Kian Cossettini
1011 lines
68 KiB
ReStructuredText
1011 lines
68 KiB
ReStructuredText
.. meta::
|
|
:description: ROCm Systems Profiler system output documentation and reference
|
|
:keywords: rocprof-sys, rocprofiler-systems, Omnitrace, ROCm, profiler, system output, tracking, visualization, tool, Instinct, accelerator, AMD, rocpd, perfetto, timemory
|
|
|
|
****************************************************
|
|
Understanding the Systems Profiler output
|
|
****************************************************
|
|
|
|
The general output form of `ROCm Systems Profiler <https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-systems>`_ is
|
|
``<OUTPUT_PATH>[/<TIMESTAMP>]/[<PREFIX>]<DATA_NAME>[-<OUTPUT_SUFFIX>].<EXT>``.
|
|
|
|
For example, starting with the following base configuration:
|
|
|
|
.. code-block:: shell
|
|
|
|
export ROCPROFSYS_OUTPUT_PATH=rocprof-sys-example-output
|
|
export ROCPROFSYS_TIME_OUTPUT=ON
|
|
export ROCPROFSYS_USE_PID=OFF
|
|
export ROCPROFSYS_PROFILE=ON
|
|
export ROCPROFSYS_TRACE=ON
|
|
|
|
.. code-block:: shell
|
|
|
|
$ rocprof-sys-instrument -- ./foo
|
|
...
|
|
[rocprof-sys] Outputting 'rocprof-sys-example-output/perfetto-trace.proto'...
|
|
|
|
[rocprof-sys] Outputting 'rocprof-sys-example-output/wall-clock.txt'...
|
|
[rocprof-sys] Outputting 'rocprof-sys-example-output/wall-clock.json'...
|
|
|
|
If the ``ROCPROFSYS_USE_PID`` option is enabled, then running a non-MPI executable
|
|
with a PID of ``63453`` results in the following output:
|
|
|
|
.. code-block:: shell
|
|
|
|
$ export ROCPROFSYS_USE_PID=ON
|
|
$ rocprof-sys-instrument -- ./foo
|
|
...
|
|
[rocprof-sys] Outputting 'rocprof-sys-example-output/perfetto-trace-63453.proto'...
|
|
|
|
[rocprof-sys] Outputting 'rocprof-sys-example-output/wall-clock-63453.txt'...
|
|
[rocprof-sys] Outputting 'rocprof-sys-example-output/wall-clock-63453.json'...
|
|
|
|
If ``ROCPROFSYS_TIME_OUTPUT`` is enabled, then a job that started on January 31, 2022 at 12:30 PM
|
|
generates the following:
|
|
|
|
.. code-block:: shell
|
|
|
|
$ export ROCPROFSYS_TIME_OUTPUT=ON
|
|
$ rocprof-sys-instrument -- ./foo
|
|
...
|
|
[rocprof-sys] Outputting 'rocprof-sys-example-output/2022-01-31_12.30_PM/perfetto-trace-63453.proto'...
|
|
|
|
[rocprof-sys] Outputting 'rocprof-sys-example-output/2022-01-31_12.30_PM/wall-clock-63453.txt'...
|
|
[rocprof-sys] Outputting 'rocprof-sys-example-output/2022-01-31_12.30_PM/wall-clock-63453.json'...
|
|
|
|
Metadata
|
|
========================================
|
|
|
|
ROCm Systems Profiler outputs a ``metadata.json`` file. This metadata file contains
|
|
information about the settings, environment variables, output files, and info
|
|
about the system and the run, as follows:
|
|
|
|
* Hardware cache sizes
|
|
* Physical CPUs
|
|
* Hardware concurrency
|
|
* CPU model, frequency, vendor, and features
|
|
* Launch date and time
|
|
* Memory maps (for example, shared libraries)
|
|
* Output files
|
|
* Environment variables
|
|
* Configuration settings
|
|
|
|
Metadata JSON Sample
|
|
-----------------------------------------------------------------------
|
|
|
|
.. dropdown:: Sample JSON
|
|
|
|
.. code-block:: json
|
|
:linenos:
|
|
|
|
{
|
|
"rocprofiler-systems": {
|
|
"metadata": {
|
|
"info": {
|
|
"CPU_MODEL": "AMD Ryzen 5 3600 6-Core Processor",
|
|
"CPU_VENDOR": "AuthenticAMD",
|
|
"HOME": "/home/rocm-dev",
|
|
"LAUNCH_DATE": "01/15/25",
|
|
"LAUNCH_TIME": "16:49",
|
|
"PWD": "/home/rocm-dev/code/rocprofiler-systems",
|
|
"ROCPROFSYS_COMPILER_ID": "GNU",
|
|
"ROCPROFSYS_COMPILER_VERSION": "11.4.0",
|
|
"ROCPROFSYS_GIT_DESCRIBE": "",
|
|
"ROCPROFSYS_GIT_REVISION": "3213dc652728f7ed01b62bf55f6af76c43bfcbdb",
|
|
"ROCPROFSYS_LIBRARY_ARCH": "x86_64-linux-gnu",
|
|
"ROCPROFSYS_ROCM_VERSION": "6.3.1",
|
|
"ROCPROFSYS_SYSTEM_NAME": "Linux",
|
|
"ROCPROFSYS_SYSTEM_PROCESSOR": "x86_64",
|
|
"ROCPROFSYS_SYSTEM_VERSION": "6.8.0-51-generic",
|
|
"ROCPROFSYS_VERSION": "1.0.0",
|
|
"SHELL": "/usr/bin/zsh",
|
|
"TIMEMORY_API": "tim::project::timemory",
|
|
"TIMEMORY_GIT_DESCRIBE": "v3.2.0-703-gba3c6486",
|
|
"TIMEMORY_GIT_REVISION": "ba3c648677b3c6f217abe147ef3198f36239e234",
|
|
"TIMEMORY_VERSION": "4.0.0rc0",
|
|
"USER": "rocm-dev",
|
|
"CPU_FREQUENCY": 1972,
|
|
"CPU_FEATURES": [
|
|
"fpu", "vme", "de", "pse", "tsc", "msr", "pae"
|
|
// ... more features
|
|
],
|
|
"HW_CONCURRENCY": 12,
|
|
"HW_PHYSICAL_CPU": 6,
|
|
"HW_L1_CACHE_SIZE": 32768,
|
|
"HW_L2_CACHE_SIZE": 524288,
|
|
"HW_L3_CACHE_SIZE": 16777216,
|
|
"ROCPROFSYS_VERSION_MAJOR": 1,
|
|
"ROCPROFSYS_VERSION_MINOR": 0,
|
|
"ROCPROFSYS_VERSION_PATCH": 0,
|
|
"ROCPROFSYS_ROCM_VERSION_MAJOR": 6,
|
|
"ROCPROFSYS_ROCM_VERSION_MINOR": 3,
|
|
"ROCPROFSYS_ROCM_VERSION_PATCH": 1,
|
|
"memory_maps_files": [
|
|
"/opt/rocm-6.3.1/lib/libhsa-amd-aqlprofile64.so.1.0.60301",
|
|
"/opt/rocm-6.3.1/lib/libhsa-runtime64.so.1.14.60301"
|
|
// ... more files
|
|
],
|
|
"memory_maps": [
|
|
{
|
|
"cereal_class_version": 0,
|
|
"load_address": "76005b800000",
|
|
"last_address": "76005b81b000",
|
|
"permissions": "r---",
|
|
"offset": "0",
|
|
"device": "",
|
|
"inode": 0,
|
|
"pathname": "/opt/rocm/lib/libhsa-runtime64.so.1"
|
|
},
|
|
{
|
|
"load_address": "76005b81b000",
|
|
"last_address": "76005b93400d",
|
|
"permissions": "r-x-",
|
|
"offset": "1b000",
|
|
"device": "",
|
|
"inode": 0,
|
|
"pathname": "/opt/rocm/lib/libhsa-runtime64.so.1"
|
|
}
|
|
// ... more mappings
|
|
]
|
|
},
|
|
"settings": {
|
|
"cereal_class_version": 2,
|
|
"ROCPROFSYS_OUTPUT_PREFIX": {
|
|
"name": "output_prefix",
|
|
"environ": "ROCPROFSYS_OUTPUT_PREFIX",
|
|
"description": "Explicitly specify a prefix for all output files",
|
|
"count": 1,
|
|
"max_count": -1,
|
|
"cmdline": ["--rocprofiler-systems-output-prefix"],
|
|
"categories": [
|
|
"filename", "io", "librocprof-sys", "native", "rocprofsys"
|
|
],
|
|
"data_type": "string",
|
|
"initial": "parallel-overhead-binary-rewrite/",
|
|
"value": "parallel-overhead-binary-rewrite/",
|
|
"updated": "config",
|
|
"enabled": true
|
|
},
|
|
// Additional settings can be added here
|
|
"command_line": [
|
|
"/home/rocm-dev/code/rocprofiler-systems/build/ubuntu/22.04/parallel-overhead.inst",
|
|
"--", "10", "12", "1000"
|
|
],
|
|
"environment": [
|
|
// Environment variables go here
|
|
]
|
|
},
|
|
"environment": [
|
|
{
|
|
"key": "LD_LIBRARY_PATH",
|
|
"value": "/home/rocm-dev/code/rocprofiler-systems/build/ubuntu/22.04/lib:/opt/rocm/lib"
|
|
},
|
|
{
|
|
"key": "LIBRARY_PATH",
|
|
"value": ""
|
|
}
|
|
// ... more environment variables
|
|
],
|
|
"output": {
|
|
"json": [
|
|
{
|
|
"key": "wall_clock",
|
|
"value": [
|
|
"/home/rocm-dev/code/rocprofiler-systems/build/ubuntu/22.04/rocprof-sys-tests-output/parallel-overhead-binary-rewrite/wall_clock.json"
|
|
]
|
|
}
|
|
],
|
|
"protobuf": [
|
|
{
|
|
"key": "perfetto",
|
|
"value": [
|
|
"/home/rocm-dev/code/rocprofiler-systems/build/ubuntu/22.04/rocprof-sys-tests-output/parallel-overhead-binary-rewrite/perfetto-trace.proto"
|
|
]
|
|
}
|
|
],
|
|
"text": [
|
|
{
|
|
"key": "wall_clock",
|
|
"value": [
|
|
"/home/rocm-dev/code/rocprofiler-systems/build/ubuntu/22.04/rocprof-sys-tests-output/parallel-overhead-binary-rewrite/wall_clock.txt"
|
|
]
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
Configuring the ROCm Systems Profiler output
|
|
============================================
|
|
|
|
ROCm Systems Profiler includes a core set of options for controlling the format
|
|
and contents of the output files. For additional information, see the guide on
|
|
:doc:`configuring runtime options <./configuring-runtime-options>`.
|
|
|
|
Core configuration settings
|
|
-----------------------------------
|
|
|
|
.. csv-table::
|
|
:header: "Setting", "Value", "Description"
|
|
:widths: 30, 30, 100
|
|
|
|
"``ROCPROFSYS_OUTPUT_PATH``", "Any valid path", "Path to folder where output files should be placed"
|
|
"``ROCPROFSYS_OUTPUT_PREFIX``", "String", "Useful for multiple runs with different arguments. See the next section on output prefix keys."
|
|
"``ROCPROFSYS_OUTPUT_FILE``", "Any valid filepath", "Specific location for the Perfetto output file"
|
|
"``ROCPROFSYS_TIME_OUTPUT``", "Boolean", "Place all output in a timestamped folder, timestamp format controlled via ``ROCPROFSYS_TIME_FORMAT``"
|
|
"``ROCPROFSYS_TIME_FORMAT``", "String", "See ``strftime`` man pages for valid identifiers"
|
|
"``ROCPROFSYS_USE_PID``", "Boolean", "Append either the PID or the MPI rank to all output files (before the extension)"
|
|
|
|
Output prefix keys
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
|
|
Output prefix keys have many uses but are most helpful when dealing with multiple
|
|
profiling runs or large MPI jobs.
|
|
They are included in ROCm Systems Profiler because they were introduced into Timemory
|
|
for `compile-time-perf <https://github.com/jrmadsen/compile-time-perf>`_.
|
|
They are needed to create different output files for a generic wrapper around
|
|
compilation commands while still
|
|
overwriting the output from the last time a file was compiled.
|
|
|
|
When doing scaling studies and specifying options via the command line,
|
|
the recommended process is to
|
|
use a common ``ROCPROFSYS_OUTPUT_PATH``, disable ``ROCPROFSYS_TIME_OUTPUT``,
|
|
set ``ROCPROFSYS_OUTPUT_PREFIX="%argt%-"``, and let ROCm Systems Profiler cleanly organize the output.
|
|
|
|
.. csv-table::
|
|
:header: "String", "Encoding"
|
|
:widths: 20, 120
|
|
|
|
"``%argv%``", "Entire command-line condensed into a single string"
|
|
"``%argt%``", "Similar to ``%argv%`` except basename of first command line argument"
|
|
"``%args%``", "All command line arguments condensed into a single string"
|
|
"``%tag%``", "Basename of first command line argument"
|
|
"``%arg<N>%``", "Command line argument at position ``<N>`` (zero indexed), e.g. ``%arg0%`` for first argument"
|
|
"``%argv_hash%``", "MD5 sum of ``%argv%``"
|
|
"``%argt_hash%``", "MD5 sum if ``%argt%``"
|
|
"``%args_hash%``", "MD5 sum of ``%args%``"
|
|
"``%tag_hash%``", "MD5 sum of ``%tag%``"
|
|
"``%arg<N>_hash%``", "MD5 sum of ``%arg<N>%``"
|
|
"``%pid%``", "Process identifier (i.e. ``getpid()``)"
|
|
"``%ppid%``", "Parent process identifier (i.e. ``getppid()``)"
|
|
"``%pgid%``", "Process group identifier (i.e. ``getpgid(getpid())``)"
|
|
"``%psid%``", "Process session identifier (i.e. ``getsid(getpid())``)"
|
|
"``%psize%``", "Number of sibling process (from reading ``/proc/<PPID>/tasks/<PPID>/children``)"
|
|
"``%job%``", "Value of ``SLURM_JOB_ID`` environment variable if exists, else ``0``"
|
|
"``%rank%``", "Value of ``SLURM_PROCID`` environment variable if exists, else ``MPI_Comm_rank`` (or ``0`` non-mpi)"
|
|
"``%size%``", "``MPI_Comm_size`` or ``1`` if non-mpi"
|
|
"``%nid%``", "``%rank%`` if possible, otherwise ``%pid%``"
|
|
"``%launch_time%``", "Launch date and time (uses ``ROCPROFSYS_TIME_FORMAT``)"
|
|
"``%env{NAME}%``", "Value of environment variable ``NAME`` (i.e. ``getenv(NAME)``)"
|
|
"``%cfg{NAME}%``", "Value of configuration variable ``NAME`` (e.g. ``%cfg{ROCPROFSYS_SAMPLING_FREQ}%`` would resolve to sampling frequency)"
|
|
"``$env{NAME}``", "Alternative syntax to ``%env{NAME}%``"
|
|
"``$cfg{NAME}``", "Alternative syntax to ``%cfg{NAME}%``"
|
|
"``%m``", "Shorthand for ``%argt_hash%``"
|
|
"``%p``", "Shorthand for ``%pid%``"
|
|
"``%j``", "Shorthand for ``%job%``"
|
|
"``%r``", "Shorthand for ``%rank%``"
|
|
"``%s``", "Shorthand for ``%size%``"
|
|
|
|
.. note::
|
|
|
|
In any output prefix key which contains a ``/`` character, the ``/`` characters
|
|
are replaced with ``_`` and any leading underscores are stripped. For example,
|
|
an ``%arg0%`` of ``/usr/bin/foo`` translates to ``usr_bin_foo``. Additionally, any ``%arg<N>%`` keys which
|
|
do not have a command line argument at position ``<N>`` are ignored.
|
|
|
|
.. _rocprof_sys_rocpd_output:
|
|
|
|
ROCm Profiling Data (rocpd) output
|
|
=========================================
|
|
|
|
Use the ``ROCPROFSYS_USE_ROCPD`` setting to trigger the ROCm Systems Profiler to output a
|
|
SQLite3 database. The ROCm Profiling Data (or ``rocpd``) database will soon be the default output
|
|
format. To output in ``rocpd`` format, ROCProfiler-SDK version 1.0.0 or later is required (introduced in ROCm 7.0.0).
|
|
|
|
Features
|
|
--------------
|
|
|
|
The features of ``rocpd`` output format are:
|
|
|
|
* **Comprehensive Data Model**: Consolidates all profiling artifacts including execution traces, performance counters, hardware metrics, and contextual metadata within a single SQLite3 database file (`.db` extension).
|
|
|
|
* **Standards-Compliant Access**: Supports querying through industry-standard SQL interfaces including command-line tools (``sqlite3`` CLI), programming language bindings (Python ``sqlite3`` module, C/C++ SQLite API), and database management applications.
|
|
|
|
* **Advanced Analytics Integration**: Facilitates sophisticated post-processing workflows through custom analytical scripts, automated reporting systems, and integration with third-party visualization and analysis frameworks that provide SQLite3 connectivity.
|
|
|
|
Generating rocpd output
|
|
-------------------------
|
|
|
|
To generate profiling data in the rocpd format, add ``ROCPROFSYS_USE_ROCPD=ON`` to your profiling configuration.
|
|
|
|
.. code-block:: shell
|
|
|
|
export ROCPROFSYS_USE_ROCPD=ON
|
|
export ROCPROFSYS_USE_TRACE=OFF # disabling default Perfetto output
|
|
rocprof-sys-sample -- ./your_application
|
|
|
|
See :doc:`configuring runtime options <./configuring-runtime-options>` for additional
|
|
details on setting up the profiling configuration options.
|
|
|
|
Converting rocpd to alternative formats
|
|
------------------------------------------
|
|
|
|
ROCm provides a Python module to convert the ``rocpd`` database to alternative
|
|
output formats for specialized analysis and visualization workflows. For example,
|
|
(Open Trace Format 2) OTF2, Perfetto Protocol Buffers (PFTrace), and
|
|
Comma-Separated Values (CSV) tables.
|
|
|
|
See :doc:`Using rocpd output format <rocprofiler-sdk:how-to/using-rocpd-output-format>` in ROCProfiler-SDK documentation,
|
|
for additional information on these conversion tools.
|
|
|
|
Native Perfetto output
|
|
========================================
|
|
|
|
Use the ``ROCPROFSYS_OUTPUT_FILE`` to specify a specific location. If this is an
|
|
absolute path, then all ``ROCPROFSYS_OUTPUT_PATH`` and similar
|
|
settings are ignored. Visit `ui.perfetto.dev <https://ui.perfetto.dev>`_ and open
|
|
this file.
|
|
|
|
.. important::
|
|
If you are using a version of ROCm prior to ROCm 6.3.1 and are experiencing problems viewing your
|
|
trace in the latest version of [Perfetto](http://ui.perfetto.dev), then try using
|
|
[Perfetto UI v46.0](https://ui.perfetto.dev/v46.0-35b3d9845/#!/).
|
|
|
|
**Figure 1:** Visualization of a performance graph in Perfetto
|
|
|
|
.. image:: ../data/rocprof-sys-perfetto.png
|
|
:alt: Visualization of a performance graph in Perfetto
|
|
:width: 800
|
|
|
|
**Figure 2:** Visualization of ROCm data in Perfetto
|
|
|
|
.. image:: ../data/rocprof-sys-rocm.png
|
|
:alt: Visualization of ROCm data in Perfetto
|
|
:width: 800
|
|
|
|
**Figure 3:** Visualization of ROCm flow data in Perfetto
|
|
|
|
.. image:: ../data/rocprof-sys-rocm-flow.png
|
|
:alt: Visualization of ROCm flow data in Perfetto
|
|
:width: 800
|
|
|
|
**Figure 4:** Visualization of ROCm API calls in Perfetto
|
|
|
|
.. image:: ../data/rocprof-sys-user-api.png
|
|
:alt: Visualization of ROCm API calls in Perfetto
|
|
:width: 800
|
|
|
|
**Figure 5:** Visualization of ROCm GPU metrics in Perfetto
|
|
|
|
.. image:: ../data/rocprof-sys-gpu-metrics.png
|
|
:alt: Visualization of ROCm GPU metrics in Perfetto
|
|
:width: 800
|
|
|
|
Timemory output
|
|
========================================
|
|
|
|
Use ``rocprof-sys-avail --components --filename`` to view the base filename for each component, as follows
|
|
|
|
.. code-block:: shell
|
|
|
|
$ rocprof-sys-avail wall_clock -C -f
|
|
|---------------------------------|---------------|------------------------|
|
|
| COMPONENT | AVAILABLE | FILENAME |
|
|
|---------------------------------|---------------|------------------------|
|
|
| wall_clock | true | wall_clock |
|
|
| sampling_wall_clock | true | sampling_wall_clock |
|
|
|---------------------------------|---------------|------------------------|
|
|
|
|
The ``ROCPROFSYS_COLLAPSE_THREADS`` and ``ROCPROFSYS_COLLAPSE_PROCESSES`` settings are
|
|
only valid when full `MPI support is enabled <../install/install.html#mpi-support-within-rocprof-sys>`_.
|
|
When they are set, Timemory combines the per-thread and per-rank data (respectively) of
|
|
identical call stacks.
|
|
|
|
The ``ROCPROFSYS_FLAT_PROFILE`` setting removes all call stack hierarchy.
|
|
Using ``ROCPROFSYS_FLAT_PROFILE=ON`` in combination
|
|
with ``ROCPROFSYS_COLLAPSE_THREADS=ON`` is a useful configuration for identifying
|
|
min/max measurements regardless of the calling context.
|
|
The ``ROCPROFSYS_TIMELINE_PROFILE`` setting (with ``ROCPROFSYS_FLAT_PROFILE=OFF``) effectively
|
|
generates similar data to that found
|
|
in Perfetto. Enabling timeline and flat profiling effectively generates
|
|
similar data to ``strace``. However, while Timemory generally
|
|
requires significantly less memory than Perfetto, this is not the case in timeline
|
|
mode, so use this setting with caution.
|
|
|
|
Timemory text output
|
|
-----------------------------------------------------------------------
|
|
|
|
Timemory text output files are meant for human consumption (while JSON formats are for analysis),
|
|
so some fields such as the ``LABEL`` might be truncated for readability.
|
|
The truncation settings be changed through the ``ROCPROFSYS_MAX_WIDTH`` setting.
|
|
|
|
.. note::
|
|
|
|
The generation of text output is configurable via ``ROCPROFSYS_TEXT_OUTPUT``.
|
|
|
|
.. _text-output-example-label:
|
|
|
|
Timemory text output example
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
|
|
In the following example, the ``N`` field in ``|N>>>`` is the thread ID. If MPI support is enabled,
|
|
this becomes ``|M|N>>>`` where ``M`` is the rank.
|
|
If ``ROCPROFSYS_COLLAPSE_THREADS=ON`` and ``ROCPROFSYS_COLLAPSE_PROCESSES=ON`` are configured,
|
|
neither the ``M`` nor the ``N`` are present unless the
|
|
component explicitly sets type traits. Type traits specify that the data is only
|
|
relevant per-thread or per-process, such as the ``thread_cpu_clock`` clock component.
|
|
|
|
.. code-block:: shell
|
|
|
|
|--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
| REAL-CLOCK TIMER (I.E. WALL-CLOCK TIMER) |
|
|
|--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
| LABEL | COUNT | DEPTH | METRIC | UNITS | SUM | MEAN | MIN | MAX | VAR | STDDEV | % SELF |
|
|
|-------------------------------------------------|--------|--------|------------|--------|----------|----------|----------|----------|----------|----------|--------|
|
|
| |0>>> openmp-cg.inst | 1 | 0 | wall_clock | sec | 6.100107 | 6.100107 | 6.100107 | 6.100107 | 0.000000 | 0.000000 | 16.7 |
|
|
| |0>>> |_omp_parallel | 1 | 1 | wall_clock | sec | 5.079807 | 5.079807 | 5.079807 | 5.079807 | 0.000000 | 0.000000 | 0.0 |
|
|
| |0>>> |_pthread_create | 2 | 2 | wall_clock | sec | 0.004790 | 0.002395 | 0.002356 | 0.002434 | 0.000000 | 0.000054 | 0.0 |
|
|
| |2>>> |_start_thread | 1 | 3 | wall_clock | sec | 5.077748 | 5.077748 | 5.077748 | 5.077748 | 0.000000 | 0.000000 | 0.0 |
|
|
| |2>>> |_omp_thread_begin | 1 | 4 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_omp_implicit_task | 1 | 4 | wall_clock | sec | 5.077417 | 5.077417 | 5.077417 | 5.077417 | 0.000000 | 0.000000 | 0.0 |
|
|
| |2>>> |_main.omp_outlined | 1 | 5 | wall_clock | sec | 5.074730 | 5.074730 | 5.074730 | 5.074730 | 0.000000 | 0.000000 | 0.0 |
|
|
| |2>>> |_omp_work | 10 | 6 | wall_clock | sec | 0.000453 | 0.000045 | 0.000004 | 0.000213 | 0.000000 | 0.000064 | 41.6 |
|
|
| |2>>> |_omp_dispatch | 6 | 7 | wall_clock | sec | 0.000003 | 0.000001 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#0] | 1 | 7 | wall_clock | sec | 0.000050 | 0.000050 | 0.000050 | 0.000050 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#12] | 1 | 7 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#1] | 1 | 7 | wall_clock | sec | 0.000183 | 0.000183 | 0.000183 | 0.000183 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#2] | 1 | 7 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#3] | 1 | 7 | wall_clock | sec | 0.000014 | 0.000014 | 0.000014 | 0.000014 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#6] | 1 | 7 | wall_clock | sec | 0.000005 | 0.000005 | 0.000005 | 0.000005 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#11] | 1 | 7 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#7] | 1 | 7 | wall_clock | sec | 0.000005 | 0.000005 | 0.000005 | 0.000005 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#9] | 1 | 7 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_omp_sync_region | 8 | 6 | wall_clock | sec | 0.000212 | 0.000027 | 0.000023 | 0.000046 | 0.000000 | 0.000008 | 55.7 |
|
|
| |2>>> |_omp_sync_region_wait | 8 | 7 | wall_clock | sec | 0.000094 | 0.000012 | 0.000010 | 0.000024 | 0.000000 | 0.000005 | 100.0 |
|
|
| |2>>> |_conj_grad | 1 | 6 | wall_clock | sec | 0.101549 | 0.101549 | 0.101549 | 0.101549 | 0.000000 | 0.000000 | 0.2 |
|
|
| |2>>> |_omp_work | 6 | 7 | wall_clock | sec | 0.003838 | 0.000640 | 0.000004 | 0.003671 | 0.000002 | 0.001485 | 3.6 |
|
|
| |2>>> |_omp_dispatch | 4 | 8 | wall_clock | sec | 0.000002 | 0.000001 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#0] | 1 | 8 | wall_clock | sec | 0.000018 | 0.000018 | 0.000018 | 0.000018 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#1] | 1 | 8 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#9] | 1 | 8 | wall_clock | sec | 0.000002 | 0.000002 | 0.000002 | 0.000002 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#8] | 1 | 8 | wall_clock | sec | 0.000013 | 0.000013 | 0.000013 | 0.000013 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#3] | 1 | 8 | wall_clock | sec | 0.003641 | 0.003641 | 0.003641 | 0.003641 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#6] | 1 | 8 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#5] | 1 | 8 | wall_clock | sec | 0.000023 | 0.000023 | 0.000023 | 0.000023 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_omp_sync_region | 6 | 7 | wall_clock | sec | 0.000386 | 0.000064 | 0.000024 | 0.000152 | 0.000000 | 0.000053 | 29.9 |
|
|
| |2>>> |_omp_sync_region_wait | 6 | 8 | wall_clock | sec | 0.000271 | 0.000045 | 0.000010 | 0.000131 | 0.000000 | 0.000052 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#2] | 1 | 7 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#7] | 1 | 7 | wall_clock | sec | 0.097136 | 0.097136 | 0.097136 | 0.097136 | 0.000000 | 0.000000 | 2.9 |
|
|
| |2>>> |_omp_work | 125 | 8 | wall_clock | sec | 0.090726 | 0.000726 | 0.000004 | 0.004120 | 0.000002 | 0.001406 | 99.9 |
|
|
| |2>>> |_omp_dispatch | 100 | 9 | wall_clock | sec | 0.000047 | 0.000000 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_omp_sync_region | 125 | 8 | wall_clock | sec | 0.003605 | 0.000029 | 0.000023 | 0.000124 | 0.000000 | 0.000013 | 51.3 |
|
|
| |2>>> |_omp_sync_region_wait | 125 | 9 | wall_clock | sec | 0.001755 | 0.000014 | 0.000009 | 0.000094 | 0.000000 | 0.000011 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#4] | 1 | 7 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#5] | 1 | 6 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#4] | 1 | 6 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_main.omp_outlined [loop#8] | 1 | 6 | wall_clock | sec | 4.972281 | 4.972281 | 4.972281 | 4.972281 | 0.000000 | 0.000000 | 0.1 |
|
|
| |2>>> |_conj_grad | 50 | 7 | wall_clock | sec | 4.958576 | 0.099172 | 0.098079 | 0.101557 | 0.000000 | 0.000660 | 0.2 |
|
|
| |2>>> |_omp_work | 300 | 8 | wall_clock | sec | 0.182672 | 0.000609 | 0.000004 | 0.003721 | 0.000002 | 0.001290 | 3.3 |
|
|
| |2>>> |_omp_dispatch | 200 | 9 | wall_clock | sec | 0.000092 | 0.000000 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#0] | 50 | 9 | wall_clock | sec | 0.001560 | 0.000031 | 0.000026 | 0.000037 | 0.000000 | 0.000002 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#1] | 50 | 9 | wall_clock | sec | 0.000053 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#9] | 50 | 9 | wall_clock | sec | 0.000067 | 0.000001 | 0.000001 | 0.000002 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#8] | 50 | 9 | wall_clock | sec | 0.000630 | 0.000013 | 0.000012 | 0.000016 | 0.000000 | 0.000001 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#3] | 50 | 9 | wall_clock | sec | 0.172947 | 0.003459 | 0.003372 | 0.003690 | 0.000000 | 0.000068 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#6] | 50 | 9 | wall_clock | sec | 0.000070 | 0.000001 | 0.000001 | 0.000002 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#5] | 50 | 9 | wall_clock | sec | 0.001137 | 0.000023 | 0.000017 | 0.000036 | 0.000000 | 0.000002 | 100.0 |
|
|
| |2>>> |_omp_sync_region | 300 | 8 | wall_clock | sec | 0.008423 | 0.000028 | 0.000023 | 0.000068 | 0.000000 | 0.000009 | 54.2 |
|
|
| |2>>> |_omp_sync_region_wait | 300 | 9 | wall_clock | sec | 0.003860 | 0.000013 | 0.000009 | 0.000053 | 0.000000 | 0.000007 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#2] | 50 | 8 | wall_clock | sec | 0.000057 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#7] | 50 | 8 | wall_clock | sec | 4.759600 | 0.095192 | 0.094130 | 0.097386 | 0.000000 | 0.000630 | 2.9 |
|
|
| |2>>> |_omp_work | 6250 | 9 | wall_clock | sec | 4.442086 | 0.000711 | 0.000004 | 0.003788 | 0.000002 | 0.001370 | 99.9 |
|
|
| |2>>> |_omp_dispatch | 5000 | 10 | wall_clock | sec | 0.002305 | 0.000000 | 0.000000 | 0.000005 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_omp_sync_region | 6250 | 9 | wall_clock | sec | 0.177916 | 0.000028 | 0.000018 | 0.000262 | 0.000000 | 0.000010 | 53.8 |
|
|
| |2>>> |_omp_sync_region_wait | 6250 | 10 | wall_clock | sec | 0.082161 | 0.000013 | 0.000004 | 0.000248 | 0.000000 | 0.000008 | 100.0 |
|
|
| |2>>> |_conj_grad [loop#4] | 50 | 8 | wall_clock | sec | 0.000058 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_omp_work | 200 | 7 | wall_clock | sec | 0.002753 | 0.000014 | 0.000004 | 0.000032 | 0.000000 | 0.000010 | 98.3 |
|
|
| |2>>> |_omp_dispatch | 100 | 8 | wall_clock | sec | 0.000046 | 0.000000 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_omp_sync_region | 250 | 7 | wall_clock | sec | 0.006061 | 0.000024 | 0.000023 | 0.000042 | 0.000000 | 0.000003 | 60.0 |
|
|
| |2>>> |_omp_sync_region_wait | 250 | 8 | wall_clock | sec | 0.002423 | 0.000010 | 0.000009 | 0.000014 | 0.000000 | 0.000000 | 100.0 |
|
|
| |2>>> |_omp_sync_region | 1 | 5 | wall_clock | sec | 0.002650 | 0.002650 | 0.002650 | 0.002650 | 0.000000 | 0.000000 | 0.3 |
|
|
| |2>>> |_omp_sync_region_wait | 1 | 6 | wall_clock | sec | 0.002641 | 0.002641 | 0.002641 | 0.002641 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_start_thread | 1 | 3 | wall_clock | sec | 5.080178 | 5.080178 | 5.080178 | 5.080178 | 0.000000 | 0.000000 | 0.1 |
|
|
| |1>>> |_omp_thread_begin | 1 | 4 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_omp_implicit_task | 1 | 4 | wall_clock | sec | 5.077434 | 5.077434 | 5.077434 | 5.077434 | 0.000000 | 0.000000 | 0.0 |
|
|
| |1>>> |_main.omp_outlined | 1 | 5 | wall_clock | sec | 5.074749 | 5.074749 | 5.074749 | 5.074749 | 0.000000 | 0.000000 | 0.0 |
|
|
| |1>>> |_omp_work | 10 | 6 | wall_clock | sec | 0.000252 | 0.000025 | 0.000002 | 0.000124 | 0.000000 | 0.000038 | 33.4 |
|
|
| |1>>> |_omp_dispatch | 6 | 7 | wall_clock | sec | 0.000001 | 0.000000 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#0] | 1 | 7 | wall_clock | sec | 0.000035 | 0.000035 | 0.000035 | 0.000035 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#12] | 1 | 7 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#1] | 1 | 7 | wall_clock | sec | 0.000113 | 0.000113 | 0.000113 | 0.000113 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#2] | 1 | 7 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#3] | 1 | 7 | wall_clock | sec | 0.000010 | 0.000010 | 0.000010 | 0.000010 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#6] | 1 | 7 | wall_clock | sec | 0.000003 | 0.000003 | 0.000003 | 0.000003 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#11] | 1 | 7 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#7] | 1 | 7 | wall_clock | sec | 0.000003 | 0.000003 | 0.000003 | 0.000003 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#9] | 1 | 7 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_omp_sync_region | 8 | 6 | wall_clock | sec | 0.000582 | 0.000073 | 0.000028 | 0.000274 | 0.000000 | 0.000082 | 9.5 |
|
|
| |1>>> |_omp_sync_region_wait | 8 | 7 | wall_clock | sec | 0.000526 | 0.000066 | 0.000022 | 0.000260 | 0.000000 | 0.000080 | 100.0 |
|
|
| |1>>> |_conj_grad | 1 | 6 | wall_clock | sec | 0.101518 | 0.101518 | 0.101518 | 0.101518 | 0.000000 | 0.000000 | 0.1 |
|
|
| |1>>> |_omp_work | 6 | 7 | wall_clock | sec | 0.002260 | 0.000377 | 0.000002 | 0.002143 | 0.000001 | 0.000865 | 3.1 |
|
|
| |1>>> |_omp_dispatch | 4 | 8 | wall_clock | sec | 0.000001 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#0] | 1 | 8 | wall_clock | sec | 0.000039 | 0.000039 | 0.000039 | 0.000039 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#1] | 1 | 8 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#9] | 1 | 8 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#8] | 1 | 8 | wall_clock | sec | 0.000006 | 0.000006 | 0.000006 | 0.000006 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#3] | 1 | 8 | wall_clock | sec | 0.002126 | 0.002126 | 0.002126 | 0.002126 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#6] | 1 | 8 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#5] | 1 | 8 | wall_clock | sec | 0.000014 | 0.000014 | 0.000014 | 0.000014 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_omp_sync_region | 6 | 7 | wall_clock | sec | 0.001972 | 0.000329 | 0.000017 | 0.001609 | 0.000000 | 0.000633 | 3.0 |
|
|
| |1>>> |_omp_sync_region_wait | 6 | 8 | wall_clock | sec | 0.001913 | 0.000319 | 0.000009 | 0.001602 | 0.000000 | 0.000634 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#2] | 1 | 7 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#7] | 1 | 7 | wall_clock | sec | 0.097191 | 0.097191 | 0.097191 | 0.097191 | 0.000000 | 0.000000 | 1.5 |
|
|
| |1>>> |_omp_work | 125 | 8 | wall_clock | sec | 0.054511 | 0.000436 | 0.000002 | 0.002273 | 0.000001 | 0.000849 | 100.0 |
|
|
| |1>>> |_omp_dispatch | 100 | 9 | wall_clock | sec | 0.000019 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_omp_sync_region | 125 | 8 | wall_clock | sec | 0.041210 | 0.000330 | 0.000011 | 0.002052 | 0.000000 | 0.000584 | 2.6 |
|
|
| |1>>> |_omp_sync_region_wait | 125 | 9 | wall_clock | sec | 0.040135 | 0.000321 | 0.000005 | 0.002033 | 0.000000 | 0.000580 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#4] | 1 | 7 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#5] | 1 | 6 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#4] | 1 | 6 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_main.omp_outlined [loop#8] | 1 | 6 | wall_clock | sec | 4.972283 | 4.972283 | 4.972283 | 4.972283 | 0.000000 | 0.000000 | 0.0 |
|
|
| |1>>> |_conj_grad | 50 | 7 | wall_clock | sec | 4.958649 | 0.099173 | 0.098081 | 0.101558 | 0.000000 | 0.000661 | 0.1 |
|
|
| |1>>> |_omp_work | 300 | 8 | wall_clock | sec | 0.110605 | 0.000369 | 0.000002 | 0.002215 | 0.000001 | 0.000786 | 2.7 |
|
|
| |1>>> |_omp_dispatch | 200 | 9 | wall_clock | sec | 0.000038 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#0] | 50 | 9 | wall_clock | sec | 0.001071 | 0.000021 | 0.000020 | 0.000023 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#1] | 50 | 9 | wall_clock | sec | 0.000022 | 0.000000 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#9] | 50 | 9 | wall_clock | sec | 0.000025 | 0.000001 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#8] | 50 | 9 | wall_clock | sec | 0.000326 | 0.000007 | 0.000006 | 0.000007 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#3] | 50 | 9 | wall_clock | sec | 0.105352 | 0.002107 | 0.002074 | 0.002198 | 0.000000 | 0.000021 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#6] | 50 | 9 | wall_clock | sec | 0.000039 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#5] | 50 | 9 | wall_clock | sec | 0.000719 | 0.000014 | 0.000013 | 0.000017 | 0.000000 | 0.000001 | 100.0 |
|
|
| |1>>> |_omp_sync_region | 300 | 8 | wall_clock | sec | 0.084256 | 0.000281 | 0.000011 | 0.001618 | 0.000000 | 0.000527 | 3.0 |
|
|
| |1>>> |_omp_sync_region_wait | 300 | 9 | wall_clock | sec | 0.081757 | 0.000273 | 0.000005 | 0.001589 | 0.000000 | 0.000523 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#2] | 50 | 8 | wall_clock | sec | 0.000026 | 0.000001 | 0.000000 | 0.000002 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#7] | 50 | 8 | wall_clock | sec | 4.759698 | 0.095194 | 0.094132 | 0.097391 | 0.000000 | 0.000630 | 1.6 |
|
|
| |1>>> |_omp_work | 6250 | 9 | wall_clock | sec | 2.699342 | 0.000432 | 0.000002 | 0.002232 | 0.000001 | 0.000837 | 100.0 |
|
|
| |1>>> |_omp_dispatch | 5000 | 10 | wall_clock | sec | 0.000934 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_omp_sync_region | 6250 | 9 | wall_clock | sec | 1.983999 | 0.000317 | 0.000010 | 0.001662 | 0.000000 | 0.000554 | 2.7 |
|
|
| |1>>> |_omp_sync_region_wait | 6250 | 10 | wall_clock | sec | 1.929991 | 0.000309 | 0.000004 | 0.001648 | 0.000000 | 0.000550 | 100.0 |
|
|
| |1>>> |_conj_grad [loop#4] | 50 | 8 | wall_clock | sec | 0.000026 | 0.000001 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_omp_work | 200 | 7 | wall_clock | sec | 0.001422 | 0.000007 | 0.000002 | 0.000017 | 0.000000 | 0.000006 | 98.7 |
|
|
| |1>>> |_omp_dispatch | 100 | 8 | wall_clock | sec | 0.000018 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |1>>> |_omp_sync_region | 250 | 7 | wall_clock | sec | 0.010015 | 0.000040 | 0.000020 | 0.000055 | 0.000000 | 0.000007 | 16.9 |
|
|
| |1>>> |_omp_sync_region_wait | 250 | 8 | wall_clock | sec | 0.008318 | 0.000033 | 0.000013 | 0.000049 | 0.000000 | 0.000007 | 100.0 |
|
|
| |1>>> |_omp_sync_region | 1 | 5 | wall_clock | sec | 0.002662 | 0.002662 | 0.002662 | 0.002662 | 0.000000 | 0.000000 | 0.2 |
|
|
| |1>>> |_omp_sync_region_wait | 1 | 6 | wall_clock | sec | 0.002657 | 0.002657 | 0.002657 | 0.002657 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_omp_implicit_task | 1 | 2 | wall_clock | sec | 5.074911 | 5.074911 | 5.074911 | 5.074911 | 0.000000 | 0.000000 | 0.0 |
|
|
| |0>>> |_main.omp_outlined | 1 | 3 | wall_clock | sec | 5.074855 | 5.074855 | 5.074855 | 5.074855 | 0.000000 | 0.000000 | 0.0 |
|
|
| |0>>> |_omp_work | 10 | 4 | wall_clock | sec | 0.000249 | 0.000025 | 0.000002 | 0.000124 | 0.000000 | 0.000037 | 35.1 |
|
|
| |0>>> |_omp_dispatch | 6 | 5 | wall_clock | sec | 0.000002 | 0.000000 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#0] | 1 | 5 | wall_clock | sec | 0.000031 | 0.000031 | 0.000031 | 0.000031 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#12] | 1 | 5 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#1] | 1 | 5 | wall_clock | sec | 0.000111 | 0.000111 | 0.000111 | 0.000111 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#2] | 1 | 5 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#3] | 1 | 5 | wall_clock | sec | 0.000011 | 0.000011 | 0.000011 | 0.000011 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#6] | 1 | 5 | wall_clock | sec | 0.000003 | 0.000003 | 0.000003 | 0.000003 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#11] | 1 | 5 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#7] | 1 | 5 | wall_clock | sec | 0.000002 | 0.000002 | 0.000002 | 0.000002 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#9] | 1 | 5 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_omp_sync_region | 8 | 4 | wall_clock | sec | 0.000650 | 0.000081 | 0.000029 | 0.000332 | 0.000000 | 0.000102 | 7.9 |
|
|
| |0>>> |_omp_sync_region_wait | 8 | 5 | wall_clock | sec | 0.000599 | 0.000075 | 0.000022 | 0.000323 | 0.000000 | 0.000101 | 100.0 |
|
|
| |0>>> |_conj_grad | 1 | 4 | wall_clock | sec | 0.101564 | 0.101564 | 0.101564 | 0.101564 | 0.000000 | 0.000000 | 0.1 |
|
|
| |0>>> |_omp_work | 6 | 5 | wall_clock | sec | 0.002244 | 0.000374 | 0.000002 | 0.002137 | 0.000001 | 0.000864 | 3.0 |
|
|
| |0>>> |_omp_dispatch | 4 | 6 | wall_clock | sec | 0.000001 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#0] | 1 | 6 | wall_clock | sec | 0.000036 | 0.000036 | 0.000036 | 0.000036 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#1] | 1 | 6 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#9] | 1 | 6 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#8] | 1 | 6 | wall_clock | sec | 0.000008 | 0.000008 | 0.000008 | 0.000008 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#3] | 1 | 6 | wall_clock | sec | 0.002118 | 0.002118 | 0.002118 | 0.002118 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#6] | 1 | 6 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#5] | 1 | 6 | wall_clock | sec | 0.000013 | 0.000013 | 0.000013 | 0.000013 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_omp_sync_region | 6 | 5 | wall_clock | sec | 0.002043 | 0.000340 | 0.000029 | 0.001609 | 0.000000 | 0.000623 | 2.0 |
|
|
| |0>>> |_omp_sync_region_wait | 6 | 6 | wall_clock | sec | 0.002002 | 0.000334 | 0.000023 | 0.001601 | 0.000000 | 0.000622 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#2] | 1 | 5 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#7] | 1 | 5 | wall_clock | sec | 0.097195 | 0.097195 | 0.097195 | 0.097195 | 0.000000 | 0.000000 | 1.5 |
|
|
| |0>>> |_omp_work | 125 | 6 | wall_clock | sec | 0.054617 | 0.000437 | 0.000002 | 0.002348 | 0.000001 | 0.000850 | 100.0 |
|
|
| |0>>> |_omp_dispatch | 100 | 7 | wall_clock | sec | 0.000020 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_omp_sync_region | 125 | 6 | wall_clock | sec | 0.041158 | 0.000329 | 0.000019 | 0.001930 | 0.000000 | 0.000577 | 2.3 |
|
|
| |0>>> |_omp_sync_region_wait | 125 | 7 | wall_clock | sec | 0.040230 | 0.000322 | 0.000012 | 0.001922 | 0.000000 | 0.000574 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#4] | 1 | 5 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#5] | 1 | 4 | wall_clock | sec | 0.000001 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#4] | 1 | 4 | wall_clock | sec | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_omp_masked | 1 | 4 | wall_clock | sec | 0.000005 | 0.000005 | 0.000005 | 0.000005 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_main.omp_outlined [loop#8] | 1 | 4 | wall_clock | sec | 4.972270 | 4.972270 | 4.972270 | 4.972270 | 0.000000 | 0.000000 | 0.1 |
|
|
| |0>>> |_omp_masked | 150 | 5 | wall_clock | sec | 0.000450 | 0.000003 | 0.000001 | 0.000007 | 0.000000 | 0.000001 | 100.0 |
|
|
| |0>>> |_conj_grad | 50 | 5 | wall_clock | sec | 4.958396 | 0.099168 | 0.098075 | 0.101553 | 0.000000 | 0.000660 | 0.1 |
|
|
| |0>>> |_omp_work | 300 | 6 | wall_clock | sec | 0.110576 | 0.000369 | 0.000001 | 0.002217 | 0.000001 | 0.000787 | 2.7 |
|
|
| |0>>> |_omp_dispatch | 200 | 7 | wall_clock | sec | 0.000039 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#0] | 50 | 7 | wall_clock | sec | 0.000950 | 0.000019 | 0.000018 | 0.000020 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#1] | 50 | 7 | wall_clock | sec | 0.000022 | 0.000000 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#9] | 50 | 7 | wall_clock | sec | 0.000028 | 0.000001 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#8] | 50 | 7 | wall_clock | sec | 0.000332 | 0.000007 | 0.000006 | 0.000011 | 0.000000 | 0.000001 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#3] | 50 | 7 | wall_clock | sec | 0.105495 | 0.002110 | 0.002082 | 0.002202 | 0.000000 | 0.000022 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#6] | 50 | 7 | wall_clock | sec | 0.000044 | 0.000001 | 0.000001 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#5] | 50 | 7 | wall_clock | sec | 0.000699 | 0.000014 | 0.000013 | 0.000017 | 0.000000 | 0.000001 | 100.0 |
|
|
| |0>>> |_omp_sync_region | 300 | 6 | wall_clock | sec | 0.084068 | 0.000280 | 0.000009 | 0.001608 | 0.000000 | 0.000525 | 2.9 |
|
|
| |0>>> |_omp_sync_region_wait | 300 | 7 | wall_clock | sec | 0.081660 | 0.000272 | 0.000002 | 0.001581 | 0.000000 | 0.000522 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#2] | 50 | 6 | wall_clock | sec | 0.000024 | 0.000000 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#7] | 50 | 6 | wall_clock | sec | 4.759733 | 0.095195 | 0.094133 | 0.097391 | 0.000000 | 0.000630 | 1.5 |
|
|
| |0>>> |_omp_work | 6250 | 7 | wall_clock | sec | 2.704389 | 0.000433 | 0.000002 | 0.002239 | 0.000001 | 0.000838 | 100.0 |
|
|
| |0>>> |_omp_dispatch | 5000 | 8 | wall_clock | sec | 0.000990 | 0.000000 | 0.000000 | 0.000003 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_omp_sync_region | 6250 | 7 | wall_clock | sec | 1.983312 | 0.000317 | 0.000008 | 0.001660 | 0.000000 | 0.000551 | 2.5 |
|
|
| |0>>> |_omp_sync_region_wait | 6250 | 8 | wall_clock | sec | 1.932873 | 0.000309 | 0.000002 | 0.001652 | 0.000000 | 0.000548 | 100.0 |
|
|
| |0>>> |_conj_grad [loop#4] | 50 | 6 | wall_clock | sec | 0.000025 | 0.000001 | 0.000000 | 0.000001 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_omp_work | 200 | 5 | wall_clock | sec | 0.001475 | 0.000007 | 0.000002 | 0.000018 | 0.000000 | 0.000006 | 98.7 |
|
|
| |0>>> |_omp_dispatch | 100 | 6 | wall_clock | sec | 0.000019 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_omp_sync_region | 250 | 5 | wall_clock | sec | 0.009059 | 0.000036 | 0.000028 | 0.000055 | 0.000000 | 0.000006 | 17.7 |
|
|
| |0>>> |_omp_sync_region_wait | 250 | 6 | wall_clock | sec | 0.007460 | 0.000030 | 0.000021 | 0.000049 | 0.000000 | 0.000006 | 100.0 |
|
|
| |0>>> |_omp_sync_region | 1 | 3 | wall_clock | sec | 0.000033 | 0.000033 | 0.000033 | 0.000033 | 0.000000 | 0.000000 | 23.0 |
|
|
| |0>>> |_omp_sync_region_wait | 1 | 4 | wall_clock | sec | 0.000025 | 0.000025 | 0.000025 | 0.000025 | 0.000000 | 0.000000 | 100.0 |
|
|
| |0>>> |_c_print_results | 1 | 1 | wall_clock | sec | 0.000012 | 0.000012 | 0.000012 | 0.000012 | 0.000000 | 0.000000 | 100.0 |
|
|
|--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
|
|
Timemory JSON output
|
|
-------------------------------------------------------------------------
|
|
|
|
Timemory represents the data within the JSON output in two forms:
|
|
a flat structure and a hierarchical structure.
|
|
The flat JSON data represents the data similar to the text files, where the hierarchical information
|
|
is represented by the indentation of the ``prefix`` field and the ``depth`` field.
|
|
The hierarchical JSON contains additional information with respect
|
|
to inclusive and exclusive values. However,
|
|
its structure must be processed using recursion. This section of the JSON output supports analysis
|
|
by `hatchet <https://github.com/hatchet/hatchet>`_.
|
|
All the data entries for the flat structure are in a single JSON array. It is easier to
|
|
write a simple Python script for post-processing using this format than with the hierarchical structure.
|
|
|
|
.. note::
|
|
|
|
The generation of flat JSON output is configurable via ``ROCPROFSYS_JSON_OUTPUT``.
|
|
The generation of hierarchical JSON data is configurable via ``ROCPROFSYS_TREE_OUTPUT``
|
|
|
|
Timemory JSON output sample
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
|
|
In the following JSON data, the flat data starts at ``["timemory"]["wall_clock"]["ranks"]``
|
|
and the hierarchical data starts at ``["timemory"]["wall_clock"]["graph"]``.
|
|
To access the name (or prefix) of the nth entry in the flat data layout, use
|
|
``["timemory"]["wall_clock"]["ranks"][0]["graph"][<N>]["prefix"]``. When full MPI
|
|
support is enabled, the per-rank data in flat layout is represented
|
|
as an entry in the ``ranks`` array. In the hierarchical data structure,
|
|
the per-rank data is represented as an entry in the ``mpi`` array. However, ``graph``
|
|
is used in lieu of ``mpi`` when full MPI support is enabled.
|
|
In the hierarchical layout, all data for the process is a child of a dummy
|
|
root node, which has the name ``unknown-hash=0``.
|
|
|
|
.. code-block:: json
|
|
|
|
{
|
|
"timemory": {
|
|
"wall_clock": {
|
|
"properties": {
|
|
"cereal_class_version": 0,
|
|
"value": 78,
|
|
"enum": "WALL_CLOCK",
|
|
"id": "wall_clock",
|
|
"ids": [
|
|
"real_clock",
|
|
"virtual_clock",
|
|
"wall_clock"
|
|
]
|
|
},
|
|
"type": "wall_clock",
|
|
"description": "Real-clock timer (i.e. wall-clock timer)",
|
|
"unit_value": 1000000000,
|
|
"unit_repr": "sec",
|
|
"thread_scope_only": false,
|
|
"thread_count": 2,
|
|
"mpi_size": 1,
|
|
"upcxx_size": 1,
|
|
"process_count": 1,
|
|
"num_ranks": 1,
|
|
"concurrency": 2,
|
|
"ranks": [
|
|
{
|
|
"rank": 0,
|
|
"graph_size": 112,
|
|
"graph": [
|
|
{
|
|
"hash": 17481650134347108265,
|
|
"prefix": "|0>>> main",
|
|
"depth": 0,
|
|
"entry": {
|
|
"cereal_class_version": 0,
|
|
"laps": 1,
|
|
"value": 894743517,
|
|
"accum": 894743517,
|
|
"repr_data": 0.894743517,
|
|
"repr_display": 0.894743517
|
|
},
|
|
"stats": {
|
|
"cereal_class_version": 0,
|
|
"sum": 0.894743517,
|
|
"count": 1,
|
|
"min": 0.894743517,
|
|
"max": 0.894743517,
|
|
"sqr": 0.8005659612135293,
|
|
"mean": 0.894743517,
|
|
"stddev": 0.0
|
|
},
|
|
"rolling_hash": 17481650134347108265
|
|
},
|
|
{
|
|
"hash": 3455444288293231339,
|
|
"prefix": "|0>>> |_read_input",
|
|
"depth": 1,
|
|
"entry": {
|
|
"laps": 1,
|
|
"value": 9808,
|
|
"accum": 9808,
|
|
"repr_data": 9.808e-06,
|
|
"repr_display": 9.808e-06
|
|
},
|
|
"stats": {
|
|
"sum": 9.808e-06,
|
|
"count": 1,
|
|
"min": 9.808e-06,
|
|
"max": 9.808e-06,
|
|
"sqr": 9.6196864e-11,
|
|
"mean": 9.808e-06,
|
|
"stddev": 0.0
|
|
},
|
|
"rolling_hash": 2490350348930787988
|
|
},
|
|
{
|
|
"hash": 8456966793631718807,
|
|
"prefix": "|0>>> |_setcoeff",
|
|
"depth": 1,
|
|
"entry": {
|
|
"laps": 1,
|
|
"value": 922,
|
|
"accum": 922,
|
|
"repr_data": 9.22e-07,
|
|
"repr_display": 9.22e-07
|
|
},
|
|
"stats": {
|
|
"sum": 9.22e-07,
|
|
"count": 1,
|
|
"min": 9.22e-07,
|
|
"max": 9.22e-07,
|
|
"sqr": 8.50084e-13,
|
|
"mean": 9.22e-07,
|
|
"stddev": 0.0
|
|
},
|
|
"rolling_hash": 7491872854269275456
|
|
},
|
|
{
|
|
"hash": 6107876127803219007,
|
|
"prefix": "|0>>> |_omp_thread_begin",
|
|
"depth": 1,
|
|
"entry": {
|
|
"laps": 1,
|
|
"value": 896506392,
|
|
"accum": 896506392,
|
|
"repr_data": 0.896506392,
|
|
"repr_display": 0.896506392
|
|
},
|
|
"stats": {
|
|
"sum": 0.896506392,
|
|
"count": 1,
|
|
"min": 0.896506392,
|
|
"max": 0.896506392,
|
|
"sqr": 0.8037237108968578,
|
|
"mean": 0.896506392,
|
|
"stddev": 0.0
|
|
},
|
|
"rolling_hash": 5142782188440775656
|
|
},
|
|
{
|
|
"hash": 15402802091993617561,
|
|
"prefix": "|0>>> |_omp_implicit_task",
|
|
"depth": 2,
|
|
"entry": {
|
|
"laps": 1,
|
|
"value": 896479111,
|
|
"accum": 896479111,
|
|
"repr_data": 0.896479111,
|
|
"repr_display": 0.896479111
|
|
},
|
|
"stats": {
|
|
"sum": 0.896479111,
|
|
"count": 1,
|
|
"min": 0.896479111,
|
|
"max": 0.896479111,
|
|
"sqr": 0.8036747964593504,
|
|
"mean": 0.896479111,
|
|
"stddev": 0.0
|
|
},
|
|
"rolling_hash": 2098840206724841601 },
|
|
{
|
|
"..." : "... etc. ..."
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"graph": [
|
|
[
|
|
{
|
|
"cereal_class_version": 0,
|
|
"node": {
|
|
"hash": 0,
|
|
"prefix": "unknown-hash=0",
|
|
"tid": [
|
|
0
|
|
],
|
|
"pid": [
|
|
2539175
|
|
],
|
|
"depth": 0,
|
|
"is_dummy": false,
|
|
"inclusive": {
|
|
"entry": {
|
|
"laps": 0,
|
|
"value": 0,
|
|
"accum": 0,
|
|
"repr_data": 0.0,
|
|
"repr_display": 0.0
|
|
},
|
|
"stats": {
|
|
"sum": 0.0,
|
|
"count": 0,
|
|
"min": 0.0,
|
|
"max": 0.0,
|
|
"sqr": 0.0,
|
|
"mean": 0.0,
|
|
"stddev": 0.0
|
|
}
|
|
},
|
|
"exclusive": {
|
|
"entry": {
|
|
"laps": 0,
|
|
"value": -894743517,
|
|
"accum": -894743517,
|
|
"repr_data": -0.894743517,
|
|
"repr_display": -0.894743517
|
|
},
|
|
"stats": {
|
|
"sum": 0.0,
|
|
"count": 0,
|
|
"min": 0.0,
|
|
"max": 0.0,
|
|
"sqr": 0.0,
|
|
"mean": 0.0,
|
|
"stddev": 0.0
|
|
}
|
|
}
|
|
},
|
|
"children": [
|
|
{
|
|
"node": {
|
|
"hash": 17481650134347108265,
|
|
"prefix": "main",
|
|
"tid": [
|
|
0
|
|
],
|
|
"pid": [
|
|
2539175
|
|
],
|
|
"depth": 1,
|
|
"is_dummy": false,
|
|
"inclusive": {
|
|
"entry": {
|
|
"laps": 1,
|
|
"value": 894743517,
|
|
"accum": 894743517,
|
|
"repr_data": 0.894743517,
|
|
"repr_display": 0.894743517
|
|
},
|
|
"stats": {
|
|
"sum": 0.894743517,
|
|
"count": 1,
|
|
"min": 0.894743517,
|
|
"max": 0.894743517,
|
|
"sqr": 0.8005659612135293,
|
|
"mean": 0.894743517,
|
|
"stddev": 0.0
|
|
}
|
|
},
|
|
"exclusive": {
|
|
"entry": {
|
|
"laps": 1,
|
|
"value": -1773605,
|
|
"accum": -1773605,
|
|
"repr_data": -0.001773605,
|
|
"repr_display": -0.001773605
|
|
},
|
|
"stats": {
|
|
"sum": -0.001773605,
|
|
"count": 1,
|
|
"min": 9.22e-07,
|
|
"max": 0.896506392,
|
|
"sqr": -0.0031577497803754,
|
|
"mean": -0.001773605,
|
|
"stddev": 0.0
|
|
}
|
|
}
|
|
},
|
|
"children": [
|
|
{
|
|
"..." : "... etc. ..."
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|
|
]
|
|
}
|
|
}
|
|
}
|
|
|
|
Timemory JSON output Python post-processing example
|
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
|
|
|
.. code-block:: python
|
|
|
|
#!/usr/bin/env python3
|
|
|
|
import sys
|
|
import json
|
|
|
|
|
|
def read_json(inp):
|
|
with open(inp, "r") as f:
|
|
return json.load(f)
|
|
|
|
|
|
def find_max(data):
|
|
"""Find the max for any function called multiple times"""
|
|
max_entry = None
|
|
for itr in data:
|
|
if itr["entry"]["laps"] == 1:
|
|
continue
|
|
if max_entry is None:
|
|
max_entry = itr
|
|
else:
|
|
if itr["stats"]["mean"] > max_entry["stats"]["mean"]:
|
|
max_entry = itr
|
|
return max_entry
|
|
|
|
|
|
def strip_name(name):
|
|
"""Return everything after |_ if it exists"""
|
|
idx = name.index("|_")
|
|
return name if idx is None else name[(idx + 2) :]
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
input_data = [[x, read_json(x)] for x in sys.argv[1:]]
|
|
|
|
for file, data in input_data:
|
|
for metric, metric_data in data["timemory"].items():
|
|
|
|
print(f"[{file}] Found metric: {metric}")
|
|
|
|
for n, itr in enumerate(metric_data["ranks"]):
|
|
|
|
max_entry = find_max(itr["graph"])
|
|
print(
|
|
"[{}] Maximum value: '{}' at depth {} was called {}x :: {:.3f} {} (mean = {:.3e} {})".format(
|
|
file,
|
|
strip_name(max_entry["prefix"]),
|
|
max_entry["depth"],
|
|
max_entry["entry"]["laps"],
|
|
max_entry["entry"]["repr_data"],
|
|
metric_data["unit_repr"],
|
|
max_entry["stats"]["mean"],
|
|
metric_data["unit_repr"],
|
|
)
|
|
)
|
|
|
|
The result of applying this script to the corresponding JSON output from the :ref:`text-output-example-label`
|
|
section is as follows:
|
|
|
|
.. code-block:: shell
|
|
|
|
[openmp-cg.inst-wall_clock.json] Found metric: wall_clock
|
|
[openmp-cg.inst-wall_clock.json] Maximum value: 'conj_grad' at depth 6 was called 76x :: 10.641 sec (mean = 1.400e-01 sec)
|