提交線圖

1206 次程式碼提交

作者 SHA1 備註 日期
vedithal-amd 7c0ffd14a9 Print counter list in DEBUG level (#758) 2025-06-16 16:53:00 -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
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
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
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
David Galiffi 1cd989a110 Copyright Header Compliance (#745)
- for SWDEV-537492
2025-06-12 12:02:58 -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
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
vedithal-amd dcbc7b15e2 Mount rocprofiler-sdk directory in docker (#743) 2025-06-10 16:43:16 -04:00
cfallows-amd 24d3e7eecd Update roofline binaries (#741)
Update roofline binaries from rocm-amdgpu-bench
- uses hip to find number of CUs dynamically instead of hardcoded values in table

Remove duplicate AI plot points printing
- only print ai points once on plot since we are measuring using total flops and value is same
- remove datatype from legend labels

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-06-10 15:43:56 -04:00
cfallows-amd ce3ef1400e Fix load_kernel_top arg for GUI analyze mode (#740)
--gui option for analyze mode failing due to missing arg in load_kernel_top call in pre_processing

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-06-10 11:27:03 -04:00
vedithal-amd a1ef3425c6 Revert default interface to rocprof v1 (#738)
* Add deprecation warning for rocprof v1 / v2 / v3 interfaces to use
  rocprofiler-sdk interface
2025-06-09 16:39:11 -04:00
Fei Zheng 96aa04fb13 TUI improvement (#732) 2025-06-09 11:29:10 -06:00
vedithal-amd 721053bd03 Bugfix for rocprofiler sdk interface not working in MI 200 (#733) 2025-06-09 12:33:25 -04:00
Jason Bonnell 8acfe40113 add pull_request_template.md (#729)
* add pull_request_template.md

* add bug fix or feature checkboxes

* Address feedback and align more with sdk implementation

* Add other category under PR type if needed
2025-06-09 10:24:59 -04:00
Fei Zheng e5b31af2a4 CLI: enable mem_chart for single run (#643) 2025-06-06 16:15:56 -06:00
Pratik Basyal ed05c00103 Formatting issue in code block and TOC fixed for PC Sampling (#731)
* Formatting issue in code block and TOC fixed

* Performance model reverted
2025-06-06 16:16:55 -04:00
vedithal-amd 25f21715bc Add SQLite3 package to test docker container (#730) 2025-06-06 14:55:32 -04:00
Fei Zheng d756aeb3fd Support stochastic pc sampling 2025-06-06 12:43:52 -06:00
xuchen-amd ca0cdaf948 Introduce rocprof-compute TUI (Text User Interface) (#682)
* rocprof-compute TUI (Text User Interface) - providing users interactive analyze experience with visuals.

* Analyze results with tables, charts, plots.

* Add menu bar, terminal, directory dialog. Improve logging and ui.

* Add display config file to manipulate result categorization.

* Add support for recently opened dirs.

* Update licensing and version.
2025-06-04 17:06:08 -04:00
Fei Zheng ab6665d317 Fix peak flops of F8 I8 F16 and BF16 on MI300 2025-06-04 12:51:46 -06:00
ywang103-amd e5c7d4795a Tcc new format input yaml (#723) 2025-06-04 12:24:57 -04:00
xuchen-amd f0fad19e8b Add chip specs (#681)
* Add perfmon config spec, enhance memory partition info.

* Add gfx950 perfmon config.

* Add High Freq variants in gfx942.

* Add backup detection methods for gpu model.

* Improve get_num_xcds logic by adding detection of 1to1 arch-to-compute_partition logic.

* Add default compute partition settings spx:8 for when gpu_model=None.

* Update gpu spec tests.

* Add backup compute partition detection.

---------

Signed-off-by: xuchen-amd <xuchen@amd.com>
2025-05-29 16:35:34 -04:00
Ben Richard 45296ceb46 Upgrade to Dash 3.0 (#719) 2025-05-29 14:36:03 -04:00
cfallows-amd bbe2e17b80 Rename roofline bins (#717)
Rename roofline bins, remove rocm version in naming. Change method for binary search.

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-05-28 14:55:51 -04:00
anisha-amd 783193c75f adding L2 model with updated legend and removal of large images (#718)
* adding L2 model with updated legend and removal of large images

* changed image name to perf_model
2025-05-28 14:03:47 -04:00
cfallows-amd cb2d928ecf Add F4 F6 to roofline for MI350 series (#709)
Add roofline bins with FP4 FP6 datatypes enabled for gfx950 arch

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-05-26 18:36:31 -04:00
jamessiddeley-amd 09b6ef4508 Fixed duplicate keys in analysis_configs yamls (#707)
* fixed duplicate keys in analysis_configs yamls

* Fix: removed TODO comment

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

---------

Signed-off-by: James Siddeley <james.siddeley@amd.com>
2025-05-20 13:12:46 -04:00
Ben Richard 41dd4aab90 Update illegal character check for profile name (#703) 2025-05-16 15:45:16 -04:00
cfallows-amd 43dbf38b27 Check mode during soc init for roofline (#705)
Check mode before creating roofline object- skip if only printing specs

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-05-16 12:54:53 -04:00
vedithal-amd 7b755fcd86 Fix MI350 tests (#706)
- TCC counter collection tests are still failing due to recent
  rocprofiler-sdk change
2025-05-15 13:37:55 -04:00
Vignesh Edithal 6522fe954b Add James Siddley to code reviewers 2025-05-15 12:14:39 -04:00
vedithal-amd 5cb86e31fc Implement interface to rocprofiler sdk (#695)
* Setting ROCPROF=rocprofiler-sdk environment variable will use rocprofiler-sdk C++ library instead of rocprofv3 python script

* Add runtime option --rocprofiler-sdk-library-path to use custom version of rocprofiler sdk library
    * Add --rocprofiler-sdk-library-path conftest option for tests

* Setup appropriate environment variables to inject rocprofiler sdk code to user command
    * Add env. vars. for counter collection and filtering
    * Add env. vars. for pc sampling

* Use python bindings to list counters supported by rocprofiler sdk
2025-05-13 10:48:21 -04:00
cfallows-amd d527d77337 Fix setting roofline-data-type option in both profile and analyze modes (#702)
Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-05-12 23:02:47 -04:00
xuchen-amd 4e24b2c60a Improve gpu spec tests using chip ids. (#701) 2025-05-09 11:48:25 -04:00
vedithal-amd dbb7f4d493 Use gpu model series instead of gpu model name for testing (#696) 2025-05-06 18:23:08 -04:00
vedithal-amd abd500593b Fix PC sampling analysis config issue (#697) 2025-05-06 18:22:15 -04:00
Ben Richard 35493f440c Avoid crash when profiling data not generated (#694)
* Avoid crash when profiling data not generated

-Handle case where program has no kernel launches
-Improve error messages
-Avoid roofline when profiling data is missing

Signed-off-by: benrichard-amd <ben.richard@amd.com>

* Update other soc_gfx files to catch missing pmc_perf.csv

* Fix formatting

* Fix incorrectly ordered imports

---------

Signed-off-by: benrichard-amd <ben.richard@amd.com>
2025-05-05 16:09:48 -04:00
cfallows-amd 41e73650d5 Enable roofline for MI350 series (#677)
Rework of roofline binaries generated from rocm-amdgpu-bench
- removed arch identifier in bin name
- removed rocm5 bins altogether

Updated required distros for roofline
- updated distro checks and bin naming
- moved up ubuntu20.04->22.04 and sles15.3->15.6 per rocm support

Enabled ctests for mi350 for test_roof_*
- removed mi350 series check to skip these specific tests

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-04-28 16:08:23 -04:00
cfallows-amd ad17c4d587 Update CODEOWNERS (#680)
Add rp-compute technical writer directly for any documentation review.
Remove existing packaging review requests for single user; every repo owner should be notified.

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-04-28 16:05:51 -04:00
Daniel Su b77fcf575e Set rocprofV3 agent-index to absolute (#675)
Signed-off-by: Daniel Su <danielsu@amd.com>
2025-04-28 15:38:07 -04:00
xuchen-amd 85bfa73e2c Add test for gfx942 number of xcds. (#674)
* Add test for 9fx942 number of xcds.

* Improve the structure of mi gpu specs, add num_xcds_spec_class test.

* Add to ctest.

---------

Signed-off-by: xuchen-amd <xuchen@amd.com>
2025-04-28 11:29:14 -04:00
xuchen-amd ee73c2a119 process hip trace output. (#654)
Signed-off-by: xuchen-amd <xuchen@amd.com>
2025-04-22 18:31:47 -04:00
xuchen-amd f145f89e30 Patch in new rocprofv3 metrics. (#679) 2025-04-22 18:30:26 -04:00
cfallows-amd 346c7e452a Update runner distro in Formatting workflow (#678)
Update formatting workflow to use 22.04. 20.04 deprecated last week.

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-04-22 16:14:15 -04:00