Untitled
unknown
c_cpp
2 months ago
146 kB
1
Indexable
Model Input Name: unique_ids_raw_output___9:0, Shape: [0]
Model Input Name: segment_ids:0, Shape: [0, 256]
Model Input Name: input_mask:0, Shape: [0, 256]
Model Input Name: input_ids:0, Shape: [0, 256]
Starting model execution...
Inputs Details:
Input Name: input_ids:0
Shape: (1, 256)
Data (first 10 values): [28148 26736 988 2528 1043 3349 8281 12138 2763 27770]...
--------------------------------------------------
Input Name: segment_ids:0
Shape: (1, 256)
Data (first 10 values): [0 1 0 0 0 0 1 0 1 0]...
--------------------------------------------------
Input Name: input_mask:0
Shape: (1, 256)
Data (first 10 values): [1 1 0 0 1 0 1 0 1 1]...
--------------------------------------------------
Input Name: unique_ids_raw_output___9:0
Shape: (0,)
Data (first 10 values): []...
--------------------------------------------------
No Add node related to MatMul output: bert/embeddings/MatMul. Executing regular MatMul.
Fusing MatMul with Add for Node: bert/encoder/layer_0/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_0/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_0/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_0/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_0/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_0/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_0/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_0/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_0/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_0/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_0/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_0/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_0/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_0/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_0/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_0/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_1/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_1/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_1/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_1/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_1/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_1/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_1/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_1/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_1/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_1/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_1/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_1/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_1/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_1/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_1/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_1/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_2/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_2/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_2/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_2/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_2/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_2/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_2/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_2/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_2/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_2/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_2/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_2/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_2/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_2/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_2/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_2/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_3/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_3/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_3/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_3/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_3/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_3/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_3/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_3/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_3/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_3/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_3/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_3/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_3/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_3/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_3/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_3/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_4/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_4/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_4/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_4/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_4/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_4/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_4/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_4/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_4/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_4/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_4/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_4/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_4/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_4/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_4/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_4/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_5/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_5/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_5/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_5/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_5/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_5/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_5/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_5/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_5/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_5/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_5/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_5/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_5/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_5/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_5/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_5/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_6/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_6/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_6/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_6/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_6/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_6/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_6/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_6/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_6/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_6/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_6/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_6/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_6/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_6/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_6/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_6/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_7/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_7/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_7/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_7/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_7/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_7/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_7/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_7/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_7/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_7/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_7/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_7/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_7/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_7/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_7/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_7/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_8/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_8/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_8/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_8/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_8/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_8/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_8/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_8/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_8/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_8/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_8/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_8/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_8/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_8/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_8/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_8/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_9/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_9/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_9/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_9/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_9/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_9/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_9/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_9/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_9/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_9/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_9/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_9/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_9/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_9/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_9/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_9/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_10/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_10/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_10/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_10/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_10/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_10/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_10/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_10/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_10/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_10/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_10/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_10/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_10/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_10/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_10/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_10/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_11/attention/self/value/MatMul
Skipping already processed Add Node: bert/encoder/layer_11/attention/self/value/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_11/attention/self/query/MatMul
Skipping already processed Add Node: bert/encoder/layer_11/attention/self/query/BiasAdd
Fusing MatMul with Add for Node: bert/encoder/layer_11/attention/self/key/MatMul
Skipping already processed Add Node: bert/encoder/layer_11/attention/self/key/BiasAdd
No Add node related to MatMul output: bert/encoder/layer_11/attention/self/MatMul. Executing regular MatMul.
No Add node related to MatMul output: bert/encoder/layer_11/attention/self/MatMul_1. Executing regular MatMul.
Fusing MatMul with 2Add for Node: bert/encoder/layer_11/attention/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_11/attention/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_11/attention/output/add
Fusing MatMul with Add for Node: bert/encoder/layer_11/intermediate/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_11/intermediate/dense/BiasAdd
Fusing MatMul with 2Add for Node: bert/encoder/layer_11/output/dense/MatMul
Skipping already processed Add Node: bert/encoder/layer_11/output/dense/BiasAdd
Skipping already processed Add Node: bert/encoder/layer_11/output/add
Fusing MatMul with Add for Node: MatMul
Skipping already processed Add Node: BiasAdd
Node Execution Times:
Node: unique_ids_graph_outputs_Identity__10, Execution Time: 0.000005 seconds
Node: bert/encoder/Shape, Execution Time: 0.000004 seconds
Node: bert/encoder/Shape__12, Execution Time: 0.000009 seconds
Node: bert/encoder/strided_slice, Execution Time: 0.000062 seconds
Node: bert/encoder/strided_slice__16, Execution Time: 0.000005 seconds
Node: bert/encoder/strided_slice__17, Execution Time: 0.000005 seconds
Node: bert/encoder/ones/packed_Unsqueeze__18, Execution Time: 0.000010 seconds
Node: bert/encoder/ones/packed_Concat__21, Execution Time: 0.000010 seconds
Node: bert/encoder/ones__22, Execution Time: 0.000004 seconds
Node: bert/encoder/ones, Execution Time: 0.000011 seconds
Node: bert/encoder/Reshape, Execution Time: 0.000006 seconds
Node: bert/encoder/Cast, Execution Time: 0.000004 seconds
Node: bert/encoder/mul, Execution Time: 0.028335 seconds
Node: bert/encoder/layer_9/attention/self/ExpandDims, Execution Time: 0.000038 seconds
Node: bert/encoder/layer_9/attention/self/sub, Execution Time: 0.006912 seconds
Node: bert/encoder/layer_9/attention/self/mul_1, Execution Time: 0.000315 seconds
Node: bert/embeddings/Reshape_2, Execution Time: 0.000020 seconds
Node: bert/embeddings/Reshape, Execution Time: 0.000006 seconds
Node: bert/embeddings/GatherV2, Execution Time: 0.000304 seconds
Node: bert/embeddings/Reshape_1, Execution Time: 0.000008 seconds
Node: bert/embeddings/one_hot, Execution Time: 0.000057 seconds
Node: bert/embeddings/MatMul, Execution Time: 0.061418 seconds
Node: bert/embeddings/Reshape_3, Execution Time: 0.000040 seconds
Node: bert/embeddings/add, Execution Time: 0.002179 seconds
Node: bert/embeddings/add_1, Execution Time: 0.001005 seconds
Node: bert/embeddings/LayerNorm/moments/mean, Execution Time: 0.005431 seconds
Node: bert/embeddings/LayerNorm/moments/SquaredDifference, Execution Time: 0.000726 seconds
Node: bert/embeddings/LayerNorm/moments/SquaredDifference__72, Execution Time: 0.000863 seconds
Node: bert/embeddings/LayerNorm/moments/variance, Execution Time: 0.000273 seconds
Node: bert/embeddings/LayerNorm/batchnorm/add, Execution Time: 0.000082 seconds
Node: bert/embeddings/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.010061 seconds
Node: bert/embeddings/LayerNorm/batchnorm/Rsqrt__74, Execution Time: 0.005280 seconds
Node: bert/embeddings/LayerNorm/batchnorm/mul, Execution Time: 0.000104 seconds
Node: bert/embeddings/LayerNorm/batchnorm/mul_2, Execution Time: 0.000079 seconds
Node: bert/embeddings/LayerNorm/batchnorm/sub, Execution Time: 0.000088 seconds
Node: bert/embeddings/LayerNorm/batchnorm/mul_1, Execution Time: 0.000667 seconds
Node: bert/embeddings/LayerNorm/batchnorm/add_1, Execution Time: 0.000691 seconds
Node: bert/encoder/Reshape_1, Execution Time: 0.000034 seconds
Matmul Fuse Node: bert/encoder/layer_0/attention/self/value/MatMul, Execution Time: 0.035522 seconds
Node: bert/encoder/layer_0/attention/self/Reshape_2, Execution Time: 0.000023 seconds
Node: bert/encoder/layer_0/attention/self/transpose_2, Execution Time: 0.000437 seconds
Matmul Fuse Node: bert/encoder/layer_0/attention/self/query/MatMul, Execution Time: 0.003021 seconds
Node: bert/encoder/layer_0/attention/self/Reshape, Execution Time: 0.000014 seconds
Node: bert/encoder/layer_0/attention/self/transpose, Execution Time: 0.000255 seconds
Matmul Fuse Node: bert/encoder/layer_0/attention/self/key/MatMul, Execution Time: 0.003390 seconds
Node: bert/encoder/layer_0/attention/self/Reshape_1, Execution Time: 0.000015 seconds
Node: bert/encoder/layer_0/attention/self/MatMul__306, Execution Time: 0.000262 seconds
Node: bert/encoder/layer_0/attention/self/MatMul, Execution Time: 0.005664 seconds
Node: bert/encoder/layer_0/attention/self/Mul, Execution Time: 0.001250 seconds
Node: bert/encoder/layer_0/attention/self/add, Execution Time: 0.001806 seconds
Node: bert/encoder/layer_0/attention/self/Softmax, Execution Time: 0.009676 seconds
Node: bert/encoder/layer_0/attention/self/MatMul_1, Execution Time: 0.001447 seconds
Node: bert/encoder/layer_0/attention/self/transpose_3, Execution Time: 0.000253 seconds
Node: bert/encoder/layer_0/attention/self/Reshape_3, Execution Time: 0.000055 seconds
Matmul Fuse Node: bert/encoder/layer_0/attention/output/dense/MatMul, Execution Time: 0.001492 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/moments/mean, Execution Time: 0.000218 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000390 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/moments/SquaredDifference__309, Execution Time: 0.000521 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/moments/variance, Execution Time: 0.000165 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000122 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000087 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/Rsqrt__311, Execution Time: 0.000131 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000120 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000568 seconds
Node: bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000690 seconds
Matmul Fuse Node: bert/encoder/layer_0/intermediate/dense/MatMul, Execution Time: 0.006251 seconds
Node: bert/encoder/layer_0/intermediate/dense/Pow, Execution Time: 0.017836 seconds
Node: bert/encoder/layer_0/intermediate/dense/mul, Execution Time: 0.001201 seconds
Node: bert/encoder/layer_0/intermediate/dense/add, Execution Time: 0.001495 seconds
Node: bert/encoder/layer_0/intermediate/dense/mul_1, Execution Time: 0.001162 seconds
Node: bert/encoder/layer_0/intermediate/dense/Tanh, Execution Time: 0.003510 seconds
Node: bert/encoder/layer_0/intermediate/dense/add_1, Execution Time: 0.001209 seconds
Node: bert/encoder/layer_0/intermediate/dense/mul_2, Execution Time: 0.001196 seconds
Node: bert/encoder/layer_0/intermediate/dense/mul_3, Execution Time: 0.001443 seconds
Matmul Fuse Node: bert/encoder/layer_0/output/dense/MatMul, Execution Time: 0.002903 seconds
Node: bert/encoder/layer_0/output/LayerNorm/moments/mean, Execution Time: 0.000174 seconds
Node: bert/encoder/layer_0/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000250 seconds
Node: bert/encoder/layer_0/output/LayerNorm/moments/SquaredDifference__313, Execution Time: 0.000330 seconds
Node: bert/encoder/layer_0/output/LayerNorm/moments/variance, Execution Time: 0.000158 seconds
Node: bert/encoder/layer_0/output/LayerNorm/batchnorm/add, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_0/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000059 seconds
Node: bert/encoder/layer_0/output/LayerNorm/batchnorm/Rsqrt__315, Execution Time: 0.000079 seconds
Node: bert/encoder/layer_0/output/LayerNorm/batchnorm/mul, Execution Time: 0.000078 seconds
Node: bert/encoder/layer_0/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000091 seconds
Node: bert/encoder/layer_0/output/LayerNorm/batchnorm/sub, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_0/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000340 seconds
Node: bert/encoder/layer_0/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000436 seconds
Matmul Fuse Node: bert/encoder/layer_1/attention/self/value/MatMul, Execution Time: 0.002877 seconds
Node: bert/encoder/layer_1/attention/self/Reshape_2, Execution Time: 0.000021 seconds
Node: bert/encoder/layer_1/attention/self/transpose_2, Execution Time: 0.000252 seconds
Matmul Fuse Node: bert/encoder/layer_1/attention/self/query/MatMul, Execution Time: 0.002599 seconds
Node: bert/encoder/layer_1/attention/self/Reshape, Execution Time: 0.000014 seconds
Node: bert/encoder/layer_1/attention/self/transpose, Execution Time: 0.000255 seconds
Matmul Fuse Node: bert/encoder/layer_1/attention/self/key/MatMul, Execution Time: 0.002547 seconds
Node: bert/encoder/layer_1/attention/self/Reshape_1, Execution Time: 0.000012 seconds
Node: bert/encoder/layer_1/attention/self/MatMul__320, Execution Time: 0.000247 seconds
Node: bert/encoder/layer_1/attention/self/MatMul, Execution Time: 0.001364 seconds
Node: bert/encoder/layer_1/attention/self/Mul, Execution Time: 0.001176 seconds
Node: bert/encoder/layer_1/attention/self/add, Execution Time: 0.001914 seconds
Node: bert/encoder/layer_1/attention/self/Softmax, Execution Time: 0.001903 seconds
Node: bert/encoder/layer_1/attention/self/MatMul_1, Execution Time: 0.001078 seconds
Node: bert/encoder/layer_1/attention/self/transpose_3, Execution Time: 0.000241 seconds
Node: bert/encoder/layer_1/attention/self/Reshape_3, Execution Time: 0.000048 seconds
Matmul Fuse Node: bert/encoder/layer_1/attention/output/dense/MatMul, Execution Time: 0.001257 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/moments/mean, Execution Time: 0.000174 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000249 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/moments/SquaredDifference__323, Execution Time: 0.000343 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/moments/variance, Execution Time: 0.000155 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000060 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/Rsqrt__325, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000078 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000092 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000087 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000334 seconds
Node: bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000696 seconds
Matmul Fuse Node: bert/encoder/layer_1/intermediate/dense/MatMul, Execution Time: 0.004094 seconds
Node: bert/encoder/layer_1/intermediate/dense/Pow, Execution Time: 0.000729 seconds
Node: bert/encoder/layer_1/intermediate/dense/mul, Execution Time: 0.001168 seconds
Node: bert/encoder/layer_1/intermediate/dense/add, Execution Time: 0.001503 seconds
Node: bert/encoder/layer_1/intermediate/dense/mul_1, Execution Time: 0.001165 seconds
Node: bert/encoder/layer_1/intermediate/dense/Tanh, Execution Time: 0.001071 seconds
Node: bert/encoder/layer_1/intermediate/dense/add_1, Execution Time: 0.001120 seconds
Node: bert/encoder/layer_1/intermediate/dense/mul_2, Execution Time: 0.001135 seconds
Node: bert/encoder/layer_1/intermediate/dense/mul_3, Execution Time: 0.001441 seconds
Matmul Fuse Node: bert/encoder/layer_1/output/dense/MatMul, Execution Time: 0.002657 seconds
Node: bert/encoder/layer_1/output/LayerNorm/moments/mean, Execution Time: 0.000176 seconds
Node: bert/encoder/layer_1/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000243 seconds
Node: bert/encoder/layer_1/output/LayerNorm/moments/SquaredDifference__327, Execution Time: 0.000338 seconds
Node: bert/encoder/layer_1/output/LayerNorm/moments/variance, Execution Time: 0.000164 seconds
Node: bert/encoder/layer_1/output/LayerNorm/batchnorm/add, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_1/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000060 seconds
Node: bert/encoder/layer_1/output/LayerNorm/batchnorm/Rsqrt__329, Execution Time: 0.000079 seconds
Node: bert/encoder/layer_1/output/LayerNorm/batchnorm/mul, Execution Time: 0.000077 seconds
Node: bert/encoder/layer_1/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000092 seconds
Node: bert/encoder/layer_1/output/LayerNorm/batchnorm/sub, Execution Time: 0.000083 seconds
Node: bert/encoder/layer_1/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000336 seconds
Node: bert/encoder/layer_1/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000424 seconds
Matmul Fuse Node: bert/encoder/layer_2/attention/self/value/MatMul, Execution Time: 0.003581 seconds
Node: bert/encoder/layer_2/attention/self/Reshape_2, Execution Time: 0.000026 seconds
Node: bert/encoder/layer_2/attention/self/transpose_2, Execution Time: 0.000279 seconds
Matmul Fuse Node: bert/encoder/layer_2/attention/self/query/MatMul, Execution Time: 0.003191 seconds
Node: bert/encoder/layer_2/attention/self/Reshape, Execution Time: 0.000017 seconds
Node: bert/encoder/layer_2/attention/self/transpose, Execution Time: 0.000271 seconds
Matmul Fuse Node: bert/encoder/layer_2/attention/self/key/MatMul, Execution Time: 0.003162 seconds
Node: bert/encoder/layer_2/attention/self/Reshape_1, Execution Time: 0.000015 seconds
Node: bert/encoder/layer_2/attention/self/MatMul__334, Execution Time: 0.000279 seconds
Node: bert/encoder/layer_2/attention/self/MatMul, Execution Time: 0.001417 seconds
Node: bert/encoder/layer_2/attention/self/Mul, Execution Time: 0.001199 seconds
Node: bert/encoder/layer_2/attention/self/add, Execution Time: 0.001837 seconds
Node: bert/encoder/layer_2/attention/self/Softmax, Execution Time: 0.001921 seconds
Node: bert/encoder/layer_2/attention/self/MatMul_1, Execution Time: 0.001089 seconds
Node: bert/encoder/layer_2/attention/self/transpose_3, Execution Time: 0.000246 seconds
Node: bert/encoder/layer_2/attention/self/Reshape_3, Execution Time: 0.000047 seconds
Matmul Fuse Node: bert/encoder/layer_2/attention/output/dense/MatMul, Execution Time: 0.001225 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/moments/mean, Execution Time: 0.000175 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000243 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/moments/SquaredDifference__337, Execution Time: 0.000339 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/moments/variance, Execution Time: 0.000157 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000059 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/Rsqrt__339, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000096 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000080 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000582 seconds
Node: bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000878 seconds
Matmul Fuse Node: bert/encoder/layer_2/intermediate/dense/MatMul, Execution Time: 0.004214 seconds
Node: bert/encoder/layer_2/intermediate/dense/Pow, Execution Time: 0.000725 seconds
Node: bert/encoder/layer_2/intermediate/dense/mul, Execution Time: 0.001163 seconds
Node: bert/encoder/layer_2/intermediate/dense/add, Execution Time: 0.001479 seconds
Node: bert/encoder/layer_2/intermediate/dense/mul_1, Execution Time: 0.001115 seconds
Node: bert/encoder/layer_2/intermediate/dense/Tanh, Execution Time: 0.001115 seconds
Node: bert/encoder/layer_2/intermediate/dense/add_1, Execution Time: 0.001124 seconds
Node: bert/encoder/layer_2/intermediate/dense/mul_2, Execution Time: 0.001173 seconds
Node: bert/encoder/layer_2/intermediate/dense/mul_3, Execution Time: 0.001371 seconds
Matmul Fuse Node: bert/encoder/layer_2/output/dense/MatMul, Execution Time: 0.002838 seconds
Node: bert/encoder/layer_2/output/LayerNorm/moments/mean, Execution Time: 0.000176 seconds
Node: bert/encoder/layer_2/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000256 seconds
Node: bert/encoder/layer_2/output/LayerNorm/moments/SquaredDifference__341, Execution Time: 0.000376 seconds
Node: bert/encoder/layer_2/output/LayerNorm/moments/variance, Execution Time: 0.000160 seconds
Node: bert/encoder/layer_2/output/LayerNorm/batchnorm/add, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_2/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000059 seconds
Node: bert/encoder/layer_2/output/LayerNorm/batchnorm/Rsqrt__343, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_2/output/LayerNorm/batchnorm/mul, Execution Time: 0.000089 seconds
Node: bert/encoder/layer_2/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000085 seconds
Node: bert/encoder/layer_2/output/LayerNorm/batchnorm/sub, Execution Time: 0.000084 seconds
Node: bert/encoder/layer_2/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000336 seconds
Node: bert/encoder/layer_2/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000438 seconds
Matmul Fuse Node: bert/encoder/layer_3/attention/self/value/MatMul, Execution Time: 0.002847 seconds
Node: bert/encoder/layer_3/attention/self/Reshape_2, Execution Time: 0.000021 seconds
Node: bert/encoder/layer_3/attention/self/transpose_2, Execution Time: 0.000258 seconds
Matmul Fuse Node: bert/encoder/layer_3/attention/self/query/MatMul, Execution Time: 0.002538 seconds
Node: bert/encoder/layer_3/attention/self/Reshape, Execution Time: 0.000013 seconds
Node: bert/encoder/layer_3/attention/self/transpose, Execution Time: 0.000247 seconds
Matmul Fuse Node: bert/encoder/layer_3/attention/self/key/MatMul, Execution Time: 0.002475 seconds
Node: bert/encoder/layer_3/attention/self/Reshape_1, Execution Time: 0.000012 seconds
Node: bert/encoder/layer_3/attention/self/MatMul__348, Execution Time: 0.000247 seconds
Node: bert/encoder/layer_3/attention/self/MatMul, Execution Time: 0.001355 seconds
Node: bert/encoder/layer_3/attention/self/Mul, Execution Time: 0.001203 seconds
Node: bert/encoder/layer_3/attention/self/add, Execution Time: 0.001965 seconds
Node: bert/encoder/layer_3/attention/self/Softmax, Execution Time: 0.002022 seconds
Node: bert/encoder/layer_3/attention/self/MatMul_1, Execution Time: 0.001136 seconds
Node: bert/encoder/layer_3/attention/self/transpose_3, Execution Time: 0.000241 seconds
Node: bert/encoder/layer_3/attention/self/Reshape_3, Execution Time: 0.000049 seconds
Matmul Fuse Node: bert/encoder/layer_3/attention/output/dense/MatMul, Execution Time: 0.001128 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/moments/mean, Execution Time: 0.000180 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000386 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/moments/SquaredDifference__351, Execution Time: 0.000455 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/moments/variance, Execution Time: 0.000154 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000088 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000059 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/Rsqrt__353, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000079 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000079 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000570 seconds
Node: bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000667 seconds
Matmul Fuse Node: bert/encoder/layer_3/intermediate/dense/MatMul, Execution Time: 0.004129 seconds
Node: bert/encoder/layer_3/intermediate/dense/Pow, Execution Time: 0.000726 seconds
Node: bert/encoder/layer_3/intermediate/dense/mul, Execution Time: 0.001235 seconds
Node: bert/encoder/layer_3/intermediate/dense/add, Execution Time: 0.001406 seconds
Node: bert/encoder/layer_3/intermediate/dense/mul_1, Execution Time: 0.001123 seconds
Node: bert/encoder/layer_3/intermediate/dense/Tanh, Execution Time: 0.001110 seconds
Node: bert/encoder/layer_3/intermediate/dense/add_1, Execution Time: 0.001189 seconds
Node: bert/encoder/layer_3/intermediate/dense/mul_2, Execution Time: 0.001317 seconds
Node: bert/encoder/layer_3/intermediate/dense/mul_3, Execution Time: 0.001786 seconds
Matmul Fuse Node: bert/encoder/layer_3/output/dense/MatMul, Execution Time: 0.003806 seconds
Node: bert/encoder/layer_3/output/LayerNorm/moments/mean, Execution Time: 0.000238 seconds
Node: bert/encoder/layer_3/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000318 seconds
Node: bert/encoder/layer_3/output/LayerNorm/moments/SquaredDifference__355, Execution Time: 0.000446 seconds
Node: bert/encoder/layer_3/output/LayerNorm/moments/variance, Execution Time: 0.000205 seconds
Node: bert/encoder/layer_3/output/LayerNorm/batchnorm/add, Execution Time: 0.000099 seconds
Node: bert/encoder/layer_3/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_3/output/LayerNorm/batchnorm/Rsqrt__357, Execution Time: 0.000107 seconds
Node: bert/encoder/layer_3/output/LayerNorm/batchnorm/mul, Execution Time: 0.000096 seconds
Node: bert/encoder/layer_3/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000088 seconds
Node: bert/encoder/layer_3/output/LayerNorm/batchnorm/sub, Execution Time: 0.000113 seconds
Node: bert/encoder/layer_3/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000434 seconds
Node: bert/encoder/layer_3/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000534 seconds
Matmul Fuse Node: bert/encoder/layer_4/attention/self/value/MatMul, Execution Time: 0.002899 seconds
Node: bert/encoder/layer_4/attention/self/Reshape_2, Execution Time: 0.000021 seconds
Node: bert/encoder/layer_4/attention/self/transpose_2, Execution Time: 0.000262 seconds
Matmul Fuse Node: bert/encoder/layer_4/attention/self/query/MatMul, Execution Time: 0.002542 seconds
Node: bert/encoder/layer_4/attention/self/Reshape, Execution Time: 0.000014 seconds
Node: bert/encoder/layer_4/attention/self/transpose, Execution Time: 0.000249 seconds
Matmul Fuse Node: bert/encoder/layer_4/attention/self/key/MatMul, Execution Time: 0.002438 seconds
Node: bert/encoder/layer_4/attention/self/Reshape_1, Execution Time: 0.000012 seconds
Node: bert/encoder/layer_4/attention/self/MatMul__362, Execution Time: 0.000249 seconds
Node: bert/encoder/layer_4/attention/self/MatMul, Execution Time: 0.001404 seconds
Node: bert/encoder/layer_4/attention/self/Mul, Execution Time: 0.001179 seconds
Node: bert/encoder/layer_4/attention/self/add, Execution Time: 0.001856 seconds
Node: bert/encoder/layer_4/attention/self/Softmax, Execution Time: 0.002107 seconds
Node: bert/encoder/layer_4/attention/self/MatMul_1, Execution Time: 0.001110 seconds
Node: bert/encoder/layer_4/attention/self/transpose_3, Execution Time: 0.000237 seconds
Node: bert/encoder/layer_4/attention/self/Reshape_3, Execution Time: 0.000047 seconds
Matmul Fuse Node: bert/encoder/layer_4/attention/output/dense/MatMul, Execution Time: 0.001309 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/moments/mean, Execution Time: 0.000175 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000243 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/moments/SquaredDifference__365, Execution Time: 0.000333 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/moments/variance, Execution Time: 0.000156 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000057 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/Rsqrt__367, Execution Time: 0.000079 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000079 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000078 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000587 seconds
Node: bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000684 seconds
Matmul Fuse Node: bert/encoder/layer_4/intermediate/dense/MatMul, Execution Time: 0.004243 seconds
Node: bert/encoder/layer_4/intermediate/dense/Pow, Execution Time: 0.000731 seconds
Node: bert/encoder/layer_4/intermediate/dense/mul, Execution Time: 0.001199 seconds
Node: bert/encoder/layer_4/intermediate/dense/add, Execution Time: 0.001486 seconds
Node: bert/encoder/layer_4/intermediate/dense/mul_1, Execution Time: 0.001201 seconds
Node: bert/encoder/layer_4/intermediate/dense/Tanh, Execution Time: 0.001122 seconds
Node: bert/encoder/layer_4/intermediate/dense/add_1, Execution Time: 0.001201 seconds
Node: bert/encoder/layer_4/intermediate/dense/mul_2, Execution Time: 0.001146 seconds
Node: bert/encoder/layer_4/intermediate/dense/mul_3, Execution Time: 0.001469 seconds
Matmul Fuse Node: bert/encoder/layer_4/output/dense/MatMul, Execution Time: 0.002865 seconds
Node: bert/encoder/layer_4/output/LayerNorm/moments/mean, Execution Time: 0.000179 seconds
Node: bert/encoder/layer_4/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000241 seconds
Node: bert/encoder/layer_4/output/LayerNorm/moments/SquaredDifference__369, Execution Time: 0.000339 seconds
Node: bert/encoder/layer_4/output/LayerNorm/moments/variance, Execution Time: 0.000156 seconds
Node: bert/encoder/layer_4/output/LayerNorm/batchnorm/add, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_4/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000059 seconds
Node: bert/encoder/layer_4/output/LayerNorm/batchnorm/Rsqrt__371, Execution Time: 0.000083 seconds
Node: bert/encoder/layer_4/output/LayerNorm/batchnorm/mul, Execution Time: 0.000079 seconds
Node: bert/encoder/layer_4/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000092 seconds
Node: bert/encoder/layer_4/output/LayerNorm/batchnorm/sub, Execution Time: 0.000084 seconds
Node: bert/encoder/layer_4/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000341 seconds
Node: bert/encoder/layer_4/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000435 seconds
Matmul Fuse Node: bert/encoder/layer_5/attention/self/value/MatMul, Execution Time: 0.003960 seconds
Node: bert/encoder/layer_5/attention/self/Reshape_2, Execution Time: 0.000022 seconds
Node: bert/encoder/layer_5/attention/self/transpose_2, Execution Time: 0.000257 seconds
Matmul Fuse Node: bert/encoder/layer_5/attention/self/query/MatMul, Execution Time: 0.002440 seconds
Node: bert/encoder/layer_5/attention/self/Reshape, Execution Time: 0.000013 seconds
Node: bert/encoder/layer_5/attention/self/transpose, Execution Time: 0.000252 seconds
Matmul Fuse Node: bert/encoder/layer_5/attention/self/key/MatMul, Execution Time: 0.002446 seconds
Node: bert/encoder/layer_5/attention/self/Reshape_1, Execution Time: 0.000011 seconds
Node: bert/encoder/layer_5/attention/self/MatMul__376, Execution Time: 0.000251 seconds
Node: bert/encoder/layer_5/attention/self/MatMul, Execution Time: 0.001244 seconds
Node: bert/encoder/layer_5/attention/self/Mul, Execution Time: 0.001164 seconds
Node: bert/encoder/layer_5/attention/self/add, Execution Time: 0.001820 seconds
Node: bert/encoder/layer_5/attention/self/Softmax, Execution Time: 0.001953 seconds
Node: bert/encoder/layer_5/attention/self/MatMul_1, Execution Time: 0.001064 seconds
Node: bert/encoder/layer_5/attention/self/transpose_3, Execution Time: 0.000276 seconds
Node: bert/encoder/layer_5/attention/self/Reshape_3, Execution Time: 0.000045 seconds
Matmul Fuse Node: bert/encoder/layer_5/attention/output/dense/MatMul, Execution Time: 0.001237 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/moments/mean, Execution Time: 0.000190 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000249 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/moments/SquaredDifference__379, Execution Time: 0.000471 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/moments/variance, Execution Time: 0.000163 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000084 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000059 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/Rsqrt__381, Execution Time: 0.000080 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000098 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000080 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000573 seconds
Node: bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000682 seconds
Matmul Fuse Node: bert/encoder/layer_5/intermediate/dense/MatMul, Execution Time: 0.004223 seconds
Node: bert/encoder/layer_5/intermediate/dense/Pow, Execution Time: 0.000738 seconds
Node: bert/encoder/layer_5/intermediate/dense/mul, Execution Time: 0.001173 seconds
Node: bert/encoder/layer_5/intermediate/dense/add, Execution Time: 0.001558 seconds
Node: bert/encoder/layer_5/intermediate/dense/mul_1, Execution Time: 0.001120 seconds
Node: bert/encoder/layer_5/intermediate/dense/Tanh, Execution Time: 0.001077 seconds
Node: bert/encoder/layer_5/intermediate/dense/add_1, Execution Time: 0.001116 seconds
Node: bert/encoder/layer_5/intermediate/dense/mul_2, Execution Time: 0.001096 seconds
Node: bert/encoder/layer_5/intermediate/dense/mul_3, Execution Time: 0.001424 seconds
Matmul Fuse Node: bert/encoder/layer_5/output/dense/MatMul, Execution Time: 0.002838 seconds
Node: bert/encoder/layer_5/output/LayerNorm/moments/mean, Execution Time: 0.000184 seconds
Node: bert/encoder/layer_5/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000249 seconds
Node: bert/encoder/layer_5/output/LayerNorm/moments/SquaredDifference__383, Execution Time: 0.000327 seconds
Node: bert/encoder/layer_5/output/LayerNorm/moments/variance, Execution Time: 0.000155 seconds
Node: bert/encoder/layer_5/output/LayerNorm/batchnorm/add, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_5/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000060 seconds
Node: bert/encoder/layer_5/output/LayerNorm/batchnorm/Rsqrt__385, Execution Time: 0.000090 seconds
Node: bert/encoder/layer_5/output/LayerNorm/batchnorm/mul, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_5/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000075 seconds
Node: bert/encoder/layer_5/output/LayerNorm/batchnorm/sub, Execution Time: 0.000085 seconds
Node: bert/encoder/layer_5/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000334 seconds
Node: bert/encoder/layer_5/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000436 seconds
Matmul Fuse Node: bert/encoder/layer_6/attention/self/value/MatMul, Execution Time: 0.002932 seconds
Node: bert/encoder/layer_6/attention/self/Reshape_2, Execution Time: 0.000021 seconds
Node: bert/encoder/layer_6/attention/self/transpose_2, Execution Time: 0.000256 seconds
Matmul Fuse Node: bert/encoder/layer_6/attention/self/query/MatMul, Execution Time: 0.002506 seconds
Node: bert/encoder/layer_6/attention/self/Reshape, Execution Time: 0.000014 seconds
Node: bert/encoder/layer_6/attention/self/transpose, Execution Time: 0.000253 seconds
Matmul Fuse Node: bert/encoder/layer_6/attention/self/key/MatMul, Execution Time: 0.002383 seconds
Node: bert/encoder/layer_6/attention/self/Reshape_1, Execution Time: 0.000013 seconds
Node: bert/encoder/layer_6/attention/self/MatMul__390, Execution Time: 0.000243 seconds
Node: bert/encoder/layer_6/attention/self/MatMul, Execution Time: 0.001354 seconds
Node: bert/encoder/layer_6/attention/self/Mul, Execution Time: 0.001219 seconds
Node: bert/encoder/layer_6/attention/self/add, Execution Time: 0.001827 seconds
Node: bert/encoder/layer_6/attention/self/Softmax, Execution Time: 0.002038 seconds
Node: bert/encoder/layer_6/attention/self/MatMul_1, Execution Time: 0.001150 seconds
Node: bert/encoder/layer_6/attention/self/transpose_3, Execution Time: 0.000246 seconds
Node: bert/encoder/layer_6/attention/self/Reshape_3, Execution Time: 0.000048 seconds
Matmul Fuse Node: bert/encoder/layer_6/attention/output/dense/MatMul, Execution Time: 0.001310 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/moments/mean, Execution Time: 0.000202 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000269 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/moments/SquaredDifference__393, Execution Time: 0.000342 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/moments/variance, Execution Time: 0.000169 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000093 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000066 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/Rsqrt__395, Execution Time: 0.000086 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000098 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000085 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000093 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000468 seconds
Node: bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000721 seconds
Matmul Fuse Node: bert/encoder/layer_6/intermediate/dense/MatMul, Execution Time: 0.004496 seconds
Node: bert/encoder/layer_6/intermediate/dense/Pow, Execution Time: 0.000743 seconds
Node: bert/encoder/layer_6/intermediate/dense/mul, Execution Time: 0.001149 seconds
Node: bert/encoder/layer_6/intermediate/dense/add, Execution Time: 0.001630 seconds
Node: bert/encoder/layer_6/intermediate/dense/mul_1, Execution Time: 0.001597 seconds
Node: bert/encoder/layer_6/intermediate/dense/Tanh, Execution Time: 0.001440 seconds
Node: bert/encoder/layer_6/intermediate/dense/add_1, Execution Time: 0.001472 seconds
Node: bert/encoder/layer_6/intermediate/dense/mul_2, Execution Time: 0.001459 seconds
Node: bert/encoder/layer_6/intermediate/dense/mul_3, Execution Time: 0.001819 seconds
Matmul Fuse Node: bert/encoder/layer_6/output/dense/MatMul, Execution Time: 0.002854 seconds
Node: bert/encoder/layer_6/output/LayerNorm/moments/mean, Execution Time: 0.000175 seconds
Node: bert/encoder/layer_6/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000244 seconds
Node: bert/encoder/layer_6/output/LayerNorm/moments/SquaredDifference__397, Execution Time: 0.000333 seconds
Node: bert/encoder/layer_6/output/LayerNorm/moments/variance, Execution Time: 0.000155 seconds
Node: bert/encoder/layer_6/output/LayerNorm/batchnorm/add, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_6/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000057 seconds
Node: bert/encoder/layer_6/output/LayerNorm/batchnorm/Rsqrt__399, Execution Time: 0.000099 seconds
Node: bert/encoder/layer_6/output/LayerNorm/batchnorm/mul, Execution Time: 0.000079 seconds
Node: bert/encoder/layer_6/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000077 seconds
Node: bert/encoder/layer_6/output/LayerNorm/batchnorm/sub, Execution Time: 0.000078 seconds
Node: bert/encoder/layer_6/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000335 seconds
Node: bert/encoder/layer_6/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000436 seconds
Matmul Fuse Node: bert/encoder/layer_7/attention/self/value/MatMul, Execution Time: 0.002808 seconds
Node: bert/encoder/layer_7/attention/self/Reshape_2, Execution Time: 0.000021 seconds
Node: bert/encoder/layer_7/attention/self/transpose_2, Execution Time: 0.000246 seconds
Matmul Fuse Node: bert/encoder/layer_7/attention/self/query/MatMul, Execution Time: 0.002673 seconds
Node: bert/encoder/layer_7/attention/self/Reshape, Execution Time: 0.000015 seconds
Node: bert/encoder/layer_7/attention/self/transpose, Execution Time: 0.000253 seconds
Matmul Fuse Node: bert/encoder/layer_7/attention/self/key/MatMul, Execution Time: 0.002464 seconds
Node: bert/encoder/layer_7/attention/self/Reshape_1, Execution Time: 0.000012 seconds
Node: bert/encoder/layer_7/attention/self/MatMul__404, Execution Time: 0.000244 seconds
Node: bert/encoder/layer_7/attention/self/MatMul, Execution Time: 0.001390 seconds
Node: bert/encoder/layer_7/attention/self/Mul, Execution Time: 0.001194 seconds
Node: bert/encoder/layer_7/attention/self/add, Execution Time: 0.001980 seconds
Node: bert/encoder/layer_7/attention/self/Softmax, Execution Time: 0.001891 seconds
Node: bert/encoder/layer_7/attention/self/MatMul_1, Execution Time: 0.001181 seconds
Node: bert/encoder/layer_7/attention/self/transpose_3, Execution Time: 0.000238 seconds
Node: bert/encoder/layer_7/attention/self/Reshape_3, Execution Time: 0.000046 seconds
Matmul Fuse Node: bert/encoder/layer_7/attention/output/dense/MatMul, Execution Time: 0.001251 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/moments/mean, Execution Time: 0.000179 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000251 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/moments/SquaredDifference__407, Execution Time: 0.000348 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/moments/variance, Execution Time: 0.000175 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000058 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/Rsqrt__409, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000098 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000087 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000552 seconds
Node: bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000713 seconds
Matmul Fuse Node: bert/encoder/layer_7/intermediate/dense/MatMul, Execution Time: 0.004113 seconds
Node: bert/encoder/layer_7/intermediate/dense/Pow, Execution Time: 0.000735 seconds
Node: bert/encoder/layer_7/intermediate/dense/mul, Execution Time: 0.001155 seconds
Node: bert/encoder/layer_7/intermediate/dense/add, Execution Time: 0.001512 seconds
Node: bert/encoder/layer_7/intermediate/dense/mul_1, Execution Time: 0.001128 seconds
Node: bert/encoder/layer_7/intermediate/dense/Tanh, Execution Time: 0.001093 seconds
Node: bert/encoder/layer_7/intermediate/dense/add_1, Execution Time: 0.001129 seconds
Node: bert/encoder/layer_7/intermediate/dense/mul_2, Execution Time: 0.001164 seconds
Node: bert/encoder/layer_7/intermediate/dense/mul_3, Execution Time: 0.001491 seconds
Matmul Fuse Node: bert/encoder/layer_7/output/dense/MatMul, Execution Time: 0.002885 seconds
Node: bert/encoder/layer_7/output/LayerNorm/moments/mean, Execution Time: 0.000183 seconds
Node: bert/encoder/layer_7/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000250 seconds
Node: bert/encoder/layer_7/output/LayerNorm/moments/SquaredDifference__411, Execution Time: 0.000327 seconds
Node: bert/encoder/layer_7/output/LayerNorm/moments/variance, Execution Time: 0.000154 seconds
Node: bert/encoder/layer_7/output/LayerNorm/batchnorm/add, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_7/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000058 seconds
Node: bert/encoder/layer_7/output/LayerNorm/batchnorm/Rsqrt__413, Execution Time: 0.000085 seconds
Node: bert/encoder/layer_7/output/LayerNorm/batchnorm/mul, Execution Time: 0.000085 seconds
Node: bert/encoder/layer_7/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_7/output/LayerNorm/batchnorm/sub, Execution Time: 0.000079 seconds
Node: bert/encoder/layer_7/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000333 seconds
Node: bert/encoder/layer_7/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000437 seconds
Matmul Fuse Node: bert/encoder/layer_8/attention/self/value/MatMul, Execution Time: 0.002903 seconds
Node: bert/encoder/layer_8/attention/self/Reshape_2, Execution Time: 0.000022 seconds
Node: bert/encoder/layer_8/attention/self/transpose_2, Execution Time: 0.000252 seconds
Matmul Fuse Node: bert/encoder/layer_8/attention/self/query/MatMul, Execution Time: 0.002493 seconds
Node: bert/encoder/layer_8/attention/self/Reshape, Execution Time: 0.000014 seconds
Node: bert/encoder/layer_8/attention/self/transpose, Execution Time: 0.000250 seconds
Matmul Fuse Node: bert/encoder/layer_8/attention/self/key/MatMul, Execution Time: 0.002375 seconds
Node: bert/encoder/layer_8/attention/self/Reshape_1, Execution Time: 0.000012 seconds
Node: bert/encoder/layer_8/attention/self/MatMul__418, Execution Time: 0.000246 seconds
Node: bert/encoder/layer_8/attention/self/MatMul, Execution Time: 0.001337 seconds
Node: bert/encoder/layer_8/attention/self/Mul, Execution Time: 0.001168 seconds
Node: bert/encoder/layer_8/attention/self/add, Execution Time: 0.001858 seconds
Node: bert/encoder/layer_8/attention/self/Softmax, Execution Time: 0.002032 seconds
Node: bert/encoder/layer_8/attention/self/MatMul_1, Execution Time: 0.001093 seconds
Node: bert/encoder/layer_8/attention/self/transpose_3, Execution Time: 0.000242 seconds
Node: bert/encoder/layer_8/attention/self/Reshape_3, Execution Time: 0.000047 seconds
Matmul Fuse Node: bert/encoder/layer_8/attention/output/dense/MatMul, Execution Time: 0.001178 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/moments/mean, Execution Time: 0.000181 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000245 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/moments/SquaredDifference__421, Execution Time: 0.000330 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/moments/variance, Execution Time: 0.000159 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000083 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000058 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/Rsqrt__423, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000078 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000559 seconds
Node: bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000686 seconds
Matmul Fuse Node: bert/encoder/layer_8/intermediate/dense/MatMul, Execution Time: 0.004353 seconds
Node: bert/encoder/layer_8/intermediate/dense/Pow, Execution Time: 0.000730 seconds
Node: bert/encoder/layer_8/intermediate/dense/mul, Execution Time: 0.001183 seconds
Node: bert/encoder/layer_8/intermediate/dense/add, Execution Time: 0.001496 seconds
Node: bert/encoder/layer_8/intermediate/dense/mul_1, Execution Time: 0.001133 seconds
Node: bert/encoder/layer_8/intermediate/dense/Tanh, Execution Time: 0.001168 seconds
Node: bert/encoder/layer_8/intermediate/dense/add_1, Execution Time: 0.001154 seconds
Node: bert/encoder/layer_8/intermediate/dense/mul_2, Execution Time: 0.001138 seconds
Node: bert/encoder/layer_8/intermediate/dense/mul_3, Execution Time: 0.001387 seconds
Matmul Fuse Node: bert/encoder/layer_8/output/dense/MatMul, Execution Time: 0.002991 seconds
Node: bert/encoder/layer_8/output/LayerNorm/moments/mean, Execution Time: 0.000182 seconds
Node: bert/encoder/layer_8/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000258 seconds
Node: bert/encoder/layer_8/output/LayerNorm/moments/SquaredDifference__425, Execution Time: 0.000333 seconds
Node: bert/encoder/layer_8/output/LayerNorm/moments/variance, Execution Time: 0.000160 seconds
Node: bert/encoder/layer_8/output/LayerNorm/batchnorm/add, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_8/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000059 seconds
Node: bert/encoder/layer_8/output/LayerNorm/batchnorm/Rsqrt__427, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_8/output/LayerNorm/batchnorm/mul, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_8/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_8/output/LayerNorm/batchnorm/sub, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_8/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000342 seconds
Node: bert/encoder/layer_8/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000425 seconds
Matmul Fuse Node: bert/encoder/layer_9/attention/self/value/MatMul, Execution Time: 0.002894 seconds
Node: bert/encoder/layer_9/attention/self/Reshape_2, Execution Time: 0.000022 seconds
Node: bert/encoder/layer_9/attention/self/transpose_2, Execution Time: 0.000255 seconds
Matmul Fuse Node: bert/encoder/layer_9/attention/self/query/MatMul, Execution Time: 0.002460 seconds
Node: bert/encoder/layer_9/attention/self/Reshape, Execution Time: 0.000013 seconds
Node: bert/encoder/layer_9/attention/self/transpose, Execution Time: 0.000249 seconds
Matmul Fuse Node: bert/encoder/layer_9/attention/self/key/MatMul, Execution Time: 0.002440 seconds
Node: bert/encoder/layer_9/attention/self/Reshape_1, Execution Time: 0.000012 seconds
Node: bert/encoder/layer_9/attention/self/MatMul__432, Execution Time: 0.000247 seconds
Node: bert/encoder/layer_9/attention/self/MatMul, Execution Time: 0.001341 seconds
Node: bert/encoder/layer_9/attention/self/Mul, Execution Time: 0.001163 seconds
Node: bert/encoder/layer_9/attention/self/add, Execution Time: 0.001809 seconds
Node: bert/encoder/layer_9/attention/self/Softmax, Execution Time: 0.001965 seconds
Node: bert/encoder/layer_9/attention/self/MatMul_1, Execution Time: 0.001070 seconds
Node: bert/encoder/layer_9/attention/self/transpose_3, Execution Time: 0.000237 seconds
Node: bert/encoder/layer_9/attention/self/Reshape_3, Execution Time: 0.000045 seconds
Matmul Fuse Node: bert/encoder/layer_9/attention/output/dense/MatMul, Execution Time: 0.001157 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/moments/mean, Execution Time: 0.000197 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000245 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/moments/SquaredDifference__435, Execution Time: 0.000330 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/moments/variance, Execution Time: 0.000159 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000059 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/Rsqrt__437, Execution Time: 0.000084 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000101 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000084 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000078 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000559 seconds
Node: bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000698 seconds
Matmul Fuse Node: bert/encoder/layer_9/intermediate/dense/MatMul, Execution Time: 0.004072 seconds
Node: bert/encoder/layer_9/intermediate/dense/Pow, Execution Time: 0.000727 seconds
Node: bert/encoder/layer_9/intermediate/dense/mul, Execution Time: 0.001199 seconds
Node: bert/encoder/layer_9/intermediate/dense/add, Execution Time: 0.001454 seconds
Node: bert/encoder/layer_9/intermediate/dense/mul_1, Execution Time: 0.001218 seconds
Node: bert/encoder/layer_9/intermediate/dense/Tanh, Execution Time: 0.001086 seconds
Node: bert/encoder/layer_9/intermediate/dense/add_1, Execution Time: 0.001137 seconds
Node: bert/encoder/layer_9/intermediate/dense/mul_2, Execution Time: 0.001107 seconds
Node: bert/encoder/layer_9/intermediate/dense/mul_3, Execution Time: 0.001379 seconds
Matmul Fuse Node: bert/encoder/layer_9/output/dense/MatMul, Execution Time: 0.002824 seconds
Node: bert/encoder/layer_9/output/LayerNorm/moments/mean, Execution Time: 0.000182 seconds
Node: bert/encoder/layer_9/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000251 seconds
Node: bert/encoder/layer_9/output/LayerNorm/moments/SquaredDifference__439, Execution Time: 0.000329 seconds
Node: bert/encoder/layer_9/output/LayerNorm/moments/variance, Execution Time: 0.000154 seconds
Node: bert/encoder/layer_9/output/LayerNorm/batchnorm/add, Execution Time: 0.000083 seconds
Node: bert/encoder/layer_9/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000059 seconds
Node: bert/encoder/layer_9/output/LayerNorm/batchnorm/Rsqrt__441, Execution Time: 0.000084 seconds
Node: bert/encoder/layer_9/output/LayerNorm/batchnorm/mul, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_9/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000096 seconds
Node: bert/encoder/layer_9/output/LayerNorm/batchnorm/sub, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_9/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000331 seconds
Node: bert/encoder/layer_9/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000436 seconds
Matmul Fuse Node: bert/encoder/layer_10/attention/self/value/MatMul, Execution Time: 0.004091 seconds
Node: bert/encoder/layer_10/attention/self/Reshape_2, Execution Time: 0.000021 seconds
Node: bert/encoder/layer_10/attention/self/transpose_2, Execution Time: 0.000257 seconds
Matmul Fuse Node: bert/encoder/layer_10/attention/self/query/MatMul, Execution Time: 0.002522 seconds
Node: bert/encoder/layer_10/attention/self/Reshape, Execution Time: 0.000013 seconds
Node: bert/encoder/layer_10/attention/self/transpose, Execution Time: 0.000260 seconds
Matmul Fuse Node: bert/encoder/layer_10/attention/self/key/MatMul, Execution Time: 0.002380 seconds
Node: bert/encoder/layer_10/attention/self/Reshape_1, Execution Time: 0.000012 seconds
Node: bert/encoder/layer_10/attention/self/MatMul__446, Execution Time: 0.000246 seconds
Node: bert/encoder/layer_10/attention/self/MatMul, Execution Time: 0.001328 seconds
Node: bert/encoder/layer_10/attention/self/Mul, Execution Time: 0.001195 seconds
Node: bert/encoder/layer_10/attention/self/add, Execution Time: 0.001870 seconds
Node: bert/encoder/layer_10/attention/self/Softmax, Execution Time: 0.001986 seconds
Node: bert/encoder/layer_10/attention/self/MatMul_1, Execution Time: 0.001072 seconds
Node: bert/encoder/layer_10/attention/self/transpose_3, Execution Time: 0.000238 seconds
Node: bert/encoder/layer_10/attention/self/Reshape_3, Execution Time: 0.000051 seconds
Matmul Fuse Node: bert/encoder/layer_10/attention/output/dense/MatMul, Execution Time: 0.001109 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/moments/mean, Execution Time: 0.000175 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000308 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/moments/SquaredDifference__449, Execution Time: 0.000433 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/moments/variance, Execution Time: 0.000211 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000099 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000074 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/Rsqrt__451, Execution Time: 0.000107 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000101 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000102 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000097 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000704 seconds
Node: bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000876 seconds
Matmul Fuse Node: bert/encoder/layer_10/intermediate/dense/MatMul, Execution Time: 0.005988 seconds
Node: bert/encoder/layer_10/intermediate/dense/Pow, Execution Time: 0.000705 seconds
Node: bert/encoder/layer_10/intermediate/dense/mul, Execution Time: 0.001194 seconds
Node: bert/encoder/layer_10/intermediate/dense/add, Execution Time: 0.001401 seconds
Node: bert/encoder/layer_10/intermediate/dense/mul_1, Execution Time: 0.001104 seconds
Node: bert/encoder/layer_10/intermediate/dense/Tanh, Execution Time: 0.001094 seconds
Node: bert/encoder/layer_10/intermediate/dense/add_1, Execution Time: 0.001137 seconds
Node: bert/encoder/layer_10/intermediate/dense/mul_2, Execution Time: 0.001155 seconds
Node: bert/encoder/layer_10/intermediate/dense/mul_3, Execution Time: 0.001385 seconds
Matmul Fuse Node: bert/encoder/layer_10/output/dense/MatMul, Execution Time: 0.002557 seconds
Node: bert/encoder/layer_10/output/LayerNorm/moments/mean, Execution Time: 0.000184 seconds
Node: bert/encoder/layer_10/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000247 seconds
Node: bert/encoder/layer_10/output/LayerNorm/moments/SquaredDifference__453, Execution Time: 0.000327 seconds
Node: bert/encoder/layer_10/output/LayerNorm/moments/variance, Execution Time: 0.000155 seconds
Node: bert/encoder/layer_10/output/LayerNorm/batchnorm/add, Execution Time: 0.000081 seconds
Node: bert/encoder/layer_10/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000059 seconds
Node: bert/encoder/layer_10/output/LayerNorm/batchnorm/Rsqrt__455, Execution Time: 0.000105 seconds
Node: bert/encoder/layer_10/output/LayerNorm/batchnorm/mul, Execution Time: 0.000086 seconds
Node: bert/encoder/layer_10/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000094 seconds
Node: bert/encoder/layer_10/output/LayerNorm/batchnorm/sub, Execution Time: 0.000080 seconds
Node: bert/encoder/layer_10/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000334 seconds
Node: bert/encoder/layer_10/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000441 seconds
Matmul Fuse Node: bert/encoder/layer_11/attention/self/value/MatMul, Execution Time: 0.002807 seconds
Node: bert/encoder/layer_11/attention/self/Reshape_2, Execution Time: 0.000021 seconds
Node: bert/encoder/layer_11/attention/self/transpose_2, Execution Time: 0.000258 seconds
Matmul Fuse Node: bert/encoder/layer_11/attention/self/query/MatMul, Execution Time: 0.002520 seconds
Node: bert/encoder/layer_11/attention/self/Reshape, Execution Time: 0.000013 seconds
Node: bert/encoder/layer_11/attention/self/transpose, Execution Time: 0.000254 seconds
Matmul Fuse Node: bert/encoder/layer_11/attention/self/key/MatMul, Execution Time: 0.002469 seconds
Node: bert/encoder/layer_11/attention/self/Reshape_1, Execution Time: 0.000012 seconds
Node: bert/encoder/layer_11/attention/self/MatMul__460, Execution Time: 0.000247 seconds
Node: bert/encoder/layer_11/attention/self/MatMul, Execution Time: 0.001390 seconds
Node: bert/encoder/layer_11/attention/self/Mul, Execution Time: 0.001185 seconds
Node: bert/encoder/layer_11/attention/self/add, Execution Time: 0.001868 seconds
Node: bert/encoder/layer_11/attention/self/Softmax, Execution Time: 0.001983 seconds
Node: bert/encoder/layer_11/attention/self/MatMul_1, Execution Time: 0.001104 seconds
Node: bert/encoder/layer_11/attention/self/transpose_3, Execution Time: 0.000240 seconds
Node: bert/encoder/layer_11/attention/self/Reshape_3, Execution Time: 0.000048 seconds
Matmul Fuse Node: bert/encoder/layer_11/attention/output/dense/MatMul, Execution Time: 0.001165 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/moments/mean, Execution Time: 0.000172 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000242 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/moments/SquaredDifference__463, Execution Time: 0.000333 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/moments/variance, Execution Time: 0.000166 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/add, Execution Time: 0.000079 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000058 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/Rsqrt__465, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/mul, Execution Time: 0.000076 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000074 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/sub, Execution Time: 0.000076 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000562 seconds
Node: bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000669 seconds
Matmul Fuse Node: bert/encoder/layer_11/intermediate/dense/MatMul, Execution Time: 0.004179 seconds
Node: bert/encoder/layer_11/intermediate/dense/Pow, Execution Time: 0.000729 seconds
Node: bert/encoder/layer_11/intermediate/dense/mul, Execution Time: 0.001209 seconds
Node: bert/encoder/layer_11/intermediate/dense/add, Execution Time: 0.001439 seconds
Node: bert/encoder/layer_11/intermediate/dense/mul_1, Execution Time: 0.001104 seconds
Node: bert/encoder/layer_11/intermediate/dense/Tanh, Execution Time: 0.001094 seconds
Node: bert/encoder/layer_11/intermediate/dense/add_1, Execution Time: 0.001142 seconds
Node: bert/encoder/layer_11/intermediate/dense/mul_2, Execution Time: 0.001143 seconds
Node: bert/encoder/layer_11/intermediate/dense/mul_3, Execution Time: 0.001404 seconds
Matmul Fuse Node: bert/encoder/layer_11/output/dense/MatMul, Execution Time: 0.002955 seconds
Node: bert/encoder/layer_11/output/LayerNorm/moments/mean, Execution Time: 0.000190 seconds
Node: bert/encoder/layer_11/output/LayerNorm/moments/SquaredDifference, Execution Time: 0.000246 seconds
Node: bert/encoder/layer_11/output/LayerNorm/moments/SquaredDifference__467, Execution Time: 0.000330 seconds
Node: bert/encoder/layer_11/output/LayerNorm/moments/variance, Execution Time: 0.000155 seconds
Node: bert/encoder/layer_11/output/LayerNorm/batchnorm/add, Execution Time: 0.000082 seconds
Node: bert/encoder/layer_11/output/LayerNorm/batchnorm/Rsqrt, Execution Time: 0.000058 seconds
Node: bert/encoder/layer_11/output/LayerNorm/batchnorm/Rsqrt__469, Execution Time: 0.000086 seconds
Node: bert/encoder/layer_11/output/LayerNorm/batchnorm/mul, Execution Time: 0.000084 seconds
Node: bert/encoder/layer_11/output/LayerNorm/batchnorm/mul_2, Execution Time: 0.000095 seconds
Node: bert/encoder/layer_11/output/LayerNorm/batchnorm/sub, Execution Time: 0.000080 seconds
Node: bert/encoder/layer_11/output/LayerNorm/batchnorm/mul_1, Execution Time: 0.000335 seconds
Node: bert/encoder/layer_11/output/LayerNorm/batchnorm/add_1, Execution Time: 0.000436 seconds
Matmul Fuse Node: MatMul, Execution Time: 0.004485 seconds
Node: Reshape_1, Execution Time: 0.000021 seconds
Node: transpose, Execution Time: 0.000088 seconds
Node: unstack, Execution Time: 0.000050 seconds
Node: unstack__490, Execution Time: 0.000005 seconds
Node: unstack__488, Execution Time: 0.000006 seconds
Total Execution Time: 0.676711 seconds
Total Matmul Fuse Execution Time: 0.241226 seconds
Execution complete.
Total execution time: 0.680221 seconds
Model outputs: {'unstack:1': array([nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan], dtype=float16), 'unstack:0': array(None, dtype=object), 'unique_ids:0': array([], dtype=int64)}
Execution order: ['unique_ids_graph_outputs_Identity__10', 'bert/encoder/Shape', 'bert/encoder/Shape__12', 'bert/encoder/strided_slice', 'bert/encoder/strided_slice__16', 'bert/encoder/strided_slice__17', 'bert/encoder/ones/packed_Unsqueeze__18', 'bert/encoder/ones/packed_Concat__21', 'bert/encoder/ones__22', 'bert/encoder/ones', 'bert/encoder/Reshape', 'bert/encoder/Cast', 'bert/encoder/mul', 'bert/encoder/layer_9/attention/self/ExpandDims', 'bert/encoder/layer_9/attention/self/sub', 'bert/encoder/layer_9/attention/self/mul_1', 'bert/embeddings/Reshape_2', 'bert/embeddings/Reshape', 'bert/embeddings/GatherV2', 'bert/embeddings/Reshape_1', 'bert/embeddings/one_hot', 'bert/embeddings/MatMul', 'bert/embeddings/Reshape_3', 'bert/embeddings/add', 'bert/embeddings/add_1', 'bert/embeddings/LayerNorm/moments/mean', 'bert/embeddings/LayerNorm/moments/SquaredDifference', 'bert/embeddings/LayerNorm/moments/SquaredDifference__72', 'bert/embeddings/LayerNorm/moments/variance', 'bert/embeddings/LayerNorm/batchnorm/add', 'bert/embeddings/LayerNorm/batchnorm/Rsqrt', 'bert/embeddings/LayerNorm/batchnorm/Rsqrt__74', 'bert/embeddings/LayerNorm/batchnorm/mul', 'bert/embeddings/LayerNorm/batchnorm/mul_2', 'bert/embeddings/LayerNorm/batchnorm/sub', 'bert/embeddings/LayerNorm/batchnorm/mul_1', 'bert/embeddings/LayerNorm/batchnorm/add_1', 'bert/encoder/Reshape_1', 'bert/encoder/layer_0/attention/self/value/MatMul', 'bert/encoder/layer_0/attention/self/value/BiasAdd', 'bert/encoder/layer_0/attention/self/Reshape_2', 'bert/encoder/layer_0/attention/self/transpose_2', 'bert/encoder/layer_0/attention/self/query/MatMul', 'bert/encoder/layer_0/attention/self/query/BiasAdd', 'bert/encoder/layer_0/attention/self/Reshape', 'bert/encoder/layer_0/attention/self/transpose', 'bert/encoder/layer_0/attention/self/key/MatMul', 'bert/encoder/layer_0/attention/self/key/BiasAdd', 'bert/encoder/layer_0/attention/self/Reshape_1', 'bert/encoder/layer_0/attention/self/MatMul__306', 'bert/encoder/layer_0/attention/self/MatMul', 'bert/encoder/layer_0/attention/self/Mul', 'bert/encoder/layer_0/attention/self/add', 'bert/encoder/layer_0/attention/self/Softmax', 'bert/encoder/layer_0/attention/self/MatMul_1', 'bert/encoder/layer_0/attention/self/transpose_3', 'bert/encoder/layer_0/attention/self/Reshape_3', 'bert/encoder/layer_0/attention/output/dense/MatMul', 'bert/encoder/layer_0/attention/output/dense/BiasAdd', 'bert/encoder/layer_0/attention/output/add', 'bert/encoder/layer_0/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_0/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_0/attention/output/LayerNorm/moments/SquaredDifference__309', 'bert/encoder/layer_0/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/Rsqrt__311', 'bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_0/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_0/intermediate/dense/MatMul', 'bert/encoder/layer_0/intermediate/dense/BiasAdd', 'bert/encoder/layer_0/intermediate/dense/Pow', 'bert/encoder/layer_0/intermediate/dense/mul', 'bert/encoder/layer_0/intermediate/dense/add', 'bert/encoder/layer_0/intermediate/dense/mul_1', 'bert/encoder/layer_0/intermediate/dense/Tanh', 'bert/encoder/layer_0/intermediate/dense/add_1', 'bert/encoder/layer_0/intermediate/dense/mul_2', 'bert/encoder/layer_0/intermediate/dense/mul_3', 'bert/encoder/layer_0/output/dense/MatMul', 'bert/encoder/layer_0/output/dense/BiasAdd', 'bert/encoder/layer_0/output/add', 'bert/encoder/layer_0/output/LayerNorm/moments/mean', 'bert/encoder/layer_0/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_0/output/LayerNorm/moments/SquaredDifference__313', 'bert/encoder/layer_0/output/LayerNorm/moments/variance', 'bert/encoder/layer_0/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_0/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_0/output/LayerNorm/batchnorm/Rsqrt__315', 'bert/encoder/layer_0/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_0/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_0/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_0/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_0/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_1/attention/self/value/MatMul', 'bert/encoder/layer_1/attention/self/value/BiasAdd', 'bert/encoder/layer_1/attention/self/Reshape_2', 'bert/encoder/layer_1/attention/self/transpose_2', 'bert/encoder/layer_1/attention/self/query/MatMul', 'bert/encoder/layer_1/attention/self/query/BiasAdd', 'bert/encoder/layer_1/attention/self/Reshape', 'bert/encoder/layer_1/attention/self/transpose', 'bert/encoder/layer_1/attention/self/key/MatMul', 'bert/encoder/layer_1/attention/self/key/BiasAdd', 'bert/encoder/layer_1/attention/self/Reshape_1', 'bert/encoder/layer_1/attention/self/MatMul__320', 'bert/encoder/layer_1/attention/self/MatMul', 'bert/encoder/layer_1/attention/self/Mul', 'bert/encoder/layer_1/attention/self/add', 'bert/encoder/layer_1/attention/self/Softmax', 'bert/encoder/layer_1/attention/self/MatMul_1', 'bert/encoder/layer_1/attention/self/transpose_3', 'bert/encoder/layer_1/attention/self/Reshape_3', 'bert/encoder/layer_1/attention/output/dense/MatMul', 'bert/encoder/layer_1/attention/output/dense/BiasAdd', 'bert/encoder/layer_1/attention/output/add', 'bert/encoder/layer_1/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_1/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_1/attention/output/LayerNorm/moments/SquaredDifference__323', 'bert/encoder/layer_1/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/Rsqrt__325', 'bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_1/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_1/intermediate/dense/MatMul', 'bert/encoder/layer_1/intermediate/dense/BiasAdd', 'bert/encoder/layer_1/intermediate/dense/Pow', 'bert/encoder/layer_1/intermediate/dense/mul', 'bert/encoder/layer_1/intermediate/dense/add', 'bert/encoder/layer_1/intermediate/dense/mul_1', 'bert/encoder/layer_1/intermediate/dense/Tanh', 'bert/encoder/layer_1/intermediate/dense/add_1', 'bert/encoder/layer_1/intermediate/dense/mul_2', 'bert/encoder/layer_1/intermediate/dense/mul_3', 'bert/encoder/layer_1/output/dense/MatMul', 'bert/encoder/layer_1/output/dense/BiasAdd', 'bert/encoder/layer_1/output/add', 'bert/encoder/layer_1/output/LayerNorm/moments/mean', 'bert/encoder/layer_1/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_1/output/LayerNorm/moments/SquaredDifference__327', 'bert/encoder/layer_1/output/LayerNorm/moments/variance', 'bert/encoder/layer_1/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_1/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_1/output/LayerNorm/batchnorm/Rsqrt__329', 'bert/encoder/layer_1/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_1/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_1/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_1/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_1/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_2/attention/self/value/MatMul', 'bert/encoder/layer_2/attention/self/value/BiasAdd', 'bert/encoder/layer_2/attention/self/Reshape_2', 'bert/encoder/layer_2/attention/self/transpose_2', 'bert/encoder/layer_2/attention/self/query/MatMul', 'bert/encoder/layer_2/attention/self/query/BiasAdd', 'bert/encoder/layer_2/attention/self/Reshape', 'bert/encoder/layer_2/attention/self/transpose', 'bert/encoder/layer_2/attention/self/key/MatMul', 'bert/encoder/layer_2/attention/self/key/BiasAdd', 'bert/encoder/layer_2/attention/self/Reshape_1', 'bert/encoder/layer_2/attention/self/MatMul__334', 'bert/encoder/layer_2/attention/self/MatMul', 'bert/encoder/layer_2/attention/self/Mul', 'bert/encoder/layer_2/attention/self/add', 'bert/encoder/layer_2/attention/self/Softmax', 'bert/encoder/layer_2/attention/self/MatMul_1', 'bert/encoder/layer_2/attention/self/transpose_3', 'bert/encoder/layer_2/attention/self/Reshape_3', 'bert/encoder/layer_2/attention/output/dense/MatMul', 'bert/encoder/layer_2/attention/output/dense/BiasAdd', 'bert/encoder/layer_2/attention/output/add', 'bert/encoder/layer_2/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_2/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_2/attention/output/LayerNorm/moments/SquaredDifference__337', 'bert/encoder/layer_2/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/Rsqrt__339', 'bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_2/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_2/intermediate/dense/MatMul', 'bert/encoder/layer_2/intermediate/dense/BiasAdd', 'bert/encoder/layer_2/intermediate/dense/Pow', 'bert/encoder/layer_2/intermediate/dense/mul', 'bert/encoder/layer_2/intermediate/dense/add', 'bert/encoder/layer_2/intermediate/dense/mul_1', 'bert/encoder/layer_2/intermediate/dense/Tanh', 'bert/encoder/layer_2/intermediate/dense/add_1', 'bert/encoder/layer_2/intermediate/dense/mul_2', 'bert/encoder/layer_2/intermediate/dense/mul_3', 'bert/encoder/layer_2/output/dense/MatMul', 'bert/encoder/layer_2/output/dense/BiasAdd', 'bert/encoder/layer_2/output/add', 'bert/encoder/layer_2/output/LayerNorm/moments/mean', 'bert/encoder/layer_2/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_2/output/LayerNorm/moments/SquaredDifference__341', 'bert/encoder/layer_2/output/LayerNorm/moments/variance', 'bert/encoder/layer_2/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_2/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_2/output/LayerNorm/batchnorm/Rsqrt__343', 'bert/encoder/layer_2/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_2/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_2/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_2/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_2/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_3/attention/self/value/MatMul', 'bert/encoder/layer_3/attention/self/value/BiasAdd', 'bert/encoder/layer_3/attention/self/Reshape_2', 'bert/encoder/layer_3/attention/self/transpose_2', 'bert/encoder/layer_3/attention/self/query/MatMul', 'bert/encoder/layer_3/attention/self/query/BiasAdd', 'bert/encoder/layer_3/attention/self/Reshape', 'bert/encoder/layer_3/attention/self/transpose', 'bert/encoder/layer_3/attention/self/key/MatMul', 'bert/encoder/layer_3/attention/self/key/BiasAdd', 'bert/encoder/layer_3/attention/self/Reshape_1', 'bert/encoder/layer_3/attention/self/MatMul__348', 'bert/encoder/layer_3/attention/self/MatMul', 'bert/encoder/layer_3/attention/self/Mul', 'bert/encoder/layer_3/attention/self/add', 'bert/encoder/layer_3/attention/self/Softmax', 'bert/encoder/layer_3/attention/self/MatMul_1', 'bert/encoder/layer_3/attention/self/transpose_3', 'bert/encoder/layer_3/attention/self/Reshape_3', 'bert/encoder/layer_3/attention/output/dense/MatMul', 'bert/encoder/layer_3/attention/output/dense/BiasAdd', 'bert/encoder/layer_3/attention/output/add', 'bert/encoder/layer_3/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_3/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_3/attention/output/LayerNorm/moments/SquaredDifference__351', 'bert/encoder/layer_3/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/Rsqrt__353', 'bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_3/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_3/intermediate/dense/MatMul', 'bert/encoder/layer_3/intermediate/dense/BiasAdd', 'bert/encoder/layer_3/intermediate/dense/Pow', 'bert/encoder/layer_3/intermediate/dense/mul', 'bert/encoder/layer_3/intermediate/dense/add', 'bert/encoder/layer_3/intermediate/dense/mul_1', 'bert/encoder/layer_3/intermediate/dense/Tanh', 'bert/encoder/layer_3/intermediate/dense/add_1', 'bert/encoder/layer_3/intermediate/dense/mul_2', 'bert/encoder/layer_3/intermediate/dense/mul_3', 'bert/encoder/layer_3/output/dense/MatMul', 'bert/encoder/layer_3/output/dense/BiasAdd', 'bert/encoder/layer_3/output/add', 'bert/encoder/layer_3/output/LayerNorm/moments/mean', 'bert/encoder/layer_3/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_3/output/LayerNorm/moments/SquaredDifference__355', 'bert/encoder/layer_3/output/LayerNorm/moments/variance', 'bert/encoder/layer_3/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_3/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_3/output/LayerNorm/batchnorm/Rsqrt__357', 'bert/encoder/layer_3/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_3/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_3/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_3/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_3/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_4/attention/self/value/MatMul', 'bert/encoder/layer_4/attention/self/value/BiasAdd', 'bert/encoder/layer_4/attention/self/Reshape_2', 'bert/encoder/layer_4/attention/self/transpose_2', 'bert/encoder/layer_4/attention/self/query/MatMul', 'bert/encoder/layer_4/attention/self/query/BiasAdd', 'bert/encoder/layer_4/attention/self/Reshape', 'bert/encoder/layer_4/attention/self/transpose', 'bert/encoder/layer_4/attention/self/key/MatMul', 'bert/encoder/layer_4/attention/self/key/BiasAdd', 'bert/encoder/layer_4/attention/self/Reshape_1', 'bert/encoder/layer_4/attention/self/MatMul__362', 'bert/encoder/layer_4/attention/self/MatMul', 'bert/encoder/layer_4/attention/self/Mul', 'bert/encoder/layer_4/attention/self/add', 'bert/encoder/layer_4/attention/self/Softmax', 'bert/encoder/layer_4/attention/self/MatMul_1', 'bert/encoder/layer_4/attention/self/transpose_3', 'bert/encoder/layer_4/attention/self/Reshape_3', 'bert/encoder/layer_4/attention/output/dense/MatMul', 'bert/encoder/layer_4/attention/output/dense/BiasAdd', 'bert/encoder/layer_4/attention/output/add', 'bert/encoder/layer_4/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_4/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_4/attention/output/LayerNorm/moments/SquaredDifference__365', 'bert/encoder/layer_4/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/Rsqrt__367', 'bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_4/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_4/intermediate/dense/MatMul', 'bert/encoder/layer_4/intermediate/dense/BiasAdd', 'bert/encoder/layer_4/intermediate/dense/Pow', 'bert/encoder/layer_4/intermediate/dense/mul', 'bert/encoder/layer_4/intermediate/dense/add', 'bert/encoder/layer_4/intermediate/dense/mul_1', 'bert/encoder/layer_4/intermediate/dense/Tanh', 'bert/encoder/layer_4/intermediate/dense/add_1', 'bert/encoder/layer_4/intermediate/dense/mul_2', 'bert/encoder/layer_4/intermediate/dense/mul_3', 'bert/encoder/layer_4/output/dense/MatMul', 'bert/encoder/layer_4/output/dense/BiasAdd', 'bert/encoder/layer_4/output/add', 'bert/encoder/layer_4/output/LayerNorm/moments/mean', 'bert/encoder/layer_4/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_4/output/LayerNorm/moments/SquaredDifference__369', 'bert/encoder/layer_4/output/LayerNorm/moments/variance', 'bert/encoder/layer_4/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_4/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_4/output/LayerNorm/batchnorm/Rsqrt__371', 'bert/encoder/layer_4/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_4/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_4/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_4/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_4/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_5/attention/self/value/MatMul', 'bert/encoder/layer_5/attention/self/value/BiasAdd', 'bert/encoder/layer_5/attention/self/Reshape_2', 'bert/encoder/layer_5/attention/self/transpose_2', 'bert/encoder/layer_5/attention/self/query/MatMul', 'bert/encoder/layer_5/attention/self/query/BiasAdd', 'bert/encoder/layer_5/attention/self/Reshape', 'bert/encoder/layer_5/attention/self/transpose', 'bert/encoder/layer_5/attention/self/key/MatMul', 'bert/encoder/layer_5/attention/self/key/BiasAdd', 'bert/encoder/layer_5/attention/self/Reshape_1', 'bert/encoder/layer_5/attention/self/MatMul__376', 'bert/encoder/layer_5/attention/self/MatMul', 'bert/encoder/layer_5/attention/self/Mul', 'bert/encoder/layer_5/attention/self/add', 'bert/encoder/layer_5/attention/self/Softmax', 'bert/encoder/layer_5/attention/self/MatMul_1', 'bert/encoder/layer_5/attention/self/transpose_3', 'bert/encoder/layer_5/attention/self/Reshape_3', 'bert/encoder/layer_5/attention/output/dense/MatMul', 'bert/encoder/layer_5/attention/output/dense/BiasAdd', 'bert/encoder/layer_5/attention/output/add', 'bert/encoder/layer_5/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_5/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_5/attention/output/LayerNorm/moments/SquaredDifference__379', 'bert/encoder/layer_5/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/Rsqrt__381', 'bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_5/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_5/intermediate/dense/MatMul', 'bert/encoder/layer_5/intermediate/dense/BiasAdd', 'bert/encoder/layer_5/intermediate/dense/Pow', 'bert/encoder/layer_5/intermediate/dense/mul', 'bert/encoder/layer_5/intermediate/dense/add', 'bert/encoder/layer_5/intermediate/dense/mul_1', 'bert/encoder/layer_5/intermediate/dense/Tanh', 'bert/encoder/layer_5/intermediate/dense/add_1', 'bert/encoder/layer_5/intermediate/dense/mul_2', 'bert/encoder/layer_5/intermediate/dense/mul_3', 'bert/encoder/layer_5/output/dense/MatMul', 'bert/encoder/layer_5/output/dense/BiasAdd', 'bert/encoder/layer_5/output/add', 'bert/encoder/layer_5/output/LayerNorm/moments/mean', 'bert/encoder/layer_5/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_5/output/LayerNorm/moments/SquaredDifference__383', 'bert/encoder/layer_5/output/LayerNorm/moments/variance', 'bert/encoder/layer_5/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_5/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_5/output/LayerNorm/batchnorm/Rsqrt__385', 'bert/encoder/layer_5/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_5/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_5/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_5/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_5/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_6/attention/self/value/MatMul', 'bert/encoder/layer_6/attention/self/value/BiasAdd', 'bert/encoder/layer_6/attention/self/Reshape_2', 'bert/encoder/layer_6/attention/self/transpose_2', 'bert/encoder/layer_6/attention/self/query/MatMul', 'bert/encoder/layer_6/attention/self/query/BiasAdd', 'bert/encoder/layer_6/attention/self/Reshape', 'bert/encoder/layer_6/attention/self/transpose', 'bert/encoder/layer_6/attention/self/key/MatMul', 'bert/encoder/layer_6/attention/self/key/BiasAdd', 'bert/encoder/layer_6/attention/self/Reshape_1', 'bert/encoder/layer_6/attention/self/MatMul__390', 'bert/encoder/layer_6/attention/self/MatMul', 'bert/encoder/layer_6/attention/self/Mul', 'bert/encoder/layer_6/attention/self/add', 'bert/encoder/layer_6/attention/self/Softmax', 'bert/encoder/layer_6/attention/self/MatMul_1', 'bert/encoder/layer_6/attention/self/transpose_3', 'bert/encoder/layer_6/attention/self/Reshape_3', 'bert/encoder/layer_6/attention/output/dense/MatMul', 'bert/encoder/layer_6/attention/output/dense/BiasAdd', 'bert/encoder/layer_6/attention/output/add', 'bert/encoder/layer_6/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_6/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_6/attention/output/LayerNorm/moments/SquaredDifference__393', 'bert/encoder/layer_6/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/Rsqrt__395', 'bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_6/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_6/intermediate/dense/MatMul', 'bert/encoder/layer_6/intermediate/dense/BiasAdd', 'bert/encoder/layer_6/intermediate/dense/Pow', 'bert/encoder/layer_6/intermediate/dense/mul', 'bert/encoder/layer_6/intermediate/dense/add', 'bert/encoder/layer_6/intermediate/dense/mul_1', 'bert/encoder/layer_6/intermediate/dense/Tanh', 'bert/encoder/layer_6/intermediate/dense/add_1', 'bert/encoder/layer_6/intermediate/dense/mul_2', 'bert/encoder/layer_6/intermediate/dense/mul_3', 'bert/encoder/layer_6/output/dense/MatMul', 'bert/encoder/layer_6/output/dense/BiasAdd', 'bert/encoder/layer_6/output/add', 'bert/encoder/layer_6/output/LayerNorm/moments/mean', 'bert/encoder/layer_6/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_6/output/LayerNorm/moments/SquaredDifference__397', 'bert/encoder/layer_6/output/LayerNorm/moments/variance', 'bert/encoder/layer_6/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_6/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_6/output/LayerNorm/batchnorm/Rsqrt__399', 'bert/encoder/layer_6/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_6/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_6/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_6/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_6/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_7/attention/self/value/MatMul', 'bert/encoder/layer_7/attention/self/value/BiasAdd', 'bert/encoder/layer_7/attention/self/Reshape_2', 'bert/encoder/layer_7/attention/self/transpose_2', 'bert/encoder/layer_7/attention/self/query/MatMul', 'bert/encoder/layer_7/attention/self/query/BiasAdd', 'bert/encoder/layer_7/attention/self/Reshape', 'bert/encoder/layer_7/attention/self/transpose', 'bert/encoder/layer_7/attention/self/key/MatMul', 'bert/encoder/layer_7/attention/self/key/BiasAdd', 'bert/encoder/layer_7/attention/self/Reshape_1', 'bert/encoder/layer_7/attention/self/MatMul__404', 'bert/encoder/layer_7/attention/self/MatMul', 'bert/encoder/layer_7/attention/self/Mul', 'bert/encoder/layer_7/attention/self/add', 'bert/encoder/layer_7/attention/self/Softmax', 'bert/encoder/layer_7/attention/self/MatMul_1', 'bert/encoder/layer_7/attention/self/transpose_3', 'bert/encoder/layer_7/attention/self/Reshape_3', 'bert/encoder/layer_7/attention/output/dense/MatMul', 'bert/encoder/layer_7/attention/output/dense/BiasAdd', 'bert/encoder/layer_7/attention/output/add', 'bert/encoder/layer_7/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_7/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_7/attention/output/LayerNorm/moments/SquaredDifference__407', 'bert/encoder/layer_7/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/Rsqrt__409', 'bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_7/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_7/intermediate/dense/MatMul', 'bert/encoder/layer_7/intermediate/dense/BiasAdd', 'bert/encoder/layer_7/intermediate/dense/Pow', 'bert/encoder/layer_7/intermediate/dense/mul', 'bert/encoder/layer_7/intermediate/dense/add', 'bert/encoder/layer_7/intermediate/dense/mul_1', 'bert/encoder/layer_7/intermediate/dense/Tanh', 'bert/encoder/layer_7/intermediate/dense/add_1', 'bert/encoder/layer_7/intermediate/dense/mul_2', 'bert/encoder/layer_7/intermediate/dense/mul_3', 'bert/encoder/layer_7/output/dense/MatMul', 'bert/encoder/layer_7/output/dense/BiasAdd', 'bert/encoder/layer_7/output/add', 'bert/encoder/layer_7/output/LayerNorm/moments/mean', 'bert/encoder/layer_7/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_7/output/LayerNorm/moments/SquaredDifference__411', 'bert/encoder/layer_7/output/LayerNorm/moments/variance', 'bert/encoder/layer_7/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_7/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_7/output/LayerNorm/batchnorm/Rsqrt__413', 'bert/encoder/layer_7/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_7/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_7/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_7/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_7/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_8/attention/self/value/MatMul', 'bert/encoder/layer_8/attention/self/value/BiasAdd', 'bert/encoder/layer_8/attention/self/Reshape_2', 'bert/encoder/layer_8/attention/self/transpose_2', 'bert/encoder/layer_8/attention/self/query/MatMul', 'bert/encoder/layer_8/attention/self/query/BiasAdd', 'bert/encoder/layer_8/attention/self/Reshape', 'bert/encoder/layer_8/attention/self/transpose', 'bert/encoder/layer_8/attention/self/key/MatMul', 'bert/encoder/layer_8/attention/self/key/BiasAdd', 'bert/encoder/layer_8/attention/self/Reshape_1', 'bert/encoder/layer_8/attention/self/MatMul__418', 'bert/encoder/layer_8/attention/self/MatMul', 'bert/encoder/layer_8/attention/self/Mul', 'bert/encoder/layer_8/attention/self/add', 'bert/encoder/layer_8/attention/self/Softmax', 'bert/encoder/layer_8/attention/self/MatMul_1', 'bert/encoder/layer_8/attention/self/transpose_3', 'bert/encoder/layer_8/attention/self/Reshape_3', 'bert/encoder/layer_8/attention/output/dense/MatMul', 'bert/encoder/layer_8/attention/output/dense/BiasAdd', 'bert/encoder/layer_8/attention/output/add', 'bert/encoder/layer_8/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_8/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_8/attention/output/LayerNorm/moments/SquaredDifference__421', 'bert/encoder/layer_8/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/Rsqrt__423', 'bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_8/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_8/intermediate/dense/MatMul', 'bert/encoder/layer_8/intermediate/dense/BiasAdd', 'bert/encoder/layer_8/intermediate/dense/Pow', 'bert/encoder/layer_8/intermediate/dense/mul', 'bert/encoder/layer_8/intermediate/dense/add', 'bert/encoder/layer_8/intermediate/dense/mul_1', 'bert/encoder/layer_8/intermediate/dense/Tanh', 'bert/encoder/layer_8/intermediate/dense/add_1', 'bert/encoder/layer_8/intermediate/dense/mul_2', 'bert/encoder/layer_8/intermediate/dense/mul_3', 'bert/encoder/layer_8/output/dense/MatMul', 'bert/encoder/layer_8/output/dense/BiasAdd', 'bert/encoder/layer_8/output/add', 'bert/encoder/layer_8/output/LayerNorm/moments/mean', 'bert/encoder/layer_8/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_8/output/LayerNorm/moments/SquaredDifference__425', 'bert/encoder/layer_8/output/LayerNorm/moments/variance', 'bert/encoder/layer_8/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_8/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_8/output/LayerNorm/batchnorm/Rsqrt__427', 'bert/encoder/layer_8/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_8/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_8/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_8/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_8/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_9/attention/self/value/MatMul', 'bert/encoder/layer_9/attention/self/value/BiasAdd', 'bert/encoder/layer_9/attention/self/Reshape_2', 'bert/encoder/layer_9/attention/self/transpose_2', 'bert/encoder/layer_9/attention/self/query/MatMul', 'bert/encoder/layer_9/attention/self/query/BiasAdd', 'bert/encoder/layer_9/attention/self/Reshape', 'bert/encoder/layer_9/attention/self/transpose', 'bert/encoder/layer_9/attention/self/key/MatMul', 'bert/encoder/layer_9/attention/self/key/BiasAdd', 'bert/encoder/layer_9/attention/self/Reshape_1', 'bert/encoder/layer_9/attention/self/MatMul__432', 'bert/encoder/layer_9/attention/self/MatMul', 'bert/encoder/layer_9/attention/self/Mul', 'bert/encoder/layer_9/attention/self/add', 'bert/encoder/layer_9/attention/self/Softmax', 'bert/encoder/layer_9/attention/self/MatMul_1', 'bert/encoder/layer_9/attention/self/transpose_3', 'bert/encoder/layer_9/attention/self/Reshape_3', 'bert/encoder/layer_9/attention/output/dense/MatMul', 'bert/encoder/layer_9/attention/output/dense/BiasAdd', 'bert/encoder/layer_9/attention/output/add', 'bert/encoder/layer_9/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_9/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_9/attention/output/LayerNorm/moments/SquaredDifference__435', 'bert/encoder/layer_9/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/Rsqrt__437', 'bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_9/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_9/intermediate/dense/MatMul', 'bert/encoder/layer_9/intermediate/dense/BiasAdd', 'bert/encoder/layer_9/intermediate/dense/Pow', 'bert/encoder/layer_9/intermediate/dense/mul', 'bert/encoder/layer_9/intermediate/dense/add', 'bert/encoder/layer_9/intermediate/dense/mul_1', 'bert/encoder/layer_9/intermediate/dense/Tanh', 'bert/encoder/layer_9/intermediate/dense/add_1', 'bert/encoder/layer_9/intermediate/dense/mul_2', 'bert/encoder/layer_9/intermediate/dense/mul_3', 'bert/encoder/layer_9/output/dense/MatMul', 'bert/encoder/layer_9/output/dense/BiasAdd', 'bert/encoder/layer_9/output/add', 'bert/encoder/layer_9/output/LayerNorm/moments/mean', 'bert/encoder/layer_9/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_9/output/LayerNorm/moments/SquaredDifference__439', 'bert/encoder/layer_9/output/LayerNorm/moments/variance', 'bert/encoder/layer_9/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_9/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_9/output/LayerNorm/batchnorm/Rsqrt__441', 'bert/encoder/layer_9/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_9/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_9/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_9/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_9/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_10/attention/self/value/MatMul', 'bert/encoder/layer_10/attention/self/value/BiasAdd', 'bert/encoder/layer_10/attention/self/Reshape_2', 'bert/encoder/layer_10/attention/self/transpose_2', 'bert/encoder/layer_10/attention/self/query/MatMul', 'bert/encoder/layer_10/attention/self/query/BiasAdd', 'bert/encoder/layer_10/attention/self/Reshape', 'bert/encoder/layer_10/attention/self/transpose', 'bert/encoder/layer_10/attention/self/key/MatMul', 'bert/encoder/layer_10/attention/self/key/BiasAdd', 'bert/encoder/layer_10/attention/self/Reshape_1', 'bert/encoder/layer_10/attention/self/MatMul__446', 'bert/encoder/layer_10/attention/self/MatMul', 'bert/encoder/layer_10/attention/self/Mul', 'bert/encoder/layer_10/attention/self/add', 'bert/encoder/layer_10/attention/self/Softmax', 'bert/encoder/layer_10/attention/self/MatMul_1', 'bert/encoder/layer_10/attention/self/transpose_3', 'bert/encoder/layer_10/attention/self/Reshape_3', 'bert/encoder/layer_10/attention/output/dense/MatMul', 'bert/encoder/layer_10/attention/output/dense/BiasAdd', 'bert/encoder/layer_10/attention/output/add', 'bert/encoder/layer_10/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_10/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_10/attention/output/LayerNorm/moments/SquaredDifference__449', 'bert/encoder/layer_10/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/Rsqrt__451', 'bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_10/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_10/intermediate/dense/MatMul', 'bert/encoder/layer_10/intermediate/dense/BiasAdd', 'bert/encoder/layer_10/intermediate/dense/Pow', 'bert/encoder/layer_10/intermediate/dense/mul', 'bert/encoder/layer_10/intermediate/dense/add', 'bert/encoder/layer_10/intermediate/dense/mul_1', 'bert/encoder/layer_10/intermediate/dense/Tanh', 'bert/encoder/layer_10/intermediate/dense/add_1', 'bert/encoder/layer_10/intermediate/dense/mul_2', 'bert/encoder/layer_10/intermediate/dense/mul_3', 'bert/encoder/layer_10/output/dense/MatMul', 'bert/encoder/layer_10/output/dense/BiasAdd', 'bert/encoder/layer_10/output/add', 'bert/encoder/layer_10/output/LayerNorm/moments/mean', 'bert/encoder/layer_10/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_10/output/LayerNorm/moments/SquaredDifference__453', 'bert/encoder/layer_10/output/LayerNorm/moments/variance', 'bert/encoder/layer_10/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_10/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_10/output/LayerNorm/batchnorm/Rsqrt__455', 'bert/encoder/layer_10/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_10/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_10/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_10/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_10/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_11/attention/self/value/MatMul', 'bert/encoder/layer_11/attention/self/value/BiasAdd', 'bert/encoder/layer_11/attention/self/Reshape_2', 'bert/encoder/layer_11/attention/self/transpose_2', 'bert/encoder/layer_11/attention/self/query/MatMul', 'bert/encoder/layer_11/attention/self/query/BiasAdd', 'bert/encoder/layer_11/attention/self/Reshape', 'bert/encoder/layer_11/attention/self/transpose', 'bert/encoder/layer_11/attention/self/key/MatMul', 'bert/encoder/layer_11/attention/self/key/BiasAdd', 'bert/encoder/layer_11/attention/self/Reshape_1', 'bert/encoder/layer_11/attention/self/MatMul__460', 'bert/encoder/layer_11/attention/self/MatMul', 'bert/encoder/layer_11/attention/self/Mul', 'bert/encoder/layer_11/attention/self/add', 'bert/encoder/layer_11/attention/self/Softmax', 'bert/encoder/layer_11/attention/self/MatMul_1', 'bert/encoder/layer_11/attention/self/transpose_3', 'bert/encoder/layer_11/attention/self/Reshape_3', 'bert/encoder/layer_11/attention/output/dense/MatMul', 'bert/encoder/layer_11/attention/output/dense/BiasAdd', 'bert/encoder/layer_11/attention/output/add', 'bert/encoder/layer_11/attention/output/LayerNorm/moments/mean', 'bert/encoder/layer_11/attention/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_11/attention/output/LayerNorm/moments/SquaredDifference__463', 'bert/encoder/layer_11/attention/output/LayerNorm/moments/variance', 'bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/Rsqrt__465', 'bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_11/attention/output/LayerNorm/batchnorm/add_1', 'bert/encoder/layer_11/intermediate/dense/MatMul', 'bert/encoder/layer_11/intermediate/dense/BiasAdd', 'bert/encoder/layer_11/intermediate/dense/Pow', 'bert/encoder/layer_11/intermediate/dense/mul', 'bert/encoder/layer_11/intermediate/dense/add', 'bert/encoder/layer_11/intermediate/dense/mul_1', 'bert/encoder/layer_11/intermediate/dense/Tanh', 'bert/encoder/layer_11/intermediate/dense/add_1', 'bert/encoder/layer_11/intermediate/dense/mul_2', 'bert/encoder/layer_11/intermediate/dense/mul_3', 'bert/encoder/layer_11/output/dense/MatMul', 'bert/encoder/layer_11/output/dense/BiasAdd', 'bert/encoder/layer_11/output/add', 'bert/encoder/layer_11/output/LayerNorm/moments/mean', 'bert/encoder/layer_11/output/LayerNorm/moments/SquaredDifference', 'bert/encoder/layer_11/output/LayerNorm/moments/SquaredDifference__467', 'bert/encoder/layer_11/output/LayerNorm/moments/variance', 'bert/encoder/layer_11/output/LayerNorm/batchnorm/add', 'bert/encoder/layer_11/output/LayerNorm/batchnorm/Rsqrt', 'bert/encoder/layer_11/output/LayerNorm/batchnorm/Rsqrt__469', 'bert/encoder/layer_11/output/LayerNorm/batchnorm/mul', 'bert/encoder/layer_11/output/LayerNorm/batchnorm/mul_2', 'bert/encoder/layer_11/output/LayerNorm/batchnorm/sub', 'bert/encoder/layer_11/output/LayerNorm/batchnorm/mul_1', 'bert/encoder/layer_11/output/LayerNorm/batchnorm/add_1', 'MatMul', 'BiasAdd', 'Reshape_1', 'transpose', 'unstack', 'unstack__490', 'unstack__488']
Generating '/tmp/nsys-report-ae10.qdstrm'
[1/8] [0% ] nsys-report-0123.nsys-rep
[1/8] [0% ] nsys-report-0123.nsys-rep
[1/8] [5% ] nsys-report-0123.nsys-rep
[1/8] [6% ] nsys-report-0123.nsys-rep
[1/8] [11% ] nsys-report-0123.nsys-rep
[1/8] [9% ] nsys-report-0123.nsys-rep
[1/8] [8% ] nsys-report-0123.nsys-rep
[1/8] [6% ] nsys-report-0123.nsys-rep
[1/8] [====25% ] nsys-report-0123.nsys-rep
[1/8] [===22% ] nsys-report-0123.nsys-rep
[1/8] [==20% ] nsys-report-0123.nsys-rep
[1/8] [==18% ] nsys-report-0123.nsys-rep
[1/8] [=17% ] nsys-report-0123.nsys-rep
[1/8] [==19% ] nsys-report-0123.nsys-rep
[1/8] [==20% ] nsys-report-0123.nsys-rep
[1/8] [==21% ] nsys-report-0123.nsys-rep
[1/8] [===22% ] nsys-report-0123.nsys-rep
[1/8] [===23% ] nsys-report-0123.nsys-rep
[1/8] [===24% ] nsys-report-0123.nsys-rep
[1/8] [====25% ] nsys-report-0123.nsys-rep
[1/8] [====26% ] nsys-report-0123.nsys-rep
[1/8] [====28% ] nsys-report-0123.nsys-rep
[1/8] [=====30% ] nsys-report-0123.nsys-rep
[1/8] [======34% ] nsys-report-0123.nsys-rep
[1/8] [=======38% ] nsys-report-0123.nsys-rep
[1/8] [==========48% ] nsys-report-0123.nsys-rep
[1/8] [============57% ] nsys-report-0123.nsys-rep
[1/8] [===============67% ] nsys-report-0123.nsys-rep
[1/8] [================71% ] nsys-report-0123.nsys-rep
[1/8] [=================72% ] nsys-report-0123.nsys-rep
[1/8] [==================76% ] nsys-report-0123.nsys-rep
[1/8] [====================83% ] nsys-report-0123.nsys-rep
[1/8] [====================84% ] nsys-report-0123.nsys-rep
[1/8] [====================85% ] nsys-report-0123.nsys-rep
[1/8] [=====================86% ] nsys-report-0123.nsys-rep
[1/8] [=====================87% ] nsys-report-0123.nsys-rep
[1/8] [=====================88% ] nsys-report-0123.nsys-rep
[1/8] [========================97% ] nsys-report-0123.nsys-rep
[1/8] [========================98% ] nsys-report-0123.nsys-rep
[1/8] [========================100%] nsys-report-0123.nsys-rep
[1/8] [========================100%] nsys-report-0123.nsys-rep
[2/8] [0% ] nsys-report-2c90.sqlite
[2/8] [1% ] nsys-report-2c90.sqlite
[2/8] [2% ] nsys-report-2c90.sqlite
[2/8] [3% ] nsys-report-2c90.sqlite
[2/8] [4% ] nsys-report-2c90.sqlite
[2/8] [5% ] nsys-report-2c90.sqlite
[2/8] [6% ] nsys-report-2c90.sqlite
[2/8] [7% ] nsys-report-2c90.sqlite
[2/8] [8% ] nsys-report-2c90.sqlite
[2/8] [9% ] nsys-report-2c90.sqlite
[2/8] [10% ] nsys-report-2c90.sqlite
[2/8] [11% ] nsys-report-2c90.sqlite
[2/8] [12% ] nsys-report-2c90.sqlite
[2/8] [13% ] nsys-report-2c90.sqlite
[2/8] [14% ] nsys-report-2c90.sqlite
[2/8] [=15% ] nsys-report-2c90.sqlite
[2/8] [=16% ] nsys-report-2c90.sqlite
[2/8] [=17% ] nsys-report-2c90.sqlite
[2/8] [==18% ] nsys-report-2c90.sqlite
[2/8] [==19% ] nsys-report-2c90.sqlite
[2/8] [==20% ] nsys-report-2c90.sqlite
[2/8] [==21% ] nsys-report-2c90.sqlite
[2/8] [===22% ] nsys-report-2c90.sqlite
[2/8] [===23% ] nsys-report-2c90.sqlite
[2/8] [===24% ] nsys-report-2c90.sqlite
[2/8] [====25% ] nsys-report-2c90.sqlite
[2/8] [====26% ] nsys-report-2c90.sqlite
[2/8] [====27% ] nsys-report-2c90.sqlite
[2/8] [====28% ] nsys-report-2c90.sqlite
[2/8] [=====29% ] nsys-report-2c90.sqlite
[2/8] [=====30% ] nsys-report-2c90.sqlite
[2/8] [=====31% ] nsys-report-2c90.sqlite
[2/8] [=====32% ] nsys-report-2c90.sqlite
[2/8] [======33% ] nsys-report-2c90.sqlite
[2/8] [======34% ] nsys-report-2c90.sqlite
[2/8] [======35% ] nsys-report-2c90.sqlite
[2/8] [=======36% ] nsys-report-2c90.sqlite
[2/8] [=======37% ] nsys-report-2c90.sqlite
[2/8] [=======38% ] nsys-report-2c90.sqlite
[2/8] [=======39% ] nsys-report-2c90.sqlite
[2/8] [========40% ] nsys-report-2c90.sqlite
[2/8] [========41% ] nsys-report-2c90.sqlite
[2/8] [========42% ] nsys-report-2c90.sqlite
[2/8] [=========43% ] nsys-report-2c90.sqlite
[2/8] [=========44% ] nsys-report-2c90.sqlite
[2/8] [=========45% ] nsys-report-2c90.sqlite
[2/8] [=========46% ] nsys-report-2c90.sqlite
[2/8] [==========47% ] nsys-report-2c90.sqlite
[2/8] [==========48% ] nsys-report-2c90.sqlite
[2/8] [==========49% ] nsys-report-2c90.sqlite
[2/8] [===========50% ] nsys-report-2c90.sqlite
[2/8] [===========51% ] nsys-report-2c90.sqlite
[2/8] [===========52% ] nsys-report-2c90.sqlite
[2/8] [===========53% ] nsys-report-2c90.sqlite
[2/8] [============54% ] nsys-report-2c90.sqlite
[2/8] [============55% ] nsys-report-2c90.sqlite
[2/8] [============56% ] nsys-report-2c90.sqlite
[2/8] [============57% ] nsys-report-2c90.sqlite
[2/8] [=============58% ] nsys-report-2c90.sqlite
[2/8] [=============59% ] nsys-report-2c90.sqlite
[2/8] [=============60% ] nsys-report-2c90.sqlite
[2/8] [==============61% ] nsys-report-2c90.sqlite
[2/8] [==============62% ] nsys-report-2c90.sqlite
[2/8] [==============63% ] nsys-report-2c90.sqlite
[2/8] [==============64% ] nsys-report-2c90.sqlite
[2/8] [===============65% ] nsys-report-2c90.sqlite
[2/8] [===============66% ] nsys-report-2c90.sqlite
[2/8] [===============67% ] nsys-report-2c90.sqlite
[2/8] [================68% ] nsys-report-2c90.sqlite
[2/8] [================69% ] nsys-report-2c90.sqlite
[2/8] [================70% ] nsys-report-2c90.sqlite
[2/8] [================71% ] nsys-report-2c90.sqlite
[2/8] [=================72% ] nsys-report-2c90.sqlite
[2/8] [=================73% ] nsys-report-2c90.sqlite
[2/8] [=================74% ] nsys-report-2c90.sqlite
[2/8] [==================75% ] nsys-report-2c90.sqlite
[2/8] [==================76% ] nsys-report-2c90.sqlite
[2/8] [==================77% ] nsys-report-2c90.sqlite
[2/8] [==================78% ] nsys-report-2c90.sqlite
[2/8] [===================79% ] nsys-report-2c90.sqlite
[2/8] [===================80% ] nsys-report-2c90.sqlite
[2/8] [===================81% ] nsys-report-2c90.sqlite
[2/8] [===================82% ] nsys-report-2c90.sqlite
[2/8] [====================83% ] nsys-report-2c90.sqlite
[2/8] [====================84% ] nsys-report-2c90.sqlite
[2/8] [====================85% ] nsys-report-2c90.sqlite
[2/8] [=====================86% ] nsys-report-2c90.sqlite
[2/8] [=====================87% ] nsys-report-2c90.sqlite
[2/8] [=====================88% ] nsys-report-2c90.sqlite
[2/8] [=====================89% ] nsys-report-2c90.sqlite
[2/8] [======================90% ] nsys-report-2c90.sqlite
[2/8] [======================91% ] nsys-report-2c90.sqlite
[2/8] [======================92% ] nsys-report-2c90.sqlite
[2/8] [=======================93% ] nsys-report-2c90.sqlite
[2/8] [=======================94% ] nsys-report-2c90.sqlite
[2/8] [=======================95% ] nsys-report-2c90.sqlite
[2/8] [=======================96% ] nsys-report-2c90.sqlite
[2/8] [========================97% ] nsys-report-2c90.sqlite
[2/8] [========================98% ] nsys-report-2c90.sqlite
[2/8] [========================99% ] nsys-report-2c90.sqlite
[2/8] [========================100%] nsys-report-2c90.sqlite
[2/8] [========================100%] nsys-report-2c90.sqlite
[3/8] Executing 'nvtx_sum' stats report
[4/8] Executing 'osrt_sum' stats report
Time (%) Total Time (ns) Num Calls Avg (ns) Med (ns) Min (ns) Max (ns) StdDev (ns) Name
-------- --------------- --------- ------------- ------------- ----------- ----------- ------------ ----------------------
55.2 5,230,820,475 63 83,028,896.4 100,119,708.0 1,280 548,595,156 73,482,897.6 poll
42.2 4,000,741,404 8 500,092,675.5 500,090,102.0 500,067,701 500,124,383 15,851.7 pthread_cond_timedwait
1.7 158,295,782 5,642 28,056.7 740.0 290 146,028,133 1,944,088.5 read
0.7 62,781,864 1,956 32,097.1 7,815.0 200 12,586,893 392,335.3 ioctl
0.1 9,348,135 3,183 2,936.9 2,700.0 1,140 36,151 1,256.3 open64
0.1 5,061,988 1 5,061,988.0 5,061,988.0 5,061,988 5,061,988 0.0 nanosleep
0.0 3,496,378 131,629 26.6 20.0 20 4,590 38.7 pthread_cond_signal
0.0 3,011,948 138 21,825.7 5,005.0 2,410 1,589,005 135,795.1 mmap64
0.0 2,619,399 71 36,892.9 930.0 580 672,060 111,420.4 pread64
0.0 809,893 13 62,299.5 59,751.0 54,861 80,871 8,354.2 sleep
0.0 515,469 583 884.2 50.0 20 60,211 5,485.3 fgets
0.0 481,325 28 17,190.2 6,820.0 1,760 114,061 23,885.3 mmap
0.0 377,505 10 37,750.5 35,975.5 15,230 78,841 20,343.3 sem_timedwait
0.0 348,995 8 43,624.4 31,290.0 25,720 72,221 20,452.4 pthread_create
0.0 221,624 29 7,642.2 2,700.0 490 52,390 12,795.7 write
0.0 204,595 44 4,649.9 2,830.5 970 21,260 4,496.3 fopen
0.0 174,132 10 17,413.2 4,120.0 1,940 79,041 29,324.5 munmap
0.0 130,762 1 130,762.0 130,762.0 130,762 130,762 0.0 pthread_cond_wait
0.0 101,411 1 101,411.0 101,411.0 101,411 101,411 0.0 waitpid
0.0 65,891 41 1,607.1 1,210.0 590 8,681 1,385.2 fclose
0.0 63,852 15 4,256.8 3,490.0 1,820 15,830 3,439.2 open
0.0 55,884 1,622 34.5 30.0 20 4,880 142.1 pthread_cond_broadcast
0.0 38,160 2 19,080.0 19,080.0 8,680 29,480 14,707.8 connect
0.0 33,752 6 5,625.3 5,155.5 2,960 10,060 2,994.9 pipe2
0.0 28,160 4 7,040.0 7,230.0 3,130 10,570 4,082.4 socket
0.0 27,231 133 204.7 210.0 20 1,210 133.4 sigaction
0.0 26,250 6 4,375.0 4,350.0 2,040 8,610 2,359.6 fopen64
0.0 22,074 68 324.6 300.0 171 1,090 148.3 fcntl
0.0 20,536 256 80.2 100.0 20 331 60.8 pthread_mutex_trylock
0.0 13,683 543 25.2 20.0 20 120 6.5 flockfile
0.0 13,500 3 4,500.0 4,280.0 1,530 7,690 3,085.9 fread
0.0 7,440 2 3,720.0 3,720.0 1,510 5,930 3,125.4 bind
0.0 3,279 30 109.3 30.0 20 880 189.0 fflush
0.0 2,620 10 262.0 255.0 220 350 37.9 dup
0.0 2,579 2 1,289.5 1,289.5 949 1,630 481.5 fwrite
0.0 1,180 2 590.0 590.0 380 800 297.0 dup2
0.0 890 1 890.0 890.0 890 890 0.0 getc
0.0 650 1 650.0 650.0 650 650 0.0 listen
[5/8] Executing 'cuda_api_sum' stats report
Time (%) Total Time (ns) Num Calls Avg (ns) Med (ns) Min (ns) Max (ns) StdDev (ns) Name
-------- --------------- --------- ----------- ----------- --------- ---------- ----------- ---------------------------------------------
54.9 214,002,149 1,676 127,686.2 26,805.5 2,240 1,491,052 249,665.4 cudaMemcpyAsync
21.6 84,145,482 1,676 50,206.1 10,940.0 580 273,074 70,961.6 cudaStreamSynchronize
18.6 72,377,733 644 112,387.8 6,425.0 3,550 16,272,670 956,381.0 cudaLaunchKernel
2.0 7,716,799 2 3,858,399.5 3,858,399.5 1,150,218 6,566,581 3,829,947.0 cudaFree
1.6 6,338,147 9 704,238.6 1,370.0 290 6,327,717 2,108,804.6 cudaStreamIsCapturing_v10000
0.6 2,334,497 49 47,642.8 47,881.0 38,230 52,011 3,374.7 cuCtxSynchronize
0.2 893,243 9 99,249.2 102,492.0 4,411 158,362 54,393.9 cudaMalloc
0.2 657,800 49 13,424.5 13,550.0 8,540 27,110 2,774.6 cuLaunchKernel
0.1 318,881 62 5,143.2 3,580.0 2,800 16,960 2,706.9 cudaMemsetAsync
0.1 303,263 1,532 198.0 180.0 50 4,640 173.3 cuGetProcAddress_v2
0.1 218,475 2 109,237.5 109,237.5 73,382 145,093 50,707.3 cuModuleLoadData
0.0 161,342 1 161,342.0 161,342.0 161,342 161,342 0.0 cudaGetDeviceProperties_v2_v12000
0.0 75,655 26 2,909.8 2,545.0 349 7,140 1,384.1 cudaOccupancyMaxActiveBlocksPerMultiprocessor
0.0 18,840 18 1,046.7 265.0 140 10,740 2,478.0 cudaEventCreateWithFlags
0.0 4,670 1 4,670.0 4,670.0 4,670 4,670 0.0 cuMemFree_v2
0.0 3,880 4 970.0 970.0 580 1,360 369.7 cuInit
0.0 1,240 1 1,240.0 1,240.0 1,240 1,240 0.0 cuCtxSetCurrent
0.0 1,200 2 600.0 600.0 250 950 495.0 cudaGetDriverEntryPoint_v11030
0.0 560 4 140.0 115.0 80 250 76.2 cuModuleGetLoadingMode
[6/8] Executing 'cuda_gpu_kern_sum' stats report
Time (%) Total Time (ns) Instances Avg (ns) Med (ns) Min (ns) Max (ns) StdDev (ns) Name
-------- --------------- --------- -------- -------- -------- -------- ----------- ----------------------------------------------------------------------------------------------------
48.6 2,147,879 49 43,834.3 43,744.0 43,680 45,728 299.6 cutlass_tensorop_f16_s16816gemm_f16_256x128_32x3_tt_align8
7.4 326,528 48 6,802.7 6,752.0 6,560 7,136 178.6 void at::native::elementwise_kernel<(int)128, (int)4, void at::native::gpu_kernel_impl<at::native::…
6.8 299,042 12 24,920.2 24,896.5 24,800 25,248 115.0 ampere_fp16_s16816gemm_fp16_128x64_ldg8_f2f_stages_64x4_nn
4.6 204,162 72 2,835.6 2,880.0 2,336 3,424 376.7 void at::native::elementwise_kernel<(int)128, (int)4, void at::native::gpu_kernel_impl<at::native::…
4.0 175,617 48 3,658.7 3,744.0 3,392 3,904 226.8 void at::native::reduce_kernel<(int)512, (int)1, at::native::ReduceOp<c10::Half, at::native::MeanOp…
3.3 143,967 12 11,997.3 11,952.0 11,872 12,543 175.8 void at::native::elementwise_kernel<(int)128, (int)4, void at::native::gpu_kernel_impl<at::native::…
2.9 126,912 24 5,288.0 5,328.0 4,832 5,696 281.0 void cutlass::Kernel<cutlass_80_wmma_tensorop_f16_s161616gemm_f16_32x32_64x1_nn_align8>(T1::Params)
2.3 102,977 48 2,145.4 2,176.0 1,984 2,368 134.6 void at::native::elementwise_kernel<(int)128, (int)4, void at::native::gpu_kernel_impl<at::native::…
2.3 100,766 36 2,799.1 2,240.0 2,207 4,000 821.3 void at::native::elementwise_kernel<(int)128, (int)4, void at::native::gpu_kernel_impl<at::native::…
2.2 96,065 12 8,005.4 8,032.0 7,713 8,161 109.7 void at::native::elementwise_kernel<(int)128, (int)4, void at::native::gpu_kernel_impl<at::native::…
2.1 94,881 12 7,906.8 7,904.0 7,809 7,999 53.2 ampere_fp16_s16816gemm_fp16_64x64_ldg8_f2f_stages_64x5_nn
1.9 84,862 12 7,071.8 7,103.0 6,752 7,168 110.8 void at::native::elementwise_kernel<(int)128, (int)4, void at::native::gpu_kernel_impl<at::native::…
1.5 65,501 36 1,819.5 1,472.0 1,440 2,560 493.3 void at::native::vectorized_elementwise_kernel<(int)4, at::native::CUDAFunctor_add<c10::Half>, at::…
1.5 65,190 36 1,810.8 1,473.0 1,409 2,528 495.9 void at::native::vectorized_elementwise_kernel<(int)4, at::native::BinaryFunctor<c10::Half, c10::Ha…
1.5 64,862 27 2,402.3 2,432.0 1,824 2,560 131.9 void at::native::elementwise_kernel<(int)128, (int)2, void at::native::gpu_kernel_impl<at::native::…
1.5 64,159 12 5,346.6 5,280.0 5,216 6,016 218.5 void <unnamed>::softmax_warp_forward<float, float, float, (int)8, (bool)0, (bool)0>(T2 *, const T1 …
1.4 61,535 49 1,255.8 1,088.0 800 1,888 340.6 void at::native::vectorized_elementwise_kernel<(int)4, at::native::FillFunctor<c10::Half>, at::deta…
0.7 31,456 24 1,310.7 1,312.0 1,216 1,344 22.0 void at::native::unrolled_elementwise_kernel<at::native::CUDAFunctor_add<c10::Half>, at::detail::Ar…
0.7 30,944 12 2,578.7 2,528.0 2,528 3,040 146.0 void at::native::vectorized_elementwise_kernel<(int)4, at::native::tanh_kernel_cuda(at::TensorItera…
0.6 27,519 27 1,019.2 992.0 928 1,824 161.4 void at::native::vectorized_elementwise_kernel<(int)4, at::native::CUDAFunctor_add<float>, at::deta…
0.6 27,229 24 1,134.5 1,151.0 1,056 1,153 23.0 void at::native::vectorized_elementwise_kernel<(int)4, at::native::reciprocal_kernel_cuda(at::Tenso…
0.6 26,368 24 1,098.7 1,088.0 1,056 1,120 18.1 void at::native::vectorized_elementwise_kernel<(int)4, at::native::sqrt_kernel_cuda(at::TensorItera…
0.5 22,369 24 932.0 928.0 896 960 14.3 void at::native::vectorized_elementwise_kernel<(int)4, at::native::AUnaryFunctor<c10::Half, c10::Ha…
0.2 9,408 5 1,881.6 1,632.0 1,344 2,464 527.5 void at::native::elementwise_kernel<(int)128, (int)2, void at::native::gpu_kernel_impl<at::native::…
0.2 7,808 2 3,904.0 3,904.0 3,744 4,064 226.3 void at::native::reduce_kernel<(int)512, (int)1, at::native::ReduceOp<float, at::native::MeanOps<fl…
0.1 2,753 1 2,753.0 2,753.0 2,753 2,753 0.0 void at::native::unrolled_elementwise_kernel<at::native::CUDAFunctor_add<float>, at::detail::Array<…
0.0 2,144 1 2,144.0 2,144.0 2,144 2,144 0.0 void cutlass::Kernel<cutlass_80_wmma_tensorop_f16_s161616gemm_f16_32x32_32x1_nn_align2>(T1::Params)
0.0 1,856 1 1,856.0 1,856.0 1,856 1,856 0.0 void at::native::vectorized_elementwise_kernel<(int)4, at::native::BinaryFunctor<float, float, floa…
0.0 1,024 1 1,024.0 1,024.0 1,024 1,024 0.0 void at::native::vectorized_elementwise_kernel<(int)4, at::native::reciprocal_kernel_cuda(at::Tenso…
0.0 991 1 991.0 991.0 991 991 0.0 void at::native::vectorized_elementwise_kernel<(int)4, at::native::sqrt_kernel_cuda(at::TensorItera…
0.0 928 1 928.0 928.0 928 928 0.0 void at::native::vectorized_elementwise_kernel<(int)4, at::native::AUnaryFunctor<float, float, floa…
[7/8] Executing 'cuda_gpu_mem_time_sum' stats report
Time (%) Total Time (ns) Count Avg (ns) Med (ns) Min (ns) Max (ns) StdDev (ns) Operation
-------- --------------- ----- --------- -------- -------- -------- ----------- ----------------------------
59.5 96,180,030 1,092 88,077.0 61,152.0 287 754,659 134,057.1 [CUDA memcpy Host-to-Device]
40.5 65,543,200 584 112,231.5 59,296.0 960 809,219 154,864.6 [CUDA memcpy Device-to-Host]
0.0 29,726 62 479.5 320.0 288 928 232.2 [CUDA memset]
[8/8] Executing 'cuda_gpu_mem_size_sum' stats report
Total (MB) Count Avg (MB) Med (MB) Min (MB) Max (MB) StdDev (MB) Operation
---------- ----- -------- -------- -------- -------- ----------- ----------------------------
626.375 1,092 0.574 0.393 0.000 4.719 0.881 [CUDA memcpy Host-to-Device]
393.055 584 0.673 0.393 0.000 3.146 0.785 [CUDA memcpy Device-to-Host]
0.001 62 0.000 0.000 0.000 0.000 0.000 [CUDA memset]
Generated:
/tmp/nsys-report-0123.nsys-rep
/tmp/nsys-report-2c90.sqlite
Editor is loading...
Leave a Comment