{"schemaVersion":1,"deviceProperties":[{"id":0,"name":"NVIDIA GeForce RTX 5080","totalGlobalMem":16608133120,"computeMajor":12,"computeMinor":0,"maxThreadsPerBlock":1024,"maxThreadsPerMultiprocessor":1536,"regsPerBlock":65536,"warpSize":32,"sharedMemPerBlock":49152,"numSms":84,"regsPerMultiprocessor":65536,"sharedMemPerBlockOptin":101376,"sharedMemPerMultiprocessor":102400}],"trace_id":"733B89DC431943F58D8D19002299FC61","profile_memory":1,"cuda_driver_version":13020,"record_shapes":1,"cuda_runtime_version":13020,"cupti_version":130201,"host_name":"42a7252ec2fb","displayTimeUnit":"ms","baseTimeNanoseconds":1782967788000000000,"traceEvents":[{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":996,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":996,"tid":0,"args":{"labels":"CPU"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":996,"tid":0,"args":{"sort_index":996}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":0,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":0,"tid":0,"args":{"labels":"GPU 0"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":0,"tid":0,"args":{"sort_index":5000000}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":1,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":1,"tid":0,"args":{"labels":"GPU 1"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":1,"tid":0,"args":{"sort_index":5000001}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":2,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":2,"tid":0,"args":{"labels":"GPU 2"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":2,"tid":0,"args":{"sort_index":5000002}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":3,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":3,"tid":0,"args":{"labels":"GPU 3"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":3,"tid":0,"args":{"sort_index":5000003}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":4,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":4,"tid":0,"args":{"labels":"GPU 4"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":4,"tid":0,"args":{"sort_index":5000004}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":5,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":5,"tid":0,"args":{"labels":"GPU 5"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":5,"tid":0,"args":{"sort_index":5000005}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":6,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":6,"tid":0,"args":{"labels":"GPU 6"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":6,"tid":0,"args":{"sort_index":5000006}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":7,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":7,"tid":0,"args":{"labels":"GPU 7"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":7,"tid":0,"args":{"sort_index":5000007}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":8,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":8,"tid":0,"args":{"labels":"GPU 8"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":8,"tid":0,"args":{"sort_index":5000008}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":9,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":9,"tid":0,"args":{"labels":"GPU 9"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":9,"tid":0,"args":{"sort_index":5000009}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":10,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":10,"tid":0,"args":{"labels":"GPU 10"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":10,"tid":0,"args":{"sort_index":5000010}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":11,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":11,"tid":0,"args":{"labels":"GPU 11"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":11,"tid":0,"args":{"sort_index":5000011}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":12,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":12,"tid":0,"args":{"labels":"GPU 12"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":12,"tid":0,"args":{"sort_index":5000012}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":13,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":13,"tid":0,"args":{"labels":"GPU 13"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":13,"tid":0,"args":{"sort_index":5000013}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":14,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":14,"tid":0,"args":{"labels":"GPU 14"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":14,"tid":0,"args":{"sort_index":5000014}},{"ph":"M","name":"process_name","ts":3148028962153.389,"pid":15,"tid":0,"args":{"name":"python"}},{"ph":"M","name":"process_labels","ts":3148028962153.389,"pid":15,"tid":0,"args":{"labels":"GPU 15"}},{"ph":"M","name":"process_sort_index","ts":3148028962153.389,"pid":15,"tid":0,"args":{"sort_index":5000015}},{"ph":"M","name":"thread_name","ts":3148028962153.389,"pid":0,"tid":7,"args":{"name":"stream 7 "}},{"ph":"M","name":"thread_sort_index","ts":3148028962153.389,"pid":0,"tid":7,"args":{"sort_index":7}},{"ph":"M","name":"thread_name","ts":3148028962153.389,"pid":996,"tid":996,"args":{"name":"thread 996 (python)"}},{"ph":"M","name":"thread_sort_index","ts":3148028962153.389,"pid":996,"tid":996,"args":{"sort_index":996}},{"ph":"M","name":"thread_name","ts":3148028962153.389,"pid":996,"tid":996,"args":{"name":"thread 996 (python)"}},{"ph":"M","name":"thread_sort_index","ts":3148028962153.389,"pid":996,"tid":996,"args":{"sort_index":996}},{"ph":"X","cat":"user_annotation","name":"ProfilerStep#3","pid":996,"tid":996,"ts":3148028962248.178,"dur":651.043,"args":{"External id":1,"Record function id":0,"Ev Idx":0}},{"ph":"X","cat":"cpu_op","name":"aten::linear","pid":996,"tid":996,"ts":3148028962302.524,"dur":78.221,"args":{"External id":2,"Sequence number":21,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","",""],"Input type":["float","float","float"],"Input Strides":[[1024,1],[1024,1],[1]],"Input Dims":[[128,1024],[2048,1024],[2048]],"Ev Idx":1}},{"ph":"X","cat":"cpu_op","name":"aten::t","pid":996,"tid":996,"ts":3148028962306.331,"dur":20.228,"args":{"External id":3,"Sequence number":21,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["float"],"Input Strides":[[1024,1]],"Input Dims":[[2048,1024]],"Ev Idx":2}},{"ph":"X","cat":"cpu_op","name":"aten::transpose","pid":996,"tid":996,"ts":3148028962316.826,"dur":7.548,"args":{"External id":4,"Record function id":0,"Concrete Inputs":["","0","1"],"Input type":["float","Scalar","Scalar"],"Input Strides":[[1024,1],[],[]],"Input Dims":[[2048,1024],[],[]],"Ev Idx":3}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028962321.586,"dur":1.244,"args":{"External id":5,"Record function id":0,"Concrete Inputs":["","[1024, 2048]","[1, 1024]",""],"Input type":["float","ScalarList","ScalarList",""],"Input Strides":[[1024,1],[],[],[]],"Input Dims":[[2048,1024],[],[],[]],"Ev Idx":4}},{"ph":"X","cat":"cpu_op","name":"aten::addmm","pid":996,"tid":996,"ts":3148028962330.306,"dur":49.094,"args":{"External id":6,"Sequence number":22,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","","","1","1"],"Input type":["float","float","float","Scalar","Scalar"],"Input Strides":[[1],[1024,1],[1,1024],[],[]],"Input Dims":[[2048],[128,1024],[1024,2048],[],[]],"Ev Idx":5}},{"ph":"X","cat":"cpu_op","name":"aten::softmax","pid":996,"tid":996,"ts":3148028962398.904,"dur":83.841,"args":{"External id":7,"Sequence number":23,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","-1",""],"Input type":["float","Scalar",""],"Input Strides":[[2048,1],[],[]],"Input Dims":[[128,2048],[],[]],"Ev Idx":6}},{"ph":"X","cat":"cpu_op","name":"aten::_softmax","pid":996,"tid":996,"ts":3148028962404.809,"dur":75.567,"args":{"External id":8,"Sequence number":23,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","-1","False"],"Input type":["float","Scalar","Scalar"],"Input Strides":[[2048,1],[],[]],"Input Dims":[[128,2048],[],[]],"Ev Idx":7}},{"ph":"X","cat":"cpu_op","name":"aten::sum","pid":996,"tid":996,"ts":3148028962493.348,"dur":38.944,"args":{"External id":9,"Sequence number":24,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","[-1]","False",""],"Input type":["float","ScalarList","Scalar",""],"Input Strides":[[2048,1],[],[],[]],"Input Dims":[[128,2048],[],[],[]],"Ev Idx":8}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028962506.289,"dur":0.908,"args":{"External id":10,"Record function id":0,"Concrete Inputs":["","[128, 1]","[1, 0]",""],"Input type":["float","ScalarList","ScalarList",""],"Input Strides":[[1],[],[],[]],"Input Dims":[[128],[],[],[]],"Ev Idx":9}},{"ph":"X","cat":"cpu_op","name":"aten::sub","pid":996,"tid":996,"ts":3148028962542.835,"dur":28.642,"args":{"External id":11,"Sequence number":25,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","","1"],"Input type":["float","double","Scalar"],"Input Strides":[[1],[],[]],"Input Dims":[[128],[],[]],"Ev Idx":10}},{"ph":"X","cat":"cpu_op","name":"aten::abs","pid":996,"tid":996,"ts":3148028962593.466,"dur":81.571,"args":{"External id":12,"Sequence number":26,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["float"],"Input Strides":[[1]],"Input Dims":[[128]],"Ev Idx":11}},{"ph":"X","cat":"cpu_op","name":"aten::empty","pid":996,"tid":996,"ts":3148028962620.852,"dur":8.704,"args":{"External id":13,"Record function id":0,"Concrete Inputs":["[0]","6","0","","",""],"Input type":["ScalarList","Scalar","Scalar","","",""],"Input Strides":[[],[],[],[],[],[]],"Input Dims":[[],[],[],[],[],[]],"Ev Idx":12}},{"ph":"X","cat":"cpu_op","name":"aten::abs","pid":996,"tid":996,"ts":3148028962634.683,"dur":38.437,"args":{"External id":14,"Record function id":0,"Concrete Inputs":["",""],"Input type":["float","float"],"Input Strides":[[1],[1]],"Input Dims":[[128],[0]],"Ev Idx":13}},{"ph":"X","cat":"cpu_op","name":"aten::resize_","pid":996,"tid":996,"ts":3148028962641.193,"dur":3.456,"args":{"External id":15,"Record function id":0,"Concrete Inputs":["","[128]",""],"Input type":["float","ScalarList",""],"Input Strides":[[1],[],[]],"Input Dims":[[0],[],[]],"Ev Idx":14}},{"ph":"X","cat":"cpu_op","name":"aten::le","pid":996,"tid":996,"ts":3148028962702.275,"dur":62.535,"args":{"External id":16,"Sequence number":27,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","1.0000000000000001e-05"],"Input type":["float","Scalar"],"Input Strides":[[1],[]],"Input Dims":[[128],[]],"Ev Idx":15}},{"ph":"X","cat":"cpu_op","name":"aten::all","pid":996,"tid":996,"ts":3148028962772.331,"dur":37.371,"args":{"External id":17,"Sequence number":27,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["bool"],"Input Strides":[[1]],"Input Dims":[[128]],"Ev Idx":16}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028962791.578,"dur":3.208,"args":{"External id":18,"Record function id":0,"Concrete Inputs":["","[1]","[0]",""],"Input type":["bool","ScalarList","ScalarList",""],"Input Strides":[[],[],[],[]],"Input Dims":[[],[],[],[]],"Ev Idx":17}},{"ph":"X","cat":"cpu_op","name":"aten::_assert_async","pid":996,"tid":996,"ts":3148028962818.951,"dur":9.578,"args":{"External id":19,"Sequence number":27,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["",""],"Input type":["bool",""],"Input Strides":[[],[]],"Input Dims":[[],[]],"Ev Idx":18}},{"ph":"X","cat":"cpu_op","name":"aten::mul","pid":996,"tid":996,"ts":3148028962835.331,"dur":19.181,"args":{"External id":20,"Sequence number":27,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["",""],"Input type":["float","double"],"Input Strides":[[2048,1],[]],"Input Dims":[[128,2048],[]],"Ev Idx":19}},{"ph":"X","cat":"user_annotation","name":"ProfilerStep#4","pid":996,"tid":996,"ts":3148028962917.173,"dur":365.507,"args":{"External id":21,"Record function id":0,"Ev Idx":20}},{"ph":"X","cat":"cpu_op","name":"aten::linear","pid":996,"tid":996,"ts":3148028962932.917,"dur":46.874,"args":{"External id":22,"Sequence number":28,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","",""],"Input type":["float","float","float"],"Input Strides":[[1024,1],[1024,1],[1]],"Input Dims":[[128,1024],[2048,1024],[2048]],"Ev Idx":21}},{"ph":"X","cat":"cpu_op","name":"aten::t","pid":996,"tid":996,"ts":3148028962933.696,"dur":7.923,"args":{"External id":23,"Sequence number":28,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["float"],"Input Strides":[[1024,1]],"Input Dims":[[2048,1024]],"Ev Idx":22}},{"ph":"X","cat":"cpu_op","name":"aten::transpose","pid":996,"tid":996,"ts":3148028962936.179,"dur":3.469,"args":{"External id":24,"Record function id":0,"Concrete Inputs":["","0","1"],"Input type":["float","Scalar","Scalar"],"Input Strides":[[1024,1],[],[]],"Input Dims":[[2048,1024],[],[]],"Ev Idx":23}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028962938.05,"dur":1.07,"args":{"External id":25,"Record function id":0,"Concrete Inputs":["","[1024, 2048]","[1, 1024]",""],"Input type":["float","ScalarList","ScalarList",""],"Input Strides":[[1024,1],[],[],[]],"Input Dims":[[2048,1024],[],[],[]],"Ev Idx":24}},{"ph":"X","cat":"cpu_op","name":"aten::addmm","pid":996,"tid":996,"ts":3148028962942.781,"dur":35.862,"args":{"External id":26,"Sequence number":29,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","","","1","1"],"Input type":["float","float","float","Scalar","Scalar"],"Input Strides":[[1],[1024,1],[1,1024],[],[]],"Input Dims":[[2048],[128,1024],[1024,2048],[],[]],"Ev Idx":25}},{"ph":"X","cat":"cpu_op","name":"aten::softmax","pid":996,"tid":996,"ts":3148028962990.379,"dur":21.987,"args":{"External id":27,"Sequence number":30,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","-1",""],"Input type":["float","Scalar",""],"Input Strides":[[2048,1],[],[]],"Input Dims":[[128,2048],[],[]],"Ev Idx":26}},{"ph":"X","cat":"cpu_op","name":"aten::_softmax","pid":996,"tid":996,"ts":3148028962991.773,"dur":19.281,"args":{"External id":28,"Sequence number":30,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","-1","False"],"Input type":["float","Scalar","Scalar"],"Input Strides":[[2048,1],[],[]],"Input Dims":[[128,2048],[],[]],"Ev Idx":27}},{"ph":"X","cat":"cpu_op","name":"aten::sum","pid":996,"tid":996,"ts":3148028963033.622,"dur":61.184,"args":{"External id":29,"Sequence number":31,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","[-1]","False",""],"Input type":["float","ScalarList","Scalar",""],"Input Strides":[[2048,1],[],[],[]],"Input Dims":[[128,2048],[],[],[]],"Ev Idx":28}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028963060.437,"dur":2.25,"args":{"External id":30,"Record function id":0,"Concrete Inputs":["","[128, 1]","[1, 0]",""],"Input type":["float","ScalarList","ScalarList",""],"Input Strides":[[1],[],[],[]],"Input Dims":[[128],[],[],[]],"Ev Idx":29}},{"ph":"X","cat":"cpu_op","name":"aten::sub","pid":996,"tid":996,"ts":3148028963104.767,"dur":20.921,"args":{"External id":31,"Sequence number":32,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","","1"],"Input type":["float","double","Scalar"],"Input Strides":[[1],[],[]],"Input Dims":[[128],[],[]],"Ev Idx":30}},{"ph":"X","cat":"cpu_op","name":"aten::abs","pid":996,"tid":996,"ts":3148028963130.805,"dur":25.72,"args":{"External id":32,"Sequence number":33,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["float"],"Input Strides":[[1]],"Input Dims":[[128]],"Ev Idx":31}},{"ph":"X","cat":"cpu_op","name":"aten::empty","pid":996,"tid":996,"ts":3148028963134.141,"dur":3.502,"args":{"External id":33,"Record function id":0,"Concrete Inputs":["[0]","6","0","","",""],"Input type":["ScalarList","Scalar","Scalar","","",""],"Input Strides":[[],[],[],[],[],[]],"Input Dims":[[],[],[],[],[],[]],"Ev Idx":32}},{"ph":"X","cat":"cpu_op","name":"aten::abs","pid":996,"tid":996,"ts":3148028963138.732,"dur":16.384,"args":{"External id":34,"Record function id":0,"Concrete Inputs":["",""],"Input type":["float","float"],"Input Strides":[[1],[1]],"Input Dims":[[128],[0]],"Ev Idx":33}},{"ph":"X","cat":"cpu_op","name":"aten::resize_","pid":996,"tid":996,"ts":3148028963141.797,"dur":2.848,"args":{"External id":35,"Record function id":0,"Concrete Inputs":["","[128]",""],"Input type":["float","ScalarList",""],"Input Strides":[[1],[],[]],"Input Dims":[[0],[],[]],"Ev Idx":34}},{"ph":"X","cat":"cpu_op","name":"aten::le","pid":996,"tid":996,"ts":3148028963161.975,"dur":18.089,"args":{"External id":36,"Sequence number":34,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","1.0000000000000001e-05"],"Input type":["float","Scalar"],"Input Strides":[[1],[]],"Input Dims":[[128],[]],"Ev Idx":35}},{"ph":"X","cat":"cpu_op","name":"aten::all","pid":996,"tid":996,"ts":3148028963187.335,"dur":20.501,"args":{"External id":37,"Sequence number":34,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["bool"],"Input Strides":[[1]],"Input Dims":[[128]],"Ev Idx":36}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028963193.267,"dur":0.73,"args":{"External id":38,"Record function id":0,"Concrete Inputs":["","[1]","[0]",""],"Input type":["bool","ScalarList","ScalarList",""],"Input Strides":[[],[],[],[]],"Input Dims":[[],[],[],[]],"Ev Idx":37}},{"ph":"X","cat":"cpu_op","name":"aten::_assert_async","pid":996,"tid":996,"ts":3148028963213.54,"dur":9.317,"args":{"External id":39,"Sequence number":34,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["",""],"Input type":["bool",""],"Input Strides":[[],[]],"Input Dims":[[],[]],"Ev Idx":38}},{"ph":"X","cat":"cpu_op","name":"aten::mul","pid":996,"tid":996,"ts":3148028963242.803,"dur":21.561,"args":{"External id":40,"Sequence number":34,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["",""],"Input type":["float","double"],"Input Strides":[[2048,1],[]],"Input Dims":[[128,2048],[]],"Ev Idx":39}},{"ph":"X","cat":"user_annotation","name":"ProfilerStep#5","pid":996,"tid":996,"ts":3148028963298.686,"dur":276.804,"args":{"External id":41,"Record function id":0,"Ev Idx":40}},{"ph":"X","cat":"cpu_op","name":"aten::linear","pid":996,"tid":996,"ts":3148028963312.704,"dur":44.188,"args":{"External id":42,"Sequence number":35,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","",""],"Input type":["float","float","float"],"Input Strides":[[1024,1],[1024,1],[1]],"Input Dims":[[128,1024],[2048,1024],[2048]],"Ev Idx":41}},{"ph":"X","cat":"cpu_op","name":"aten::t","pid":996,"tid":996,"ts":3148028963313.445,"dur":7.452,"args":{"External id":43,"Sequence number":35,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["float"],"Input Strides":[[1024,1]],"Input Dims":[[2048,1024]],"Ev Idx":42}},{"ph":"X","cat":"cpu_op","name":"aten::transpose","pid":996,"tid":996,"ts":3148028963315.658,"dur":3.473,"args":{"External id":44,"Record function id":0,"Concrete Inputs":["","0","1"],"Input type":["float","Scalar","Scalar"],"Input Strides":[[1024,1],[],[]],"Input Dims":[[2048,1024],[],[]],"Ev Idx":43}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028963317.565,"dur":1.043,"args":{"External id":45,"Record function id":0,"Concrete Inputs":["","[1024, 2048]","[1, 1024]",""],"Input type":["float","ScalarList","ScalarList",""],"Input Strides":[[1024,1],[],[],[]],"Input Dims":[[2048,1024],[],[],[]],"Ev Idx":44}},{"ph":"X","cat":"cpu_op","name":"aten::addmm","pid":996,"tid":996,"ts":3148028963321.967,"dur":33.877,"args":{"External id":46,"Sequence number":36,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","","","1","1"],"Input type":["float","float","float","Scalar","Scalar"],"Input Strides":[[1],[1024,1],[1,1024],[],[]],"Input Dims":[[2048],[128,1024],[1024,2048],[],[]],"Ev Idx":45}},{"ph":"X","cat":"cpu_op","name":"aten::softmax","pid":996,"tid":996,"ts":3148028963366.407,"dur":21.131,"args":{"External id":47,"Sequence number":37,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","-1",""],"Input type":["float","Scalar",""],"Input Strides":[[2048,1],[],[]],"Input Dims":[[128,2048],[],[]],"Ev Idx":46}},{"ph":"X","cat":"cpu_op","name":"aten::_softmax","pid":996,"tid":996,"ts":3148028963367.693,"dur":18.576,"args":{"External id":48,"Sequence number":37,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","-1","False"],"Input type":["float","Scalar","Scalar"],"Input Strides":[[2048,1],[],[]],"Input Dims":[[128,2048],[],[]],"Ev Idx":47}},{"ph":"X","cat":"cpu_op","name":"aten::sum","pid":996,"tid":996,"ts":3148028963394.627,"dur":23.844,"args":{"External id":49,"Sequence number":38,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","[-1]","False",""],"Input type":["float","ScalarList","Scalar",""],"Input Strides":[[2048,1],[],[],[]],"Input Dims":[[128,2048],[],[],[]],"Ev Idx":48}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028963401.548,"dur":0.716,"args":{"External id":50,"Record function id":0,"Concrete Inputs":["","[128, 1]","[1, 0]",""],"Input type":["float","ScalarList","ScalarList",""],"Input Strides":[[1],[],[],[]],"Input Dims":[[128],[],[],[]],"Ev Idx":49}},{"ph":"X","cat":"cpu_op","name":"aten::sub","pid":996,"tid":996,"ts":3148028963425.728,"dur":17.577,"args":{"External id":51,"Sequence number":39,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","","1"],"Input type":["float","double","Scalar"],"Input Strides":[[1],[],[]],"Input Dims":[[128],[],[]],"Ev Idx":50}},{"ph":"X","cat":"cpu_op","name":"aten::abs","pid":996,"tid":996,"ts":3148028963447.716,"dur":23.757,"args":{"External id":52,"Sequence number":40,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["float"],"Input Strides":[[1]],"Input Dims":[[128]],"Ev Idx":51}},{"ph":"X","cat":"cpu_op","name":"aten::empty","pid":996,"tid":996,"ts":3148028963450.558,"dur":3.257,"args":{"External id":53,"Record function id":0,"Concrete Inputs":["[0]","6","0","","",""],"Input type":["ScalarList","Scalar","Scalar","","",""],"Input Strides":[[],[],[],[],[],[]],"Input Dims":[[],[],[],[],[],[]],"Ev Idx":52}},{"ph":"X","cat":"cpu_op","name":"aten::abs","pid":996,"tid":996,"ts":3148028963454.778,"dur":15.288,"args":{"External id":54,"Record function id":0,"Concrete Inputs":["",""],"Input type":["float","float"],"Input Strides":[[1],[1]],"Input Dims":[[128],[0]],"Ev Idx":53}},{"ph":"X","cat":"cpu_op","name":"aten::resize_","pid":996,"tid":996,"ts":3148028963457.655,"dur":2.654,"args":{"External id":55,"Record function id":0,"Concrete Inputs":["","[128]",""],"Input type":["float","ScalarList",""],"Input Strides":[[1],[],[]],"Input Dims":[[0],[],[]],"Ev Idx":54}},{"ph":"X","cat":"cpu_op","name":"aten::le","pid":996,"tid":996,"ts":3148028963476.338,"dur":17.706,"args":{"External id":56,"Sequence number":41,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","1.0000000000000001e-05"],"Input type":["float","Scalar"],"Input Strides":[[1],[]],"Input Dims":[[128],[]],"Ev Idx":55}},{"ph":"X","cat":"cpu_op","name":"aten::all","pid":996,"tid":996,"ts":3148028963500.742,"dur":19.404,"args":{"External id":57,"Sequence number":41,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["bool"],"Input Strides":[[1]],"Input Dims":[[128]],"Ev Idx":56}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028963506.272,"dur":0.706,"args":{"External id":58,"Record function id":0,"Concrete Inputs":["","[1]","[0]",""],"Input type":["bool","ScalarList","ScalarList",""],"Input Strides":[[],[],[],[]],"Input Dims":[[],[],[],[]],"Ev Idx":57}},{"ph":"X","cat":"cpu_op","name":"aten::_assert_async","pid":996,"tid":996,"ts":3148028963525.37,"dur":8.908,"args":{"External id":59,"Sequence number":41,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["",""],"Input type":["bool",""],"Input Strides":[[],[]],"Input Dims":[[],[]],"Ev Idx":58}},{"ph":"X","cat":"cpu_op","name":"aten::mul","pid":996,"tid":996,"ts":3148028963540.248,"dur":18.039,"args":{"External id":60,"Sequence number":41,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["",""],"Input type":["float","double"],"Input Strides":[[2048,1],[]],"Input Dims":[[128,2048],[]],"Ev Idx":59}},{"ph":"X","cat":"user_annotation","name":"ProfilerStep#6","pid":996,"tid":996,"ts":3148028963591.116,"dur":338.94,"args":{"External id":61,"Record function id":0,"Ev Idx":60}},{"ph":"X","cat":"cpu_op","name":"aten::linear","pid":996,"tid":996,"ts":3148028963604.817,"dur":46.313,"args":{"External id":62,"Sequence number":42,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","",""],"Input type":["float","float","float"],"Input Strides":[[1024,1],[1024,1],[1]],"Input Dims":[[128,1024],[2048,1024],[2048]],"Ev Idx":61}},{"ph":"X","cat":"cpu_op","name":"aten::t","pid":996,"tid":996,"ts":3148028963605.525,"dur":7.028,"args":{"External id":63,"Sequence number":42,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["float"],"Input Strides":[[1024,1]],"Input Dims":[[2048,1024]],"Ev Idx":62}},{"ph":"X","cat":"cpu_op","name":"aten::transpose","pid":996,"tid":996,"ts":3148028963607.652,"dur":3.223,"args":{"External id":64,"Record function id":0,"Concrete Inputs":["","0","1"],"Input type":["float","Scalar","Scalar"],"Input Strides":[[1024,1],[],[]],"Input Dims":[[2048,1024],[],[]],"Ev Idx":63}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028963609.447,"dur":0.987,"args":{"External id":65,"Record function id":0,"Concrete Inputs":["","[1024, 2048]","[1, 1024]",""],"Input type":["float","ScalarList","ScalarList",""],"Input Strides":[[1024,1],[],[],[]],"Input Dims":[[2048,1024],[],[],[]],"Ev Idx":64}},{"ph":"X","cat":"cpu_op","name":"aten::addmm","pid":996,"tid":996,"ts":3148028963613.625,"dur":36.336,"args":{"External id":66,"Sequence number":43,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","","","1","1"],"Input type":["float","float","float","Scalar","Scalar"],"Input Strides":[[1],[1024,1],[1,1024],[],[]],"Input Dims":[[2048],[128,1024],[1024,2048],[],[]],"Ev Idx":65}},{"ph":"X","cat":"cpu_op","name":"aten::softmax","pid":996,"tid":996,"ts":3148028963660.858,"dur":21.285,"args":{"External id":67,"Sequence number":44,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","-1",""],"Input type":["float","Scalar",""],"Input Strides":[[2048,1],[],[]],"Input Dims":[[128,2048],[],[]],"Ev Idx":66}},{"ph":"X","cat":"cpu_op","name":"aten::_softmax","pid":996,"tid":996,"ts":3148028963662.264,"dur":18.583,"args":{"External id":68,"Sequence number":44,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","-1","False"],"Input type":["float","Scalar","Scalar"],"Input Strides":[[2048,1],[],[]],"Input Dims":[[128,2048],[],[]],"Ev Idx":67}},{"ph":"X","cat":"cpu_op","name":"aten::sum","pid":996,"tid":996,"ts":3148028963720.191,"dur":40.774,"args":{"External id":69,"Sequence number":45,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","[-1]","False",""],"Input type":["float","ScalarList","Scalar",""],"Input Strides":[[2048,1],[],[],[]],"Input Dims":[[128,2048],[],[],[]],"Ev Idx":68}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028963728.167,"dur":0.808,"args":{"External id":70,"Record function id":0,"Concrete Inputs":["","[128, 1]","[1, 0]",""],"Input type":["float","ScalarList","ScalarList",""],"Input Strides":[[1],[],[],[]],"Input Dims":[[128],[],[],[]],"Ev Idx":69}},{"ph":"X","cat":"cpu_op","name":"aten::sub","pid":996,"tid":996,"ts":3148028963781.61,"dur":17.775,"args":{"External id":71,"Sequence number":46,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","","1"],"Input type":["float","double","Scalar"],"Input Strides":[[1],[],[]],"Input Dims":[[128],[],[]],"Ev Idx":70}},{"ph":"X","cat":"cpu_op","name":"aten::abs","pid":996,"tid":996,"ts":3148028963803.949,"dur":23.925,"args":{"External id":72,"Sequence number":47,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["float"],"Input Strides":[[1]],"Input Dims":[[128]],"Ev Idx":71}},{"ph":"X","cat":"cpu_op","name":"aten::empty","pid":996,"tid":996,"ts":3148028963806.837,"dur":3.222,"args":{"External id":73,"Record function id":0,"Concrete Inputs":["[0]","6","0","","",""],"Input type":["ScalarList","Scalar","Scalar","","",""],"Input Strides":[[],[],[],[],[],[]],"Input Dims":[[],[],[],[],[],[]],"Ev Idx":72}},{"ph":"X","cat":"cpu_op","name":"aten::abs","pid":996,"tid":996,"ts":3148028963811.045,"dur":15.438,"args":{"External id":74,"Record function id":0,"Concrete Inputs":["",""],"Input type":["float","float"],"Input Strides":[[1],[1]],"Input Dims":[[128],[0]],"Ev Idx":73}},{"ph":"X","cat":"cpu_op","name":"aten::resize_","pid":996,"tid":996,"ts":3148028963813.861,"dur":2.703,"args":{"External id":75,"Record function id":0,"Concrete Inputs":["","[128]",""],"Input type":["float","ScalarList",""],"Input Strides":[[1],[],[]],"Input Dims":[[0],[],[]],"Ev Idx":74}},{"ph":"X","cat":"cpu_op","name":"aten::le","pid":996,"tid":996,"ts":3148028963832.756,"dur":16.872,"args":{"External id":76,"Sequence number":48,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","1.0000000000000001e-05"],"Input type":["float","Scalar"],"Input Strides":[[1],[]],"Input Dims":[[128],[]],"Ev Idx":75}},{"ph":"X","cat":"cpu_op","name":"aten::all","pid":996,"tid":996,"ts":3148028963856.252,"dur":19.437,"args":{"External id":77,"Sequence number":48,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["bool"],"Input Strides":[[1]],"Input Dims":[[128]],"Ev Idx":76}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028963861.831,"dur":0.676,"args":{"External id":78,"Record function id":0,"Concrete Inputs":["","[1]","[0]",""],"Input type":["bool","ScalarList","ScalarList",""],"Input Strides":[[],[],[],[]],"Input Dims":[[],[],[],[]],"Ev Idx":77}},{"ph":"X","cat":"cpu_op","name":"aten::_assert_async","pid":996,"tid":996,"ts":3148028963880.769,"dur":8.702,"args":{"External id":79,"Sequence number":48,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["",""],"Input type":["bool",""],"Input Strides":[[],[]],"Input Dims":[[],[]],"Ev Idx":78}},{"ph":"X","cat":"cpu_op","name":"aten::mul","pid":996,"tid":996,"ts":3148028963895.111,"dur":17.728,"args":{"External id":80,"Sequence number":48,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["",""],"Input type":["float","double"],"Input Strides":[[2048,1],[]],"Input Dims":[[128,2048],[]],"Ev Idx":79}},{"ph":"X","cat":"user_annotation","name":"ProfilerStep#7","pid":996,"tid":996,"ts":3148028963946.011,"dur":278.868,"args":{"External id":81,"Record function id":0,"Ev Idx":80}},{"ph":"X","cat":"cpu_op","name":"aten::linear","pid":996,"tid":996,"ts":3148028963959.643,"dur":42.847,"args":{"External id":82,"Sequence number":49,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","",""],"Input type":["float","float","float"],"Input Strides":[[1024,1],[1024,1],[1]],"Input Dims":[[128,1024],[2048,1024],[2048]],"Ev Idx":81}},{"ph":"X","cat":"cpu_op","name":"aten::t","pid":996,"tid":996,"ts":3148028963960.317,"dur":7.128,"args":{"External id":83,"Sequence number":49,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["float"],"Input Strides":[[1024,1]],"Input Dims":[[2048,1024]],"Ev Idx":82}},{"ph":"X","cat":"cpu_op","name":"aten::transpose","pid":996,"tid":996,"ts":3148028963962.451,"dur":3.317,"args":{"External id":84,"Record function id":0,"Concrete Inputs":["","0","1"],"Input type":["float","Scalar","Scalar"],"Input Strides":[[1024,1],[],[]],"Input Dims":[[2048,1024],[],[]],"Ev Idx":83}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028963964.306,"dur":0.976,"args":{"External id":85,"Record function id":0,"Concrete Inputs":["","[1024, 2048]","[1, 1024]",""],"Input type":["float","ScalarList","ScalarList",""],"Input Strides":[[1024,1],[],[],[]],"Input Dims":[[2048,1024],[],[],[]],"Ev Idx":84}},{"ph":"X","cat":"cpu_op","name":"aten::addmm","pid":996,"tid":996,"ts":3148028963968.4,"dur":32.949,"args":{"External id":86,"Sequence number":50,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","","","1","1"],"Input type":["float","float","float","Scalar","Scalar"],"Input Strides":[[1],[1024,1],[1,1024],[],[]],"Input Dims":[[2048],[128,1024],[1024,2048],[],[]],"Ev Idx":85}},{"ph":"X","cat":"cpu_op","name":"aten::softmax","pid":996,"tid":996,"ts":3148028964012.038,"dur":26.558,"args":{"External id":87,"Sequence number":51,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","-1",""],"Input type":["float","Scalar",""],"Input Strides":[[2048,1],[],[]],"Input Dims":[[128,2048],[],[]],"Ev Idx":86}},{"ph":"X","cat":"cpu_op","name":"aten::_softmax","pid":996,"tid":996,"ts":3148028964013.38,"dur":23.68,"args":{"External id":88,"Sequence number":51,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","-1","False"],"Input type":["float","Scalar","Scalar"],"Input Strides":[[2048,1],[],[]],"Input Dims":[[128,2048],[],[]],"Ev Idx":87}},{"ph":"X","cat":"cpu_op","name":"aten::sum","pid":996,"tid":996,"ts":3148028964045.639,"dur":24.034,"args":{"External id":89,"Sequence number":52,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","[-1]","False",""],"Input type":["float","ScalarList","Scalar",""],"Input Strides":[[2048,1],[],[],[]],"Input Dims":[[128,2048],[],[],[]],"Ev Idx":88}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028964052.785,"dur":0.707,"args":{"External id":90,"Record function id":0,"Concrete Inputs":["","[128, 1]","[1, 0]",""],"Input type":["float","ScalarList","ScalarList",""],"Input Strides":[[1],[],[],[]],"Input Dims":[[128],[],[],[]],"Ev Idx":89}},{"ph":"X","cat":"cpu_op","name":"aten::sub","pid":996,"tid":996,"ts":3148028964076.795,"dur":17.542,"args":{"External id":91,"Sequence number":53,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","","1"],"Input type":["float","double","Scalar"],"Input Strides":[[1],[],[]],"Input Dims":[[128],[],[]],"Ev Idx":90}},{"ph":"X","cat":"cpu_op","name":"aten::abs","pid":996,"tid":996,"ts":3148028964098.769,"dur":23.7,"args":{"External id":92,"Sequence number":54,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["float"],"Input Strides":[[1]],"Input Dims":[[128]],"Ev Idx":91}},{"ph":"X","cat":"cpu_op","name":"aten::empty","pid":996,"tid":996,"ts":3148028964101.497,"dur":3.226,"args":{"External id":93,"Record function id":0,"Concrete Inputs":["[0]","6","0","","",""],"Input type":["ScalarList","Scalar","Scalar","","",""],"Input Strides":[[],[],[],[],[],[]],"Input Dims":[[],[],[],[],[],[]],"Ev Idx":92}},{"ph":"X","cat":"cpu_op","name":"aten::abs","pid":996,"tid":996,"ts":3148028964105.628,"dur":15.406,"args":{"External id":94,"Record function id":0,"Concrete Inputs":["",""],"Input type":["float","float"],"Input Strides":[[1],[1]],"Input Dims":[[128],[0]],"Ev Idx":93}},{"ph":"X","cat":"cpu_op","name":"aten::resize_","pid":996,"tid":996,"ts":3148028964108.49,"dur":2.684,"args":{"External id":95,"Record function id":0,"Concrete Inputs":["","[128]",""],"Input type":["float","ScalarList",""],"Input Strides":[[1],[],[]],"Input Dims":[[0],[],[]],"Ev Idx":94}},{"ph":"X","cat":"cpu_op","name":"aten::le","pid":996,"tid":996,"ts":3148028964127.297,"dur":16.842,"args":{"External id":96,"Sequence number":55,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["","1.0000000000000001e-05"],"Input type":["float","Scalar"],"Input Strides":[[1],[]],"Input Dims":[[128],[]],"Ev Idx":95}},{"ph":"X","cat":"cpu_op","name":"aten::all","pid":996,"tid":996,"ts":3148028964150.772,"dur":19.685,"args":{"External id":97,"Sequence number":55,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":[""],"Input type":["bool"],"Input Strides":[[1]],"Input Dims":[[128]],"Ev Idx":96}},{"ph":"X","cat":"cpu_op","name":"aten::as_strided","pid":996,"tid":996,"ts":3148028964156.398,"dur":0.665,"args":{"External id":98,"Record function id":0,"Concrete Inputs":["","[1]","[0]",""],"Input type":["bool","ScalarList","ScalarList",""],"Input Strides":[[],[],[],[]],"Input Dims":[[],[],[],[]],"Ev Idx":97}},{"ph":"X","cat":"cpu_op","name":"aten::_assert_async","pid":996,"tid":996,"ts":3148028964175.397,"dur":8.704,"args":{"External id":99,"Sequence number":55,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["",""],"Input type":["bool",""],"Input Strides":[[],[]],"Input Dims":[[],[]],"Ev Idx":98}},{"ph":"X","cat":"cpu_op","name":"aten::mul","pid":996,"tid":996,"ts":3148028964190.154,"dur":17.94,"args":{"External id":100,"Sequence number":55,"Fwd thread id":0,"Record function id":0,"Concrete Inputs":["",""],"Input type":["float","double"],"Input Strides":[[2048,1],[]],"Input Dims":[[128,2048],[]],"Ev Idx":99}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962337.679,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131794499272704,"finished":false,"Ev Idx":100}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962413.253,"args":{"Total Reserved":60817408,"Total Allocated":46669824,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131793518854144,"finished":false,"Ev Idx":101}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962486.797,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794499272704,"finished":false,"Ev Idx":102}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962500.97,"args":{"Total Reserved":60817408,"Total Allocated":45621760,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455764992,"finished":false,"Ev Idx":103}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962539.045,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814286016,"finished":false,"Ev Idx":104}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962552.217,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":105}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962588.663,"args":{"Total Reserved":0,"Total Allocated":0,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814286016,"finished":false,"Ev Idx":106}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962643.686,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455766016,"finished":false,"Ev Idx":107}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962704.326,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814286848,"finished":false,"Ev Idx":108}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962735.841,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455766528,"finished":false,"Ev Idx":109}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962738.502,"args":{"Total Reserved":0,"Total Allocated":0,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814286848,"finished":false,"Ev Idx":110}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962768.231,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":111}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962769.659,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455766016,"finished":false,"Ev Idx":112}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962788.603,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":113}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962812.046,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455766528,"finished":false,"Ev Idx":114}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962832.798,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814289216,"finished":false,"Ev Idx":115}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962842.079,"args":{"Total Reserved":60817408,"Total Allocated":46670848,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131793519902720,"finished":false,"Ev Idx":116}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962857.254,"args":{"Total Reserved":60817408,"Total Allocated":46670336,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":117}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962858.103,"args":{"Total Reserved":60817408,"Total Allocated":46669824,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455764992,"finished":false,"Ev Idx":118}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962871.113,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794498224128,"finished":false,"Ev Idx":119}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962888.377,"args":{"Total Reserved":60817408,"Total Allocated":44572672,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794454716416,"finished":false,"Ev Idx":120}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962949.124,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131794454716416,"finished":false,"Ev Idx":121}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028962995.965,"args":{"Total Reserved":60817408,"Total Allocated":46669824,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131794498224128,"finished":false,"Ev Idx":122}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963028.898,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794454716416,"finished":false,"Ev Idx":123}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963054.196,"args":{"Total Reserved":60817408,"Total Allocated":45621760,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794499272704,"finished":false,"Ev Idx":124}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963101.167,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":633556416,"finished":false,"Ev Idx":125}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963111.987,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794499273216,"finished":false,"Ev Idx":126}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963127.694,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":633556416,"finished":false,"Ev Idx":127}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963143.82,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794499273728,"finished":false,"Ev Idx":128}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963163.492,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814291072,"finished":false,"Ev Idx":129}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963167.83,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794499274240,"finished":false,"Ev Idx":130}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963170.198,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814291072,"finished":false,"Ev Idx":131}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963183.217,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794499273216,"finished":false,"Ev Idx":132}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963184.582,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794499273728,"finished":false,"Ev Idx":133}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963190.176,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794499273216,"finished":false,"Ev Idx":134}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963210.086,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794499274240,"finished":false,"Ev Idx":135}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963226.704,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814292480,"finished":false,"Ev Idx":136}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963248.927,"args":{"Total Reserved":60817408,"Total Allocated":46670848,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131794454716416,"finished":false,"Ev Idx":137}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963267.415,"args":{"Total Reserved":60817408,"Total Allocated":46670336,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794499273216,"finished":false,"Ev Idx":138}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963268.316,"args":{"Total Reserved":60817408,"Total Allocated":46669824,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794499272704,"finished":false,"Ev Idx":139}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963270.27,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814289216,"finished":false,"Ev Idx":140}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963271.181,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131793518854144,"finished":false,"Ev Idx":141}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963272.619,"args":{"Total Reserved":60817408,"Total Allocated":44572672,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131793519902720,"finished":false,"Ev Idx":142}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963327.66,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131794499272704,"finished":false,"Ev Idx":143}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963371.624,"args":{"Total Reserved":60817408,"Total Allocated":46669824,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131793518854144,"finished":false,"Ev Idx":144}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963390.16,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794499272704,"finished":false,"Ev Idx":145}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963398.683,"args":{"Total Reserved":60817408,"Total Allocated":45621760,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455764992,"finished":false,"Ev Idx":146}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963423.324,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814289216,"finished":false,"Ev Idx":147}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963431.301,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":148}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963444.913,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814289216,"finished":false,"Ev Idx":149}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963459.54,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455766016,"finished":false,"Ev Idx":150}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963478.072,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814295552,"finished":false,"Ev Idx":151}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963482.068,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455766528,"finished":false,"Ev Idx":152}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963484.351,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814295552,"finished":false,"Ev Idx":153}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963496.915,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":154}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963498.289,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455766016,"finished":false,"Ev Idx":155}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963503.388,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":156}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963522.24,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455766528,"finished":false,"Ev Idx":157}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963537.98,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814296640,"finished":false,"Ev Idx":158}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963546.397,"args":{"Total Reserved":60817408,"Total Allocated":46670848,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131793519902720,"finished":false,"Ev Idx":159}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963560.921,"args":{"Total Reserved":60817408,"Total Allocated":46670336,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":160}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963561.727,"args":{"Total Reserved":60817408,"Total Allocated":46669824,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455764992,"finished":false,"Ev Idx":161}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963563.514,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814292480,"finished":false,"Ev Idx":162}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963564.34,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794498224128,"finished":false,"Ev Idx":163}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963565.716,"args":{"Total Reserved":60817408,"Total Allocated":44572672,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794454716416,"finished":false,"Ev Idx":164}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963622.403,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131794454716416,"finished":false,"Ev Idx":165}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963666.251,"args":{"Total Reserved":60817408,"Total Allocated":46669824,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131794498224128,"finished":false,"Ev Idx":166}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963684.953,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794454716416,"finished":false,"Ev Idx":167}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963724.803,"args":{"Total Reserved":60817408,"Total Allocated":45621760,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794499272704,"finished":false,"Ev Idx":168}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963765.934,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":630754048,"finished":false,"Ev Idx":169}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963787.35,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794499273216,"finished":false,"Ev Idx":170}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963801.079,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":630754048,"finished":false,"Ev Idx":171}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963815.719,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794499273728,"finished":false,"Ev Idx":172}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963834.167,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814298752,"finished":false,"Ev Idx":173}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963838.031,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794499274240,"finished":false,"Ev Idx":174}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963840.309,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814298752,"finished":false,"Ev Idx":175}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963852.433,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794499273216,"finished":false,"Ev Idx":176}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963853.768,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794499273728,"finished":false,"Ev Idx":177}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963859.002,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794499273216,"finished":false,"Ev Idx":178}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963877.795,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794499274240,"finished":false,"Ev Idx":179}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963892.99,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814300160,"finished":false,"Ev Idx":180}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963900.996,"args":{"Total Reserved":60817408,"Total Allocated":46670848,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131794454716416,"finished":false,"Ev Idx":181}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963915.607,"args":{"Total Reserved":60817408,"Total Allocated":46670336,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794499273216,"finished":false,"Ev Idx":182}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963916.489,"args":{"Total Reserved":60817408,"Total Allocated":46669824,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794499272704,"finished":false,"Ev Idx":183}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963918.243,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814296640,"finished":false,"Ev Idx":184}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963919.072,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131793518854144,"finished":false,"Ev Idx":185}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963920.509,"args":{"Total Reserved":60817408,"Total Allocated":44572672,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131793519902720,"finished":false,"Ev Idx":186}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028963974.089,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131794499272704,"finished":false,"Ev Idx":187}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964017.363,"args":{"Total Reserved":60817408,"Total Allocated":46669824,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131793518854144,"finished":false,"Ev Idx":188}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964041.327,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794499272704,"finished":false,"Ev Idx":189}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964049.793,"args":{"Total Reserved":60817408,"Total Allocated":45621760,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455764992,"finished":false,"Ev Idx":190}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964074.501,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814296640,"finished":false,"Ev Idx":191}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964082.457,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":192}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964096.057,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814296640,"finished":false,"Ev Idx":193}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964110.355,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455766016,"finished":false,"Ev Idx":194}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964128.684,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814303104,"finished":false,"Ev Idx":195}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964132.726,"args":{"Total Reserved":60817408,"Total Allocated":45623296,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455766528,"finished":false,"Ev Idx":196}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964134.928,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814303104,"finished":false,"Ev Idx":197}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964146.867,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":198}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964148.197,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455766016,"finished":false,"Ev Idx":199}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964153.524,"args":{"Total Reserved":60817408,"Total Allocated":45622784,"Bytes":512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":200}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964172.485,"args":{"Total Reserved":60817408,"Total Allocated":45622272,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455766528,"finished":false,"Ev Idx":201}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964187.913,"args":{"Total Reserved":0,"Total Allocated":16,"Bytes":8,"Device Id":-1,"Device Type":0,"Addr":814304320,"finished":false,"Ev Idx":202}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964196.296,"args":{"Total Reserved":60817408,"Total Allocated":46670848,"Bytes":1048576,"Device Id":0,"Device Type":1,"Addr":131793519902720,"finished":false,"Ev Idx":203}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964210.856,"args":{"Total Reserved":60817408,"Total Allocated":46670336,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455765504,"finished":false,"Ev Idx":204}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964211.707,"args":{"Total Reserved":60817408,"Total Allocated":46669824,"Bytes":-512,"Device Id":0,"Device Type":1,"Addr":131794455764992,"finished":false,"Ev Idx":205}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964213.466,"args":{"Total Reserved":0,"Total Allocated":8,"Bytes":-8,"Device Id":-1,"Device Type":0,"Addr":814300160,"finished":false,"Ev Idx":206}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964214.298,"args":{"Total Reserved":60817408,"Total Allocated":45621248,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794498224128,"finished":false,"Ev Idx":207}},{"ph":"i","cat":"cpu_instant_event","s":"t","name":"[memory]","pid":996,"tid":996,"ts":3148028964215.514,"args":{"Total Reserved":60817408,"Total Allocated":44572672,"Bytes":-1048576,"Device Id":0,"Device Type":1,"Addr":131794454716416,"finished":false,"Ev Idx":208}},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceGetAttribute","pid":996,"tid":996,"ts":3148028962364.636,"dur":0.659,"args":{"External id":6,"cbid":200,"correlation":1678}},{"ph":"f","id":1678,"pid":996,"tid":996,"ts":3148028962364.636,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaMemsetAsync","pid":996,"tid":996,"ts":3148028962367.116,"dur":0.314,"args":{"External id":6,"cbid":51,"correlation":1681}},{"ph":"s","id":1681,"pid":996,"tid":996,"ts":3148028962367.116,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void cutlass::Kernel2<cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4>(cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4::Params)","pid":0,"tid":7,"ts":3148028962376.886,"dur":13.824,"args":{"External id":6,"queued":0,"device":0,"context":1,"stream":7,"correlation":1682,"registers per thread":94,"shared memory":98304,"blocks per SM":0.761905,"warps per SM":3.047619,"grid":[16,4,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":0,"limitingFactors":"SMEM","blockLimitRegs":5,"blockLimitSharedMem":0,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":12288,"allocatedSharedMemPerBlock":99328},"graph id":0,"graph node id":0}},{"ph":"f","id":1682,"pid":0,"tid":7,"ts":3148028962376.886,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":996,"tid":996,"ts":3148028962367.673,"dur":8.359,"args":{"External id":6,"cbid":307,"correlation":1682}},{"ph":"s","id":1682,"pid":996,"tid":996,"ts":3148028962367.673,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void (anonymous namespace)::softmax_warp_forward<float, float, float, 11, false, false, 32>(float*, float const*, int, int, int, bool const*, int, bool)","pid":0,"tid":7,"ts":3148028962445.719,"dur":3.487,"args":{"External id":8,"queued":0,"device":0,"context":1,"stream":7,"correlation":1694,"registers per thread":168,"shared memory":0,"blocks per SM":0.380952,"warps per SM":1.52381,"grid":[32,1,1],"block":[32,4,1],"est. achieved occupancy %":3,"occupancy":{"activeBlocksPerMultiprocessor":3,"limitingFactors":"REGS","blockLimitRegs":3,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":21504,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1694,"pid":0,"tid":7,"ts":3148028962445.719,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028962433.853,"dur":39.07,"args":{"External id":8,"cbid":211,"correlation":1694}},{"ph":"s","id":1694,"pid":996,"tid":996,"ts":3148028962433.853,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::operator()(at::TensorIterator&)::{lambda(float, float)#1}>, unsigned int, float, 4, 4> >(at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::operator()(at::TensorIterator&)::{lambda(float, float)#1}>, unsigned int, float, 4, 4>)","pid":0,"tid":7,"ts":3148028962527.479,"dur":3.68,"args":{"External id":9,"queued":0,"device":0,"context":1,"stream":7,"correlation":1709,"registers per thread":30,"shared memory":16,"blocks per SM":0.095238,"warps per SM":1.52381,"grid":[8,1,1],"block":[32,16,1],"est. achieved occupancy %":3,"occupancy":{"activeBlocksPerMultiprocessor":3,"limitingFactors":"WARPS","blockLimitRegs":4,"blockLimitSharedMem":88,"blockLimitWarps":3,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":16384,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":1709,"pid":0,"tid":7,"ts":3148028962527.479,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028962517.624,"dur":9.455,"args":{"External id":9,"cbid":211,"correlation":1709}},{"ph":"s","id":1709,"pid":996,"tid":996,"ts":3148028962517.624,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul> >(int, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028962567.991,"dur":0.896,"args":{"External id":11,"queued":0,"device":0,"context":1,"stream":7,"correlation":1720,"registers per thread":36,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1720,"pid":0,"tid":7,"ts":3148028962567.991,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028962558.53,"dur":8.813,"args":{"External id":11,"cbid":211,"correlation":1720}},{"ph":"s","id":1720,"pid":996,"tid":996,"ts":3148028962558.53,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::AbsFunctor<float>, std::array<char*, 2ul> >(int, at::native::AbsFunctor<float>, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028962667,"dur":0.928,"args":{"External id":14,"queued":0,"device":0,"context":1,"stream":7,"correlation":1738,"registers per thread":36,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1738,"pid":0,"tid":7,"ts":3148028962667,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028962647.983,"dur":23.49,"args":{"External id":14,"cbid":211,"correlation":1738}},{"ph":"s","id":1738,"pid":996,"tid":996,"ts":3148028962647.983,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul> >(int, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028962748.952,"dur":0.928,"args":{"External id":16,"queued":0,"device":0,"context":1,"stream":7,"correlation":1749,"registers per thread":38,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1749,"pid":0,"tid":7,"ts":3148028962748.952,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028962740.561,"dur":7.475,"args":{"External id":16,"cbid":211,"correlation":1749}},{"ph":"s","id":1749,"pid":996,"tid":996,"ts":3148028962740.561,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4> >(at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4>)","pid":0,"tid":7,"ts":3148028962808.6,"dur":1.504,"args":{"External id":17,"queued":0,"device":0,"context":1,"stream":7,"correlation":1764,"registers per thread":36,"shared memory":16,"blocks per SM":0.011905,"warps per SM":0.011905,"grid":[1,1,1],"block":[32,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"BLOCKS","blockLimitRegs":48,"blockLimitSharedMem":88,"blockLimitWarps":48,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":1280,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":1764,"pid":0,"tid":7,"ts":3148028962808.6,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028962800.596,"dur":6.752,"args":{"External id":17,"cbid":211,"correlation":1764}},{"ph":"s","id":1764,"pid":996,"tid":996,"ts":3148028962800.596,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::_assert_async_cuda_kernel<bool>(bool const*, at::native::Msg)","pid":0,"tid":7,"ts":3148028962828.793,"dur":5.152,"args":{"External id":19,"queued":0,"device":0,"context":1,"stream":7,"correlation":1771,"registers per thread":24,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.000372,"grid":[1,1,1],"block":[1,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"BLOCKS","blockLimitRegs":84,"blockLimitSharedMem":100,"blockLimitWarps":48,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":768,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1771,"pid":0,"tid":7,"ts":3148028962828.793,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028962821.526,"dur":5.628,"args":{"External id":19,"cbid":211,"correlation":1771}},{"ph":"s","id":1771,"pid":996,"tid":996,"ts":3148028962821.526,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul> >(int, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028962853.337,"dur":1.216,"args":{"External id":20,"queued":0,"device":0,"context":1,"stream":7,"correlation":1782,"registers per thread":36,"shared memory":0,"blocks per SM":3.047619,"warps per SM":12.190476,"grid":[256,1,1],"block":[128,1,1],"est. achieved occupancy %":25,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1782,"pid":0,"tid":7,"ts":3148028962853.337,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028962845.705,"dur":6.214,"args":{"External id":20,"cbid":211,"correlation":1782}},{"ph":"s","id":1782,"pid":996,"tid":996,"ts":3148028962845.705,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceGetAttribute","pid":996,"tid":996,"ts":3148028962964.673,"dur":0.647,"args":{"External id":26,"cbid":200,"correlation":1800}},{"ph":"f","id":1800,"pid":996,"tid":996,"ts":3148028962964.673,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaMemsetAsync","pid":996,"tid":996,"ts":3148028962966.996,"dur":0.289,"args":{"External id":26,"cbid":51,"correlation":1803}},{"ph":"s","id":1803,"pid":996,"tid":996,"ts":3148028962966.996,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void cutlass::Kernel2<cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4>(cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4::Params)","pid":0,"tid":7,"ts":3148028962976.377,"dur":13.953,"args":{"External id":26,"queued":0,"device":0,"context":1,"stream":7,"correlation":1804,"registers per thread":94,"shared memory":98304,"blocks per SM":0.761905,"warps per SM":3.047619,"grid":[16,4,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":0,"limitingFactors":"SMEM","blockLimitRegs":5,"blockLimitSharedMem":0,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":12288,"allocatedSharedMemPerBlock":99328},"graph id":0,"graph node id":0}},{"ph":"f","id":1804,"pid":0,"tid":7,"ts":3148028962976.377,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":996,"tid":996,"ts":3148028962967.489,"dur":7.929,"args":{"External id":26,"cbid":307,"correlation":1804}},{"ph":"s","id":1804,"pid":996,"tid":996,"ts":3148028962967.489,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void (anonymous namespace)::softmax_warp_forward<float, float, float, 11, false, false, 32>(float*, float const*, int, int, int, bool const*, int, bool)","pid":0,"tid":7,"ts":3148028963008.506,"dur":3.456,"args":{"External id":28,"queued":0,"device":0,"context":1,"stream":7,"correlation":1816,"registers per thread":168,"shared memory":0,"blocks per SM":0.380952,"warps per SM":1.52381,"grid":[32,1,1],"block":[32,4,1],"est. achieved occupancy %":3,"occupancy":{"activeBlocksPerMultiprocessor":3,"limitingFactors":"REGS","blockLimitRegs":3,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":21504,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1816,"pid":0,"tid":7,"ts":3148028963008.506,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963000.349,"dur":6.971,"args":{"External id":28,"cbid":211,"correlation":1816}},{"ph":"s","id":1816,"pid":996,"tid":996,"ts":3148028963000.349,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::operator()(at::TensorIterator&)::{lambda(float, float)#1}>, unsigned int, float, 4, 4> >(at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::operator()(at::TensorIterator&)::{lambda(float, float)#1}>, unsigned int, float, 4, 4>)","pid":0,"tid":7,"ts":3148028963090.106,"dur":3.712,"args":{"External id":29,"queued":0,"device":0,"context":1,"stream":7,"correlation":1831,"registers per thread":30,"shared memory":16,"blocks per SM":0.095238,"warps per SM":1.52381,"grid":[8,1,1],"block":[32,16,1],"est. achieved occupancy %":3,"occupancy":{"activeBlocksPerMultiprocessor":3,"limitingFactors":"WARPS","blockLimitRegs":4,"blockLimitSharedMem":88,"blockLimitWarps":3,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":16384,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":1831,"pid":0,"tid":7,"ts":3148028963090.106,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963077.468,"dur":12.446,"args":{"External id":29,"cbid":211,"correlation":1831}},{"ph":"s","id":1831,"pid":996,"tid":996,"ts":3148028963077.468,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul> >(int, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963124.346,"dur":0.928,"args":{"External id":31,"queued":0,"device":0,"context":1,"stream":7,"correlation":1842,"registers per thread":36,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1842,"pid":0,"tid":7,"ts":3148028963124.346,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963116.293,"dur":6.923,"args":{"External id":31,"cbid":211,"correlation":1842}},{"ph":"s","id":1842,"pid":996,"tid":996,"ts":3148028963116.293,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::AbsFunctor<float>, std::array<char*, 2ul> >(int, at::native::AbsFunctor<float>, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963154.906,"dur":0.896,"args":{"External id":34,"queued":0,"device":0,"context":1,"stream":7,"correlation":1860,"registers per thread":36,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1860,"pid":0,"tid":7,"ts":3148028963154.906,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963147.315,"dur":6.273,"args":{"External id":34,"cbid":211,"correlation":1860}},{"ph":"s","id":1860,"pid":996,"tid":996,"ts":3148028963147.315,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul> >(int, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963179.803,"dur":0.928,"args":{"External id":36,"queued":0,"device":0,"context":1,"stream":7,"correlation":1871,"registers per thread":38,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1871,"pid":0,"tid":7,"ts":3148028963179.803,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963171.977,"dur":6.4,"args":{"External id":36,"cbid":211,"correlation":1871}},{"ph":"s","id":1871,"pid":996,"tid":996,"ts":3148028963171.977,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4> >(at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4>)","pid":0,"tid":7,"ts":3148028963207.035,"dur":1.504,"args":{"External id":37,"queued":0,"device":0,"context":1,"stream":7,"correlation":1886,"registers per thread":36,"shared memory":16,"blocks per SM":0.011905,"warps per SM":0.011905,"grid":[1,1,1],"block":[32,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"BLOCKS","blockLimitRegs":48,"blockLimitSharedMem":88,"blockLimitWarps":48,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":1280,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":1886,"pid":0,"tid":7,"ts":3148028963207.035,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963199.298,"dur":6.291,"args":{"External id":37,"cbid":211,"correlation":1886}},{"ph":"s","id":1886,"pid":996,"tid":996,"ts":3148028963199.298,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::_assert_async_cuda_kernel<bool>(bool const*, at::native::Msg)","pid":0,"tid":7,"ts":3148028963223.099,"dur":5.152,"args":{"External id":39,"queued":0,"device":0,"context":1,"stream":7,"correlation":1893,"registers per thread":24,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.000372,"grid":[1,1,1],"block":[1,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"BLOCKS","blockLimitRegs":84,"blockLimitSharedMem":100,"blockLimitWarps":48,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":768,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1893,"pid":0,"tid":7,"ts":3148028963223.099,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963216.066,"dur":5.367,"args":{"External id":39,"cbid":211,"correlation":1893}},{"ph":"s","id":1893,"pid":996,"tid":996,"ts":3148028963216.066,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul> >(int, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963262.971,"dur":1.216,"args":{"External id":40,"queued":0,"device":0,"context":1,"stream":7,"correlation":1904,"registers per thread":36,"shared memory":0,"blocks per SM":3.047619,"warps per SM":12.190476,"grid":[256,1,1],"block":[128,1,1],"est. achieved occupancy %":25,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1904,"pid":0,"tid":7,"ts":3148028963262.971,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963252.476,"dur":9.101,"args":{"External id":40,"cbid":211,"correlation":1904}},{"ph":"s","id":1904,"pid":996,"tid":996,"ts":3148028963252.476,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceGetAttribute","pid":996,"tid":996,"ts":3148028963342.623,"dur":0.599,"args":{"External id":46,"cbid":200,"correlation":1922}},{"ph":"f","id":1922,"pid":996,"tid":996,"ts":3148028963342.623,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaMemsetAsync","pid":996,"tid":996,"ts":3148028963344.803,"dur":0.282,"args":{"External id":46,"cbid":51,"correlation":1925}},{"ph":"s","id":1925,"pid":996,"tid":996,"ts":3148028963344.803,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void cutlass::Kernel2<cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4>(cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4::Params)","pid":0,"tid":7,"ts":3148028963354.107,"dur":13.889,"args":{"External id":46,"queued":0,"device":0,"context":1,"stream":7,"correlation":1926,"registers per thread":94,"shared memory":98304,"blocks per SM":0.761905,"warps per SM":3.047619,"grid":[16,4,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":0,"limitingFactors":"SMEM","blockLimitRegs":5,"blockLimitSharedMem":0,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":12288,"allocatedSharedMemPerBlock":99328},"graph id":0,"graph node id":0}},{"ph":"f","id":1926,"pid":0,"tid":7,"ts":3148028963354.107,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":996,"tid":996,"ts":3148028963345.312,"dur":7.504,"args":{"External id":46,"cbid":307,"correlation":1926}},{"ph":"s","id":1926,"pid":996,"tid":996,"ts":3148028963345.312,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void (anonymous namespace)::softmax_warp_forward<float, float, float, 11, false, false, 32>(float*, float const*, int, int, int, bool const*, int, bool)","pid":0,"tid":7,"ts":3148028963383.772,"dur":3.456,"args":{"External id":48,"queued":0,"device":0,"context":1,"stream":7,"correlation":1938,"registers per thread":168,"shared memory":0,"blocks per SM":0.380952,"warps per SM":1.52381,"grid":[32,1,1],"block":[32,4,1],"est. achieved occupancy %":3,"occupancy":{"activeBlocksPerMultiprocessor":3,"limitingFactors":"REGS","blockLimitRegs":3,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":21504,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1938,"pid":0,"tid":7,"ts":3148028963383.772,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963375.775,"dur":6.788,"args":{"External id":48,"cbid":211,"correlation":1938}},{"ph":"s","id":1938,"pid":996,"tid":996,"ts":3148028963375.775,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::operator()(at::TensorIterator&)::{lambda(float, float)#1}>, unsigned int, float, 4, 4> >(at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::operator()(at::TensorIterator&)::{lambda(float, float)#1}>, unsigned int, float, 4, 4>)","pid":0,"tid":7,"ts":3148028963416.7,"dur":3.68,"args":{"External id":49,"queued":0,"device":0,"context":1,"stream":7,"correlation":1953,"registers per thread":30,"shared memory":16,"blocks per SM":0.095238,"warps per SM":1.52381,"grid":[8,1,1],"block":[32,16,1],"est. achieved occupancy %":3,"occupancy":{"activeBlocksPerMultiprocessor":3,"limitingFactors":"WARPS","blockLimitRegs":4,"blockLimitSharedMem":88,"blockLimitWarps":3,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":16384,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":1953,"pid":0,"tid":7,"ts":3148028963416.7,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963408.403,"dur":7.042,"args":{"External id":49,"cbid":211,"correlation":1953}},{"ph":"s","id":1953,"pid":996,"tid":996,"ts":3148028963408.403,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul> >(int, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963442.46,"dur":0.896,"args":{"External id":51,"queued":0,"device":0,"context":1,"stream":7,"correlation":1964,"registers per thread":36,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1964,"pid":0,"tid":7,"ts":3148028963442.46,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963434.999,"dur":6.05,"args":{"External id":51,"cbid":211,"correlation":1964}},{"ph":"s","id":1964,"pid":996,"tid":996,"ts":3148028963434.999,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::AbsFunctor<float>, std::array<char*, 2ul> >(int, at::native::AbsFunctor<float>, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963470.076,"dur":0.896,"args":{"External id":54,"queued":0,"device":0,"context":1,"stream":7,"correlation":1982,"registers per thread":36,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1982,"pid":0,"tid":7,"ts":3148028963470.076,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963462.72,"dur":5.956,"args":{"External id":54,"cbid":211,"correlation":1982}},{"ph":"s","id":1982,"pid":996,"tid":996,"ts":3148028963462.72,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul> >(int, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963493.852,"dur":0.928,"args":{"External id":56,"queued":0,"device":0,"context":1,"stream":7,"correlation":1993,"registers per thread":38,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":1993,"pid":0,"tid":7,"ts":3148028963493.852,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963486.073,"dur":6.327,"args":{"External id":56,"cbid":211,"correlation":1993}},{"ph":"s","id":1993,"pid":996,"tid":996,"ts":3148028963486.073,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4> >(at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4>)","pid":0,"tid":7,"ts":3148028963519.421,"dur":1.503,"args":{"External id":57,"queued":0,"device":0,"context":1,"stream":7,"correlation":2008,"registers per thread":36,"shared memory":16,"blocks per SM":0.011905,"warps per SM":0.011905,"grid":[1,1,1],"block":[32,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"BLOCKS","blockLimitRegs":48,"blockLimitSharedMem":88,"blockLimitWarps":48,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":1280,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2008,"pid":0,"tid":7,"ts":3148028963519.421,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963512.041,"dur":6.003,"args":{"External id":57,"cbid":211,"correlation":2008}},{"ph":"s","id":2008,"pid":996,"tid":996,"ts":3148028963512.041,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::_assert_async_cuda_kernel<bool>(bool const*, at::native::Msg)","pid":0,"tid":7,"ts":3148028963534.685,"dur":5.184,"args":{"External id":59,"queued":0,"device":0,"context":1,"stream":7,"correlation":2015,"registers per thread":24,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.000372,"grid":[1,1,1],"block":[1,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"BLOCKS","blockLimitRegs":84,"blockLimitSharedMem":100,"blockLimitWarps":48,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":768,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2015,"pid":0,"tid":7,"ts":3148028963534.685,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963527.756,"dur":5.216,"args":{"External id":59,"cbid":211,"correlation":2015}},{"ph":"s","id":2015,"pid":996,"tid":996,"ts":3148028963527.756,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul> >(int, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963557.405,"dur":1.216,"args":{"External id":60,"queued":0,"device":0,"context":1,"stream":7,"correlation":2026,"registers per thread":36,"shared memory":0,"blocks per SM":3.047619,"warps per SM":12.190476,"grid":[256,1,1],"block":[128,1,1],"est. achieved occupancy %":25,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2026,"pid":0,"tid":7,"ts":3148028963557.405,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963549.87,"dur":5.992,"args":{"External id":60,"cbid":211,"correlation":2026}},{"ph":"s","id":2026,"pid":996,"tid":996,"ts":3148028963549.87,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceGetAttribute","pid":996,"tid":996,"ts":3148028963636.962,"dur":0.548,"args":{"External id":66,"cbid":200,"correlation":2044}},{"ph":"f","id":2044,"pid":996,"tid":996,"ts":3148028963636.962,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaMemsetAsync","pid":996,"tid":996,"ts":3148028963639.028,"dur":0.26,"args":{"External id":66,"cbid":51,"correlation":2047}},{"ph":"s","id":2047,"pid":996,"tid":996,"ts":3148028963639.028,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void cutlass::Kernel2<cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4>(cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4::Params)","pid":0,"tid":7,"ts":3148028963648.029,"dur":13.984,"args":{"External id":66,"queued":0,"device":0,"context":1,"stream":7,"correlation":2048,"registers per thread":94,"shared memory":98304,"blocks per SM":0.761905,"warps per SM":3.047619,"grid":[16,4,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":0,"limitingFactors":"SMEM","blockLimitRegs":5,"blockLimitSharedMem":0,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":12288,"allocatedSharedMemPerBlock":99328},"graph id":0,"graph node id":0}},{"ph":"f","id":2048,"pid":0,"tid":7,"ts":3148028963648.029,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":996,"tid":996,"ts":3148028963639.505,"dur":7.427,"args":{"External id":66,"cbid":307,"correlation":2048}},{"ph":"s","id":2048,"pid":996,"tid":996,"ts":3148028963639.505,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void (anonymous namespace)::softmax_warp_forward<float, float, float, 11, false, false, 32>(float*, float const*, int, int, int, bool const*, int, bool)","pid":0,"tid":7,"ts":3148028963678.494,"dur":3.456,"args":{"External id":68,"queued":0,"device":0,"context":1,"stream":7,"correlation":2060,"registers per thread":168,"shared memory":0,"blocks per SM":0.380952,"warps per SM":1.52381,"grid":[32,1,1],"block":[32,4,1],"est. achieved occupancy %":3,"occupancy":{"activeBlocksPerMultiprocessor":3,"limitingFactors":"REGS","blockLimitRegs":3,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":21504,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2060,"pid":0,"tid":7,"ts":3148028963678.494,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963670.461,"dur":6.837,"args":{"External id":68,"cbid":211,"correlation":2060}},{"ph":"s","id":2060,"pid":996,"tid":996,"ts":3148028963670.461,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::operator()(at::TensorIterator&)::{lambda(float, float)#1}>, unsigned int, float, 4, 4> >(at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::operator()(at::TensorIterator&)::{lambda(float, float)#1}>, unsigned int, float, 4, 4>)","pid":0,"tid":7,"ts":3148028963744.158,"dur":3.68,"args":{"External id":69,"queued":0,"device":0,"context":1,"stream":7,"correlation":2075,"registers per thread":30,"shared memory":16,"blocks per SM":0.095238,"warps per SM":1.52381,"grid":[8,1,1],"block":[32,16,1],"est. achieved occupancy %":3,"occupancy":{"activeBlocksPerMultiprocessor":3,"limitingFactors":"WARPS","blockLimitRegs":4,"blockLimitSharedMem":88,"blockLimitWarps":3,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":16384,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2075,"pid":0,"tid":7,"ts":3148028963744.158,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963735.417,"dur":22.305,"args":{"External id":69,"cbid":211,"correlation":2075}},{"ph":"s","id":2075,"pid":996,"tid":996,"ts":3148028963735.417,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul> >(int, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963798.718,"dur":0.928,"args":{"External id":71,"queued":0,"device":0,"context":1,"stream":7,"correlation":2086,"registers per thread":36,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2086,"pid":0,"tid":7,"ts":3148028963798.718,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963791.015,"dur":6.159,"args":{"External id":71,"cbid":211,"correlation":2086}},{"ph":"s","id":2086,"pid":996,"tid":996,"ts":3148028963791.015,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::AbsFunctor<float>, std::array<char*, 2ul> >(int, at::native::AbsFunctor<float>, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963826.398,"dur":0.928,"args":{"External id":74,"queued":0,"device":0,"context":1,"stream":7,"correlation":2104,"registers per thread":36,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2104,"pid":0,"tid":7,"ts":3148028963826.398,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963819.025,"dur":5.966,"args":{"External id":74,"cbid":211,"correlation":2104}},{"ph":"s","id":2104,"pid":996,"tid":996,"ts":3148028963819.025,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul> >(int, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963849.374,"dur":0.928,"args":{"External id":76,"queued":0,"device":0,"context":1,"stream":7,"correlation":2115,"registers per thread":38,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2115,"pid":0,"tid":7,"ts":3148028963849.374,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963841.975,"dur":6.001,"args":{"External id":76,"cbid":211,"correlation":2115}},{"ph":"s","id":2115,"pid":996,"tid":996,"ts":3148028963841.975,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4> >(at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4>)","pid":0,"tid":7,"ts":3148028963875.071,"dur":1.472,"args":{"External id":77,"queued":0,"device":0,"context":1,"stream":7,"correlation":2130,"registers per thread":36,"shared memory":16,"blocks per SM":0.011905,"warps per SM":0.011905,"grid":[1,1,1],"block":[32,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"BLOCKS","blockLimitRegs":48,"blockLimitSharedMem":88,"blockLimitWarps":48,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":1280,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2130,"pid":0,"tid":7,"ts":3148028963875.071,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963867.42,"dur":6.122,"args":{"External id":77,"cbid":211,"correlation":2130}},{"ph":"s","id":2130,"pid":996,"tid":996,"ts":3148028963867.42,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::_assert_async_cuda_kernel<bool>(bool const*, at::native::Msg)","pid":0,"tid":7,"ts":3148028963889.823,"dur":5.184,"args":{"External id":79,"queued":0,"device":0,"context":1,"stream":7,"correlation":2137,"registers per thread":24,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.000372,"grid":[1,1,1],"block":[1,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"BLOCKS","blockLimitRegs":84,"blockLimitSharedMem":100,"blockLimitWarps":48,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":768,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2137,"pid":0,"tid":7,"ts":3148028963889.823,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963883.177,"dur":4.961,"args":{"External id":79,"cbid":211,"correlation":2137}},{"ph":"s","id":2137,"pid":996,"tid":996,"ts":3148028963883.177,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul> >(int, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028963911.935,"dur":1.216,"args":{"External id":80,"queued":0,"device":0,"context":1,"stream":7,"correlation":2148,"registers per thread":36,"shared memory":0,"blocks per SM":3.047619,"warps per SM":12.190476,"grid":[256,1,1],"block":[128,1,1],"est. achieved occupancy %":25,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2148,"pid":0,"tid":7,"ts":3148028963911.935,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028963904.474,"dur":5.908,"args":{"External id":80,"cbid":211,"correlation":2148}},{"ph":"s","id":2148,"pid":996,"tid":996,"ts":3148028963904.474,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceGetAttribute","pid":996,"tid":996,"ts":3148028963988.589,"dur":0.597,"args":{"External id":86,"cbid":200,"correlation":2166}},{"ph":"f","id":2166,"pid":996,"tid":996,"ts":3148028963988.589,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaMemsetAsync","pid":996,"tid":996,"ts":3148028963990.724,"dur":0.257,"args":{"External id":86,"cbid":51,"correlation":2169}},{"ph":"s","id":2169,"pid":996,"tid":996,"ts":3148028963990.724,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void cutlass::Kernel2<cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4>(cutlass_80_tensorop_s1688gemm_64x64_32x6_tn_align4::Params)","pid":0,"tid":7,"ts":3148028963999.583,"dur":13.824,"args":{"External id":86,"queued":0,"device":0,"context":1,"stream":7,"correlation":2170,"registers per thread":94,"shared memory":98304,"blocks per SM":0.761905,"warps per SM":3.047619,"grid":[16,4,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":0,"limitingFactors":"SMEM","blockLimitRegs":5,"blockLimitSharedMem":0,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":12288,"allocatedSharedMemPerBlock":99328},"graph id":0,"graph node id":0}},{"ph":"f","id":2170,"pid":0,"tid":7,"ts":3148028963999.583,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_driver","name":"cuLaunchKernel","pid":996,"tid":996,"ts":3148028963991.187,"dur":7.193,"args":{"External id":86,"cbid":307,"correlation":2170}},{"ph":"s","id":2170,"pid":996,"tid":996,"ts":3148028963991.187,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void (anonymous namespace)::softmax_warp_forward<float, float, float, 11, false, false, 32>(float*, float const*, int, int, int, bool const*, int, bool)","pid":0,"tid":7,"ts":3148028964029.247,"dur":3.456,"args":{"External id":88,"queued":0,"device":0,"context":1,"stream":7,"correlation":2182,"registers per thread":168,"shared memory":0,"blocks per SM":0.380952,"warps per SM":1.52381,"grid":[32,1,1],"block":[32,4,1],"est. achieved occupancy %":3,"occupancy":{"activeBlocksPerMultiprocessor":3,"limitingFactors":"REGS","blockLimitRegs":3,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":21504,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2182,"pid":0,"tid":7,"ts":3148028964029.247,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028964021.397,"dur":6.58,"args":{"External id":88,"cbid":211,"correlation":2182}},{"ph":"s","id":2182,"pid":996,"tid":996,"ts":3148028964021.397,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::operator()(at::TensorIterator&)::{lambda(float, float)#1}>, unsigned int, float, 4, 4> >(at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::operator()(at::TensorIterator&)::{lambda(float, float)#1}>, unsigned int, float, 4, 4>)","pid":0,"tid":7,"ts":3148028964067.936,"dur":3.68,"args":{"External id":89,"queued":0,"device":0,"context":1,"stream":7,"correlation":2197,"registers per thread":30,"shared memory":16,"blocks per SM":0.095238,"warps per SM":1.52381,"grid":[8,1,1],"block":[32,16,1],"est. achieved occupancy %":3,"occupancy":{"activeBlocksPerMultiprocessor":3,"limitingFactors":"WARPS","blockLimitRegs":4,"blockLimitSharedMem":88,"blockLimitWarps":3,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":16384,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2197,"pid":0,"tid":7,"ts":3148028964067.936,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028964059.595,"dur":7.124,"args":{"External id":89,"cbid":211,"correlation":2197}},{"ph":"s","id":2197,"pid":996,"tid":996,"ts":3148028964059.595,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul> >(int, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028964093.472,"dur":0.928,"args":{"External id":91,"queued":0,"device":0,"context":1,"stream":7,"correlation":2208,"registers per thread":36,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2208,"pid":0,"tid":7,"ts":3148028964093.472,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028964086.06,"dur":6.029,"args":{"External id":91,"cbid":211,"correlation":2208}},{"ph":"s","id":2208,"pid":996,"tid":996,"ts":3148028964086.06,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::AbsFunctor<float>, std::array<char*, 2ul> >(int, at::native::AbsFunctor<float>, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028964120.96,"dur":0.896,"args":{"External id":94,"queued":0,"device":0,"context":1,"stream":7,"correlation":2226,"registers per thread":36,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2226,"pid":0,"tid":7,"ts":3148028964120.96,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028964113.562,"dur":6.052,"args":{"External id":94,"cbid":211,"correlation":2226}},{"ph":"s","id":2226,"pid":996,"tid":996,"ts":3148028964113.562,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul> >(int, at::native::compare_scalar_kernel<float>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, float)::{lambda(float)#1}, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028964144.032,"dur":0.96,"args":{"External id":96,"queued":0,"device":0,"context":1,"stream":7,"correlation":2237,"registers per thread":38,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.047619,"grid":[1,1,1],"block":[128,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2237,"pid":0,"tid":7,"ts":3148028964144.032,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028964136.545,"dur":6,"args":{"External id":96,"cbid":211,"correlation":2237}},{"ph":"s","id":2237,"pid":996,"tid":996,"ts":3148028964136.545,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::reduce_kernel<512, 1, at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4> >(at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4>)","pid":0,"tid":7,"ts":3148028964169.824,"dur":1.504,"args":{"External id":97,"queued":0,"device":0,"context":1,"stream":7,"correlation":2252,"registers per thread":36,"shared memory":16,"blocks per SM":0.011905,"warps per SM":0.011905,"grid":[1,1,1],"block":[32,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"BLOCKS","blockLimitRegs":48,"blockLimitSharedMem":88,"blockLimitWarps":48,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":1280,"allocatedSharedMemPerBlock":1152},"graph id":0,"graph node id":0}},{"ph":"f","id":2252,"pid":0,"tid":7,"ts":3148028964169.824,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028964162.118,"dur":6.17,"args":{"External id":97,"cbid":211,"correlation":2252}},{"ph":"s","id":2252,"pid":996,"tid":996,"ts":3148028964162.118,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::_assert_async_cuda_kernel<bool>(bool const*, at::native::Msg)","pid":0,"tid":7,"ts":3148028964184.416,"dur":5.184,"args":{"External id":99,"queued":0,"device":0,"context":1,"stream":7,"correlation":2259,"registers per thread":24,"shared memory":0,"blocks per SM":0.011905,"warps per SM":0.000372,"grid":[1,1,1],"block":[1,1,1],"est. achieved occupancy %":0,"occupancy":{"activeBlocksPerMultiprocessor":24,"limitingFactors":"BLOCKS","blockLimitRegs":84,"blockLimitSharedMem":100,"blockLimitWarps":48,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":768,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2259,"pid":0,"tid":7,"ts":3148028964184.416,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028964177.806,"dur":4.958,"args":{"External id":99,"cbid":211,"correlation":2259}},{"ph":"s","id":2259,"pid":996,"tid":996,"ts":3148028964177.806,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"kernel","name":"void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul> >(int, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>)","pid":0,"tid":7,"ts":3148028964207.233,"dur":1.183,"args":{"External id":100,"queued":0,"device":0,"context":1,"stream":7,"correlation":2270,"registers per thread":36,"shared memory":0,"blocks per SM":3.047619,"warps per SM":12.190476,"grid":[256,1,1],"block":[128,1,1],"est. achieved occupancy %":25,"occupancy":{"activeBlocksPerMultiprocessor":12,"limitingFactors":"WARPS|REGS","blockLimitRegs":12,"blockLimitSharedMem":100,"blockLimitWarps":12,"blockLimitBlocks":24,"blockLimitBarriers":2147483647,"allocatedRegistersPerBlock":5120,"allocatedSharedMemPerBlock":1024},"graph id":0,"graph node id":0}},{"ph":"f","id":2270,"pid":0,"tid":7,"ts":3148028964207.233,"cat":"ac2g","name":"ac2g","bp":"e"},{"ph":"X","cat":"cuda_runtime","name":"cudaLaunchKernel","pid":996,"tid":996,"ts":3148028964199.822,"dur":5.895,"args":{"External id":100,"cbid":211,"correlation":2270}},{"ph":"s","id":2270,"pid":996,"tid":996,"ts":3148028964199.822,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"cuda_runtime","name":"cudaDeviceSynchronize","pid":996,"tid":996,"ts":3148028964268.066,"dur":4.554,"args":{"cbid":165,"correlation":2276}},{"ph":"s","id":2276,"pid":996,"tid":996,"ts":3148028964268.066,"cat":"ac2g","name":"ac2g"},{"ph":"X","cat":"gpu_user_annotation","name":"ProfilerStep#7","pid":0,"tid":7,"ts":3148028963999.582,"dur":208.835,"args":{"External id":81}},{"ph":"X","cat":"gpu_user_annotation","name":"ProfilerStep#6","pid":0,"tid":7,"ts":3148028963648.028,"dur":265.124,"args":{"External id":61}},{"ph":"X","cat":"gpu_user_annotation","name":"ProfilerStep#5","pid":0,"tid":7,"ts":3148028963354.106,"dur":204.516,"args":{"External id":41}},{"ph":"X","cat":"gpu_user_annotation","name":"ProfilerStep#4","pid":0,"tid":7,"ts":3148028962976.376,"dur":287.812,"args":{"External id":21}},{"ph":"X","cat":"gpu_user_annotation","name":"ProfilerStep#3","pid":0,"tid":7,"ts":3148028962376.885,"dur":477.669,"args":{"External id":1}},{"ph":"X","cat":"Trace","name":"PyTorch Profiler (0)","pid":"Spans","tid":"PyTorch Profiler","ts":3148028962098.617,"dur":2180.049,"args":{"Op count":0}},{"ph":"M","name":"process_sort_index","ts":3148028962098.617,"pid":"Spans","tid":0,"args":{"sort_index":536870912}},{"ph":"i","s":"g","name":"Iteration Start: PyTorch Profiler","pid":"Traces","tid":"Trace PyTorch Profiler","ts":3148028962098.617},{"ph":"i","s":"g","name":"Record Window End","pid":"","tid":"","ts":3148028964520.408}],"traceName":"assert_async_trace.json"}