Add topk_tpch benchmark (#16410)

* Add topk benchmark

* Add topk benchmark

* Add topk benchmark

Author: Dandandan

benchmarks/README.md

@@ -510,6 +510,15 @@ See [`sort_tpch.rs`](src/sort_tpch.rs) for more details.
 ./bench.sh run sort_tpch
 ```
 
+### TopK TPCH
+
+In addition, topk_tpch is available from the bench.sh script:
+
+```bash
+./bench.sh run topk_tpch
+```
+
+
 ## IMDB
 
 Run Join Order Benchmark (JOB) on IMDB dataset.

benchmarks/bench.sh

@@ -236,6 +236,10 @@ main() {
                     # same data as for tpch
                     data_tpch "1"
                     ;;
+                topk_tpch)
+                    # same data as for tpch
+                    data_tpch "1"
+                    ;;
                 *)
                     echo "Error: unknown benchmark '$BENCHMARK' for data generation"
                     usage
@@ -361,6 +365,9 @@ main() {
                 sort_tpch)
                     run_sort_tpch
                     ;;
+                topk_tpch)
+                    run_topk_tpch
+                    ;;
                 *)
                     echo "Error: unknown benchmark '$BENCHMARK' for run"
                     usage
@@ -981,6 +988,16 @@ run_sort_tpch() {
     debug_run $CARGO_COMMAND --bin dfbench -- sort-tpch --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}"
 }
 
+# Runs the sort tpch integration benchmark with limit 100 (topk)
+run_topk_tpch() {
+    TPCH_DIR="${DATA_DIR}/tpch_sf1"
+    RESULTS_FILE="${RESULTS_DIR}/run_topk_tpch.json"
+    echo "RESULTS_FILE: ${RESULTS_FILE}"
+    echo "Running topk tpch benchmark..."
+
+    $CARGO_COMMAND --bin dfbench -- sort-tpch --iterations 5 --path "${TPCH_DIR}" -o "${RESULTS_FILE}" --limit 100
+}
+
 
 compare_benchmarks() {
     BASE_RESULTS_DIR="${SCRIPT_DIR}/results"