| /dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/arm/ |
| H A D | convolution_7x7.h | 273 _sum = vfmaq_laneq_f32(_sum, _r00, _k0123, 0); in conv7x7s1_neon()
274 _sum = vfmaq_laneq_f32(_sum, _r01, _k0123, 1); in conv7x7s1_neon()
275 _sum = vfmaq_laneq_f32(_sum, _r02, _k0123, 2); in conv7x7s1_neon()
276 _sum = vfmaq_laneq_f32(_sum, _r03, _k0123, 3); in conv7x7s1_neon()
277 _sum = vfmaq_laneq_f32(_sum, _r04, _k4567, 0); in conv7x7s1_neon()
278 _sum = vfmaq_laneq_f32(_sum, _r05, _k4567, 1); in conv7x7s1_neon()
279 _sum = vfmaq_laneq_f32(_sum, _r06, _k4567, 2); in conv7x7s1_neon()
290 _sum = vfmaq_laneq_f32(_sum, _r10, _k78910, 0); in conv7x7s1_neon()
291 _sum = vfmaq_laneq_f32(_sum, _r11, _k78910, 1); in conv7x7s1_neon()
292 _sum = vfmaq_laneq_f32(_sum, _r12, _k78910, 2); in conv7x7s1_neon()
[all …]
|
| H A D | convolution_pack8_fp16s.h | 57 float16x8_t _sum = vdupq_n_f16((__fp16)0.f); in convolution_pack8_fp16sa_neon() local
85 _sum = vfmaq_laneq_f16(_sum, _w0, _val, 0); in convolution_pack8_fp16sa_neon()
86 _sum = vfmaq_laneq_f16(_sum, _w1, _val, 1); in convolution_pack8_fp16sa_neon()
87 _sum = vfmaq_laneq_f16(_sum, _w2, _val, 2); in convolution_pack8_fp16sa_neon()
88 _sum = vfmaq_laneq_f16(_sum, _w3, _val, 3); in convolution_pack8_fp16sa_neon()
89 _sum = vfmaq_laneq_f16(_sum, _w4, _val, 4); in convolution_pack8_fp16sa_neon()
90 _sum = vfmaq_laneq_f16(_sum, _w5, _val, 5); in convolution_pack8_fp16sa_neon()
91 _sum = vfmaq_laneq_f16(_sum, _w6, _val, 6); in convolution_pack8_fp16sa_neon()
92 _sum = vfmaq_laneq_f16(_sum, _w7, _val, 7); in convolution_pack8_fp16sa_neon()
98 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack8_fp16sa_neon()
[all …]
|
| H A D | convolution_pack8to4_fp16s.h | 57 float16x4_t _sum = vdup_n_f16((__fp16)0.f); in convolution_pack8to4_fp16sa_neon() local
85 _sum = vfma_laneq_f16(_sum, _w0, _val, 0); in convolution_pack8to4_fp16sa_neon()
86 _sum = vfma_laneq_f16(_sum, _w1, _val, 1); in convolution_pack8to4_fp16sa_neon()
87 _sum = vfma_laneq_f16(_sum, _w2, _val, 2); in convolution_pack8to4_fp16sa_neon()
88 _sum = vfma_laneq_f16(_sum, _w3, _val, 3); in convolution_pack8to4_fp16sa_neon()
89 _sum = vfma_laneq_f16(_sum, _w4, _val, 4); in convolution_pack8to4_fp16sa_neon()
90 _sum = vfma_laneq_f16(_sum, _w5, _val, 5); in convolution_pack8to4_fp16sa_neon()
91 _sum = vfma_laneq_f16(_sum, _w6, _val, 6); in convolution_pack8to4_fp16sa_neon()
92 _sum = vfma_laneq_f16(_sum, _w7, _val, 7); in convolution_pack8to4_fp16sa_neon()
98 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack8to4_fp16sa_neon()
[all …]
|
| H A D | convolution_pack4_fp16s.h | 81 _sum = vfmaq_laneq_f32(_sum, _w0, _val, 0); in convolution_pack4_fp16s_neon()
82 _sum = vfmaq_laneq_f32(_sum, _w1, _val, 1); in convolution_pack4_fp16s_neon()
83 _sum = vfmaq_laneq_f32(_sum, _w2, _val, 2); in convolution_pack4_fp16s_neon()
84 _sum = vfmaq_laneq_f32(_sum, _w3, _val, 3); in convolution_pack4_fp16s_neon()
90 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack4_fp16s_neon()
166 _sum = vfma_lane_f16(_sum, _w0, _val, 0); in convolution_pack4_fp16sa_neon()
167 _sum = vfma_lane_f16(_sum, _w1, _val, 1); in convolution_pack4_fp16sa_neon()
168 _sum = vfma_lane_f16(_sum, _w2, _val, 2); in convolution_pack4_fp16sa_neon()
169 _sum = vfma_lane_f16(_sum, _w3, _val, 3); in convolution_pack4_fp16sa_neon()
175 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack4_fp16sa_neon()
[all …]
|
| /dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/arm/ |
| H A D | convolution_7x7.h | 273 _sum = vfmaq_laneq_f32(_sum, _r00, _k0123, 0); in conv7x7s1_neon()
274 _sum = vfmaq_laneq_f32(_sum, _r01, _k0123, 1); in conv7x7s1_neon()
275 _sum = vfmaq_laneq_f32(_sum, _r02, _k0123, 2); in conv7x7s1_neon()
276 _sum = vfmaq_laneq_f32(_sum, _r03, _k0123, 3); in conv7x7s1_neon()
277 _sum = vfmaq_laneq_f32(_sum, _r04, _k4567, 0); in conv7x7s1_neon()
278 _sum = vfmaq_laneq_f32(_sum, _r05, _k4567, 1); in conv7x7s1_neon()
279 _sum = vfmaq_laneq_f32(_sum, _r06, _k4567, 2); in conv7x7s1_neon()
290 _sum = vfmaq_laneq_f32(_sum, _r10, _k78910, 0); in conv7x7s1_neon()
291 _sum = vfmaq_laneq_f32(_sum, _r11, _k78910, 1); in conv7x7s1_neon()
292 _sum = vfmaq_laneq_f32(_sum, _r12, _k78910, 2); in conv7x7s1_neon()
[all …]
|
| H A D | convolution_pack8to4_fp16s.h | 57 float16x4_t _sum = vdup_n_f16((__fp16)0.f); in convolution_pack8to4_fp16sa_neon() local
85 _sum = vfma_laneq_f16(_sum, _w0, _val, 0); in convolution_pack8to4_fp16sa_neon()
86 _sum = vfma_laneq_f16(_sum, _w1, _val, 1); in convolution_pack8to4_fp16sa_neon()
87 _sum = vfma_laneq_f16(_sum, _w2, _val, 2); in convolution_pack8to4_fp16sa_neon()
88 _sum = vfma_laneq_f16(_sum, _w3, _val, 3); in convolution_pack8to4_fp16sa_neon()
89 _sum = vfma_laneq_f16(_sum, _w4, _val, 4); in convolution_pack8to4_fp16sa_neon()
90 _sum = vfma_laneq_f16(_sum, _w5, _val, 5); in convolution_pack8to4_fp16sa_neon()
91 _sum = vfma_laneq_f16(_sum, _w6, _val, 6); in convolution_pack8to4_fp16sa_neon()
92 _sum = vfma_laneq_f16(_sum, _w7, _val, 7); in convolution_pack8to4_fp16sa_neon()
98 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack8to4_fp16sa_neon()
[all …]
|
| H A D | convolution_pack8_fp16s.h | 57 float16x8_t _sum = vdupq_n_f16((__fp16)0.f); in convolution_pack8_fp16sa_neon() local
85 _sum = vfmaq_laneq_f16(_sum, _w0, _val, 0); in convolution_pack8_fp16sa_neon()
86 _sum = vfmaq_laneq_f16(_sum, _w1, _val, 1); in convolution_pack8_fp16sa_neon()
87 _sum = vfmaq_laneq_f16(_sum, _w2, _val, 2); in convolution_pack8_fp16sa_neon()
88 _sum = vfmaq_laneq_f16(_sum, _w3, _val, 3); in convolution_pack8_fp16sa_neon()
89 _sum = vfmaq_laneq_f16(_sum, _w4, _val, 4); in convolution_pack8_fp16sa_neon()
90 _sum = vfmaq_laneq_f16(_sum, _w5, _val, 5); in convolution_pack8_fp16sa_neon()
91 _sum = vfmaq_laneq_f16(_sum, _w6, _val, 6); in convolution_pack8_fp16sa_neon()
92 _sum = vfmaq_laneq_f16(_sum, _w7, _val, 7); in convolution_pack8_fp16sa_neon()
98 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack8_fp16sa_neon()
[all …]
|
| H A D | convolution_pack4_fp16s.h | 81 _sum = vfmaq_laneq_f32(_sum, _w0, _val, 0); in convolution_pack4_fp16s_neon()
82 _sum = vfmaq_laneq_f32(_sum, _w1, _val, 1); in convolution_pack4_fp16s_neon()
83 _sum = vfmaq_laneq_f32(_sum, _w2, _val, 2); in convolution_pack4_fp16s_neon()
84 _sum = vfmaq_laneq_f32(_sum, _w3, _val, 3); in convolution_pack4_fp16s_neon()
90 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack4_fp16s_neon()
166 _sum = vfma_lane_f16(_sum, _w0, _val, 0); in convolution_pack4_fp16sa_neon()
167 _sum = vfma_lane_f16(_sum, _w1, _val, 1); in convolution_pack4_fp16sa_neon()
168 _sum = vfma_lane_f16(_sum, _w2, _val, 2); in convolution_pack4_fp16sa_neon()
169 _sum = vfma_lane_f16(_sum, _w3, _val, 3); in convolution_pack4_fp16sa_neon()
175 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack4_fp16sa_neon()
[all …]
|
| /dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/arm/ |
| H A D | convolution_7x7.h | 273 _sum = vfmaq_laneq_f32(_sum, _r00, _k0123, 0); in conv7x7s1_neon()
274 _sum = vfmaq_laneq_f32(_sum, _r01, _k0123, 1); in conv7x7s1_neon()
275 _sum = vfmaq_laneq_f32(_sum, _r02, _k0123, 2); in conv7x7s1_neon()
276 _sum = vfmaq_laneq_f32(_sum, _r03, _k0123, 3); in conv7x7s1_neon()
277 _sum = vfmaq_laneq_f32(_sum, _r04, _k4567, 0); in conv7x7s1_neon()
278 _sum = vfmaq_laneq_f32(_sum, _r05, _k4567, 1); in conv7x7s1_neon()
279 _sum = vfmaq_laneq_f32(_sum, _r06, _k4567, 2); in conv7x7s1_neon()
290 _sum = vfmaq_laneq_f32(_sum, _r10, _k78910, 0); in conv7x7s1_neon()
291 _sum = vfmaq_laneq_f32(_sum, _r11, _k78910, 1); in conv7x7s1_neon()
292 _sum = vfmaq_laneq_f32(_sum, _r12, _k78910, 2); in conv7x7s1_neon()
[all …]
|
| H A D | convolution_pack8_fp16s.h | 57 float16x8_t _sum = vdupq_n_f16((__fp16)0.f); in convolution_pack8_fp16sa_neon() local
85 _sum = vfmaq_laneq_f16(_sum, _w0, _val, 0); in convolution_pack8_fp16sa_neon()
86 _sum = vfmaq_laneq_f16(_sum, _w1, _val, 1); in convolution_pack8_fp16sa_neon()
87 _sum = vfmaq_laneq_f16(_sum, _w2, _val, 2); in convolution_pack8_fp16sa_neon()
88 _sum = vfmaq_laneq_f16(_sum, _w3, _val, 3); in convolution_pack8_fp16sa_neon()
89 _sum = vfmaq_laneq_f16(_sum, _w4, _val, 4); in convolution_pack8_fp16sa_neon()
90 _sum = vfmaq_laneq_f16(_sum, _w5, _val, 5); in convolution_pack8_fp16sa_neon()
91 _sum = vfmaq_laneq_f16(_sum, _w6, _val, 6); in convolution_pack8_fp16sa_neon()
92 _sum = vfmaq_laneq_f16(_sum, _w7, _val, 7); in convolution_pack8_fp16sa_neon()
98 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack8_fp16sa_neon()
[all …]
|
| H A D | convolution_pack8to4_fp16s.h | 57 float16x4_t _sum = vdup_n_f16((__fp16)0.f); in convolution_pack8to4_fp16sa_neon() local
85 _sum = vfma_laneq_f16(_sum, _w0, _val, 0); in convolution_pack8to4_fp16sa_neon()
86 _sum = vfma_laneq_f16(_sum, _w1, _val, 1); in convolution_pack8to4_fp16sa_neon()
87 _sum = vfma_laneq_f16(_sum, _w2, _val, 2); in convolution_pack8to4_fp16sa_neon()
88 _sum = vfma_laneq_f16(_sum, _w3, _val, 3); in convolution_pack8to4_fp16sa_neon()
89 _sum = vfma_laneq_f16(_sum, _w4, _val, 4); in convolution_pack8to4_fp16sa_neon()
90 _sum = vfma_laneq_f16(_sum, _w5, _val, 5); in convolution_pack8to4_fp16sa_neon()
91 _sum = vfma_laneq_f16(_sum, _w6, _val, 6); in convolution_pack8to4_fp16sa_neon()
92 _sum = vfma_laneq_f16(_sum, _w7, _val, 7); in convolution_pack8to4_fp16sa_neon()
98 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack8to4_fp16sa_neon()
[all …]
|
| H A D | convolution_pack4_fp16s.h | 81 _sum = vfmaq_laneq_f32(_sum, _w0, _val, 0); in convolution_pack4_fp16s_neon()
82 _sum = vfmaq_laneq_f32(_sum, _w1, _val, 1); in convolution_pack4_fp16s_neon()
83 _sum = vfmaq_laneq_f32(_sum, _w2, _val, 2); in convolution_pack4_fp16s_neon()
84 _sum = vfmaq_laneq_f32(_sum, _w3, _val, 3); in convolution_pack4_fp16s_neon()
90 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack4_fp16s_neon()
166 _sum = vfma_lane_f16(_sum, _w0, _val, 0); in convolution_pack4_fp16sa_neon()
167 _sum = vfma_lane_f16(_sum, _w1, _val, 1); in convolution_pack4_fp16sa_neon()
168 _sum = vfma_lane_f16(_sum, _w2, _val, 2); in convolution_pack4_fp16sa_neon()
169 _sum = vfma_lane_f16(_sum, _w3, _val, 3); in convolution_pack4_fp16sa_neon()
175 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack4_fp16sa_neon()
[all …]
|
| /dports/misc/ncnn/ncnn-20211208/src/layer/arm/ |
| H A D | convolution_7x7.h | 273 _sum = vfmaq_laneq_f32(_sum, _r00, _k0123, 0); in conv7x7s1_neon()
274 _sum = vfmaq_laneq_f32(_sum, _r01, _k0123, 1); in conv7x7s1_neon()
275 _sum = vfmaq_laneq_f32(_sum, _r02, _k0123, 2); in conv7x7s1_neon()
276 _sum = vfmaq_laneq_f32(_sum, _r03, _k0123, 3); in conv7x7s1_neon()
277 _sum = vfmaq_laneq_f32(_sum, _r04, _k4567, 0); in conv7x7s1_neon()
278 _sum = vfmaq_laneq_f32(_sum, _r05, _k4567, 1); in conv7x7s1_neon()
279 _sum = vfmaq_laneq_f32(_sum, _r06, _k4567, 2); in conv7x7s1_neon()
290 _sum = vfmaq_laneq_f32(_sum, _r10, _k78910, 0); in conv7x7s1_neon()
291 _sum = vfmaq_laneq_f32(_sum, _r11, _k78910, 1); in conv7x7s1_neon()
292 _sum = vfmaq_laneq_f32(_sum, _r12, _k78910, 2); in conv7x7s1_neon()
[all …]
|
| H A D | convolution1d_arm.cpp | 188 _sum = vmlaq_laneq_f32(_sum, _w0, _val, 0); in forward()
189 _sum = vmlaq_laneq_f32(_sum, _w1, _val, 1); in forward()
190 _sum = vmlaq_laneq_f32(_sum, _w2, _val, 2); in forward()
191 _sum = vmlaq_laneq_f32(_sum, _w3, _val, 3); in forward()
240 _sum = vmlaq_f32(_sum, _val, _w); in forward()
462 _sum = vfmaq_laneq_f32(_sum, _w0, _val, 0); in forward_fp16s()
463 _sum = vfmaq_laneq_f32(_sum, _w1, _val, 1); in forward_fp16s()
508 _sum = vfmaq_f32(_sum, _val, _w); in forward_fp16s()
730 _sum = vfmaq_f16(_sum, _val, _w); in forward_fp16sa()
979 _sum = vfma_f16(_sum, _val, _w); in forward_fp16sa()
[all …]
|
| H A D | convolution_pack8to4_fp16s.h | 57 float16x4_t _sum = vdup_n_f16((__fp16)0.f); in convolution_pack8to4_fp16sa_neon() local
85 _sum = vfma_laneq_f16(_sum, _w0, _val, 0); in convolution_pack8to4_fp16sa_neon()
86 _sum = vfma_laneq_f16(_sum, _w1, _val, 1); in convolution_pack8to4_fp16sa_neon()
87 _sum = vfma_laneq_f16(_sum, _w2, _val, 2); in convolution_pack8to4_fp16sa_neon()
88 _sum = vfma_laneq_f16(_sum, _w3, _val, 3); in convolution_pack8to4_fp16sa_neon()
89 _sum = vfma_laneq_f16(_sum, _w4, _val, 4); in convolution_pack8to4_fp16sa_neon()
90 _sum = vfma_laneq_f16(_sum, _w5, _val, 5); in convolution_pack8to4_fp16sa_neon()
91 _sum = vfma_laneq_f16(_sum, _w6, _val, 6); in convolution_pack8to4_fp16sa_neon()
92 _sum = vfma_laneq_f16(_sum, _w7, _val, 7); in convolution_pack8to4_fp16sa_neon()
98 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack8to4_fp16sa_neon()
[all …]
|
| H A D | convolution_pack8_fp16s.h | 57 float16x8_t _sum = vdupq_n_f16((__fp16)0.f); in convolution_pack8_fp16sa_neon() local
85 _sum = vfmaq_laneq_f16(_sum, _w0, _val, 0); in convolution_pack8_fp16sa_neon()
86 _sum = vfmaq_laneq_f16(_sum, _w1, _val, 1); in convolution_pack8_fp16sa_neon()
87 _sum = vfmaq_laneq_f16(_sum, _w2, _val, 2); in convolution_pack8_fp16sa_neon()
88 _sum = vfmaq_laneq_f16(_sum, _w3, _val, 3); in convolution_pack8_fp16sa_neon()
89 _sum = vfmaq_laneq_f16(_sum, _w4, _val, 4); in convolution_pack8_fp16sa_neon()
90 _sum = vfmaq_laneq_f16(_sum, _w5, _val, 5); in convolution_pack8_fp16sa_neon()
91 _sum = vfmaq_laneq_f16(_sum, _w6, _val, 6); in convolution_pack8_fp16sa_neon()
92 _sum = vfmaq_laneq_f16(_sum, _w7, _val, 7); in convolution_pack8_fp16sa_neon()
98 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack8_fp16sa_neon()
[all …]
|
| H A D | convolution_pack4_fp16s.h | 81 _sum = vfmaq_laneq_f32(_sum, _w0, _val, 0); in convolution_pack4_fp16s_neon()
82 _sum = vfmaq_laneq_f32(_sum, _w1, _val, 1); in convolution_pack4_fp16s_neon()
83 _sum = vfmaq_laneq_f32(_sum, _w2, _val, 2); in convolution_pack4_fp16s_neon()
84 _sum = vfmaq_laneq_f32(_sum, _w3, _val, 3); in convolution_pack4_fp16s_neon()
90 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack4_fp16s_neon()
166 _sum = vfma_lane_f16(_sum, _w0, _val, 0); in convolution_pack4_fp16sa_neon()
167 _sum = vfma_lane_f16(_sum, _w1, _val, 1); in convolution_pack4_fp16sa_neon()
168 _sum = vfma_lane_f16(_sum, _w2, _val, 2); in convolution_pack4_fp16sa_neon()
169 _sum = vfma_lane_f16(_sum, _w3, _val, 3); in convolution_pack4_fp16sa_neon()
175 _sum = activation_ps(_sum, activation_type, activation_params); in convolution_pack4_fp16sa_neon()
[all …]
|
| /dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/arm/ |
| H A D | convolution_7x7.h | 273 _sum = vfmaq_laneq_f32(_sum, _r00, _k0123, 0); in conv7x7s1_neon()
274 _sum = vfmaq_laneq_f32(_sum, _r01, _k0123, 1); in conv7x7s1_neon()
275 _sum = vfmaq_laneq_f32(_sum, _r02, _k0123, 2); in conv7x7s1_neon()
276 _sum = vfmaq_laneq_f32(_sum, _r03, _k0123, 3); in conv7x7s1_neon()
277 _sum = vfmaq_laneq_f32(_sum, _r04, _k4567, 0); in conv7x7s1_neon()
278 _sum = vfmaq_laneq_f32(_sum, _r05, _k4567, 1); in conv7x7s1_neon()
279 _sum = vfmaq_laneq_f32(_sum, _r06, _k4567, 2); in conv7x7s1_neon()
290 _sum = vfmaq_laneq_f32(_sum, _r10, _k78910, 0); in conv7x7s1_neon()
291 _sum = vfmaq_laneq_f32(_sum, _r11, _k78910, 1); in conv7x7s1_neon()
292 _sum = vfmaq_laneq_f32(_sum, _r12, _k78910, 2); in conv7x7s1_neon()
[all …]
|
| /dports/misc/ncnn/ncnn-20211208/src/layer/x86/ |
| H A D | convolution1d_x86.cpp | 223 _sum = _mm256_comp_fmadd_ps(_val, _w, _sum); in forward()
270 _sum = _mm256_comp_fmadd_ps(_val0, _w0, _sum); in forward()
272 _sum = _mm256_comp_fmadd_ps(_val1, _w1, _sum); in forward()
372 _sum = _mm_comp_fmadd_ps(_val0, _w0, _sum); in forward()
374 _sum = _mm_comp_fmadd_ps(_val1, _w1, _sum); in forward()
376 _sum = _mm_comp_fmadd_ps(_val2, _w2, _sum); in forward()
378 _sum = _mm_comp_fmadd_ps(_val3, _w3, _sum); in forward()
380 _sum = _mm_comp_fmadd_ps(_val4, _w4, _sum); in forward()
382 _sum = _mm_comp_fmadd_ps(_val5, _w5, _sum); in forward()
384 _sum = _mm_comp_fmadd_ps(_val6, _w6, _sum); in forward()
[all …]
|
| H A D | convolution_2x2_pack8.h | 262 _sum = _mm256_comp_fmadd_ps(_k00, _r00, _sum); in conv2x2s1_pack8_avx()
263 _sum = _mm256_comp_fmadd_ps(_k01, _r01, _sum); in conv2x2s1_pack8_avx()
264 _sum = _mm256_comp_fmadd_ps(_k02, _r02, _sum); in conv2x2s1_pack8_avx()
265 _sum = _mm256_comp_fmadd_ps(_k03, _r03, _sum); in conv2x2s1_pack8_avx()
273 _sum = _mm256_comp_fmadd_ps(_k04, _r04, _sum); in conv2x2s1_pack8_avx()
274 _sum = _mm256_comp_fmadd_ps(_k05, _r05, _sum); in conv2x2s1_pack8_avx()
275 _sum = _mm256_comp_fmadd_ps(_k06, _r06, _sum); in conv2x2s1_pack8_avx()
276 _sum = _mm256_comp_fmadd_ps(_k07, _r07, _sum); in conv2x2s1_pack8_avx()
295 _sum = _mm256_comp_fmadd_ps(_k00, _r00, _sum); in conv2x2s1_pack8_avx()
296 _sum = _mm256_comp_fmadd_ps(_k01, _r01, _sum); in conv2x2s1_pack8_avx()
[all …]
|
| /dports/lang/mono/mono-5.10.1.57/external/rx/Rx/NET/Source/System.Reactive.Linq/Reactive/Linq/Observable/ |
| H A D | Sum.cs | 26 private double _sum; field in System.Reactive.Linq.ObservableImpl.SumDouble._
31 _sum = 0.0; in _()
36 _sum += value; in OnNext()
123 _sum = 0M; in _()
164 private int _sum; field in System.Reactive.Linq.ObservableImpl.SumInt32._
169 _sum = 0; in _()
226 _sum = 0L; in _()
283 _sum = 0.0; in _()
377 _sum = 0M; in _()
424 _sum = 0; in _()
[all …]
|
| /dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/ |
| H A D | convolution_2x2_pack8.h | 262 _sum = _mm256_fmadd_ps(_k00, _r00, _sum); in conv2x2s1_pack8_avx()
263 _sum = _mm256_fmadd_ps(_k01, _r01, _sum); in conv2x2s1_pack8_avx()
264 _sum = _mm256_fmadd_ps(_k02, _r02, _sum); in conv2x2s1_pack8_avx()
265 _sum = _mm256_fmadd_ps(_k03, _r03, _sum); in conv2x2s1_pack8_avx()
273 _sum = _mm256_fmadd_ps(_k04, _r04, _sum); in conv2x2s1_pack8_avx()
274 _sum = _mm256_fmadd_ps(_k05, _r05, _sum); in conv2x2s1_pack8_avx()
275 _sum = _mm256_fmadd_ps(_k06, _r06, _sum); in conv2x2s1_pack8_avx()
276 _sum = _mm256_fmadd_ps(_k07, _r07, _sum); in conv2x2s1_pack8_avx()
295 _sum = _mm256_fmadd_ps(_k00, _r00, _sum); in conv2x2s1_pack8_avx()
296 _sum = _mm256_fmadd_ps(_k01, _r01, _sum); in conv2x2s1_pack8_avx()
[all …]
|
| /dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/ |
| H A D | convolution_2x2_pack8.h | 262 _sum = _mm256_fmadd_ps(_k00, _r00, _sum); in conv2x2s1_pack8_avx()
263 _sum = _mm256_fmadd_ps(_k01, _r01, _sum); in conv2x2s1_pack8_avx()
264 _sum = _mm256_fmadd_ps(_k02, _r02, _sum); in conv2x2s1_pack8_avx()
265 _sum = _mm256_fmadd_ps(_k03, _r03, _sum); in conv2x2s1_pack8_avx()
273 _sum = _mm256_fmadd_ps(_k04, _r04, _sum); in conv2x2s1_pack8_avx()
274 _sum = _mm256_fmadd_ps(_k05, _r05, _sum); in conv2x2s1_pack8_avx()
275 _sum = _mm256_fmadd_ps(_k06, _r06, _sum); in conv2x2s1_pack8_avx()
276 _sum = _mm256_fmadd_ps(_k07, _r07, _sum); in conv2x2s1_pack8_avx()
295 _sum = _mm256_fmadd_ps(_k00, _r00, _sum); in conv2x2s1_pack8_avx()
296 _sum = _mm256_fmadd_ps(_k01, _r01, _sum); in conv2x2s1_pack8_avx()
[all …]
|
| /dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/ |
| H A D | convolution_2x2_pack8.h | 262 _sum = _mm256_fmadd_ps(_k00, _r00, _sum); in conv2x2s1_pack8_avx()
263 _sum = _mm256_fmadd_ps(_k01, _r01, _sum); in conv2x2s1_pack8_avx()
264 _sum = _mm256_fmadd_ps(_k02, _r02, _sum); in conv2x2s1_pack8_avx()
265 _sum = _mm256_fmadd_ps(_k03, _r03, _sum); in conv2x2s1_pack8_avx()
273 _sum = _mm256_fmadd_ps(_k04, _r04, _sum); in conv2x2s1_pack8_avx()
274 _sum = _mm256_fmadd_ps(_k05, _r05, _sum); in conv2x2s1_pack8_avx()
275 _sum = _mm256_fmadd_ps(_k06, _r06, _sum); in conv2x2s1_pack8_avx()
276 _sum = _mm256_fmadd_ps(_k07, _r07, _sum); in conv2x2s1_pack8_avx()
295 _sum = _mm256_fmadd_ps(_k00, _r00, _sum); in conv2x2s1_pack8_avx()
296 _sum = _mm256_fmadd_ps(_k01, _r01, _sum); in conv2x2s1_pack8_avx()
[all …]
|
| /dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/ |
| H A D | convolution_2x2_pack8.h | 262 _sum = _mm256_fmadd_ps(_k00, _r00, _sum); in conv2x2s1_pack8_avx()
263 _sum = _mm256_fmadd_ps(_k01, _r01, _sum); in conv2x2s1_pack8_avx()
264 _sum = _mm256_fmadd_ps(_k02, _r02, _sum); in conv2x2s1_pack8_avx()
265 _sum = _mm256_fmadd_ps(_k03, _r03, _sum); in conv2x2s1_pack8_avx()
273 _sum = _mm256_fmadd_ps(_k04, _r04, _sum); in conv2x2s1_pack8_avx()
274 _sum = _mm256_fmadd_ps(_k05, _r05, _sum); in conv2x2s1_pack8_avx()
275 _sum = _mm256_fmadd_ps(_k06, _r06, _sum); in conv2x2s1_pack8_avx()
276 _sum = _mm256_fmadd_ps(_k07, _r07, _sum); in conv2x2s1_pack8_avx()
295 _sum = _mm256_fmadd_ps(_k00, _r00, _sum); in conv2x2s1_pack8_avx()
296 _sum = _mm256_fmadd_ps(_k01, _r01, _sum); in conv2x2s1_pack8_avx()
[all …]
|