AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
8,920 Commits 3 Branches 0 Tags
93958aa8b9a8b0c19ea57ed15cddc668bef0ffa9
Commit Graph

8920 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Trowbridge, Ian 19fe192e8f Add copyright disclaimer for new files (#16) 2025-06-17 10:34:21 -05:00
Elwazir, Ammar 8dad9518dc Add test target to the default build target (#117) 
Signed-off-by: zichguan-amd <zichuan.guan@amd.com>
Co-authored-by: zichguan-amd <zichuan.guan@amd.com>
 2025-06-17 10:13:37 -05:00
David Galiffi 244c193a57 Unhandled enum in switch statement (#247) 
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2025-06-17 09:57:27 -04:00
Elwazir, Ammar aeb1621c2b [SDK] Support CMake option for using internal RCCL tracing + (temporary) enable in CI (#457) 
* Temp: disable RCCL tracing

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Adding option to disable rccl tracing from CMake

* Update codeql.yml

* Misc updates

- ROCPROFILER_BUILD_RCCL -> ROCPROFILER_INTERNAL_RCCL_API_TRACE
- env.EXTRA_TEMP_CMAKE_OPTIONS -> env.GLOBAL_CMAKE_OPTIONS
- add (advanced) option ROCPROFILER_INTERNAL_RCCL_API_TRACE

* Fix rocprofiler::sdk::get_enum_label

- missing enum labels for HIP_RUNTIME_API_TABLE_STEP_VERSION > 8

* Update tests/rocprofv3/advanced-thread-trace/CMakeLists.txt

- improve various aspect of cmake -- particularly echoing where attdecoder_LIBRARY was found

* Use CMAKE_MESSAGE_INDENT

- add prefix to cmake messages to help indicate where messages are coming from
- make find_package(Python3 ...) QUIET for bindings

* Fix rocprofiler::sdk::get_enum_label

- handle HSA_AMD_EXT_API_TABLE_MAJOR_VERSION

* Fix rocprofv3 message for att library path

* Fix tests/rocprofv3/advanced-thread-trace/att_input.yml config

* Fix rocprofv3 check_att_capability + soversion/version library resolution

- Account for ROCPROF_ATT_LIBRARY_PATH in env in check_att_capability
- Add resolve_library_path
  - supports resolution of library names to SOVERSION and VERSION paths

* Fix python linting error (unused import)

---------

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
 2025-06-17 08:32:54 -05:00
Bhardwaj, Gopesh 3e43b1f019 Adding rocpd documenation (#449) 
* Adding rocpd docuemenation

* rocpd format

* CHANGELOG update and indexing

* Fixing links

* format fixes

* fixing table

* major edits

* fixed logical error

* fixing rocprofv3 avail
 2025-06-17 15:41:53 +05:30
David Yat Sin 649ec63a4f rocrtst: Reduce host memory limit to 90% 
Further reduce upper bound for rocrtstFunc.Memory_Max_Mem
as previous limit of 95% can still trigger OOM killer.
 2025-06-16 21:02:20 -04:00
David Yat Sin 488cfd467c rocr: Always send free scratch notifications 
Always send notification to profiler tools when scratch memory is freed.
 2025-06-16 17:39:33 -04:00
Vladimir Indic 451be8a600 [PC Sampling] Separate counts for issued and stalled samples (#756) 2025-06-16 15:09:21 -06:00
Kandula, Venkateshwar reddy 41cd5d6531 [BUG FIX] [Counter Collection] SWDEV-523582- Use a map to differenciate xcc_sample_count wrt event id. (#99) 
* use a map to differenciate xcc_sample_count wrt event id.

Change-Id: Ie1f2e8466edb244574686d49008125dc9f4e7efd

* Format.

Change-Id: I668c6ed448d8610d9d66f9cf77d0d27d7cf4e8b6

* use blockinfo to get xcc_sample_count.

Change-Id: I066a10e3185df4c8767d4f8eae59aca1f78f5284

* use EventAttribDim for xcc_sample_count.

Change-Id: Ide3707934b5b42c0462ea332b27f6e2e4fc0449f

---------

Co-authored-by: Venkateshwar Reddy Kandula <vkandula@amd.com>
 2025-06-16 16:09:13 -05:00
vedithal-amd 7c0ffd14a9 Print counter list in DEBUG level (#758) 2025-06-16 16:53:00 -04:00
Alysa Liu 3b450397d6 rocr: Fix wrong sizeof argument 
Update size calculation from 2 * sizeof(void*) to 2 * sizeof(uint64_t)

Signed-off-by: Alysa Liu <Alysa.Liu@amd.com>
 2025-06-16 13:11:07 -04:00
David Galiffi eaaec2cc3b Cleanup of Dyninst build dependencies (#238) 
- Refactor elfutils build folders. Move build artifacts to the "external" subfolders
- Remove reference to unused DYNINST configuration
- Declare Dyninst interfaces with other external declarations
- Updated cmake warning message
- Update the deprecation warning for "DYNINST_BUILD_${dep}" to make it clearer that the option is being translated to the new option, "ROCPROFSYS_BUILD_${dep}"
 2025-06-13 17:19:46 -04:00
David Galiffi 8535da17c8 Removing dyninst builds from CI docker files (#249) 
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2025-06-13 17:16:01 -04:00
David Galiffi 6dd1ee78bf Add perfetto validation to rccl ctests (#246) 
Check for the "RCCL Communication Send / Receive" data counters

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2025-06-13 17:09:49 -04:00
Baraldi, Giovanni b1637869b3 Adding LDS Bank conflict metric to MI300 (#456) 
Adding LDS Bank conflict metric to MI3

Co-authored-by: Giovanni Baraldi <gbaraldi@amd.com>
 2025-06-13 19:28:57 +02:00
Ranjith Ramakrishnan 59468e3f78 SWDEV-534264 - Add liboam.a to static rocm-smi package 
liboam.a was missing in static rocm-smi package and resulting in compilation error on appliction that use rocm-smi
 2025-06-13 12:09:41 -05:00
Sunday Clement 31b6474801 rocr: Remove Recursive Include 
Removed unnecessary header inlude in file to prevent circular include.

Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
 2025-06-13 12:29:52 -04:00
Sunday Clement 06efa50c09 rocr: Fix Recursive Include in header files 
scratch_cache.h includes amd_gpu_agent.h which then again includes
scratch_cache.h, this has now been fixed removing the unecessary
header include.

Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
 2025-06-13 12:29:52 -04:00
ywang103-amd b8dd6d049d format the code after mem chart's fix of test (#753) 2025-06-13 12:03:42 -04:00
Jason Bonnell da6bf4b5c9 Move pr template file (#746) 
* updated documentation wording, added cherry pick option for PR type

* moved pull_request_template to base .github directory
 2025-06-13 11:37:56 -04:00
vedithal-amd fa1e9965f8 fix test_gpu_specs.py (#752) 2025-06-13 10:01:59 -04:00
ywang103-amd bb0c417871 fix broken test with --cols options (#750) 2025-06-12 19:45:24 -04:00
Arif, Maisam 5cc6c1ca1c Revert "SWDEV-534264 - Add liboam.a to static package" 
This reverts commit ff7561607e.
 2025-06-12 16:26:19 -05:00
jamessiddeley-amd 667128e3c7 Fix: Add explicit includes for assert.h and thread in sample files (#751) 
* Fix: Add explicit includes for assert.h and thread in sample/vcopy.cpp

The HIP/CLR change e3cb5399c removed transitive inclusion  
of standard headers like assert.h from hip_runtime.h.  
This caused build failures in rocprof-compute samples.  

This commit explicitly includes <assert.h> and <thread>  
in vcopy.cpp to resolve potential missing definitions.  


Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>

* Update vsequential_access.cpp

Added assert and thread imports

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>

* Update vrandom_access.cpp

Added assert import

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>

* Update vsequential_access.cpp

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>

---------

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>
 2025-06-12 17:03:48 -04:00
Jason Bonnell da326048b9 add pull_request_template.md (#237) 
* add pull_request_template.md

* Update .github/PULL_REQUEST_TEMPLATE/pull_request_template.md

Co-authored-by: David Galiffi <David.Galiffi@amd.com>

* fix markdown linting errors

* Update .github/PULL_REQUEST_TEMPLATE/pull_request_template.md

Co-authored-by: David Galiffi <David.Galiffi@amd.com>

* moved pull_request_template.md to base /.github/ directory

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
 2025-06-12 16:13:48 -04:00
Vignesh Edithal 6054b3b7fd Bugfix for PR #744 2025-06-12 16:09:15 -04:00
vedithal-amd d27ee69b52 Change default rocprof to rocprofv3 (#748) 
* Revert of https://github.com/ROCm/rocprofiler-compute/pull/738

* Change default rocprof backend interface to rocprofv3

* Add MI 350 support in documentation

* Added known issue that MI 100 profiling will not work unless rocprofv1
  is explicitly opted in

* Remove MI 50 soc gfx python class since MI 50 is not supported
 2025-06-12 15:45:11 -04:00
David Yat Sin 3c0af843e3 rocr: Remove scratch_backing_memory_byte_size 
scratch_backing_memory_byte_size was originally removed, and then put
back in 02b38d0614. This was because it
was used by rocgdb. rocgdb code has been updated to not use this field.
Bumped _amdgpu_r_debug for the ABI change.
 2025-06-12 15:33:47 -04:00
vedithal-amd cdd41dee40 Remove rocscope related code and add deprecation warning for mongo db usecase (#744) 
* Remove rocscope related code

* Add deprecation warning for database update mode which is used for grafana and mongodb functionality
 2025-06-12 14:21:24 -04:00
Verma, Saurabh d046917427 Readme update for open-sourcing (#84) 
* Initial commit

Change-Id: I24703941cda0d009f1eb4dac8846195fac9ebb24

* Updated "Supported Architectures and Counter Blocks"

Change-Id: Ia7cdc46d4623d7a6664550ee4e0ab9425a3ac52f

* Added HSA links

Change-Id: Id506362f6d913dc94943a6ee047e25c00cf85f53

* addressing review comments

Change-Id: Iec35efc55e49f5b9c57c2de455fbef2afed80a77

* Minor change

Change-Id: I0bfdc774dcc42aa01b2f3dfc24d97cf301e364d7

* minor update

Change-Id: I970d5fa416a1c3e4c3fc37dde5269a37f02a4c60
 2025-06-12 22:07:03 +05:30
David Galiffi 1cd989a110 Copyright Header Compliance (#745) 
- for SWDEV-537492
 2025-06-12 12:02:58 -04:00
Trowbridge, Ian 72b97a8b7e Removed roc_video_dec files due to reoccurring errors (#439) 
* Removed roc_video_dec files due to reoccurring errors

* Added back rocDecCreateVideoParser

* Fix remaining errors with rocdecode.cpp
 2025-06-12 10:49:08 -05:00
Elwazir, Ammar 5c6b03801d Changing the Github Runner Sets (#446) 
* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml
 2025-06-12 10:32:01 -05:00
David Yat Sin 17b8f9b24d cmake: Remove unused file 2025-06-12 10:38:58 -04:00
David Yat Sin 24ce840732 rocr: Remove support for Kaveri GPUs 
Kaveri GPUs are EoL
 2025-06-12 10:38:58 -04:00
David Yat Sin 96d0f07b15 rocr: Fix compile warning when using clang 2025-06-12 10:38:58 -04:00
jamessiddeley-amd f004aeebe9 fixed long kernel names cut off in --kernel-names option (#728) 
* reformatted kernel roofline PDF to use table

* restored kernel symbol icons

* enhance code readability

* restored cell text wrap

---------

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>
 2025-06-12 10:23:40 -04:00
jamessiddeley-amd 97dad3f7f1 increased utils.py code coverage to ~84% (#742) 
* code coverage file cover: utils.py

* added code coverage 82% for utils.py

* reverted unused_code rebase
 2025-06-12 10:21:40 -04:00
David Galiffi 877fa671cc Updated Dockerfile.ubuntu (#245) 
Using miniforge instead of miniconda

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2025-06-12 10:19:01 -04:00
David Galiffi d9381c3e0a SWDEV-525474 - Fixed CMake 4 configuration error (#244) 
Update Timemory / GOTCHA modules

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2025-06-12 10:14:55 -04:00
Bhardwaj, Gopesh eca6739e13 Adding tests for code coverage (#82) 
* Adding tests for code coverage

* integration tests

* Fixing gtest dependencies

* Removing gmock linkage

* build fixes

* Fixing Analyze job

* CMake updates

* Fixing PSDB

* Addressing feedback

* Adding licenses

* Addressing feedback

* updating dashboard

* more API tests

* Addressing feedback

* correcting Macro

* preloading libintercept
 2025-06-12 19:13:44 +05:30
David Yat Sin ed7a2104ef Remove unnecessary dependency on hsakmt 2025-06-12 09:36:19 -04:00
Pranjal Swarup c00070ddbf Change docker scripts to use miniforge instead of miniconda (#242) 2025-06-11 23:43:34 -04:00
Alysa Liu 77b86ca908 rocr: Prevent int overflow in arithmetic operation 
Cast range->x and range->y to uint64_t before performing multiplication

Signed-off-by: Alysa Liu <Alysa.Liu@amd.com>
 2025-06-11 19:36:36 -04:00
David Yat Sin df5d66eae5 rocr: document pseudo-code for scratch reclaim 
Document CP FW and ROCr pseudo-code for asynchronous reclaim.
No code change.
 2025-06-11 16:19:59 -04:00
David Galiffi 28bee27253 Fix OpenMP-Target ctest (#241) 
Test is missing from rocm-7.0 stack because of a HIP version check.
In these builds, hip_version.h is still reporting 6.5.0.
This check was originally put in to skip the test on older versions
of ROCm, which should no longer be required

- For SWDEV-537718

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
 2025-06-11 16:00:48 -04:00
cfallows-amd 0415bb9740 Add roofline cli_generate_plot method (#737) 
Add option to print out roofline plot in terminal using plotext.
Takes in one datatype and returns the str from plot.build() which contains the visual plot of roofline analysis for said datatype.

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
 2025-06-11 15:38:21 -04:00
Ranjith Ramakrishnan ff7561607e SWDEV-534264 - Add liboam.a to static package 
liboam.a was missing in static package. The library is gettting created but not packaged.
Fixed the same
 2025-06-11 13:45:21 -05:00
Elwazir, Ammar 67fee2f03f Update kws-caller.yml (#103) 2025-06-10 18:49:16 -05:00
vedithal-amd dcbc7b15e2 Mount rocprofiler-sdk directory in docker (#743) 2025-06-10 16:43:16 -04:00