derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
62 lines
2.5 KiB
Markdown
62 lines
2.5 KiB
Markdown
# Python
|
|
|
|
## Overview
|
|
|
|
This directory contains Python examples demonstrating rocprofiler-systems' Python profiling capabilities. The examples show different instrumentation approaches: the `@rocprofsys.profile()` decorator for automatic function tracing, `omni_user_region()` for manual named regions, `@noprofile` for excluding specific functions, and `rocprofsys.user.stop_trace()` for runtime tracing control. Workloads include recursive Fibonacci computation, nested loops, and optional NumPy array operations.
|
|
|
|
## Source Files
|
|
|
|
- `source.py` - Uses `@rocprofsys.profile()` decorator and `omni_user_region()` for manual region instrumentation with selective tracing control.
|
|
- `source-numpy.py` - Same as `source.py` with additional NumPy random array operations (falls back to standard `random` if NumPy is unavailable).
|
|
- `builtin.py` - Uses the built-in `@profile` decorator without rocprofiler-systems-specific integration.
|
|
- `external.py` - No profiling decorators; intended for external instrumentation via `rocprof-sys-python`.
|
|
- `noprofile.py` - Demonstrates `@noprofile` to exclude specific functions (fibonacci, inefficient loops) from profiling while tracing only the outer `run()` function.
|
|
- `fill.py` - Minimal loop-based test with `include_args = True` configuration for argument-level tracing.
|
|
|
|
## Prerequisites
|
|
|
|
- Python 3
|
|
- rocprofiler-systems Python module
|
|
- (Optional) NumPy for `source-numpy.py`
|
|
|
|
## Running
|
|
|
|
Python examples are run via `rocprof-sys-python` or `python -m rocprofsys`:
|
|
|
|
```bash
|
|
# Using rocprof-sys-python wrapper
|
|
rocprof-sys-python -- ./source.py -n 5 -v 20
|
|
|
|
# Using python module
|
|
python -m rocprofsys -- ./source.py -n 5 -v 20
|
|
|
|
# Scripts without rocprofiler-systems decorators
|
|
rocprof-sys-python -- ./external.py -n 3 -v 15
|
|
|
|
# NumPy variant
|
|
rocprof-sys-python -- ./source-numpy.py -n 3 -v 20
|
|
```
|
|
|
|
**Common arguments:**
|
|
|
|
| Flag | Description | Default |
|
|
| ------ | ------------- | --------- |
|
|
| `-n, --num-iterations` | Number of iterations | 3 |
|
|
| `-v, --value` | Starting Fibonacci value | 20 |
|
|
| `-s, --stop-profile` | Stop tracing after N iterations (0 = never) | 0 |
|
|
|
|
## Profiling with rocprofiler-systems
|
|
|
|
```bash
|
|
rocprof-sys-python -- ./source.py -n 5 -v 20
|
|
```
|
|
|
|
### Recommended Configuration
|
|
|
|
| Variable | Value | Purpose |
|
|
| ---------- | ------- | --------- |
|
|
| `ROCPROFSYS_TRACE` | `true` | Generate Perfetto trace with Python call stacks |
|
|
| `ROCPROFSYS_PROFILE` | `true` | Generate call-stack profile |
|
|
| `ROCPROFSYS_USE_SAMPLING` | `ON` | Enable statistical sampling |
|
|
| `ROCPROFSYS_SAMPLING_FREQ` | `50` | Sampling frequency (interrupts/sec) |
|