benchmark.yml

name: Benchmark

on:
  pull_request:
    paths:
      - crates/**
      - Cargo.toml
      - py-polars/tests/benchmark/**
      - .github/workflows/benchmark.yml
  push:
    branches:
      - main
    paths:
      - crates/**
      - Cargo.toml
      - py-polars/tests/benchmark/**
      - .github/workflows/benchmark.yml

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

env:
  SCCACHE_GHA_ENABLED: 'true'
  RUSTC_WRAPPER: sccache

jobs:
  main:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.12'

      - name: Create virtual environment
        run: |
          python -m venv .venv
          echo "$GITHUB_WORKSPACE/.venv/bin" >> $GITHUB_PATH

      - name: Install Python dependencies
        working-directory: py-polars
        run: pip install -r requirements-dev.txt

      - name: Load benchmark data from cache
        id: cache-data
        uses: actions/cache/restore@v4
        with:
          path: py-polars/tests/benchmark/G1_1e7_1e2_5_0.csv
          key: benchmark-data

      - name: Set up R
        if: steps.cache-data.outputs.cache-hit != 'true'
        uses: r-lib/actions/setup-r@v2
        with:
          r-version: '3.5.3'

      - name: Generate data
        if: steps.cache-data.outputs.cache-hit != 'true'
        working-directory: py-polars/tests/benchmark
        run: |
          Rscript -e 'install.packages("data.table", repos="https://cloud.r-project.org")'
          Rscript groupby-datagen.R 1e7 1e2 5 0

      - name: Save benchmark data in cache
        if: github.ref_name == 'main'
        uses: actions/cache/save@v4
        with:
          path: py-polars/tests/benchmark/G1_1e7_1e2_5_0.csv
          key: ${{ steps.cache-data.outputs.cache-primary-key }}

      - name: Set up Rust
        run: rustup show

      - name: Cache Rust
        uses: Swatinem/rust-cache@v2
        with:
          workspaces: py-polars
          save-if: ${{ github.ref_name == 'main' }}

      - name: Run sccache-cache
        uses: mozilla-actions/sccache-action@v0.0.3

      - name: Install Polars release build
        env:
          RUSTFLAGS: -C embed-bitcode -D warnings
        working-directory: py-polars
        run: maturin develop --release -- -C codegen-units=8 -C lto=thin -C target-cpu=native

      - name: Run H2O AI database benchmark - on strings
        working-directory: py-polars/tests/benchmark
        run: python run_h2oai_benchmark.py on_strings

      - name: Run H2O AI database benchmark - on categoricals
        working-directory: py-polars/tests/benchmark
        run: python run_h2oai_benchmark.py

      - name: Run various benchmark tests
        working-directory: py-polars
        run: pytest -m benchmark --durations 0 -v