Files
Raptor/validation/operations/validation_results.csv
T
NiccoloN db8d1c1707
Validate Operations / validate-operations (push) Has been cancelled
better throughput in pipeline mode
2026-08-19 16:03:52 +02:00

32 KiB

1OperationArchResult (l)Result (t)Compile (l)Host mem (l)Cores mem (l)Cores (l)Xbars (l)Latency (l)Power (l)Energy (l)Compile (t)Host mem (t)Cores mem (t)Cores (t)Xbars (t)Avg latency (t)Throughput (t)Avg power (t)Avg energy (t)
2add/after_gemmarch-aPASSPASS0.056 s0.01 MiB0.01 MiB540.01 ms104.70 mW815012.96 pJ0.043 s0.01 MiB0.01 MiB64218000.00 samples/s0.00 ms107.94 mW570766.12 pJ/it
3add/basicarch-aPASSPASS0.053 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.041 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
4add/broadcast_rowarch-aPASSPASS0.052 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.037 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
5add/channel_broadcast_1024arch-aPASSPASS0.052 s0.02 MiB0.01 MiB100.01 ms78.12 mW540030.00 pJ0.036 s0.02 MiB0.01 MiB10145000.00 samples/s0.01 ms2.11 mW13388.67 pJ/it
6add/leading_dimension_broadcastarch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.038 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
7concat/channel_axisarch-aPASSPASS0.047 s0.00 MiB0.00 MiB100.00 ms78.16 mW35718.00 pJ0.034 s0.00 MiB0.00 MiB102200000.00 samples/s0.00 ms2.16 mW934.67 pJ/it
8concat/negative_axisarch-aPASSPASS0.046 s0.00 MiB0.00 MiB100.00 ms78.09 mW81450.00 pJ0.038 s0.00 MiB0.00 MiB10961000.00 samples/s0.00 ms2.09 mW2108.00 pJ/it
9concat/three_inputs_channel_axisarch-aPASSPASS0.056 s0.00 MiB0.00 MiB100.00 ms78.15 mW50328.00 pJ0.035 s0.00 MiB0.00 MiB101560000.00 samples/s0.00 ms2.15 mW1332.67 pJ/it
10conv/batch_2arch-aPASSPASS0.057 s0.00 MiB0.00 MiB220.01 ms82.62 mW1131451.48 pJ0.044 s0.00 MiB0.01 MiB42147000.00 samples/s0.01 ms92.90 mW669920.48 pJ/it
11conv/batch_4_pointwisearch-aPASSPASS0.055 s0.00 MiB0.01 MiB540.00 ms116.08 mW456420.96 pJ0.043 s0.01 MiB0.01 MiB54242000.00 samples/s0.00 ms69.62 mW291187.04 pJ/it
12conv/depthwise_1024_channelsarch-aPASSPASS0.082 s0.19 MiB0.38 MiB1291280.22 ms178.45 mW39393966.72 pJ0.117 s0.38 MiB0.46 MiB451184930.00 samples/s0.20 ms144.34 mW33005602.67 pJ/it
13conv/depthwise_groupedarch-aPASSPASS0.055 s0.01 MiB0.00 MiB540.01 ms107.78 mW671878.96 pJ0.042 s0.01 MiB0.00 MiB74418000.00 samples/s0.00 ms168.64 mW479471.12 pJ/it
14conv/dilated_3x3arch-aPASSPASS0.057 s0.01 MiB0.01 MiB1090.01 ms118.77 mW1034819.16 pJ0.057 s0.01 MiB0.01 MiB129104000.00 samples/s0.01 ms155.40 mW1574973.57 pJ/it
15conv/dynamicarch-aPASSPASS0.062 s0.00 MiB0.00 MiB500.00 ms92.28 mW169336.00 pJ0.044 s0.00 MiB0.00 MiB60778000.00 samples/s0.00 ms86.62 mW124092.33 pJ/it
16conv/explicit_paddingarch-aPASSPASS0.053 s0.01 MiB0.02 MiB17160.01 ms145.34 mW1454397.84 pJ0.048 s0.01 MiB0.02 MiB1916179000.00 samples/s0.01 ms201.80 mW1234440.20 pJ/it
17conv/grouped_many_groupsarch-aPASSPASS0.474 s0.05 MiB0.09 MiB65640.18 ms142.21 mW25867112.36 pJ0.476 s0.08 MiB0.73 MiB87643660.00 samples/s0.27 ms97.46 mW30277556.57 pJ/it
18conv/grouped_two_groupsarch-aPASSPASS0.057 s0.00 MiB0.00 MiB320.01 ms101.46 mW543914.48 pJ0.047 s0.00 MiB0.01 MiB92378000.00 samples/s0.00 ms105.40 mW353700.73 pJ/it
19conv/huge_pointwise_1024arch-aPASSPASS0.151 s0.01 MiB0.11 MiB73640.02 ms249.58 mW3895759.36 pJ0.163 s0.08 MiB0.10 MiB526419200.00 samples/s0.05 ms163.09 mW8722111.37 pJ/it
20conv/huge_pointwise_1024_dynamicarch-aPASSPASS0.080 s8.04 MiB12.61 MiB16802.63 ms169.52 mW445489032.00 pJ0.224 s12.75 MiB6.82 MiB450188.00 samples/s5.31 ms134.20 mW746263826.70 pJ/it
21conv/input_224_7x7_stride2arch-aPASSPASS0.759 s24.14 MiB61.87 MiB16816938.41 ms185.26 mW7116544212.12 pJ1.060 s51.25 MiB67.85 MiB458424.70 samples/s40.56 ms148.32 mW6561548886.00 pJ/it
22conv/kernel_2x2arch-aPASSPASS0.061 s0.00 MiB0.00 MiB110.00 ms83.83 mW360568.24 pJ0.046 s0.00 MiB0.00 MiB31356000.00 samples/s0.00 ms93.82 mW298919.07 pJ/it
23conv/kernel_3x3arch-aPASSPASS0.061 s0.01 MiB0.01 MiB1090.01 ms123.80 mW889640.16 pJ0.046 s0.01 MiB0.01 MiB129271000.00 samples/s0.00 ms195.49 mW787478.85 pJ/it
24conv/kernel_equals_input_spatialarch-aPASSPASS0.052 s0.00 MiB0.00 MiB220.00 ms89.61 mW415689.48 pJ0.041 s0.00 MiB0.00 MiB42376000.00 samples/s0.00 ms104.42 mW305239.85 pJ/it
25conv/large_input_channels_1x1arch-aPASSPASS0.085 s0.01 MiB0.02 MiB980.01 ms117.84 mW900569.92 pJ0.081 s0.02 MiB0.02 MiB108135000.00 samples/s0.01 ms113.25 mW910683.04 pJ/it
26conv/large_output_channels_1x1arch-aPASSPASS0.095 s0.01 MiB0.02 MiB1780.01 ms128.44 mW1139415.92 pJ0.078 s0.02 MiB0.02 MiB18893600.00 samples/s0.01 ms151.83 mW1755770.60 pJ/it
27conv/large_spatialarch-aPASSPASS0.061 s0.01 MiB0.04 MiB37360.02 ms172.07 mW2928344.64 pJ0.061 s0.01 MiB0.04 MiB393684200.00 samples/s0.01 ms208.30 mW2603711.62 pJ/it
28conv/multi_channelarch-aPASSPASS0.054 s0.00 MiB0.00 MiB430.01 ms105.68 mW685040.72 pJ0.050 s0.00 MiB0.00 MiB43140000.00 samples/s0.01 ms54.54 mW393755.39 pJ/it
29conv/non_square_kernel_1x3arch-aPASSPASS0.056 s0.00 MiB0.00 MiB320.01 ms99.35 mW679752.48 pJ0.044 s0.00 MiB0.00 MiB32140000.00 samples/s0.01 ms51.01 mW367557.81 pJ/it
30conv/non_square_kernel_3x1arch-aPASSPASS0.053 s0.00 MiB0.00 MiB320.01 ms95.89 mW1292976.48 pJ0.045 s0.00 MiB0.00 MiB3272200.00 samples/s0.01 ms47.79 mW664683.81 pJ/it
31conv/non_uniform_stridearch-aPASSPASS0.056 s0.00 MiB0.00 MiB430.01 ms104.05 mW790874.72 pJ0.044 s0.00 MiB0.00 MiB43126000.00 samples/s0.01 ms53.56 mW429978.05 pJ/it
32conv/output_channel_grouping_minimalarch-aPASSPASS0.080 s0.10 MiB0.34 MiB1311280.26 ms170.73 mW44125916.72 pJ0.148 s0.28 MiB0.96 MiB87842630.00 samples/s0.38 ms136.74 mW58542917.01 pJ/it
33conv/pointwise_1x1arch-aPASSPASS0.054 s0.00 MiB0.00 MiB110.01 ms80.24 mW987244.24 pJ0.041 s0.00 MiB0.00 MiB31131000.00 samples/s0.01 ms89.08 mW719413.57 pJ/it
34conv/pointwise_tiled_chainarch-aPASSPASS0.642 s0.01 MiB0.04 MiB20800.04 ms153.90 mW6443957.20 pJ0.620 s0.06 MiB0.08 MiB228016400.00 samples/s0.06 ms186.69 mW12410041.37 pJ/it
35conv/real_asymmetric_paddingarch-aPASSPASS0.057 s0.01 MiB0.03 MiB29280.01 ms153.67 mW2221606.72 pJ0.055 s0.01 MiB0.03 MiB3128105000.00 samples/s0.01 ms204.35 mW2058223.49 pJ/it
36conv/relu_conv_storearch-aPASSPASS0.085 s0.16 MiB0.67 MiB1681840.56 ms183.08 mW103057723.80 pJ0.209 s0.37 MiB0.58 MiB60581500.00 samples/s0.67 ms146.73 mW101291048.70 pJ/it
37conv/same_lower_3x3arch-aPASSPASS0.060 s0.01 MiB0.02 MiB26250.01 ms166.15 mW2215009.00 pJ0.054 s0.01 MiB0.03 MiB2825119000.00 samples/s0.01 ms204.48 mW1837219.40 pJ/it
38conv/same_padding_3x3arch-aPASSPASS0.058 s0.01 MiB0.02 MiB26250.01 ms166.15 mW2215009.00 pJ0.056 s0.01 MiB0.03 MiB2825119000.00 samples/s0.01 ms204.48 mW1837219.40 pJ/it
39conv/strategy_depthwise_16arch-aPASSPASS0.093 s0.06 MiB0.35 MiB1681680.34 ms197.94 mW66331479.08 pJ0.257 s0.20 MiB0.17 MiB45842650.00 samples/s0.38 ms153.71 mW60322816.49 pJ/it
40conv/strategy_input_k_tiledarch-aPASSPASS0.082 s0.08 MiB0.27 MiB1091080.35 ms170.81 mW60422605.92 pJ0.100 s0.22 MiB0.28 MiB45904250.00 samples/s0.24 ms143.52 mW36750587.75 pJ/it
41conv/strategy_output_channel_tiledarch-aPASSPASS0.073 s0.03 MiB0.16 MiB74720.09 ms155.74 mW14244739.28 pJ0.110 s0.13 MiB0.22 MiB81729220.00 samples/s0.11 ms145.73 mW18577796.14 pJ/it
42conv/strategy_streamed_packedarch-aPASSPASS0.155 s3.34 MiB7.89 MiB1681689.35 ms179.86 mW1682364509.56 pJ0.357 s5.32 MiB7.79 MiB4342113.00 samples/s8.87 ms61.68 mW558465684.90 pJ/it
43conv/strategy_streamed_patcharch-aPASSPASS0.115 s0.34 MiB1.32 MiB1681681.90 ms181.91 mW346476645.64 pJ0.299 s0.82 MiB1.21 MiB4342501.00 samples/s1.99 ms62.44 mW125148059.00 pJ/it
44conv/strategy_tiled_2darch-aPASSPASS0.111 s0.11 MiB0.44 MiB1681680.42 ms182.13 mW75690907.84 pJ0.219 s0.36 MiB0.46 MiB471444070.00 samples/s0.25 ms155.26 mW43400768.51 pJ/it
45conv/stride_2arch-aPASSPASS0.056 s0.01 MiB0.00 MiB540.01 ms110.78 mW580154.96 pJ0.043 s0.01 MiB0.00 MiB74476000.00 samples/s0.00 ms175.93 mW424103.12 pJ/it
46conv/with_bias_3x3arch-aPASSPASS0.059 s0.00 MiB0.01 MiB430.01 ms104.16 mW776220.72 pJ0.046 s0.00 MiB0.01 MiB43133000.00 samples/s0.01 ms53.85 mW416288.72 pJ/it
47conv/with_constantarch-aPASSPASS0.054 s0.00 MiB0.00 MiB110.01 ms81.74 mW541270.24 pJ0.043 s0.00 MiB0.00 MiB41231000.00 samples/s0.00 ms133.09 mW655848.91 pJ/it
48conv/without_kernel_shape_attrarch-aPASSPASS0.053 s0.01 MiB0.01 MiB1090.01 ms123.80 mW889640.16 pJ0.047 s0.01 MiB0.01 MiB129271000.00 samples/s0.00 ms195.49 mW787478.85 pJ/it
49conv/yolo11n_depthwise_headarch-aPASSPASS1.709 s8.66 MiB34.24 MiB16825542.70 ms200.52 mW8562452412.00 pJ2.373 s27.15 MiB20.31 MiB8721420.60 samples/s48.55 ms157.12 mW8007922821.00 pJ/it
50conv/yolo11n_heavyarch-aPASSPASS0.519 s4.82 MiB19.10 MiB1618008.53 ms350.87 mW2994683017.00 pJ1.007 s11.06 MiB13.87 MiB8542079.10 samples/s12.64 ms218.17 mW2857451109.00 pJ/it
51conv/yolo11n_stemarch-aPASSPASS0.893 s12.86 MiB37.59 MiB16848814.24 ms301.23 mW4289558246.00 pJ1.374 s25.19 MiB21.24 MiB8512644.60 samples/s22.42 ms176.88 mW4028789243.00 pJ/it
52div/after_gemmarch-aPASSPASS0.053 s0.01 MiB0.01 MiB540.01 ms104.70 mW815012.96 pJ0.045 s0.01 MiB0.01 MiB64218000.00 samples/s0.00 ms107.94 mW570766.12 pJ/it
53div/basicarch-aPASSPASS0.051 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.036 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
54div/channel_broadcast_1024arch-aPASSPASS0.049 s0.02 MiB0.01 MiB100.01 ms78.12 mW540030.00 pJ0.039 s0.02 MiB0.01 MiB10145000.00 samples/s0.01 ms2.11 mW13388.67 pJ/it
55div/leading_dimension_broadcastarch-aPASSPASS0.050 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.040 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
56div/runtime_scalar_rhsarch-aPASSPASS0.053 s0.02 MiB0.01 MiB100.01 ms78.12 mW540030.00 pJ0.040 s0.02 MiB0.01 MiB10145000.00 samples/s0.01 ms2.11 mW13388.67 pJ/it
57div/scalar_constantarch-aPASSPASS0.052 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.036 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
58gather/3d_input_axis1arch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.08 mW45990.00 pJ0.038 s0.00 MiB0.00 MiB101700000.00 samples/s0.00 ms2.08 mW1174.67 pJ/it
59gather/axis0_matrix_indicesarch-aPASSPASS0.052 s0.00 MiB0.00 MiB100.00 ms78.07 mW54414.00 pJ0.039 s0.00 MiB0.00 MiB101440000.00 samples/s0.00 ms2.07 mW1390.67 pJ/it
60gather/axis1arch-aPASSPASS0.050 s0.00 MiB0.00 MiB100.00 ms78.06 mW62526.00 pJ0.036 s0.00 MiB0.00 MiB101250000.00 samples/s0.00 ms2.06 mW1598.67 pJ/it
61gather/negative_axisarch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.03 mW112134.00 pJ0.039 s0.00 MiB0.00 MiB10697000.00 samples/s0.00 ms2.03 mW2870.67 pJ/it
62gather/negative_indicesarch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.13 mW29376.00 pJ0.041 s0.00 MiB0.00 MiB102670000.00 samples/s0.00 ms2.12 mW748.67 pJ/it
63gemm/alpha_betaarch-aPASSPASS0.056 s0.01 MiB0.01 MiB540.01 ms105.27 mW784908.96 pJ0.050 s0.01 MiB0.01 MiB64212000.00 samples/s0.00 ms107.78 mW574589.95 pJ/it
64gemm/bias_rank2_broadcastarch-aPASSPASS0.056 s0.00 MiB0.01 MiB540.01 ms105.98 mW749484.96 pJ0.043 s0.01 MiB0.01 MiB64229000.00 samples/s0.00 ms109.50 mW540708.12 pJ/it
65gemm/dynamicarch-aPASSPASS0.052 s0.00 MiB0.00 MiB500.00 ms91.48 mW221475.00 pJ0.044 s0.00 MiB0.00 MiB50489000.00 samples/s0.00 ms44.34 mW93754.67 pJ/it
66gemm/dynamic_alphaarch-aPASSPASS0.052 s0.00 MiB0.00 MiB500.00 ms91.42 mW298198.00 pJ0.041 s0.00 MiB0.00 MiB50464000.00 samples/s0.00 ms44.39 mW105291.67 pJ/it
67gemm/dynamic_betaarch-aPASSPASS0.052 s0.00 MiB0.00 MiB500.00 ms91.32 mW397230.00 pJ0.042 s0.00 MiB0.00 MiB50247000.00 samples/s0.00 ms20.21 mW81901.75 pJ/it
68gemm/dynamic_biasarch-aPASSPASS0.057 s0.00 MiB0.00 MiB500.00 ms91.45 mW243703.00 pJ0.046 s0.00 MiB0.00 MiB50422000.00 samples/s0.00 ms20.28 mW48009.75 pJ/it
69gemm/dynamic_bias_alpha_betaarch-aPASSPASS0.054 s0.00 MiB0.00 MiB500.01 ms91.28 mW513811.00 pJ0.043 s0.00 MiB0.00 MiB50188000.00 samples/s0.01 ms20.20 mW107673.75 pJ/it
70gemm/dynamic_transpose_barch-aPASSPASS0.052 s0.00 MiB0.00 MiB500.00 ms91.38 mW118883.00 pJ0.040 s0.00 MiB0.00 MiB50803000.00 samples/s0.00 ms44.55 mW58232.00 pJ/it
71gemm/huge_1024arch-aPASSPASS0.149 s0.01 MiB0.10 MiB73640.02 ms215.07 mW3767010.36 pJ0.160 s0.05 MiB0.09 MiB516426400.00 samples/s0.04 ms135.13 mW5670462.59 pJ/it
72gemm/largearch-aPASSPASS0.058 s0.02 MiB0.03 MiB17160.01 ms140.15 mW1573768.84 pJ0.050 s0.03 MiB0.03 MiB171678500.00 samples/s0.01 ms79.60 mW1008067.12 pJ/it
73gemm/large_k_small_narch-aPASSPASS0.088 s0.01 MiB0.01 MiB980.00 ms133.53 mW633217.92 pJ0.082 s0.01 MiB0.01 MiB98182000.00 samples/s0.01 ms84.31 mW476982.66 pJ/it
74gemm/non_squarearch-aPASSPASS0.059 s0.00 MiB0.01 MiB540.00 ms118.96 mW419565.96 pJ0.043 s0.01 MiB0.01 MiB54242000.00 samples/s0.00 ms71.16 mW302182.45 pJ/it
75gemm/scalar_biasarch-aPASSPASS0.055 s0.00 MiB0.01 MiB540.01 ms105.98 mW749484.96 pJ0.045 s0.01 MiB0.01 MiB64229000.00 samples/s0.00 ms109.50 mW540708.12 pJ/it
76gemm/smallarch-aPASSPASS0.055 s0.00 MiB0.00 MiB220.00 ms90.14 mW398436.48 pJ0.043 s0.00 MiB0.00 MiB42376000.00 samples/s0.00 ms105.00 mW297577.19 pJ/it
77gemm/small_k_large_narch-aPASSPASS0.090 s0.01 MiB0.02 MiB1780.01 ms131.01 mW1043061.92 pJ0.082 s0.02 MiB0.02 MiB18892700.00 samples/s0.01 ms152.38 mW1742739.72 pJ/it
78gemm/square_weightsarch-aPASSPASS0.073 s0.03 MiB0.08 MiB42400.02 ms151.77 mW3284393.60 pJ0.075 s0.07 MiB0.09 MiB444025700.00 samples/s0.04 ms155.80 mW6344327.95 pJ/it
79gemm/transpose_aarch-aPASSPASS0.056 s0.00 MiB0.01 MiB540.01 ms109.14 mW628868.96 pJ0.047 s0.01 MiB0.01 MiB64290000.00 samples/s0.00 ms115.23 mW456854.62 pJ/it
80gemm/transpose_a_and_barch-aPASSPASS0.054 s0.00 MiB0.01 MiB540.01 ms109.14 mW628868.96 pJ0.044 s0.01 MiB0.01 MiB64290000.00 samples/s0.00 ms115.23 mW456854.62 pJ/it
81gemm/transpose_barch-aPASSPASS0.056 s0.00 MiB0.01 MiB540.00 ms118.96 mW419565.96 pJ0.045 s0.01 MiB0.01 MiB54242000.00 samples/s0.00 ms71.16 mW302182.45 pJ/it
82gemm/transpose_b_with_biasarch-aPASSPASS0.057 s0.01 MiB0.01 MiB540.01 ms110.55 mW557818.96 pJ0.046 s0.01 MiB0.01 MiB54218000.00 samples/s0.00 ms67.31 mW333372.79 pJ/it
83gemm/with_biasarch-aPASSPASS0.057 s0.01 MiB0.01 MiB540.01 ms108.77 mW604966.96 pJ0.043 s0.01 MiB0.01 MiB54203000.00 samples/s0.00 ms66.54 mW341027.79 pJ/it
84gemv/all_constantarch-aPASSPASS0.053 s0.00 MiB0.00 MiB000.00 ms2.00 mW0.00 pJ0.039 s0.00 MiB0.00 MiB000.00 samples/s0.00 ms2.00 mW0.00 pJ/it
85gemv/constant_weightarch-aPASSPASS0.065 s0.00 MiB0.01 MiB640.01 ms111.15 mW573535.96 pJ0.051 s0.01 MiB0.01 MiB84263000.00 samples/s0.00 ms154.40 mW641346.96 pJ/it
86gemv/non_uniform_biasarch-aPASSPASS0.062 s0.00 MiB0.01 MiB640.01 ms109.81 mW609463.96 pJ0.051 s0.01 MiB0.01 MiB84243000.00 samples/s0.00 ms152.55 mW697203.20 pJ/it
87gemv/scalar_biasarch-aPASSPASS0.061 s0.00 MiB0.01 MiB640.01 ms109.81 mW609463.96 pJ0.052 s0.01 MiB0.01 MiB84243000.00 samples/s0.00 ms152.55 mW697203.20 pJ/it
88gemv/uniform_biasarch-aPASSPASS0.066 s0.00 MiB0.01 MiB640.01 ms109.81 mW609463.96 pJ0.049 s0.01 MiB0.01 MiB84243000.00 samples/s0.00 ms152.55 mW697203.20 pJ/it
89matmul/basicarch-aPASSPASS0.054 s0.00 MiB0.00 MiB220.00 ms90.14 mW398436.48 pJ0.040 s0.00 MiB0.00 MiB42376000.00 samples/s0.00 ms105.00 mW297577.19 pJ/it
90matmul/batched_3darch-aPASSPASS0.059 s0.00 MiB0.01 MiB540.01 ms108.59 mW646972.96 pJ0.048 s0.01 MiB0.01 MiB64275000.00 samples/s0.00 ms114.15 mW469999.95 pJ/it
91matmul/batched_3d_dynamicarch-aPASSPASS0.057 s0.00 MiB0.00 MiB400.00 ms92.19 mW167975.00 pJ0.041 s0.00 MiB0.00 MiB50758000.00 samples/s0.00 ms18.49 mW24624.50 pJ/it
92matmul/batched_left_constantarch-aPASSPASS0.057 s0.00 MiB0.02 MiB980.01 ms114.39 mW1009105.92 pJ0.059 s0.01 MiB0.02 MiB118149000.00 samples/s0.01 ms159.00 mW1186296.28 pJ/it
93matmul/batched_lhs_broadcastarch-aPASSPASS0.057 s0.00 MiB0.01 MiB540.01 ms109.39 mW621440.96 pJ0.042 s0.01 MiB0.01 MiB64276000.00 samples/s0.00 ms114.66 mW463736.29 pJ/it
94matmul/batched_rhs_broadcastarch-aPASSPASS0.058 s0.00 MiB0.01 MiB540.01 ms108.59 mW646972.96 pJ0.043 s0.01 MiB0.01 MiB64275000.00 samples/s0.00 ms114.15 mW469999.95 pJ/it
95matmul/dynamicarch-aPASSPASS0.056 s0.00 MiB0.00 MiB500.00 ms91.42 mW148195.00 pJ0.041 s0.00 MiB0.00 MiB50660000.00 samples/s0.00 ms44.46 mW70471.33 pJ/it
96matmul/huge_1024arch-aPASSPASS0.146 s0.01 MiB0.10 MiB73640.02 ms215.07 mW3767010.36 pJ0.162 s0.05 MiB0.09 MiB516426400.00 samples/s0.04 ms135.13 mW5670462.59 pJ/it
97matmul/left_constantarch-aPASSPASS0.055 s0.00 MiB0.01 MiB540.01 ms108.86 mW637168.96 pJ0.045 s0.01 MiB0.01 MiB64297000.00 samples/s0.00 ms115.66 mW451626.62 pJ/it
98matmul/matrix_vectorarch-aPASSPASS0.098 s0.52 MiB0.78 MiB1681730.38 ms202.13 mW77751476.88 pJ0.289 s1.04 MiB0.84 MiB441712150.00 samples/s0.46 ms119.16 mW65096859.53 pJ/it
99matmul/vector_matrixarch-aPASSPASS0.089 s0.01 MiB0.01 MiB980.01 ms118.70 mW878749.92 pJ0.083 s0.02 MiB0.02 MiB108140000.00 samples/s0.01 ms115.31 mW910373.16 pJ/it
100matmul/yolo_attentionarch-aPASSPASS0.474 s1.02 MiB43.44 MiB16808.15 ms170.00 mW1385775865.00 pJ0.645 s5.57 MiB42.54 MiB750145.00 samples/s6.89 ms119.04 mW932561637.00 pJ/it
101mul/after_convarch-aPASSPASS0.059 s0.00 MiB0.00 MiB430.01 ms107.64 mW586955.72 pJ0.050 s0.00 MiB0.00 MiB43194000.00 samples/s0.01 ms58.31 mW304072.05 pJ/it
102mul/after_conv_scalar_constantarch-aPASSPASS0.056 s0.00 MiB0.00 MiB430.01 ms107.64 mW586955.72 pJ0.046 s0.00 MiB0.00 MiB43194000.00 samples/s0.01 ms58.31 mW304072.05 pJ/it
103mul/basicarch-aPASSPASS0.051 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.040 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
104mul/channel_broadcast_1024arch-aPASSPASS0.050 s0.02 MiB0.01 MiB100.01 ms78.12 mW540030.00 pJ0.038 s0.02 MiB0.01 MiB10145000.00 samples/s0.01 ms2.11 mW13388.67 pJ/it
105mul/leading_dimension_broadcastarch-aPASSPASS0.057 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.038 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
106mul/scalar_constantarch-aPASSPASS0.048 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.034 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
107pool/avg_basicarch-aPASSPASS0.051 s0.00 MiB0.00 MiB100.01 ms78.02 mW929400.00 pJ0.038 s0.00 MiB0.00 MiB1084200.00 samples/s0.01 ms2.02 mW24013.00 pJ/it
108pool/avg_ceil_modearch-aPASSPASS0.055 s0.00 MiB0.00 MiB100.00 ms78.03 mW339210.00 pJ0.044 s0.00 MiB0.00 MiB10230000.00 samples/s0.00 ms2.03 mW8786.67 pJ/it
109pool/avg_explicit_paddingarch-aPASSPASS0.055 s0.00 MiB0.00 MiB100.01 ms78.03 mW685860.00 pJ0.039 s0.00 MiB0.00 MiB10114000.00 samples/s0.01 ms2.03 mW17745.00 pJ/it
110pool/avg_include_padarch-aPASSPASS0.054 s0.00 MiB0.00 MiB100.01 ms78.02 mW661116.00 pJ0.041 s0.00 MiB0.00 MiB10118000.00 samples/s0.01 ms2.02 mW17017.00 pJ/it
111pool/avg_large_channelsarch-aPASSPASS0.059 s0.04 MiB0.02 MiB100.24 ms78.00 mW18397284.00 pJ0.046 s0.04 MiB0.02 MiB104250.00 samples/s0.24 ms2.00 mW471380.00 pJ/it
112pool/avg_non_uniform_stridearch-aPASSPASS0.055 s0.00 MiB0.00 MiB100.01 ms78.02 mW1129134.00 pJ0.039 s0.00 MiB0.00 MiB1069300.00 samples/s0.01 ms2.02 mW29111.00 pJ/it
113pool/avg_real_asymmetric_paddingarch-aPASSPASS0.054 s0.00 MiB0.00 MiB100.03 ms78.02 mW1959204.00 pJ0.041 s0.00 MiB0.00 MiB1039900.00 samples/s0.03 ms2.02 mW50769.00 pJ/it
114pool/max_after_convarch-aPASSPASS0.063 s0.00 MiB0.00 MiB540.01 ms99.12 mW1209961.96 pJ0.051 s0.00 MiB0.00 MiB54140000.00 samples/s0.01 ms58.47 mW468396.45 pJ/it
115pool/max_basicarch-aPASSPASS0.051 s0.00 MiB0.00 MiB100.00 ms78.06 mW324744.00 pJ0.039 s0.00 MiB0.00 MiB10241000.00 samples/s0.00 ms2.06 mW8532.67 pJ/it
116pool/max_ceil_modearch-aPASSPASS0.050 s0.00 MiB0.00 MiB100.00 ms78.07 mW151464.00 pJ0.035 s0.00 MiB0.00 MiB10516000.00 samples/s0.00 ms2.07 mW3972.67 pJ/it
117pool/max_global_style_kernel_equals_inputarch-aPASSPASS0.055 s0.00 MiB0.00 MiB100.01 ms78.01 mW657534.00 pJ0.042 s0.00 MiB0.00 MiB10119000.00 samples/s0.01 ms2.01 mW16843.00 pJ/it
118pool/max_non_square_kernelarch-aPASSPASS0.052 s0.00 MiB0.00 MiB100.01 ms78.02 mW1060572.00 pJ0.047 s0.00 MiB0.00 MiB1073700.00 samples/s0.01 ms2.02 mW27353.00 pJ/it
119pool/max_real_asymmetric_paddingarch-aPASSPASS0.052 s0.00 MiB0.00 MiB100.01 ms78.03 mW814992.00 pJ0.040 s0.00 MiB0.00 MiB1096100.00 samples/s0.01 ms2.03 mW21173.00 pJ/it
120pool/max_same_upperarch-aPASSPASS0.052 s0.00 MiB0.00 MiB100.01 ms78.04 mW625068.00 pJ0.042 s0.00 MiB0.00 MiB10125000.00 samples/s0.01 ms2.04 mW16233.00 pJ/it
121pool/max_stride2_multichannelarch-aPASSPASS0.051 s0.00 MiB0.00 MiB100.02 ms78.02 mW1245870.00 pJ0.036 s0.00 MiB0.00 MiB1062800.00 samples/s0.02 ms2.02 mW32117.00 pJ/it
122reduce_mean/4d_spatialarch-aPASSPASS0.054 s0.00 MiB0.00 MiB100.00 ms78.02 mW326814.00 pJ0.044 s0.00 MiB0.00 MiB10239000.00 samples/s0.00 ms2.02 mW8390.67 pJ/it
123reduce_mean/4d_spatial_keepdims_0arch-aPASSPASS0.050 s0.00 MiB0.00 MiB400.00 ms94.35 mW61801.00 pJ0.041 s0.00 MiB0.00 MiB401470000.00 samples/s0.00 ms44.66 mW31425.33 pJ/it
124reduce_mean/after_convarch-aPASSPASS0.062 s0.00 MiB0.00 MiB430.01 ms100.79 mW1119699.72 pJ0.057 s0.00 MiB0.00 MiB43125000.00 samples/s0.01 ms54.14 mW474782.17 pJ/it
125reduce_mean/all_axes_keepdims_0arch-aPASSPASS0.050 s0.00 MiB0.00 MiB200.00 ms79.24 mW30982.00 pJ0.038 s0.00 MiB0.00 MiB202720000.00 samples/s0.00 ms44.37 mW16707.00 pJ/it
126reduce_mean/all_axes_keepdims_1arch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.22 mW17286.00 pJ0.039 s0.00 MiB0.00 MiB104570000.00 samples/s0.00 ms2.22 mW437.33 pJ/it
127reduce_mean/basicarch-aPASSPASS0.054 s0.00 MiB0.00 MiB400.00 ms93.51 mW34881.00 pJ0.042 s0.00 MiB0.00 MiB402600000.00 samples/s0.00 ms5.85 mW2235.67 pJ/it
128reduce_mean/channel_axis_nchwarch-aPASSPASS0.054 s0.03 MiB0.02 MiB400.16 ms93.60 mW15436518.00 pJ0.040 s0.03 MiB0.08 MiB4012900.00 samples/s0.08 ms5.00 mW388853.50 pJ/it
129reduce_mean/keepdims_0arch-aPASSPASS0.053 s0.00 MiB0.00 MiB500.00 ms91.40 mW68368.00 pJ0.043 s0.00 MiB0.00 MiB501300000.00 samples/s0.00 ms44.76 mW36032.00 pJ/it
130reduce_mean/large_dimension_1024arch-aPASSPASS0.048 s0.01 MiB0.00 MiB100.00 ms78.02 mW217278.00 pJ0.040 s0.01 MiB0.00 MiB10359000.00 samples/s0.00 ms2.02 mW5274.00 pJ/it
131reduce_mean/legacy_axes_1_2_keepdims_1arch-aPASSPASS0.050 s0.00 MiB0.00 MiB200.00 ms79.35 mW21505.00 pJ0.042 s0.00 MiB0.00 MiB203620000.00 samples/s0.00 ms3.45 mW898.00 pJ/it
132reduce_mean/legacy_axis1_keepdims_0arch-aPASSPASS0.056 s0.00 MiB0.00 MiB900.00 ms92.50 mW183708.00 pJ0.042 s0.00 MiB0.00 MiB90654000.00 samples/s0.00 ms45.89 mW72573.50 pJ/it
133reduce_mean/legacy_axis1_keepdims_1arch-aPASSPASS0.050 s0.00 MiB0.00 MiB800.00 ms94.56 mW129830.00 pJ0.049 s0.00 MiB0.00 MiB801340000.00 samples/s0.00 ms10.15 mW7594.50 pJ/it
134reduce_mean/legacy_empty_axes_nooparch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.22 mW17286.00 pJ0.037 s0.00 MiB0.00 MiB104570000.00 samples/s0.00 ms2.22 mW437.33 pJ/it
135reduce_mean/legacy_nchw_spatialarch-aPASSPASS0.055 s0.00 MiB0.00 MiB100.01 ms78.01 mW498648.00 pJ0.044 s0.00 MiB0.00 MiB10156000.00 samples/s0.01 ms2.01 mW12796.67 pJ/it
136reduce_mean/legacy_negative_axisarch-aPASSPASS0.053 s0.00 MiB0.00 MiB600.00 ms93.52 mW51717.00 pJ0.041 s0.00 MiB0.00 MiB601760000.00 samples/s0.00 ms8.07 mW4588.50 pJ/it
137reduce_mean/legacy_reduce_all_keepdims_1arch-aPASSPASS0.054 s0.00 MiB0.00 MiB100.00 ms78.22 mW17286.00 pJ0.038 s0.00 MiB0.00 MiB104570000.00 samples/s0.00 ms2.22 mW437.33 pJ/it
138reduce_mean/negative_axisarch-aPASSPASS0.051 s0.00 MiB0.00 MiB600.00 ms93.52 mW51717.00 pJ0.041 s0.00 MiB0.00 MiB601760000.00 samples/s0.00 ms8.07 mW4588.50 pJ/it
139relu/4darch-aPASSPASS0.047 s0.00 MiB0.00 MiB100.00 ms78.18 mW40734.00 pJ0.046 s0.00 MiB0.00 MiB101930000.00 samples/s0.00 ms2.18 mW1014.00 pJ/it
140relu/after_convarch-aPASSPASS0.057 s0.00 MiB0.00 MiB430.01 ms107.89 mW577437.72 pJ0.048 s0.00 MiB0.00 MiB43191000.00 samples/s0.01 ms58.26 mW304800.72 pJ/it
141relu/after_gemmarch-aPASSPASS0.054 s0.01 MiB0.01 MiB540.01 ms105.16 mW790056.96 pJ0.042 s0.01 MiB0.01 MiB64230000.00 samples/s0.00 ms109.21 mW545663.29 pJ/it
142relu/basicarch-aPASSPASS0.050 s0.00 MiB0.00 MiB100.00 ms78.22 mW17286.00 pJ0.036 s0.00 MiB0.00 MiB104570000.00 samples/s0.00 ms2.22 mW437.33 pJ/it
143reshape/4d_to_2d_flattenarch-aPASSPASS0.050 s0.00 MiB0.00 MiB100.00 ms78.28 mW20196.00 pJ0.039 s0.00 MiB0.00 MiB103910000.00 samples/s0.00 ms2.28 mW488.00 pJ/it
144reshape/infer_dim_minus_onearch-aPASSPASS0.051 s0.00 MiB0.00 MiB100.00 ms78.30 mW12684.00 pJ0.036 s0.00 MiB0.00 MiB106250000.00 samples/s0.00 ms2.30 mW308.00 pJ/it
145reshape/same_rankarch-aPASSPASS0.048 s0.00 MiB0.00 MiB100.00 ms78.30 mW12684.00 pJ0.036 s0.00 MiB0.00 MiB106250000.00 samples/s0.00 ms2.30 mW308.00 pJ/it
146reshape/zero_copies_input_dimarch-aPASSPASS0.054 s0.00 MiB0.00 MiB100.00 ms78.30 mW12684.00 pJ0.034 s0.00 MiB0.00 MiB106250000.00 samples/s0.00 ms2.30 mW308.00 pJ/it
147resize/height_onlyarch-aPASSPASS0.052 s0.00 MiB0.00 MiB400.00 ms93.55 mW64833.00 pJ0.038 s0.00 MiB0.00 MiB401880000.00 samples/s0.00 ms5.60 mW2986.00 pJ/it
148resize/nearest_2xarch-aPASSPASS0.051 s0.00 MiB0.00 MiB400.00 ms93.57 mW109761.00 pJ0.038 s0.00 MiB0.00 MiB401450000.00 samples/s0.00 ms5.46 mW3776.00 pJ/it
149resize/nearest_downsamplearch-aPASSPASS0.052 s0.00 MiB0.00 MiB200.00 ms79.45 mW33925.00 pJ0.039 s0.00 MiB0.00 MiB202330000.00 samples/s0.00 ms3.28 mW1360.50 pJ/it
150resize/non_uniform_scalesarch-aPASSPASS0.052 s0.00 MiB0.00 MiB600.00 ms93.58 mW164037.00 pJ0.042 s0.00 MiB0.00 MiB601250000.00 samples/s0.00 ms7.76 mW6207.25 pJ/it
151resize/width_onlyarch-aPASSPASS0.050 s0.00 MiB0.00 MiB200.00 ms79.50 mW53029.00 pJ0.037 s0.00 MiB0.00 MiB201700000.00 samples/s0.00 ms3.20 mW1833.50 pJ/it
152resize/with_sizesarch-aPASSPASS0.051 s0.00 MiB0.00 MiB300.00 ms92.54 mW73756.00 pJ0.039 s0.00 MiB0.00 MiB301700000.00 samples/s0.00 ms4.39 mW2586.75 pJ/it
153sigmoid/4darch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.18 mW40734.00 pJ0.035 s0.00 MiB0.00 MiB101930000.00 samples/s0.00 ms2.18 mW1014.00 pJ/it
154sigmoid/after_gemmarch-aPASSPASS0.054 s0.01 MiB0.01 MiB540.01 ms105.16 mW790056.96 pJ0.043 s0.01 MiB0.01 MiB64230000.00 samples/s0.00 ms109.21 mW545663.29 pJ/it
155sigmoid/basicarch-aPASSPASS0.048 s0.00 MiB0.00 MiB100.00 ms78.22 mW17286.00 pJ0.036 s0.00 MiB0.00 MiB104570000.00 samples/s0.00 ms2.22 mW437.33 pJ/it
156slice/2d_basicarch-aPASSPASS0.050 s0.00 MiB0.00 MiB100.00 ms78.30 mW18948.00 pJ0.038 s0.00 MiB0.00 MiB104170000.00 samples/s0.00 ms2.30 mW491.67 pJ/it
157slice/after_convarch-aPASSPASS0.057 s0.00 MiB0.01 MiB760.01 ms118.19 mW1335082.88 pJ0.053 s0.00 MiB0.01 MiB76106000.00 samples/s0.01 ms73.96 mW732218.55 pJ/it
158slice/default_axesarch-aPASSPASS0.047 s0.00 MiB0.00 MiB100.00 ms78.30 mW18948.00 pJ0.035 s0.00 MiB0.00 MiB104170000.00 samples/s0.00 ms2.30 mW491.67 pJ/it
159slice/large_channel_1024arch-aPASSPASS0.049 s0.01 MiB0.00 MiB100.00 ms78.14 mW221304.00 pJ0.036 s0.01 MiB0.00 MiB10353000.00 samples/s0.00 ms2.14 mW5058.00 pJ/it
160slice/nchw_spatial_croparch-aPASSPASS0.050 s0.00 MiB0.00 MiB100.00 ms78.24 mW101868.00 pJ0.042 s0.00 MiB0.00 MiB10769000.00 samples/s0.00 ms2.24 mW2851.67 pJ/it
161slice/negative_axisarch-aPASSPASS0.048 s0.00 MiB0.00 MiB100.00 ms78.30 mW44004.00 pJ0.037 s0.00 MiB0.00 MiB101790000.00 samples/s0.00 ms2.30 mW1227.67 pJ/it
162slice/negative_indicesarch-aPASSPASS0.052 s0.00 MiB0.00 MiB100.00 ms78.30 mW25212.00 pJ0.037 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.30 mW675.67 pJ/it
163slice/step2arch-aPASSPASS0.053 s0.00 MiB0.00 MiB100.00 ms78.29 mW159876.00 pJ0.042 s0.00 MiB0.00 MiB10490000.00 samples/s0.00 ms2.29 mW4619.67 pJ/it
164softmax/3d_last_axisarch-aPASSPASS0.048 s0.00 MiB0.00 MiB10UNSUPPORTEDUNSUPPORTEDUNSUPPORTED0.035 s0.00 MiB0.00 MiB10UNSUPPORTEDUNSUPPORTEDUNSUPPORTEDUNSUPPORTED
165softmax/basicarch-aPASSPASS0.048 s0.00 MiB0.00 MiB10UNSUPPORTEDUNSUPPORTEDUNSUPPORTED0.036 s0.00 MiB0.00 MiB10UNSUPPORTEDUNSUPPORTEDUNSUPPORTEDUNSUPPORTED
166softmax/channel_axisarch-aPASSPASS0.050 s0.00 MiB0.00 MiB10UNSUPPORTEDUNSUPPORTEDUNSUPPORTED0.040 s0.00 MiB0.00 MiB30UNSUPPORTEDUNSUPPORTEDUNSUPPORTEDUNSUPPORTED
167softmax/large_dimension_1024arch-aPASSPASS0.049 s0.01 MiB0.01 MiB10UNSUPPORTEDUNSUPPORTEDUNSUPPORTED0.036 s0.01 MiB0.01 MiB10UNSUPPORTEDUNSUPPORTEDUNSUPPORTEDUNSUPPORTED
168softmax/negative_axisarch-aPASSPASS0.048 s0.00 MiB0.00 MiB10UNSUPPORTEDUNSUPPORTEDUNSUPPORTED0.036 s0.00 MiB0.00 MiB10UNSUPPORTEDUNSUPPORTEDUNSUPPORTEDUNSUPPORTED
169split/basicarch-aPASSPASS0.051 s0.00 MiB0.00 MiB100.00 ms78.30 mW31554.00 pJ0.037 s0.00 MiB0.00 MiB102490000.00 samples/s0.00 ms2.30 mW861.67 pJ/it
170split/equal_three_wayarch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.30 mW44160.00 pJ0.035 s0.00 MiB0.00 MiB101780000.00 samples/s0.00 ms2.30 mW1231.67 pJ/it
171split/negative_axisarch-aPASSPASS0.053 s0.00 MiB0.00 MiB100.00 ms78.29 mW84786.00 pJ0.039 s0.00 MiB0.00 MiB10925000.00 samples/s0.00 ms2.29 mW2413.67 pJ/it
172split/uneven_channel_axis_4darch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.30 mW18948.00 pJ0.046 s0.00 MiB0.00 MiB104170000.00 samples/s0.00 ms2.30 mW491.67 pJ/it
173sub/after_gemmarch-aPASSPASS0.056 s0.01 MiB0.01 MiB540.01 ms104.70 mW815012.96 pJ0.045 s0.01 MiB0.01 MiB64218000.00 samples/s0.00 ms107.94 mW570766.12 pJ/it
174sub/basicarch-aPASSPASS0.046 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.037 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
175sub/broadcast_rowarch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.042 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it
176sub/channel_broadcast_1024arch-aPASSPASS0.052 s0.02 MiB0.01 MiB100.01 ms78.12 mW540030.00 pJ0.037 s0.02 MiB0.01 MiB10145000.00 samples/s0.01 ms2.11 mW13388.67 pJ/it
177sub/constant_lhs_broadcastarch-aPASSPASS0.049 s0.00 MiB0.00 MiB100.00 ms78.22 mW25188.00 pJ0.034 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW656.67 pJ/it
178sub/leading_dimension_broadcastarch-aPASSPASS0.050 s0.00 MiB0.00 MiB100.00 ms78.22 mW25266.00 pJ0.038 s0.00 MiB0.00 MiB103120000.00 samples/s0.00 ms2.23 mW658.67 pJ/it