Add JMH benchmark for the brightness kernel

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

@@ -0,0 +1,55 @@
+package com.ankurm.vectorapi;
+
+import jdk.incubator.vector.*;
+import org.openjdk.jmh.annotations.*;
+import org.openjdk.jmh.infra.Blackhole;
+import java.util.Random;
+import java.util.concurrent.TimeUnit;
+
+/** JMH version of the image brightness + clamp kernel. */
+@BenchmarkMode(Mode.AverageTime)
+@OutputTimeUnit(TimeUnit.NANOSECONDS)
+@State(Scope.Thread)
+@Warmup(iterations = 5, time = 1)
+@Measurement(iterations = 5, time = 1)
+@Fork(1)
+public class BrightnessBench {
+    static final VectorSpecies<Float> SP = FloatVector.SPECIES_PREFERRED;
+    float[] in, out;
+    float gain = 1.4f, bias = 12f;
+
+    @Setup
+    public void setup() {
+        in = new float[8192]; out = new float[8192];
+        Random r = new Random(11);
+        for (int i = 0; i < in.length; i++) in[i] = r.nextFloat() * 300f - 20f;
+    }
+
+    @Benchmark
+    public void scalarClamp(Blackhole bh) {
+        for (int i = 0; i < in.length; i++) {
+            float v = in[i] * gain + bias;
+            if (v < 0f) v = 0f; else if (v > 255f) v = 255f;
+            out[i] = v;
+        }
+        bh.consume(out);
+    }
+
+    @Benchmark
+    public void vectorClamp(Blackhole bh) {
+        var vg = FloatVector.broadcast(SP, gain);
+        var vb = FloatVector.broadcast(SP, bias);
+        var lo = FloatVector.zero(SP);
+        var hi = FloatVector.broadcast(SP, 255f);
+        int i = 0, bound = SP.loopBound(in.length);
+        for (; i < bound; i += SP.length()) {
+            FloatVector.fromArray(SP, in, i).fma(vg, vb).max(lo).min(hi).intoArray(out, i);
+        }
+        for (; i < in.length; i++) {
+            float v = in[i] * gain + bias;
+            if (v < 0f) v = 0f; else if (v > 255f) v = 255f;
+            out[i] = v;
+        }
+        bh.consume(out);
+    }
+}