Add image brightness + clamp kernel

timings/src/main/java/com/ankurm/vectorapi/Brightness.java

@@ -0,0 +1,51 @@
+package com.ankurm.vectorapi;
+
+import jdk.incubator.vector.*;
+
+/** Image brightness: scale, bias, clamp to [0, 255]. The clamp is two branches. */
+public final class Brightness {
+
+    static final VectorSpecies<Float> SP = FloatVector.SPECIES_PREFERRED;
+
+    // Scalar: the clamp is two data-dependent branches
+    static void brightScalar(float[] in, float[] out, float gain, float bias) {
+        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;
+        }
+    }
+
+    static void brightVector(float[] in, float[] out, float gain, float bias) {
+        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++) {                 // scalar tail
+            float v = in[i] * gain + bias;
+            if (v < 0f) v = 0f; else if (v > 255f) v = 255f;
+            out[i] = v;
+        }
+    }
+
+    static void run(int n) {
+        float[] in = Data.randomFloats(n, 4);
+        for (int i = 0; i < n; i++) in[i] = in[i] * 300f - 20f;   // some pixels clamp at both ends
+        float[] o1 = new float[n], o2 = new float[n];
+        brightScalar(in, o1, 1.4f, 12f);
+        brightVector(in, o2, 1.4f, 12f);
+        Data.assertSame("brightness", o1, o2);
+
+        System.out.println("--- kernel 3: image brightness + clamp, " + n + " pixels ---");
+        double s = Bench.measure("scalar (branchy clamp)", () -> brightScalar(in, o1, 1.4f, 12f));
+        double v = Bench.measure("Vector API (max/min)", () -> brightVector(in, o2, 1.4f, 12f));
+        Bench.speedup("vector advantage", s, v);
+        System.out.println();
+    }
+
+    private Brightness() {}
+}