8 Commits

Author SHA1 Message Date
Madsen, Jonathan b097e276a9 [rocprofv3] Add rocpd output support (part 1: prelude) (#401)
* [rocprofv3] Add rocpd output support (part 1: prelude)

- git submodules for sqlite3, GOTCHA, and pybind11
- HIP stream data
- rocprofiler_query_intercept_table_name(...)
- serialization load
- rocprofiler::sdk::get_perfetto_category(KindT)
- rocprofiler::sdk::parse::strip
- common library updates
  - md5sum
  - hasher
  - simple_timer
  - static_tl_object
  - get_process_start_time_ns(pid_t)
- output library updates
  - node_info
  - file_generator (generator is now virtual base class)
  - stream info updates

* Added submodules

* Code review updates

* Minor unused-but-set-X warning fixes

* Update CI

- install libsqlite3-dev package

* Update CI

- install libsqlite3-dev package

* Fix static thread-local object memory leak

- also fix signal handler chaining

* Remove URL from comment

* Remove page migration exception

* Enable ROCPROFILER_BUILD_SQLITE3 by default

- try find_package(SQLite3) first and then build when ROCPROFILER_BUILD_SQLITE3=ON

* Fix gotcha installation

- make install of target optional

* Validate tracing + counter collection dispatch data

- i.e. correlation ids, thread ids, timestamps

* Make find_package(SQLite3) optional

- ROCm CI does not have SQLite3 dev package installed and cannot build from source (missing tclsh)

* Fixes to tracing + counter collection test

* get_process_start_time_ns update

- original implementation did not work

* Fix pytest-packages test_perfetto_data for counter collection

- erroneous failure when used with same PMC + multiple agents

* cmake policy: option() honors normal variables

- for GOTCHA submodule

* Improve samples/api_buffered_tracing stability

- reduce likelihood of sporadic exception throw

* Update gotcha submodule

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 7166b1ab58]
2025-05-18 20:11:26 -05:00
Madsen, Jonathan 8f891cdcc8 [SDK][rocprofv3] Buffer tracing records with args (HIP) (#285)
* [SDK][rocprofv3] HIP API buffer records with args (ext)

- New buffer tracing domain(s) for HIP APIs which include the arguments and the return value in the buffer records
- Update HIP stream support for extended HIP buffer tracing
- Update rocprofv3 tool library and output library to use extended HIP buffer tracing recods

* Update stream.cpp

- handle hipStream_t address being reused for a new stream

* Update doxygen docs for rocprofiler_iterate_buffer_tracing_record_args

* Update rocprofv3 tool.cpp

- configure buffer tracing services with HIP_*_API_EXT variants
- tweak logging level for hip_stream_display_callback

* Fix validation tests

- add HIP_RUNTIME_API_EXT and HIP_COMPILER_API_EXT to valid domain names

* Serialization support for buffer tracing args

* Disable stream service for __hipPopCallConfiguration

- this is interpreted as a stream create but it doesn't create a stream

* Fix execute_buffer_record_emplace for HIP extended contexts

* Add uint64_t_retval to rocprofiler_hip_api_retval_t union

- reading in hipError_t_retval during serialization of pointer return value causes undefined behavior

* Fix compilation warning about unused but set parameter

- in hip/stream.cpp

* Add synchronization for async_copy_data

* Fix compilation error

* Fix compilation error

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: e33dff7ad0]
2025-03-22 19:57:32 -05:00
Trowbridge, Ian 7aeaffd871 HIP Streams to Queues Translation (#235)
* rocprofiler_stream_id_t: opaque handle for a stream

- e.g. HIP stream
- the same HIP stream may map to different HSA queues at different points in the application
- added to:
  - rocprofiler_buffer_tracing_hip_api_record_t
  - rocprofiler_buffer_tracing_memory_copy_record_t
  - rocprofiler_callback_tracing_hip_api_data_t
  - rocprofiler_callback_tracing_memory_copy_data_t
---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Mark Meserve <mark.meserve@amd.com>
Co-authored-by: Elwazir, Ammar <Ammar.Elwazir@amd.com>
Co-authored-by: Ammar ELWazir <aelwazir@amd.com>
Co-authored-by: Jakaraddi, Manjunath <Manjunath.Jakaraddi@amd.com>
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com>
Co-authored-by: Nagaraj, Sriraksha <Sriraksha.Nagaraj@amd.com>
Co-authored-by: U, Srihari <Srihari.U@amd.com>
Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>
Co-authored-by: Welton, Benjamin <Benjamin.Welton@amd.com>
Co-authored-by: Benjamin Welton <ben@amd.com>
Co-authored-by: Indic, Vladimir <Vladimir.Indic@amd.com>
Co-authored-by: Benjamin Welton <bewelton@amd.com>

[ROCm/rocprofiler-sdk commit: ccd1e54293]
2025-03-14 02:45:13 -07:00
Madsen, Jonathan 6cb0dda8ba Fix async memory copy validation tests (#182)
* Fix async copy validation test

- make the async copy tracing test work regardless of however many HSA memory copies the HIP memory copy decomposes into

* Fix rocprofv3 memory copy tests

* Fix compilation support for hipGraphBatchMemOpNodeGetParams

* Fix rocprofv3-test-summary-*-validate

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 7fcd80f744]
2025-02-04 02:41:19 -06:00
Rawat, Swati edb51fc861 update copyright date to 2025 (#102)
* Update LICENSE

* Update conf.py

* Update copyright year

* [fix] Update copyright year

* Update copyright year "ROCm Developer Tools"

* Add license headers to c++ files

* Add license to *.py

* Update licenses in rocdecode sources

---------

Co-authored-by: srawat <120587655+SwRaw@users.noreply.github.com>
Co-authored-by: Mythreya <mythreya.kuricheti@amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 97b7a6315d]
2025-01-22 19:11:20 -06:00
Jonathan R. Madsen 6743608258 rocprofv3: summary reports + more JSON metadata (#1029)
* Move include/rocprofiler-sdk/cxx/details/delimit.hpp to tokenize.hpp

* Update docs/how-to/using-rocprofv3.rst

- fix code block indents
- reorder rocprofv3 options, limit them to important options
- add docs for `--runtime-trace`

* Update rocprofv3.py

- parser argument groups
- new `--runtime-trace` option
- new `--summary` option
- new `--summary-per-domain` option
- new `--summary-groups` option
- new `--summary-output-file` option
- new `--summary-units` option

* Update lib/rocprofiler-sdk/hsa/async_copy.cpp

- fix async copy operation names: add "MEMORY_COPY_" prefix

* lib/rocprofiler-sdk-tool: update statistics.{hpp,cpp}

- statistics<>::get_percent function
- stats_entry_t struct
- stats_formatter struct
- percentage struct
- std::to_string(::rocprofiler::tool::percentage)

* lib/rocprofiler-sdk-tool: update domain_type.{hpp,cpp}

- reorder domain_type enum values

* lib/rocprofiler-sdk-tool: update generateCSV.{hpp,cpp}

- separate writing CSV from accumulating statistics
- a lot of functionality was moved to statistics.{hpp,cpp}

* lib/rocprofiler-sdk-tool: update output_file.{hpp,cpp}

- output_stream_t struct
- get_output_stream(...) returns output_stream_t instance

* lib/rocprofiler-sdk-tool: update generateJSON.cpp

- update get_output_stream usage to output_stream_t

* lib/rocprofiler-sdk-tool: update generateOTF2.cpp

- header include order tweak

* lib/rocprofiler-sdk-tool: update buffered_output.hpp

- stats_data_t was renamed to stats_entry_t

* lib/rocprofiler-sdk-tool: update generatePerfetto.cpp

- header include tweak

* lib/rocprofiler-sdk-tool: update tmp_file_buffer.hpp

- emit warning message if write_ring_buffer fails after offloading instead of aborting
- prefer placement new instead of assignment in write_ring_buffer

* lib/rocprofiler-sdk-tool: add generateStats.{hpp,cpp}

- functions for accumulating statistics

* Update tests/rocprofv3/tracing-hip-in-libraries/CMakeLists.txt

- accommodate tweak to CSV output file name for HIP and HSA traces

* lib/rocprofiler-sdk-tool: update config.{hpp,cpp}

- new config variables
  - stats_summary
  - stats_summary_per_domain
  - summary_output
  - stats_summary_unit_value
  - stats_summary_unit
  - stats_summary_file
  - stats_summary_groups
- support output keys for hostname: %hostname% / %h

* lib/rocprofiler-sdk-tool: update tool.cpp

- support summary output

* Documentation fixes

* Test for summary output

* Update tests/bin/transpose to use more ROCTx

- also support building with the roctracer ROCTx

* Remove roctxMark from OTF2 + fix kernel-rename tests

- following more ROCTx calls in transpose, kernel-rename validation had to be updated

* JSON metadata + JSON summary

- add serialization support for config
- add serialization support for statistics
- additions to json spec
  - rocprofiler-sdk-tool/metadata/config
  - rocprofiler-sdk-tool/metadata/command
  - rocprofiler-sdk-tool/summary
- config output_keys support for NVIDIA %q{<ENV-VAR>} syntax
- config output_keys support keys within keys

* rocprofv3 --summary-groups warning if no domain matches

- emit warning if a regex in for summary groups did not match any domain names

* Compile fix for lib/rocprofiler-sdk-tool/tool.cpp

- get_config().scratch_memory_trace
- pass contributions to write_json

* Update rocprofv3.py to preload rocprofiler-sdk-roctx

- appended to LD_PRELOAD when args.marker_trace is enabled

* Fix ReST link errors about subtitle underline being too short

* Patch tokenization of config::stats_summary_groups

- guard against array values of empty strings

* Tweak rocprofv3 summary test

- input-summary.yaml (used by rocprofv3-test-summary-inp-yaml-execute) only provides one summary group regex

* Disable LD_PRELOAD of librocprofiler-sdk-roctx.so

- this causes problems in the sanitizers, will be addressed in another PR

[ROCm/rocprofiler-sdk commit: 395f01b689]
2024-09-09 11:20:55 -05:00
Jonathan R. Madsen ef22b7a484 rocprofv3 OTF2 Output Support (#995)
* CMake support for OTF2 library

* Preliminary OTF2 generation implementation

* Completed OTF2 Support

- HSA API
- HIP API
- Marker API
- Async Memory Copies
- Kernel Dispatch

* Update lib/rocprofiler-sdk-tool/generateOTF2.cpp

- fix location type for dispatches

* Testing for OTF2 output

* Add OTF2 to requirements.txt

* Update lib/rocprofiler-sdk-tool/generateOTF2.cpp

- fix getting kernel name

* OTF2 testing with rocprofv3/tracing-hip-in-libraries

* Format external/otf2/CMakeLists.txt

* Update external/otf2/CMakeLists.txt

- guard CMP0135 for cmake < 3.24

* Update lib/rocprofiler-sdk-tool/generateOTF2.cpp

- fix duplicate string ref issue

* Update lib/rocprofiler-sdk-tool/generateOTF2.cpp

- fix header includes

* Update CI workflow

- sudo install pypi requirements for core-rpm for $HOME/.local installs

* Update pytest_utils/otf2_reader.py

- modifications for reading trace

* Update pytest_utils/otf2_reader.py

- misc cleanup

* Update CI workflow

- fix installer artifact naming

* Update pytest_utils/otf2_reader.py

- handle slightly overlapping kernel timestamps for MI300

* OTF2 attributes for category

* Testing with OTF2Reader category attributes

* Fix memory leak in OTF2 generation

- leaking OTF2_AttributeList

[ROCm/rocprofiler-sdk commit: 16d535ef48]
2024-07-30 19:57:19 -05:00
Jonathan R. Madsen a728a4b4cd rocprofv3 kernel renaming support + misc rocprofv3 updates (#992)
* Increase rocprofv3 tool buffer size

- 32 pages instead of 1 page

* Improve rocprofv3 perfetto track labels

* Preliminary kernel renaming support + misc rocprofv3 updates

- add rocprofv3 option --kernel-rename
- add rocprofv3 options for perfetto settings (buffer size, etc.)
- add CSV columns for kernel trace
  - Thread_Id
  - Dispatch_Id
- add CSV column for counter_collection
 - Kernel_Id

[ROCm/rocprofiler-sdk commit: ebb021c59f]
2024-07-29 14:33:50 -05:00