2 issues here

.github/workflows/cmake.yml

@@ -0,0 +1,86 @@
+# Workflow with cmake build system
+name: Short-Tests-CMake
+
+# Controls when the workflow will run
+on:
+  # Triggers the workflow on push or pull request events but only for the mydev branch
+  push:
+    branches-ignore:
+      - "gh-readonly-queue**"
+  merge_group:
+  pull_request:
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+# A workflow run is made up of one or more jobs that can run sequentially or in parallel
+jobs:
+  build-TITANV:
+    runs-on: ubuntu-latest
+    container:
+      image: tgrogers/accel-sim_regress:Ubuntu-22.04-cuda-11.7
+      env:
+        CONFIG: TITANV
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Run Simulation
+        run: /bin/bash $GITHUB_WORKSPACE/short-tests-cmake.sh
+
+  build-TITANV-LOCALXBAR:
+    runs-on: ubuntu-latest
+    container:
+      image: tgrogers/accel-sim_regress:Ubuntu-22.04-cuda-11.7
+      env:
+        CONFIG: TITANV-LOCALXBAR
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Run Simulation
+        run: /bin/bash $GITHUB_WORKSPACE/short-tests-cmake.sh
+
+  build-QV100:
+    runs-on: ubuntu-latest
+    container:
+      image: tgrogers/accel-sim_regress:Ubuntu-22.04-cuda-11.7
+      env:
+        CONFIG: QV100
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Run Simulation
+        run: /bin/bash $GITHUB_WORKSPACE/short-tests-cmake.sh
+
+  build-2060:
+    runs-on: ubuntu-latest
+    container:
+      image: tgrogers/accel-sim_regress:Ubuntu-22.04-cuda-11.7
+      env:
+        CONFIG: RTX2060
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Run Simulation
+        run: /bin/bash $GITHUB_WORKSPACE/short-tests-cmake.sh
+
+  build-3070:
+    runs-on: ubuntu-latest
+    container:
+      image: tgrogers/accel-sim_regress:Ubuntu-22.04-cuda-11.7
+      env:
+        CONFIG: RTX3070
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Run Simulation
+        run: /bin/bash $GITHUB_WORKSPACE/short-tests-cmake.sh

.github/workflows/main.yml

@@ -0,0 +1,105 @@
+# This is a basic workflow to help you get started with Actions
+
+name: Short-Tests
+
+# Controls when the workflow will run
+on:
+  push:
+    branches-ignore:
+      - "gh-readonly-queue**"
+  merge_group:
+  pull_request:
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+# A workflow run is made up of one or more jobs that can run sequentially or in parallel
+jobs:
+  build-TITANV:
+    runs-on: ubuntu-latest
+    container:
+      image: tgrogers/accel-sim_regress:Ubuntu-22.04-cuda-11.7
+      env:
+        CONFIG: TITANV
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Run Simulation
+        run: /bin/bash $GITHUB_WORKSPACE/short-tests.sh
+
+  build-TITANV-LOCALXBAR:
+    runs-on: ubuntu-latest
+    container:
+      image: tgrogers/accel-sim_regress:Ubuntu-22.04-cuda-11.7
+      env:
+        CONFIG: TITANV-LOCALXBAR
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Run Simulation
+        run: /bin/bash $GITHUB_WORKSPACE/short-tests.sh
+
+  build-QV100:
+    runs-on: ubuntu-latest
+    container:
+      image: tgrogers/accel-sim_regress:Ubuntu-22.04-cuda-11.7
+      env:
+        CONFIG: QV100
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Run Simulation
+        run: /bin/bash $GITHUB_WORKSPACE/short-tests.sh
+
+  build-2060:
+    runs-on: ubuntu-latest
+    container:
+      image: tgrogers/accel-sim_regress:Ubuntu-22.04-cuda-11.7
+      env:
+        CONFIG: RTX2060
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Run Simulation
+        run: /bin/bash $GITHUB_WORKSPACE/short-tests.sh
+
+  build-3070:
+    runs-on: ubuntu-latest
+    container:
+      image: tgrogers/accel-sim_regress:Ubuntu-22.04-cuda-11.7
+      env:
+        CONFIG: RTX3070
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Run Simulation
+        run: /bin/bash $GITHUB_WORKSPACE/short-tests.sh
+  format-code:
+    if: github.event_name == 'pull_request'
+    runs-on: tgrogers-raid
+    needs: [build-TITANV, build-TITANV-LOCALXBAR, build-QV100, build-2060, build-3070]
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{github.event.pull_request.head.ref}}
+          repository: ${{github.event.pull_request.head.repo.full_name}}
+          ssh-key: ''
+
+      - name: Run clang-format
+        run: |
+          git config user.name "purdue-jenkins"
+          git config user.email "[email protected]"
+          git remote set-url origin [email protected]:${{github.event.pull_request.head.repo.full_name}}
+          git remote -v
+          /bin/bash ./format-code.sh
+          if git status --untracked-files=no | grep -q "nothing to commit"; then echo "No changes to commit."; else git commit -a -m "Automated Format"; git push; fi

.github/workflows/sst_integration.yml

@@ -0,0 +1,80 @@
+# Workflow with cmake build system
+name: SST Integration Test
+
+# Controls when the workflow will run
+on:
+  # Triggers the workflow on push or pull request events but only for the mydev branch
+  push:
+    branches-ignore:
+      - "gh-readonly-queue**"
+  pull_request:
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+# A workflow run is made up of one or more jobs that can run sequentially or in parallel
+jobs:
+  build-QV100:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        # test_type: [simple, medium, long]
+        test_type: [simple, medium]
+    container:
+      image: tgrogers/accel-sim_regress:SST-Integration-Ubuntu-22.04-cuda-11.7-llvm-18.1.8-riscv-gnu-2024.08.06-nightly
+      env:
+        CONFIG: QV100
+        GPU_ARCH: sm_70
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+      - name: Build GPGPU-Sim in SST mode
+        run: |
+          source ./setup_environment
+          make -j4
+      - name: Prepare SST dependencies
+        run: |
+          apt install -y openmpi-bin openmpi-common libtool libtool-bin autoconf python3 python3-dev automake build-essential git
+      # Use personal repo for now
+      - name: Build SST-Core
+        run: |
+          git clone https://github.com/William-An/sst-core.git
+          cd sst-core
+          git pull
+          git checkout devel
+          ./autogen.sh
+          ./configure --prefix=`realpath ../sstcore-install` --disable-mpi --disable-mem-pools
+          make -j4
+          make install
+          cd ..
+          rm -rf ./sst-core
+      # Use personal repo for now
+      - name: Build SST-Elements
+        run: |
+          git clone https://github.com/William-An/sst-elements.git
+          source ./setup_environment
+          cd sst-elements
+          git pull
+          git checkout balar-mmio-vanadis-llvm
+          ./autogen.sh
+          ./configure --prefix=`realpath ../sstelements-install` --with-sst-core=`realpath ../sstcore-install` --with-cuda=$CUDA_INSTALL_PATH --with-gpgpusim=$GPGPUSIM_ROOT
+          make -j4
+          make install
+      # Have to resource the gpu app
+      # Also fake a SDK since rodinia 2.0 does not need this, speed things up on github
+      - name: Balar Test
+        run: |
+          pip install testtools blessings pygments
+          source ./setup_environment
+          mkdir 4.2
+          mkdir fake_sdk
+          export NVIDIA_COMPUTE_SDK_LOCATION=$(readlink -f ./fake_sdk)
+          source $GPUAPPS_ROOT/src/setup_environment sst
+          rm -rf 4.2
+          rm -f gpucomputingsdk_4.2.9_linux.run
+          ./sstcore-install/bin/sst-test-elements -w "*balar*${{ matrix.test_type }}*"

.gitignore

@@ -61,3 +61,4 @@ debug_tools/WatchYourStep/ptxjitplus/*.ptx
 accel-sim-framework/
 gpu-app-collection/
 
+setup

CHANGES

@@ -1,4 +1,20 @@
 LOG:
+Version 4.2.0 vs 4.1.0 
+- Added AccelWattch power model v1.0 which replaces GPUWattch. 
+- Added AccelWattch XML configuration files for SM7_QV100, SM7_TITANV, SM75_RTX2060_S, SM6_TITANX. Note that all these AccelWattch XML configuration files are tuned only for SM7_QV100. 
+
+Version 4.1.0 versus 4.0.0
+-Features:
+1- Supporting L1 write-allocate with sub-sector writing policy as in Volta+ hardware, and changing the Volta+ cards config to make L1 write-allocate with write-through
+2- Making the L1 adaptive cache policy to be configurable 
+3- Adding Ampere RTX 3060 config files
+-Bugs:
+1- Fixing L1 bank hash function bug
+2- Fixing L1 read hit counters in gpgpu-sim to match nvprof, to achieve more accurate L1 correlation with the HW
+3- Fixing bugs in lazy write handling, thanks to Gwendolyn Voskuilen from Sandia labs for this fix
+4- Fixing the backend pipeline for sub_core model 
+5- Fixing Memory stomp bug at the shader_config
+6- Some code refactoring:
 Version 4.0.0 (development branch) versus 3.2.3
 -Front-End:
 1- Support .nc cache modifier and __ldg function to access the read-only L1D cache