update doc #5
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Enwik8 Benchmark | |
| on: | |
| workflow_dispatch: | |
| push: | |
| jobs: | |
| enwik8-benchmark: | |
| runs-on: ubuntu-latest | |
| permissions: | |
| actions: write | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions-rust-lang/setup-rust-toolchain@v1 | |
| - name: Build | |
| run: cargo build --release | |
| - name: Install zstd | |
| run: sudo apt-get -y update && sudo apt-get -y install zstd | |
| - name: Preparing enwik8 | |
| run: xz -d < test/enwik8.xz >enwik8 | |
| - name: Benchmark with with enwik8 | |
| run: | | |
| (time gzip < enwik8 >enwik8.gz) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >gzip.enc_time | |
| (time gzip -d < enwik8.gz >enwik8.ungz) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >gzip.dec_time | |
| (time bzip2 < enwik8 >enwik8.bz2) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >bzip2.enc_time | |
| (time bzip2 -d < enwik8.bz2 >enwik8.unbz2) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >bzip2.dec_time | |
| (time zstd -11 < enwik8 >enwik8.zstd11) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >zstd11.enc_time | |
| (time zstd -d < enwik9.zstd10 >enwik8.unzstd11) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >zstd11.dec_time | |
| (time zstd -19 < enwik8 >enwik8.zstd19) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >zstd19.enc_time | |
| (time zstd -d < enwik8.zstd19 >enwik8.unzstd19) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >zstd19.dec_time | |
| (time xz -6 < enwik8 >enwik8.xz) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >xz.enc_time | |
| (time xz -d < enwik8.xz >enwik8.unxz) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >xz.dec_time | |
| (time target/release/orz encode --silent -l0 < enwik8 >enwik8.orz0) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >orz0.enc_time | |
| (time target/release/orz decode --silent < enwik8.orz0 >enwik8.unorz0) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >orz0.dec_time | |
| (time target/release/orz encode --silent -l1 < enwik8 >enwik8.orz1) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >orz1.enc_time | |
| (time target/release/orz decode --silent < enwik8.orz1 >enwik8.unorz1) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >orz1.dec_time | |
| (time target/release/orz encode --silent -l2 < enwik8 >enwik8.orz2) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >orz2.enc_time | |
| (time target/release/orz decode --silent < enwik8.orz2 >enwik8.unorz2) 2>&1 | grep -Poi 'real\s+\K[0-9.ms]+' >orz2.dec_time | |
| cmp enwik8.unorz0 enwik8 | |
| cmp enwik8.unorz1 enwik8 | |
| cmp enwik8.unorz2 enwik8 | |
| - name: "==================== Benchmark Result ====================" | |
| run: | | |
| echo "" | |
| printf "+----------+------------------+--------------+--------------+\n" | |
| printf "| | %16s | %12s | %12s |\n" "Compressed Size" "Encode time" "Decode time" | |
| printf "|----------+------------------+--------------+--------------|\n" | |
| printf "| gzip | %16s | %12s | %12s |\n" "$(wc -c < enwik8.gz | grep -Poi '\d+')" "$(cat < gzip.enc_time)" "$(cat < gzip.dec_time)" | |
| printf "| bzip2 | %16s | %12s | %12s |\n" "$(wc -c < enwik8.bz2 | grep -Poi '\d+')" "$(cat < bzip2.enc_time)" "$(cat < bzip2.dec_time)" | |
| printf "| zstd -11 | %16s | %12s | %12s |\n" "$(wc -c < enwik8.zstd11 | grep -Poi '\d+')" "$(cat < zstd11.enc_time)" "$(cat < zstd11.dec_time)" | |
| printf "| orz -l0 | %16s | %12s | %12s |\n" "$(wc -c < enwik8.orz0 | grep -Poi '\d+')" "$(cat < orz0.enc_time)" "$(cat < orz0.dec_time)" | |
| printf "| orz -l1 | %16s | %12s | %12s |\n" "$(wc -c < enwik8.orz1 | grep -Poi '\d+')" "$(cat < orz1.enc_time)" "$(cat < orz1.dec_time)" | |
| printf "| orz -l2 | %16s | %12s | %12s |\n" "$(wc -c < enwik8.orz2 | grep -Poi '\d+')" "$(cat < orz2.enc_time)" "$(cat < orz2.dec_time)" | |
| printf "| zstd -19 | %16s | %12s | %12s |\n" "$(wc -c < enwik8.zstd19 | grep -Poi '\d+')" "$(cat < zstd19.enc_time)" "$(cat < zstd19.dec_time)" | |
| printf "| xz -6 | %16s | %12s | %12s |\n" "$(wc -c < enwik8.xz | grep -Poi '\d+')" "$(cat < xz.enc_time)" "$(cat < xz.dec_time)" | |
| printf "+----------+------------------+--------------+--------------+\n" |