Junior — Middle
What is your experience with using the Fork/Join mechanism for parallel task processing?
sobes.tech AI
Answer from AI
The Fork/Join mechanism in Java is used for efficient parallel processing of tasks that can be recursively divided into subtasks.
Typical usage includes:
- Creating a class that extends
RecursiveTask<V>(if the task returns a result) orRecursiveAction(if it does not). - Overriding the
compute()method, where the task is split into subtasks usingfork(), and then results are combined viajoin(). - Using
ForkJoinPoolto execute the task.
Example:
import java.util.concurrent.*;
public class SumTask extends RecursiveTask<Integer> {
private final int[] array;
private final int start, end;
private static final int THRESHOLD = 10;
public SumTask(int[] array, int start, int end) {
this.array = array;
this.start = start;
this.end = end;
}
@Override
protected Integer compute() {
if (end - start <= THRESHOLD) {
int sum = 0;
for (int i = start; i < end; i++) {
sum += array[i];
}
return sum;
} else {
int mid = (start + end) / 2;
SumTask leftTask = new SumTask(array, start, mid);
SumTask rightTask = new SumTask(array, mid, end);
leftTask.fork();
int rightResult = rightTask.compute();
int leftResult = leftTask.join();
return leftResult + rightResult;
}
}
public static void main(String[] args) {
ForkJoinPool pool = new ForkJoinPool();
int[] array = new int[100];
for (int i = 0; i < array.length; i++) {
array[i] = i + 1;
}
SumTask task = new SumTask(array, 0, array.length);
int result = pool.invoke(task);
System.out.println("Sum: " + result); // Outputs the sum of numbers from 1 to 100
}
}
This approach allows efficient utilization of multi-core processors for parallel processing of large data volumes.