Class ProfilingInterpreter

intermediate_source/fx_profiling_tutorial.py:98–194

# Let's define our ``ProfilingInterpreter`` class:

class ProfilingInterpreter(Interpreter):
    def __init__(self, mod : torch.nn.Module):
        # Rather than have the user symbolically trace their model,
        # we're going to do it in the constructor. As a result, the
        # user can pass in any ``Module`` without having to worry about
        # symbolic tracing APIs
        gm = torch.fx.symbolic_trace(mod)
        super().__init__(gm)

        # We are going to store away two things here:
        #
        # 1. A list of total runtimes for ``mod``. In other words, we are
        #    storing away the time ``mod(...)`` took each time this
        #    interpreter is called.
        self.total_runtime_sec : List[float] = []
        # 2. A map from ``Node`` to a list of times (in seconds) that
        #    node took to run. This can be seen as similar to (1) but
        #    for specific sub-parts of the model.
        self.runtimes_sec : Dict[torch.fx.Node, List[float]] = {}

    ######################################################################
    # Next, let's override our first method: ``run()``. ``Interpreter``'s ``run``
    # method is the top-level entry point for execution of the model. We will
    # want to intercept this so that we can record the total runtime of the
    # model.

    def run(self, *args) -> Any:
        # Record the time we started running the model
        t_start = time.time()
        # Run the model by delegating back into Interpreter.run()
        return_val = super().run(*args)
        # Record the time we finished running the model
        t_end = time.time()
        # Store the total elapsed time this model execution took in the
        # ``ProfilingInterpreter``
        self.total_runtime_sec.append(t_end - t_start)
        return return_val

    ######################################################################
    # Now, let's override ``run_node``. ``Interpreter`` calls ``run_node`` each
    # time it executes a single node. We will intercept this so that we
    # can measure and record the time taken for each individual call in
    # the model.

    def run_node(self, n : torch.fx.Node) -> Any:
        # Record the time we started running the op
        t_start = time.time()
        # Run the op by delegating back into Interpreter.run_node()
        return_val = super().run_node(n)
        # Record the time we finished running the op
        t_end = time.time()
        # If we don't have an entry for this node in our runtimes_sec
        # data structure, add one with an empty list value.
        self.runtimes_sec.setdefault(n, [])
        # Record the total elapsed time for this single invocation
        # in the runtimes_sec data structure
        self.runtimes_sec[n].append(t_end - t_start)
        return return_val