Add JMH benchmark for the masked filter

jmh/src/main/java/com/ankurm/vectorapi/MaskedBench.java

@@ -0,0 +1,47 @@
+package com.ankurm.vectorapi;
+
+import jdk.incubator.vector.*;
+import org.openjdk.jmh.annotations.*;
+import java.util.Random;
+import java.util.concurrent.TimeUnit;
+
+/** JMH version of the masked filter-and-sum: the headline speedup case. */
+@BenchmarkMode(Mode.AverageTime)
+@OutputTimeUnit(TimeUnit.NANOSECONDS)
+@State(Scope.Thread)
+@Warmup(iterations = 5, time = 1)
+@Measurement(iterations = 5, time = 1)
+@Fork(1)
+public class MaskedBench {
+    static final VectorSpecies<Float> SP = FloatVector.SPECIES_PREFERRED;
+    static final float THRESH = 0.5f;
+    float[] a;
+
+    @Setup
+    public void setup() {
+        a = new float[8192];
+        Random r = new Random(7);
+        for (int i = 0; i < a.length; i++) a[i] = r.nextFloat();
+    }
+
+    // Both methods return their result, so JMH consumes it and nothing is dead.
+    @Benchmark
+    public float scalarBranch() {
+        float sum = 0;
+        for (int i = 0; i < a.length; i++) if (a[i] > THRESH) sum += a[i];
+        return sum;
+    }
+
+    @Benchmark
+    public float vectorMasked() {
+        FloatVector acc = FloatVector.zero(SP);
+        int i = 0, bound = SP.loopBound(a.length);
+        for (; i < bound; i += SP.length()) {
+            var v = FloatVector.fromArray(SP, a, i);
+            acc = acc.add(v, v.compare(VectorOperators.GT, THRESH));
+        }
+        float sum = acc.reduceLanes(VectorOperators.ADD);
+        for (; i < a.length; i++) if (a[i] > THRESH) sum += a[i];
+        return sum;
+    }
+}