Rich t kid/introduce dict benchmarks (apache#21860)

## Which issue does this PR close?
This PR provides the benchmarks mentioned in
apache#7647 &
apache#9017
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes apache#123` indicates that this PR will close issue apache#123.
-->

- Works towards closing apache#7647.

## Rationale for this change
Currently the benchmark suite doesn't have any dictionary-encoded tables
with aggregations performed on them. This makes it difficult to prove
performance improvements, for example, a separate PR I'm working on
(apache#21765) is hard to validate because the existing benchmarks don't
exercise this path. This PR attempts to close that gap.
<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->

## What changes are included in this PR?
Adds a new dict benchmark to dfbench that measures group-by performance
on dictionary-encoded columns across varying cardinality (5/10/25%),
null rates (0/15%), and value types (Utf8 and List<Utf8>), covering both
single and multi-column group-by scenarios.

<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->

## Are these changes tested?
--
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code

If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->

## Are there any user-facing changes?
no
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->

<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->

---------

Co-authored-by: Dmitrii Blaginin <dmitrii@blaginin.me>
Co-authored-by: Kumar Ujjawal <ujjawalpathak6@gmail.com>

Author: 3 people

benchmarks/bench.sh

@@ -147,6 +147,7 @@ cancellation:           How long cancelling a query takes
 nlj:                    Benchmark for simple nested loop joins, testing various join scenarios
 hj:                     Benchmark for simple hash joins, testing various join scenarios
 smj:                    Benchmark for simple sort merge joins, testing various join scenarios
+dict:                   Benchmark for dictionary-encoded group-by scenarios
 compile_profile:        Compile and execute TPC-H across selected Cargo profiles, reporting timing and binary size
 
 
@@ -351,6 +352,10 @@ main() {
                     # smj uses range() function, no data generation needed
                     echo "SMJ benchmark does not require data generation"
                     ;;
+                dict)
+                    # dict generates in-memory data, no data generation needed
+                    echo "DICT benchmark does not require data generation"
+                    ;;
                 compile_profile)
                     data_tpch "1" "parquet"
                     ;;
@@ -430,6 +435,7 @@ main() {
                     run_hj
                     run_tpcds
                     run_smj
+                    run_dict 
                     ;;
                 tpch)
                     run_tpch "1" "parquet"
@@ -564,6 +570,9 @@ main() {
                 smj)
                     run_smj
                     ;;
+                dict)
+                    run_dict
+                    ;;
                 compile_profile)
                     run_compile_profile "${PROFILE_ARGS[@]}"
                     ;;
@@ -1460,6 +1469,14 @@ run_smj() {
     debug_run $CARGO_COMMAND --bin dfbench -- smj --iterations 5 -o "${RESULTS_FILE}" ${QUERY_ARG} ${LATENCY_ARG}
 }
 
+# Runs the dict benchmark
+run_dict() {
+    RESULTS_FILE="${RESULTS_DIR}/dict.json"
+    echo "RESULTS_FILE: ${RESULTS_FILE}"
+    echo "Running dict benchmark..."
+    debug_run $CARGO_COMMAND --bin dfbench -- dict --iterations 5 -o "${RESULTS_FILE}" ${QUERY_ARG} ${LATENCY_ARG}
+}
+
 
 compare_benchmarks() {
     BASE_RESULTS_DIR="${SCRIPT_DIR}/results"

benchmarks/src/bin/dfbench.rs

@@ -17,6 +17,7 @@
 
 //! DataFusion benchmark runner
 use datafusion::error::Result;
+use datafusion_benchmarks::sort_pushdown;
 
 use clap::{Parser, Subcommand};
 
@@ -31,8 +32,7 @@ static ALLOC: snmalloc_rs::SnMalloc = snmalloc_rs::SnMalloc;
 static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
 
 use datafusion_benchmarks::{
-    cancellation, clickbench, h2o, hj, imdb, nlj, smj, sort_pushdown, sort_tpch, tpcds,
-    tpch,
+    cancellation, clickbench, dict, h2o, hj, imdb, nlj, smj, sort_tpch, tpcds, tpch,
 };
 
 #[derive(Debug, Parser)]
@@ -46,6 +46,7 @@ struct Cli {
 enum Options {
     Cancellation(cancellation::RunOpt),
     Clickbench(clickbench::RunOpt),
+    Dict(dict::RunOpt),
     H2o(h2o::RunOpt),
     HJ(hj::RunOpt),
     Imdb(imdb::RunOpt),
@@ -66,6 +67,7 @@ pub async fn main() -> Result<()> {
     match cli.command {
         Options::Cancellation(opt) => opt.run().await,
         Options::Clickbench(opt) => opt.run().await,
+        Options::Dict(opt) => opt.run().await,
         Options::H2o(opt) => opt.run().await,
         Options::HJ(opt) => opt.run().await,
         Options::Imdb(opt) => Box::pin(opt.run()).await,