This patch enhances compatibility for DXG environments by introducing conditional
checks for DRM operations, particularly around buffer object metadata handling
in IPC scenarios. These changes improve robustness in DXG IPC memory management
without impacting existing functionality in standard Linux environments.
Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com>
* Fix powercap default to enum for sensor_ind
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
* [SWDEV-559965] Refactor amdsmi set power cap
Modified power cap set to accept args with
optional power_cap type. Added power_cap helper
validate_and_set_power_cap(). Fixed JSON output
format.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
---------
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Co-authored-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
* Add exception handling for native tool path search
* Fix formatting in roofline benchmark code
* Fix detection of .so files
* include hip code and native tool code in standalone binary
* add fallback path for ROCM_PATH
Changes:
- Fixed `amd-smi` showing:
```console
$ amd-smi
Traceback (most recent call last):
File "/opt/rocm/bin/amd-smi", line 53, in <module>
from amdsmi_init import *
File "/opt/rocm/libexec/amdsmi_cli/amdsmi_init.py", line 38, in <module>
from amdsmi import amdsmi_interface, amdsmi_exception
File "/usr/local/lib/python3.8/dist-packages/amdsmi/__init__.py", line 24, in <module>
from .amdsmi_interface import amdsmi_init
File "/usr/local/lib/python3.8/dist-packages/amdsmi/amdsmi_interface.py", line 5581, in <module>
) -> tuple[int, int]:
TypeError: 'type' object is not subscriptable
```
This was a python3.8 issue, which is now resolved by using
`Tuple[int, int]` typing for Python 3.8 compatibility.
* Enable running tests from installation only
* Use cmake option -DTEST_FROM_INSTALL=ON to enable running tests from installation folder only
* It is not possible to run tests from build folder in this case
* This option prevents changing working directory to source folder
* Fix SourceFileLoader to import rocprof-compute main module correctly
* Install sample executables in the test folder
* fix num_xcds_cli_output test
* Fix tests
* Skip autogen. config. test and add a TODO task for re-design of this
test
* Add flexible import of source code in test_gpu_specs.py
* Update cmake to install tests/workloads folder when INSTALL_TESTS=ON
* Fix sys.argv[0] for tests
* fix live attach detach test
* refactor: centralize update_env across binaries with unit test added for testing
* removed unused includes suggested by clangd and small cleanup
* use centralized update_env in argparse as well
* review comments incorporated
* move update_env tests closer to common library
* fix: missing common:: prefix in rocprof-sys-sample
* cmake formatting
* [hip-tests] Fix Unit_Assert_Positive_Basic_KernelFail
This test was expecting a call to abort() when assertions
where hit on AMD devices. This is no longer true since
aborts from assertions are disabled unless
HIP_SKIP_ABORT_ON_GPU_ERROR is set.
This PR simplifies the test by removing the SIGABRT signal
handling (which was also undefined behaviour). Instead,
if HIP_SKIP_ABORT_ON_GPU_ERROR is set, the test is skipped.
## Motivation
Resolved: SWDEV-566226
The current implementation of agents inside of rocprof-systems keeps just the minimal necessary set of information required for populating the `info_agent` table inside of rocpd database. There is a sufficient amount of data that is being left out from database, so this change should fix that and store the additional agent information as an `extdata` row inside of `info_agent` table.
## Technical Details
This PR introduces additional filed inside of `agent` structure inside which is representing the JSON formatted string of all the additional information we can acquire about particular agent. This data is processed and added during the initial fetching of agents, and afterwards pushed inside of the database.
---------
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
* SWDEV-557412 - Incorporate proper chunk offset when remapping virtual memory (#1848)
* SWDEV-557412 - Incorporate proper offset when remapping virtual memory
* Fix condition to check if VMHeap allocation address matches a chunk address
* Move offset calculation outside if/else block
---------
Co-authored-by: JeniferC99 <150404595+JeniferC99@users.noreply.github.com>
* SWDEV-567852 - Clean-up hip::init() (#1948)
* SWDEV-559267 - Use CLPrint to DevLogPrintf with Log Level - detail debug. (#1160)
* SWDEV-548892 - Stop using ocml isinf wrapper (#1854)
* SWDEV-562708 - change default maximum SVM size to 256GB (#1731)
* SWDEV-503089 - Fix and enable disabled HIP tests from math group (#1319)
* SWDEV-503089 - Fix and enable disabled HIP tests from math group
* SWDEV-503089 - Move single precision reduced run to a common function
* SWDEV-548892 - Stop using ockl steadyctr function (#1882)
Directly use the builtin
* Implement PTL support (#1957)
* Implement PTL support
Signed-off-by: adapryor <Adam.pryor@amd.com>
(cherry picked from commit 45bc31292e7940a3b8fca044ef7df22047b95733)
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
---------
Signed-off-by: adapryor <Adam.pryor@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
* SWDEV-558080 - Add recommended granularity (#1176)
* Add recommended granularity
* Improve granularity testing
* Update based on feedback
* Fix and enable VMM tests on cuda (#1855)
* Fix and enable VMM tests on cuda
* Minor syntax fixes
---------
Co-authored-by: Rahul Manocha <rmanocha@amd.com>
* [rocprofiler-systems] Add support for ompt_callback_thread_begin (#1681)
* Add thread_begin callback
* Make OMPT callbacks that are instant have start_ts = end_ts
* SWDEV-567514: Remove default stream wait (#1977)
- when virtual map command is called
- can create deadlock
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
* Fix flaky test Unit_hipStreamAddCallback_StrmSyncTiming (#2022)
* Review comments
* skip the 3 failing tests to merge hip-tests rocm-systems PR
---------
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Signed-off-by: adapryor <Adam.pryor@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Co-authored-by: GunaShekar <agunashe@amd.com>
Co-authored-by: agunashe <ajay.gunashekar@amd.com>
Co-authored-by: Ethan Trinh <Ethan.Trinh@amd.com>
Co-authored-by: JeniferC99 <150404595+JeniferC99@users.noreply.github.com>
Co-authored-by: Victor Zhang <111778801+victzhan@users.noreply.github.com>
Co-authored-by: German Andryeyev <56892148+gandryey@users.noreply.github.com>
Co-authored-by: usrihari123 <srihari.u@amd.com>
Co-authored-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Co-authored-by: anujshuk-amd <anujshuk@amd.com>
Co-authored-by: itrowbri <Ian.Trowbridge@amd.com>
Co-authored-by: marantic-amd <marantic@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
Co-authored-by: cadolphe-amd <chris.adolphe@amd.com>
Co-authored-by: Karthik Jayaprakash <54370791+kjayapra-amd@users.noreply.github.com>
Co-authored-by: Matt Arsenault <Matthew.Arsenault@amd.com>
Co-authored-by: Todd tiantuo Li <88386084+lttamd@users.noreply.github.com>
Co-authored-by: amilanov-amd <Aleksandar.Milanov@amd.com>
Co-authored-by: Adam Pryor <61172547+adam360x@users.noreply.github.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: AidanBeltonS <abeltons@amd.com>
Co-authored-by: Rahul Manocha <153310294+manocharahul@users.noreply.github.com>
Co-authored-by: Rahul Manocha <rmanocha@amd.com>
Co-authored-by: Kian Cossettini <Kian.Cossettini@amd.com>
Co-authored-by: Shadi Dashmiz <94885391+shadidashmiz@users.noreply.github.com>
Co-authored-by: Ioannis Assiouras <38722728+iassiour@users.noreply.github.com>
Co-authored-by: Ajay GunaShekar <86270081+agunashe@users.noreply.github.com>
WSL uses the call just for the thread wake-up, however under Windows
KMD needs the actual value (SWDEV-568592). The interface is changed
to avoid programming of a modified write_ptr value, which somewhat
changes the client's logic.
Changed ipc_sock_server_conns_ map's value type to size_t. Previous
type of int caused allocations of sizes greater than 2GB to overflow,
causing the message len to be stored as a negative value, preventing the
IPC server from exporting dmabuf file descriptors, which lead to hangs.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
* kfdtest: Replace pthread with std::thread
Modify concurrent kfdtest to use std::thread
instead of pthread, eventually modify KFDTestLaunch
to take in a member function of test instance
instead of static function.
Convert KFDQMTest to pass in member function for
multi-gpu kfdtest.
* kfdtest: Convert KFDPerfCountersTest to use std::thread
Convert KFDPerfCountersTest to use std::thread for
multi-gpu kfdtest.
* kfdtest: Convert KFDGraphicsInterop to use std::thread
Convert KFDGraphicsInterop to use std::thread for
multi-gpu kfdtest.
* kfdtest: Convert KFDGWSTest to use std::thread
Convert KFDGWSTest to use std::thread for
multi-gpu kfdtest.
* kfdtest: Convert KFDCWSRTest to use std::thread
Convert KFDCWSRTest to use std::thread for
multi-gpu kfdtest.
* kfdtest: Convert KFDEventTest to use std::thread
Convert KFDEventTest to use std::thread for
multi-gpu kfdtest.
* kfdtest: Convert KFDExceptionTest to use std::thread
Convert KFDExceptionTest to use std::thread for
multi-gpu kfdtest.
* kfdtest: Convert KFDLocalMemoryTest to use std::thread
Convert KFDLocalMemoryTest to use std::thread for
multi-gpu kfdtest.
* kfdtest: Convert KFDMemoryTest to use std::thread
Convert KFDMemoryTest to use std::thread for
multi-gpu kfdtest.
* kfdtest: Convert KFDSVMRangeTest to use std::thread
Convert KFDSVMRangeTest to use std::thread for
multi-gpu kfdtest.
* kfdtest: Convert KFDHWSTest to use std::thread
Convert KFDHWSTest to use std::thread for
multi-gpu kfdtest.
* kfdtest: Remove pthread multigpu test structure
Remove older multi-gpu test framework which
uses pthread.
Core dumps are not supporetd for gfx110x, but should be possible for
gfx115x. The current code disables core dumps completly for all gfx11xx
agents, relax this to allow gfx115x.
* clr: Use graph segment scheduling to process HIP Graphs
* Add a broader path to use capture packet capture for all topologies
* Refactor code
* Use DEBUG_HIP_GRAPH_SEGMENT_SCHEDULING to toggle new vs classic path,
Enabled by default
* clr: Few fixes and improvements
* clr: Detect complex graphs to take classic path
* Use DEBUG_HIP_GRAPH_SEGMENT_SCHEDULING=2 to force segment scheduling
path
* clr: Fix a cornercase stack corruption
* clr: Track commands of segments instead of snapshots
* clr: Fix Batch dispatch logic
* Track fence_dirty_ flag for command of other streams
* Dependency resolution markers can now accomodate dirty fence on cross
streams
---------
Co-authored-by: Ioannis Assiouras <Ioannis.Assiouras@amd.com>
Co-authored-by: Godavarthy Surya, Anusha <agodavar@amd.com>
## Motivation
The idea is to unify the way and place where we store our traces. Current implementation uses `trace_cache` for rocpd traces, but perfetto is in lined inside of each module. This change allows us to have a single point in code where we will collect data, process it and store it in the desired format. This means that we can declutter the code further and have single point of responsibility and single point of failure.
## Technical Details
New `processor` (perfetto_post_processing.cpp) is added to the `trace_cache` which purpose is to use the cached data to populate perfetto tracks. Cache manager is responsible for keeping the instance of this processor and for its lifetime.
When doing this ticket, I also noticed the program would SEGFAULT when ROCPROFSYS_ROCM_DOMAINS=roctx even though the docs tell us we can do this. Went ahead and fixed that.
Also noticed that timemory push/pop in rocprofiler-sdk.cpp was always using category::rocm_marker_api instead of CategoryT. Fixed that as well.
* Enable HOST ompvv runtime-instrumentation ctests
* Fix rocprofiler-systems-avail-regex-negation test failure
* Exclude problematic function from instrumentation
* Make push pop skip an env option for ctests
* Remove SKIP_PUSH_POP_CHECK from argument parse
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
---------
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
- Added `binary-rewrite-cleanup` and `runtime-instrument-cleanup` tests that remove instrumented binaries and output directories using `cmake -E rm -rf`
- Implemented CMake test fixtures (`FIXTURES_SETUP` and `FIXTURES_CLEANUP`) to establish proper test ordering:
- `binary-rewrite` sets up the `binary-rewrite-fixture`
- `binary-rewrite-run` and validation tests require this fixture
- `binary-rewrite-cleanup` performs cleanup for this fixture
- Same pattern applied for `runtime-instrument`
- Extended `ROCPROFILER_SYSTEMS_ADD_PYTHON_TEST` to accept `FIXTURES_REQUIRED` parameter
- Updated validation tests to require appropriate cleanup fixtures based on test name pattern matching
- Added fixture requirements to Python code-coverage tests
Update the format script to use absolute path for clang-format-diff.py
instead of relative path. This ensures the script works correctly
regardless of the current working directory when executed.
- Change from './clang-format-diff.py' to '${root}/projects/rocr-runtime/clang-format-diff.py'
- Improves script reliability and portability
Signed-off-by: Honglei Huang <honghuan@amd.com>
* libhsakmt/virtio: change shmem size to 80
Some DGPU props have a lot of information,
so it is necessary to increase the size of shmem.
Signed-off-by: Honglei Huang <honghuan@amd.com>
* libhsakmt/virtio: use BO handle instead of pointer in memory registration
Change vhsakmt_map_to_gpu() return type from void* to vhsakmt_bo_handle
to properly handle buffer object information. This allows access to
both the host address and resource ID needed for memory registration.
Signed-off-by: Honglei Huang <honghuan@amd.com>
* libhsakmt/virtio: Improve memory mapping logic
- Update vhsakmt_mappable() to check NoAddress flag and require HostAccess
- Remove mappable checks in cpu_map/unmap to allow all BOs to be mapped
- Set BO flags properly in vhsakmt_alloc_memory and scratch memory creation
- Ensure scratch memory is correctly flagged for proper handling
Signed-off-by: Honglei Huang <honghuan@amd.com>
* libhsakmt/virtio: add no svm mode for libhsakmt virtio
Add no svm mode for libhsakmt virtio driver, in no svm mode userptrs
need UMD to manage, so add interval tree to manage them.
New Features:
- Add augmented red-black tree based interval tree implementation
* Implement RB-tree insertion, deletion, and color balancing
* Provide interval query for fast overlapping range lookup
* Based on Linux kernel's augmented rbtree implementation
- Improve userptr memory management
* Use interval tree to efficiently track userptr memory regions
* Support finding registered memory within given address ranges
* Optimize memory mapping and unmapping performance
Signed-off-by: Honglei Huang <honghuan@amd.com>
---------
Signed-off-by: Honglei Huang <honghuan@amd.com>
arvindcheru
hongkzha-amd
ywang103-amd
Ammar ELWazir
Maisam Arif
vedithal-amd
Charis Poag Jones
habajpai-amd
Yazen AL Musaffar
harkgill-amd
Jaydeep
Fábio Mestre
Jatin Chaudhary
German Andryeyev
Alysa Liu
Sunday Clement
Ben Richard
Kian Cossettini
Milan Radosavljevic
Jan Stephan
Todd tiantuo Li
Mark Meserve
Matt Arsenault
Mythreya Kuricheti
Jin Jung
lancesix
Ioannis Assiouras
SaleelK
Bindhiya Kanangot Balakrishnan
cfallows-amd
marantic-amd
vstojilj
abchoudh-amd
Honglei Huang
Pratik Basyal