Use hsa header files from /opt/rocm-ver/include rather than using wrapper files from /opt/rocm-ver/hsa/include/hsa
Change-Id: Id7a9bde19447cd2a0fd6e03b11c08471f09c2a46
We should link against numa without hardcoding the path to it.
CMake should determine how to link numa automatically, similar to how rt
and pthread is linked.
Fixes
Change-Id: Ifb9ac30e200c66cbd7f1cf80d25fffef1dcf8d2f
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
LoopIsa is a shader that performs a variety of intensive
calculations in a loop. It is used by tests such as
KFDQMTest.QueuePriorityOn*
It contained a scalar load, despite not having any buffer to
read from. This load causes page faults on GFX11. It is
unclear why it did not cause page faults on earlier ASICs.
Remove the load.
Signed-off-by: David Francis <David.Francis@amd.com>
Change-Id: I7426d0db48e933f3bb870467ea88476f7a283040
When the shaders were moved to ShaderStore,
KFDQMTest.EmptyDispatch was erroneously
changed to use LoopIsa instead of NoopIsa.
Change it back.
Signed-off-by: David Francis <David.Francis@amd.com>
Change-Id: Iaf7d0d107e3bf3bd8b7d616b137a1740e309cf91
Kernel debug IOCTL got version bumped to v11.
Updated runtime enable but missed runtime disable check update.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Change-Id: I71a8970ccfe7dc517abe7b4ad962369aea6a0496
* Improved sampling performance
* Sampling tweaks
- backtrace::get() returns vector of string_view
- further performance improvements
- tweaked _use_label
- wrapped samples in perfetto "samples [omnitrace]" block
- samples in TID=0 in sampling mode are in separate thread row
* Fix empty HW counter desc + category for sampling
- fallback to to metric name if papi event info description not found
- add perfetto sampling category
* Limit the SIGALRM frequency
Previously we omitted the version and arch in the filenames. By adding this,
as well as the ROCM build variable, this will allow for easy version
version detection on systems. Instead of kfdtest = v1.0.0, now it will
feature the build number, allowing for easier identification as to which
version is installed.
Change-Id: I311ed7010486e7c70af669d282910fe29ee8db45
- 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
To improve performance on queue preemption, allocate ctx s/r
area in VRAM instead of system memory, and migrate it back
to system memory when VRAM is full.
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Change-Id: If775782027188dbe84b6868260e429373675434c
It is to add new option for always keeping gpu mapping
and bump KFD version for the feature of unified save
restore memory.
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Change-Id: Iebee35e6de4d52fa29f82dd19f6bbf5640249492
Use GNUInstallDirs variables to determine the location of BINDIR,
LIBDIR, INCLUDEDIR, DATADIR, DOCDIR, LIBEXECDIR.
Depends-On: Id11f862fb4bdb2425d68f455074172c38814ec92
Change-Id: I6459a4531ef899321a5e2d8050cf8b553e89a968
A work group processor (WGP) require both its CU to be enabled
in order to be enabled.
The KFD will round robin distribute by even-indexed pairs so
enforce this requirement for runtime set mask calls.
Change-Id: Ic46661b01f398aa1fe24d96b5c9c31f122f967a3
Open SMI event file handle, prefetch to migrate svm range to GPU, read
HMM profiling events, then check event_id, address, size, pid, event
triggers are the expected value.
Start separate thread to read SMI event, the same way applications use.
Use thread barrier to ensure no event is dropped.
Change-Id: I0683969d18d1579847e125d86aa4257602adb13f
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Discovered agent handles should only apply to copy routing, not to
copy device selection. The user may not have mapped all allocations
to all GPUs so we must ensure that the copying device is one passed
by the user.
Change-Id: I2532e66d30e6842624e594f235dd144a186220d4
The roctracer-tests package contains all the roctracer test binaries
and scripts needed to run the testsuite outside of the build directory.
Change-Id: Id11f862fb4bdb2425d68f455074172c38814ec92
Changes made on rsmi_perf_determinism_mode_set function documentation
as well for styling consistency.
Change-Id: I09ce8139eb9cbda94352ac7725c4c9b9bb06bd59
- handle OMNITRACE_ENABLED=OFF by disabling everything
- use set_data to get wrappee in pthread_create_gotcha
- clear roctracer_data storage if roctracer not initialized
* HIP API perfetto args + updated perfetto categories
- Support for HIP API args field in perfetto
- PERFETTO_CATEGORIES -> OMNITRACE_PERFETTO_CATEGORIES
- Changed perfetto categories for several trace events and trace counters
- migrated several TRACE_EVENT_* to use omnitrace::tracing::{push,pop}_perfetto_ts(...)
* Tweaked category_region to encode the type of args as well as value
- Affects MPI args field in perfetto
* Improved testing in ubuntu-focal.yml
- "Test Install" step sources setup-env.sh
- "Test Install" step tests python support
- "Test Install" step tests reading ~/.omnitrace.cfg
- Avoid installing boost and tbb libs when building from submodule
* validate-perfetto-proto.py accepts -m / --categories
* Remove reference from category_region typeids
* Tweak opensuse action name
* Tweak the "Test Install" Step of ubuntu-focal
* Use concurrency + remove cancelling
* Combined ubuntu-focal-external with ubuntu-focal-external-rocm
* Update workflow names and README
* Update ubuntu-focal name
* More tweaks to the name
* Change names in formatting workflow
* Adds test which validates errors for missing configs
- updates timemory submodule with fix for protection against recursion
* Removed PASS_REGULAR_EXPRESSION
- this seems to have different behaviors depending on cmake version
activity.h and rocprofiler.h are already exposed in rocprofiler
through the rocm installation directory.
Change-Id: Ia383d3818fd51452390d2217d82503af4d91aac6
* Rework submodule installation
- use add_subdirectory(... EXCLUDE_FROM_ALL) + explicit installation of deps
- install all library deps to lib/omnitrace
- internal builds of dyninst use libomnitrace-rt for binary rewriting
- support libdyninstAPI_RT not in LD_LIBRARY_PATH when dyninst built internally
* Update ubuntu-focal to test full dyninst install
* Use RelWithDebInfo because Dyninst segfaults with MinSizeRel
* Fix ubuntu-focal.yml install step
* Config updates
- See PR #69 for details
- change type of OMNITRACE_DL_VERBOSE
- add "deprecated" category to OMNITRACE_ROCM_SMI_DEVICES
- reduce size of perfetto shared memory size hint
- deprecate OMNITRACE_OUTPUT_FILE in favor of OMNITRACE_PERFETTO_FILE
- set papi event choices
- read config file after reading command line
- fix update of OMNITRACE_DL_VERBOSE
- mark several settings as hidden
- timemory update support hidden attribute for settings
- rework get_perfetto_output_filename()
- Hide settings from not available backends
* Rework omnitrace-avail to support dumping configurations
* Overwrite query, tests, output flag
- Support using -O flag when dumping config
- Support checking before overwriting existing config
- Support --force to overwrite existing config
- Fix get_component_info not including omnitrace components
- Testing for dumping config
* Update documentation on omnitrace-avail
* Fix issue with timemory format + "/__w/"
* Update output prefix keys docs
* Rename --dump-config to --generate-config
* Hide MPI related options
- OMNITRACE_PERFETTO_COMBINE_TRACES and OMNITRACE_COLLAPSE_PROCESSES are hidden w/o MPI support
* Fix to pid via mpi_gotcha
* OMNITRACE_VERSION defines
* call perfetto on hsa_activity_callback thread
* Test label tweak
* Config fixes
- Change type of OMNITRACE_DL_VERBOSE
- Update OMNITRACE_DL_VERBOSE properly
- Add OMNITRACE_ROCM_SMI_DEVICES to deprecated group
- Set default_process_suffix
* metadata for OMNITRACE_VERSION and OMNITRACE_HIP_VERSION
The ROCR now detects already loaded tool libraries and calls OnLoad/
OnUnload in the order specified with HSA_AMD_TOOL_ORDER.
It is no longer necessary to set the HSA_TOOLS_LIB environment variable
to load the roctracer API. The roctracer tool library should be
pre-loaded with LD_PRELOAD.
Change-Id: I6de1b1bd4f93caa08d3554aad2376d242c74fb7e
tracing NS + category region component
- made library.cpp impl more broadly available
- support for perfetto args
- MPI wrappers encode args and return type
- new categories / perfetto categories
- omnitrace_library category -> libomnitrace
- omnitrace_dl_library -> libomnitrace-dl
The KFD no longer allow debug ops that modify HW state prior to
trap activation so permit bump in major version.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Change-Id: I072d3998b7b043df9a67f0f6762b0afdfa9382c6
* adding perfetto-validation-script
* Rename validation script
* Update tests/validate_perfetto.py
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
* Update tests/validate_perfetto.py
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
* Update tests/validate_perfetto.py
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
* Update tests/validate_perfetto.py
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
* addressed the edits in the validation script
* addressed the edits in the validation script
* Perfetto validation script (#1)
* Fixed mismatch message in validate-timemory-json
* validate_perfetto.py -> validate-perfetto-proto.py
* Add python-source-validate-perfetto
- python-source-validate-perfetto uses validate-python-proto.py to validate perfetto output
- renamed python-source-check test to python-source-validate timemory
* Moved python-source-validate tests outside of cat command if block
- these tests don't rely on OMNITRACE_CAT_COMMAND
* CMake/CTest OMNITRACE_ADD_PYTHON_VALIDATION_TEST function
- generalized function for performing validation test with validate-{timemory-json,perfetto-proto}.py scripts
* Print perfetto validation
* Install perfetto python package in workflows
* cmake format
* Python formatting
* Python formatting CI
* Install perfetto python package in workflows
* Install dataclasses for perfetto in opensuse
* Install dataclasses for perfetto in ubuntu
- uninstalled dependency for perfetto in Python 3.6
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Mostly a demo at this point. Logs SVM (aka HMM) info to
HSA_SVM_PROFILE if set.
Example: HSA_SVM_PROFILE=log.txt SomeApp
Change-Id: Ib6fd688f661a21b2c695f586b833be93662a15f4
During hsa initializing stage, ROCr now searches all the loaded libraries
for a symbol "HSA_AMD_TOOL_PRIORITY" and adds all those libraries to
the tools library init list. Tools libraries listed in HSA_TOOLS_LIB
env variable are also loaded in the given order and take priority
over HSA_AMD_TOOL_PRIORITY.
Change-Id: I739af42bbd777c44a9152c11e17dd69979b65e82
Adds a script to run clang-format on the latest patch so we don't
need to remember the command line.
Also applies missing formatting to the prior commit,
"Add API for available GPU memory".
Change-Id: Ida51aedc38af229f6a26e275072654860748fa93
Kernel amd-staging-drm-next branch changes GFX11 fish_colour sysfs
naming to "ip discovery". Update run_kfdtest.sh to use sysfs
gfx_target_version for ASICs that have transitioned to IP discovery
topology.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: If202a0ceeed7324364539a33661f0abcf0973f07
Ranjith Ramakrishnan
Jeremy Newton
David Francis
Sriraksha Nagaraj
Jonathan R. Madsen
Jonathan Kim
Kent Russell
Eric Huang
Ammar ELWazir
Hao Zhou
Philip Yang
Sean Keely
Laurent Morichetti
Sreekant Somasekharan
Elena Sakhnovitch
Tamima Rashid
skhatri
Graham Sider