ROCm · coleramos425 · Sep 27, 2024 · Aug 9, 2024 · Aug 12, 2024 · Aug 12, 2024
@@ -0,0 +1,46 @@
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml@pipelines_repo
+
+trigger:
+  batch: true
+  branches:
+    include:
+    - amd-staging
+    - amd-mainline
+  paths:
+    exclude:
+    - .github
+    - docs
+    - '.*.y*ml'
+    - '*.md'
+    - AUTHORS
+    - LICENSE
+    - VERSION
+
+pr:
+  autoCancel: true
+  branches:
+    include:
+    - amd-staging
+    - amd-mainline
+  paths:
+    exclude:
+    - .github
+    - docs
+    - '.*.y*ml'
+    - '*.md'
+    - AUTHORS
+    - LICENSE
+    - VERSION
+  drafts: false
+
+jobs:
+  - template: ${{ variables.CI_COMPONENT_PATH }}/omniperf.yml@pipelines_repo
@@ -10,7 +10,7 @@ updates:
     open-pull-requests-limit: 10
     schedule:
       interval: "daily"
-    target-branch: "dev"
+    target-branch: "amd-staging"
     labels:
       - "documentation"
       - "dependencies"

@@ -2,7 +2,7 @@ name: Documentation
 
 on:
   push:
-    branches: [ main, amd-mainline ]
+    branches: [ amd-mainline ]
     paths:
       - 'docs/archive/docs-2.x/**'
       - 'docs/archive/docs-1.x/**'

@@ -3,9 +3,9 @@ name: Formatting
 
 on:
   push:
-    branches: [ main, dev, amd-mainline, amd-staging ]
+    branches: [ amd-mainline, amd-staging, release/** ]
   pull_request:
-    branches: [ main, dev, amd-mainline, amd-staging ]
+    branches: [ amd-mainline, amd-staging, release/** ]
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

@@ -2,7 +2,7 @@ name: mi-rhel9
 
 on:
   push:
-    branches: [ main, amd-mainline ]
+    branches: [ amd-mainline, release/** ]
 
   # Allows manual execution
   workflow_dispatch:

@@ -4,6 +4,7 @@ on:
   push:
     tags:
       - "v[1-9].[0-9]+.[0-9]+*"
+      - "rocm-[0-9]+.[0-9]+.[0-9]+*"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -42,3 +43,19 @@ jobs:
         with:
           name: omniperf-${{github.ref_name}}.tar.gz
           path: build/omniperf-${{github.ref_name}}.tar.gz
+      - name: Set version
+        run: echo "VERSION=$(cat VERSION)" >> $GITHUB_ENV
+      - name: Determine release name
+        run: |
+          if [[ ${{github.ref_name}} == rocm-* ]]; then
+            echo "RELEASE_NAME=Omniperf ${{ env.VERSION }} for ${{github.ref_name}}"
+          else
+            echo "RELEASE_NAME=Omniperf ${{ env.VERSION }}"
+          fi >> $GITHUB_ENV
+      - name: Upload tarball Release Asset
+        uses: softprops/action-gh-release@v2
+        if: startsWith(github.ref, 'refs/tags/') && github.repository == 'ROCm/omniperf'
+        with:
+          fail_on_unmatched: True
+          files: |
+            build/omniperf-${{github.ref_name}}.tar.gz
@@ -5,9 +5,9 @@ name: RHEL 8
 # Controls when the workflow will run
 on:
   push:
-    branches: [ main, dev, amd-mainline, amd-staging ]
+    branches: [ amd-mainline, amd-staging, release/** ]
   pull_request:
-    branches: [ main, dev, amd-mainline, amd-staging ]
+    branches: [ amd-mainline, amd-staging, release/** ]
 
   # Allows you to run this workflow manually from the Actions tab
   workflow_dispatch:

@@ -2,7 +2,7 @@ name: tarball
 
 on:
   push:
-    branches: [ main, amd-mainline ]
+    branches: [ amd-mainline, release/** ]
   pull_request:
 
 concurrency:

@@ -4,9 +4,9 @@ name: Ubuntu 22.04
 
 on:
   push:
-    branches: [ main, dev, amd-mainline, amd-staging ]
+    branches: [ amd-mainline, amd-staging, release/** ]
   pull_request:
-    branches: [ main, dev, amd-mainline, amd-staging ]
+    branches: [ amd-mainline, amd-staging, release/** ]
 
   # Allows you to run this workflow manually from the Actions tab
   workflow_dispatch:

@@ -1,11 +1,42 @@
-Version 2.0.1 (03 Jun 2024)
+# Changelog for Omniperf
 
-  * new option to force hardware target via OMNIPERF_ARCH_OVERRIDE global (#370)
+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/).
+
+## Omniperf 2.1.0 for ROCm 6.2.2
+
+### Changes
+
+  * enable rocprofv1 for MI300 hardware (#391)
+  * refactoring and updating documemtation (#362, #394, #398, #414, #420)
+  * branch renaming and workflow updates (#389, #404, #409)
+  * bug fix for analysis output
+  * add dependency checks on application launch (#393)
+  * patch for profiling multi-process/multi-GPU applications (#376, #396)
+  * packaging updates (#386)
+  * rename CHANGES to CHANGELOG.md (#410)
+  * rollback Grafana version in Dockerfile for Angular plugin compatibility (#416)
+  * enable CI triggers for Azure CI (#426)
+  * add GPU model distinction for MI300 systems (#423)
+  * new MAINTAINERS.md guide for omniperf publishing procedures (#402)
+
+### Optimizations
+
+  * reduced running time of Omniperf when profiling (#384) 
+  * console logging improvements
+
+## Omniperf 2.0.1 for ROCm 6.2.0
+
+### Changes
+
+  * new option to force hardware target via `OMNIPERF_ARCH_OVERRIDE` global (#370)
   * CI/CD support for MI300 hardware (#373)
-  * cmake build improvements (#374)
   * support for MI308X hardware (#375)
 
-Version 2.0.0 (17 May 2024)
+### Optimizations
+
+  * cmake build improvements (#374)
+
+## Omniperf 2.0.0 (17 May 2024)
 
   * improved logging than spans all modes (#177) (#317) (#335) (#341)
   * overhauled CI/CD that spans all modes (#179)
@@ -20,7 +51,7 @@ Version 2.0.0 (17 May 2024)
   * new --quiet option will suppress verbose output and show a progress bar (#308)
   * roofline support for Ubuntu 22.04 (#319)
 
-Version 1.1.0-PR1 (13 Oct 2023)
+## Omniperf 1.1.0-PR1 (13 Oct 2023)
 
   * standardize headers to use 'avg' instead of 'mean'
   * add color code thresholds to standalone gui to match grafana
@@ -29,11 +60,11 @@ Version 1.1.0-PR1 (13 Oct 2023)
   * patch grafana plugin module to address a known issue in the latest version (#186)
   * enhanced communication between analyze mode kernel flags (#187)
 
-Version 1.0.10 (22 Aug 2023)
+## Omniperf 1.0.10 (22 Aug 2023)
 
   * critical patch for detection of llvm in rocm installs on SLURM systems
 
-Version 1.0.9 (17 Aug 2023)
+## Omniperf 1.0.9 (17 Aug 2023)
 
   * add units to L2 per-channel panel (#133)
   * new quickstart guide for Grafana setup in docs (#135)
@@ -45,7 +76,7 @@ Version 1.0.9 (17 Aug 2023)
   * general metric updates and enhancements (#144, #155, #159)
   * add min/max/avg breakdown to instruction mix panel (#154)
 
-Version 1.0.8 (30 May 2023)
+## Omniperf 1.0.8 (30 May 2023)
 
   * add `--kernel-names` option to toggle kernelName overlay in standalone roofline plot (#93)
   * remove unused python modules (#96)
@@ -66,7 +97,7 @@ Version 1.0.8 (30 May 2023)
   * manually merge rocprof runs, overriding default rocprofiler implementation (#125)
   * fixed compatibility issues with Python 3.11 (#131)
 
-Version 1.0.8-PR2 (17 Apr 2023)
+## Omniperf 1.0.8-PR2 (17 Apr 2023)
 
   * ux improvements in standalone GUI (#101)
   * enhanced readability for filtering dropdowns in standalone GUI (#102)
@@ -75,14 +106,14 @@ Version 1.0.8-PR2 (17 Apr 2023)
   * adding dockerfiles for all supported Linux distros
   * new examples for `--roof-only` and `--kernel` options added to documentation
 
-Version 1.0.8-PR1 (13 Mar 2023)
+## Omniperf 1.0.8-PR1 (13 Mar 2023)
 
   * add `--kernel-names` option to toggle kernelName overlay in standalone roofline plot (#93)
   * remove unused python modules (#96)
   * fix empirical roofline calculation for single dispatch workloads (#97)
   * match color of arithmetic intensity points to corresponding bw lines
 
-Version 1.0.7 (21 Feb 2023)
+## Omniperf 1.0.7 (21 Feb 2023)
 
   * update documentation (#52, #64)
   * improved detection of invalid command line arguments (#58, #76)
@@ -96,12 +127,12 @@ Version 1.0.7 (21 Feb 2023)
   * improve error message when no GPU(s) detected (#85)
   * separate CI tests by Linux distro and add status badges
 
-Version 1.0.6 (21 Dec 2022)
+## Omniperf 1.0.6 (21 Dec 2022)
 
   * CI update: documentation now published via github action (#22)
   * better error detection for incomplete ROCm installs (#56)
 
-Version 1.0.5 (13 Dec 2022)
+## Omniperf 1.0.5 (13 Dec 2022)
 
   * store application command-line parameters in profiling output (#27)
   * enable additional normalizations in CLI mode (#30)
@@ -112,7 +143,7 @@ Version 1.0.5 (13 Dec 2022)
   * enhanced subprocess logging to identify critical errors in rocprofiler (#50)
   * maintain git sha in production installs from tarball (#53)
 
-Version 1.0.4 (11 Nov 2022)
+## Omniperf 1.0.4 (11 Nov 2022)
 
   * update python requirements.txt with minimum versions for numpy and pandas
   * addition of progress bar indicator in web-based GUI (#8)
@@ -121,6 +152,6 @@ Version 1.0.4 (11 Nov 2022)
   * variety of documentation updates  
   * added an optional argument to vcopy.cpp workload example to specify device id
 
-Version 1.0.3 (07 Nov 2022)
+## Omniperf 1.0.3 (07 Nov 2022)
 
   * initial Omniperf release
@@ -416,6 +416,7 @@ set(CPACK_RPM_PACKAGE_PROVIDES "${CPACK_PACKAGE_NAME}")
 set(CPACK_RPM_COMPONENT_INSTALL ON)
 set(CPACK_RPM_PACKAGE_RELEASE_DIST ON)
 set(CPACK_RPM_FILE_NAME "RPM-DEFAULT")
+set(CPACK_RPM_SPEC_MORE_DEFINE "%undefine __brp_mangle_shebangs")
 
 if(DEFINED CPACK_PACKAGING_INSTALL_PREFIX)
     set(CPACK_RPM_EXCLUDE_FROM_AUTO_FILELIST_ADDITION "${CPACK_PACKAGING_INSTALL_PREFIX}")

@@ -0,0 +1,29 @@
+# Maintainers Guide to Omniperf
+
+## Publishing a release
+
+Before publishing a new Omniperf release, please review this checklist to ensure all prerequisites are met:
+
+1) **Ensure [VERSION](VERSION) file is updated** to reflect your desired release version.
+2) **Sync `amd-mainline` with `amd-staging`**. A rebase may be required to pull all the desired patches from the development branch to our stable mainline. Click [here](https://github.com/ROCm/omniperf/compare/amd-mainline...amd-staging) to begin that process.
+3) **Update [CHANGES](CHANGES)** to reflect all major modifications to the codebase since the last release. When modifying [CHANGES](CHANGES) please ensure formatting is consistent with the rest of the ROCm software stack. See [this template](https://github.com/ROCm/hipTensor/blob/develop/CHANGELOG.md) for reference.
+4) **Confirm all CI tests are passing**. You can easily confirm this by peeking the passing status of all GitHub continuous integration tests.
+5) **Create a tag from `amd-mainline`**. More information on tagging can be found at [Git Docs - Tagging](https://git-scm.com/book/en/v2/Git-Basics-Tagging). 
+
+> [!NOTE]
+Note: A successful tag should trigger the [packaging action](.github/workflows/packaging.yml) which will produce a tarball artifact. **This artifact needs to be included as an asset in your release**. Please find that the [packaging action](.github/workflows/packaging.yml) will automatically create a draft release with your tarball attached.
+
+Once you've completed the above checklist, you are ready to publish your release. Please ensure you follow formatting from [past Omniperf releases](https://github.com/ROCm/omniperf/releases) for consistency. Some important aspects of our release formatting include:
+
+- Date of release is included in "Release Title".
+- Updates are called out in "Release Description". Updates should mirror those listed in [CHANGES](CHANGES).
+- Links to documentation and associated release tarball are called out in "Release Description".
+- The tarball artifact from the corresponding tag is added to "Release Assets".
+
+### Publishing a release for ROCm
+
+If you are preparing for a new ROCm release, note that the [rocm-ci](https://github.com/rocm-ci) bot managed by DevOps will be triggering a tag automatically. This tag will follow the format `rocm-X.X.X`.
+
+Traditionally, we will bump the Omniperf [VERSION](VERSION) with a new ROCm release. When we bump the version and reach the prerequisite step (5) above, try tagging with `vX.X.X` to validate the release tarball generated by the [packaging action](.github/workflows/packaging.yml).
+
+In addition to the prerequisites mentioned above, please make sure that all changes have been merged from `amd-staging` -> `release/rocm-rel-X.X.X` to ensure that the "rocm-ci" bot will capture all your changes. It is easiest to file a single pull request ahead of the ROCm release.
@@ -50,11 +50,11 @@ style reference is provided below for convenience:
                   Keith Lowery and
                   Nicholas Curtis and
                   Cristian Di Pietrantonio},
-  title        = {AMDResearch/omniperf: v2.0.1 (03 June 2024)},
-  month        = june,
+  title        = {AMDResearch/omniperf: v2.1.0 (27 Sept 2024)},
+  month        = sept,
   year         = 2024,
   publisher    = {Zenodo},
-  version      = {v2.0.1},
+  version      = {v2.1.0},
   doi          = {10.5281/zenodo.7314631},
   url          = {https://doi.org/10.5281/zenodo.7314631}
 }

@@ -1 +1 @@
-2.0.1
+2.1.0
@@ -171,7 +171,7 @@ $ omniperf analyze -p workloads/vcopy/mi200/ --list-metrics gfx90a
 ├─────────┼─────────────────────────────┤
 ...
  ```
- 2. Choose your own customized subset of metrics with `-b` (a.k.a. `--metric`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/main/src/omniperf_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light).
+ 2. Choose your own customized subset of metrics with `-b` (a.k.a. `--metric`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/amd-mainline/src/omniperf_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light).
 ```shell-session
 $ omniperf analyze -p workloads/vcopy/mi200/ -b 2
 --------

@@ -181,7 +181,7 @@ Analysis mode = cli
                 2.1.30 -> L1I Fetch Latency
 ...
 ```
-3. Choose your own customized subset of metrics with `-b` (a.k.a. `--block`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/main/src/omniperf_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light).
+3. Choose your own customized subset of metrics with `-b` (a.k.a. `--block`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/amd-mainline/src/omniperf_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light).
 ```shell-session
 $ omniperf analyze -p workloads/vcopy/MI200/ -b 2
 --------