/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
H A D | convolution_3x3_pack1to4_fp16s.h | 48 float16x4_t _k10 = vld1_f16(k0 + 12); in conv3x3s1_pack1to4_fp16sa_neon() local 430 float16x4_t _k10 = vld1_f16(k0 + 12); in conv3x3s2_pack1to4_fp16sa_neon() local
|
H A D | convolution_3x3_pack1to8_fp16s.h | 48 float16x8_t _k10 = vld1q_f16(k0 + 24); in conv3x3s1_pack1to8_fp16sa_neon() local 430 float16x8_t _k10 = vld1q_f16(k0 + 24); in conv3x3s2_pack1to8_fp16sa_neon() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16s.h | 48 float16x8_t _k10 = vld1q_f16(k0 + 24); in convdw3x3s1_pack8_fp16sa_neon() local 658 float16x8_t _k10 = vld1q_f16(k0 + 24); in convdw3x3s2_pack8_fp16sa_neon() local
|
H A D | convolutiondepthwise_3x3_pack4.h | 48 float32x4_t _k10 = vld1q_f32(k0 + 12); in convdw3x3s1_pack4_neon() local 837 float32x4_t _k10 = vld1q_f32(k0 + 12); in convdw3x3s2_pack4_neon() local
|
H A D | convolutiondepthwise_3x3_pack4_bf16s.h | 48 float32x4_t _k10 = vcvt_f32_bf16(vld1_u16(k0 + 12)); in convdw3x3s1_pack4_bf16s_neon() local 1086 float32x4_t _k10 = vcvt_f32_bf16(vld1_u16(k0 + 12)); in convdw3x3s2_pack4_bf16s_neon() local
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/arm/ |
H A D | convolution_3x3_pack1to8_fp16s.h | 48 float16x8_t _k10 = vld1q_f16(k0 + 24); in conv3x3s1_pack1to8_fp16sa_neon() local 430 float16x8_t _k10 = vld1q_f16(k0 + 24); in conv3x3s2_pack1to8_fp16sa_neon() local
|
H A D | convolution_3x3_pack1to4_fp16s.h | 48 float16x4_t _k10 = vld1_f16(k0 + 12); in conv3x3s1_pack1to4_fp16sa_neon() local 430 float16x4_t _k10 = vld1_f16(k0 + 12); in conv3x3s2_pack1to4_fp16sa_neon() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16s.h | 48 float16x8_t _k10 = vld1q_f16(k0 + 24); in convdw3x3s1_pack8_fp16sa_neon() local 658 float16x8_t _k10 = vld1q_f16(k0 + 24); in convdw3x3s2_pack8_fp16sa_neon() local
|
H A D | convolutiondepthwise_3x3_pack4.h | 48 float32x4_t _k10 = vld1q_f32(k0 + 12); in convdw3x3s1_pack4_neon() local 837 float32x4_t _k10 = vld1q_f32(k0 + 12); in convdw3x3s2_pack4_neon() local
|
H A D | convolutiondepthwise_3x3_pack4_bf16s.h | 48 float32x4_t _k10 = vcvt_f32_bf16(vld1_u16(k0 + 12)); in convdw3x3s1_pack4_bf16s_neon() local 1086 float32x4_t _k10 = vcvt_f32_bf16(vld1_u16(k0 + 12)); in convdw3x3s2_pack4_bf16s_neon() local
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
H A D | convolution_3x3_pack1to4_fp16s.h | 48 float16x4_t _k10 = vld1_f16(k0 + 12); in conv3x3s1_pack1to4_fp16sa_neon() local 430 float16x4_t _k10 = vld1_f16(k0 + 12); in conv3x3s2_pack1to4_fp16sa_neon() local
|
H A D | convolutiondepthwise_3x3_pack8_fp16s.h | 48 float16x8_t _k10 = vld1q_f16(k0 + 24); in convdw3x3s1_pack8_fp16sa_neon() local 658 float16x8_t _k10 = vld1q_f16(k0 + 24); in convdw3x3s2_pack8_fp16sa_neon() local
|
H A D | convolution_3x3_pack1to8_fp16s.h | 48 float16x8_t _k10 = vld1q_f16(k0 + 24); in conv3x3s1_pack1to8_fp16sa_neon() local 430 float16x8_t _k10 = vld1q_f16(k0 + 24); in conv3x3s2_pack1to8_fp16sa_neon() local
|
H A D | convolutiondepthwise_3x3_pack4.h | 48 float32x4_t _k10 = vld1q_f32(k0 + 12); in convdw3x3s1_pack4_neon() local 837 float32x4_t _k10 = vld1q_f32(k0 + 12); in convdw3x3s2_pack4_neon() local
|
H A D | convolutiondepthwise_3x3_pack4_bf16s.h | 48 float32x4_t _k10 = vcvt_f32_bf16(vld1_u16(k0 + 12)); in convdw3x3s1_pack4_bf16s_neon() local 1086 float32x4_t _k10 = vcvt_f32_bf16(vld1_u16(k0 + 12)); in convdw3x3s2_pack4_bf16s_neon() local
|
/dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack8_fp16s.h | 48 float16x8_t _k10 = vld1q_f16(k0 + 24); in convdw3x3s1_pack8_fp16sa_neon() local 658 float16x8_t _k10 = vld1q_f16(k0 + 24); in convdw3x3s2_pack8_fp16sa_neon() local
|
H A D | convolution_3x3_pack1to4_fp16s.h | 48 float16x4_t _k10 = vld1_f16(k0 + 12); in conv3x3s1_pack1to4_fp16sa_neon() local 430 float16x4_t _k10 = vld1_f16(k0 + 12); in conv3x3s2_pack1to4_fp16sa_neon() local
|
H A D | convolution_3x3_pack1to8_fp16s.h | 48 float16x8_t _k10 = vld1q_f16(k0 + 24); in conv3x3s1_pack1to8_fp16sa_neon() local 430 float16x8_t _k10 = vld1q_f16(k0 + 24); in conv3x3s2_pack1to8_fp16sa_neon() local
|
H A D | convolutiondepthwise_3x3_pack4.h | 48 float32x4_t _k10 = vld1q_f32(k0 + 12); in convdw3x3s1_pack4_neon() local 837 float32x4_t _k10 = vld1q_f32(k0 + 12); in convdw3x3s2_pack4_neon() local
|
H A D | convolutiondepthwise_3x3_pack4_bf16s.h | 48 float32x4_t _k10 = vcvt_f32_bf16(vld1_u16(k0 + 12)); in convdw3x3s1_pack4_bf16s_neon() local 1086 float32x4_t _k10 = vcvt_f32_bf16(vld1_u16(k0 + 12)); in convdw3x3s2_pack4_bf16s_neon() local
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack8_fp16s.h | 48 float16x8_t _k10 = vld1q_f16(k0 + 24); in convdw3x3s1_pack8_fp16sa_neon() local 658 float16x8_t _k10 = vld1q_f16(k0 + 24); in convdw3x3s2_pack8_fp16sa_neon() local
|
H A D | convolution_3x3_pack1to8_fp16s.h | 48 float16x8_t _k10 = vld1q_f16(k0 + 24); in conv3x3s1_pack1to8_fp16sa_neon() local 430 float16x8_t _k10 = vld1q_f16(k0 + 24); in conv3x3s2_pack1to8_fp16sa_neon() local
|
H A D | convolutiondepthwise_3x3_pack4_bf16s.h | 48 float32x4_t _k10 = vcvt_f32_bf16(vld1_u16(k0 + 12)); in convdw3x3s1_pack4_bf16s_neon() local 1086 float32x4_t _k10 = vcvt_f32_bf16(vld1_u16(k0 + 12)); in convdw3x3s2_pack4_bf16s_neon() local
|
H A D | convolutiondepthwise_3x3_pack4.h | 48 float32x4_t _k10 = vld1q_f32(k0 + 12); in convdw3x3s1_pack4_neon() local 837 float32x4_t _k10 = vld1q_f32(k0 + 12); in convdw3x3s2_pack4_neon() local
|
/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
H A D | convolution_2x2_pack8.h | 156 __m256 _k10 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local 321 __m256 _k10 = _mm256_loadu_ps(kptr); in conv2x2s1_pack8_avx() local
|