import java.util.*; import java.util.zip.*; import java.util.List; import java.util.regex.*; import java.util.concurrent.*; import java.util.concurrent.atomic.*; import java.util.concurrent.locks.*; import java.util.function.*; import javax.swing.*; import javax.swing.event.*; import javax.swing.text.*; import javax.swing.table.*; import java.io.*; import java.net.*; import java.lang.reflect.*; import java.lang.ref.*; import java.lang.management.*; import java.security.*; import java.security.spec.*; import java.awt.*; import java.awt.event.*; import java.awt.image.*; import java.awt.geom.*; import javax.imageio.*; import java.math.*; import java.time.Duration; import java.lang.invoke.VarHandle; import java.lang.invoke.MethodHandles; import jdk.incubator.vector.*; class main { static int countDifferingBits_1024bit_vectorAPI(long[] array1, long[] array2, int i1) { VectorSpecies SPECIES = LongVector.SPECIES_PREFERRED; int diff = 0; int n = 1024/64; var upperBound = SPECIES.loopBound(n); var i = 0; for (; i < upperBound; i += SPECIES.length()) { var vector1 = LongVector.fromArray(SPECIES, array1, i); var vector2 = LongVector.fromArray(SPECIES, array2, i1+i); var xored = vector1.lanewise(VectorOperators.XOR, vector2); var bitCount = xored.lanewise(VectorOperators.BIT_COUNT); diff += (int) bitCount.reduceLanes(VectorOperators.ADD); } // Compute elements not fitting in the vector alignment. for (; i < n; i++) diff += Long.bitCount(array1[i]^array2[i1+i]); return diff; }}