add info about comparing and storing bench results

Author: pbalcer

scripts/benchmarks/README.md

@@ -31,6 +31,16 @@ By default, all benchmark runs are compared against `baseline`, which is a well-
 
 You must be a member of the `oneapi-src` organization to access these features.
 
+## Comparing results
+
+By default, the benchmark results are not stored. To store them, use the option `--save <name>`. This will make the results available for comparison during the next benchmark runs.
+
+To compare a benchmark run with a previously stored result, use the option `--compare <name>`. You can compare with more than one result.
+
+If no `--compare` option is specified, the benchmark run is compared against a previously stored `baseline`. This baseline is **not** automatically updated. To update it, use the `--save baseline` option.
+The recommended way of updating the baseline is running the benchmarking
+job on main after a merge of relevant changes.
+
 ## Requirements
 
 ### Python