Print out intermediate benchmark results (#1100)

* Print out intermediate benchmark results

* Fix benchmarks action

* Formatter

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* Formatter

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Author: mhauru

.github/workflows/Benchmarking.yml

@@ -33,14 +33,19 @@ jobs:
           echo "$version_info" >> $GITHUB_ENV
           echo "EOF" >> $GITHUB_ENV
 
-          # Capture benchmark output into a variable
+          # Capture benchmark output into a variable. The sed and tail calls cut out anything but the
+          # final block of results.
           echo "Running Benchmarks..."
-          benchmark_output=$(julia --project=benchmarks benchmarks/benchmarks.jl)
-          
+          benchmark_output=$(\
+            julia --project=benchmarks benchmarks/benchmarks.jl \
+            | sed -n '/Final results:/,$p' \
+            | tail -n +2\
+          )
+
           # Print benchmark results directly to the workflow log
           echo "Benchmark Results:"
           echo "$benchmark_output"
-          
+
           # Set the benchmark output as an env var for later steps
           echo "BENCHMARK_OUTPUT<<EOF" >> $GITHUB_ENV
           echo "$benchmark_output" >> $GITHUB_ENV

benchmarks/benchmarks.jl

@@ -7,6 +7,27 @@ using StableRNGs: StableRNG
 
 rng = StableRNG(23)
 
+function print_results(results_table)
+    table_matrix = hcat(Iterators.map(collect, zip(results_table...))...)
+    header = [
+        "Model",
+        "Dim",
+        "AD Backend",
+        "VarInfo",
+        "Linked",
+        "t(eval)/t(ref)",
+        "t(grad)/t(eval)",
+    ]
+    return pretty_table(
+        table_matrix;
+        column_labels=header,
+        backend=:text,
+        formatters=[fmt__printf("%.1f", [6, 7])],
+        fit_table_in_display_horizontally=false,
+        fit_table_in_display_vertically=false,
+    )
+end
+
 # Create DynamicPPL.Model instances to run benchmarks on.
 smorgasbord_instance = Models.smorgasbord(randn(rng, 100), randn(rng, 100))
 loop_univariate1k, multivariate1k = begin
@@ -82,17 +103,9 @@ for (model_name, model, varinfo_choice, adbackend, islinked) in chosen_combinati
             relative_ad_eval_time,
         ),
     )
+    println("Results so far:")
+    print_results(results_table)
 end
 
-table_matrix = hcat(Iterators.map(collect, zip(results_table...))...)
-header = [
-    "Model", "Dim", "AD Backend", "VarInfo", "Linked", "t(eval)/t(ref)", "t(grad)/t(eval)"
-]
-pretty_table(
-    table_matrix;
-    column_labels=header,
-    backend=:text,
-    formatters=[fmt__printf("%.1f", [6, 7])],
-    fit_table_in_display_horizontally=false,
-    fit_table_in_display_vertically=false,
-)
+println("Final results:")
+print_results(results_table)