U ʹj6@s8ddlZddlZddlZddlZddlZddlmZddlmZddl m Z m Z ddl Z ddl Z ddl mZddlmZddlmZddlmZddlmZdd lmZmZmZdd lmZdd lmZmZm Z ddl!m"m#Z$e%e&Z'd d Z(eddZ)eej*e dddZ+d0ddZ,ddZ-eej*e dddZ.Gdddej/Z0eej*e dddZ1eddZ2d d!Z3e j4j5Z5e5j6e5j7e5j8e5j9e5j:e5j;e5je5j?e5j@e5jAe5jBe5jCjDe5jCjEe5jFe5jGe5jHe5jIe5jJe5jKe5jLhZMeeMZMed"d#ZNe e ejOfd$d%d&ZPd'd(ZQdaRd)d*ZSd+d,ZTd1d.d/ZUdS)2N)contextmanager)partial)CallableUnion)SymInt)get_decompositions) bind_symbols) aot_function aot_modulemake_boxed_compiler)strip_overloads)default_partition draw_graph#min_cut_rematerialization_partitioncCs6|jjD] }|jtjjjkrtjjj|_q||SN) graphnodestargettorchopsaten_to_copyto recompile)fx_gnoderY/var/www/html/bwave/python/venv/lib/python3.8/site-packages/torch/_functorch/compilers.py _canonicalize!s  rc cs*tjd}z dVW5tj|XdS)NF)r_CZ_jit_set_autocast_mode)Zold_jit_autocast_flagrrr_disable_jit_autocast)s  r!)rreturnc Cstt||jjD]F}|jtjjjkrt |j dkrt |j dkrd|j krtjjj |_q|jjD]<}i}|j D]"\}}t|tjr|j}|||<q|||_ qj|j|tj|}tj|jtj|}tj|}tdd|Ds ||W5QRX|S)a Compiles the :attr:`fx_g` with Torchscript compiler. .. warning:: This API is experimental and likely to change. Args: fx_g(fx.GraphModule): The input Fx graph module to be compiled. Returns: Torch scripted model. r dtypecss|]}t|tjjVqdSr) isinstancerZ _subclassesZ FakeTensor).0trrr _szts_compile..)r!r rrrrrrrlenargskwargsritemsr$devicetypeZlintrjitscriptr Z_jit_pass_remove_mutationfreezeevalZoptimize_for_inferenceany)rinpsrZ new_kwargskvfrrr ts_compile2s8          r7TcCst|jt|||d|S)N) clear_meta)printcoder)r_namer8rrr_draw_graph_compileds r=cCsttt|dS)Nr<)r rr=r>rrrdraw_graph_compilejs r?cCs|S)z Returns the :attr:`fx_g` Fx graph module as it is. This is a no-op compiler and can be used to check accuracy. .. warning:: This API is experimental and likely to change. rrr;rrrnopps rAcs(eZdZfddZfddZZS)DebugInterpretercs"t|jf||_tj|dSr)rmodulesymbol_mappingsuperrun)selfr) __class__rrrF}szDebugInterpreter.runc sfddfddfddfdd}t|}d |jkrt|jd \}}t|\}}t|t|kstt|d t|ttt|||D].\}} t | t j sq||| fd d q|S) NcsBt|ts|St|jjj}t|j dks:t |t |S)Nr) r$rsympyexpandrexprZxreplacerDr(Z free_symbolsAssertionErrorint)nir)rGrr subst_symints  z/DebugInterpreter.run_node..subst_symintcstfdd|DS)Nc3s|]}|VqdSrr)r%rOrQrrr'szHDebugInterpreter.run_node..subst_symint_tuple..)tuple)ZnisrRrrsubst_symint_tuplesz5DebugInterpreter.run_node..subst_symint_tuplecsT|dkrPt|jD]4}||||kr||dkrdSqdS)Nrr FT)Znumelrangendimstridesize)abidxrRrrcheck_significant_stridess *z.check_significant_stridesc st|s t|j|jks6t|d|jd|j||kszt|d|d|d|||}|st|d|d|d|dS)Nz:  != z aka )callablerMr#rXrW)nvrvdescZ same_strides)r\rTrrchecks ** z(DebugInterpreter.run_node..checkvalr]csddjS)Nzoutput z where )rDr)irGrrz+DebugInterpreter.run_node..) rErun_nodemetapytreeZ tree_flattenr(rMziprUr$rTensor) rGnrbrPZn_valsZn_specZr_valsZr_specr_r`rH)r\rdrGrQrTrrgs     * zDebugInterpreter.run_node)__name__ __module__ __qualname__rFrg __classcell__rrrHrrB|s rBcCs t|jS)z Returns a (slow) interpreter over the FX graph module that also checks various debugging properties (e.g., that tracing strides matched real strides.) )rBrFr@rrr debug_nopsrqcCs(t|tj|}tj|}|Sr)r rr.r/r0r1)rr;r6rrrsimple_ts_compiles rrcCs t|tSr)r rr)r6rrrnnc_jitsrscCst|j|Sr)r9r:r@rrr print_compiles rt)fncKsBttttd}||t|tjjr2t|f|St |f|SdS)a Wrapper function over :func:`aot_function` and :func:`aot_module` to perform memory efficient fusion. It uses the :func:`min_cut_rematerialization_partition` partitioner to perform efficient recomputation. It uses NVFuser to compile the generated forward and backward graphs. .. warning:: This API is experimental and likely to change. Args: fn (Union[Callable, nn.Module]): A Python function or a ``nn.Module`` that takes one ore more arguments. Must return one or more Tensors. **kwargs: Any other overrides you want to make to the settings Returns: Returns a ``Callable`` or ``nn.Module`` that retains the eager behavior of the original :attr:`fn`, but whose forward and backward graphs have gone through recomputation optimizations, and the graphs have been compiled with nvfuser. Z fw_compilerZ bw_compilerZ partition_fnZdecompositionsN) r7rdefault_decompositionsupdater$rnnModuler r )rur*configrrrmemory_efficient_fusions  r|cCsH|dtddd|Ddddlm}||t||S)NfooaQ ############################################################## # To minimize FX graph, copy and paste the below and run it # ############################################################## import torch import torch.fx as fx from functorch.compile import minifier, check_nvfuser_subprocess, check_nvfuser_correctness_subprocess inps = cSsg|]}|j|jfqSr)shaper#)r%rdrrr sz!debug_compile..a? inps = [torch.ones(shape, dtype=dtype, device='cuda') for (shape, dtype) in inps] from foo import FxModule mod = FxModule().cuda() with torch.jit.fuser("fuser2"): # check_nvfuser_subprocess can be replaced with check_nvfuser_correctness_subprocess minifier(fx.symbolic_trace(mod), inps, check_nvfuser_subprocess) r)FxModule) to_folderr9r}rcudar7)rr3rrrr debug_compile s   rc Csg}t|d}t|}g}|D]}t|dkrD|}|t}nX|\}}}} } | tjtjtj tj tjtj tt hkrtj dd|| | d}ntj|| | d}||q"W5QRX|S)zZ Return a random input for the given inputs meta generated from _save_fx_default. rbr r)r#r,)openpickleloadr(randomZrandrrNZint32Zint64boolZuint8floatrandintappend) Zinput_data_pathinputsr6Z inputs_metarhr-inputr~rWr#r,rrr get_inputs-s.    rc sbddlm}fddfddfdd}fd d }fd d }||||||td S)aO The forward, backward, and joint computation graph will be stored in {folder_name}/{current_name}/{current_name}_forward_{graph_index}, {folder_name}/{current_name}/{current_name}_backward_{graph_index}, and {folder_name}/{current_name}/{current_name}_joint_{graph_index} respectively. The input shape of the graphs will be stored in the .input files. These files can be loaded with pickle, and is a list of format (type, shape, stride, dtype, device). In the case of type = int or float, it is just (type,). For joint graph input, it is a nested list [[],[]] where the two inner lists have the same format. If dump_example_input is True, example_inputs will be stored in .pt file. Since each function might produce multiple graphs, the graph_index is used to distinguish difference graphs r)aot_module_simplifiedcsg}t|dkrBt|dtrB||d7}||d7}|S|D]P}t|tksbt|tkrt|t|fqF|t||j||j |j fqF|S)Nrr ) r(r$rSr-rNrrr~rWr#r,)r) input_metaarg)get_input_metarrr^sz(_save_fx_default..get_input_metacs2t|jjdkr(ttjd|tdSt|}|j t j j | |}tjd}|std|ddd|dt t|tddd|dtdd|dtddr.t |ddd|dtdd|dtddS)Nrz!No nodes in graph {%s}_{%s}_{%s}./r;z.inputwbz.pt)r(rrlogloggingWARNING graph_indexcopydeepcopyZ set_codegenrfxZCodeGenrospathexistsmakedirsrrdumprsave)Z gm_to_saver) type_namegmrZisExist) current_namedump_example_input folder_namerrrgraph_saver_helperms> 22z,_save_fx_default..graph_saver_helpercs||d|S)Nforwardr)rZfw_argsrrrgraph_saver_forwards z-_save_fx_default..graph_saver_forwardcs||dtd7a|S)NZbackwardr )r)rZbw_argsrrrgraph_saver_backwards z._save_fx_default..graph_saver_backwardcs||dt||S)NZjoint)r)rZ joint_argsrrrgraph_saver_joints z+_save_fx_default..graph_saver_jointrv)Zfunctorch.compilerrw) rrrrZexample_inputsrrrrr)rrrrrr_save_fx_defaultLs  %   rFcCsdatt|||S)as Dump the forward, backward, and joint computation graph. Example Usage: save_fx_func = graph_dumper_aot(current_name, folder_name, dump_example_input = False) optimize_ctx = torchdynamo.optimize( save_fx_func ) with torch.enable_grad(): with optimize_ctx: result = forward_and_backward_pass(model, example_inputs) r)rrr)rrrrrrgraph_dumper_aots r)T)F)Vrrrrr contextlibr functoolsrtypingrrrJrrZtorch.fxrZtorch.nnryZ torch._decomprZ%torch.fx.experimental.symbolic_shapesrZ aot_autogradr r r Z compile_utilsr Z partitionersrrrZtorch.utils._pytreeutilsZ_pytreeri getLoggerrmrrr!Z GraphModuler7r=r?rAZ InterpreterrBrqrrrsrrdetachZ gelu_backwardZleaky_relu_backwardZsigmoid_backwardZthreshold_backwardZhardtanh_backwardZhardsigmoid_backwardZhardswish_backwardZ tanh_backwardZ silu_backwardZ elu_backwardZcudnn_batch_normZcudnn_batch_norm_backwardZ masked_fillZScalarrkZeluZ leaky_reluZhardtanhZ hardswishZ hardsigmoidZ conj_physicalZ is_same_sizerwrtrzr|rrrrrrrrrs          1  2   '_