2022-04-04 15:27:38 -05:00
|
|
|
# Features
|
|
|
|
|
|
|
|
|
|
```eval_rst
|
|
|
|
|
.. toctree::
|
|
|
|
|
:glob:
|
|
|
|
|
:maxdepth: 4
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
## Overview
|
|
|
|
|
|
2024-04-23 02:44:02 -04:00
|
|
|
[OmniTrace](https://github.com/ROCm/omnitrace) is designed to be highly extensible. Internally, it leverages the
|
2022-04-04 15:27:38 -05:00
|
|
|
[timemory performance analysis toolkit](https://github.com/NERSC/timemory) to
|
|
|
|
|
manage extensions, resources, data, etc.
|
|
|
|
|
|
|
|
|
|
### Data Collection Modes
|
|
|
|
|
|
|
|
|
|
- Dynamic instrumentation
|
|
|
|
|
- Runtime instrumentation
|
|
|
|
|
- Instrument executable and shared libraries at runtime
|
|
|
|
|
- Binary rewriting
|
|
|
|
|
- Generate a new executable and/or library with instrumentation built-in
|
|
|
|
|
- Statistical sampling
|
|
|
|
|
- Periodic software interrupts per-thread
|
2022-07-21 12:56:10 -05:00
|
|
|
- Process-level sampling
|
|
|
|
|
- Background thread records process-, system- and device-level metrics while the application executes
|
2023-01-24 18:53:23 -06:00
|
|
|
- Causal profiling
|
|
|
|
|
- Quantifies the potential impact of optimizations in parallel codes
|
2022-04-04 15:27:38 -05:00
|
|
|
|
|
|
|
|
### Data Analysis
|
|
|
|
|
|
2022-07-21 12:56:10 -05:00
|
|
|
- High-level summary profiles with mean/min/max/stddev statistics
|
|
|
|
|
- Low overhead, memory efficient
|
|
|
|
|
- Ideal for running at scale
|
|
|
|
|
- Comprehensive traces
|
|
|
|
|
- Every individual event/measurement
|
2023-01-24 18:53:23 -06:00
|
|
|
- Application speedup predictions resulting from potential optimizations in functions and lines of code (causal profiling)
|
2022-04-04 15:27:38 -05:00
|
|
|
|
|
|
|
|
### Parallelism API Support
|
|
|
|
|
|
2022-07-21 12:56:10 -05:00
|
|
|
- HIP
|
|
|
|
|
- HSA
|
|
|
|
|
- Pthreads
|
|
|
|
|
- MPI
|
|
|
|
|
- Kokkos-Tools (KokkosP)
|
2022-06-13 15:57:44 -05:00
|
|
|
- OpenMP-Tools (OMPT)
|
2022-04-04 15:27:38 -05:00
|
|
|
|
|
|
|
|
### GPU Metrics
|
|
|
|
|
|
2022-07-21 12:56:10 -05:00
|
|
|
- GPU hardware counters
|
2022-04-04 15:27:38 -05:00
|
|
|
- HIP API tracing
|
2022-07-21 12:56:10 -05:00
|
|
|
- HIP kernel tracing
|
|
|
|
|
- HSA API tracing
|
|
|
|
|
- HSA operation tracing
|
2022-04-04 15:27:38 -05:00
|
|
|
- System-level sampling (via rocm-smi)
|
|
|
|
|
- Memory usage
|
|
|
|
|
- Power usage
|
|
|
|
|
- Temperature
|
|
|
|
|
- Utilization
|
|
|
|
|
|
|
|
|
|
### CPU Metrics
|
|
|
|
|
|
|
|
|
|
- CPU hardware counters sampling and profiles
|
|
|
|
|
- CPU frequency sampling
|
|
|
|
|
- Various timing metrics
|
|
|
|
|
- Wall time
|
|
|
|
|
- CPU time (process and/or thread)
|
|
|
|
|
- CPU utilization (process and/or thread)
|
|
|
|
|
- User CPU time
|
|
|
|
|
- Kernel CPU time
|
|
|
|
|
- Various memory metrics
|
|
|
|
|
- High-water mark (sampling and profiles)
|
|
|
|
|
- Memory page allocation
|
|
|
|
|
- Virtual memory usage
|
|
|
|
|
- Network statistics
|
|
|
|
|
- I/O metrics
|
|
|
|
|
- ... many more
|
|
|
|
|
|
|
|
|
|
### Third-party API support
|
|
|
|
|
|
|
|
|
|
- TAU
|
|
|
|
|
- LIKWID
|
|
|
|
|
- Caliper
|
|
|
|
|
- CrayPAT
|
|
|
|
|
- VTune
|
|
|
|
|
- NVTX
|
|
|
|
|
- ROCTX
|
