diff --git a/README.md b/README.md
index a2becb7..9d9152f 100644
--- a/README.md
+++ b/README.md
@@ -65,6 +65,8 @@ algorithms in Rust and benchmark them. Let the battle begin.
 
 - `single thread`: No multi-threading or any optimization of any kind. Used as
   a reference.
+- `multi threads`: Manual multi-threading but no optimization of any kind. Used
+  as a reference.
 - `lpt`: Manual multi-threading. Tasks are sorted so the shortest ones are
   executed first. This is the [longest-processing-time-first algorithm][lpt].
 - `rayon`: Multi-threading provided by the `rayon` crate, but no optimization
diff --git a/benches/job_scheduling.rs b/benches/job_scheduling.rs
index 8d8ef53..2566dd7 100644
--- a/benches/job_scheduling.rs
+++ b/benches/job_scheduling.rs
@@ -6,6 +6,7 @@ use rust_job_scheduling::Task;
 const TEST_DATA: &[(&str, &[Task])] = &[("10 tasks", T_10), ("500 tasks", T_500)];
 const TEST_FUNCS: &[(&str, &dyn Fn(&[Task]))] = &[
 	("single thread", &single_thread),
+	("multi threads", &multi_threads),
 	("lpt", &lpt),
 	("rayon", &rayon),
 	("rayon sorted", &rayon_sorted),
diff --git a/src/algorithm.rs b/src/algorithm.rs
index e46e616..0ef1550 100644
--- a/src/algorithm.rs
+++ b/src/algorithm.rs
@@ -2,6 +2,6 @@ mod lpt;
 mod rayon;
 mod single_thread;
 
-pub use lpt::lpt;
+pub use lpt::*;
 pub use rayon::*;
 pub use single_thread::single_thread;
diff --git a/src/algorithm/lpt.rs b/src/algorithm/lpt.rs
index 237d493..1467e5d 100644
--- a/src/algorithm/lpt.rs
+++ b/src/algorithm/lpt.rs
@@ -5,7 +5,16 @@ use std::thread;
 pub fn lpt(data: &[Task]) {
 	let mut data = data.to_vec();
 	data.sort();
+	run_multi(data);
+}
 
+pub fn multi_threads(data: &[Task]) {
+	let data = data.to_vec();
+	run_multi(data);
+}
+
+#[inline(always)]
+fn run_multi(data: Vec<Task>) {
 	let data_mt = Arc::new(Mutex::new(data));
 	let nb_threads = thread::available_parallelism()
 		.map(|n| n.get())