mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-03-25 09:37:42 +00:00
a213ce676b
This PR introduces a Python toolkit for analyzing Clang's `-ftime-trace` build performance data. This is the foundation for our systematic effort to reduce CK and CK-Tile build times (#3575). The toolkit provides fast parsing of trace JSON files into pandas DataFrames using orjson, with specialized functions for analyzing template instantiation costs and compilation phase breakdowns. It includes a core library (`trace_analysis/`), example scripts for quick analysis, a comprehensive README with usage documentation, and an interactive Jupyter notebook demonstration. Key features include memory-efficient DataFrame schemas with optimized dtypes, recursive hierarchical phase analysis, automatic metadata extraction (source file, compilation timing), and template instantiation filtering. The design supports both standalone scripts and interactive Jupyter notebook workflows. This single-file analysis capability lays the groundwork for future multi-file analysis across thousands of compilation units, enabling data-driven optimization and build time regression detection.
81 lines
2.5 KiB
Python
81 lines
2.5 KiB
Python
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
"""
|
|
Template instantiation analysis for Clang -ftime-trace data.
|
|
|
|
This module provides specialized functions for analyzing C++ template
|
|
instantiation costs from Clang's -ftime-trace output.
|
|
"""
|
|
|
|
import pandas as pd
|
|
from .template_parser import parse_template_detail
|
|
|
|
|
|
def get_template_instantiation_events(df: pd.DataFrame) -> pd.DataFrame:
|
|
"""
|
|
Filter to template instantiation events and parse arg_detail into structured columns.
|
|
|
|
Returns events for:
|
|
- InstantiateFunction: Function template instantiations
|
|
- InstantiateClass: Class template instantiations
|
|
|
|
The returned DataFrame includes parsed columns from arg_detail:
|
|
- namespace: Top-level namespace (e.g., 'std', 'ck')
|
|
- template_name: Template name without parameters
|
|
- full_qualified_name: Full namespace::template_name
|
|
- param_count: Number of template parameters
|
|
- is_ck_type: Boolean indicating if this is a CK library type
|
|
- is_nested: Boolean indicating if contains nested templates
|
|
|
|
Args:
|
|
df: DataFrame from parse_file()
|
|
|
|
Returns:
|
|
Filtered DataFrame containing template instantiation events with parsed columns
|
|
|
|
Example:
|
|
>>> df = parse_file('trace.json')
|
|
>>> templates = get_template_instantiation_events(df)
|
|
>>> templates.sort_values('dur', ascending=False).head(10)
|
|
>>> # Filter to CK types only
|
|
>>> ck_templates = templates[templates['is_ck_type']]
|
|
>>> # Group by template name
|
|
>>> templates.groupby('template_name')['dur'].sum()
|
|
"""
|
|
# Filter to template instantiation events
|
|
filtered_df = (
|
|
df[
|
|
df["name"].isin(
|
|
[
|
|
"InstantiateClass",
|
|
"InstantiateFunction",
|
|
]
|
|
)
|
|
]
|
|
.drop(
|
|
columns=[
|
|
"arg_avg ms",
|
|
"arg_count",
|
|
"arg_name",
|
|
"cat",
|
|
"id",
|
|
"ph",
|
|
"pid",
|
|
"tid",
|
|
]
|
|
)
|
|
.reset_index(drop=True)
|
|
)
|
|
|
|
# Parse arg_detail into structured columns
|
|
parsed_data = filtered_df["arg_detail"].apply(parse_template_detail)
|
|
|
|
# Convert list of dicts to DataFrame and join with original
|
|
parsed_df = pd.DataFrame(parsed_data.tolist())
|
|
|
|
# Combine with original data
|
|
result_df = pd.concat([filtered_df, parsed_df], axis=1)
|
|
|
|
return result_df
|