Merge branch 'main' into docs/refactor

.github/workflows/mi-rhel9.yml

@@ -81,13 +81,11 @@ jobs:
           mkdir build
           cd build
           ml cmake
-          cmake -DENABLE_COVERAGE=ON -DPYTEST_NUMPROCS=8 ..
-      - name: Create HIP binary (vcopy)
-        run: |
-          hipcc --offload-arch=$CI_ARCH -o tests/vcopy ./sample/vcopy.cpp
-      - name: Run [profile] mode
+          cmake -DENABLE_TESTS=ON -DCMAKE_HIP_ARCHITECTURES=$CI_ARCH -DENABLE_COVERAGE=ON -DPYTEST_NUMPROCS=8 ..
+      - name: Build tests and Run [profile] mode
         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
       - name: Run [analyze workloads] mode
         if: '!cancelled()'

.github/workflows/packaging.yml

@@ -38,7 +38,7 @@ jobs:
       - name: Rename tarball
         run: mv build/omniperf-*.tar.gz build/omniperf-${{github.ref_name}}.tar.gz
       - name: Archive tarball
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: omniperf-${{github.ref_name}}.tar.gz
           path: build/omniperf-${{github.ref_name}}.tar.gz

.github/workflows/rhel-8.yml

@@ -51,4 +51,4 @@ jobs:
       - name: CTest- Analyze Workloads
         run: |
           cd build
-          ctest --verbose -R test_analyze_workloads test_saved_analysis
+          ctest --verbose -R test_analyze_workloads

.github/workflows/ubuntu-jammy.yml

@@ -50,4 +50,4 @@ jobs:
       - name: CTest- Analyze Workloads
         run: |
           cd build
-          ctest --verbose -R test_analyze_workloads test_saved_analysis
+          ctest --verbose -R test_analyze_workloads

AUTHORS

@@ -6,6 +6,7 @@
 # source control.
 Xiaomin Lu
 Cole Ramos
+Karl Schultz
 Fei Zheng
+Nicholas Curtis
 Jose Santos
-Karl Schultz

CHANGES

@@ -1,3 +1,25 @@
+Version 2.0.1 (03 Jun 2024)
+
+  * 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)
+
+  * improved logging than spans all modes (#177) (#317) (#335) (#341)
+  * overhauled CI/CD that spans all modes (#179)
+  * extensible SoC classes to better support adding new hardware configs (#180)
+  * --kernel-verbose no longer overwrites kernel names (#193)
+  * general cleanup and improved organization of source code (#200) (#210) 
+  * separate requirement files for docs and testing dependencies (#205) (#262) (#358)
+  * add support for MI300 hardware (#231)
+  * upgrade Grafana assets and build script to latest release (#235)
+  * update minimum ROCm and Python requirements (#277)
+  * sort rocprofiler input files prior to profiling (#304)
+  * 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)
 
   * standardize headers to use 'avg' instead of 'mean'

CMakeLists.txt

@@ -156,6 +156,16 @@ if(${GIT_CLONE})
 endif()
 
 # Setup testing collateral
+
+option(ENABLE_TESTS "Enable compilation of testing collateral" OFF)
+set(CMAKE_HIP_FLAGS_RELEASE "-O2")
+if(${ENABLE_TESTS})
+    enable_language("C" "HIP")
+    add_subdirectory(tests)
+
+endif()
+message(STATUS "Enable tests compilation: ${ENABLE_TESTS}")
+
 enable_testing()
 
 option(ENABLE_COVERAGE "Enable code coverage" OFF)
@@ -251,15 +261,6 @@ add_test(
             ${COV_OPTION} ${PROJECT_SOURCE_DIR}/tests/test_analyze_workloads.py
     WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
 
-# ---------------------------
-# saved analysis tests
-# ---------------------------
-
-add_test(
-    NAME test_saved_analysis
-    COMMAND pytest ${COV_OPTION} ${PROJECT_SOURCE_DIR}/tests/test_saved_analysis.py
-    WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
-
 # ---------
 # Install
 # ---------
@@ -312,6 +313,11 @@ install(
     DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME}
     COMPONENT main
     PATTERN "__pycache__" EXCLUDE)
+# grafana assets
+install(
+    DIRECTORY grafana
+    DESTINATION ${CMAKE_INSTALL_DATADIR}/${PROJECT_NAME}
+    COMPONENT main)
 # samples
 install(
     DIRECTORY sample

README.md

@@ -10,7 +10,7 @@
 ## General
 Omniperf is a system performance profiling tool for machine
 learning/HPC workloads running on AMD MI GPUs. The tool presently
-targets usage on MI100 and MI200 accelerators.
+targets usage on MI100, MI200, and MI300 accelerators.
 
 * For more information on available features, installation steps, and
 workload profiling and analysis, please refer to the online
@@ -50,11 +50,11 @@ style reference is provided below for convenience:
                   Keith Lowery and
                   Nicholas Curtis and
                   Cristian Di Pietrantonio},
-  title        = {AMDResearch/omniperf: v1.1.0-PR1 (13 Oct 2023)},
-  month        = oct,
-  year         = 2023,
+  title        = {AMDResearch/omniperf: v2.0.1 (03 June 2024)},
+  month        = june,
+  year         = 2024,
   publisher    = {Zenodo},
-  version      = {v1.1.0-PR1},
+  version      = {v2.0.1},
   doi          = {10.5281/zenodo.7314631},
   url          = {https://doi.org/10.5281/zenodo.7314631}
 }

VERSION

@@ -1 +1 @@
-2.0.0
+2.0.1

grafana/.dockerignore

@@ -0,0 +1 @@
+/dashboards

grafana/Dockerfile

@@ -0,0 +1,75 @@
+# -----------------------------------------------------------------------
+# NOTE:
+# Dependencies are not included as part of Omniperf.
+# It's the user's responsibility to accept any licensing implications 
+# before building the project
+# -----------------------------------------------------------------------
+
+FROM ubuntu:22.04
+WORKDIR /app
+
+USER root
+
+ENV DEBIAN_FRONTEND noninteractive
+ENV TZ "US/Chicago"
+ENV NVM_DIR /usr/local/nvm
+ENV NODE_VERSION 20.12.2
+
+ADD plugins/omniperf_plugin /var/lib/grafana/plugins/omniperf_plugin
+
+# Install Grafana and MongoDB Community Edition
+RUN apt-get update && \
+    apt-get install -y apt-transport-https software-properties-common wget && \
+    mkdir -p /etc/apt/keyrings/ && \
+    wget -q -O - https://apt.grafana.com/gpg.key | gpg --dearmor | tee /etc/apt/keyrings/grafana.gpg > /dev/null && \
+    echo "deb [signed-by=/etc/apt/keyrings/grafana.gpg] https://apt.grafana.com stable main" | tee -a /etc/apt/sources.list.d/grafana.list && \
+    apt-get update && \
+    apt-get install -y grafana && \
+    apt-get install -y gnupg curl && \
+    curl -fsSL https://www.mongodb.org/static/pgp/server-7.0.asc | gpg -o /usr/share/keyrings/mongodb-server-7.0.gpg  --dearmor && \
+    echo "deb [ arch=amd64,arm64 signed-by=/usr/share/keyrings/mongodb-server-7.0.gpg ] https://repo.mongodb.org/apt/ubuntu jammy/mongodb-org/7.0 multiverse" | tee /etc/apt/sources.list.d/mongodb-org-7.0.list && \
+    apt-get update && \
+    apt-get install -y mongodb-org
+
+RUN mkdir /usr/local/nvm && \
+    curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash && \
+    . $NVM_DIR/nvm.sh && \
+    nvm install $NODE_VERSION && \
+    nvm alias default $NODE_VERSION && \
+    nvm use default
+
+ENV NODE_PATH $NVM_DIR/v$NODE_VERSION/lib/node_modules
+ENV PATH $NVM_DIR/versions/node/v$NODE_VERSION/bin:$PATH
+
+RUN npm --version && \
+    node --version
+
+# Install Grafana plugins
+RUN apt-get install -y tzdata systemd apt-utils npm vim net-tools && \
+    /usr/sbin/grafana-cli plugins install michaeldmoore-multistat-panel && \
+    /usr/sbin/grafana-cli plugins install ae3e-plotly-panel && \
+    /usr/sbin/grafana-cli plugins install natel-plotly-panel && \
+    /usr/sbin/grafana-cli plugins install grafana-image-renderer && \
+    /usr/sbin/grafana-cli plugins install aceiot-svg-panel && \
+    chown root:grafana /etc/grafana && \
+    cd /var/lib/grafana/plugins/omniperf_plugin && \
+    npm install && \
+    npm run build && \
+    apt-get autoremove -y && \
+    apt-get autoclean -y && \
+    sed -i "s/  bindIp.*/  bindIp: 0.0.0.0/" /etc/mongod.conf && \
+    mkdir -p /var/lib/grafana && \
+    touch /var/lib/grafana/grafana.lib && \
+    chown grafana:grafana /var/lib/grafana/grafana.lib 
+
+# Overwrite grafana ini file
+COPY grafana.ini /etc/grafana
+
+# Switch Grafana port to 4000
+RUN sed -i "s/^;http_port = 3000/http_port = 4000/" /etc/grafana/grafana.ini && \
+    sed -i "s/^http_port = 3000/http_port = 4000/" /usr/share/grafana/conf/defaults.ini
+
+# Starts mongo and grafana-server at startup
+COPY docker-entrypoint.sh /docker-entrypoint.sh
+
+ENTRYPOINT [ "/docker-entrypoint.sh" ]

docker-compose.yml → grafana/docker-compose.yml

@@ -13,6 +13,10 @@ services:
     container_name: omniperf-grafana-v1.0
     restart: always
     build: .
+    environment:
+      - GF_PATHS_CONFIG="grafana/etc/grafana.ini"
+      - GF_PLUGINS_ALLOW_LOADING_UNSIGNED_PLUGINS=amd-omniperf-data-plugin
+      - GF_DEFAULT_APP_MODE=development
     ports:
       - "14000:4000"
     volumes:

docker/docker-entrypoint.sh → grafana/docker-entrypoint.sh

@@ -24,7 +24,7 @@
 # SOFTWARE.
 ##############################################################################el
 
-pushd /var/lib/grafana/plugins/omniperfData_plugin
+pushd /var/lib/grafana/plugins/omniperf_plugin
 npm run server &
 popd
 

docker/grafana.ini → grafana/grafana.ini

@@ -4,7 +4,7 @@
 # change
 
 # possible values : production, development
-;app_mode = production
+app_mode = development
 
 # instance name, defaults to HOSTNAME environment variable value or hostname if HOSTNAME var is empty
 ;instance_name = ${HOSTNAME}

grafana/plugins/omniperf_plugin/.gitignore

@@ -0,0 +1,7 @@
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Nuxt.js build / generate output
+.nuxt
+dist