Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

rocprof-compute branding update #428

Merged
merged 2,258 commits into from
Nov 1, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2258 commits
Select commit Hold shift + click to select a range
40d4e65
Update to work with rocprof v1
benrichard-amd Jul 12, 2024
b31fa31
Remove unused method
benrichard-amd Jul 12, 2024
2ef632e
Fix code formatting
benrichard-amd Jul 17, 2024
aa2ae8c
Fix conflicts for rebase.
xuchen-amd Oct 17, 2024
d03d036
Fix test failures on MI300X
benrichard-amd Aug 2, 2024
56b46b8
Docs housekeeping post-6.2.0 (#394)
peterjunpark Aug 2, 2024
bd62297
Fix ctests for MI100
benrichard-amd Aug 3, 2024
3bf6231
Fix formatting
benrichard-amd Aug 6, 2024
115c02f
Amend the Fix reference links in tutorial includes files commit (#398)
amd-jnovotny Aug 8, 2024
0d0c935
Check Python version on application launch (#393)
dgaliffiAMD Aug 9, 2024
8e308f5
Remove `dev` and `main` branch from workflows. (#404)
dgaliffiAMD Aug 12, 2024
25b6ff7
Update dependabot.yml target-branch
dgaliffiAMD Aug 12, 2024
010bed1
Run Workflows on Release Branches (#409)
dgaliffiAMD Aug 13, 2024
fbe2040
Add omniperf suffix to MOD_INSTALL_PATH in docs (#414)
coleramos425 Aug 16, 2024
b8bb0a5
update package manager install docs to include omniperf in PATH (#420)
peterjunpark Sep 4, 2024
1041648
Add the ability to determine GPU model from Chip ID (#423)
xuchen-amd Sep 24, 2024
c096d63
Update issue template
coleramos425 Sep 30, 2024
d3ec1bb
Rebranding of top level md files.
xuchen-amd Oct 3, 2024
ed00397
Work around crash when profiling multi-process/multi-GPU application …
benrichard-amd Jun 12, 2024
62aec24
Split rocprofv2 cmd args prior to subprocess call (#347)
coleramos425 Jul 3, 2024
007a826
Improve perfmon coalescing
benrichard-amd Jul 8, 2024
b708251
Interleve TCC channel counters
benrichard-amd Jul 8, 2024
65f781e
Remove duplicate normal counters
benrichard-amd Jul 10, 2024
c1b74b2
Save accumulate counters to SQ_ files
benrichard-amd Jul 12, 2024
f5d1bb6
Update to work with rocprof v1
benrichard-amd Jul 12, 2024
64903a7
Remove unused method
benrichard-amd Jul 12, 2024
4f639cb
Fix code formatting
benrichard-amd Jul 17, 2024
a04cb75
Docs: refactor and integrate into ROCm docs portal (#362)
peterjunpark Jul 31, 2024
a4647b4
Inital commit of the rocprof-compute rebrand process. This commit ren…
xuchen-amd Sep 24, 2024
556fb1b
Rebranding of github README.md and AUTHORS.
xuchen-amd Sep 24, 2024
b6b3a18
Rebranding of top level md files.
xuchen-amd Oct 3, 2024
71a1a99
Rename all occurrences of omniperf_analyze to rocprof_compute_analyze.
xuchen-amd Oct 3, 2024
00b55b7
Rename all occurrences of omniperf_soc to rocprof_compute_soc.
xuchen-amd Oct 3, 2024
f48e53b
Rename all occurrences of omniperf_profile to rocprof_compute_profile.
xuchen-amd Oct 3, 2024
1c42d35
Remove outdated omniperf_base.py
xuchen-amd Oct 3, 2024
475c607
Rename of grafana dir.
xuchen-amd Oct 4, 2024
483b82f
Rename CMake file and rename paths from omniperf to rocprofcompute.
xuchen-amd Oct 9, 2024
bc08da1
Revert to omniperf until pipeline ready for rebrand.
xuchen-amd Oct 19, 2024
533b8bf
Improve perfmon coalescing
benrichard-amd Jul 8, 2024
05539d6
Interleve TCC channel counters
benrichard-amd Jul 8, 2024
4104cfd
Remove duplicate normal counters
benrichard-amd Jul 10, 2024
377e274
Save accumulate counters to SQ_ files
benrichard-amd Jul 12, 2024
65bb140
Remove unused method
benrichard-amd Jul 12, 2024
b9904c7
Fix code formatting
benrichard-amd Jul 17, 2024
ecad1dc
Docs: refactor and integrate into ROCm docs portal (#362)
peterjunpark Jul 31, 2024
3754ac9
Fix test failures on MI300X
benrichard-amd Aug 2, 2024
9f40b80
Prep work for branch renaming (#389)
dgaliffiAMD Aug 2, 2024
7160720
Docs housekeeping post-6.2.0 (#394)
peterjunpark Aug 2, 2024
c9526a6
Fix ctests for MI100
benrichard-amd Aug 3, 2024
98d1e1e
Fix formatting
benrichard-amd Aug 6, 2024
acb9de2
Amend the Fix reference links in tutorial includes files commit (#398)
amd-jnovotny Aug 8, 2024
f88ebc8
Check Python version on application launch (#393)
dgaliffiAMD Aug 9, 2024
be6eaa8
Remove `dev` and `main` branch from workflows. (#404)
dgaliffiAMD Aug 12, 2024
e37eff3
Update dependabot.yml target-branch
dgaliffiAMD Aug 12, 2024
36e6ef4
Run Workflows on Release Branches (#409)
dgaliffiAMD Aug 13, 2024
8064430
Add omniperf suffix to MOD_INSTALL_PATH in docs (#414)
coleramos425 Aug 16, 2024
d37f411
update package manager install docs to include omniperf in PATH (#420)
peterjunpark Sep 4, 2024
56b7d63
Tarball on rocm tags and MAINTAINERS guide (#402)
coleramos425 Sep 24, 2024
ce9196d
Update VERSION, CHANGELOG, and README citation for next release (#433)
cfallows-amd Sep 27, 2024
f2d78cd
Rebranding of top-level excutable.
xuchen-amd Sep 24, 2024
61e3237
Rebranding of top level md files.
xuchen-amd Oct 3, 2024
1ca0cfd
Work around crash when profiling multi-process/multi-GPU application …
benrichard-amd Jun 12, 2024
e9de6c9
Split rocprofv2 cmd args prior to subprocess call (#347)
coleramos425 Jul 3, 2024
92fa2bb
Improve perfmon coalescing
benrichard-amd Jul 8, 2024
0ac8aee
Interleve TCC channel counters
benrichard-amd Jul 8, 2024
88812ba
Remove duplicate normal counters
benrichard-amd Jul 10, 2024
b789913
Save accumulate counters to SQ_ files
benrichard-amd Jul 12, 2024
a6eebd8
Update to work with rocprof v1
benrichard-amd Jul 12, 2024
dad9e1a
Remove unused method
benrichard-amd Jul 12, 2024
9c82fab
Fix code formatting
benrichard-amd Jul 17, 2024
a07ced4
Docs: refactor and integrate into ROCm docs portal (#362)
peterjunpark Jul 31, 2024
903c487
Rebranding of github README.md and AUTHORS.
xuchen-amd Sep 24, 2024
cf6c6ea
Rebranding of top level md files.
xuchen-amd Oct 3, 2024
bd78dea
Rename all occurrences of omniperf_analyze to rocprof_compute_analyze.
xuchen-amd Oct 3, 2024
b8af5d5
Rename all occurrences of omniperf_soc to rocprof_compute_soc.
xuchen-amd Oct 3, 2024
e0357c8
Rename all occurrences of omniperf_profile to rocprof_compute_profile.
xuchen-amd Oct 3, 2024
57b2f2d
Remove outdated omniperf_base.py
xuchen-amd Oct 3, 2024
5efd1a7
Fix formatting.
xuchen-amd Oct 9, 2024
26effb4
Rename CMake file and rename paths from omniperf to rocprofcompute.
xuchen-amd Oct 9, 2024
f4794f4
Include Grafana assets in CMake build
coleramos425 May 9, 2024
2d50066
Add support for --quiet flag to roofline
coleramos425 May 9, 2024
5250e5c
Format CMake and Python
coleramos425 May 10, 2024
defe8c1
Add ability to overide arch when name missing in rocminfo
skyreflectedinmirrors May 9, 2024
99f4f31
Create dedicated subdirectory in perfmon configs for archs supporting…
coleramos425 May 28, 2024
7e07be9
Support MI300 in PyTest profile tests
coleramos425 May 28, 2024
f5eff01
Remove redundant code in PyTest
coleramos425 May 28, 2024
a53ac44
Remove debug print statements from profile_general
coleramos425 May 29, 2024
f6e09f5
update test analyze scripts
JoseSantosAMD May 29, 2024
eaf4655
updating expected exit codes for pytest
JoseSantosAMD May 30, 2024
5f562f6
Add vcopy workloads for MI300A and MI300X
coleramos425 May 30, 2024
7e84692
Update gpu-id on MI300 CI workloads and update test case
coleramos425 May 31, 2024
2b98668
Remove outdated CTest case from CMakeLists
coleramos425 May 31, 2024
2fb178f
Comply to Python formatting
coleramos425 May 31, 2024
d7c77aa
Fixing some typos from debug
coleramos425 May 31, 2024
9f5c70f
Missing test case
coleramos425 May 31, 2024
5bb27dc
Re-implementing HBM stack / XCD info for incoming product sku
coleramos425 Jun 3, 2024
a651c0e
Comply to formatting
coleramos425 Jun 3, 2024
a011091
change project language to HIP; identify tests as cmake subdir
koomie Jun 3, 2024
d56acce
update CI to build necessary vcopy binary via new additions to build
koomie Jun 3, 2024
9660012
wrap up test compilation with an ENABLE_TESTS option
koomie Jun 3, 2024
650fc98
set CMAKE_HIP_ARCHITECTURES at configure time so that build matches
koomie Jun 3, 2024
0b3860f
Work around crash when profiling multi-process/multi-GPU application …
benrichard-amd Jun 12, 2024
9210cb9
Split rocprofv2 cmd args prior to subprocess call (#347)
coleramos425 Jul 3, 2024
f5531db
Explicitly define Python path in CTest test declaration
coleramos425 Jul 8, 2024
4453697
Docs: refactor and integrate into ROCm docs portal (#362)
peterjunpark Jul 31, 2024
18d5999
Fix test failures on MI300X
benrichard-amd Aug 2, 2024
9a4fecd
Prep work for branch renaming (#389)
dgaliffiAMD Aug 2, 2024
9475f8b
Docs housekeeping post-6.2.0 (#394)
peterjunpark Aug 2, 2024
05c6fc6
Fix ctests for MI100
benrichard-amd Aug 3, 2024
00c4a85
Fix formatting
benrichard-amd Aug 6, 2024
bd3f981
Amend the Fix reference links in tutorial includes files commit (#398)
amd-jnovotny Aug 8, 2024
0996c5b
Check Python version on application launch (#393)
dgaliffiAMD Aug 9, 2024
6bfbc63
Remove `dev` and `main` branch from workflows. (#404)
dgaliffiAMD Aug 12, 2024
5da8748
Update dependabot.yml target-branch
dgaliffiAMD Aug 12, 2024
e2f9e77
Add omniperf suffix to MOD_INSTALL_PATH in docs (#414)
coleramos425 Aug 16, 2024
923bbb3
Fix typo and CHANGELOG modification
coleramos425 Aug 28, 2024
ed246b0
update package manager install docs to include omniperf in PATH (#420)
peterjunpark Sep 4, 2024
51bd49d
External CI: enable CI triggers (#426)
danielsu-amd Sep 23, 2024
af6f7cd
Tarball on rocm tags and MAINTAINERS guide (#402)
coleramos425 Sep 24, 2024
ec4c815
Update VERSION, CHANGELOG, and README citation for next release (#433)
cfallows-amd Sep 27, 2024
0671cdd
Remove unrelease prefix from CHANGELOG
coleramos425 Sep 27, 2024
273129a
Update issue template
coleramos425 Sep 30, 2024
7310f36
Documented Docker container OpenSSL abilities being affected by Host …
vstempen Oct 7, 2024
34012d3
Update CODEOWNERS for product team
coleramos425 Oct 11, 2024
ebcc1fd
Inital commit of the rocprof-compute rebrand process. This commit ren…
xuchen-amd Sep 24, 2024
b6e1734
Rebranding of top level md files.
xuchen-amd Oct 3, 2024
4691025
Work around crash when profiling multi-process/multi-GPU application …
benrichard-amd Jun 12, 2024
0bb39b1
Split rocprofv2 cmd args prior to subprocess call (#347)
coleramos425 Jul 3, 2024
4421e93
Improve perfmon coalescing
benrichard-amd Jul 8, 2024
489911c
Remove duplicate normal counters
benrichard-amd Jul 10, 2024
30d2a3d
Save accumulate counters to SQ_ files
benrichard-amd Jul 12, 2024
10fb7e2
Update to work with rocprof v1
benrichard-amd Jul 12, 2024
0d9849b
Docs: refactor and integrate into ROCm docs portal (#362)
peterjunpark Jul 31, 2024
bd30898
Rebranding of top level md files.
xuchen-amd Oct 3, 2024
b7ac9b6
Rename all occurrences of omniperf_analyze to rocprof_compute_analyze.
xuchen-amd Oct 3, 2024
f3a872f
Rename all occurrences of omniperf_soc to rocprof_compute_soc.
xuchen-amd Oct 3, 2024
71e5f23
Rename all occurrences of omniperf_profile to rocprof_compute_profile.
xuchen-amd Oct 3, 2024
d96f9a8
Remove outdated omniperf_base.py
xuchen-amd Oct 3, 2024
2a20978
Rename of .github dir.
xuchen-amd Oct 3, 2024
d0a3fd6
Fix formatting.
xuchen-amd Oct 9, 2024
9b79f44
Rename CMake file and rename paths from omniperf to rocprofcompute.
xuchen-amd Oct 9, 2024
d8f1a9e
Rename of tests dir.
xuchen-amd Oct 10, 2024
91eb313
Improve perfmon coalescing
benrichard-amd Jul 8, 2024
fc14351
Interleve TCC channel counters
benrichard-amd Jul 8, 2024
1ead054
Remove duplicate normal counters
benrichard-amd Jul 10, 2024
9bf2ce0
Save accumulate counters to SQ_ files
benrichard-amd Jul 12, 2024
cc2e140
Update to work with rocprof v1
benrichard-amd Jul 12, 2024
d8b7dce
Remove unused method
benrichard-amd Jul 12, 2024
ad40a8c
Fix code formatting
benrichard-amd Jul 17, 2024
084899e
Fix conflicts for rebase.
xuchen-amd Oct 17, 2024
bda2d7a
Fix test failures on MI300X
benrichard-amd Aug 2, 2024
f3b0c8f
Prep work for branch renaming (#389)
dgaliffiAMD Aug 2, 2024
fdf3603
Docs housekeeping post-6.2.0 (#394)
peterjunpark Aug 2, 2024
19e6935
Fix ctests for MI100
benrichard-amd Aug 3, 2024
3c2d5fd
Fix formatting
benrichard-amd Aug 6, 2024
ff21848
Amend the Fix reference links in tutorial includes files commit (#398)
amd-jnovotny Aug 8, 2024
5b2706a
Check Python version on application launch (#393)
dgaliffiAMD Aug 9, 2024
79e5670
Remove `dev` and `main` branch from workflows. (#404)
dgaliffiAMD Aug 12, 2024
f1d1301
Update dependabot.yml target-branch
dgaliffiAMD Aug 12, 2024
16ea30d
Run Workflows on Release Branches (#409)
dgaliffiAMD Aug 13, 2024
9e0c6ec
Add omniperf suffix to MOD_INSTALL_PATH in docs (#414)
coleramos425 Aug 16, 2024
8cb6608
update package manager install docs to include omniperf in PATH (#420)
peterjunpark Sep 4, 2024
9a090dd
Add the ability to determine GPU model from Chip ID (#423)
xuchen-amd Sep 24, 2024
8548016
Update issue template
coleramos425 Sep 30, 2024
ec7bf16
Work around crash when profiling multi-process/multi-GPU application …
benrichard-amd Jun 12, 2024
366a8d3
Split rocprofv2 cmd args prior to subprocess call (#347)
coleramos425 Jul 3, 2024
05ed8db
Improve perfmon coalescing
benrichard-amd Jul 8, 2024
18ec8e7
Interleve TCC channel counters
benrichard-amd Jul 8, 2024
b471ab3
Remove duplicate normal counters
benrichard-amd Jul 10, 2024
19f6562
Save accumulate counters to SQ_ files
benrichard-amd Jul 12, 2024
809e799
Update to work with rocprof v1
benrichard-amd Jul 12, 2024
6ae70d1
Remove unused method
benrichard-amd Jul 12, 2024
579d758
Fix code formatting
benrichard-amd Jul 17, 2024
47e23df
Docs: refactor and integrate into ROCm docs portal (#362)
peterjunpark Jul 31, 2024
5ae0b6d
Inital commit of the rocprof-compute rebrand process. This commit ren…
xuchen-amd Sep 24, 2024
de73d9f
Rename all occurrences of omniperf_analyze to rocprof_compute_analyze.
xuchen-amd Oct 3, 2024
78118f4
Rename all occurrences of omniperf_soc to rocprof_compute_soc.
xuchen-amd Oct 3, 2024
0104577
Rename all occurrences of omniperf_profile to rocprof_compute_profile.
xuchen-amd Oct 3, 2024
521fdb4
Remove outdated omniperf_base.py
xuchen-amd Oct 3, 2024
337ab71
Rename the remaining omniperf occurrences in src dir.
xuchen-amd Oct 3, 2024
f21c3cc
Rename of .github dir.
xuchen-amd Oct 3, 2024
4d278b4
Rename of grafana dir.
xuchen-amd Oct 4, 2024
13a6a64
Rename CMake file and rename paths from omniperf to rocprofcompute.
xuchen-amd Oct 9, 2024
b41fe6c
Fix lingering rebranding issues.
xuchen-amd Oct 16, 2024
8c9dcdc
Revert to omniperf until pipeline ready for rebrand.
xuchen-amd Oct 19, 2024
e6f85e6
Docs: refactor and integrate into ROCm docs portal (#362)
peterjunpark Jul 31, 2024
db0dcb8
Prep work for branch renaming (#389)
dgaliffiAMD Aug 2, 2024
60a289d
Docs housekeeping post-6.2.0 (#394)
peterjunpark Aug 2, 2024
bbf90e4
Fix ctests for MI100
benrichard-amd Aug 3, 2024
1d3b553
Fix formatting
benrichard-amd Aug 6, 2024
126be85
Amend the Fix reference links in tutorial includes files commit (#398)
amd-jnovotny Aug 8, 2024
4e98f96
Check Python version on application launch (#393)
dgaliffiAMD Aug 9, 2024
4fec30f
Remove `dev` and `main` branch from workflows. (#404)
dgaliffiAMD Aug 12, 2024
01df175
Update dependabot.yml target-branch
dgaliffiAMD Aug 12, 2024
9ea3681
Run Workflows on Release Branches (#409)
dgaliffiAMD Aug 13, 2024
70cae42
Add omniperf suffix to MOD_INSTALL_PATH in docs (#414)
coleramos425 Aug 16, 2024
8ef063d
update package manager install docs to include omniperf in PATH (#420)
peterjunpark Sep 4, 2024
21f6035
Update issue template
coleramos425 Sep 30, 2024
0c68989
Rebranding of top level md files.
xuchen-amd Oct 3, 2024
e07a05f
Work around crash when profiling multi-process/multi-GPU application …
benrichard-amd Jun 12, 2024
42d9621
Split rocprofv2 cmd args prior to subprocess call (#347)
coleramos425 Jul 3, 2024
ef0ef4d
Improve perfmon coalescing
benrichard-amd Jul 8, 2024
2936b9d
Interleve TCC channel counters
benrichard-amd Jul 8, 2024
45cebda
Remove duplicate normal counters
benrichard-amd Jul 10, 2024
2972d15
Save accumulate counters to SQ_ files
benrichard-amd Jul 12, 2024
25c4a46
Update to work with rocprof v1
benrichard-amd Jul 12, 2024
40549e3
Remove unused method
benrichard-amd Jul 12, 2024
9637a7b
Fix code formatting
benrichard-amd Jul 17, 2024
fb2bb5b
Docs: refactor and integrate into ROCm docs portal (#362)
peterjunpark Jul 31, 2024
2d97c3f
Rebranding of top level md files.
xuchen-amd Oct 3, 2024
1ea9dd0
Rename of src variables.
xuchen-amd Oct 3, 2024
4f51204
Rename all occurrences of omniperf_base to rocprof_compute_base.
xuchen-amd Oct 3, 2024
dbc63bf
Rename all occurrences of omniperf_soc to rocprof_compute_soc.
xuchen-amd Oct 3, 2024
dd4d9a6
Rename all occurrences of omniperf_profile to rocprof_compute_profile.
xuchen-amd Oct 3, 2024
fd3fdc1
Remove outdated omniperf_base.py
xuchen-amd Oct 3, 2024
59471c7
Fix formatting.
xuchen-amd Oct 9, 2024
69fe89d
Rename CMake file and rename paths from omniperf to rocprofcompute.
xuchen-amd Oct 9, 2024
8076ee9
Update rocprof-compute to rocprofiler-compute.
xuchen-amd Oct 22, 2024
49d23b1
Fix python formatting.
xuchen-amd Oct 22, 2024
8473888
Fix executable name.
xuchen-amd Oct 23, 2024
3b8e292
Fix executable name.
xuchen-amd Oct 23, 2024
e9f06a2
Fix conflicts.
xuchen-amd Oct 23, 2024
0159e09
Fix CMakeLists.
xuchen-amd Oct 23, 2024
0241139
Fix tarball.
xuchen-amd Oct 23, 2024
7728043
Fix duplication issues.
xuchen-amd Oct 23, 2024
2ae1ed9
Resolve reviews.
xuchen-amd Oct 24, 2024
1b30b3d
Revert unintended changes in rocprof_compute_analyze.
xuchen-amd Oct 24, 2024
63bb7dc
Rename OmniProfiler_Base to RocProfCompute_Base in rocprof_compute_pr…
xuchen-amd Oct 24, 2024
dcce38a
Revert unintended changes in rocprof_compute_soc.
xuchen-amd Oct 24, 2024
e3dc685
Revert unintended changes in tests\workloads\multikernel\MI200.
xuchen-amd Oct 24, 2024
de9bf3b
Fix format + rename env to ROCPROFCOMPUTE*.
xuchen-amd Oct 24, 2024
344e09d
Move rocprofcompute.lua.in to its correct location.
xuchen-amd Oct 25, 2024
1a1a7a9
Merge branch 'rocprof-compute_branding_update' of github.com:xuchen-a…
xuchen-amd Oct 29, 2024
1dbe560
Fix python formatting.
xuchen-amd Oct 29, 2024
14b3dbe
Remove unintended changes.
xuchen-amd Oct 29, 2024
9dc2a78
Update docs/tutorial/profiling-by-example.rst
xuchen-amd Oct 29, 2024
d00ea74
Update .github/workflows/docs.yml
xuchen-amd Oct 29, 2024
f28ed48
Update CHANGELOG.md
xuchen-amd Oct 29, 2024
f4ad866
Update README.md
xuchen-amd Oct 29, 2024
923e4eb
Remove duplicates and fix unintended removal.
xuchen-amd Oct 29, 2024
705ed7a
Merge branch 'rocprof-compute_branding_update' of github.com:xuchen-a…
xuchen-amd Oct 29, 2024
5c029d0
Update src/utils/specs.py
xuchen-amd Oct 29, 2024
d35c21c
Update docs/tutorial/includes/vector-memory-operation-counting.rst
xuchen-amd Oct 29, 2024
9e0740f
Update docs/conf.py
xuchen-amd Oct 29, 2024
d6f6428
Update docs/tutorial/includes/infinity-fabric-transactions.rst
xuchen-amd Oct 29, 2024
213a36c
Update docs/tutorial/includes/occupancy-limiters-example.rst
xuchen-amd Oct 29, 2024
d3a5f2c
Fix unintended changes.
xuchen-amd Oct 29, 2024
f2c3d0e
Merge branch 'rocprof-compute_branding_update' of github.com:xuchen-a…
xuchen-amd Oct 29, 2024
ab12160
Update docs/how-to/profile/mode.rst
xuchen-amd Oct 29, 2024
f7414d9
Update CMakeLists.txt
dgaliffiAMD Nov 1, 2024
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
10 changes: 5 additions & 5 deletions .github/ISSUE_TEMPLATE/bug_report.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -38,13 +38,13 @@ body:
required: true

- type: input
id: omniperf-version
id: rocprofiler-compute-version
attributes:
label: Omniperf Version
label: ROCm Compute Profiler Version
description: |
What version of Omniperf are you using? Hint:
What version of ROCm Compute Profiler are you using? Hint:
```shell
omniperf --version
rocprof-compute --version
```
placeholder: e.g. 2.1.0
validations:
Expand Down Expand Up @@ -115,7 +115,7 @@ body:
id: logs
attributes:
label: Relevant log output
description: Please copy and paste Omniperf's `log.txt` file. This will be automatically formatted into code, so no need for backticks.
description: Please copy and paste rocprofiler-compute's `log.txt` file. This will be automatically formatted into code, so no need for backticks.
render: shell

- type: textarea
Expand Down
6 changes: 3 additions & 3 deletions .github/workflows/mi-rhel9.yml
Original file line number Diff line number Diff line change
Expand Up @@ -85,17 +85,17 @@ jobs:
run: |
cd build
make
srun -N 1 -J omniperf -p $CI_QUEUE -t 00:20:00 ctest -j 4 --resource-spec-file ../tests/4gpus.json --verbose -L profile
srun -N 1 -J rocprof-compute -p $CI_QUEUE -t 00:20:00 ctest -j 4 --resource-spec-file ../tests/4gpus.json --verbose -L profile
- name: Run [analyze workloads] mode
if: '!cancelled()'
run: |
cd build
srun -N 1 -J omniperf -p $CI_QUEUE -t 00:10:00 ctest --verbose -R test_analyze_workloads
srun -N 1 -J rocprof-compute -p $CI_QUEUE -t 00:10:00 ctest --verbose -R test_analyze_workloads
- name: Run [analyze commands] mode
if: '!cancelled()'
run: |
cd build
srun -N 1 -J omniperf -p $CI_QUEUE -t 00:10:00 ctest --verbose -R test_analyze_commands
srun -N 1 -J rocprof-compute -p $CI_QUEUE -t 00:10:00 ctest --verbose -R test_analyze_commands
- name: Publish Test Results
uses: EnricoMi/publish-unit-test-result-action/linux@v2
if: always()
Expand Down
14 changes: 7 additions & 7 deletions .github/workflows/packaging.yml
Original file line number Diff line number Diff line change
Expand Up @@ -37,29 +37,29 @@ jobs:
cd build
make package_source
- name: Rename tarball
run: mv build/omniperf-*.tar.gz build/omniperf-${{github.ref_name}}.tar.gz
run: mv build/rocprofiler-compute-*.tar.gz build/rocprofiler-compute-${{github.ref_name}}.tar.gz
- name: Archive tarball
uses: actions/upload-artifact@v4
with:
name: omniperf-${{github.ref_name}}.tar.gz
path: build/omniperf-${{github.ref_name}}.tar.gz
name: rocprofiler-compute-${{github.ref_name}}.tar.gz
path: build/rocprofiler-compute-${{github.ref_name}}.tar.gz
- name: Set version
run: echo "VERSION=$(cat VERSION)" >> $GITHUB_ENV
- name: Determine release name
dgaliffiAMD marked this conversation as resolved.
Show resolved Hide resolved
run: |
if [[ ${{github.ref_name}} == rocm-* ]]; then
echo "RELEASE_NAME=Omniperf ${{ env.VERSION }} for ${{github.ref_name}}"
echo "RELEASE_NAME=rocprofiler-compute ${{ env.VERSION }} for ${{github.ref_name}}"
else
echo "RELEASE_NAME=Omniperf ${{ env.VERSION }}"
echo "RELEASE_NAME=rocprofiler-compute ${{ env.VERSION }}"
fi >> $GITHUB_ENV
- name: Upload tarball Release Asset
uses: softprops/action-gh-release@v2
if: startsWith(github.ref, 'refs/tags/') && github.repository == 'ROCm/omniperf'
if: startsWith(github.ref, 'refs/tags/') && github.repository == 'ROCm/rocprofiler-compute'
dgaliffiAMD marked this conversation as resolved.
Show resolved Hide resolved
with:
fail_on_unmatched: True
generate_release_notes: True
draft: False # toggle for debugging
files: |
build/omniperf-${{github.ref_name}}.tar.gz
build/rocprofiler-compute-${{github.ref_name}}.tar.gz
name: ${{ env.RELEASE_NAME }}

2 changes: 1 addition & 1 deletion .github/workflows/rhel-8.yml
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ jobs:
run: |
mkdir build
cd build
cmake -DCMAKE_INSTALL_PREFIX=/opt/omniperf -DPYTEST_NUMPROCS=4 ..
cmake -DCMAKE_INSTALL_PREFIX=/opt/rocprofiler-compute -DPYTEST_NUMPROCS=4 ..
make install
- name: CTest- Analyze Commands
run: |
Expand Down
44 changes: 22 additions & 22 deletions .github/workflows/tarball.yml
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ on:
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true

jobs:
distbuild:
runs-on: ubuntu-latest
Expand Down Expand Up @@ -47,7 +47,7 @@ jobs:
uses: actions/upload-artifact@v4
with:
name: tarball-testing
path: build/omniperf-*.tar.gz
path: build/rocprofiler-compute-*.tar.gz
retention-days: 3
disttest:
runs-on: ubuntu-latest
Expand All @@ -61,47 +61,47 @@ jobs:
with:
name: tarball-testing
- name: Expand
run: tar xfz omniperf-*.tar.gz; rm omniperf-*.tar.gz
run: tar xfz rocprofiler-compute-*.tar.gz; rm rocprofiler-compute-*.tar.gz
- name: Python dependency installs
run: |
cd omniperf-*
cd rocprofiler-compute-*
python3 -m pip install -t${INSTALL_DIR}/python-libs -r requirements.txt
- name: Configure
run: |
cd omniperf-*
cd rocprofiler-compute-*
mkdir build
cd build
cmake -DCMAKE_INSTALL_PREFIX=${INSTALL_DIR}/omniperf \
cmake -DCMAKE_INSTALL_PREFIX=${INSTALL_DIR}/rocprofiler-compute \
-DPYTHON_DEPS=${INSTALL_DIR}/python-libs ..
- name: Install
run: |
cd omniperf-*
cd rocprofiler-compute-*
cd build
make install
- name: Verify expected paths
run: |
# find $INSTALL_DIR
test -d $INSTALL_DIR/omniperf
test -x $INSTALL_DIR/omniperf/bin/omniperf
test -s $INSTALL_DIR/omniperf/libexec/omniperf/VERSION
test -s $INSTALL_DIR/omniperf/libexec/omniperf/VERSION.sha
test -d $INSTALL_DIR/omniperf/libexec/omniperf/omniperf_analyze
test -d $INSTALL_DIR/omniperf/libexec/omniperf/omniperf_profile
test -d $INSTALL_DIR/omniperf/libexec/omniperf/omniperf_soc
test -d $INSTALL_DIR/omniperf/libexec/omniperf/utils
test -s $INSTALL_DIR/omniperf/share/omniperf/sample/vcopy.cpp
test -d $INSTALL_DIR/omniperf/share/omniperf/modulefiles
test -d $INSTALL_DIR/rocprofiler-compute
test -x $INSTALL_DIR/rocprofiler-compute/bin/rocprof-compute
test -s $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/VERSION
test -s $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/VERSION.sha
test -d $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/rocprof_compute_analyze
test -d $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/rocprof_compute_profile
test -d $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/rocprof_compute_soc
test -d $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/utils
test -s $INSTALL_DIR/rocprofiler-compute/share/rocprofiler-compute/sample/vcopy.cpp
test -d $INSTALL_DIR/rocprofiler-compute/share/rocprofiler-compute/modulefiles
- name: Query version (setting PYTHONPATH by hand)
run: |
export PYTHONPATH=${INSTALL_DIR}/python-libs:$PYTHONPATH
$INSTALL_DIR/omniperf/bin/omniperf --version
$INSTALL_DIR/rocprofiler-compute/bin/rocprof-compute --version
- name: Install Lmod
run: sudo apt-get install -y lmod
- name: Access omniperf using modulefile
- name: Access rocprofiler-compute using modulefile
run: |
. /etc/profile.d/lmod.sh
module use $INSTALL_DIR/omniperf/share/omniperf/modulefiles
module load omniperf
module use $INSTALL_DIR/rocprofiler-compute/share/rocprofiler-compute/modulefiles
module load rocprofiler-compute
module list
omniperf --version
rocprof-compute --version
2 changes: 1 addition & 1 deletion .github/workflows/ubuntu-jammy.yml
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ jobs:
run: |
mkdir build
cd build
cmake -DCMAKE_INSTALL_PREFIX=/opt/omniperf -DPYTEST_NUMPROCS=4 ..
cmake -DCMAKE_INSTALL_PREFIX=/opt/rocprofiler-compute -DPYTEST_NUMPROCS=4 ..
make install
- name: CTest- Analyze Commands
run: |
Expand Down
2 changes: 1 addition & 1 deletion AUTHORS
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# This is the list of Omniperf's significant contributors.
# This is the list of ROCm Compute Profiler's significant contributors.
#
# This does not necessarily list everyone who has contributed code,
# especially since many employees of one corporation may be contributing.
Expand Down
4 changes: 2 additions & 2 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Changelog for Omniperf
# Changelog for ROCm Compute Profiler

Full documentation for Omniperf is available at [https://rocm.docs.amd.com/projects/omniperf/en/latest/](https://rocm.docs.amd.com/projects/omniperf/en/latest/).
Full documentation for ROCm Compute Profiler is available at [https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/](https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/).

## Omniperf 2.1.0 for ROCm 6.2.2

Expand Down
74 changes: 42 additions & 32 deletions CMakeLists.txt
Original file line number Diff line number Diff line change
Expand Up @@ -16,20 +16,27 @@ message(STATUS "Hostname: ${LOCALHOST}")
# Versioning info derived from file
file(READ "${CMAKE_CURRENT_SOURCE_DIR}/VERSION" FULL_VERSION_STRING LIMIT_COUNT 1)
string(REGEX REPLACE "(\n|\r)" "" FULL_VERSION_STRING "${FULL_VERSION_STRING}")
set(OMNIPERF_FULL_VERSION "${FULL_VERSION_STRING}")
string(REGEX REPLACE "([0-9]+)\.([0-9]+)\.([0-9]+)(.*)" "\\1.\\2.\\3" OMNIPERF_VERSION
"${FULL_VERSION_STRING}")
set(ROCPROFCOMPUTE_FULL_VERSION "${FULL_VERSION_STRING}")
string(REGEX REPLACE "([0-9]+)\.([0-9]+)\.([0-9]+)(.*)" "\\1.\\2.\\3"
ROCPROFCOMPUTE_VERSION "${FULL_VERSION_STRING}")

# string(REGEX REPLACE "(${OMNIPERF_VERSION})(.*)" "\\2" OMNIPERF_VERSION_TWEAK
# string(REGEX REPLACE "(${ROCPROFCOMPUTE_VERSION})(.*)" "\\2"
# ROCPROFCOMPUTE_VERSION_TWEAK
# "${FULL_VERSION_STRING}")
# string(REGEX REPLACE "^\\." "" OMNIPERF_VERSION_TWEAK "${OMNIPERF_VERSION_TWEAK}")
# string(REGEX REPLACE "^\\." "" ROCPROFCOMPUTE_VERSION_TWEAK
# "${ROCPROFCOMPUTE_VERSION_TWEAK}")

project(
omniperf
VERSION ${OMNIPERF_VERSION}
rocprofiler-compute
VERSION ${ROCPROFCOMPUTE_VERSION}
LANGUAGES C
DESCRIPTION "OmniPerf"
HOMEPAGE_URL "https://github.com/ROCm/omniperf")
DESCRIPTION
"A kernel-level profiling tool for machine learning/HPC workloads running on AMD MI GPUs"
HOMEPAGE_URL "https://github.com/ROCm/rocprofiler-compute")

set(PACKAGE_NAME "rocprofiler-compute")
set(PACKAGE_NAME_UNDERSCORE "rocprofiler_compute")
set(EXECUTABLE_NAME "rocprof-compute")

include(ExternalProject)
include(GNUInstallDirs)
Expand All @@ -39,9 +46,9 @@ find_package(Git)
if(Git_FOUND AND EXISTS "${PROJECT_SOURCE_DIR}/.git")
execute_process(
COMMAND git log --pretty=format:%h -n 1
OUTPUT_VARIABLE OMNIPERF_GIT_REV
OUTPUT_VARIABLE ROCPROFCOMPUTE_GIT_REV
OUTPUT_STRIP_TRAILING_WHITESPACE)
message(STATUS "Git revision: ${OMNIPERF_GIT_REV}")
message(STATUS "Git revision: ${ROCPROFCOMPUTE_GIT_REV}")
set(GIT_CLONE TRUE)
else()
set(GIT_CLONE FALSER)
Expand Down Expand Up @@ -133,18 +140,19 @@ set(MOD_INSTALL_PATH
CACHE STRING "Install path for modulefile")
message(STATUS "Modulefile install path: ${MOD_INSTALL_PATH}")

set(moduleFileTemplate "omniperf.lua.in")
set(moduleFileTemplate "rocprofcompute.lua.in")

configure_file(
${PROJECT_SOURCE_DIR}/cmake/${moduleFileTemplate}
${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${OMNIPERF_FULL_VERSION}.lua @ONLY)
${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${ROCPROFCOMPUTE_FULL_VERSION}.lua @ONLY)

# Thera mods
if(LOCALHOST MATCHES "TheraS01|.*\.thera\.amd\.com|thera-hn")
list(APPEND CMAKE_MESSAGE_INDENT " ")
message(STATUS "Using thera-specific modulefile modification")
file(READ ${PROJECT_SOURCE_DIR}/cmake/modfile.thera.mod mod_additions)
file(APPEND ${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${OMNIPERF_FULL_VERSION}.lua
file(APPEND
${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${ROCPROFCOMPUTE_FULL_VERSION}.lua
${mod_additions})
list(POP_BACK CMAKE_MESSAGE_INDENT)
endif()
Expand Down Expand Up @@ -274,9 +282,9 @@ add_test(
# Install
# ---------

# top-level omniperf utility
# top-level rocprofiler-compute utility
install(
PROGRAMS src/omniperf
PROGRAMS src/${EXECUTABLE_NAME}
DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME}
COMPONENT main)
# python dependency requirements
Expand All @@ -286,16 +294,16 @@ install(
COMPONENT main)
# support files and version info
install(
FILES src/argparser.py src/config.py src/omniperf_base.py src/roofline.py VERSION
VERSION.sha
FILES src/argparser.py src/config.py src/rocprof_compute_base.py src/roofline.py
VERSION VERSION.sha
DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME}
COMPONENT main)
# src/omniperf_analyze
# src/rocprof_compute_analyze
install(
DIRECTORY src/omniperf_analyze
DIRECTORY src/rocprof_compute_analyze
DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME}
COMPONENT main
PATTERN src/omniperf_analyze/tests EXCLUDE
PATTERN src/rocprof_compute_analyze/tests EXCLUDE
PATTERN "__pycache__" EXCLUDE)
# src/utils
install(
Expand All @@ -310,15 +318,15 @@ install(
PROGRAMS ${rooflinebins}
DESTINATION ${CMAKE_INSTALL_BINDIR}
COMPONENT main)
# src/omniperf_soc
# src/rocprof_compute_soc
install(
DIRECTORY src/omniperf_soc
DIRECTORY src/rocprof_compute_soc
DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME}
COMPONENT main
PATTERN "__pycache__" EXCLUDE)
# src/omniperf_profile
# src/rocprof_compute_profile
install(
DIRECTORY src/omniperf_profile
DIRECTORY src/rocprof_compute_profile
DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME}
COMPONENT main
PATTERN "__pycache__" EXCLUDE)
Expand All @@ -339,16 +347,16 @@ install(
PATTERN "workloads" EXCLUDE)
# modulefile
install(
FILES ${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${OMNIPERF_FULL_VERSION}.lua
FILES ${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${ROCPROFCOMPUTE_FULL_VERSION}.lua
DESTINATION ${MOD_INSTALL_PATH}
COMPONENT main)

# top-level symlink for bin/omniperf
# top-level symlink for bin/rocprof-compute
install(
CODE "execute_process(
COMMAND bash -c \"set -e
cd \$ENV{DESTDIR}\${CMAKE_INSTALL_PREFIX}
ln -sf ../${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME}/omniperf ${CMAKE_INSTALL_BINDIR}/omniperf
ln -sf ../${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME}/${EXECUTABLE_NAME} ${CMAKE_INSTALL_BINDIR}/${EXECUTABLE_NAME}
\")"
COMPONENT main)

Expand All @@ -361,7 +369,7 @@ add_custom_target(
COMMAND
${PROJECT_SOURCE_DIR}/utils/update_license.py --source ${PROJECT_SOURCE_DIR}
--license ${PROJECT_SOURCE_DIR}/LICENSE --file
"src/omniperf,cmake/Dockerfile,cmake/rocm_install.sh,docker/docker-entrypoint.sh,src/omniperf_analyze/convertor/mongodb/convert"
"src/${PACKAGE_NAME},cmake/Dockerfile,cmake/rocm_install.sh,docker/docker-entrypoint.sh,src/rocprof_compute_analyze/convertor/mongodb/convert"
)

# TEST collateral
Expand Down Expand Up @@ -396,9 +404,11 @@ set(CPACK_GENERATOR
set(CPACK_PACKAGE_NAME
"${PROJECT_NAME}"
CACHE STRING "")
set(CPACK_PACKAGE_CONTACT "https://github.com/ROCm/omniperf")
set(CPACK_PACKAGE_DESCRIPTION_SUMMARY "Omniperf: tool for GPU performance profiling")
set(CPACK_RPM_PACKAGE_DESCRIPTION "Omniperf is a performance analysis tool for profiling
set(CPACK_PACKAGE_CONTACT "https://github.com/ROCm/rocprofiler-compute")
set(CPACK_PACKAGE_DESCRIPTION_SUMMARY
"ROCm Compute Profiler: tool for GPU performance profiling")
set(CPACK_RPM_PACKAGE_DESCRIPTION
"ROCm Compute Profiler is a performance analysis tool for profiling
machine learning/HPC workloads running on AMD GPUs.")
set(CPACK_PACKAGE_VENDOR "Advanced Micro Devices, Inc.")

Expand Down
Loading