/*
 * Copyright (c) 2017, Oracle and/or its affiliates. All rights reserved.
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * This code is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 only, as
 * published by the Free Software Foundation.  Oracle designates this
 * particular file as subject to the "Classpath" exception as provided
 * by Oracle in the LICENSE file that accompanied this code.
 *
 * This code is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
 * version 2 for more details (a copy is included in the LICENSE file that
 * accompanied this code).
 *
 * You should have received a copy of the GNU General Public License version
 * 2 along with this work; if not, write to the Free Software Foundation,
 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
 *
 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
 * or visit www.oracle.com if you need additional information or have
 * questions.
 */
package jdk.incubator.vector;

import java.nio.ByteBuffer;
#if[!byte]
import java.nio.$Type$Buffer;
#end[!byte]
import java.nio.ByteOrder;
import java.util.Objects;
import java.util.function.IntUnaryOperator;
import java.util.function.Function;
import java.util.concurrent.ThreadLocalRandom;

import jdk.internal.misc.Unsafe;
import jdk.internal.vm.annotation.ForceInline;
import static jdk.incubator.vector.VectorIntrinsics.*;


/**
 * A specialized {@link Vector} representing an ordered immutable sequence of
 * {@code $type$} values.
 */
@SuppressWarnings("cast")
public abstract class $abstractvectortype$ extends Vector<$Boxtype$> {

    $abstractvectortype$() {}

    private static final int ARRAY_SHIFT = 31 - Integer.numberOfLeadingZeros(Unsafe.ARRAY_$TYPE$_INDEX_SCALE);

    // Unary operator

    interface FUnOp {
        $type$ apply(int i, $type$ a);
    }

    abstract $abstractvectortype$ uOp(FUnOp f);

    abstract $abstractvectortype$ uOp(VectorMask<$Boxtype$> m, FUnOp f);

    // Binary operator

    interface FBinOp {
        $type$ apply(int i, $type$ a, $type$ b);
    }

    abstract $abstractvectortype$ bOp(Vector<$Boxtype$> v, FBinOp f);

    abstract $abstractvectortype$ bOp(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m, FBinOp f);

    // Trinary operator

    interface FTriOp {
        $type$ apply(int i, $type$ a, $type$ b, $type$ c);
    }

    abstract $abstractvectortype$ tOp(Vector<$Boxtype$> v1, Vector<$Boxtype$> v2, FTriOp f);

    abstract $abstractvectortype$ tOp(Vector<$Boxtype$> v1, Vector<$Boxtype$> v2, VectorMask<$Boxtype$> m, FTriOp f);

    // Reduction operator

    abstract $type$ rOp($type$ v, FBinOp f);

    // Binary test

    interface FBinTest {
        boolean apply(int i, $type$ a, $type$ b);
    }

    abstract VectorMask<$Boxtype$> bTest(Vector<$Boxtype$> v, FBinTest f);

    // Foreach

    interface FUnCon {
        void apply(int i, $type$ a);
    }

    abstract void forEach(FUnCon f);

    abstract void forEach(VectorMask<$Boxtype$> m, FUnCon f);

    // Static factories

    /**
     * Returns a vector where all lane elements are set to the default
     * primitive value.
     *
     * @param species species of desired vector
     * @return a zero vector of given species
     */
    @ForceInline
    @SuppressWarnings("unchecked")
    public static $abstractvectortype$ zero(VectorSpecies<$Boxtype$> species) {
#if[FP]
        return VectorIntrinsics.broadcastCoerced((Class<$Type$Vector>) species.boxType(), $type$.class, species.length(),
                                                 $Type$.$type$To$Bitstype$Bits(0.0f), species,
                                                 ((bits, s) -> (($Type$Species)s).op(i -> $Type$.$bitstype$BitsTo$Type$(($bitstype$)bits))));
#else[FP]
        return VectorIntrinsics.broadcastCoerced((Class<$Type$Vector>) species.boxType(), $type$.class, species.length(),
                                                 0, species,
                                                 ((bits, s) -> (($Type$Species)s).op(i -> ($type$)bits)));
#end[FP]
    }

    /**
     * Loads a vector from a byte array starting at an offset.
     * <p>
     * Bytes are composed into primitive lane elements according to the
     * native byte order of the underlying platform
     * <p>
     * This method behaves as if it returns the result of calling the
     * byte buffer, offset, and mask accepting
     * {@link #fromByteBuffer(VectorSpecies<$Boxtype$>, ByteBuffer, int, VectorMask) method} as follows:
     * <pre>{@code
     * return this.fromByteBuffer(ByteBuffer.wrap(a), i, this.maskAllTrue());
     * }</pre>
     *
     * @param species species of desired vector
     * @param a the byte array
     * @param ix the offset into the array
     * @return a vector loaded from a byte array
     * @throws IndexOutOfBoundsException if {@code i < 0} or
     * {@code i > a.length - (this.length() * this.elementSize() / Byte.SIZE)}
     */
    @ForceInline
    @SuppressWarnings("unchecked")
    public static $abstractvectortype$ fromByteArray(VectorSpecies<$Boxtype$> species, byte[] a, int ix) {
        Objects.requireNonNull(a);
        ix = VectorIntrinsics.checkIndex(ix, a.length, species.bitSize() / Byte.SIZE);
        return VectorIntrinsics.load((Class<$abstractvectortype$>) species.boxType(), $type$.class, species.length(),
                                     a, ((long) ix) + Unsafe.ARRAY_BYTE_BASE_OFFSET,
                                     a, ix, species,
                                     (c, idx, s) -> {
                                         ByteBuffer bbc = ByteBuffer.wrap(c, idx, a.length - idx).order(ByteOrder.nativeOrder());
                                         $Type$Buffer tb = bbc{#if[byte]?;:.as$Type$Buffer();}
                                         return (($Type$Species)s).op(i -> tb.get());
                                     });
    }

    /**
     * Loads a vector from a byte array starting at an offset and using a
     * mask.
     * <p>
     * Bytes are composed into primitive lane elements according to the
     * native byte order of the underlying platform.
     * <p>
     * This method behaves as if it returns the result of calling the
     * byte buffer, offset, and mask accepting
     * {@link #fromByteBuffer(VectorSpecies<$Boxtype$>, ByteBuffer, int, VectorMask) method} as follows:
     * <pre>{@code
     * return this.fromByteBuffer(ByteBuffer.wrap(a), i, m);
     * }</pre>
     *
     * @param species species of desired vector
     * @param a the byte array
     * @param ix the offset into the array
     * @param m the mask
     * @return a vector loaded from a byte array
     * @throws IndexOutOfBoundsException if {@code i < 0} or
     * {@code i > a.length - (this.length() * this.elementSize() / Byte.SIZE)}
     * @throws IndexOutOfBoundsException if the offset is {@code < 0},
     * or {@code > a.length},
     * for any vector lane index {@code N} where the mask at lane {@code N}
     * is set
     * {@code i >= a.length - (N * this.elementSize() / Byte.SIZE)}
     */
    @ForceInline
    public static $abstractvectortype$ fromByteArray(VectorSpecies<$Boxtype$> species, byte[] a, int ix, VectorMask<$Boxtype$> m) {
        return zero(species).blend(fromByteArray(species, a, ix), m);
    }

    /**
     * Loads a vector from an array starting at offset.
     * <p>
     * For each vector lane, where {@code N} is the vector lane index, the
     * array element at index {@code i + N} is placed into the
     * resulting vector at lane index {@code N}.
     *
     * @param species species of desired vector
     * @param a the array
     * @param i the offset into the array
     * @return the vector loaded from an array
     * @throws IndexOutOfBoundsException if {@code i < 0}, or
     * {@code i > a.length - this.length()}
     */
    @ForceInline
    @SuppressWarnings("unchecked")
    public static $abstractvectortype$ fromArray(VectorSpecies<$Boxtype$> species, $type$[] a, int i){
        Objects.requireNonNull(a);
        i = VectorIntrinsics.checkIndex(i, a.length, species.length());
        return VectorIntrinsics.load((Class<$abstractvectortype$>) species.boxType(), $type$.class, species.length(),
                                     a, (((long) i) << ARRAY_SHIFT) + Unsafe.ARRAY_$TYPE$_BASE_OFFSET,
                                     a, i, species,
                                     (c, idx, s) -> (($Type$Species)s).op(n -> c[idx + n]));
    }


    /**
     * Loads a vector from an array starting at offset and using a mask.
     * <p>
     * For each vector lane, where {@code N} is the vector lane index,
     * if the mask lane at index {@code N} is set then the array element at
     * index {@code i + N} is placed into the resulting vector at lane index
     * {@code N}, otherwise the default element value is placed into the
     * resulting vector at lane index {@code N}.
     *
     * @param species species of desired vector
     * @param a the array
     * @param i the offset into the array
     * @param m the mask
     * @return the vector loaded from an array
     * @throws IndexOutOfBoundsException if {@code i < 0}, or
     * for any vector lane index {@code N} where the mask at lane {@code N}
     * is set {@code i > a.length - N}
     */
    @ForceInline
    public static $abstractvectortype$ fromArray(VectorSpecies<$Boxtype$> species, $type$[] a, int i, VectorMask<$Boxtype$> m) {
        return zero(species).blend(fromArray(species, a, i), m);
    }

    /**
     * Loads a vector from an array using indexes obtained from an index
     * map.
     * <p>
     * For each vector lane, where {@code N} is the vector lane index, the
     * array element at index {@code i + indexMap[j + N]} is placed into the
     * resulting vector at lane index {@code N}.
     *
     * @param species species of desired vector
     * @param a the array
     * @param i the offset into the array, may be negative if relative
     * indexes in the index map compensate to produce a value within the
     * array bounds
     * @param indexMap the index map
     * @param j the offset into the index map
     * @return the vector loaded from an array
     * @throws IndexOutOfBoundsException if {@code j < 0}, or
     * {@code j > indexMap.length - this.length()},
     * or for any vector lane index {@code N} the result of
     * {@code i + indexMap[j + N]} is {@code < 0} or {@code >= a.length}
     */
#if[byteOrShort]
    public static $abstractvectortype$ fromArray(VectorSpecies<$Boxtype$> species, $type$[] a, int i, int[] indexMap, int j) {
        return (($Type$Species)species).op(n -> a[i + indexMap[j + n]]);
    }
#else[byteOrShort]
    @ForceInline
    @SuppressWarnings("unchecked")
    public static $abstractvectortype$ fromArray(VectorSpecies<$Boxtype$> species, $type$[] a, int i, int[] indexMap, int j) {
        Objects.requireNonNull(a);
        Objects.requireNonNull(indexMap);

#if[longOrDouble]
        if (species.length() == 1) {
          return $abstractvectortype$.fromArray(species, a, i + indexMap[j]);
        }
#end[longOrDouble]

        // Index vector: vix[0:n] = k -> i + indexMap[j + k]
        IntVector vix = IntVector.fromArray(IntVector.species(species.indexShape()), indexMap, j).add(i);

        vix = VectorIntrinsics.checkIndex(vix, a.length);

        return VectorIntrinsics.loadWithMap((Class<$abstractvectortype$>) species.boxType(), $type$.class, species.length(),
                                            IntVector.species(species.indexShape()).boxType(), a, Unsafe.ARRAY_$TYPE$_BASE_OFFSET, vix,
                                            a, i, indexMap, j, species,
                                            ($type$[] c, int idx, int[] iMap, int idy, VectorSpecies<$Boxtype$> s) ->
                                                (($Type$Species)s).op(n -> c[idx + iMap[idy+n]]));
        }

#end[byteOrShort]
    /**
     * Loads a vector from an array using indexes obtained from an index
     * map and using a mask.
     * <p>
     * For each vector lane, where {@code N} is the vector lane index,
     * if the mask lane at index {@code N} is set then the array element at
     * index {@code i + indexMap[j + N]} is placed into the resulting vector
     * at lane index {@code N}.
     *
     * @param species species of desired vector
     * @param a the array
     * @param i the offset into the array, may be negative if relative
     * indexes in the index map compensate to produce a value within the
     * array bounds
     * @param m the mask
     * @param indexMap the index map
     * @param j the offset into the index map
     * @return the vector loaded from an array
     * @throws IndexOutOfBoundsException if {@code j < 0}, or
     * {@code j > indexMap.length - this.length()},
     * or for any vector lane index {@code N} where the mask at lane
     * {@code N} is set the result of {@code i + indexMap[j + N]} is
     * {@code < 0} or {@code >= a.length}
     */
#if[byteOrShort]
    public static $abstractvectortype$ fromArray(VectorSpecies<$Boxtype$> species, $type$[] a, int i, VectorMask<$Boxtype$> m, int[] indexMap, int j) {
        return (($Type$Species)species).op(m, n -> a[i + indexMap[j + n]]);
    }
#else[byteOrShort]
    @ForceInline
    @SuppressWarnings("unchecked")
    public static $abstractvectortype$ fromArray(VectorSpecies<$Boxtype$> species, $type$[] a, int i, VectorMask<$Boxtype$> m, int[] indexMap, int j) {
        // @@@ This can result in out of bounds errors for unset mask lanes
        return zero(species).blend(fromArray(species, a, i, indexMap, j), m);
    }

#end[byteOrShort]

    /**
     * Loads a vector from a {@link ByteBuffer byte buffer} starting at an
     * offset into the byte buffer.
     * <p>
     * Bytes are composed into primitive lane elements according to the
     * native byte order of the underlying platform.
     * <p>
     * This method behaves as if it returns the result of calling the
     * byte buffer, offset, and mask accepting
     * {@link #fromByteBuffer(VectorSpecies<$Boxtype$>, ByteBuffer, int, VectorMask)} method} as follows:
     * <pre>{@code
     *   return this.fromByteBuffer(b, i, this.maskAllTrue())
     * }</pre>
     *
     * @param species species of desired vector
     * @param bb the byte buffer
     * @param ix the offset into the byte buffer
     * @return a vector loaded from a byte buffer
     * @throws IndexOutOfBoundsException if the offset is {@code < 0},
     * or {@code > b.limit()},
     * or if there are fewer than
     * {@code this.length() * this.elementSize() / Byte.SIZE} bytes
     * remaining in the byte buffer from the given offset
     */
    @ForceInline
    @SuppressWarnings("unchecked")
    public static $abstractvectortype$ fromByteBuffer(VectorSpecies<$Boxtype$> species, ByteBuffer bb, int ix) {
        if (bb.order() != ByteOrder.nativeOrder()) {
            throw new IllegalArgumentException();
        }
        ix = VectorIntrinsics.checkIndex(ix, bb.limit(), species.bitSize() / Byte.SIZE);
        return VectorIntrinsics.load((Class<$abstractvectortype$>) species.boxType(), $type$.class, species.length(),
                                     U.getReference(bb, BYTE_BUFFER_HB), U.getLong(bb, BUFFER_ADDRESS) + ix,
                                     bb, ix, species,
                                     (c, idx, s) -> {
                                         ByteBuffer bbc = c.duplicate().position(idx).order(ByteOrder.nativeOrder());
                                         $Type$Buffer tb = bbc{#if[byte]?;:.as$Type$Buffer();}
                                         return (($Type$Species)s).op(i -> tb.get());
                                     });
    }

    /**
     * Loads a vector from a {@link ByteBuffer byte buffer} starting at an
     * offset into the byte buffer and using a mask.
     * <p>
     * This method behaves as if the byte buffer is viewed as a primitive
     * {@link java.nio.Buffer buffer} for the primitive element type,
     * according to the native byte order of the underlying platform, and
     * the returned vector is loaded with a mask from a primitive array
     * obtained from the primitive buffer.
     * The following pseudocode expresses the behaviour, where
     * {@coce EBuffer} is the primitive buffer type, {@code e} is the
     * primitive element type, and {@code ESpecies<S>} is the primitive
     * species for {@code e}:
     * <pre>{@code
     * EBuffer eb = b.duplicate().
     *     order(ByteOrder.nativeOrder()).position(i).
     *     asEBuffer();
     * e[] es = new e[this.length()];
     * for (int n = 0; n < t.length; n++) {
     *     if (m.isSet(n))
     *         es[n] = eb.get(n);
     * }
     * Vector<E> r = ((ESpecies<S>)this).fromArray(es, 0, m);
     * }</pre>
     *
     * @param species species of desired vector
     * @param bb the byte buffer
     * @param ix the offset into the byte buffer
     * @param m the mask
     * @return a vector loaded from a byte buffer
     * @throws IndexOutOfBoundsException if the offset is {@code < 0},
     * or {@code > b.limit()},
     * for any vector lane index {@code N} where the mask at lane {@code N}
     * is set
     * {@code i >= b.limit() - (N * this.elementSize() / Byte.SIZE)}
     */
    @ForceInline
    public static $abstractvectortype$ fromByteBuffer(VectorSpecies<$Boxtype$> species, ByteBuffer bb, int ix, VectorMask<$Boxtype$> m) {
        return zero(species).blend(fromByteBuffer(species, bb, ix), m);
    }

    /**
     * Returns a vector where all lane elements are set to the primitive
     * value {@code e}.
     *
     * @param s species of the desired vector
     * @param e the value
     * @return a vector of vector where all lane elements are set to
     * the primitive value {@code e}
     */
#if[FP]
    @ForceInline
    @SuppressWarnings("unchecked")
    public static $abstractvectortype$ broadcast(VectorSpecies<$Boxtype$> s, $type$ e) {
        return VectorIntrinsics.broadcastCoerced(
            (Class<$abstractvectortype$>) s.boxType(), $type$.class, s.length(),
            $Type$.$type$To$Bitstype$Bits(e), s,
            ((bits, sp) -> (($Type$Species)sp).op(i -> $Type$.$bitstype$BitsTo$Type$(($bitstype$)bits))));
    }
#else[FP]
    @ForceInline
    @SuppressWarnings("unchecked")
    public static $abstractvectortype$ broadcast(VectorSpecies<$Boxtype$> s, $type$ e) {
        return VectorIntrinsics.broadcastCoerced(
            (Class<$abstractvectortype$>) s.boxType(), $type$.class, s.length(),
            e, s,
            ((bits, sp) -> (($Type$Species)sp).op(i -> ($type$)bits)));
    }
#end[FP]

    /**
     * Returns a vector where each lane element is set to a given
     * primitive value.
     * <p>
     * For each vector lane, where {@code N} is the vector lane index, the
     * the primitive value at index {@code N} is placed into the resulting
     * vector at lane index {@code N}.
     *
     * @param s species of the desired vector
     * @param es the given primitive values
     * @return a vector where each lane element is set to a given primitive
     * value
     * @throws IndexOutOfBoundsException if {@code es.length < this.length()}
     */
    @ForceInline
    @SuppressWarnings("unchecked")
    public static $abstractvectortype$ scalars(VectorSpecies<$Boxtype$> s, $type$... es) {
        Objects.requireNonNull(es);
        int ix = VectorIntrinsics.checkIndex(0, es.length, s.length());
        return VectorIntrinsics.load((Class<$abstractvectortype$>) s.boxType(), $type$.class, s.length(),
                                     es, Unsafe.ARRAY_$TYPE$_BASE_OFFSET,
                                     es, ix, s,
                                     (c, idx, sp) -> (($Type$Species)sp).op(n -> c[idx + n]));
    }

    /**
     * Returns a vector where the first lane element is set to the primtive
     * value {@code e}, all other lane elements are set to the default
     * value.
     *
     * @param s species of the desired vector
     * @param e the value
     * @return a vector where the first lane element is set to the primitive
     * value {@code e}
     */
    @ForceInline
    public static final $abstractvectortype$ single(VectorSpecies<$Boxtype$> s, $type$ e) {
        return zero(s).with(0, e);
    }

    /**
     * Returns a vector where each lane element is set to a randomly
     * generated primitive value.
     *
     * The semantics are equivalent to calling
#if[byteOrShort]
     * ($type$){@link ThreadLocalRandom#nextInt()}
#else[byteOrShort]
     * {@link ThreadLocalRandom#next$Type$()}
#end[byteOrShort]
     *
     * @param s species of the desired vector
     * @return a vector where each lane elements is set to a randomly
     * generated primitive value
     */
#if[intOrLong]
    public static $abstractvectortype$ random(VectorSpecies<$Boxtype$> s) {
        ThreadLocalRandom r = ThreadLocalRandom.current();
        return (($Type$Species)s).op(i -> r.next$Type$());
    }
#else[intOrLong]
#if[FP]
    public static $abstractvectortype$ random(VectorSpecies<$Boxtype$> s) {
        ThreadLocalRandom r = ThreadLocalRandom.current();
        return (($Type$Species)s).op(i -> r.next$Type$());
    }
#else[FP]
    public static $abstractvectortype$ random(VectorSpecies<$Boxtype$> s) {
        ThreadLocalRandom r = ThreadLocalRandom.current();
        return (($Type$Species)s).op(i -> ($type$) r.nextInt());
    }
#end[FP]
#end[intOrLong]

    // Ops

    @Override
    public abstract $abstractvectortype$ add(Vector<$Boxtype$> v);

    /**
     * Adds this vector to the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive addition operation
     * ({@code +}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the result of adding this vector to the broadcast of an input
     * scalar
     */
    public abstract $abstractvectortype$ add($type$ s);

    @Override
    public abstract $abstractvectortype$ add(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m);

    /**
     * Adds this vector to broadcast of an input scalar,
     * selecting lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive addition operation
     * ({@code +}) is applied to lane elements.
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return the result of adding this vector to the broadcast of an input
     * scalar
     */
    public abstract $abstractvectortype$ add($type$ s, VectorMask<$Boxtype$> m);

    @Override
    public abstract $abstractvectortype$ sub(Vector<$Boxtype$> v);

    /**
     * Subtracts the broadcast of an input scalar from this vector.
     * <p>
     * This is a vector binary operation where the primitive subtraction
     * operation ({@code -}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the result of subtracting the broadcast of an input
     * scalar from this vector
     */
    public abstract $abstractvectortype$ sub($type$ s);

    @Override
    public abstract $abstractvectortype$ sub(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m);

    /**
     * Subtracts the broadcast of an input scalar from this vector, selecting
     * lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive subtraction
     * operation ({@code -}) is applied to lane elements.
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return the result of subtracting the broadcast of an input
     * scalar from this vector
     */
    public abstract $abstractvectortype$ sub($type$ s, VectorMask<$Boxtype$> m);

    @Override
    public abstract $abstractvectortype$ mul(Vector<$Boxtype$> v);

    /**
     * Multiplies this vector with the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive multiplication
     * operation ({@code *}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the result of multiplying this vector with the broadcast of an
     * input scalar
     */
    public abstract $abstractvectortype$ mul($type$ s);

    @Override
    public abstract $abstractvectortype$ mul(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m);

    /**
     * Multiplies this vector with the broadcast of an input scalar, selecting
     * lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive multiplication
     * operation ({@code *}) is applied to lane elements.
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return the result of multiplying this vector with the broadcast of an
     * input scalar
     */
    public abstract $abstractvectortype$ mul($type$ s, VectorMask<$Boxtype$> m);

    @Override
    public abstract $abstractvectortype$ neg();

    @Override
    public abstract $abstractvectortype$ neg(VectorMask<$Boxtype$> m);

    @Override
    public abstract $abstractvectortype$ abs();

    @Override
    public abstract $abstractvectortype$ abs(VectorMask<$Boxtype$> m);

    @Override
    public abstract $abstractvectortype$ min(Vector<$Boxtype$> v);

    @Override
    public abstract $abstractvectortype$ min(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m);

    /**
     * Returns the minimum of this vector and the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the operation
     * {@code (a, b) -> Math.min(a, b)} is applied to lane elements.
     *
     * @param s the input scalar
     * @return the minimum of this vector and the broadcast of an input scalar
     */
    public abstract $abstractvectortype$ min($type$ s);

    @Override
    public abstract $abstractvectortype$ max(Vector<$Boxtype$> v);

    @Override
    public abstract $abstractvectortype$ max(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m);

    /**
     * Returns the maximum of this vector and the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the operation
     * {@code (a, b) -> Math.max(a, b)} is applied to lane elements.
     *
     * @param s the input scalar
     * @return the maximum of this vector and the broadcast of an input scalar
     */
    public abstract $abstractvectortype$ max($type$ s);

    @Override
    public abstract VectorMask<$Boxtype$> equal(Vector<$Boxtype$> v);

    /**
     * Tests if this vector is equal to the broadcast of an input scalar.
     * <p>
     * This is a vector binary test operation where the primitive equals
     * operation ({@code ==}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the result mask of testing if this vector is equal to the
     * broadcast of an input scalar
     */
    public abstract VectorMask<$Boxtype$> equal($type$ s);

    @Override
    public abstract VectorMask<$Boxtype$> notEqual(Vector<$Boxtype$> v);

    /**
     * Tests if this vector is not equal to the broadcast of an input scalar.
     * <p>
     * This is a vector binary test operation where the primitive not equals
     * operation ({@code !=}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the result mask of testing if this vector is not equal to the
     * broadcast of an input scalar
     */
    public abstract VectorMask<$Boxtype$> notEqual($type$ s);

    @Override
    public abstract VectorMask<$Boxtype$> lessThan(Vector<$Boxtype$> v);

    /**
     * Tests if this vector is less than the broadcast of an input scalar.
     * <p>
     * This is a vector binary test operation where the primitive less than
     * operation ({@code <}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the mask result of testing if this vector is less than the
     * broadcast of an input scalar
     */
    public abstract VectorMask<$Boxtype$> lessThan($type$ s);

    @Override
    public abstract VectorMask<$Boxtype$> lessThanEq(Vector<$Boxtype$> v);

    /**
     * Tests if this vector is less or equal to the broadcast of an input scalar.
     * <p>
     * This is a vector binary test operation where the primitive less than
     * or equal to operation ({@code <=}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the mask result of testing if this vector is less than or equal
     * to the broadcast of an input scalar
     */
    public abstract VectorMask<$Boxtype$> lessThanEq($type$ s);

    @Override
    public abstract VectorMask<$Boxtype$> greaterThan(Vector<$Boxtype$> v);

    /**
     * Tests if this vector is greater than the broadcast of an input scalar.
     * <p>
     * This is a vector binary test operation where the primitive greater than
     * operation ({@code >}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the mask result of testing if this vector is greater than the
     * broadcast of an input scalar
     */
    public abstract VectorMask<$Boxtype$> greaterThan($type$ s);

    @Override
    public abstract VectorMask<$Boxtype$> greaterThanEq(Vector<$Boxtype$> v);

    /**
     * Tests if this vector is greater than or equal to the broadcast of an
     * input scalar.
     * <p>
     * This is a vector binary test operation where the primitive greater than
     * or equal to operation ({@code >=}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the mask result of testing if this vector is greater than or
     * equal to the broadcast of an input scalar
     */
    public abstract VectorMask<$Boxtype$> greaterThanEq($type$ s);

    @Override
    public abstract $abstractvectortype$ blend(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m);

    /**
     * Blends the lane elements of this vector with those of the broadcast of an
     * input scalar, selecting lanes controlled by a mask.
     * <p>
     * For each lane of the mask, at lane index {@code N}, if the mask lane
     * is set then the lane element at {@code N} from the input vector is
     * selected and placed into the resulting vector at {@code N},
     * otherwise the the lane element at {@code N} from this input vector is
     * selected and placed into the resulting vector at {@code N}.
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return the result of blending the lane elements of this vector with
     * those of the broadcast of an input scalar
     */
    public abstract $abstractvectortype$ blend($type$ s, VectorMask<$Boxtype$> m);

    @Override
    public abstract $abstractvectortype$ rearrange(Vector<$Boxtype$> v,
                                                      VectorShuffle<$Boxtype$> s, VectorMask<$Boxtype$> m);

    @Override
    public abstract $abstractvectortype$ rearrange(VectorShuffle<$Boxtype$> m);

    @Override
    public abstract $abstractvectortype$ reshape(VectorSpecies<$Boxtype$> s);

    @Override
    public abstract $abstractvectortype$ rotateEL(int i);

    @Override
    public abstract $abstractvectortype$ rotateER(int i);

    @Override
    public abstract $abstractvectortype$ shiftEL(int i);

    @Override
    public abstract $abstractvectortype$ shiftER(int i);

#if[FP]
    /**
     * Divides this vector by an input vector.
     * <p>
     * This is a vector binary operation where the primitive division
     * operation ({@code /}) is applied to lane elements.
     *
     * @param v the input vector
     * @return the result of dividing this vector by the input vector
     */
    public abstract $abstractvectortype$ div(Vector<$Boxtype$> v);

    /**
     * Divides this vector by the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive division
     * operation ({@code /}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the result of dividing this vector by the broadcast of an input
     * scalar
     */
    public abstract $abstractvectortype$ div($type$ s);

    /**
     * Divides this vector by an input vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive division
     * operation ({@code /}) is applied to lane elements.
     *
     * @param v the input vector
     * @param m the mask controlling lane selection
     * @return the result of dividing this vector by the input vector
     */
    public abstract $abstractvectortype$ div(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m);

    /**
     * Divides this vector by the broadcast of an input scalar, selecting lane
     * elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive division
     * operation ({@code /}) is applied to lane elements.
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return the result of dividing this vector by the broadcast of an input
     * scalar
     */
    public abstract $abstractvectortype$ div($type$ s, VectorMask<$Boxtype$> m);

    /**
     * Calculates the square root of this vector.
     * <p>
     * This is a vector unary operation where the {@link Math#sqrt} operation
     * is applied to lane elements.
     *
     * @return the square root of this vector
     */
    public abstract $abstractvectortype$ sqrt();

    /**
     * Calculates the square root of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * This is a vector unary operation where the {@link Math#sqrt} operation
     * is applied to lane elements.
     *
     * @param m the mask controlling lane selection
     * @return the square root of this vector
     */
    public $abstractvectortype$ sqrt(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.sqrt((double) a));
    }

    /**
     * Calculates the trigonometric tangent of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#tan} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#tan}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#tan}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the tangent of this vector
     */
    public $abstractvectortype$ tan() {
        return uOp((i, a) -> ($type$) Math.tan((double) a));
    }

    /**
     * Calculates the trigonometric tangent of this vector, selecting lane
     * elements controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#tan}
     *
     * @param m the mask controlling lane selection
     * @return the tangent of this vector
     */
    public $abstractvectortype$ tan(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.tan((double) a));
    }

    /**
     * Calculates the hyperbolic tangent of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#tanh} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#tanh}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#tanh}
     * specifications. The computed result will be within 2.5 ulps of the
     * exact result.
     *
     * @return the hyperbolic tangent of this vector
     */
    public $abstractvectortype$ tanh() {
        return uOp((i, a) -> ($type$) Math.tanh((double) a));
    }

    /**
     * Calculates the hyperbolic tangent of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#tanh}
     *
     * @param m the mask controlling lane selection
     * @return the hyperbolic tangent of this vector
     */
    public $abstractvectortype$ tanh(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.tanh((double) a));
    }

    /**
     * Calculates the trigonometric sine of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#sin} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#sin}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#sin}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the sine of this vector
     */
    public $abstractvectortype$ sin() {
        return uOp((i, a) -> ($type$) Math.sin((double) a));
    }

    /**
     * Calculates the trigonometric sine of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#sin}
     *
     * @param m the mask controlling lane selection
     * @return the sine of this vector
     */
    public $abstractvectortype$ sin(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.sin((double) a));
    }

    /**
     * Calculates the hyperbolic sine of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#sinh} operation applied to lane elements.
     * The implementation is not required to return same
     * results as  {@link Math#sinh}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#sinh}
     * specifications. The computed result will be within 2.5 ulps of the
     * exact result.
     *
     * @return the hyperbolic sine of this vector
     */
    public $abstractvectortype$ sinh() {
        return uOp((i, a) -> ($type$) Math.sinh((double) a));
    }

    /**
     * Calculates the hyperbolic sine of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#sinh}
     *
     * @param m the mask controlling lane selection
     * @return the hyperbolic sine of this vector
     */
    public $abstractvectortype$ sinh(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.sinh((double) a));
    }

    /**
     * Calculates the trigonometric cosine of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#cos} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#cos}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#cos}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the cosine of this vector
     */
    public $abstractvectortype$ cos() {
        return uOp((i, a) -> ($type$) Math.cos((double) a));
    }

    /**
     * Calculates the trigonometric cosine of this vector, selecting lane
     * elements controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#cos}
     *
     * @param m the mask controlling lane selection
     * @return the cosine of this vector
     */
    public $abstractvectortype$ cos(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.cos((double) a));
    }

    /**
     * Calculates the hyperbolic cosine of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#cosh} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#cosh}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#cosh}
     * specifications. The computed result will be within 2.5 ulps of the
     * exact result.
     *
     * @return the hyperbolic cosine of this vector
     */
    public $abstractvectortype$ cosh() {
        return uOp((i, a) -> ($type$) Math.cosh((double) a));
    }

    /**
     * Calculates the hyperbolic cosine of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#cosh}
     *
     * @param m the mask controlling lane selection
     * @return the hyperbolic cosine of this vector
     */
    public $abstractvectortype$ cosh(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.cosh((double) a));
    }

    /**
     * Calculates the arc sine of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#asin} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#asin}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#asin}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the arc sine of this vector
     */
    public $abstractvectortype$ asin() {
        return uOp((i, a) -> ($type$) Math.asin((double) a));
    }

    /**
     * Calculates the arc sine of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#asin}
     *
     * @param m the mask controlling lane selection
     * @return the arc sine of this vector
     */
    public $abstractvectortype$ asin(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.asin((double) a));
    }

    /**
     * Calculates the arc cosine of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#acos} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#acos}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#acos}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the arc cosine of this vector
     */
    public $abstractvectortype$ acos() {
        return uOp((i, a) -> ($type$) Math.acos((double) a));
    }

    /**
     * Calculates the arc cosine of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#acos}
     *
     * @param m the mask controlling lane selection
     * @return the arc cosine of this vector
     */
    public $abstractvectortype$ acos(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.acos((double) a));
    }

    /**
     * Calculates the arc tangent of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#atan} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#atan}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#atan}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the arc tangent of this vector
     */
    public $abstractvectortype$ atan() {
        return uOp((i, a) -> ($type$) Math.atan((double) a));
    }

    /**
     * Calculates the arc tangent of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#atan}
     *
     * @param m the mask controlling lane selection
     * @return the arc tangent of this vector
     */
    public $abstractvectortype$ atan(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.atan((double) a));
    }

    /**
     * Calculates the arc tangent of this vector divided by an input vector.
     * <p>
     * This is a vector binary operation with same semantic definition as
     * {@link Math#atan2} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#atan2}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#atan2}
     * specifications. The computed result will be within 2 ulps of the
     * exact result.
     *
     * @param v the input vector
     * @return the arc tangent of this vector divided by the input vector
     */
    public $abstractvectortype$ atan2(Vector<$Boxtype$> v) {
        return bOp(v, (i, a, b) -> ($type$) Math.atan2((double) a, (double) b));
    }

    /**
     * Calculates the arc tangent of this vector divided by the broadcast of an
     * an input scalar.
     * <p>
     * This is a vector binary operation with same semantic definition as
     * {@link Math#atan2} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#atan2}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#atan2}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @param s the input scalar
     * @return the arc tangent of this vector over the input vector
     */
    public abstract $abstractvectortype$ atan2($type$ s);

    /**
     * Calculates the arc tangent of this vector divided by an input vector,
     * selecting lane elements controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#atan2}
     *
     * @param v the input vector
     * @param m the mask controlling lane selection
     * @return the arc tangent of this vector divided by the input vector
     */
    public $abstractvectortype$ atan2(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m) {
        return bOp(v, m, (i, a, b) -> ($type$) Math.atan2((double) a, (double) b));
    }

    /**
     * Calculates the arc tangent of this vector divided by the broadcast of an
     * an input scalar, selecting lane elements controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#atan2}
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return the arc tangent of this vector over the input vector
     */
    public abstract $abstractvectortype$ atan2($type$ s, VectorMask<$Boxtype$> m);

    /**
     * Calculates the cube root of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#cbrt} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#cbrt}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#cbrt}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the cube root of this vector
     */
    public $abstractvectortype$ cbrt() {
        return uOp((i, a) -> ($type$) Math.cbrt((double) a));
    }

    /**
     * Calculates the cube root of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#cbrt}
     *
     * @param m the mask controlling lane selection
     * @return the cube root of this vector
     */
    public $abstractvectortype$ cbrt(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.cbrt((double) a));
    }

    /**
     * Calculates the natural logarithm of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#log} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#log}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#log}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the natural logarithm of this vector
     */
    public $abstractvectortype$ log() {
        return uOp((i, a) -> ($type$) Math.log((double) a));
    }

    /**
     * Calculates the natural logarithm of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#log}
     *
     * @param m the mask controlling lane selection
     * @return the natural logarithm of this vector
     */
    public $abstractvectortype$ log(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.log((double) a));
    }

    /**
     * Calculates the base 10 logarithm of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#log10} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#log10}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#log10}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the base 10 logarithm of this vector
     */
    public $abstractvectortype$ log10() {
        return uOp((i, a) -> ($type$) Math.log10((double) a));
    }

    /**
     * Calculates the base 10 logarithm of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#log10}
     *
     * @param m the mask controlling lane selection
     * @return the base 10 logarithm of this vector
     */
    public $abstractvectortype$ log10(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.log10((double) a));
    }

    /**
     * Calculates the natural logarithm of the sum of this vector and the
     * broadcast of {@code 1}.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#log1p} operation applied to lane elements.
     * The implementation is not required to return same
     * results as  {@link Math#log1p}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#log1p}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the natural logarithm of the sum of this vector and the broadcast
     * of {@code 1}
     */
    public $abstractvectortype$ log1p() {
        return uOp((i, a) -> ($type$) Math.log1p((double) a));
    }

    /**
     * Calculates the natural logarithm of the sum of this vector and the
     * broadcast of {@code 1}, selecting lane elements controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#log1p}
     *
     * @param m the mask controlling lane selection
     * @return the natural logarithm of the sum of this vector and the broadcast
     * of {@code 1}
     */
    public $abstractvectortype$ log1p(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.log1p((double) a));
    }

    /**
     * Calculates this vector raised to the power of an input vector.
     * <p>
     * This is a vector binary operation with same semantic definition as
     * {@link Math#pow} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#pow}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#pow}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @param v the input vector
     * @return this vector raised to the power of an input vector
     */
    public $abstractvectortype$ pow(Vector<$Boxtype$> v) {
        return bOp(v, (i, a, b) -> ($type$) Math.pow((double) a, (double) b));
    }

    /**
     * Calculates this vector raised to the power of the broadcast of an input
     * scalar.
     * <p>
     * This is a vector binary operation with same semantic definition as
     * {@link Math#pow} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#pow}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#pow}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @param s the input scalar
     * @return this vector raised to the power of the broadcast of an input
     * scalar.
     */
    public abstract $abstractvectortype$ pow($type$ s);

    /**
     * Calculates this vector raised to the power of an input vector, selecting
     * lane elements controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#pow}
     *
     * @param v the input vector
     * @param m the mask controlling lane selection
     * @return this vector raised to the power of an input vector
     */
    public $abstractvectortype$ pow(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m) {
        return bOp(v, m, (i, a, b) -> ($type$) Math.pow((double) a, (double) b));
    }

    /**
     * Calculates this vector raised to the power of the broadcast of an input
     * scalar, selecting lane elements controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#pow}
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return this vector raised to the power of the broadcast of an input
     * scalar.
     */
    public abstract $abstractvectortype$ pow($type$ s, VectorMask<$Boxtype$> m);

    /**
     * Calculates the broadcast of Euler's number {@code e} raised to the power
     * of this vector.
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#exp} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#exp}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#exp}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the broadcast of Euler's number {@code e} raised to the power of
     * this vector
     */
    public $abstractvectortype$ exp() {
        return uOp((i, a) -> ($type$) Math.exp((double) a));
    }

    /**
     * Calculates the broadcast of Euler's number {@code e} raised to the power
     * of this vector, selecting lane elements controlled by a mask.
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#exp}
     *
     * @param m the mask controlling lane selection
     * @return the broadcast of Euler's number {@code e} raised to the power of
     * this vector
     */
    public $abstractvectortype$ exp(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.exp((double) a));
    }

    /**
     * Calculates the broadcast of Euler's number {@code e} raised to the power
     * of this vector minus the broadcast of {@code -1}.
     * More specifically as if the following (ignoring any differences in
     * numerical accuracy):
     * <pre>{@code
     *   this.exp().sub(this.species().broadcast(1))
     * }</pre>
     * <p>
     * This is a vector unary operation with same semantic definition as
     * {@link Math#expm1} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#expm1}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#expm1}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @return the broadcast of Euler's number {@code e} raised to the power of
     * this vector minus the broadcast of {@code -1}
     */
    public $abstractvectortype$ expm1() {
        return uOp((i, a) -> ($type$) Math.expm1((double) a));
    }

    /**
     * Calculates the broadcast of Euler's number {@code e} raised to the power
     * of this vector minus the broadcast of {@code -1}, selecting lane elements
     * controlled by a mask
     * More specifically as if the following (ignoring any differences in
     * numerical accuracy):
     * <pre>{@code
     *   this.exp(m).sub(this.species().broadcast(1), m)
     * }</pre>
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#expm1}
     *
     * @param m the mask controlling lane selection
     * @return the broadcast of Euler's number {@code e} raised to the power of
     * this vector minus the broadcast of {@code -1}
     */
    public $abstractvectortype$ expm1(VectorMask<$Boxtype$> m) {
        return uOp(m, (i, a) -> ($type$) Math.expm1((double) a));
    }

    /**
     * Calculates the product of this vector and a first input vector summed
     * with a second input vector.
     * More specifically as if the following (ignoring any differences in
     * numerical accuracy):
     * <pre>{@code
     *   this.mul(v1).add(v2)
     * }</pre>
     * <p>
     * This is a vector ternary operation where the {@link Math#fma} operation
     * is applied to lane elements.
     *
     * @param v1 the first input vector
     * @param v2 the second input vector
     * @return the product of this vector and the first input vector summed with
     * the second input vector
     */
    public abstract $abstractvectortype$ fma(Vector<$Boxtype$> v1, Vector<$Boxtype$> v2);

    /**
     * Calculates the product of this vector and the broadcast of a first input
     * scalar summed with the broadcast of a second input scalar.
     * More specifically as if the following:
     * <pre>{@code
     *   this.fma(this.species().broadcast(s1), this.species().broadcast(s2))
     * }</pre>
     * <p>
     * This is a vector ternary operation where the {@link Math#fma} operation
     * is applied to lane elements.
     *
     * @param s1 the first input scalar
     * @param s2 the second input scalar
     * @return the product of this vector and the broadcast of a first input
     * scalar summed with the broadcast of a second input scalar
     */
    public abstract $abstractvectortype$ fma($type$ s1, $type$ s2);

    /**
     * Calculates the product of this vector and a first input vector summed
     * with a second input vector, selecting lane elements controlled by a mask.
     * More specifically as if the following (ignoring any differences in
     * numerical accuracy):
     * <pre>{@code
     *   this.mul(v1, m).add(v2, m)
     * }</pre>
     * <p>
     * This is a vector ternary operation where the {@link Math#fma} operation
     * is applied to lane elements.
     *
     * @param v1 the first input vector
     * @param v2 the second input vector
     * @param m the mask controlling lane selection
     * @return the product of this vector and the first input vector summed with
     * the second input vector
     */
    public $abstractvectortype$ fma(Vector<$Boxtype$> v1, Vector<$Boxtype$> v2, VectorMask<$Boxtype$> m) {
        return tOp(v1, v2, m, (i, a, b, c) -> Math.fma(a, b, c));
    }

    /**
     * Calculates the product of this vector and the broadcast of a first input
     * scalar summed with the broadcast of a second input scalar, selecting lane
     * elements controlled by a mask
     * More specifically as if the following:
     * <pre>{@code
     *   this.fma(this.species().broadcast(s1), this.species().broadcast(s2), m)
     * }</pre>
     * <p>
     * This is a vector ternary operation where the {@link Math#fma} operation
     * is applied to lane elements.
     *
     * @param s1 the first input scalar
     * @param s2 the second input scalar
     * @param m the mask controlling lane selection
     * @return the product of this vector and the broadcast of a first input
     * scalar summed with the broadcast of a second input scalar
     */
    public abstract $abstractvectortype$ fma($type$ s1, $type$ s2, VectorMask<$Boxtype$> m);

    /**
     * Calculates square root of the sum of the squares of this vector and an
     * input vector.
     * More specifically as if the following (ignoring any differences in
     * numerical accuracy):
     * <pre>{@code
     *   this.mul(this).add(v.mul(v)).sqrt()
     * }</pre>
     * <p>
     * This is a vector binary operation with same semantic definition as
     * {@link Math#hypot} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#hypot}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#hypot}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @param v the input vector
     * @return square root of the sum of the squares of this vector and an input
     * vector
     */
    public $abstractvectortype$ hypot(Vector<$Boxtype$> v) {
        return bOp(v, (i, a, b) -> ($type$) Math.hypot((double) a, (double) b));
    }

    /**
     * Calculates square root of the sum of the squares of this vector and the
     * broadcast of an input scalar.
     * More specifically as if the following (ignoring any differences in
     * numerical accuracy):
     * <pre>{@code
     *   this.mul(this).add(this.species().broadcast(v * v)).sqrt()
     * }</pre>
     * <p>
     * This is a vector binary operation with same semantic definition as
     * {@link Math#hypot} operation applied to lane elements.
     * The implementation is not required to return same
     * results as {@link Math#hypot}, but adheres to rounding, monotonicity,
     * and special case semantics as defined in the {@link Math#hypot}
     * specifications. The computed result will be within 1 ulp of the
     * exact result.
     *
     * @param s the input scalar
     * @return square root of the sum of the squares of this vector and the
     * broadcast of an input scalar
     */
    public abstract $abstractvectortype$ hypot($type$ s);

    /**
     * Calculates square root of the sum of the squares of this vector and an
     * input vector, selecting lane elements controlled by a mask.
     * More specifically as if the following (ignoring any differences in
     * numerical accuracy):
     * <pre>{@code
     *   this.mul(this, m).add(v.mul(v), m).sqrt(m)
     * }</pre>
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#hypot}
     *
     * @param v the input vector
     * @param m the mask controlling lane selection
     * @return square root of the sum of the squares of this vector and an input
     * vector
     */
    public $abstractvectortype$ hypot(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m) {
        return bOp(v, m, (i, a, b) -> ($type$) Math.hypot((double) a, (double) b));
    }

    /**
     * Calculates square root of the sum of the squares of this vector and the
     * broadcast of an input scalar, selecting lane elements controlled by a
     * mask.
     * More specifically as if the following (ignoring any differences in
     * numerical accuracy):
     * <pre>{@code
     *   this.mul(this, m).add(this.species().broadcast(v * v), m).sqrt(m)
     * }</pre>
     * <p>
     * Semantics for rounding, monotonicity, and special cases are
     * described in {@link $abstractvectortype$#hypot}
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return square root of the sum of the squares of this vector and the
     * broadcast of an input scalar
     */
    public abstract $abstractvectortype$ hypot($type$ s, VectorMask<$Boxtype$> m);
#end[FP]

#if[BITWISE]

    /**
     * Bitwise ANDs this vector with an input vector.
     * <p>
     * This is a vector binary operation where the primitive bitwise AND
     * operation ({@code &}) is applied to lane elements.
     *
     * @param v the input vector
     * @return the bitwise AND of this vector with the input vector
     */
    public abstract $abstractvectortype$ and(Vector<$Boxtype$> v);

    /**
     * Bitwise ANDs this vector with the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive bitwise AND
     * operation ({@code &}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the bitwise AND of this vector with the broadcast of an input
     * scalar
     */
    public abstract $abstractvectortype$ and($type$ s);

    /**
     * Bitwise ANDs this vector with an input vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive bitwise AND
     * operation ({@code &}) is applied to lane elements.
     *
     * @param v the input vector
     * @param m the mask controlling lane selection
     * @return the bitwise AND of this vector with the input vector
     */
    public abstract $abstractvectortype$ and(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m);

    /**
     * Bitwise ANDs this vector with the broadcast of an input scalar, selecting
     * lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive bitwise AND
     * operation ({@code &}) is applied to lane elements.
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return the bitwise AND of this vector with the broadcast of an input
     * scalar
     */
    public abstract $abstractvectortype$ and($type$ s, VectorMask<$Boxtype$> m);

    /**
     * Bitwise ORs this vector with an input vector.
     * <p>
     * This is a vector binary operation where the primitive bitwise OR
     * operation ({@code |}) is applied to lane elements.
     *
     * @param v the input vector
     * @return the bitwise OR of this vector with the input vector
     */
    public abstract $abstractvectortype$ or(Vector<$Boxtype$> v);

    /**
     * Bitwise ORs this vector with the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive bitwise OR
     * operation ({@code |}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the bitwise OR of this vector with the broadcast of an input
     * scalar
     */
    public abstract $abstractvectortype$ or($type$ s);

    /**
     * Bitwise ORs this vector with an input vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive bitwise OR
     * operation ({@code |}) is applied to lane elements.
     *
     * @param v the input vector
     * @param m the mask controlling lane selection
     * @return the bitwise OR of this vector with the input vector
     */
    public abstract $abstractvectortype$ or(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m);

    /**
     * Bitwise ORs this vector with the broadcast of an input scalar, selecting
     * lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive bitwise OR
     * operation ({@code |}) is applied to lane elements.
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return the bitwise OR of this vector with the broadcast of an input
     * scalar
     */
    public abstract $abstractvectortype$ or($type$ s, VectorMask<$Boxtype$> m);

    /**
     * Bitwise XORs this vector with an input vector.
     * <p>
     * This is a vector binary operation where the primitive bitwise XOR
     * operation ({@code ^}) is applied to lane elements.
     *
     * @param v the input vector
     * @return the bitwise XOR of this vector with the input vector
     */
    public abstract $abstractvectortype$ xor(Vector<$Boxtype$> v);

    /**
     * Bitwise XORs this vector with the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive bitwise XOR
     * operation ({@code ^}) is applied to lane elements.
     *
     * @param s the input scalar
     * @return the bitwise XOR of this vector with the broadcast of an input
     * scalar
     */
    public abstract $abstractvectortype$ xor($type$ s);

    /**
     * Bitwise XORs this vector with an input vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive bitwise XOR
     * operation ({@code ^}) is applied to lane elements.
     *
     * @param v the input vector
     * @param m the mask controlling lane selection
     * @return the bitwise XOR of this vector with the input vector
     */
    public abstract $abstractvectortype$ xor(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m);

    /**
     * Bitwise XORs this vector with the broadcast of an input scalar, selecting
     * lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive bitwise XOR
     * operation ({@code ^}) is applied to lane elements.
     *
     * @param s the input scalar
     * @param m the mask controlling lane selection
     * @return the bitwise XOR of this vector with the broadcast of an input
     * scalar
     */
    public abstract $abstractvectortype$ xor($type$ s, VectorMask<$Boxtype$> m);

    /**
     * Bitwise NOTs this vector.
     * <p>
     * This is a vector unary operation where the primitive bitwise NOT
     * operation ({@code ~}) is applied to lane elements.
     *
     * @return the bitwise NOT of this vector
     */
    public abstract $abstractvectortype$ not();

    /**
     * Bitwise NOTs this vector, selecting lane elements controlled by a mask.
     * <p>
     * This is a vector unary operation where the primitive bitwise NOT
     * operation ({@code ~}) is applied to lane elements.
     *
     * @param m the mask controlling lane selection
     * @return the bitwise NOT of this vector
     */
    public abstract $abstractvectortype$ not(VectorMask<$Boxtype$> m);

#if[byte]
    /**
     * Logically left shifts this vector by the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive logical left shift
     * operation ({@code <<}) is applied to lane elements to left shift the
     * element by shift value as specified by the input scalar. Only the 3
     * lowest-order bits of shift value are used. It is as if the shift value
     * were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0x7.
     * The shift distance actually used is therefore always in the range 0 to 7, inclusive.
     *
     * @param s the input scalar; the number of the bits to left shift
     * @return the result of logically left shifting left this vector by the
     * broadcast of an input scalar
     */
#end[byte]
#if[short]
    /**
     * Logically left shifts this vector by the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive logical left shift
     * operation ({@code <<}) is applied to lane elements to left shift the
     * element by shift value as specified by the input scalar. Only the 4
     * lowest-order bits of shift value are used. It is as if the shift value
     * were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0xF.
     * The shift distance actually used is therefore always in the range 0 to 15, inclusive.
     *
     * @param s the input scalar; the number of the bits to left shift
     * @return the result of logically left shifting left this vector by the
     * broadcast of an input scalar
     */
#end[short]
#if[intOrLong]
    /**
     * Logically left shifts this vector by the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive logical left shift
     * operation ({@code <<}) is applied to lane elements.
     *
     * @param s the input scalar; the number of the bits to left shift
     * @return the result of logically left shifting left this vector by the
     * broadcast of an input scalar
     */
#end[intOrLong]
    public abstract $abstractvectortype$ shiftL(int s);

#if[byte]
    /**
     * Logically left shifts this vector by the broadcast of an input scalar,
     * selecting lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive logical left shift
     * operation ({@code <<}) is applied to lane elements to left shift the
     * element by shift value as specified by the input scalar. Only the 3
     * lowest-order bits of shift value are used. It is as if the shift value
     * were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0x7.
     * The shift distance actually used is therefore always in the range 0 to 7, inclusive.
     *
     * @param s the input scalar; the number of the bits to left shift
     * @param m the mask controlling lane selection
     * @return the result of logically left shifting left this vector by the
     * broadcast of an input scalar
     */
#end[byte]
#if[short]
    /**
     * Logically left shifts this vector by the broadcast of an input scalar,
     * selecting lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive logical left shift
     * operation ({@code <<}) is applied to lane elements to left shift the
     * element by shift value as specified by the input scalar. Only the 4
     * lowest-order bits of shift value are used. It is as if the shift value
     * were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0xF.
     * The shift distance actually used is therefore always in the range 0 to 15, inclusive.
     *
     * @param s the input scalar; the number of the bits to left shift
     * @param m the mask controlling lane selection
     * @return the result of logically left shifting left this vector by the
     * broadcast of an input scalar
     */
#end[short]
#if[intOrLong]
    /**
     * Logically left shifts this vector by the broadcast of an input scalar,
     * selecting lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive logical left shift
     * operation ({@code <<}) is applied to lane elements.
     *
     * @param s the input scalar; the number of the bits to left shift
     * @param m the mask controlling lane selection
     * @return the result of logically left shifting this vector by the
     * broadcast of an input scalar
     */
#end[intOrLong]
    public abstract $abstractvectortype$ shiftL(int s, VectorMask<$Boxtype$> m);

#if[intOrLong]
    /**
     * Logically left shifts this vector by an input vector.
     * <p>
     * This is a vector binary operation where the primitive logical left shift
     * operation ({@code <<}) is applied to lane elements.
     *
     * @param v the input vector
     * @return the result of logically left shifting this vector by the input
     * vector
     */
    public abstract $abstractvectortype$ shiftL(Vector<$Boxtype$> v);

    /**
     * Logically left shifts this vector by an input vector, selecting lane
     * elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive logical left shift
     * operation ({@code <<}) is applied to lane elements.
     *
     * @param v the input vector
     * @param m the mask controlling lane selection
     * @return the result of logically left shifting this vector by the input
     * vector
     */
    public $abstractvectortype$ shiftL(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m) {
        return bOp(v, m, (i, a, b) -> ($type$) (a << b));
    }
#end[intOrLong]

    // logical, or unsigned, shift right

#if[byte]
     /**
     * Logically right shifts (or unsigned right shifts) this vector by the
     * broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive logical right shift
     * operation ({@code >>>}) is applied to lane elements to logically right shift the
     * element by shift value as specified by the input scalar. Only the 3
     * lowest-order bits of shift value are used. It is as if the shift value
     * were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0x7.
     * The shift distance actually used is therefore always in the range 0 to 7, inclusive.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @return the result of logically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[byte]
#if[short]
     /**
     * Logically right shifts (or unsigned right shifts) this vector by the
     * broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive logical right shift
     * operation ({@code >>>}) is applied to lane elements to logically right shift the
     * element by shift value as specified by the input scalar. Only the 4
     * lowest-order bits of shift value are used. It is as if the shift value
     * were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0xF.
     * The shift distance actually used is therefore always in the range 0 to 15, inclusive.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @return the result of logically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[short]
#if[intOrLong]
    /**
     * Logically right shifts (or unsigned right shifts) this vector by the
     * broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive logical right shift
     * operation ({@code >>>}) is applied to lane elements.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @return the result of logically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[intOrLong]
    public abstract $abstractvectortype$ shiftR(int s);

#if[byte]
     /**
     * Logically right shifts (or unsigned right shifts) this vector by the
     * broadcast of an input scalar, selecting lane elements controlled by a
     * mask.
     * <p>
     * This is a vector binary operation where the primitive logical right shift
     * operation ({@code >>>}) is applied to lane elements to logically right shift the
     * element by shift value as specified by the input scalar. Only the 3
     * lowest-order bits of shift value are used. It is as if the shift value
     * were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0x7.
     * The shift distance actually used is therefore always in the range 0 to 7, inclusive.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @param m the mask controlling lane selection
     * @return the result of logically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[byte]
#if[short]
     /**
     * Logically right shifts (or unsigned right shifts) this vector by the
     * broadcast of an input scalar, selecting lane elements controlled by a
     * mask.
     * <p>
     * This is a vector binary operation where the primitive logical right shift
     * operation ({@code >>>}) is applied to lane elements to logically right shift the
     * element by shift value as specified by the input scalar. Only the 4
     * lowest-order bits of shift value are used. It is as if the shift value
     * were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0xF.
     * The shift distance actually used is therefore always in the range 0 to 15, inclusive.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @param m the mask controlling lane selection
     * @return the result of logically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[short]
#if[intOrLong]
    /**
     * Logically right shifts (or unsigned right shifts) this vector by the
     * broadcast of an input scalar, selecting lane elements controlled by a
     * mask.
     * <p>
     * This is a vector binary operation where the primitive logical right shift
     * operation ({@code >>>}) is applied to lane elements.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @param m the mask controlling lane selection
     * @return the result of logically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[intOrLong]
    public abstract $abstractvectortype$ shiftR(int s, VectorMask<$Boxtype$> m);

#if[intOrLong]
    /**
     * Logically right shifts (or unsigned right shifts) this vector by an
     * input vector.
     * <p>
     * This is a vector binary operation where the primitive logical right shift
     * operation ({@code >>>}) is applied to lane elements.
     *
     * @param v the input vector
     * @return the result of logically right shifting this vector by the
     * input vector
     */
    public abstract $abstractvectortype$ shiftR(Vector<$Boxtype$> v);

    /**
     * Logically right shifts (or unsigned right shifts) this vector by an
     * input vector, selecting lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive logical right shift
     * operation ({@code >>>}) is applied to lane elements.
     *
     * @param v the input vector
     * @param m the mask controlling lane selection
     * @return the result of logically right shifting this vector by the
     * input vector
     */
    public $abstractvectortype$ shiftR(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m) {
        return bOp(v, m, (i, a, b) -> ($type$) (a >>> b));
    }
#end[intOrLong]

#if[byte]
    /**
     * Arithmetically right shifts (or signed right shifts) this vector by the
     * broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive arithmetic right
     * shift operation ({@code >>}) is applied to lane elements  to arithmetically
     * right shift the element by shift value as specified by the input scalar.
     * Only the 3 lowest-order bits of shift value are used. It is as if the shift
     * value were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0x7.
     * The shift distance actually used is therefore always in the range 0 to 7, inclusive.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @return the result of arithmetically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[byte]
#if[short]
    /**
     * Arithmetically right shifts (or signed right shifts) this vector by the
     * broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive arithmetic right
     * shift operation ({@code >>}) is applied to lane elements  to arithmetically
     * right shift the element by shift value as specified by the input scalar.
     * Only the 4 lowest-order bits of shift value are used. It is as if the shift
     * value were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0xF.
     * The shift distance actually used is therefore always in the range 0 to 15, inclusive.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @return the result of arithmetically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[short]
#if[intOrLong]
    /**
     * Arithmetically right shifts (or signed right shifts) this vector by the
     * broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the primitive arithmetic right
     * shift operation ({@code >>}) is applied to lane elements.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @return the result of arithmetically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[intOrLong]
    public abstract $abstractvectortype$ aShiftR(int s);

#if[byte]
    /**
     * Arithmetically right shifts (or signed right shifts) this vector by the
     * broadcast of an input scalar, selecting lane elements controlled by a
     * mask.
     * <p>
     * This is a vector binary operation where the primitive arithmetic right
     * shift operation ({@code >>}) is applied to lane elements  to arithmetically
     * right shift the element by shift value as specified by the input scalar.
     * Only the 3 lowest-order bits of shift value are used. It is as if the shift
     * value were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0x7.
     * The shift distance actually used is therefore always in the range 0 to 7, inclusive.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @param m the mask controlling lane selection
     * @return the result of arithmetically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[byte]
#if[short]
    /**
     * Arithmetically right shifts (or signed right shifts) this vector by the
     * broadcast of an input scalar, selecting lane elements controlled by a
     * mask.
     * <p>
     * This is a vector binary operation where the primitive arithmetic right
     * shift operation ({@code >>}) is applied to lane elements  to arithmetically
     * right shift the element by shift value as specified by the input scalar.
     * Only the 4 lowest-order bits of shift value are used. It is as if the shift
     * value were subjected to a bitwise logical AND operator ({@code &}) with the mask value 0xF.
     * The shift distance actually used is therefore always in the range 0 to 15, inclusive.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @param m the mask controlling lane selection
     * @return the result of arithmetically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[short]
#if[intOrLong]
    /**
     * Arithmetically right shifts (or signed right shifts) this vector by the
     * broadcast of an input scalar, selecting lane elements controlled by a
     * mask.
     * <p>
     * This is a vector binary operation where the primitive arithmetic right
     * shift operation ({@code >>}) is applied to lane elements.
     *
     * @param s the input scalar; the number of the bits to right shift
     * @param m the mask controlling lane selection
     * @return the result of arithmetically right shifting this vector by the
     * broadcast of an input scalar
     */
#end[intOrLong]
    public abstract $abstractvectortype$ aShiftR(int s, VectorMask<$Boxtype$> m);

#if[intOrLong]
    /**
     * Arithmetically right shifts (or signed right shifts) this vector by an
     * input vector.
     * <p>
     * This is a vector binary operation where the primitive arithmetic right
     * shift operation ({@code >>}) is applied to lane elements.
     *
     * @param v the input vector
     * @return the result of arithmetically right shifting this vector by the
     * input vector
     */
    public abstract $abstractvectortype$ aShiftR(Vector<$Boxtype$> v);

    /**
     * Arithmetically right shifts (or signed right shifts) this vector by an
     * input vector, selecting lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the primitive arithmetic right
     * shift operation ({@code >>}) is applied to lane elements.
     *
     * @param v the input vector
     * @param m the mask controlling lane selection
     * @return the result of arithmetically right shifting this vector by the
     * input vector
     */
    public $abstractvectortype$ aShiftR(Vector<$Boxtype$> v, VectorMask<$Boxtype$> m) {
        return bOp(v, m, (i, a, b) -> ($type$) (a >> b));
    }

    /**
     * Rotates left this vector by the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the operation
     * {@link $Wideboxtype$#rotateLeft} is applied to lane elements and where
     * lane elements of this vector apply to the first argument, and lane
     * elements of the broadcast vector apply to the second argument (the
     * rotation distance).
     *
     * @param s the input scalar; the number of the bits to rotate left
     * @return the result of rotating left this vector by the broadcast of an
     * input scalar
     */
    @ForceInline
    public final $abstractvectortype$ rotateL(int s) {
        return shiftL(s).or(shiftR(-s));
    }

    /**
     * Rotates left this vector by the broadcast of an input scalar, selecting
     * lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the operation
     * {@link $Wideboxtype$#rotateLeft} is applied to lane elements and where
     * lane elements of this vector apply to the first argument, and lane
     * elements of the broadcast vector apply to the second argument (the
     * rotation distance).
     *
     * @param s the input scalar; the number of the bits to rotate left
     * @param m the mask controlling lane selection
     * @return the result of rotating left this vector by the broadcast of an
     * input scalar
     */
    @ForceInline
    public final $abstractvectortype$ rotateL(int s, VectorMask<$Boxtype$> m) {
        return shiftL(s, m).or(shiftR(-s, m), m);
    }

    /**
     * Rotates right this vector by the broadcast of an input scalar.
     * <p>
     * This is a vector binary operation where the operation
     * {@link $Wideboxtype$#rotateRight} is applied to lane elements and where
     * lane elements of this vector apply to the first argument, and lane
     * elements of the broadcast vector apply to the second argument (the
     * rotation distance).
     *
     * @param s the input scalar; the number of the bits to rotate right
     * @return the result of rotating right this vector by the broadcast of an
     * input scalar
     */
    @ForceInline
    public final $abstractvectortype$ rotateR(int s) {
        return shiftR(s).or(shiftL(-s));
    }

    /**
     * Rotates right this vector by the broadcast of an input scalar, selecting
     * lane elements controlled by a mask.
     * <p>
     * This is a vector binary operation where the operation
     * {@link $Wideboxtype$#rotateRight} is applied to lane elements and where
     * lane elements of this vector apply to the first argument, and lane
     * elements of the broadcast vector apply to the second argument (the
     * rotation distance).
     *
     * @param s the input scalar; the number of the bits to rotate right
     * @param m the mask controlling lane selection
     * @return the result of rotating right this vector by the broadcast of an
     * input scalar
     */
    @ForceInline
    public final $abstractvectortype$ rotateR(int s, VectorMask<$Boxtype$> m) {
        return shiftR(s, m).or(shiftL(-s, m), m);
    }
#end[intOrLong]
#end[BITWISE]

    @Override
    public abstract void intoByteArray(byte[] a, int ix);

    @Override
    public abstract void intoByteArray(byte[] a, int ix, VectorMask<$Boxtype$> m);

    @Override
    public abstract void intoByteBuffer(ByteBuffer bb, int ix);

    @Override
    public abstract void intoByteBuffer(ByteBuffer bb, int ix, VectorMask<$Boxtype$> m);


    // Type specific horizontal reductions
    /**
     * Adds all lane elements of this vector.
     * <p>
#if[FP]
     * This is a vector reduction operation where the addition
     * operation ({@code +}) is applied to lane elements,
     * and the identity value is {@code 0.0}.
     *
     * <p>The value of a floating-point sum is a function both of the input values as well
     * as the order of addition operations. The order of addition operations of this method
     * is intentionally not defined to allow for JVM to generate optimal machine
     * code for the underlying platform at runtime. If the platform supports a vector
     * instruction to add all values in the vector, or if there is some other efficient machine
     * code sequence, then the JVM has the option of generating this machine code. Otherwise,
     * the default implementation of adding vectors sequentially from left to right is used.
     * For this reason, the output of this method may vary for the same input values.
#else[FP]
     * This is an associative vector reduction operation where the addition
     * operation ({@code +}) is applied to lane elements,
     * and the identity value is {@code 0}.
#end[FP]
     *
     * @return the addition of all the lane elements of this vector
     */
    public abstract $type$ addAll();

    /**
     * Adds all lane elements of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
#if[FP]
     * This is a vector reduction operation where the addition
     * operation ({@code +}) is applied to lane elements,
     * and the identity value is {@code 0.0}.
     *
     * <p>The value of a floating-point sum is a function both of the input values as well
     * as the order of addition operations. The order of addition operations of this method
     * is intentionally not defined to allow for JVM to generate optimal machine
     * code for the underlying platform at runtime. If the platform supports a vector
     * instruction to add all values in the vector, or if there is some other efficient machine
     * code sequence, then the JVM has the option of generating this machine code. Otherwise,
     * the default implementation of adding vectors sequentially from left to right is used.
     * For this reason, the output of this method may vary on the same input values.
#else[FP]
     * This is an associative vector reduction operation where the addition
     * operation ({@code +}) is applied to lane elements,
     * and the identity value is {@code 0}.
#end[FP]
     *
     * @param m the mask controlling lane selection
     * @return the addition of the selected lane elements of this vector
     */
    public abstract $type$ addAll(VectorMask<$Boxtype$> m);

    /**
     * Multiplies all lane elements of this vector.
     * <p>
#if[FP]
     * This is a vector reduction operation where the
     * multiplication operation ({@code *}) is applied to lane elements,
     * and the identity value is {@code 1.0}.
     *
     * <p>The order of multiplication operations of this method
     * is intentionally not defined to allow for JVM to generate optimal machine
     * code for the underlying platform at runtime. If the platform supports a vector
     * instruction to multiply all values in the vector, or if there is some other efficient machine
     * code sequence, then the JVM has the option of generating this machine code. Otherwise,
     * the default implementation of multiplying vectors sequentially from left to right is used.
     * For this reason, the output of this method may vary on the same input values.
#else[FP]
     * This is an associative vector reduction operation where the
     * multiplication operation ({@code *}) is applied to lane elements,
     * and the identity value is {@code 1}.
#end[FP]
     *
     * @return the multiplication of all the lane elements of this vector
     */
    public abstract $type$ mulAll();

    /**
     * Multiplies all lane elements of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
#if[FP]
     * This is a vector reduction operation where the
     * multiplication operation ({@code *}) is applied to lane elements,
     * and the identity value is {@code 1.0}.
     *
     * <p>The order of multiplication operations of this method
     * is intentionally not defined to allow for JVM to generate optimal machine
     * code for the underlying platform at runtime. If the platform supports a vector
     * instruction to multiply all values in the vector, or if there is some other efficient machine
     * code sequence, then the JVM has the option of generating this machine code. Otherwise,
     * the default implementation of multiplying vectors sequentially from left to right is used.
     * For this reason, the output of this method may vary on the same input values.
#else[FP]
     * This is an associative vector reduction operation where the
     * multiplication operation ({@code *}) is applied to lane elements,
     * and the identity value is {@code 1}.
#end[FP]
     *
     * @param m the mask controlling lane selection
     * @return the multiplication of all the lane elements of this vector
     */
    public abstract $type$ mulAll(VectorMask<$Boxtype$> m);

    /**
     * Returns the minimum lane element of this vector.
     * <p>
     * This is an associative vector reduction operation where the operation
     * {@code (a, b) -> Math.min(a, b)} is applied to lane elements,
     * and the identity value is
#if[FP]
     * {@link $Boxtype$#POSITIVE_INFINITY}.
#else[FP]
     * {@link $Boxtype$#MAX_VALUE}.
#end[FP]
     *
     * @return the minimum lane element of this vector
     */
    public abstract $type$ minAll();

    /**
     * Returns the minimum lane element of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * This is an associative vector reduction operation where the operation
     * {@code (a, b) -> Math.min(a, b)} is applied to lane elements,
     * and the identity value is
#if[FP]
     * {@link $Boxtype$#POSITIVE_INFINITY}.
#else[FP]
     * {@link $Boxtype$#MAX_VALUE}.
#end[FP]
     *
     * @param m the mask controlling lane selection
     * @return the minimum lane element of this vector
     */
    public abstract $type$ minAll(VectorMask<$Boxtype$> m);

    /**
     * Returns the maximum lane element of this vector.
     * <p>
     * This is an associative vector reduction operation where the operation
     * {@code (a, b) -> Math.max(a, b)} is applied to lane elements,
     * and the identity value is
#if[FP]
     * {@link $Boxtype$#NEGATIVE_INFINITY}.
#else[FP]
     * {@link $Boxtype$#MIN_VALUE}.
#end[FP]
     *
     * @return the maximum lane element of this vector
     */
    public abstract $type$ maxAll();

    /**
     * Returns the maximum lane element of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * This is an associative vector reduction operation where the operation
     * {@code (a, b) -> Math.max(a, b)} is applied to lane elements,
     * and the identity value is
#if[FP]
     * {@link $Boxtype$#NEGATIVE_INFINITY}.
#else[FP]
     * {@link $Boxtype$#MIN_VALUE}.
#end[FP]
     *
     * @param m the mask controlling lane selection
     * @return the maximum lane element of this vector
     */
    public abstract $type$ maxAll(VectorMask<$Boxtype$> m);

#if[BITWISE]
    /**
     * Logically ORs all lane elements of this vector.
     * <p>
     * This is an associative vector reduction operation where the logical OR
     * operation ({@code |}) is applied to lane elements,
     * and the identity value is {@code 0}.
     *
     * @return the logical OR all the lane elements of this vector
     */
    public abstract $type$ orAll();

    /**
     * Logically ORs all lane elements of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * This is an associative vector reduction operation where the logical OR
     * operation ({@code |}) is applied to lane elements,
     * and the identity value is {@code 0}.
     *
     * @param m the mask controlling lane selection
     * @return the logical OR all the lane elements of this vector
     */
    public abstract $type$ orAll(VectorMask<$Boxtype$> m);

    /**
     * Logically ANDs all lane elements of this vector.
     * <p>
     * This is an associative vector reduction operation where the logical AND
     * operation ({@code |}) is applied to lane elements,
     * and the identity value is {@code -1}.
     *
     * @return the logical AND all the lane elements of this vector
     */
    public abstract $type$ andAll();

    /**
     * Logically ANDs all lane elements of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * This is an associative vector reduction operation where the logical AND
     * operation ({@code |}) is applied to lane elements,
     * and the identity value is {@code -1}.
     *
     * @param m the mask controlling lane selection
     * @return the logical AND all the lane elements of this vector
     */
    public abstract $type$ andAll(VectorMask<$Boxtype$> m);

    /**
     * Logically XORs all lane elements of this vector.
     * <p>
     * This is an associative vector reduction operation where the logical XOR
     * operation ({@code ^}) is applied to lane elements,
     * and the identity value is {@code 0}.
     *
     * @return the logical XOR all the lane elements of this vector
     */
    public abstract $type$ xorAll();

    /**
     * Logically XORs all lane elements of this vector, selecting lane elements
     * controlled by a mask.
     * <p>
     * This is an associative vector reduction operation where the logical XOR
     * operation ({@code ^}) is applied to lane elements,
     * and the identity value is {@code 0}.
     *
     * @param m the mask controlling lane selection
     * @return the logical XOR all the lane elements of this vector
     */
    public abstract $type$ xorAll(VectorMask<$Boxtype$> m);
#end[BITWISE]

    // Type specific accessors

    /**
     * Gets the lane element at lane index {@code i}
     *
     * @param i the lane index
     * @return the lane element at lane index {@code i}
     * @throws IllegalArgumentException if the index is is out of range
     * ({@code < 0 || >= length()})
     */
    public abstract $type$ get(int i);

    /**
     * Replaces the lane element of this vector at lane index {@code i} with
     * value {@code e}.
     * <p>
     * This is a cross-lane operation and behaves as if it returns the result
     * of blending this vector with an input vector that is the result of
     * broadcasting {@code e} and a mask that has only one lane set at lane
     * index {@code i}.
     *
     * @param i the lane index of the lane element to be replaced
     * @param e the value to be placed
     * @return the result of replacing the lane element of this vector at lane
     * index {@code i} with value {@code e}.
     * @throws IllegalArgumentException if the index is is out of range
     * ({@code < 0 || >= length()})
     */
    public abstract $abstractvectortype$ with(int i, $type$ e);

    // Type specific extractors

    /**
     * Returns an array containing the lane elements of this vector.
     * <p>
     * This method behaves as if it {@link #intoArray($type$[], int)} stores}
     * this vector into an allocated array and returns the array as follows:
     * <pre>{@code
     *   $type$[] a = new $type$[this.length()];
     *   this.intoArray(a, 0);
     *   return a;
     * }</pre>
     *
     * @return an array containing the the lane elements of this vector
     */
    @ForceInline
    public final $type$[] toArray() {
        $type$[] a = new $type$[species().length()];
        intoArray(a, 0);
        return a;
    }

    /**
     * Stores this vector into an array starting at offset.
     * <p>
     * For each vector lane, where {@code N} is the vector lane index,
     * the lane element at index {@code N} is stored into the array at index
     * {@code i + N}.
     *
     * @param a the array
     * @param i the offset into the array
     * @throws IndexOutOfBoundsException if {@code i < 0}, or
     * {@code i > a.length - this.length()}
     */
    public abstract void intoArray($type$[] a, int i);

    /**
     * Stores this vector into an array starting at offset and using a mask.
     * <p>
     * For each vector lane, where {@code N} is the vector lane index,
     * if the mask lane at index {@code N} is set then the lane element at
     * index {@code N} is stored into the array index {@code i + N}.
     *
     * @param a the array
     * @param i the offset into the array
     * @param m the mask
     * @throws IndexOutOfBoundsException if {@code i < 0}, or
     * for any vector lane index {@code N} where the mask at lane {@code N}
     * is set {@code i >= a.length - N}
     */
    public abstract void intoArray($type$[] a, int i, VectorMask<$Boxtype$> m);

    /**
     * Stores this vector into an array using indexes obtained from an index
     * map.
     * <p>
     * For each vector lane, where {@code N} is the vector lane index, the
     * lane element at index {@code N} is stored into the array at index
     * {@code i + indexMap[j + N]}.
     *
     * @param a the array
     * @param i the offset into the array, may be negative if relative
     * indexes in the index map compensate to produce a value within the
     * array bounds
     * @param indexMap the index map
     * @param j the offset into the index map
     * @throws IndexOutOfBoundsException if {@code j < 0}, or
     * {@code j > indexMap.length - this.length()},
     * or for any vector lane index {@code N} the result of
     * {@code i + indexMap[j + N]} is {@code < 0} or {@code >= a.length}
     */
#if[byteOrShort]
    public void intoArray($type$[] a, int i, int[] indexMap, int j) {
        forEach((n, e) -> a[i + indexMap[j + n]] = e);
    }
#else[byteOrShort]
    public abstract void intoArray($type$[] a, int i, int[] indexMap, int j);
#end[byteOrShort]

    /**
     * Stores this vector into an array using indexes obtained from an index
     * map and using a mask.
     * <p>
     * For each vector lane, where {@code N} is the vector lane index,
     * if the mask lane at index {@code N} is set then the lane element at
     * index {@code N} is stored into the array at index
     * {@code i + indexMap[j + N]}.
     *
     * @param a the array
     * @param i the offset into the array, may be negative if relative
     * indexes in the index map compensate to produce a value within the
     * array bounds
     * @param m the mask
     * @param indexMap the index map
     * @param j the offset into the index map
     * @throws IndexOutOfBoundsException if {@code j < 0}, or
     * {@code j > indexMap.length - this.length()},
     * or for any vector lane index {@code N} where the mask at lane
     * {@code N} is set the result of {@code i + indexMap[j + N]} is
     * {@code < 0} or {@code >= a.length}
     */
#if[byteOrShort]
    public void intoArray($type$[] a, int i, VectorMask<$Boxtype$> m, int[] indexMap, int j) {
        forEach(m, (n, e) -> a[i + indexMap[j + n]] = e);
    }
#else[byteOrShort]
    public abstract void intoArray($type$[] a, int i, VectorMask<$Boxtype$> m, int[] indexMap, int j);
#end[byteOrShort]
    // Species

    @Override
    public abstract VectorSpecies<$Boxtype$> species();

    /**
     * Class representing {@link $abstractvectortype$}'s of the same {@link VectorShape VectorShape}.
     */
    static final class $Type$Species extends AbstractSpecies<$Boxtype$> {
        final Function<$type$[], $Type$Vector> vectorFactory;

        private $Type$Species(VectorShape shape,
                          Class<?> boxType,
                          Class<?> maskType,
                          Function<$type$[], $Type$Vector> vectorFactory,
                          Function<boolean[], VectorMask<$Boxtype$>> maskFactory,
                          Function<IntUnaryOperator, VectorShuffle<$Boxtype$>> shuffleFromArrayFactory,
                          fShuffleFromArray<$Boxtype$> shuffleFromOpFactory) {
            super(shape, $type$.class, $Boxtype$.SIZE, boxType, maskType, maskFactory,
                  shuffleFromArrayFactory, shuffleFromOpFactory);
            this.vectorFactory = vectorFactory;
        }

        interface FOp {
            $type$ apply(int i);
        }

        $Type$Vector op(FOp f) {
            $type$[] res = new $type$[length()];
            for (int i = 0; i < length(); i++) {
                res[i] = f.apply(i);
            }
            return vectorFactory.apply(res);
        }

        $Type$Vector op(VectorMask<$Boxtype$> o, FOp f) {
            $type$[] res = new $type$[length()];
            boolean[] mbits = ((AbstractMask<$Boxtype$>)o).getBits();
            for (int i = 0; i < length(); i++) {
                if (mbits[i]) {
                    res[i] = f.apply(i);
                }
            }
            return vectorFactory.apply(res);
        }
    }

    /**
     * Finds the preferred species for an element type of {@code $type$}.
     * <p>
     * A preferred species is a species chosen by the platform that has a
     * shape of maximal bit size.  A preferred species for different element
     * types will have the same shape, and therefore vectors, masks, and
     * shuffles created from such species will be shape compatible.
     *
     * @return the preferred species for an element type of {@code $type$}
     */
    private static $Type$Species preferredSpecies() {
        return ($Type$Species) VectorSpecies.ofPreferred($type$.class);
    }

    /**
     * Finds a species for an element type of {@code $type$} and shape.
     *
     * @param s the shape
     * @return a species for an element type of {@code $type$} and shape
     * @throws IllegalArgumentException if no such species exists for the shape
     */
    static $Type$Species species(VectorShape s) {
        Objects.requireNonNull(s);
        switch (s) {
            case S_64_BIT: return ($Type$Species) SPECIES_64;
            case S_128_BIT: return ($Type$Species) SPECIES_128;
            case S_256_BIT: return ($Type$Species) SPECIES_256;
            case S_512_BIT: return ($Type$Species) SPECIES_512;
            case S_Max_BIT: return ($Type$Species) SPECIES_MAX;
            default: throw new IllegalArgumentException("Bad shape: " + s);
        }
    }

    /** Species representing {@link $Type$Vector}s of {@link VectorShape#S_64_BIT VectorShape.S_64_BIT}. */
    public static final VectorSpecies<$Boxtype$> SPECIES_64 = new $Type$Species(VectorShape.S_64_BIT, $Type$64Vector.class, $Type$64Vector.$Type$64Mask.class,
                                                                     $Type$64Vector::new, $Type$64Vector.$Type$64Mask::new,
                                                                     $Type$64Vector.$Type$64Shuffle::new, $Type$64Vector.$Type$64Shuffle::new);

    /** Species representing {@link $Type$Vector}s of {@link VectorShape#S_128_BIT VectorShape.S_128_BIT}. */
    public static final VectorSpecies<$Boxtype$> SPECIES_128 = new $Type$Species(VectorShape.S_128_BIT, $Type$128Vector.class, $Type$128Vector.$Type$128Mask.class,
                                                                      $Type$128Vector::new, $Type$128Vector.$Type$128Mask::new,
                                                                      $Type$128Vector.$Type$128Shuffle::new, $Type$128Vector.$Type$128Shuffle::new);

    /** Species representing {@link $Type$Vector}s of {@link VectorShape#S_256_BIT VectorShape.S_256_BIT}. */
    public static final VectorSpecies<$Boxtype$> SPECIES_256 = new $Type$Species(VectorShape.S_256_BIT, $Type$256Vector.class, $Type$256Vector.$Type$256Mask.class,
                                                                      $Type$256Vector::new, $Type$256Vector.$Type$256Mask::new,
                                                                      $Type$256Vector.$Type$256Shuffle::new, $Type$256Vector.$Type$256Shuffle::new);

    /** Species representing {@link $Type$Vector}s of {@link VectorShape#S_512_BIT VectorShape.S_512_BIT}. */
    public static final VectorSpecies<$Boxtype$> SPECIES_512 = new $Type$Species(VectorShape.S_512_BIT, $Type$512Vector.class, $Type$512Vector.$Type$512Mask.class,
                                                                      $Type$512Vector::new, $Type$512Vector.$Type$512Mask::new,
                                                                      $Type$512Vector.$Type$512Shuffle::new, $Type$512Vector.$Type$512Shuffle::new);

    /** Species representing {@link $Type$Vector}s of {@link VectorShape#S_Max_BIT VectorShape.S_Max_BIT}. */
    public static final VectorSpecies<$Boxtype$> SPECIES_MAX = new $Type$Species(VectorShape.S_Max_BIT, $Type$MaxVector.class, $Type$MaxVector.$Type$MaxMask.class,
                                                                      $Type$MaxVector::new, $Type$MaxVector.$Type$MaxMask::new,
                                                                      $Type$MaxVector.$Type$MaxShuffle::new, $Type$MaxVector.$Type$MaxShuffle::new);

    /**
     * Preferred species for {@link $Type$Vector}s.
     * A preferred species is a species of maximal bit size for the platform.
     */
    public static final VectorSpecies<$Boxtype$> SPECIES_PREFERRED = (VectorSpecies<$Boxtype$>) preferredSpecies();
}