16_v_f16m1(k0 + packn * 3, vl); in convdw5x5s2_packn_fp16sa_rvv() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/mips/ |
H A D | convolutiondepthwise_5x5_pack4.h | 74 v4f32 _k03 = (v4f32)__msa_ld_w(k0 + 4 * 3, 0); in convdw5x5s1_pack4_msa() local 244 v4f32 _k03 = (v4f32)__msa_ld_w(k0 + 4 * 3, 0); in convdw5x5s1_pack4_msa() local 407 v4f32 _k03 = (v4f32)__msa_ld_w(k0 + 4 * 3, 0); in convdw5x5s2_pack4_msa() local
|