Merge branch 'main' into bio_dev

.github/workflows/tests.yml

@@ -10,9 +10,11 @@ jobs:
   run-benchmark:
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
         benchmark: [nlp, file-enc, unix50, log-analysis, max-temp, uniq-ips, media-conv, sklearn, covid-mts, bio]
 
+
     steps:
       - name: Checkout code
         uses: actions/checkout@v3
@@ -30,6 +32,7 @@ jobs:
 
       - name: Upload .out and .err files
         uses: actions/upload-artifact@v4
+        if: always()
         with:
           name: ${{ matrix.benchmark }}-logs
           path: ${{ matrix.benchmark }}/${{ matrix.benchmark }}.*

README.md

@@ -2,7 +2,28 @@
 
 > _It's a suite that has benchmarks in it._
 
-## Docker
+## Benchmarks
+
+| Benchmark    | Description                                             |
+| ---------    | -----------                                             |
+| aurpkg       |                                                         |
+| bio          | Bioinformatics.                                         |
+| covid-mts    | COVID-19 multivariate time series.                      |
+| file-enc     | File encoding.                                          |
+| log-analysis | Log analysis.                                           |
+| max-temp     | Maximum temperature.                                    |
+| media-conv   | Media conversion.                                       |
+| nlp          | Natural language processing.                            |
+| oneliners    | One-liners.                                             |
+| riker        |                                                         |
+| sklearn      | Machine learning.                                       |
+| teraseq      |                                                         |
+| tuft-weather | Tuft weather.                                           |
+| uniq-ips     | Unique IPs.                                             |
+| unix50       | Unix 50.                                                |
+| web-index    | Web index.                                              |
+
+## Docker Instructions
 
 ```sh
 # Build the container

main.sh

@@ -8,6 +8,9 @@ correct() { [ "$(cat $BENCHMARK.hash | cut -d' ' -f 2 | grep -c 1)" -eq 0 ]; }
 
 main()
 {
+    export BENCHMARK="$1"
+    shift
+
     cd "$(dirname "$0")/$BENCHMARK" || exit 1
 
     # Download dependencies
@@ -34,7 +37,4 @@ main()
     cd - || exit 1
 }
 
-export BENCHMARK="$1"
-shift
-
 main $@

oneliners/deps.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+sudo apt update
+sudo apt install -y \
+    wget \
+    bsdmainutils \
+    file \
+    dos2unix

oneliners/hashes/small/diff.hash

@@ -1 +1 @@
-1095af6f701dc683c2c88fcd4cdf86fe324f10784a540b38d3240e279e3af244
+e0f3f7916effc9373fa39b3a8c211671305b5771d4a8bb10b37c3b9a5cf1f2b7

oneliners/hashes/small/nfa-regex.hash

@@ -1 +1 @@
-4582552d134115ffd6052b5e445c9eb775304da7c2c1f86b32599eb04c6eff63
+589f64d6c9a5c9501b0a2b92ee35a880fcdf2b89075628b18d3472661d00fcb6

oneliners/hashes/small/set-diff.hash

@@ -1 +1 @@
-b82baa59f30e29dd37094d092df024e376dd2ca1d62c23339b2b009b692eedaa
+e737aa088e2771e162fb60ce42d9374c8a8768b9bba9f3d6aaba6c7b47bbd862

oneliners/hashes/small/sort-sort.hash

@@ -1 +1 @@
-bba05f5706fffdfcc17244553a01595957fe7de6025a404da5e9e826e694667f
+b10dd497b66955e63cf32eb3a4796d7edd0ae4876a450cca6970a9d261968780

oneliners/hashes/small/sort.hash

@@ -1 +1 @@
-18979d4fae333d462c406a7cb4d9a59db5b935d5f6b95e8ab9e737b744432b96
+965dfcdb1fa45be5cb5b125683e01a1882d2693384cd76782beacadfda5f2872

oneliners/hashes/small/spell.hash

@@ -1 +1 @@
-4aae590c69ab5f5aa63f101c330b15942ae8e94f356d8c45598061e795edbdb4
+83a9657314b52598447ebc4a4a6717fdd23d3d81b27e4821d434054a989a97b9

oneliners/inputs.sh → oneliners/input.sh

@@ -7,9 +7,10 @@ cd inputs
 input_files=("1M.txt" "1G.txt" "3G.txt" "all_cmds.txt" "all_cmdsx100.txt" "dict.txt")
 
 if [ ! -f ./1M.txt ]; then
-    wget https://atlas-group.cs.brown.edu/data/dummy/1M.txt
+    wget --no-check-certificate https://atlas-group.cs.brown.edu/data/dummy/1M.txt
     # TODO: Add newline to the original file
     echo >> 1M.txt
+    dos2unix 1M.txt
 fi
 
 if [ ! -f ./1G.txt ]; then
@@ -27,7 +28,7 @@ if [ ! -f ./3G.txt ]; then
 fi
 
 if [ ! -f ./dict.txt ]; then
-    wget -O - https://atlas-group.cs.brown.edu/data/dummy/dict.txt | sort > dict.txt
+    wget -O - https://atlas-group.cs.brown.edu/data/dummy/dict.txt --no-check-certificate | sort > dict.txt
 fi
 
 if [ ! -f ./all_cmds.txt ]; then

oneliners/run.sh

@@ -15,7 +15,6 @@ if [[ "$@" == *"--small"* ]]; then
         "bi-grams;1M"
         "set-diff;1M"
         "sort-sort;1M"
-        "shortest-scripts;all_cmds"
     )
 else
     scripts_inputs=(
@@ -28,40 +27,21 @@ else
         "bi-grams;3G"
         "set-diff;3G"
         "sort-sort;3G"
-        "shortest-scripts;all_cmdsx100"
     )
 fi
 
 mkdir -p "outputs"
-all_res_file="./outputs/oneliners.res"
-> $all_res_file
 
-# time_file stores the time taken for each script
-# mode_res_file stores the time taken and the script name for every script in a mode (e.g. bash, pash, dish, fish)
-# all_res_file stores the time taken for each script for every script run, making it easy to copy and paste into the spreadsheet
-oneliners() {
-    mkdir -p "outputs/$1"
-    mode_res_file="./outputs/$1/oneliners.res"
-    > $mode_res_file
+echo executing oneliners $(date)
 
-    echo executing oneliners $1 $(date) | tee -a $mode_res_file $all_res_file
+for script_input in ${scripts_inputs[@]}
+do
+    IFS=";" read -r -a parsed <<< "${script_input}"
+    script_file="./scripts/${parsed[0]}.sh"
+    input_file="./inputs/${parsed[1]}.txt"
+    output_file="./outputs/${parsed[0]}.out"
 
-    for script_input in ${scripts_inputs[@]}
-    do
-        IFS=";" read -r -a parsed <<< "${script_input}"
-        script_file="./scripts/${parsed[0]}.sh"
-        input_file="./inputs/${parsed[1]}.txt"
-        output_file="./outputs/$1/${parsed[0]}.out"
-        time_file="./outputs/$1/${parsed[0]}.time"
-        log_file="./outputs/$1/${parsed[0]}.log"
-
-        if [[ "$1" == "bash" ]]; then
-            (time $script_file $input_file > $output_file) 2> $time_file
-        fi
-
-        cat "${time_file}" >> $all_res_file
-        echo "$script_file $(cat "$time_file")" | tee -a $mode_res_file
-    done
-}
-
-oneliners "bash"
+    echo "$script_file"
+    time "$SHELL" "$script_file" "$input_file" > "$output_file"
+    echo "$?"
+done