GithubStar/ncnn
1
0
Fork 0
mirror of https://github.com/Tencent/ncnn.git synced 2026-10-19 06:21:39 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
master
ncnn/benchmark/models/efficientnet_b0.param
T
nihui f6f734f44d vulkan int8 kernels (#6751) 
* vulkan: add int8 kernels for core layers
Implement Vulkan int8 paths for convolution, convolutiondepthwise, innerproduct, and gemm with scalar fallback and integer dot product shader branches. Add goal.md and enable existing int8 unit tests for Vulkan coverage.
* enable int8 gpu benchmark
2026-06-17 17:39:49 +08:00

203 lines
20 KiB
Plaintext
Raw Permalink Blame History

7767517
200 225
Input input.1 0 1 data -23330=4,3,224,224,3 0=224 1=224 2=3
Convolution Conv_0 1 1 data 362 -23330=4,3,112,112,32 0=32 1=3 3=2 4=1 5=1 6=864
Swish Mul_3 1 1 362 364 -23330=4,3,112,112,32
ConvolutionDepthWise Conv_4 1 1 364 366 -23330=4,3,112,112,32 0=32 1=3 4=1 5=1 6=288 7=32
Swish Mul_7 1 1 366 368 -23330=4,3,112,112,32
Split splitncnn_0 1 2 368 368_splitncnn_0 368_splitncnn_1 -23330=8,3,112,112,32,3,112,112,32
Pooling GlobalAveragePool_8 1 1 368_splitncnn_1 369 -23330=4,1,32,1,1 0=1 4=1
InnerProduct Conv_9 1 1 369 370 -23330=4,1,8,1,1 0=8 1=1 2=256
Swish Mul_11 1 1 370 372 -23330=4,1,8,1,1
InnerProduct Conv_12 1 1 372 374 -23330=4,1,32,1,1 0=32 1=1 2=256 9=4
BinaryOp Mul_14 2 1 368_splitncnn_0 374 375 -23330=4,3,112,112,32 0=2
Convolution Conv_15 1 1 375 377 -23330=4,3,112,112,16 0=16 1=1 5=1 6=512
Convolution Conv_17 1 1 377 379 -23330=4,3,112,112,96 0=96 1=1 5=1 6=1536
Swish Mul_20 1 1 379 381 -23330=4,3,112,112,96
ConvolutionDepthWise Conv_21 1 1 381 383 -23330=4,3,56,56,96 0=96 1=3 3=2 4=1 5=1 6=864 7=96
Swish Mul_24 1 1 383 385 -23330=4,3,56,56,96
Split splitncnn_1 1 2 385 385_splitncnn_0 385_splitncnn_1 -23330=8,3,56,56,96,3,56,56,96
Pooling GlobalAveragePool_25 1 1 385_splitncnn_1 386 -23330=4,1,96,1,1 0=1 4=1
InnerProduct Conv_26 1 1 386 387 -23330=4,1,4,1,1 0=4 1=1 2=384
Swish Mul_28 1 1 387 389 -23330=4,1,4,1,1
InnerProduct Conv_29 1 1 389 391 -23330=4,1,96,1,1 0=96 1=1 2=384 9=4
BinaryOp Mul_31 2 1 385_splitncnn_0 391 392 -23330=4,3,56,56,96 0=2
Convolution Conv_32 1 1 392 394 -23330=4,3,56,56,24 0=24 1=1 5=1 6=2304
Split splitncnn_2 1 2 394 394_splitncnn_0 394_splitncnn_1 -23330=8,3,56,56,24,3,56,56,24
Convolution Conv_34 1 1 394_splitncnn_1 396 -23330=4,3,56,56,144 0=144 1=1 5=1 6=3456
Swish Mul_37 1 1 396 398 -23330=4,3,56,56,144
ConvolutionDepthWise Conv_38 1 1 398 400 -23330=4,3,56,56,144 0=144 1=3 4=1 5=1 6=1296 7=144
Swish Mul_41 1 1 400 402 -23330=4,3,56,56,144
Split splitncnn_3 1 2 402 402_splitncnn_0 402_splitncnn_1 -23330=8,3,56,56,144,3,56,56,144
Pooling GlobalAveragePool_42 1 1 402_splitncnn_1 403 -23330=4,1,144,1,1 0=1 4=1
InnerProduct Conv_43 1 1 403 404 -23330=4,1,6,1,1 0=6 1=1 2=864
Swish Mul_45 1 1 404 406 -23330=4,1,6,1,1
InnerProduct Conv_46 1 1 406 408 -23330=4,1,144,1,1 0=144 1=1 2=864 9=4
BinaryOp Mul_48 2 1 402_splitncnn_0 408 409 -23330=4,3,56,56,144 0=2
Convolution Conv_49 1 1 409 411 -23330=4,3,56,56,24 0=24 1=1 5=1 6=3456
BinaryOp Add_51 2 1 394_splitncnn_0 411 412 -23330=4,3,56,56,24
Convolution Conv_52 1 1 412 414 -23330=4,3,56,56,144 0=144 1=1 5=1 6=3456
Swish Mul_55 1 1 414 416 -23330=4,3,56,56,144
ConvolutionDepthWise Conv_56 1 1 416 418 -23330=4,3,28,28,144 0=144 1=5 3=2 4=2 5=1 6=3600 7=144
Swish Mul_59 1 1 418 420 -23330=4,3,28,28,144
Split splitncnn_4 1 2 420 420_splitncnn_0 420_splitncnn_1 -23330=8,3,28,28,144,3,28,28,144
Pooling GlobalAveragePool_60 1 1 420_splitncnn_1 421 -23330=4,1,144,1,1 0=1 4=1
InnerProduct Conv_61 1 1 421 422 -23330=4,1,6,1,1 0=6 1=1 2=864
Swish Mul_63 1 1 422 424 -23330=4,1,6,1,1
InnerProduct Conv_64 1 1 424 426 -23330=4,1,144,1,1 0=144 1=1 2=864 9=4
BinaryOp Mul_66 2 1 420_splitncnn_0 426 427 -23330=4,3,28,28,144 0=2
Convolution Conv_67 1 1 427 429 -23330=4,3,28,28,40 0=40 1=1 5=1 6=5760
Split splitncnn_5 1 2 429 429_splitncnn_0 429_splitncnn_1 -23330=8,3,28,28,40,3,28,28,40
Convolution Conv_69 1 1 429_splitncnn_1 431 -23330=4,3,28,28,240 0=240 1=1 5=1 6=9600
Swish Mul_72 1 1 431 433 -23330=4,3,28,28,240
ConvolutionDepthWise Conv_73 1 1 433 435 -23330=4,3,28,28,240 0=240 1=5 4=2 5=1 6=6000 7=240
Swish Mul_76 1 1 435 437 -23330=4,3,28,28,240
Split splitncnn_6 1 2 437 437_splitncnn_0 437_splitncnn_1 -23330=8,3,28,28,240,3,28,28,240
Pooling GlobalAveragePool_77 1 1 437_splitncnn_1 438 -23330=4,1,240,1,1 0=1 4=1
InnerProduct Conv_78 1 1 438 439 -23330=4,1,10,1,1 0=10 1=1 2=2400
Swish Mul_80 1 1 439 441 -23330=4,1,10,1,1
InnerProduct Conv_81 1 1 441 443 -23330=4,1,240,1,1 0=240 1=1 2=2400 9=4
BinaryOp Mul_83 2 1 437_splitncnn_0 443 444 -23330=4,3,28,28,240 0=2
Convolution Conv_84 1 1 444 446 -23330=4,3,28,28,40 0=40 1=1 5=1 6=9600
BinaryOp Add_86 2 1 429_splitncnn_0 446 447 -23330=4,3,28,28,40
Convolution Conv_87 1 1 447 449 -23330=4,3,28,28,240 0=240 1=1 5=1 6=9600
Swish Mul_90 1 1 449 451 -23330=4,3,28,28,240
ConvolutionDepthWise Conv_91 1 1 451 453 -23330=4,3,14,14,240 0=240 1=3 3=2 4=1 5=1 6=2160 7=240
Swish Mul_94 1 1 453 455 -23330=4,3,14,14,240
Split splitncnn_7 1 2 455 455_splitncnn_0 455_splitncnn_1 -23330=8,3,14,14,240,3,14,14,240
Pooling GlobalAveragePool_95 1 1 455_splitncnn_1 456 -23330=4,1,240,1,1 0=1 4=1
InnerProduct Conv_96 1 1 456 457 -23330=4,1,10,1,1 0=10 1=1 2=2400
Swish Mul_98 1 1 457 459 -23330=4,1,10,1,1
InnerProduct Conv_99 1 1 459 461 -23330=4,1,240,1,1 0=240 1=1 2=2400 9=4
BinaryOp Mul_101 2 1 455_splitncnn_0 461 462 -23330=4,3,14,14,240 0=2
Convolution Conv_102 1 1 462 464 -23330=4,3,14,14,80 0=80 1=1 5=1 6=19200
Split splitncnn_8 1 2 464 464_splitncnn_0 464_splitncnn_1 -23330=8,3,14,14,80,3,14,14,80
Convolution Conv_104 1 1 464_splitncnn_1 466 -23330=4,3,14,14,480 0=480 1=1 5=1 6=38400
Swish Mul_107 1 1 466 468 -23330=4,3,14,14,480
ConvolutionDepthWise Conv_108 1 1 468 470 -23330=4,3,14,14,480 0=480 1=3 4=1 5=1 6=4320 7=480
Swish Mul_111 1 1 470 472 -23330=4,3,14,14,480
Split splitncnn_9 1 2 472 472_splitncnn_0 472_splitncnn_1 -23330=8,3,14,14,480,3,14,14,480
Pooling GlobalAveragePool_112 1 1 472_splitncnn_1 473 -23330=4,1,480,1,1 0=1 4=1
InnerProduct Conv_113 1 1 473 474 -23330=4,1,20,1,1 0=20 1=1 2=9600
Swish Mul_115 1 1 474 476 -23330=4,1,20,1,1
InnerProduct Conv_116 1 1 476 478 -23330=4,1,480,1,1 0=480 1=1 2=9600 9=4
BinaryOp Mul_118 2 1 472_splitncnn_0 478 479 -23330=4,3,14,14,480 0=2
Convolution Conv_119 1 1 479 481 -23330=4,3,14,14,80 0=80 1=1 5=1 6=38400
BinaryOp Add_121 2 1 464_splitncnn_0 481 482 -23330=4,3,14,14,80
Split splitncnn_10 1 2 482 482_splitncnn_0 482_splitncnn_1 -23330=8,3,14,14,80,3,14,14,80
Convolution Conv_122 1 1 482_splitncnn_1 484 -23330=4,3,14,14,480 0=480 1=1 5=1 6=38400
Swish Mul_125 1 1 484 486 -23330=4,3,14,14,480
ConvolutionDepthWise Conv_126 1 1 486 488 -23330=4,3,14,14,480 0=480 1=3 4=1 5=1 6=4320 7=480
Swish Mul_129 1 1 488 490 -23330=4,3,14,14,480
Split splitncnn_11 1 2 490 490_splitncnn_0 490_splitncnn_1 -23330=8,3,14,14,480,3,14,14,480
Pooling GlobalAveragePool_130 1 1 490_splitncnn_1 491 -23330=4,1,480,1,1 0=1 4=1
InnerProduct Conv_131 1 1 491 492 -23330=4,1,20,1,1 0=20 1=1 2=9600
Swish Mul_133 1 1 492 494 -23330=4,1,20,1,1
InnerProduct Conv_134 1 1 494 496 -23330=4,1,480,1,1 0=480 1=1 2=9600 9=4
BinaryOp Mul_136 2 1 490_splitncnn_0 496 497 -23330=4,3,14,14,480 0=2
Convolution Conv_137 1 1 497 499 -23330=4,3,14,14,80 0=80 1=1 5=1 6=38400
BinaryOp Add_139 2 1 482_splitncnn_0 499 500 -23330=4,3,14,14,80
Convolution Conv_140 1 1 500 502 -23330=4,3,14,14,480 0=480 1=1 5=1 6=38400
Swish Mul_143 1 1 502 504 -23330=4,3,14,14,480
ConvolutionDepthWise Conv_144 1 1 504 506 -23330=4,3,14,14,480 0=480 1=5 4=2 5=1 6=12000 7=480
Swish Mul_147 1 1 506 508 -23330=4,3,14,14,480
Split splitncnn_12 1 2 508 508_splitncnn_0 508_splitncnn_1 -23330=8,3,14,14,480,3,14,14,480
Pooling GlobalAveragePool_148 1 1 508_splitncnn_1 509 -23330=4,1,480,1,1 0=1 4=1
InnerProduct Conv_149 1 1 509 510 -23330=4,1,20,1,1 0=20 1=1 2=9600
Swish Mul_151 1 1 510 512 -23330=4,1,20,1,1
InnerProduct Conv_152 1 1 512 514 -23330=4,1,480,1,1 0=480 1=1 2=9600 9=4
BinaryOp Mul_154 2 1 508_splitncnn_0 514 515 -23330=4,3,14,14,480 0=2
Convolution Conv_155 1 1 515 517 -23330=4,3,14,14,112 0=112 1=1 5=1 6=53760
Split splitncnn_13 1 2 517 517_splitncnn_0 517_splitncnn_1 -23330=8,3,14,14,112,3,14,14,112
Convolution Conv_157 1 1 517_splitncnn_1 519 -23330=4,3,14,14,672 0=672 1=1 5=1 6=75264
Swish Mul_160 1 1 519 521 -23330=4,3,14,14,672
ConvolutionDepthWise Conv_161 1 1 521 523 -23330=4,3,14,14,672 0=672 1=5 4=2 5=1 6=16800 7=672
Swish Mul_164 1 1 523 525 -23330=4,3,14,14,672
Split splitncnn_14 1 2 525 525_splitncnn_0 525_splitncnn_1 -23330=8,3,14,14,672,3,14,14,672
Pooling GlobalAveragePool_165 1 1 525_splitncnn_1 526 -23330=4,1,672,1,1 0=1 4=1
InnerProduct Conv_166 1 1 526 527 -23330=4,1,28,1,1 0=28 1=1 2=18816
Swish Mul_168 1 1 527 529 -23330=4,1,28,1,1
InnerProduct Conv_169 1 1 529 531 -23330=4,1,672,1,1 0=672 1=1 2=18816 9=4
BinaryOp Mul_171 2 1 525_splitncnn_0 531 532 -23330=4,3,14,14,672 0=2
Convolution Conv_172 1 1 532 534 -23330=4,3,14,14,112 0=112 1=1 5=1 6=75264
BinaryOp Add_174 2 1 517_splitncnn_0 534 535 -23330=4,3,14,14,112
Split splitncnn_15 1 2 535 535_splitncnn_0 535_splitncnn_1 -23330=8,3,14,14,112,3,14,14,112
Convolution Conv_175 1 1 535_splitncnn_1 537 -23330=4,3,14,14,672 0=672 1=1 5=1 6=75264
Swish Mul_178 1 1 537 539 -23330=4,3,14,14,672
ConvolutionDepthWise Conv_179 1 1 539 541 -23330=4,3,14,14,672 0=672 1=5 4=2 5=1 6=16800 7=672
Swish Mul_182 1 1 541 543 -23330=4,3,14,14,672
Split splitncnn_16 1 2 543 543_splitncnn_0 543_splitncnn_1 -23330=8,3,14,14,672,3,14,14,672
Pooling GlobalAveragePool_183 1 1 543_splitncnn_1 544 -23330=4,1,672,1,1 0=1 4=1
InnerProduct Conv_184 1 1 544 545 -23330=4,1,28,1,1 0=28 1=1 2=18816
Swish Mul_186 1 1 545 547 -23330=4,1,28,1,1
InnerProduct Conv_187 1 1 547 549 -23330=4,1,672,1,1 0=672 1=1 2=18816 9=4
BinaryOp Mul_189 2 1 543_splitncnn_0 549 550 -23330=4,3,14,14,672 0=2
Convolution Conv_190 1 1 550 552 -23330=4,3,14,14,112 0=112 1=1 5=1 6=75264
BinaryOp Add_192 2 1 535_splitncnn_0 552 553 -23330=4,3,14,14,112
Convolution Conv_193 1 1 553 555 -23330=4,3,14,14,672 0=672 1=1 5=1 6=75264
Swish Mul_196 1 1 555 557 -23330=4,3,14,14,672
ConvolutionDepthWise Conv_197 1 1 557 559 -23330=4,3,7,7,672 0=672 1=5 3=2 4=2 5=1 6=16800 7=672
Swish Mul_200 1 1 559 561 -23330=4,3,7,7,672
Split splitncnn_17 1 2 561 561_splitncnn_0 561_splitncnn_1 -23330=8,3,7,7,672,3,7,7,672
Pooling GlobalAveragePool_201 1 1 561_splitncnn_1 562 -23330=4,1,672,1,1 0=1 4=1
InnerProduct Conv_202 1 1 562 563 -23330=4,1,28,1,1 0=28 1=1 2=18816
Swish Mul_204 1 1 563 565 -23330=4,1,28,1,1
InnerProduct Conv_205 1 1 565 567 -23330=4,1,672,1,1 0=672 1=1 2=18816 9=4
BinaryOp Mul_207 2 1 561_splitncnn_0 567 568 -23330=4,3,7,7,672 0=2
Convolution Conv_208 1 1 568 570 -23330=4,3,7,7,192 0=192 1=1 5=1 6=129024
Split splitncnn_18 1 2 570 570_splitncnn_0 570_splitncnn_1 -23330=8,3,7,7,192,3,7,7,192
Convolution Conv_210 1 1 570_splitncnn_1 572 -23330=4,3,7,7,1152 0=1152 1=1 5=1 6=221184
Swish Mul_213 1 1 572 574 -23330=4,3,7,7,1152
ConvolutionDepthWise Conv_214 1 1 574 576 -23330=4,3,7,7,1152 0=1152 1=5 4=2 5=1 6=28800 7=1152
Swish Mul_217 1 1 576 578 -23330=4,3,7,7,1152
Split splitncnn_19 1 2 578 578_splitncnn_0 578_splitncnn_1 -23330=8,3,7,7,1152,3,7,7,1152
Pooling GlobalAveragePool_218 1 1 578_splitncnn_1 579 -23330=4,1,1152,1,1 0=1 4=1
InnerProduct Conv_219 1 1 579 580 -23330=4,1,48,1,1 0=48 1=1 2=55296
Swish Mul_221 1 1 580 582 -23330=4,1,48,1,1
InnerProduct Conv_222 1 1 582 584 -23330=4,1,1152,1,1 0=1152 1=1 2=55296 9=4
BinaryOp Mul_224 2 1 578_splitncnn_0 584 585 -23330=4,3,7,7,1152 0=2
Convolution Conv_225 1 1 585 587 -23330=4,3,7,7,192 0=192 1=1 5=1 6=221184
BinaryOp Add_227 2 1 570_splitncnn_0 587 588 -23330=4,3,7,7,192
Split splitncnn_20 1 2 588 588_splitncnn_0 588_splitncnn_1 -23330=8,3,7,7,192,3,7,7,192
Convolution Conv_228 1 1 588_splitncnn_1 590 -23330=4,3,7,7,1152 0=1152 1=1 5=1 6=221184
Swish Mul_231 1 1 590 592 -23330=4,3,7,7,1152
ConvolutionDepthWise Conv_232 1 1 592 594 -23330=4,3,7,7,1152 0=1152 1=5 4=2 5=1 6=28800 7=1152
Swish Mul_235 1 1 594 596 -23330=4,3,7,7,1152
Split splitncnn_21 1 2 596 596_splitncnn_0 596_splitncnn_1 -23330=8,3,7,7,1152,3,7,7,1152
Pooling GlobalAveragePool_236 1 1 596_splitncnn_1 597 -23330=4,1,1152,1,1 0=1 4=1
InnerProduct Conv_237 1 1 597 598 -23330=4,1,48,1,1 0=48 1=1 2=55296
Swish Mul_239 1 1 598 600 -23330=4,1,48,1,1
InnerProduct Conv_240 1 1 600 602 -23330=4,1,1152,1,1 0=1152 1=1 2=55296 9=4
BinaryOp Mul_242 2 1 596_splitncnn_0 602 603 -23330=4,3,7,7,1152 0=2
Convolution Conv_243 1 1 603 605 -23330=4,3,7,7,192 0=192 1=1 5=1 6=221184
BinaryOp Add_245 2 1 588_splitncnn_0 605 606 -23330=4,3,7,7,192
Split splitncnn_22 1 2 606 606_splitncnn_0 606_splitncnn_1 -23330=8,3,7,7,192,3,7,7,192
Convolution Conv_246 1 1 606_splitncnn_1 608 -23330=4,3,7,7,1152 0=1152 1=1 5=1 6=221184
Swish Mul_249 1 1 608 610 -23330=4,3,7,7,1152
ConvolutionDepthWise Conv_250 1 1 610 612 -23330=4,3,7,7,1152 0=1152 1=5 4=2 5=1 6=28800 7=1152
Swish Mul_253 1 1 612 614 -23330=4,3,7,7,1152
Split splitncnn_23 1 2 614 614_splitncnn_0 614_splitncnn_1 -23330=8,3,7,7,1152,3,7,7,1152
Pooling GlobalAveragePool_254 1 1 614_splitncnn_1 615 -23330=4,1,1152,1,1 0=1 4=1
InnerProduct Conv_255 1 1 615 616 -23330=4,1,48,1,1 0=48 1=1 2=55296
Swish Mul_257 1 1 616 618 -23330=4,1,48,1,1
InnerProduct Conv_258 1 1 618 620 -23330=4,1,1152,1,1 0=1152 1=1 2=55296 9=4
BinaryOp Mul_260 2 1 614_splitncnn_0 620 621 -23330=4,3,7,7,1152 0=2
Convolution Conv_261 1 1 621 623 -23330=4,3,7,7,192 0=192 1=1 5=1 6=221184
BinaryOp Add_263 2 1 606_splitncnn_0 623 624 -23330=4,3,7,7,192
Convolution Conv_264 1 1 624 626 -23330=4,3,7,7,1152 0=1152 1=1 5=1 6=221184
Swish Mul_267 1 1 626 628 -23330=4,3,7,7,1152
ConvolutionDepthWise Conv_268 1 1 628 630 -23330=4,3,7,7,1152 0=1152 1=3 4=1 5=1 6=10368 7=1152
Swish Mul_271 1 1 630 632 -23330=4,3,7,7,1152
Split splitncnn_24 1 2 632 632_splitncnn_0 632_splitncnn_1 -23330=8,3,7,7,1152,3,7,7,1152
Pooling GlobalAveragePool_272 1 1 632_splitncnn_1 633 -23330=4,1,1152,1,1 0=1 4=1
InnerProduct Conv_273 1 1 633 634 -23330=4,1,48,1,1 0=48 1=1 2=55296
Swish Mul_275 1 1 634 636 -23330=4,1,48,1,1
InnerProduct Conv_276 1 1 636 638 -23330=4,1,1152,1,1 0=1152 1=1 2=55296 9=4
BinaryOp Mul_278 2 1 632_splitncnn_0 638 639 -23330=4,3,7,7,1152 0=2
Convolution Conv_279 1 1 639 641 -23330=4,3,7,7,320 0=320 1=1 5=1 6=368640
Convolution Conv_281 1 1 641 643 -23330=4,3,7,7,1280 0=1280 1=1 5=1 6=409600
Swish Mul_284 1 1 643 645 -23330=4,3,7,7,1280
Pooling GlobalAveragePool_285 1 1 645 654 -23330=4,1,1280,1,1 0=1 4=1
InnerProduct Gemm_292 1 1 654 655 -23330=4,1,1000,1,1 0=1000 1=1 2=1280000
Softmax prob 1 1 655 output -23330=4,1,1000,1,1
Reference in New Issue View Git Blame Copy Permalink