tvm.runtime.profiling

Registration of profiling objects in python.

class tvm.runtime.profiling.Count(count)

A integer count of something

参数:

count (int)

class tvm.runtime.profiling.DeviceWrapper(dev)

Wraps a tvm.runtime.Device

参数:

dev (Device)

class tvm.runtime.profiling.Duration(duration)

A duration of something

参数:

duration (float)

class tvm.runtime.profiling.MetricCollector

Interface for user defined profiling metric collection.

class tvm.runtime.profiling.Percent(percent)

A Percent of something

参数:

percent (float)

class tvm.runtime.profiling.Ratio(ratio)

A Ratio of two things

参数:

ratio (float)

class tvm.runtime.profiling.Report(calls, device_metrics, configuration)

A container for information gathered during a profiling run.

Attributes

callsArray[Dict[str, Object]]

Per-call profiling metrics (function name, runtime, device, ...).

device_metricsDict[Device, Dict[str, Object]]

Per-device metrics collected over the entire run.

__init__(calls, device_metrics, configuration)

Construct a profiling report from a list of metrics and per-device metrics.

Parameters

callsSequence[Dict[str, Object]]

Per function call metrics.

device_metricsDict[str, Dict[str, Object]]

Per device metrics.

configurationDict[str, Object]

Configuration of TVM for this profiling run. Includes number of threads, executor.

参数:

• calls (Sequence[Dict[str, Object]])

• device_metrics (Dict[str, Dict[str, Object]])

• configuration (Dict[str, Object])

csv()

Convert this profiling report into CSV format.

This only includes calls and not overall metrics.

Returns

csvstr

calls in CSV format.

classmethod from_json(s)

Deserialize a report from JSON.

Parameters

sstr

Report serialize via json().

Returns

reportReport

The deserialized report.

json()

Convert this profiling report into JSON format.

Example output:

Returns

jsonstr

Formatted JSON

table(sort=True, aggregate=True, col_sums=True)

Generate a human-readable table

Parameters

sort : bool

If aggregate is true, whether to sort call frames by descending duration. If aggregate is False, whether to sort frames by order of appearancei n the program.

aggregate : bool

Whether to join multiple calls to the same op into a single line.

col_sums : bool

Whether to include the sum of each column.

Returns

table : str

A human-readable table

参数:

• calls (Sequence[Dict[str, Object]])

• device_metrics (Dict[str, Dict[str, Object]])

• configuration (Dict[str, Object])

tvm.runtime.profiling.profile_function(mod, dev, collectors, func_name=None, warmup_iters=10)

Collect performance information of a function execution. Usually used with a compiled PrimFunc.

This information can include performance counters like cache hits and FLOPs that are useful in debugging performance issues of individual PrimFuncs. Different metrics can be collected depending on which MetricCollector is used.

Example

Parameters

mod: Module

Module containing the function to profile.

dev: Device

Device to run the function on.

collectors: List[MetricCollector]

MetricCollector which will collect performance information.

func_name: Optional[str]

Name of the function in mod to profile. Defaults to the entry_name of mod.

warmup_iters: int

Number of iterations to run the function before collecting performance information. Recommended to set this larger than 0 for consistent cache effects. Defaults to 10.

Returns

prof: PackedFunc[args, Dict[str, ObjectRef]]

PackedFunc which takes the same arguments as the mod[func_name] and returns performance metrics as a Dict[str, ObjectRef] where values can be CountNode, DurationNode, PercentNode.