Commit Graph

8 Commits

Author SHA1 Message Date
Jonathan R. Madsen 99da25ea80 exit gotcha + remove DelayedInit state + rocm-smi + cleanup (#110)
* exit gotcha + remove DelayedInit state + cleanup

- exit gotcha which wraps exit, quick_exit, abort
- minor refactor of mpi gotchas
- removed some redundant code in omnitrace_finalized_hidden
- exclude instrumenting functions starting with dlopen and dlsym
- exclude instrumenting exit, quick_exit, and abort functions
- update timemory submodule with support for new gotcha_invoker with (gotcha_data, <function pointer>, args...)

* Improved rocm_smi error handling
2022-07-24 22:09:32 -05:00
Jonathan R. Madsen 0729e1737b Pthread category region (#102)
* Perfetto args support for pthread functions

* Add pthread category
2022-07-22 16:45:35 -05:00
Jonathan R. Madsen 4208b5654c GPU HW Counters via rocprofiler (#84)
* Initial support for GPU hardware counters

* Update find modules for roctracer and rocprofiler

- /opt/rocm/{rocprofiler,roctracer} path is deprecated so tweak search procedure

* Improve ConfigCPack for MPI

* Update rocprofiler

- rocm_metrics()
- minor cleanup

* Update rocm find modules

* declare rocm_metrics + call in omnitrace-avail

* relocate omnitrace-launch-compiler

* REALPATH and find_modules

* Examples cmake (may drop)

* omnitrace-avail

- hw_counter categories
- init rocm

* setenv updates for rocprofiler in library.cpp and dl.cpp

* get_rocm_events config

* gpu::hip_device_count()

* rocm_metrics returns hardware_counters::info

* - relocated library/components/roctracer_callbacks.* to library/roctracer.*
- relocated library/components/rocprofiler.* to library/rocprofiler.*
- cleaned up rocprofiler.hpp
- added perfetto output of rocprofiler
- added timemory output of rocprofiler
- renamed omni.roctracer thread to roctracer.hip
- added roctracer.hsa thread name
- updated timemory submodule to support std::variant
- updated timemory submodule to support = in config value
- updated timemory submodule to support standalone storage
- updated timemory submodule to support new hw counter apis
- updated timemory submodule to prevent label/description caching in data_tracker

* update omnitrace-avail info_type generation

* Update timemory submodule

* rocprofiler component

* cmake formatting

* omnitrace-avail handle no GPUs

- Add -c command-line option for --categories
- support verbosity

* hsa_rsrc_factory throws exceptions

- throw exceptions to avoid aborting on HSA_STATUS_ERROR_NOT_INITIALIZED when advantageous
- removed duplicate specialization of is_available for component::rocprofiler

* rocprofiler symbols for when disabled

* Fix warning in omnitrace-avail

- std::stringstream from initializer list would use explicit constructor

* Fix finalization after settings are deleted

* Reorganized rocprofiler source

* Updated formatting

* Miscellaneous tweaks

- added using statements from timemory
- tweaked the main and thread bundle names
- fixed timemory header includes
2022-07-17 21:52:09 -05:00
Jonathan R. Madsen e099c84640 pthread_rwlock deadlock fix (#82)
- found when using ROCm-enabled OpenMPI with rocHPL
  - when wrapping pthread_rwlock_rdlock, pthread_rwlock_wrlock, and pthread_rwlock_unlock, omnitrace has been found to deadlock for some unknown reason
- New configuration variable: OMNITRACE_TRACE_THREAD_RW_LOCKS which defaults to false
2022-07-11 20:59:57 -05:00
Jonathan R. Madsen 27e4e82376 Deprecate omnitrace use thread sampling (#68)
* Deprecate OMNITRACE_USE_THREAD_SAMPLING

* Reworked config based on OMNITRACE_MODE

- config::set_default_setting_value(...)
- config::get_mode() is now dynamically deduced
- moved tweaking defaults from library.cpp to config::configure_mode_settings(...)
- timemory submodule update fixing vsetting issue

* runtime.md update

* revert accidental lambda name change

* Reintroduce (deprecated) OMNITRACE_ROCM_SMI_DEVICES

- add handle_deprecated_setting(...) for this deprecated setting
2022-06-24 15:03:15 -05:00
Jonathan R. Madsen 424a3593e7 MPI headers + mutex gotcha + roctracer + kokkosp (#11)
* MPI headers, mutex gotcha + roctracer + kokkosp

- relocate internal MPI headers
- pthread_barrier in parallel-overhead
- doc fixes to DYNINST options
- minor tweaks to dynamic_library
- dlopen libamdhip64.so
- scoped thread state in kokkos
- extended pthread_mutex_gotcha

* Fix for unused-but-set-variables
2022-05-30 18:25:12 -05:00
Jonathan R. Madsen 353e8eeb69 Critical trace updates (#6)
* critical trace updates

- better handling of OMNITRACE_USE_PERFETTO in omnitrace-critical-trace exe
- changed some data types in `critical_trace::entry`
- added device ids to critical trace entries
- added process ids to critical trace entries
- added packing to critical trace entries

* Update timemory submodule
2022-05-24 19:25:54 -05:00
Jonathan R. Madsen b208047741 Support for tracing mutex locking (#52)
* Parallel overhead example with locks

* Support tracing mutex locking + more

- support wrapping pthread_mutex_lock
- support wrapping pthread_mutex_unlock
- support wrapping pthread_mutex_trylock
- get_perfetto_combined_traces setting
- OMNITRACE_TRACE_THREAD_LOCKS option
- ThreadState
- critical trace includes queue id
- enabled/disabled settings in timemory
- fix OMNITRACE_TIMEMORY_COMPONENTS
- fix reading config
- fix setting categories
- applied ThreadState::Internal in various places
- utility::get_filled_array
- utility::get_reserved_vector
- utility::get_thread_index
- fork_gotcha messages about forks
- split out some pthread_gotcha functionality into pthread_create_gotcha
- handle queue id in roctracer callbacks

* Update timemory and PTL submodules

* Misc CMake updates

- Includes fix to omnitrace-static-lib{gcc,stdcxx}

* Misc cleanup to pthread_mutex_gotcha and backtrace

* Fix to duplicate field in module_function json

* Improvement to debug messages

* omnitrace-dl and common improvements

- tweak to delimit
- common::ignore message
- common::join quoting of strings
- omnitrace_set_env ignores if inited and active
- omnitrace_set_mpi ignores if inited and active

* nsync for transpose example

* Fix to thread_deleter<void> functor invoke

* Fix thread state and HIP stream enums
2022-05-08 04:40:10 -05:00