/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack4.h | 210 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 310 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 390 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 504 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 605 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 683 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 756 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 945 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() 1080 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() 1161 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() [all …]
|
H A D | convolutiondepthwise_3x3_pack4_bf16s.h | 282 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 428 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 533 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 685 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 818 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 914 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 1005 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 1032 _sum0 = vmlaq_f32(_sum0, _k11, _r11); in convdw3x3s1_pack4_bf16s_neon() 1247 "w"(_k11), // %12 in convdw3x3s2_pack4_bf16s_neon() 1355 "w"(_k11), // %12 in convdw3x3s2_pack4_bf16s_neon() [all …]
|
H A D | convolutiondepthwise_3x3_pack8_fp16s.h | 49 float16x8_t _k11 = vld1q_f16(k0 + 32); in convdw3x3s1_pack8_fp16sa_neon() local 206 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 301 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 380 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 485 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 552 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 609 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 659 float16x8_t _k11 = vld1q_f16(k0 + 32); in convdw3x3s2_pack8_fp16sa_neon() local 763 "w"(_k11), // %12 in convdw3x3s2_pack8_fp16sa_neon() 838 "w"(_k11), // %12 in convdw3x3s2_pack8_fp16sa_neon() [all …]
|
H A D | convolution_3x3_pack1to4_fp16s.h | 49 float16x4_t _k11 = vld1_f16(k0 + 16); in conv3x3s1_pack1to4_fp16sa_neon() local 178 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 263 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 324 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 376 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 431 float16x4_t _k11 = vld1_f16(k0 + 16); in conv3x3s2_pack1to4_fp16sa_neon() local 518 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon() 578 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon() 630 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon()
|
H A D | convolution_3x3_pack1to8_fp16s.h | 49 float16x8_t _k11 = vld1q_f16(k0 + 32); in conv3x3s1_pack1to8_fp16sa_neon() local 178 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 263 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 324 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 376 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 431 float16x8_t _k11 = vld1q_f16(k0 + 32); in conv3x3s2_pack1to8_fp16sa_neon() local 518 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon() 578 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon() 630 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon()
|
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack4.h | 210 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 310 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 390 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 504 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 605 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 683 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 756 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 945 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() 1080 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() 1161 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() [all …]
|
H A D | convolutiondepthwise_3x3_pack4_bf16s.h | 282 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 428 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 533 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 685 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 818 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 914 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 1005 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 1032 _sum0 = vmlaq_f32(_sum0, _k11, _r11); in convdw3x3s1_pack4_bf16s_neon() 1247 "w"(_k11), // %12 in convdw3x3s2_pack4_bf16s_neon() 1355 "w"(_k11), // %12 in convdw3x3s2_pack4_bf16s_neon() [all …]
|
H A D | convolutiondepthwise_3x3_pack8_fp16s.h | 49 float16x8_t _k11 = vld1q_f16(k0 + 32); in convdw3x3s1_pack8_fp16sa_neon() local 206 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 301 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 380 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 485 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 552 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 609 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 659 float16x8_t _k11 = vld1q_f16(k0 + 32); in convdw3x3s2_pack8_fp16sa_neon() local 763 "w"(_k11), // %12 in convdw3x3s2_pack8_fp16sa_neon() 838 "w"(_k11), // %12 in convdw3x3s2_pack8_fp16sa_neon() [all …]
|
H A D | convolution_3x3_pack1to8_fp16s.h | 49 float16x8_t _k11 = vld1q_f16(k0 + 32); in conv3x3s1_pack1to8_fp16sa_neon() local 178 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 263 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 324 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 376 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 431 float16x8_t _k11 = vld1q_f16(k0 + 32); in conv3x3s2_pack1to8_fp16sa_neon() local 518 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon() 578 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon() 630 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon()
|
H A D | convolution_3x3_pack1to4_fp16s.h | 49 float16x4_t _k11 = vld1_f16(k0 + 16); in conv3x3s1_pack1to4_fp16sa_neon() local 178 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 263 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 324 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 376 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 431 float16x4_t _k11 = vld1_f16(k0 + 16); in conv3x3s2_pack1to4_fp16sa_neon() local 518 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon() 578 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon() 630 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon()
|
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack4.h | 210 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 310 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 390 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 504 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 605 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 683 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 756 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 945 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() 1080 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() 1161 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() [all …]
|
H A D | convolutiondepthwise_3x3_pack4_bf16s.h | 282 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 428 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 533 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 685 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 818 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 914 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 1005 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 1032 _sum0 = vmlaq_f32(_sum0, _k11, _r11); in convdw3x3s1_pack4_bf16s_neon() 1247 "w"(_k11), // %12 in convdw3x3s2_pack4_bf16s_neon() 1355 "w"(_k11), // %12 in convdw3x3s2_pack4_bf16s_neon() [all …]
|
H A D | convolutiondepthwise_3x3_pack8_fp16s.h | 49 float16x8_t _k11 = vld1q_f16(k0 + 32); in convdw3x3s1_pack8_fp16sa_neon() local 206 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 301 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 380 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 485 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 552 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 609 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 659 float16x8_t _k11 = vld1q_f16(k0 + 32); in convdw3x3s2_pack8_fp16sa_neon() local 763 "w"(_k11), // %12 in convdw3x3s2_pack8_fp16sa_neon() 838 "w"(_k11), // %12 in convdw3x3s2_pack8_fp16sa_neon() [all …]
|
H A D | convolution_3x3_pack1to4_fp16s.h | 49 float16x4_t _k11 = vld1_f16(k0 + 16); in conv3x3s1_pack1to4_fp16sa_neon() local 178 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 263 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 324 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 376 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 431 float16x4_t _k11 = vld1_f16(k0 + 16); in conv3x3s2_pack1to4_fp16sa_neon() local 518 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon() 578 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon() 630 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon()
|
H A D | convolution_3x3_pack1to8_fp16s.h | 49 float16x8_t _k11 = vld1q_f16(k0 + 32); in conv3x3s1_pack1to8_fp16sa_neon() local 178 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 263 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 324 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 376 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 431 float16x8_t _k11 = vld1q_f16(k0 + 32); in conv3x3s2_pack1to8_fp16sa_neon() local 518 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon() 578 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon() 630 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon()
|
/dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack4.h | 210 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 310 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 390 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 504 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 605 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 683 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 756 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 945 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() 1080 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() 1161 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() [all …]
|
H A D | convolutiondepthwise_3x3_pack4_bf16s.h | 282 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 428 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 533 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 685 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 818 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 914 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 1005 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 1032 _sum0 = vmlaq_f32(_sum0, _k11, _r11); in convdw3x3s1_pack4_bf16s_neon() 1247 "w"(_k11), // %12 in convdw3x3s2_pack4_bf16s_neon() 1355 "w"(_k11), // %12 in convdw3x3s2_pack4_bf16s_neon() [all …]
|
H A D | convolutiondepthwise_3x3_pack8_fp16s.h | 49 float16x8_t _k11 = vld1q_f16(k0 + 32); in convdw3x3s1_pack8_fp16sa_neon() local 206 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 301 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 380 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 485 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 552 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 609 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 659 float16x8_t _k11 = vld1q_f16(k0 + 32); in convdw3x3s2_pack8_fp16sa_neon() local 763 "w"(_k11), // %12 in convdw3x3s2_pack8_fp16sa_neon() 838 "w"(_k11), // %12 in convdw3x3s2_pack8_fp16sa_neon() [all …]
|
H A D | convolution_3x3_pack1to4_fp16s.h | 49 float16x4_t _k11 = vld1_f16(k0 + 16); in conv3x3s1_pack1to4_fp16sa_neon() local 178 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 263 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 324 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 376 "w"(_k11), // %12 in conv3x3s1_pack1to4_fp16sa_neon() 431 float16x4_t _k11 = vld1_f16(k0 + 16); in conv3x3s2_pack1to4_fp16sa_neon() local 518 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon() 578 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon() 630 "w"(_k11), // %12 in conv3x3s2_pack1to4_fp16sa_neon()
|
H A D | convolution_3x3_pack1to8_fp16s.h | 49 float16x8_t _k11 = vld1q_f16(k0 + 32); in conv3x3s1_pack1to8_fp16sa_neon() local 178 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 263 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 324 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 376 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 431 float16x8_t _k11 = vld1q_f16(k0 + 32); in conv3x3s2_pack1to8_fp16sa_neon() local 518 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon() 578 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon() 630 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon()
|
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/arm/ |
H A D | convolutiondepthwise_3x3_pack4.h | 210 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 310 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 390 "w"(_k11), // %16 in convdw3x3s1_pack4_neon() 504 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 605 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 683 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 756 "w"(_k11), // %12 in convdw3x3s1_pack4_neon() 945 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() 1080 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() 1161 "w"(_k11), // %12 in convdw3x3s2_pack4_neon() [all …]
|
H A D | convolutiondepthwise_3x3_pack4_bf16s.h | 282 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 428 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 533 "w"(_k11), // %16 in convdw3x3s1_pack4_bf16s_neon() 685 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 818 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 914 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 1005 "w"(_k11), // %12 in convdw3x3s1_pack4_bf16s_neon() 1032 _sum0 = vmlaq_f32(_sum0, _k11, _r11); in convdw3x3s1_pack4_bf16s_neon() 1247 "w"(_k11), // %12 in convdw3x3s2_pack4_bf16s_neon() 1355 "w"(_k11), // %12 in convdw3x3s2_pack4_bf16s_neon() [all …]
|
H A D | convolutiondepthwise_3x3_pack8_fp16s.h | 49 float16x8_t _k11 = vld1q_f16(k0 + 32); in convdw3x3s1_pack8_fp16sa_neon() local 206 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 301 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 380 "w"(_k11), // %16 in convdw3x3s1_pack8_fp16sa_neon() 485 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 552 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 609 "w"(_k11), // %12 in convdw3x3s1_pack8_fp16sa_neon() 659 float16x8_t _k11 = vld1q_f16(k0 + 32); in convdw3x3s2_pack8_fp16sa_neon() local 763 "w"(_k11), // %12 in convdw3x3s2_pack8_fp16sa_neon() 838 "w"(_k11), // %12 in convdw3x3s2_pack8_fp16sa_neon() [all …]
|
H A D | convolution_3x3_pack1to8_fp16s.h | 49 float16x8_t _k11 = vld1q_f16(k0 + 32); in conv3x3s1_pack1to8_fp16sa_neon() local 178 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 263 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 324 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 376 "w"(_k11), // %12 in conv3x3s1_pack1to8_fp16sa_neon() 431 float16x8_t _k11 = vld1q_f16(k0 + 32); in conv3x3s2_pack1to8_fp16sa_neon() local 518 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon() 578 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon() 630 "w"(_k11), // %12 in conv3x3s2_pack1to8_fp16sa_neon()
|
/dports/misc/ncnn/ncnn-20211208/src/layer/riscv/ |
H A D | convolution_3x3_pack1ton.h | 52 vfloat32m1_t _k11 = vle32_v_f32m1(k0 + packn * 4, vl); in conv3x3s1_pack1ton_rvv() local 106 _sum0 = vfmacc_vf_f32m1(_sum0, r1[1], _k11, vl); in conv3x3s1_pack1ton_rvv() 107 _sum1 = vfmacc_vf_f32m1(_sum1, r1[2], _k11, vl); in conv3x3s1_pack1ton_rvv() 108 _sum2 = vfmacc_vf_f32m1(_sum2, r1[3], _k11, vl); in conv3x3s1_pack1ton_rvv() 109 _sum3 = vfmacc_vf_f32m1(_sum3, r1[4], _k11, vl); in conv3x3s1_pack1ton_rvv() 110 _sum4 = vfmacc_vf_f32m1(_sum4, r1[5], _k11, vl); in conv3x3s1_pack1ton_rvv() 111 _sum5 = vfmacc_vf_f32m1(_sum5, r1[6], _k11, vl); in conv3x3s1_pack1ton_rvv() 112 _sum6 = vfmacc_vf_f32m1(_sum6, r1[7], _k11, vl); in conv3x3s1_pack1ton_rvv() 113 _sum7 = vfmacc_vf_f32m1(_sum7, r1[8], _k11, vl); in conv3x3s1_pack1ton_rvv() 187 _sum0 = vfmacc_vf_f32m1(_sum0, r1[1], _k11, vl); in conv3x3s1_pack1ton_rvv() [all …]
|