o I&i%@sddlZddlZddlmZddlmZmZmZddlm Z ddl Z ddl m Z ddl m Z ddlmZdd lmZ ed d Zed d ZeddZeddddZddZeee dZededeedZededeeeddeje dddZed edee dZed!edGd"d#d#eZGd$d%d%eZed&e j j!fd'd(Z"ed&e j j!fd)d*Z#ed&e j j!fd+d,Z$ed&e j j!fd-d.Z%ej&Gd/d0d0Z'd&e j j!fd1d2Z(Gd3d4d4Z)dS)5N) import_module)AnyListOptional)#min_cut_rematerialization_partition)_guards) ts_compile) aot_autograd)register_debug_backendcCs|SNgmfake_tensor_inputsr r KC:\wamp64\www\opt\env\Lib\site-packages\torch/_dynamo/backends/debugging.pyeagersrcs4ddlm}fdd}||dd|}||S)Nr)make_fxcstjj|Sr torchfx Interpreterrunargsrr r runnable_gmz'pre_dispatch_eager..runnable_gmT)Z pre_dispatch)Z"torch.fx.experimental.proxy_tensorrZprint_readable)rrrrZpre_dispatch_gmr rrpre_dispatch_eagers  rcsddlmfdd}|S)Nr)SchemaCheckModecs<tjj|WdS1swYdSr rrrrr rinner,s$zeager_debug..inner)Z#torch._subclasses.schema_check_moder)rrr!r r r eager_debug%s r"ts)namecCs tj|Sr )rZjitscriptrr r r torchscript3s r&csfdd}d|_|S)Ncstj|Sr )rrrZ boxed_runrfx_gr rr:rzboxed_nop..runT)Z _boxed_call)r(example_inputsrr r'r boxed_nop9s r*) fw_compiler partition_fn aot_eager)r$Z compiler_fn)r+aot_eager_default_partitionercCs tdS)Nztorch._inductor.compile_fx)rZselect_decomp_tabler r r rVsr/Zinductor)compiler)r+Z bw_compilerZdecompositionsr,aot_eager_decomp_partitionaot_tsc@ eZdZdS)ReluCompileErrorN__name__ __module__ __qualname__r r r rr4kr4c@r3)TestingOnlyCompileErrorNr5r r r rr:or9r:rcCs$|jjD] }|jtjkrtq|Sr )graphnodestargetrrelur4rr)noder r rrelu_compile_error_TESTING_ONLYss  rAcCs4|jjD]}|jtjkrtj|_d|_q||S)N)FZReluRuntimeError)r;r<r=rr>Z_assertr recompiler?r r rrelu_runtime_error_TESTING_ONLY{s  rCcCs>|jjD]}|jtjkrtj|_|jddf|_q||S)Nrr )r;r<r=rr>addrrBr?r r r relu_accuracy_error_TESTING_ONLYs  rEcCs:|jjD] }|jdkr nq|S|D]}|jstq|S)N call_function)r;r<opZis_leafr:)rr)r@tr r r#non_leaf_compile_error_TESTING_ONLYs  rIc@seZdZUdZeejjed<e ed<e ed<ee ed<e ed<dZ e eejj ed<dZe eejed <dZe eed <d d ZdS) ExplainOutputzu This is the output of :func:`torch._dynamo.explain()` There is no reason to create this class directly. graphs graph_countgraph_break_count break_reasonsop_countN ops_per_graph out_guards compile_timesc CsXd|jd}|d|jd7}|d|jd7}|d7}t|jD])\}}|d|dd7}|d |jd7}|d 7}|jD] }|d |d7}q@q"|jdurv|d 7}t|jD]\}}|d |dd7}|D] }|d|d7}qjqZ|jdur|d7}t|jD]\}}|d|dd7}|dt |7}q|j dur|d|j d7}|S)Nz Graph Count:  zGraph Break Count: z Op Count: zBreak Reasons: z Break Reason r z: z Reason: z User Stack: z zOps per Graph: z Ops z z Out Guards: z Guard zCompile Times: ) rLrMrO enumeraterNreasonZ user_stackrPrQstrrR) selfoutputidxZ break_reason frame_summaryopsrGiguardr r r__str__s4    zExplainOutput.__str__)r6r7r8__doc__rrr GraphModule__annotations__intrrPrNoderQrZGuardrRrVr^r r r rrJs  rJcCsT||dd|jjD}|t|7}|||jjr#||j|||||fS)a This function is a utility which processes a torch.fx.GraphModule and accumulates information about its ops, graph breaks, and other details. It is intended to be used by the ExplainWithBackend class and `torch._dynamo.explain()` to provide details from Dynamo's graph capture. Parameters: gm (torch.fx.GraphModule): The GraphModule to be processed. graphs (list): A list that accumulates all the GraphModules processed. op_count (int): The total count of operations in all GraphModules processed so far. ops_per_graph (list): A list that accumulates the operations of each GraphModule. break_reasons (list): A list that accumulates the reasons for breaks in each GraphModule. Returns: tuple: A tuple containing the processed GraphModule, the updated lists of graphs, operations per graph, and break reasons, and the updated operation count. cSsg|] }|jdkr|jqS)rF)rGr=).0r@r r r sz)_explain_graph_detail..)appendr;r<lenZcompile_subgraph_reasonZ graph_break)rrKrOrPrNr[r r r_explain_graph_details    rhc@s8eZdZdZddZdejjfddZde fdd Z d S) ExplainWithBackenda This class is intended to be used as a backend for `torch.compile`. It is composable with other backends. When used in this way, it accumulates information about graph breaks, ops, and other info and provides a string representation summarizing this information. Attributes: backend (str): The name of the backend to use for optimization. graphs (list): A list of the graphs captured by TorchDynamo. op_count (int): The total number of operations in all optimized graphs. break_reasons (list): A list of graph break reasons with stack traces. Example Usage: def fn(x): x = torch.sigmoid(x) return x torch._dynamo.reset() eb = ExplainWithBackend("inductor") optimized_fn = torch.compile(fn, backend=eb) result = optimized_fn(torch.randn(5)) print(eb.output()) cCs,ddlm}|||_g|_d|_g|_dS)Nr )lookup_backendr)registryrjbackendrKrOrN)rWrlrjr r r__init__s   zExplainWithBackend.__init__rcCs2t||j|jg|j\}|_|_}|_|||Sr )rhrKrOrNrl)rWrr)_r r r__call__s zExplainWithBackend.__call__returncCs(t|j}t|j||d|j|j}|S)Nr )rgrKrJrNrO)rWrLrXr r rrXs zExplainWithBackend.outputN) r6r7r8r_rmrrr`rorJrXr r r rris ri)* dataclasses functools importlibrtypingrrrZfunctorch.compilerrrZtorch._functorch.compilersrcommonr rkr Zregister_backendrrr"r&r*r-r.partialr1r2 Exceptionr4r:rr`rArCrErI dataclassrJrhrir r r rsr                  0