Skip to content

Introduce unified test framework for benchmark and functional tests#2803

Closed
lajagapp wants to merge 42 commits intomainfrom
users/lajagapp/add-miopen-driver-test
Closed

Introduce unified test framework for benchmark and functional tests#2803
lajagapp wants to merge 42 commits intomainfrom
users/lajagapp/add-miopen-driver-test

Conversation

@lajagapp
Copy link
Copy Markdown
Contributor

@lajagapp lajagapp commented Jan 7, 2026

Motivation

The existing benchmarks/ directory was originally designed only for performance benchmarks, but as testing needs have evolved, we need support for multiple test types:

  1. Benchmark tests: Performance regression detection against LKG (Last Known Good) baselines
  2. Functional tests: Extended correctness validation with detailed reporting

This PR restructures the testing infrastructure to accommodate both test types under a unified framework, improving maintainability, code reuse, and extensibility.

Naming Note: "Benchmark tests" could also be called "performance tests" - they measure performance and detect regressions. Current naming aligns with existing conventions.

Technical Details

1. Directory Restructure (with git history preservation)

Renamed: benchmarks/extended_tests/
New structure: Updated in extended_tests/README.md

2. Key Changes

Shared Infrastructure

  • Renamed BenchmarkClientTestClient for use across all test types
  • Moved utils/ to top-level (extended_tests/utils/) for sharing across test types
  • Updated all import paths in benchmark scripts to reflect new structure

Functional Test Framework (New)

  • scripts/: Base class and actual test file for functional tests
  • configs/: Shared functional test configuration
  • functional_test_matrix.py: Test matrix for functional tests

Documentation Updates

  • extended_tests/README.md: Framework overview comparing benchmark vs functional tests
  • extended_tests/benchmark/README.md: Benchmark-specific documentation
  • extended_tests/functional/README.md: Functional test documentation
  • extended_tests/utils/README.md: Updated paths from benchmarks/ to extended_tests/

CI Integration

  • Updated fetch_test_configurations.py: New module path (extended_tests.benchmark.benchmark_test_matrix)
  • Updated configure_ci_test.py: Support for functional test matrix
  • Both benchmark and functional tests run on nightly CI only
  • Added CI workflow for extended functional tests (test_extended_functional_tests.yml)

Test Plan

Benchmark Tests:

  • Verified all existing benchmark tests still work with new paths
  • Confirmed imports updated correctly (extended_tests.benchmark...)

Functional Tests:

  • Ran test_miopendriver_conv.py locally on gfx94x GPUs
  • Verified correct parsing of MIOpenDriver output
  • Confirmed pass/fail detection and summary tables

Results

Nightly-CI run with this PR - https://github.com/ROCm/TheRock/actions/runs/21151021971

Next Steps

  • Add more functional tests for other libraries
  • Rename "benchmark tests" to "performance tests" for clarity (separate PR if needed)

Renamed benchmarks/ to test_framework/ with support for benchmark,
and functional tests.

-  Framework restructure (benchmarks → test_framework)
-  Test type organization (benchmark, functional)
-  Shared utilities moved to framework level
-  benchmark_client.py → test_client.py rename
-  benchmark_test_matrix.py → benchmark_matrix.py rename
-  Functional test base class (functional_base.py)
-  Updated documentation (main + benchmark READMEs)
-  Updated all imports

Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Created FunctionalBase class and MIOpen driver convolution test.
Features: two-table display, 4 status types, JSON configs, accurate
per-command parsing with 'Verifies OK' detection, GitHub Actions
integration. Consistent with benchmark test patterns.

Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
log.error(f"Error running command: {e}")
f.write(f"ERROR: {e}\n\n")

log.info("Test execution complete")
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

more details to this log pls

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done!

test_results = []

try:
with open(self.log_file, "r") as f:
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why not add the data to JSON previously? instead of having to parse a .txt file which may be prone to error

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done! I've refactored the code to write test results directly to JSON during execution in run_tests(), eliminating all the complex regex-based log parsing in parse_results(). Now parse_results() simply reads the JSON file - much cleaner, more maintainable, and less error-prone.

Comment on lines +156 to +183
if cmd_match:
# Extract content after this command until next command or end
start_pos = cmd_match.end()
next_cmd_match = re.search(
r"\nCommand:", suite_content[start_pos:]
)
if next_cmd_match:
cmd_section = suite_content[
start_pos : start_pos + next_cmd_match.start()
]
else:
cmd_section = suite_content[start_pos:]

# Check return code in THIS command's section only
return_code_match = re.search(
r"Return code:\s*(\d+)", cmd_section
)
if return_code_match:
return_code = int(return_code_match.group(1))
status = "PASS" if return_code == 0 else "FAIL"
elif "PASSED" in cmd_section:
status = "PASS"
elif "FAILED" in cmd_section or "ERROR" in cmd_section:
status = "FAIL"
else:
status = "FAIL" # Unknown result, assume fail
else:
status = "FAIL" # Command not found in log
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think a lot of this can be avoided by using JSON

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done!

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

just curious, are functional tests run once a day in rocm-ci?

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

^

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We didn't run these functional & benchmark tests in rocm-ci and these were tested in QA validation. We were running only limited unit tests in rocm-ci previously.


from github_actions_utils import *
from benchmarks.benchmark_test_matrix import benchmark_matrix
from test_framework.benchmark.benchmark_matrix import benchmark_matrix
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

could we perhaps be more specific than test_framework? maybe extended or a better word

test_framework is broad

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the feedback. Renamed top-level folder from test_framework to extended_tests for better clarity and updated all references accordingly.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is this needed?

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, not required. Removed now.

display_name: Display name for reports (e.g., 'MIOpen Driver Convolution')
"""
self.test_name = test_name
self.display_name = display_name or test_name.replace("_", " ").title()
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i think it's fine to have _ in the test name, no need to do replacing

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done!

Returns:
True if upload successful, False otherwise
"""
log.info("Uploading Results to API")
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can we add functional test results to the log

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Already logged! The SUMMARY section prints the full results table with all stats right before the upload (lines 274-276), so the information is already in the logs.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

no, as in:

Suggested change
log.info("Uploading Results to API")
log.info("Uploading Functional Tests Results to API")

Comment on lines +236 to +248
def get_gpu_id(self) -> str:
"""Detect GPU ID using rocminfo."""
try:
result = subprocess.run(
["rocminfo"], capture_output=True, text=True, check=True
)
# Extract GPU name (e.g., gfx90a, gfx942)
match = re.search(r"Name:\s+(gfx\w+)", result.stdout)
if match:
return match.group(1)
except (subprocess.CalledProcessError, FileNotFoundError):
log.warning("Could not detect GPU ID, assuming default")
return "unknown"
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

shouldn't this be a part of the utils?

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good catch! Moved get_gpu_id() to the shared utils module (utils/system/hardware.py) since it's common functionality that can be reused across benchmark and functional tests.

try:
exit_code = test_instance.run()
if exit_code != 0:
raise RuntimeError(f"Test failed with exit code {exit_code}")
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can we let python handle errors? in the long run, this won't be helpful as failures will just have a very broad error. better to let python do the errors in my opinion

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done! Removed try/except wrapper in run_functional_test_main(), exceptions propagate naturally with full stack traces. Added semantic TestResultError to distinguish execution vs result failures.

- Consolidate common setup and architecture in main README
- Move implementation details to benchmark/functional sub-READMEs

Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
- benchmark_matrix.py → benchmark_test_matrix.py
- functional_matrix.py → functional_test_matrix.py
- Update all imports and documentation references

Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
- Move get_gpu_architecture() to hardware.py
- Simplify display_name default

Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
- Add TestResultError for result failures vs execution errors
- Remove sys.exit() - let exceptions propagate naturally
- Add progress indicators and better error messages
- Consistent exception pattern across all test files

Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
@HereThereBeDragons
Copy link
Copy Markdown
Contributor

The reaction to my review seem AI created and in some place absolutely wrong.
I will not further review this PR until you, @lajagapp, manually reviewed it and fixed it.

@lajagapp
Copy link
Copy Markdown
Contributor Author

The reaction to my review seem AI created and in some place absolutely wrong.
I will not further review this PR until you, @lajagapp, manually reviewed it and fixed it.

I’ve addressed all the comments except for this one, which I’m checking now - #2803 (comment).
If there are any specific responses that still need clarification or further fixes, please let me know and I will update them accordingly.

The reaction to my review seem AI created and in some place absolutely wrong. I will not further review this PR until you, @lajagapp, manually reviewed it and fixed it.

Hi @HereThereBeDragons - I’ve reviewed and addressed all the comments.
If any response needs further correction or clarification, please let me know and I will update it.

lajagapp and others added 3 commits January 20, 2026 16:17
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
@stellaraccident
Copy link
Copy Markdown
Collaborator

The reaction to my review seem AI created and in some place absolutely wrong.
I will not further review this PR until you, @lajagapp, manually reviewed it and fixed it.

I’ve addressed all the comments except for this one, which I’m checking now - #2803 (comment). If there are any specific responses that still need clarification or further fixes, please let me know and I will update them accordingly.

The reaction to my review seem AI created and in some place absolutely wrong. I will not further review this PR until you, @lajagapp, manually reviewed it and fixed it.

Hi @HereThereBeDragons - I’ve reviewed and addressed all the comments. If any response needs further correction or clarification, please let me know and I will update it.

Please always review, understand and take ownership of AI generated content before asking someone else to give their attention. Repeated failures to do so will result in automatic rejection of future contributions.

Copy link
Copy Markdown
Contributor

@geomin12 geomin12 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

please rebase your changes with main, so I am able to see code changes properly

@lajagapp lajagapp requested a review from geomin12 January 26, 2026 17:49
@lajagapp
Copy link
Copy Markdown
Contributor Author

please rebase your changes with main, so I am able to see code changes properly

I've rebased the PR with latest main branch.

Copy link
Copy Markdown
Contributor

@geomin12 geomin12 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please take a look at the changes, there are a lot of files that are not a part of this PR. Please rebase again or perhaps open a clean branch and make updates there

@geomin12 geomin12 self-requested a review January 30, 2026 17:07
Comment thread .github/workflows/ci_linux.yml Outdated

run_linux_extended_functional_tests:
needs: [build_portable_linux_artifacts]
name: Run Extended Functional Tests
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

let's add linux to the name

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added Linux in name.

Comment thread .github/workflows/ci_windows.yml Outdated

run_windows_extended_functional_tests:
needs: [build_windows_artifacts]
name: Run Extended Functional Tests
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

let's add windows to the name

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added Windows in name.

IS_EXTENDED_FUNCTIONAL_TESTS: "true"
run: python ./build_tools/github_actions/fetch_test_configurations.py

run_tests:
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

better job name please, run_tests is too generic

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Update job name to run_extended_functional_tests.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

instead of extended_tests folder, why not just have:

benchmark_tests/
functional_tests/

seeing benchmark tests under extended_tests leads me to believe that test_extended_functional_tests might run that. let's separate them out, or call the workflow file test_functional_tests. whatever you think is best!

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the feedback. I'm keeping extended_tests/ as the parent folder since benchmarks and functional tests share utilities and follow identical patterns (execution → parsing → upload).

Renamed workflow from test_extended_functional_tests.yml to test_functional_tests.yml. And updated all its references and variables.

Returns:
True if upload successful, False otherwise
"""
log.info("Uploading Results to API")
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

no, as in:

Suggested change
log.info("Uploading Results to API")
log.info("Uploading Functional Tests Results to API")

Comment on lines +94 to +98
backward_flags = self.gpu_specific_flags[gfx_id].get(
"backward_flags", ""
)
if backward_flags:
full_cmd = f"{full_cmd} {backward_flags}"
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
backward_flags = self.gpu_specific_flags[gfx_id].get(
"backward_flags", ""
)
if backward_flags:
full_cmd = f"{full_cmd} {backward_flags}"
backward_flags = self.gpu_specific_flags[gfx_id].get(
"backward_flags", ""
)
full_cmd = f"{full_cmd} {backward_flags}"

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested changes are updated.

Returns:
tuple: (test_results list, detailed PrettyTable, number of test suites)
"""
log.info("Parsing Results")
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

parsing results for miopendriver, please add more specifics otherwise these logs are useless

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Updated the info with {self.display_name}.

with open(self.results_json, "w") as f:
json.dump(all_results, f, indent=2)

log.info(f"Results saved to {self.results_json}")
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

for miopendriver

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Updated the info with {self.display_name}.


for line in process.stdout:
log.info(line.strip())
f.write(line)
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i notice we are writing to a file but it isn't being used anywhere. do we need to write to a file?

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You're correct. Since we are using generated JSON data for the parsing the results, this writing to file is not required and we can remove it.
Now, removed log file definition and all the file write operations.

"fetch_artifact_args": "--miopen --tests",
"timeout_minutes": 30,
"test_script": f"python {_get_script_path('test_miopendriver_conv.py')}",
# TODO(lajagapp): Add windows support
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can we make a github issue and tag it here?

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Created github issue and updated in TODO.

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If creating an issue, this should be linked here in the code and you should not solely link your GH handle.

- Remove write_step_summary wrapper and redundant log file writing
- Use display_name consistently in logging

Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
- Rename test_extended_functional_tests.yml to test_functional_tests.yml
- Update all variables and references in workflow files and documentation

Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
@lajagapp lajagapp requested a review from geomin12 February 2, 2026 20:57
@marbre
Copy link
Copy Markdown
Member

marbre commented Feb 3, 2026

This already has several reviewers involved but kind of feels of the rails just looking at the number of review comments. Most answers to comments seem AI generated. I would strongly suggest to split this into smaller chunks and more PRs. Will unassign myself and leave review to others.

@marbre marbre removed their request for review February 3, 2026 14:01
Copy link
Copy Markdown
Contributor

@geomin12 geomin12 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i would agree with Marius, let's split this up into smaller chunks to make it faster to iterate and easier to understand what changes are occuring.

In my opinion, let's split it up to:

  • adding functional tests
  • organizing files under new folder

@lajagapp
Copy link
Copy Markdown
Contributor Author

lajagapp commented Feb 5, 2026

smaller chunks

Thanks for the suggestion. Sure, I will split this PR into multiple smaller PRs and will add you for the review. Now, I'm closing this PR.

@lajagapp lajagapp closed this Feb 5, 2026
@github-project-automation github-project-automation Bot moved this from TODO to Done in TheRock Triage Feb 5, 2026
jayhawk-commits pushed a commit that referenced this pull request Mar 11, 2026
## Motivation

Bump rocm-systems from 93bc019 to 093b66caa3 (includes fix for hip-tests
issue and revert for mathlib hiprtc issues and revert for rccl-test,
added revert for miopen failures due to PR 653):

Commits:
093b66caa3 (HEAD, origin/develop, origin/HEAD) Revert "SWDEV-546177 -
hipModuleGetLoadingMode API impl (#653)" (#3858)
d8a0adbc9f [AMD-SMI] Hide libamd_smi.so internal symbols (#3777)
d4da458f94 [rocprofiler-sdk] [Documentation ] Updating changelog (#3827)
19fadeb082 (origin/users/abchoudh/fix_dispatch_count) [RCCL][Tuner
Plugin] Enable tuning of RCCL tuning constants (#3757)
b4f5f8a6a8 rocr: Fix IPC dmabuf hang with large allocations (#3211)
64efea0435 RCCL: allow users to override max and per job memory & fix
defaults. (#3797)
9b3dd101bb Removing ready_for_review (#3849)
7e43880a64 [rocprofiler-systems] Update ROCm version to 7.2.0 in CI
workflows for Debian, RedHat, and Ubuntu (#3431)
1fdb6b9827 [rocshmem] add gda/topology unit tests (#3715)
be1ea24a96 Move hipMipmappedArrayGetMemoryRequirements test to common
tests
e4513f04c8 Update amdgpu-windows-interop with latest changes, pal
58aa0bab2ced0cc9ebe8d2d0932db6774feb4e49 2026-03-04(#3773)
b1f964d796 [rocprofiler-compute] Ensure long kernel name fully shows in
compute analyze (#3665)
4dcf1e3ce0 SWDEV-567112 - Replace test names (#3787)
33f5f302e5 ROCM-2428 - fixes hipStreamBatchMemOp invalid operation
checks (#3099)
139f4bfff8 [SWDEV-556456] Align HIP_UUID with rocminfo (#3614)
8e8928544c Reduce buffers alignment to 4 bytes (#3821)
51be29a647 AIRUNTIME-125: Consolidate Windows optimization and debug
flags (#3825)
1407392240 [AMD-SMI] CI: Fix root workflow to use ASIC-specific test
filters (#3807)
63f78a98d7 (origin/users/mcao/fix_rocpdsummary) [ROCM-SMI] Fix DRM
include dirs leaking absolute build paths to consumers (#3808)
caf2f7e1eb [ROCM-186] amd-smi: Add support for a VRAM and GTT tuning
interface (#3636)
a0712d4c2a [TheRock CI] Update projects_to_test lists (#3749)
02090c42c9 rocrtst: install gfx .hsaco files to share/rocrtst (#3744)
4a0a1cbfce Merge other simd table (#3696)
0d07657d78 Add missing kwargs from
rocprofiler_add_integration_validate_test in .cmake-format.yaml (#2336)
3a3df301dc Optimize device counting service GPU interactions (#1583)
95d9da0098 Add SPM Enable flag in build infrastructure (#3677)
12bb9435b2 [rocprofiler-sdk] On-demand GPU profile queue
creation/destruction (#3586)
941057c2c0  Navi4 tuning table iter 1 (#3052)
dbf2b7369f [AMD-SMI] Display N/A for cu_occupancy when file is
unavailable (#3589)
b0efc7c639 [RCCL] [UT] Add ROCTX test (#3625)
ba7a20ea18 Reducing the p2pnChannels for half-subscription A2A on
multi-node MI350 (#3381)
75238c98a2 [clr] Fix memory leak in getOrCreateHostcallBuffer (#3699)
af2ee0e8ad [hip-tests] ASAN Check for image support before we create
context (#3834)
ad4496678e Update windows ci subtree in include amdgpu-windows-interop
(#3814)
c8ad252208 [rocprofiler-register] Fix compilation with system fmt/glog
(#1243)
781881544d Update README to include dbgapi and debug agent components
(#3731)
88e4a7837e ROCProfiler and ROCTracer: Modifying deprecation note (#3831)
b5918a5f35 [ROCM-3124-3125-3126] CUID file generation hangs on MI350
systems/CUID test failures/Segmentation fault in CUID example code
(#3548)
97a5dd993c Update copyright to use SPDX IDs (#3805)
511730ab45 [rocshmem]: add flood-amo tester (#3653)
2d650a0065 [clr] Fix heap use after free error in device allocations
(#3789)
b6b179ad81 Disable hipHostRegister_Negative test for ASAN (#3832)
39ec318c8d [RCCL] Add GDA alltoallv via rocshmem integration (#3613)
fb0f4d53b1 [RCCL] [CUMEM] Fix cuMem multi-process runs (#3811)
c3de7d4bf6 SWDEV-526201 - Fix and enable disabled HIP tests from warp
group (#3089)
8d9a8ca161 roofline: code cleanup and refactor vector types (#3813)
8957e49028 Don't wait on command completion if worker thread is
destroyed (#3790)
9e7586a5fa [rocshmem] Add barrier APIs and expose `ROCSHMEM_TEAM_WORLD`
on device (#3651)
91b09235b0 Revert "fix local gpu release static build failure (#3667)"
(#3799)
0fda754b1b libhsakmt: Add secondary KFD context creation support
ee43db95b0 Revert "Update TheRock reference to 20260303 commit (#3709)"
(#3826)
86e28b9fae Added fix to update GL2C counters instance count for GFX11.5
(#3100)
93f69f7de4 Adjust includes to match use (#3742)
e9fbc3f1a2 (develop) Update TheRock reference to 20260303 commit (#3709)
be0675a1a6 (HEAD) Revert "Support fp8 types in hiprtc (#2605)" (#3792)
3e3a94a4ef [rocprofiler-systems] Add trace_cache support for
std::optional<T> serialization (#3490)
0b42a7f472 clr: Eliminate unnecessary kernel name string copies (#3774)
b6b0d77b29 rocr: Add hsa_amd_memory_async_batch_copy API for batched
memory copies (#3259)
486e6d12d2 Resolve staircase RS regression with 48 max channels (#3684)
eb59c85ac4 [gfx942][gfx950] Leverage new cache bypass builtins for
simple protocol where available (#2847)
4d74d27f0e (origin/users/raramakr/rocm-smi-target) Revert "Auto Labeler:
Add ci:regression-detection label to rccl PRs (#3543)" (#3769)
8f0795517c [AMD-SMI] CI: Use ASIC-specific test blacklists in workflows
(#3775)
7cef5b64c1 Fix MFMA total FLOPS calculation (#3371)
aea37512ba Remove duplicated tests (#3235)
b6c656fdd4 Remove duplicated tests in memory module (#3087)
ca3137d8f9 [rocprofiler-sdk] Install integration tests without building
for therock & Misc. fixes (#3047)
0ab5c41f65 [rdc] Enable on-demand queue mode in rocprofiler-sdk to
prevent inference degradation (#3629)
a1eb2a1f7c rocr/wsl: a library should not output to std::out by default
(#3718)
b7da296cc8 Reenable flood_put/get testers on mlx5 since they should work
after pr2732 (#3748)
000e24de2f [rocprofiler-sdk] Add automatic late-start support to
rocprofiler_force_configure (#2168)
64ea87f592 [hip-tests] Fix memory leaks in hipMemPoolTrimTo tests
(#3643)
543a7d765f rocr: Include code object allocs in lightweight coredump
a58da378d4 [rocdecode] - update rocdecode ctest (#3768)
f88e4ee44d [rocprofiler-systems] Make CDash submit non-fatal and add
GitHub Actions logging (#3525)
cb14debc3a [rocprofiler-systems] Update nlohmann-json submodule (#3391)
449253009a SWDEV-567112 - Introduce new mechanism for tagging and
disabling tests - Part 2 (#3707)
8ca991393d disabling rccl from full build (linux), covered in RCCL CI
(#3770)
c4fdb20b74 [ATT] Re-enable tests. Add option to specify perf to target
CU only (#2819)
615aab95ed ROCM-3816 Out of Memory fix (#3588)
8ffad41b24 Fix rocm_smi64 exporting invalid absolute paths to consumers
(#3717)
042d76a626 rocr: Remove dependency on KFD in Runtime::VMemoryHandleMap
(#2515)
555db59b2a [AMD-SMI] CPU: Added support for family 1A Models 50h-57h
(#3206)
3affa2c7a3 [SWDEV-555935] Fix shared mutex and self-heal (#3729)
ba0bf0f3db Replace hipMemGetInfo with ihipMemGetInfo and use it for
internal calls. (#2845)
c5cef9b18e Fix HIP_RETURN on all HIP API calls. (#2838)
241ce7ba83 Revert "memory: fix "contiguous_bytes" calculation in generic
conversion (#3285)" (#3755)
8a690f482e [kpack/clr] Windows PE/COFF support for kpack artifact
splitting and runtime loading (#3728)
863bdf8aa8 MFMA pre-processor guards for ipc.hip (#3724)
90bb9b1921 Release queue outside of vgpusAccess lock (#3705)
de4523910c clr: Add build support of ROCR and PAL backends together
(#3722)
dfb7abc2d8 [rocprofiler-sdk] RCCL API changes for
RCCL_API_TRACE_VERSION_PATCH = 3 (#3477)
d69d4f23db [AICOMRCCL-633] - Fixed warnings in tests (#3402)
067d86dcaa rocr/wsl: Disable AQL Queue usage with flag ROCR_USE_PM4
(#3663)
594eb60d42 [TheRock CI] rocm-systems build full ROCm stack (#3182)
27d17e8ea0 [ROCProfiler-SDK] Fix SWDEV-556922: Handle comments before
checking for pmc: (#1723)
c80d90439d memory: fix "contiguous_bytes" calculation in generic
conversion (#3285)
669987c83f [hip-tests] ASAN - add missing release handles (#3735)
a24bbd75a4 fix local gpu release static build failure (#3667)
259b2ff913 Speed up DeviceId (#2803)
65d9264bf4 Simplify MPI trace merge logic and remove legacy guards
(#3562)
1076c083cb use system to look for zcat path instead (#3720)
22f1d19db3 [AICOMRCCL-355] Enable threshold-based p2p-batching (#3000)
a2e4c794d2 Partially flatten template tests cases (#2597)
e242abe219 Pass space separated gfx target list to RCCL build command
(#3701)
4f78aea66d SWDEV-570074 - Refactor Memset memory object handling.
(#2228)
b3ad12d834 Support Nvidia build on theRock for HIP-tests (#3335)
a1cf15ea9a Support fp8 types in hiprtc (#2605)
8ef84b0a50 [rocprofiler-systems] Add HPC examples to automated testing
(#3437)
db3a70dfa0 Free memory which was allocated in tests (#3710)
27e6809c7e [rocprofiler-systems]: Fix rhel CI failure on for MPI and UCX
tests (#3700)
0d9aaf59d8 rccl/topo_expl: fix build issue. (#3719)
be04d75765 Fix zcat path used for checking kernel configs (#3423)
cab60a7b27 rocr/thunk/win: Add CU mask support (#3518)
5b3d826c05 [CUMEM] Initial support for cuMem APIs (#2763)
0606ff491f [HIP] [PLAT-194496] Improve Stress_hipMalloc_HighSizeAlloc
reliability (#3550)
05750a77cc fix hip-test name in config (#3716)
33f777f3e9 hsakmt: Remove --high functionality from run_kfdtest.sh
(#2486)
e4c46e3480 Hide the retain under direct dispatch check (#3698)
bfe0ca0279 Add rocprof trace decoder to CI tests (#3690)
a769b6f54e [rocSHMEM] Edgar/abstract allocator ipc part1 (#3411)
659fb52243 [AMD-SMI] Fix bugs, improve error handling, and clean up
NIC/switch code (#3654)
0eb26ea571 hsakmt: Fix Import/Export of dmabuf_fd for WSL/Windows
(#3348)
a122936abb [SWDEV-567812] Add UBB power and power_limit fields to
npm_info (#3262)
c3bec090c5 [rocprofiler-sdk][rocprofv3][rocpd] Updates for KFD data
(#340)
7c44d47740 SWDEV-547659 - Remove HIP_VERSION_GITHASH in logs (#448)
74b6487a6a SWDEV-547008 - Documentation fix for function return values
(#463)
af21cd44f1 SWDEV-545553 - Improve clarity and robustness of CALLBACK
unit tests (#546)
180d639044 SWDEV-544900 - Change hip-test test case name (#547)
feeca99950 Doc improvements (#3688)
c1822b6336 ROCprofiler-SDK: deprecation of legacy tools (#3609)
5d7aff8462 Fix rocprof-compute-viewer link (#3459)
0b0b4846f0 AIRUNTIME-129 - Fix Ocl test failures of 2D image with
pitches. (#3584)
ac569b87e0 Fix memory tests config (#3687)
603fe7a5cf [hip-tests] Enable hipMipmappedArrayGetMemoryRequirements
test via cmake
4fad4452d9 [hip] Docs: Updates to some memory management pages
8cc59559fe AICOMRCCL-656 fix memory leak in ncclCommInitRankFunc (#3628)
94a4595a5d Fix missing amd_comgr linkage in pc-sampling integration test
(#3453)
2a68565dce rocrtst: CMAke file: strip xnack/feature suffixes from gfxNum
in build_kernel (#3652)
c3542bfb2b [rocprofv3] Deprecating input text files for counter
collection (#1562)
ff122e7ed7 SWDEV-573073 - Cleanup hipHostAlloc/Malloc/Register tests
(#3017)
5b1deaf29d SWDEV-567112 - Introduce new mechanism for tagging and
disabling tests - Part 1 - Core (#2351)
6e0cc309e1 rocrtst: MaxSingleAllocationTest: skip CPU NUMA nodes >0
(#3208)
d65f601195 [AICOMRCCL-667] rccl: Change GDR selection logic. (#3607)
f1c44ab200 Patch Back to Old Repo: fixes from manual runs (#3621)
fe53bcd715 [AMD-SMI] Allow amdsmi init to succeed when no NIC hardware
is present (#3403)
b25600efdb [ROCM SMI] Fix fw pldm version not displayed in default
amd-smi (#3594)
169d2ef763 root to module wiring, remove legacy source collection
(#3482)
7469781988 [LRT][clr] SWDEV-512963-Fix CTS test failures for 1D buffer
copy (#3520)
c8f55d9b86 Adding rocprof trace decoder (#3576)
425e983502 Trace decoder codeowners (#3600)
a176efd648 [hip-tests] Add return statements to HIP_SKIP_TEST (#3647)
32687cf183 rocrtst: CPUAccessToGPUMemoryTest: Cap host allocation to 512
MB under ASAN (#3407)
97c0206753 Update codeowners for thunk DXG (#3334)
be44b28bb6 [rocdecode][rocjpeg] - ctest CMakeLists cleanup (#3632)
80ff0b8942 Various memory leak fixes in hip-tests (#3605)
0988f67a85 fix typo in help text (#3314)
9f823c53f1 Fix CUID file lookup by loading files before searching
entries (#3436)
064c89261b SWDEV-546177 - hipModuleGetLoadingMode API impl (#653)
006213e112 ROCM-2696: Ignare size and base if null ptr (#3336)
6060b99d83 Improve atomic min max test perf (#2580)
3fbcc13602 Change printf capture impl (#1127)
93bc01937c (tag: hip-version_7.12.60610,
origin/users/mradosav-amd/rocprofsys-selective-region) [ROCM-CORE]
Update rdhc script to support rocm install prefix
(ROCm/rocm-systems#3596)

[AICOMRCCL-355]:
https://amd-hub.atlassian.net/browse/AICOMRCCL-355?atlOrigin=eyJpIjoiNWRkNTljNzYxNjVmNDY3MDlhMDU5Y2ZhYzA5YTRkZjUiLCJwIjoiZ2l0aHViLWNvbS1KU1cifQ
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

Status: Done

Development

Successfully merging this pull request may close these issues.

5 participants