1 /*
   2  * Copyright (c) 2017, 2020, Oracle and/or its affiliates. All rights reserved.
   3  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
   4  *
   5  * This code is free software; you can redistribute it and/or modify it
   6  * under the terms of the GNU General Public License version 2 only, as
   7  * published by the Free Software Foundation.  Oracle designates this
   8  * particular file as subject to the "Classpath" exception as provided
   9  * by Oracle in the LICENSE file that accompanied this code.
  10  *
  11  * This code is distributed in the hope that it will be useful, but WITHOUT
  12  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  13  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  14  * version 2 for more details (a copy is included in the LICENSE file that
  15  * accompanied this code).
  16  *
  17  * You should have received a copy of the GNU General Public License version
  18  * 2 along with this work; if not, write to the Free Software Foundation,
  19  * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
  20  *
  21  * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
  22  * or visit www.oracle.com if you need additional information or have any
  23  * questions.
  24  */
  25 package jdk.incubator.vector;
  26 
  27 import java.nio.ByteBuffer;
  28 import java.nio.ByteOrder;
  29 import java.util.Arrays;
  30 
  31 /**
  32  * A
  33  *
  34  * <!-- The following paragraphs are shared verbatim
  35  *   -- between Vector.java and package-info.java -->
  36  * sequence of a fixed number of <em>lanes</em>,
  37  * all of some fixed
  38  * {@linkplain Vector#elementType() <em>element type</em>}
  39  * such as {@code byte}, {@code long}, or {@code float}.
  40  * Each lane contains an independent value of the element type.
  41  * Operations on vectors are typically
  42  * <a href="Vector.html#lane-wise"><em>lane-wise</em></a>,
  43  * distributing some scalar operator (such as
  44  * {@linkplain Vector#add(Vector) addition})
  45  * across the lanes of the participating vectors,
  46  * usually generating a vector result whose lanes contain the various
  47  * scalar results.  When run on a supporting platform, lane-wise
  48  * operations can be executed in parallel by the hardware.  This style
  49  * of parallelism is called <em>Single Instruction Multiple Data</em>
  50  * (SIMD) parallelism.
  51  *
  52  * <p> In the SIMD style of programming, most of the operations within
  53  * a vector lane are unconditional, but the effect of conditional
  54  * execution may be achieved using
  55  * <a href="Vector.html#masking"><em>masked operations</em></a>
  56  * such as {@link Vector#blend(Vector,VectorMask) blend()},
  57  * under the control of an associated {@link VectorMask}.
  58  * Data motion other than strictly lane-wise flow is achieved using
  59  * <a href="Vector.html#cross-lane"><em>cross-lane</em></a>
  60  * operations, often under the control of an associated
  61  * {@link VectorShuffle}.
  62  * Lane data and/or whole vectors can be reformatted using various
  63  * kinds of lane-wise
  64  * {@linkplain Vector#convert(VectorOperators.Conversion,int) conversions},
  65  * and byte-wise reformatting
  66  * {@linkplain Vector#reinterpretShape(VectorSpecies,int) reinterpretations},
  67  * often under the control of a reflective {@link VectorSpecies}
  68  * object which selects an alternative vector format different
  69  * from that of the input vector.
  70  *
  71  * <p> {@code Vector<E>} declares a set of vector operations (methods)
  72  * that are common to all element types.  These common operations
  73  * include generic access to lane values, data selection and movement,
  74  * reformatting, and certain arithmetic and logical operations (such as addition
  75  * or comparison) that are common to all primitive types.
  76  *
  77  * <p> <a href="Vector.html#subtypes">Public subtypes of {@code Vector}</a>
  78  * correspond to specific
  79  * element types.  These declare further operations that are specific
  80  * to that element type, including unboxed access to lane values,
  81  * bitwise operations on values of integral element types, or
  82  * transcendental operations on values of floating point element
  83  * types.
  84  *
  85  * <p> Some lane-wise operations, such as the {@code add} operator, are defined as
  86  * a full-service named operation, where a corresponding method on {@code Vector}
  87  * comes in masked and unmasked overloadings, and (in subclasses) also comes in
  88  * covariant overrides (returning the subclass) and additional scalar-broadcast
  89  * overloadings (both masked and unmasked).
  90  *
  91  * Other lane-wise operations, such as the {@code min} operator, are defined as a
  92  * partially serviced (not a full-service) named operation, where a corresponding
  93  * method on {@code Vector} and/or a subclass provide some but all possible
  94  * overloadings and overrides (commonly the unmasked varient with scalar-broadcast
  95  * overloadings).
  96  *
  97  * Finally, all lane-wise operations (those named as previously described,
  98  * or otherwise unnamed method-wise) have a corresponding
  99  * {@link VectorOperators.Operator operator token}
 100  * declared as a static constant on {@link VectorOperators}.
 101  * Each operator token defines a symbolic Java expression for the operation,
 102  * such as {@code a + b} for the
 103  * {@link VectorOperators#ADD ADD} operator token.
 104  * General lane-wise operation-token accepting methods, such as for a
 105  * {@linkplain Vector#lanewise(VectorOperators.Unary) unary lane-wise}
 106  * operation, are provided on {@code Vector} and come in the same variants as
 107  * a full-service named operation.
 108  *
 109  * <p>This package contains a public subtype of {@link Vector}
 110  * corresponding to each supported element type:
 111  * {@link ByteVector}, {@link ShortVector},
 112  * {@link IntVector}, {@link LongVector},
 113  * {@link FloatVector}, and {@link DoubleVector}.
 114  *
 115  * <!-- The preceding paragraphs are shared verbatim
 116  *   -- between Vector.java and package-info.java -->
 117  *
 118  * <p><a id="ETYPE"></a> The {@linkplain #elementType element type} of a vector,
 119  * referred to as {@code ETYPE}, is one of the primitive types
 120  * {@code byte}, {@code short}, {@code int}, {@code long}, {@code
 121  * float}, or {@code double}.
 122  *
 123  * <p> The type {@code E} in {@code Vector<E>} is the <em>boxed</em> version
 124  * of {@code ETYPE}. For example, in the type {@code Vector<Integer>}, the {@code E}
 125  * parameter is {@code Integer} and the {@code ETYPE} is {@code int}.  In such a
 126  * vector, each lane carries a primitive {@code int} value.  This pattern continues
 127  * for the other primitive types as well. (See also sections {@jls 5.1.7} and
 128  * {@jls 5.1.8} of the <cite>The Java Language Specification</cite>.)
 129  *
 130  * <p><a id="VLENGTH"></a> The {@linkplain #length() length} of a vector
 131  * is the lane count, the number of lanes it contains.
 132  *
 133  * This number is also called {@code VLENGTH} when the context makes
 134  * clear which vector it belongs to.  Each vector has its own fixed
 135  * {@code VLENGTH} but different instances of vectors may have
 136  * different lengths.  {@code VLENGTH} is an important number, because
 137  * it estimates the SIMD performance gain of a single vector operation
 138  * as compared to scalar execution of the {@code VLENGTH} scalar
 139  * operators which underly the vector operation.
 140  *
 141  * <h2><a id="species"></a>Shapes and species</h2>
 142  *
 143  * The information capacity of a vector is determined by its
 144  * {@linkplain #shape() <em>vector shape</em>}, also called its
 145  * {@code VSHAPE}.  Each possible {@code VSHAPE} is represented by
 146  * a member of the {@link VectorShape} enumeration, and represents
 147  * an implementation format shared in common by all vectors of
 148  * that shape.  Thus, the {@linkplain #bitSize() size in bits} of
 149  * of a vector is determined by appealing to its vector shape.
 150  *
 151  * <p> Some Java platforms give special support to only one shape,
 152  * while others support several.  A typical platform is not likely
 153  * to support all the shapes described by this API.  For this reason,
 154  * most vector operations work on a single input shape and
 155  * produce the same shape on output.  Operations which change
 156  * shape are clearly documented as such <em>shape-changing</em>,
 157  * while the majority of operations are <em>shape-invariant</em>,
 158  * to avoid disadvantaging platforms which support only one shape.
 159  * There are queries to discover, for the current Java platform,
 160  * the {@linkplain VectorShape#preferredShape() preferred shape}
 161  * for general SIMD computation, or the
 162  * {@linkplain VectorShape#largestShapeFor(Class) largest
 163  * available shape} for any given lane type.  To be portable,
 164  * code using this API should start by querying a supported
 165  * shape, and then process all data with shape-invariant
 166  * operations, within the selected shape.
 167  *
 168  * <p> Each unique combination of element type and vector shape
 169  * determines a unique
 170  * {@linkplain #species() <em>vector species</em>}.
 171  * A vector species is represented by a fixed instance of
 172  * {@link VectorSpecies VectorSpecies&lt;E&gt;}
 173  * shared in common by all vectors of the same shape and
 174  * {@code ETYPE}.
 175  *
 176  * <p> Unless otherwise documented, lane-wise vector operations
 177  * require that all vector inputs have exactly the same {@code VSHAPE}
 178  * and {@code VLENGTH}, which is to say that they must have exactly
 179  * the same species.  This allows corresponding lanes to be paired
 180  * unambiguously.  The {@link #check(VectorSpecies) check()} method
 181  * provides an easy way to perform this check explicitly.
 182  *
 183  * <p> Vector shape, {@code VLENGTH}, and {@code ETYPE} are all
 184  * mutually constrained, so that {@code VLENGTH} times the
 185  * {@linkplain #elementSize() bit-size of each lane}
 186  * must always match the bit-size of the vector's shape.
 187  *
 188  * Thus, {@linkplain #reinterpretShape(VectorSpecies,int) reinterpreting} a
 189  * vector may double its length if and only if it either halves the lane size,
 190  * or else changes the shape.  Likewise, reinterpreting a vector may double the
 191  * lane size if and only if it either halves the length, or else changes the
 192  * shape of the vector.
 193  *
 194  * <h2><a id="subtypes"></a>Vector subtypes</h2>
 195  *
 196  * Vector declares a set of vector operations (methods) that are common to all
 197  * element types (such as addition).  Sub-classes of Vector with a concrete
 198  * element type declare further operations that are specific to that
 199  * element type (such as access to element values in lanes, logical operations
 200  * on values of integral elements types, or transcendental operations on values
 201  * of floating point element types).
 202  * There are six abstract sub-classes of Vector corresponding to the supported set
 203  * of element types, {@link ByteVector}, {@link ShortVector},
 204  * {@link IntVector}, {@link LongVector}, {@link FloatVector}, and
 205  * {@link DoubleVector}. Along with type-specific operations these classes
 206  * support creation of vector values (instances of Vector).
 207  * They expose static constants corresponding to the supported species,
 208  * and static methods on these types generally take a species as a parameter.
 209  * For example,
 210  * {@link FloatVector#fromArray(VectorSpecies, float[], int) FloatVector.fromArray}
 211  * creates and returns a float vector of the specified species, with elements
 212  * loaded from the specified float array.
 213  * It is recommended that Species instances be held in {@code static final}
 214  * fields for optimal creation and usage of Vector values by the runtime compiler.
 215  *
 216  * <p> As an example of static constants defined by the typed vector classes,
 217  * constant {@link FloatVector#SPECIES_256 FloatVector.SPECIES_256}
 218  * is the unique species whose lanes are {@code float}s and whose
 219  * vector size is 256 bits.  Again, the constant
 220  * {@link FloatVector#SPECIES_PREFERRED} is the species which
 221  * best supports processing of {@code float} vector lanes on
 222  * the currently running Java platform.
 223  *
 224  * <p> As another example, a broadcast scalar value of
 225  * {@code (double)0.5} can be obtained by calling
 226  * {@link DoubleVector#broadcast(VectorSpecies,double)
 227  * DoubleVector.broadcast(dsp, 0.5)}, but the argument {@code dsp} is
 228  * required to select the species (and hence the shape and length) of
 229  * the resulting vector.
 230  *
 231  * <h2><a id="lane-wise"></a>Lane-wise operations</h2>
 232  *
 233  * We use the term <em>lanes</em> when defining operations on
 234  * vectors. The number of lanes in a vector is the number of scalar
 235  * elements it holds. For example, a vector of type {@code float} and
 236  * shape {@code S_256_BIT} has eight lanes, since {@code 32*8=256}.
 237  *
 238  * <p> Most operations on vectors are lane-wise, which means the operation
 239  * is composed of an underlying scalar operator, which is repeated for
 240  * each distinct lane of the input vector.  If there are additional
 241  * vector arguments of the same type, their lanes are aligned with the
 242  * lanes of the first input vector.  (They must all have a common
 243  * {@code VLENGTH}.)  For most lane-wise operations, the output resulting
 244  * from a lane-wise operation will have a {@code VLENGTH} which is equal to
 245  * the {@code VLENGTH} of the input(s) to the operation.  Thus, such lane-wise
 246  * operations are <em>length-invariant</em>, in their basic definitions.
 247  *
 248  * <p> The principle of length-invariance is combined with another
 249  * basic principle, that most length-invariant lane-wise operations are also
 250  * <em>shape-invariant</em>, meaning that the inputs and the output of
 251  * a lane-wise operation will have a common {@code VSHAPE}.  When the
 252  * principles conflict, because a logical result (with an invariant
 253  * {@code VLENGTH}), does not fit into the invariant {@code VSHAPE},
 254  * the resulting expansions and contractions are handled explicitly
 255  * with
 256  * <a href="Vector.html#expansion">special conventions</a>.
 257  *
 258  * <p> Vector operations can be grouped into various categories and
 259  * their behavior can be generally specified in terms of underlying
 260  * scalar operators.  In the examples below, {@code ETYPE} is the
 261  * element type of the operation (such as {@code int.class}) and
 262  * {@code EVector} is the corresponding concrete vector type (such as
 263  * {@code IntVector.class}).
 264  *
 265  * <ul>
 266  * <li>
 267  * A <em>lane-wise unary</em> operation, such as
 268  * {@code w = v0.}{@link Vector#neg() neg}{@code ()},
 269  * takes one input vector,
 270  * distributing a unary scalar operator across the lanes,
 271  * and produces a result vector of the same type and shape.
 272  *
 273  * For each lane of the input vector {@code a},
 274  * the underlying scalar operator is applied to the lane value.
 275  * The result is placed into the vector result in the same lane.
 276  * The following pseudocode illustrates the behavior of this operation
 277  * category:
 278  *
 279  * <pre>{@code
 280  * ETYPE scalar_unary_op(ETYPE s);
 281  * EVector a = ...;
 282  * VectorSpecies<E> species = a.species();
 283  * ETYPE[] ar = new ETYPE[a.length()];
 284  * for (int i = 0; i < ar.length; i++) {
 285  *     ar[i] = scalar_unary_op(a.lane(i));
 286  * }
 287  * EVector r = EVector.fromArray(species, ar, 0);
 288  * }</pre>
 289  *
 290  * <li>
 291  * A <em>lane-wise binary</em> operation, such as
 292  * {@code w = v0.}{@link Vector#add(Vector) add}{@code (v1)},
 293  * takes two input vectors,
 294  * distributing a binary scalar operator across the lanes,
 295  * and produces a result vector of the same type and shape.
 296  *
 297  * For each lane of the two input vectors {@code a} and {@code b},
 298  * the underlying scalar operator is applied to the lane values.
 299  * The result is placed into the vector result in the same lane.
 300  * The following pseudocode illustrates the behavior of this operation
 301  * category:
 302  *
 303  * <pre>{@code
 304  * ETYPE scalar_binary_op(ETYPE s, ETYPE t);
 305  * EVector a = ...;
 306  * VectorSpecies<E> species = a.species();
 307  * EVector b = ...;
 308  * b.check(species);  // must have same species
 309  * ETYPE[] ar = new ETYPE[a.length()];
 310  * for (int i = 0; i < ar.length; i++) {
 311  *     ar[i] = scalar_binary_op(a.lane(i), b.lane(i));
 312  * }
 313  * EVector r = EVector.fromArray(species, ar, 0);
 314  * }</pre>
 315  * </li>
 316  *
 317  * <li>
 318  * Generalizing from unary and binary operations,
 319  * a <em>lane-wise n-ary</em> operation takes {@code N} input vectors {@code v[j]},
 320  * distributing an n-ary scalar operator across the lanes,
 321  * and produces a result vector of the same type and shape.
 322  * Except for a few ternary operations, such as
 323  * {@code w = v0.}{@link FloatVector#fma(Vector,Vector) fma}{@code (v1,v2)},
 324  * this API has no support for
 325  * lane-wise n-ary operations.
 326  *
 327  * For each lane of all of the input vectors {@code v[j]},
 328  * the underlying scalar operator is applied to the lane values.
 329  * The result is placed into the vector result in the same lane.
 330  * The following pseudocode illustrates the behavior of this operation
 331  * category:
 332  *
 333  * <pre>{@code
 334  * ETYPE scalar_nary_op(ETYPE... args);
 335  * EVector[] v = ...;
 336  * int N = v.length;
 337  * VectorSpecies<E> species = v[0].species();
 338  * for (EVector arg : v) {
 339  *     arg.check(species);  // all must have same species
 340  * }
 341  * ETYPE[] ar = new ETYPE[a.length()];
 342  * for (int i = 0; i < ar.length; i++) {
 343  *     ETYPE[] args = new ETYPE[N];
 344  *     for (int j = 0; j < N; j++) {
 345  *         args[j] = v[j].lane(i);
 346  *     }
 347  *     ar[i] = scalar_nary_op(args);
 348  * }
 349  * EVector r = EVector.fromArray(species, ar, 0);
 350  * }</pre>
 351  * </li>
 352  *
 353  * <li>
 354  * A <em>lane-wise conversion</em> operation, such as
 355  * {@code w0 = v0.}{@link
 356  * Vector#convert(VectorOperators.Conversion,int)
 357  * convert}{@code (VectorOperators.I2D, 0)},
 358  * takes one input vector,
 359  * distributing a unary scalar conversion operator across the lanes,
 360  * and produces a logical result of the converted values.  The logical
 361  * result (or at least a part of it) is presented in a vector of the
 362  * same shape as the input vector.
 363  *
 364  * <p> Unlike other lane-wise operations, conversions can change lane
 365  * type, from the input (domain) type to the output (range) type.  The
 366  * lane size may change along with the type.  In order to manage the
 367  * size changes, lane-wise conversion methods can product <em>partial
 368  * results</em>, under the control of a {@code part} parameter, which
 369  * is <a href="Vector.html#expansion">explained elsewhere</a>.
 370  * (Following the example above, the second group of converted lane
 371  * values could be obtained as
 372  * {@code w1 = v0.convert(VectorOperators.I2D, 1)}.)
 373  *
 374  * <p> The following pseudocode illustrates the behavior of this
 375  * operation category in the specific example of a conversion from
 376  * {@code int} to {@code double}, retaining either lower or upper
 377  * lanes (depending on {@code part}) to maintain shape-invariance:
 378  *
 379  * <pre>{@code
 380  * IntVector a = ...;
 381  * int VLENGTH = a.length();
 382  * int part = ...;  // 0 or 1
 383  * VectorShape VSHAPE = a.shape();
 384  * double[] arlogical = new double[VLENGTH];
 385  * for (int i = 0; i < limit; i++) {
 386  *     int e = a.lane(i);
 387  *     arlogical[i] = (double) e;
 388  * }
 389  * VectorSpecies<Double> rs = VSHAPE.withLanes(double.class);
 390  * int M = Double.BITS / Integer.BITS;  // expansion factor
 391  * int offset = part * (VLENGTH / M);
 392  * DoubleVector r = DoubleVector.fromArray(rs, arlogical, offset);
 393  * assert r.length() == VLENGTH / M;
 394  * }</pre>
 395  * </li>
 396  *
 397  * <li>
 398  * A <em>cross-lane reduction</em> operation, such as
 399  * {@code e = v0.}{@link
 400  * IntVector#reduceLanes(VectorOperators.Associative)
 401  * reduceLanes}{@code (VectorOperators.ADD)},
 402  * operates on all
 403  * the lane elements of an input vector.
 404  * An accumulation function is applied to all the
 405  * lane elements to produce a scalar result.
 406  * If the reduction operation is associative then the result may be accumulated
 407  * by operating on the lane elements in any order using a specified associative
 408  * scalar binary operation and identity value.  Otherwise, the reduction
 409  * operation specifies the order of accumulation.
 410  * The following pseudocode illustrates the behavior of this operation category
 411  * if it is associative:
 412  * <pre>{@code
 413  * ETYPE assoc_scalar_binary_op(ETYPE s, ETYPE t);
 414  * EVector a = ...;
 415  * ETYPE r = <identity value>;
 416  * for (int i = 0; i < a.length(); i++) {
 417  *     r = assoc_scalar_binary_op(r, a.lane(i));
 418  * }
 419  * }</pre>
 420  * </li>
 421  *
 422  * <li>
 423  * A <em>cross-lane movement</em> operation, such as
 424  * {@code w = v0.}{@link
 425  * Vector#rearrange(VectorShuffle) rearrange}{@code (shuffle)}
 426  * operates on all
 427  * the lane elements of an input vector and moves them
 428  * in a data-dependent manner into <em>different lanes</em>
 429  * in an output vector.
 430  * The movement is steered by an auxiliary datum, such as
 431  * a {@link VectorShuffle} or a scalar index defining the
 432  * origin of the movement.
 433  * The following pseudocode illustrates the behavior of this
 434  * operation category, in the case of a shuffle:
 435  * <pre>{@code
 436  * EVector a = ...;
 437  * Shuffle<E> s = ...;
 438  * ETYPE[] ar = new ETYPE[a.length()];
 439  * for (int i = 0; i < ar.length; i++) {
 440  *     int source = s.laneSource(i);
 441  *     ar[i] = a.lane(source);
 442  * }
 443  * EVector r = EVector.fromArray(a.species(), ar, 0);
 444  * }</pre>
 445  * </li>
 446  *
 447  * <li>
 448  * A <em>masked operation</em> is one which is a variation on one of the
 449  * previous operations (either lane-wise or cross-lane), where
 450  * the operation takes an extra trailing {@link VectorMask} argument.
 451  * In lanes the mask is set, the operation behaves as if the mask
 452  * argument were absent, but in lanes where the mask is unset, the
 453  * underlying scalar operation is suppressed.
 454  * Masked operations are explained in
 455  * <a href="Vector.html#masking">greater detail elsewhere</a>.
 456  * </li>
 457  *
 458  * <li>
 459  * A very special case of a masked lane-wise binary operation is a
 460  * {@linkplain #blend(Vector,VectorMask) blend}, which operates
 461  * lane-wise on two input vectors {@code a} and {@code b}, selecting lane
 462  * values from one input or the other depending on a mask {@code m}.
 463  * In lanes where {@code m} is set, the corresponding value from
 464  * {@code b} is selected into the result; otherwise the value from
 465  * {@code a} is selected.  Thus, a blend acts as a vectorized version
 466  * of Java's ternary selection expression {@code m?b:a}:
 467  * <pre>{@code
 468  * ETYPE[] ar = new ETYPE[a.length()];
 469  * for (int i = 0; i < ar.length; i++) {
 470  *     boolean isSet = m.laneIsSet(i);
 471  *     ar[i] = isSet ? b.lane(i) : a.lane(i);
 472  * }
 473  * EVector r = EVector.fromArray(species, ar, 0);
 474  * }</pre>
 475  * </li>
 476  *
 477  * <li>
 478  * A <em>lane-wise binary test</em> operation, such as
 479  * {@code m = v0.}{@link Vector#lt(Vector) lt}{@code (v1)},
 480  * takes two input vectors,
 481  * distributing a binary scalar comparison across the lanes,
 482  * and produces, not a vector of booleans, but rather a
 483  * {@linkplain VectorMask vector mask}.
 484  *
 485  * For each lane of the two input vectors {@code a} and {@code b},
 486  * the underlying scalar comparison operator is applied to the lane values.
 487  * The resulting boolean is placed into the vector mask result in the same lane.
 488  * The following pseudocode illustrates the behavior of this operation
 489  * category:
 490  * <pre>{@code
 491  * boolean scalar_binary_test_op(ETYPE s, ETYPE t);
 492  * EVector a = ...;
 493  * VectorSpecies<E> species = a.species();
 494  * EVector b = ...;
 495  * b.check(species);  // must have same species
 496  * boolean[] mr = new boolean[a.length()];
 497  * for (int i = 0; i < mr.length; i++) {
 498  *     mr[i] = scalar_binary_test_op(a.lane(i), b.lane(i));
 499  * }
 500  * VectorMask<E> m = VectorMask.fromArray(species, mr, 0);
 501  * }</pre>
 502  * </li>
 503  *
 504  * <li>
 505  * Similarly to a binary comparison, a <em>lane-wise unary test</em>
 506  * operation, such as
 507  * {@code m = v0.}{@link Vector#test(VectorOperators.Test)
 508  * test}{@code (IS_FINITE)},
 509  * takes one input vector, distributing a scalar predicate
 510  * (a test function) across the lanes, and produces a
 511  * {@linkplain VectorMask vector mask}.
 512  * </li>
 513  *
 514  * </ul>
 515  *
 516  * <p>
 517  * If a vector operation does not belong to one of the above categories then
 518  * the method documentation explicitly specifies how it processes the lanes of
 519  * input vectors, and where appropriate illustrates the behavior using
 520  * pseudocode.
 521  *
 522  * <p>
 523  * Most lane-wise binary and comparison operations offer convenience
 524  * overloadings which accept a scalar as the second input, in place of a
 525  * vector.  In this case the scalar value is promoted to a vector by
 526  * {@linkplain Vector#broadcast(long) broadcasting it}
 527  * into the same lane structure as the first input.
 528  *
 529  * For example, to multiply all lanes of a {@code double} vector by
 530  * a scalar value {@code 1.1}, the expression {@code v.mul(1.1)} is
 531  * easier to work with than an equivalent expression with an explicit
 532  * broadcast operation, such as {@code v.mul(v.broadcast(1.1))}
 533  * or {@code v.mul(DoubleVector.broadcast(v.species(), 1.1))}.
 534  *
 535  * Unless otherwise specified the scalar variant always behaves as if
 536  * each scalar value is first transformed to a vector of the same
 537  * species as the first vector input, using the appropriate
 538  * {@code broadcast} operation.
 539  *
 540  * <h2><a id="masking"></a>Masked operations</h2>
 541  *
 542  * <p> Many vector operations accept an optional
 543  * {@link VectorMask mask} argument, selecting which lanes participate
 544  * in the underlying scalar operator.  If present, the mask argument
 545  * appears at the end of the method argument list.
 546  *
 547  * <p> Each lane of the mask argument is a boolean which is either in
 548  * the <em>set</em> or <em>unset</em> state.  For lanes where the mask
 549  * argument is unset, the underlying scalar operator is suppressed.
 550  * In this way, masks allow vector operations to emulate scalar
 551  * control flow operations, without losing SIMD parallelism, except
 552  * where the mask lane is unset.
 553  *
 554  * <p> An operation suppressed by a mask will never cause an exception
 555  * or side effect of any sort, even if the underlying scalar operator
 556  * can potentially do so.  For example, an unset lane that seems to
 557  * access an out of bounds array element or divide an integral value
 558  * by zero will simply be ignored.  Values in suppressed lanes never
 559  * participate or appear in the result of the overall operation.
 560  *
 561  * <p> Result lanes corresponding to a suppressed operation will be
 562  * filled with a default value which depends on the specific
 563  * operation, as follows:
 564  *
 565  * <ul>
 566  *
 567  * <li>If the masked operation is a unary, binary, or n-ary arithmetic or
 568  * logical operation, suppressed lanes are filled from the first
 569  * vector operand (i.e., the vector receiving the method call), as if
 570  * by a {@linkplain #blend(Vector,VectorMask) blend}.</li>
 571  *
 572  * <li>If the masked operation is a memory load or a {@code slice()} from
 573  * another vector, suppressed lanes are not loaded, and are filled
 574  * with the default value for the {@code ETYPE}, which in every case
 575  * consists of all zero bits.  An unset lane can never cause an
 576  * exception, even if the hypothetical corresponding memory location
 577  * does not exist (because it is out of an array's index range).</li>
 578  *
 579  * <li>If the operation is a cross-lane operation with an operand
 580  * which supplies lane indexes (of type {@code VectorShuffle} or
 581  * {@code Vector}, suppressed lanes are not computed, and are filled
 582  * with the zero default value.  Normally, invalid lane indexes elicit
 583  * an {@code IndexOutOfBoundsException}, but if a lane is unset, the
 584  * zero value is quietly substituted, regardless of the index.  This
 585  * rule is similar to the previous rule, for masked memory loads.</li>
 586  *
 587  * <li>If the masked operation is a memory store or an {@code unslice()} into
 588  * another vector, suppressed lanes are not stored, and the
 589  * corresponding memory or vector locations (if any) are unchanged.
 590  *
 591  * <p> (Note: Memory effects such as race conditions never occur for
 592  * suppressed lanes.  That is, implementations will not secretly
 593  * re-write the existing value for unset lanes.  In the Java Memory
 594  * Model, reassigning a memory variable to its current value is not a
 595  * no-op; it may quietly undo a racing store from another
 596  * thread.)</p>
 597  * </li>
 598  *
 599  * <li>If the masked operation is a reduction, suppressed lanes are ignored
 600  * in the reduction.  If all lanes are suppressed, a suitable neutral
 601  * value is returned, depending on the specific reduction operation,
 602  * and documented by the masked variant of that method.  (This means
 603  * that users can obtain the neutral value programmatically by
 604  * executing the reduction on a dummy vector with an all-unset mask.)
 605  *
 606  * <li>If the masked operation is a comparison operation, suppressed output
 607  * lanes in the resulting mask are themselves unset, as if the
 608  * suppressed comparison operation returned {@code false} regardless
 609  * of the suppressed input values.  In effect, it is as if the
 610  * comparison operation were performed unmasked, and then the
 611  * result intersected with the controlling mask.</li>
 612  *
 613  * <li>In other cases, such as masked
 614  * <a href="Vector.html#cross-lane"><em>cross-lane movements</em></a>,
 615  * the specific effects of masking are documented by the masked
 616  * variant of the method.
 617  *
 618  * </ul>
 619  *
 620  * <p> As an example, a masked binary operation on two input vectors
 621  * {@code a} and {@code b} suppresses the binary operation for lanes
 622  * where the mask is unset, and retains the original lane value from
 623  * {@code a}.  The following pseudocode illustrates this behavior:
 624  * <pre>{@code
 625  * ETYPE scalar_binary_op(ETYPE s, ETYPE t);
 626  * EVector a = ...;
 627  * VectorSpecies<E> species = a.species();
 628  * EVector b = ...;
 629  * b.check(species);  // must have same species
 630  * VectorMask<E> m = ...;
 631  * m.check(species);  // must have same species
 632  * boolean[] ar = new boolean[a.length()];
 633  * for (int i = 0; i < ar.length; i++) {
 634  *     if (m.laneIsSet(i)) {
 635  *         ar[i] = scalar_binary_op(a.lane(i), b.lane(i));
 636  *     } else {
 637  *         ar[i] = a.lane(i);  // from first input
 638  *     }
 639  * }
 640  * EVector r = EVector.fromArray(species, ar, 0);
 641  * }</pre>
 642  *
 643  * <h2><a id="lane-order"></a>Lane order and byte order</h2>
 644  *
 645  * The number of lane values stored in a given vector is referred to
 646  * as its {@linkplain #length() vector length} or {@code VLENGTH}.
 647  *
 648  * It is useful to consider vector lanes as ordered
 649  * <em>sequentially</em> from first to last, with the first lane
 650  * numbered {@code 0}, the next lane numbered {@code 1}, and so on to
 651  * the last lane numbered {@code VLENGTH-1}.  This is a temporal
 652  * order, where lower-numbered lanes are considered earlier than
 653  * higher-numbered (later) lanes.  This API uses these terms
 654  * in preference to spatial terms such as "left", "right", "high",
 655  * and "low".
 656  *
 657  * <p> Temporal terminology works well for vectors because they
 658  * (usually) represent small fixed-sized segments in a long sequence
 659  * of workload elements, where the workload is conceptually traversed
 660  * in time order from beginning to end.  (This is a mental model: it
 661  * does not exclude multicore divide-and-conquer techniques.)  Thus,
 662  * when a scalar loop is transformed into a vector loop, adjacent
 663  * scalar items (one earlier, one later) in the workload end up as
 664  * adjacent lanes in a single vector (again, one earlier, one later).
 665  * At a vector boundary, the last lane item in the earlier vector is
 666  * adjacent to (and just before) the first lane item in the
 667  * immediately following vector.
 668  *
 669  * <p> Vectors are also sometimes thought of in spatial terms, where
 670  * the first lane is placed at an edge of some virtual paper, and
 671  * subsequent lanes are presented in order next to it.  When using
 672  * spatial terms, all directions are equally plausible: Some vector
 673  * notations present lanes from left to right, and others from right
 674  * to left; still others present from top to bottom or vice versa.
 675  * Using the language of time (before, after, first, last) instead of
 676  * space (left, right, high, low) is often more likely to avoid
 677  * misunderstandings.
 678  *
 679  * <p> As second reason to prefer temporal to spatial language about
 680  * vector lanes is the fact that the terms "left", "right", "high" and
 681  * "low" are widely used to describe the relations between bits in
 682  * scalar values.  The leftmost or highest bit in a given type is
 683  * likely to be a sign bit, while the rightmost or lowest bit is
 684  * likely to be the arithmetically least significant, and so on.
 685  * Applying these terms to vector lanes risks confusion, however,
 686  * because it is relatively rare to find algorithms where, given two
 687  * adjacent vector lanes, one lane is somehow more arithmetically
 688  * significant than its neighbor, and even in those cases, there is no
 689  * general way to know which neighbor is the the more significant.
 690  *
 691  * <p> Putting the terms together, we view the information structure
 692  * of a vector as a temporal sequence of lanes ("first", "next",
 693  * "earlier", "later", "last", etc.)  of bit-strings which are
 694  * internally ordered spatially (either "low" to "high" or "right" to
 695  * "left").  The primitive values in the lanes are decoded from these
 696  * bit-strings, in the usual way.  Most vector operations, like most
 697  * Java scalar operators, treat primitive values as atomic values, but
 698  * some operations reveal the internal bit-string structure.
 699  *
 700  * <p> When a vector is loaded from or stored into memory, the order
 701  * of vector lanes is <em>always consistent </em> with the inherent
 702  * ordering of the memory container.  This is true whether or not
 703  * individual lane elements are subject to "byte swapping" due to
 704  * details of byte order.  Thus, while the scalar lane elements of
 705  * vector might be "byte swapped", the lanes themselves are never
 706  * reordered, except by an explicit method call that performs
 707  * cross-lane reordering.
 708  *
 709  * <p> When vector lane values are stored to Java variables of the
 710  * same type, byte swapping is performed if and only if the
 711  * implementation of the vector hardware requires such swapping.  It
 712  * is therefore unconditional and invisible.
 713  *
 714  * <p> As a useful fiction, this API presents a consistent illusion
 715  * that vector lane bytes are composed into larger lane scalars in
 716  * <em>little endian order</em>.  This means that storing a vector
 717  * into a Java byte array will reveal the successive bytes of the
 718  * vector lane values in little-endian order on all platforms,
 719  * regardless of native memory order, and also regardless of byte
 720  * order (if any) within vector unit registers.
 721  *
 722  * <p> This hypothetical little-endian ordering also appears when a
 723  * {@linkplain #reinterpretShape(VectorSpecies,int) reinterpretation cast} is
 724  * applied in such a way that lane boundaries are discarded and
 725  * redrawn differently, while maintaining vector bits unchanged.  In
 726  * such an operation, two adjacent lanes will contribute bytes to a
 727  * single new lane (or vice versa), and the sequential order of the
 728  * two lanes will determine the arithmetic order of the bytes in the
 729  * single lane.  In this case, the little-endian convention provides
 730  * portable results, so that on all platforms earlier lanes tend to
 731  * contribute lower (rightward) bits, and later lanes tend to
 732  * contribute higher (leftward) bits.  The {@linkplain #reinterpretAsBytes()
 733  * reinterpretation casts} between {@link ByteVector}s and the
 734  * other non-byte vectors use this convention to clarify their
 735  * portable semantics.
 736  *
 737  * <p> The little-endian fiction for relating lane order to per-lane
 738  * byte order is slightly preferable to an equivalent big-endian
 739  * fiction, because some related formulas are much simpler,
 740  * specifically those which renumber bytes after lane structure
 741  * changes.  The earliest byte is invariantly earliest across all lane
 742  * structure changes, but only if little-endian convention are used.
 743  * The root cause of this is that bytes in scalars are numbered from
 744  * the least significant (rightmost) to the most significant
 745  * (leftmost), and almost never vice-versa.  If we habitually numbered
 746  * sign bits as zero (as on some computers) then this API would reach
 747  * for big-endian fictions to create unified addressing of vector
 748  * bytes.
 749  *
 750  * <h2><a id="memory"></a>Memory operations</h2>
 751  *
 752  * As was already mentioned, vectors can be loaded from memory and
 753  * stored back.  An optional mask can control which individual memory
 754  * locations are read from or written to.  The shape of a vector
 755  * determines how much memory it will occupy.
 756  *
 757  * An implementation typically has the property, in the absence of
 758  * masking, that lanes are stored as a dense sequence of back-to-back
 759  * values in memory, the same as a dense (gap-free) series of single
 760  * scalar values in an array of the scalar type.
 761  *
 762  * In such cases memory order corresponds exactly to lane order.  The
 763  * first vector lane value occupies the first position in memory, and so on,
 764  * up to the length of the vector. Further, the memory order of stored
 765  * vector lanes corresponds to increasing index values in a Java array or
 766  * in a {@link java.nio.ByteBuffer}.
 767  *
 768  * <p> Byte order for lane storage is chosen such that the stored
 769  * vector values can be read or written as single primitive values,
 770  * within the array or buffer that holds the vector, producing the
 771  * same values as the lane-wise values within the vector.
 772  * This fact is independent of the convenient fiction that lane values
 773  * inside of vectors are stored in little-endian order.
 774  *
 775  * <p> For example,
 776  * {@link FloatVector#fromArray(VectorSpecies, float[], int)
 777  *        FloatVector.fromArray(fsp,fa,i)}
 778  * creates and returns a float vector of some particular species {@code fsp},
 779  * with elements loaded from some float array {@code fa}.
 780  * The first lane is loaded from {@code fa[i]} and the last lane
 781  * is initialized loaded from {@code fa[i+VL-1]}, where {@code VL}
 782  * is the length of the vector as derived from the species {@code fsp}.
 783  * Then, {@link FloatVector#add(Vector) fv=fv.add(fv2)}
 784  * will produce another float vector of that species {@code fsp},
 785  * given a vector {@code fv2} of the same species {@code fsp}.
 786  * Next, {@link FloatVector#compare(VectorOperators.Comparison,float)
 787  * mnz=fv.compare(NE, 0.0f)} tests whether the result is zero,
 788  * yielding a mask {@code mnz}.  The non-zero lanes (and only those
 789  * lanes) can then be stored back into the original array elements
 790  * using the statement
 791  * {@link FloatVector#intoArray(float[],int,VectorMask) fv.intoArray(fa,i,mnz)}.
 792  *
 793  * <h2><a id="expansion"></a>Expansions, contractions, and partial results</h2>
 794  *
 795  * Since vectors are fixed in size, occasions often arise where the
 796  * logical result of an operation is not the same as the physical size
 797  * of the proposed output vector.  To encourage user code that is as
 798  * portable and predictable as possible, this API has a systematic
 799  * approach to the design of such <em>resizing</em> vector operations.
 800  *
 801  * <p> As a basic principle, lane-wise operations are
 802  * <em>length-invariant</em>, unless clearly marked otherwise.
 803  * Length-invariance simply means that
 804  * if {@code VLENGTH} lanes go into an operation, the same number
 805  * of lanes come out, with nothing discarded and no extra padding.
 806  *
 807  * <p> As a second principle, sometimes in tension with the first,
 808  * lane-wise operations are also <em>shape-invariant</em>, unless
 809  * clearly marked otherwise.
 810  *
 811  * Shape-invariance means that {@code VSHAPE} is constant for typical
 812  * computations.  Keeping the same shape throughout a computation
 813  * helps ensure that scarce vector resources are efficiently used.
 814  * (On some hardware platforms shape changes could cause unwanted
 815  * effects like extra data movement instructions, round trips through
 816  * memory, or pipeline bubbles.)
 817  *
 818  * <p> Tension between these principles arises when an operation
 819  * produces a <em>logical result</em> that is too large for the
 820  * required output {@code VSHAPE}.  In other cases, when a logical
 821  * result is smaller than the capacity of the output {@code VSHAPE},
 822  * the positioning of the logical result is open to question, since
 823  * the physical output vector must contain a mix of logical result and
 824  * padding.
 825  *
 826  * <p> In the first case, of a too-large logical result being crammed
 827  * into a too-small output {@code VSHAPE}, we say that data has
 828  * <em>expanded</em>.  In other words, an <em>expansion operation</em>
 829  * has caused the output shape to overflow.  Symmetrically, in the
 830  * second case of a small logical result fitting into a roomy output
 831  * {@code VSHAPE}, the data has <em>contracted</em>, and the
 832  * <em>contraction operation</em> has required the output shape to pad
 833  * itself with extra zero lanes.
 834  *
 835  * <p> In both cases we can speak of a parameter {@code M} which
 836  * measures the <em>expansion ratio</em> or <em>contraction ratio</em>
 837  * between the logical result size (in bits) and the bit-size of the
 838  * actual output shape.  When vector shapes are changed, and lane
 839  * sizes are not, {@code M} is just the integral ratio of the output
 840  * shape to the logical result.  (With the possible exception of
 841  * the {@linkplain VectorShape#S_Max_BIT maximum shape}, all vector
 842  * sizes are powers of two, and so the ratio {@code M} is always
 843  * an integer.  In the hypothetical case of a non-integral ratio,
 844  * the value {@code M} would be rounded up to the next integer,
 845  * and then the same general considerations would apply.)
 846  *
 847  * <p> If the logical result is larger than the physical output shape,
 848  * such a shape change must inevitably drop result lanes (all but
 849  * {@code 1/M} of the logical result).  If the logical size is smaller
 850  * than the output, the shape change must introduce zero-filled lanes
 851  * of padding (all but {@code 1/M} of the physical output).  The first
 852  * case, with dropped lanes, is an expansion, while the second, with
 853  * padding lanes added, is a contraction.
 854  *
 855  * <p> Similarly, consider a lane-wise conversion operation which
 856  * leaves the shape invariant but changes the lane size by a ratio of
 857  * {@code M}.  If the logical result is larger than the output (or
 858  * input), this conversion must reduce the {@code VLENGTH} lanes of the
 859  * output by {@code M}, dropping all but {@code 1/M} of the logical
 860  * result lanes.  As before, the dropping of lanes is the hallmark of
 861  * an expansion.  A lane-wise operation which contracts lane size by a
 862  * ratio of {@code M} must increase the {@code VLENGTH} by the same
 863  * factor {@code M}, filling the extra lanes with a zero padding
 864  * value; because padding must be added this is a contraction.
 865  *
 866  * <p> It is also possible (though somewhat confusing) to change both
 867  * lane size and container size in one operation which performs both
 868  * lane conversion <em>and</em> reshaping.  If this is done, the same
 869  * rules apply, but the logical result size is the product of the
 870  * input size times any expansion or contraction ratio from the lane
 871  * change size.
 872  *
 873  * <p> For completeness, we can also speak of <em>in-place
 874  * operations</em> for the frequent case when resizing does not occur.
 875  * With an in-place operation, the data is simply copied from logical
 876  * output to its physical container with no truncation or padding.
 877  * The ratio parameter {@code M} in this case is unity.
 878  *
 879  * <p> Note that the classification of contraction vs. expansion
 880  * depends on the relative sizes of the logical result and the
 881  * physical output container.  The size of the input container may be
 882  * larger or smaller than either of the other two values, without
 883  * changing the classification.  For example, a conversion from a
 884  * 128-bit shape to a 256-bit shape will be a contraction in many
 885  * cases, but it would be an expansion if it were combined with a
 886  * conversion from {@code byte} to {@code long}, since in that case
 887  * the logical result would be 1024 bits in size.  This example also
 888  * illustrates that a logical result does not need to correspond to
 889  * any particular platform-supported vector shape.
 890  *
 891  * <p> Although lane-wise masked operations can be viewed as producing
 892  * partial operations, they are not classified (in this API) as
 893  * expansions or contractions.  A masked load from an array surely
 894  * produces a partial vector, but there is no meaningful "logical
 895  * output vector" that this partial result was contracted from.
 896  *
 897  * <p> Some care is required with these terms, because it is the
 898  * <em>data</em>, not the <em>container size</em>, that is expanding
 899  * or contracting, relative to the size of its output container.
 900  * Thus, resizing a 128-bit input into 512-bit vector has the effect
 901  * of a <em>contraction</em>.  Though the 128 bits of payload hasn't
 902  * changed in size, we can say it "looks smaller" in its new 512-bit
 903  * home, and this will capture the practical details of the situation.
 904  *
 905  * <p> If a vector method might expand its data, it accepts an extra
 906  * {@code int} parameter called {@code part}, or the "part number".
 907  * The part number must be in the range {@code [0..M-1]}, where
 908  * {@code M} is the expansion ratio.  The part number selects one
 909  * of {@code M} contiguous disjoint equally-sized blocks of lanes
 910  * from the logical result and fills the physical output vector
 911  * with this block of lanes.
 912  *
 913  * <p> Specifically, the lanes selected from the logical result of an
 914  * expansion are numbered in the range {@code [R..R+L-1]}, where
 915  * {@code L} is the {@code VLENGTH} of the physical output vector, and
 916  * the origin of the block, {@code R}, is {@code part*L}.
 917  *
 918  * <p> A similar convention applies to any vector method that might
 919  * contract its data.  Such a method also accepts an extra part number
 920  * parameter (again called {@code part}) which steers the contracted
 921  * data lanes one of {@code M} contiguous disjoint equally-sized
 922  * blocks of lanes in the physical output vector.  The remaining lanes
 923  * are filled with zero, or as specified by the method.
 924  *
 925  * <p> Specifically, the data is steered into the lanes numbered in the
 926  * range {@code [R..R+L-1]}, where {@code L} is the {@code VLENGTH} of
 927  * the logical result vector, and the origin of the block, {@code R},
 928  * is again a multiple of {@code L} selected by the part number,
 929  * specifically {@code |part|*L}.
 930  *
 931  * <p> In the case of a contraction, the part number must be in the
 932  * non-positive range {@code [-M+1..0]}.  This convention is adopted
 933  * because some methods can perform both expansions and contractions,
 934  * in a data-dependent manner, and the extra sign on the part number
 935  * serves as an error check.  If vector method takes a part number and
 936  * is invoked to perform an in-place operation (neither contracting
 937  * nor expanding), the {@code part} parameter must be exactly zero.
 938  * Part numbers outside the allowed ranges will elicit an indexing
 939  * exception.  Note that in all cases a zero part number is valid, and
 940  * corresponds to an operation which preserves as many lanes as
 941  * possible from the beginning of the logical result, and places them
 942  * into the beginning of the physical output container.  This is
 943  * often a desirable default, so a part number of zero is safe
 944  * in all cases and useful in most cases.
 945  *
 946  * <p> The various resizing operations of this API contract or expand
 947  * their data as follows:
 948  * <ul>
 949  *
 950  * <li>
 951  * {@link Vector#convert(VectorOperators.Conversion,int) Vector.convert()}
 952  * will expand (respectively, contract) its operand by ratio
 953  * {@code M} if the
 954  * {@linkplain #elementSize() element size} of its output is
 955  * larger (respectively, smaller) by a factor of {@code M}.
 956  * If the element sizes of input and output are the same,
 957  * then {@code convert()} is an in-place operation.
 958  *
 959  * <li>
 960  * {@link Vector#convertShape(VectorOperators.Conversion,VectorSpecies,int) Vector.convertShape()}
 961  * will expand (respectively, contract) its operand by ratio
 962  * {@code M} if the bit-size of its logical result is
 963  * larger (respectively, smaller) than the bit-size of its
 964  * output shape.
 965  * The size of the logical result is defined as the
 966  * {@linkplain #elementSize() element size} of the output,
 967  * times the {@code VLENGTH} of its input.
 968  *
 969  * Depending on the ratio of the changed lane sizes, the logical size
 970  * may be (in various cases) either larger or smaller than the input
 971  * vector, independently of whether the operation is an expansion
 972  * or contraction.
 973  *
 974  * <li>
 975  * Since {@link Vector#castShape(VectorSpecies,int) Vector.castShape()}
 976  * is a convenience method for {@code convertShape()}, its classification
 977  * as an expansion or contraction is the same as for {@code convertShape()}.
 978  *
 979  * <li>
 980  * {@link Vector#reinterpretShape(VectorSpecies,int) Vector.reinterpretShape()}
 981  * is an expansion (respectively, contraction) by ratio {@code M} if the
 982  * {@linkplain #bitSize() vector bit-size} of its input is
 983  * crammed into a smaller (respectively, dropped into a larger)
 984  * output container by a factor of {@code M}.
 985  * Otherwise it is an in-place operation.
 986  *
 987  * Since this method is a reinterpretation cast that can erase and
 988  * redraw lane boundaries as well as modify shape, the input vector's
 989  * lane size and lane count are irrelevant to its classification as
 990  * expanding or contracting.
 991  *
 992  * <li>
 993  * The {@link #unslice(int,Vector,int) unslice()} methods expand
 994  * by a ratio of {@code M=2}, because the single input slice is
 995  * positioned and inserted somewhere within two consecutive background
 996  * vectors.  The part number selects the first or second background
 997  * vector, as updated by the inserted slice.
 998  * Note that the corresponding
 999  * {@link #slice(int,Vector) slice()} methods, although inverse
1000  * to the {@code unslice()} methods, do not contract their data
1001  * and thus require no part number.  This is because
1002  * {@code slice()} delivers a slice of exactly {@code VLENGTH}
1003  * lanes extracted from two input vectors.
1004  * </ul>
1005  *
1006  * The method {@link VectorSpecies#partLimit(VectorSpecies,boolean)
1007  * partLimit()} on {@link VectorSpecies} can be used, before any
1008  * expanding or contracting operation is performed, to query the
1009  * limiting value on a part parameter for a proposed expansion
1010  * or contraction.  The value returned from {@code partLimit()} is
1011  * positive for expansions, negative for contractions, and zero for
1012  * in-place operations.  Its absolute value is the parameter {@code
1013  * M}, and so it serves as an exclusive limit on valid part number
1014  * arguments for the relevant methods.  Thus, for expansions, the
1015  * {@code partLimit()} value {@code M} is the exclusive upper limit
1016  * for part numbers, while for contractions the {@code partLimit()}
1017  * value {@code -M} is the exclusive <em>lower</em> limit.
1018  *
1019  * <h2><a id="cross-lane"></a>Moving data across lane boundaries</h2>
1020  * The cross-lane methods which do not redraw lanes or change species
1021  * are more regularly structured and easier to reason about.
1022  * These operations are:
1023  * <ul>
1024  *
1025  * <li>The {@link #slice(int,Vector) slice()} family of methods,
1026  * which extract contiguous slice of {@code VLENGTH} fields from
1027  * a given origin point within a concatenated pair of vectors.
1028  *
1029  * <li>The {@link #unslice(int,Vector,int) unslice()} family of
1030  * methods, which insert a contiguous slice of {@code VLENGTH} fields
1031  * into a concatenated pair of vectors at a given origin point.
1032  *
1033  * <li>The {@link #rearrange(VectorShuffle) rearrange()} family of
1034  * methods, which select an arbitrary set of {@code VLENGTH} lanes
1035  * from one or two input vectors, and assemble them in an arbitrary
1036  * order.  The selection and order of lanes is controlled by a
1037  * {@code VectorShuffle} object, which acts as an routing table
1038  * mapping source lanes to destination lanes.  A {@code VectorShuffle}
1039  * can encode a mathematical permutation as well as many other
1040  * patterns of data movement.
1041  *
1042  * </ul>
1043  * <p> Some vector operations are not lane-wise, but rather move data
1044  * across lane boundaries.  Such operations are typically rare in SIMD
1045  * code, though they are sometimes necessary for specific algorithms
1046  * that manipulate data formats at a low level, and/or require SIMD
1047  * data to move in complex local patterns.  (Local movement in a small
1048  * window of a large array of data is relatively unusual, although
1049  * some highly patterned algorithms call for it.)  In this API such
1050  * methods are always clearly recognizable, so that simpler lane-wise
1051  * reasoning can be confidently applied to the rest of the code.
1052  *
1053  * <p> In some cases, vector lane boundaries are discarded and
1054  * "redrawn from scratch", so that data in a given input lane might
1055  * appear (in several parts) distributed through several output lanes,
1056  * or (conversely) data from several input lanes might be consolidated
1057  * into a single output lane.  The fundamental method which can redraw
1058  * lanes boundaries is
1059  * {@link #reinterpretShape(VectorSpecies,int) reinterpretShape()}.
1060  * Built on top of this method, certain convenience methods such
1061  * as {@link #reinterpretAsBytes() reinterpretAsBytes()} or
1062  * {@link #reinterpretAsInts() reinterpretAsInts()} will
1063  * (potentially) redraw lane boundaries, while retaining the
1064  * same overall vector shape.
1065  *
1066  * <p> Operations which produce or consume a scalar result can be
1067  * viewed as very simple cross-lane operations.  Methods in the
1068  * {@link #reduceLanesToLong(VectorOperators.Associative)
1069  * reduceLanes()} family fold together all lanes (or mask-selected
1070  * lanes) of a method and return a single result.  As an inverse, the
1071  * {@link #broadcast(long) broadcast} family of methods can be thought
1072  * of as crossing lanes in the other direction, from a scalar to all
1073  * lanes of the output vector.  Single-lane access methods such as
1074  * {@code lane(I)} or {@code withLane(I,E)} might also be regarded as
1075  * very simple cross-lane operations.
1076  *
1077  * <p> Likewise, a method which moves a non-byte vector to or from a
1078  * byte array could be viewed as a cross-lane operation, because the
1079  * vector lanes must be distributed into separate bytes, or (in the
1080  * other direction) consolidated from array bytes.
1081  *
1082  * @implNote
1083  *
1084  * <h2>Hardware platform dependencies and limitations</h2>
1085  *
1086  * The Vector API is to accelerate computations in style of Single
1087  * Instruction Multiple Data (SIMD), using available hardware
1088  * resources such as vector hardware registers and vector hardware
1089  * instructions.  The API is designed to make effective use of
1090  * multiple SIMD hardware platforms.
1091  *
1092  * <p> This API will also work correctly even on Java platforms which
1093  * do not include specialized hardware support for SIMD computations.
1094  * The Vector API is not likely to provide any special performance
1095  * benefit on such platforms.
1096  *
1097  * <p> Currently the implementation is optimized to work best on:
1098  *
1099  * <ul>
1100  *
1101  * <li> Intel x64 platforms supporting at least AVX2 up to AVX-512.
1102  * Masking using mask registers and mask accepting hardware
1103  * instructions on AVX-512 are not currently supported.
1104  *
1105  * <li> ARM AArch64 platforms supporting NEON.  Although the API has
1106  * been designed to ensure ARM SVE instructions can be supported
1107  * (vector sizes between 128 to 2048 bits) there is currently no
1108  * implementation of such instructions and the general masking
1109  * capability.
1110  *
1111  * </ul>
1112  * The implementation currently supports masked lane-wise operations
1113  * in a cross-platform manner by composing the unmasked lane-wise
1114  * operation with {@link #blend(Vector, VectorMask) blend} as in
1115  * the expression {@code a.blend(a.lanewise(op, b), m)}, where
1116  * {@code a} and {@code b} are vectors, {@code op} is the vector
1117  * operation, and {@code m} is the mask.
1118  *
1119  * <p> The implementation does not currently support optimal
1120  * vectorized instructions for floating point transcendental
1121  * functions (such as operators {@link VectorOperators#SIN SIN}
1122  * and {@link VectorOperators#LOG LOG}).
1123  *
1124  * <h2>No boxing of primitives</h2>
1125  *
1126  * Although a vector type like {@code Vector<Integer>} may seem to
1127  * work with boxed {@code Integer} values, the overheads associated
1128  * with boxing are avoided by having each vector subtype work
1129  * internally on lane values of the actual {@code ETYPE}, such as
1130  * {@code int}.
1131  *
1132  * <h2>Value-based classes and identity operations</h2>
1133  *
1134  * {@code Vector}, along with all of its subtypes and many of its
1135  * helper types like {@code VectorMask} and {@code VectorShuffle}, is a
1136  * <a href="{@docRoot}/java.base/java/lang/doc-files/ValueBased.html">value-based</a>
1137  * class.
1138  *
1139  * <p> Once created, a vector is never mutated, not even if only
1140  * {@linkplain IntVector#withLane(int,int) a single lane is changed}.
1141  * A new vector is always created to hold a new configuration
1142  * of lane values.  The unavailability of mutative methods is a
1143  * necessary consequence of suppressing the object identity of
1144  * all vectors, as value-based classes.
1145  *
1146  * <p> With {@code Vector},
1147  *
1148  * <!-- The following paragraph is shared verbatim
1149  *   -- between Vector.java and package-info.java -->
1150  * identity-sensitive operations such as {@code ==} may yield
1151  * unpredictable results, or reduced performance.  Oddly enough,
1152  * {@link Vector#equals(Object) v.equals(w)} is likely to be faster
1153  * than {@code v==w}, since {@code equals} is <em>not</em> an identity
1154  * sensitive method.
1155  *
1156  * Also, these objects can be stored in locals and parameters and as
1157  * {@code static final} constants, but storing them in other Java
1158  * fields or in array elements, while semantically valid, may incur
1159  * performance penalties.
1160  * <!-- The preceding paragraph is shared verbatim
1161  *   -- between Vector.java and package-info.java -->
1162  *
1163  * @param <E> the boxed version of {@code ETYPE},
1164  *           the element type of a vector
1165  *
1166  */
1167 @SuppressWarnings("exports")
1168 public abstract class Vector<E> extends jdk.internal.vm.vector.VectorSupport.Vector<E> {
1169 
1170     // This type is sealed within its package.
1171     // Users cannot roll their own vector types.
1172     Vector(Object bits) {
1173         super(bits);
1174     }
1175 
1176     /**
1177      * Returns the species of this vector.
1178      *
1179      * @return the species of this vector
1180      */
1181     public abstract VectorSpecies<E> species();
1182 
1183     /**
1184      * Returns the primitive <a href="Vector.html#ETYPE">element type</a>
1185      * ({@code ETYPE}) of this vector.
1186      *
1187      * @implSpec
1188      * This is the same value as {@code this.species().elementType()}.
1189      *
1190      * @return the primitive element type of this vector
1191      */
1192     public abstract Class<E> elementType();
1193 
1194     /**
1195      * Returns the size of each lane, in bits, of this vector.
1196      *
1197      * @implSpec
1198      * This is the same value as {@code this.species().elementSize()}.
1199      *
1200      * @return the lane size, in bits, of this vector
1201      */
1202     public abstract int elementSize();
1203 
1204     /**
1205      * Returns the shape of this vector.
1206      *
1207      * @implSpec
1208      * This is the same value as {@code this.species().vectorShape()}.
1209      *
1210      * @return the shape of this vector
1211      */
1212     public abstract VectorShape shape();
1213 
1214     /**
1215      * Returns the lane count, or <a href="Vector.html#VLENGTH">vector length</a>
1216      * ({@code VLENGTH}).
1217      *
1218      * @return the lane count
1219      */
1220     public abstract int length();
1221 
1222     /**
1223      * Returns the total size, in bits, of this vector.
1224      *
1225      * @implSpec
1226      * This is the same value as {@code this.shape().vectorBitSize()}.
1227      *
1228      * @return the total size, in bits, of this vector
1229      */
1230     public abstract int bitSize();
1231 
1232     /**
1233      * Returns the total size, in bytes, of this vector.
1234      *
1235      * @implSpec
1236      * This is the same value as {@code this.bitSize()/Byte.SIZE}.
1237      *
1238      * @return the total size, in bytes, of this vector
1239      */
1240     public abstract int byteSize();
1241 
1242     /// Arithmetic
1243 
1244     /**
1245      * Operates on the lane values of this vector.
1246      *
1247      * This is a <a href="Vector.html#lane-wise">lane-wise</a>
1248      * unary operation which applies
1249      * the selected operation to each lane.
1250      *
1251      * @apiNote
1252      * Subtypes improve on this method by sharpening
1253      * the method return type.
1254      *
1255      * @param op the operation used to process lane values
1256      * @return the result of applying the operation lane-wise
1257      *         to the input vector
1258      * @throws UnsupportedOperationException if this vector does
1259      *         not support the requested operation
1260      * @see VectorOperators#NEG
1261      * @see VectorOperators#NOT
1262      * @see VectorOperators#SIN
1263      * @see #lanewise(VectorOperators.Unary,VectorMask)
1264      * @see #lanewise(VectorOperators.Binary,Vector)
1265      * @see #lanewise(VectorOperators.Ternary,Vector,Vector)
1266      */
1267     public abstract Vector<E> lanewise(VectorOperators.Unary op);
1268 
1269     /**
1270      * Operates on the lane values of this vector,
1271      * with selection of lane elements controlled by a mask.
1272      *
1273      * This is a lane-wise unary operation which applies
1274      * the selected operation to each lane.
1275      *
1276      * @apiNote
1277      * Subtypes improve on this method by sharpening
1278      * the method return type.
1279      *
1280      * @param op the operation used to process lane values
1281      * @param m the mask controlling lane selection
1282      * @return the result of applying the operation lane-wise
1283      *         to the input vector
1284      * @throws UnsupportedOperationException if this vector does
1285      *         not support the requested operation
1286      * @see #lanewise(VectorOperators.Unary)
1287      */
1288     public abstract Vector<E> lanewise(VectorOperators.Unary op,
1289                                        VectorMask<E> m);
1290 
1291     /**
1292      * Combines the corresponding lane values of this vector
1293      * with those of a second input vector.
1294      *
1295      * This is a <a href="Vector.html#lane-wise">lane-wise</a>
1296      * binary operation which applies
1297      * the selected operation to each lane.
1298      *
1299      * @apiNote
1300      * Subtypes improve on this method by sharpening
1301      * the method return type.
1302      *
1303      * @param op the operation used to combine lane values
1304      * @param v the input vector
1305      * @return the result of applying the operation lane-wise
1306      *         to the two input vectors
1307      * @throws UnsupportedOperationException if this vector does
1308      *         not support the requested operation
1309      * @see VectorOperators#ADD
1310      * @see VectorOperators#XOR
1311      * @see VectorOperators#ATAN2
1312      * @see #lanewise(VectorOperators.Binary,Vector,VectorMask)
1313      * @see #lanewise(VectorOperators.Unary)
1314      * @see #lanewise(VectorOperators.Ternary,Vector, Vector)
1315      */
1316     public abstract Vector<E> lanewise(VectorOperators.Binary op,
1317                                        Vector<E> v);
1318 
1319     /**
1320      * Combines the corresponding lane values of this vector
1321      * with those of a second input vector,
1322      * with selection of lane elements controlled by a mask.
1323      *
1324      * This is a lane-wise binary operation which applies
1325      * the selected operation to each lane.
1326      *
1327      * @apiNote
1328      * Subtypes improve on this method by sharpening
1329      * the method return type.
1330      *
1331      * @param op the operation used to combine lane values
1332      * @param v the second input vector
1333      * @param m the mask controlling lane selection
1334      * @return the result of applying the operation lane-wise
1335      *         to the two input vectors
1336      * @throws UnsupportedOperationException if this vector does
1337      *         not support the requested operation
1338      * @see #lanewise(VectorOperators.Binary,Vector)
1339      */
1340     public abstract Vector<E> lanewise(VectorOperators.Binary op,
1341                                        Vector<E> v, VectorMask<E> m);
1342 
1343     /**
1344      * Combines the lane values of this vector
1345      * with the value of a broadcast scalar.
1346      *
1347      * This is a lane-wise binary operation which applies
1348      * the selected operation to each lane.
1349      * The return value will be equal to this expression:
1350      * {@code this.lanewise(op, this.broadcast(e))}.
1351      *
1352      * @apiNote
1353      * The {@code long} value {@code e} must be accurately
1354      * representable by the {@code ETYPE} of this vector's species,
1355      * so that {@code e==(long)(ETYPE)e}.  This rule is enforced
1356      * by the implicit call to {@code broadcast()}.
1357      * <p>
1358      * Subtypes improve on this method by sharpening
1359      * the method return type and
1360      * the type of the scalar parameter {@code e}.
1361      *
1362      * @param op the operation used to combine lane values
1363      * @param e the input scalar
1364      * @return the result of applying the operation lane-wise
1365      *         to the input vector and the scalar
1366      * @throws UnsupportedOperationException if this vector does
1367      *         not support the requested operation
1368      * @throws IllegalArgumentException
1369      *         if the given {@code long} value cannot
1370      *         be represented by the right operand type
1371      *         of the vector operation
1372      * @see #broadcast(long)
1373      * @see #lanewise(VectorOperators.Binary,long,VectorMask)
1374      */
1375     public abstract Vector<E> lanewise(VectorOperators.Binary op,
1376                                        long e);
1377 
1378     /**
1379      * Combines the corresponding lane values of this vector
1380      * with those of a second input vector,
1381      * with selection of lane elements controlled by a mask.
1382      *
1383      * This is a lane-wise binary operation which applies
1384      * the selected operation to each lane.
1385      * The second operand is a broadcast integral value.
1386      * The return value will be equal to this expression:
1387      * {@code this.lanewise(op, this.broadcast(e), m)}.
1388      *
1389      * @apiNote
1390      * The {@code long} value {@code e} must be accurately
1391      * representable by the {@code ETYPE} of this vector's species,
1392      * so that {@code e==(long)(ETYPE)e}.  This rule is enforced
1393      * by the implicit call to {@code broadcast()}.
1394      * <p>
1395      * Subtypes improve on this method by sharpening
1396      * the method return type and
1397      * the type of the scalar parameter {@code e}.
1398      *
1399      * @param op the operation used to combine lane values
1400      * @param e the input scalar
1401      * @param m the mask controlling lane selection
1402      * @return the result of applying the operation lane-wise
1403      *         to the input vector and the scalar
1404      * @throws UnsupportedOperationException if this vector does
1405      *         not support the requested operation
1406      * @throws IllegalArgumentException
1407      *         if the given {@code long} value cannot
1408      *         be represented by the right operand type
1409      *         of the vector operation
1410      * @see #broadcast(long)
1411      * @see #lanewise(VectorOperators.Binary,Vector,VectorMask)
1412      */
1413     public abstract Vector<E> lanewise(VectorOperators.Binary op,
1414                                        long e, VectorMask<E> m);
1415 
1416     /**
1417      * Combines the corresponding lane values of this vector
1418      * with the lanes of a second and a third input vector.
1419      *
1420      * This is a <a href="Vector.html#lane-wise">lane-wise</a>
1421      * ternary operation which applies
1422      * the selected operation to each lane.
1423      *
1424      * @apiNote
1425      * Subtypes improve on this method by sharpening
1426      * the method return type.
1427      *
1428      * @param op the operation used to combine lane values
1429      * @param v1 the second input vector
1430      * @param v2 the third input vector
1431      * @return the result of applying the operation lane-wise
1432      *         to the three input vectors
1433      * @throws UnsupportedOperationException if this vector does
1434      *         not support the requested operation
1435      * @see VectorOperators#BITWISE_BLEND
1436      * @see VectorOperators#FMA
1437      * @see #lanewise(VectorOperators.Unary)
1438      * @see #lanewise(VectorOperators.Binary,Vector)
1439      * @see #lanewise(VectorOperators.Ternary,Vector,Vector,VectorMask)
1440      */
1441     public abstract Vector<E> lanewise(VectorOperators.Ternary op,
1442                                        Vector<E> v1,
1443                                        Vector<E> v2);
1444 
1445     /**
1446      * Combines the corresponding lane values of this vector
1447      * with the lanes of a second and a third input vector,
1448      * with selection of lane elements controlled by a mask.
1449      *
1450      * This is a lane-wise ternary operation which applies
1451      * the selected operation to each lane.
1452      *
1453      * @apiNote
1454      * Subtypes improve on this method by sharpening
1455      * the method return type.
1456      *
1457      * @param op the operation used to combine lane values
1458      * @param v1 the second input vector
1459      * @param v2 the third input vector
1460      * @param m the mask controlling lane selection
1461      * @return the result of applying the operation lane-wise
1462      *         to the three input vectors
1463      * @throws UnsupportedOperationException if this vector does
1464      *         not support the requested operation
1465      * @see #lanewise(VectorOperators.Ternary,Vector,Vector)
1466      */
1467     public abstract Vector<E> lanewise(VectorOperators.Ternary op,
1468                                        Vector<E> v1, Vector<E> v2,
1469                                        VectorMask<E> m);
1470 
1471     // Note:  lanewise(Binary) has two rudimentary broadcast
1472     // operations from an approximate scalar type (long).
1473     // We do both with that, here, for lanewise(Ternary).
1474     // The vector subtypes supply a full suite of
1475     // broadcasting and masked lanewise operations
1476     // for their specific ETYPEs:
1477     //   lanewise(Unary, [mask])
1478     //   lanewise(Binary, [e | v], [mask])
1479     //   lanewise(Ternary, [e1 | v1], [e2 | v2], [mask])
1480 
1481     /// Full-service binary ops: ADD, SUB, MUL, DIV
1482 
1483     // Full-service functions support all four variations
1484     // of vector vs. broadcast scalar, and mask vs. not.
1485     // The lanewise generic operator is (by this definition)
1486     // also a full-service function.
1487 
1488     // Other named functions handle just the one named
1489     // variation.  Most lanewise operations are *not* named,
1490     // and are reached only by lanewise.
1491 
1492     /**
1493      * Adds this vector to a second input vector.
1494      *
1495      * This is a lane-wise binary operation which applies
1496      * the primitive addition operation ({@code +})
1497      * to each pair of corresponding lane values.
1498      *
1499      * This method is also equivalent to the expression
1500      * {@link #lanewise(VectorOperators.Binary,Vector)
1501      *    lanewise}{@code (}{@link VectorOperators#ADD
1502      *    ADD}{@code , v)}.
1503      *
1504      * <p>
1505      * As a full-service named operation, this method
1506      * comes in masked and unmasked overloadings, and
1507      * (in subclasses) also comes in scalar-broadcast
1508      * overloadings (both masked and unmasked).
1509      *
1510      * @param v a second input vector
1511      * @return the result of adding this vector to the second input vector
1512      * @see #add(Vector,VectorMask)
1513      * @see IntVector#add(int)
1514      * @see VectorOperators#ADD
1515      * @see #lanewise(VectorOperators.Binary,Vector)
1516      * @see IntVector#lanewise(VectorOperators.Binary,int)
1517      */
1518     public abstract Vector<E> add(Vector<E> v);
1519 
1520     /**
1521      * Adds this vector to a second input vector, selecting lanes
1522      * under the control of a mask.
1523      *
1524      * This is a masked lane-wise binary operation which applies
1525      * the primitive addition operation ({@code +})
1526      * to each pair of corresponding lane values.
1527      *
1528      * For any lane unset in the mask, the primitive operation is
1529      * suppressed and this vector retains the original value stored in
1530      * that lane.
1531      *
1532      * This method is also equivalent to the expression
1533      * {@link #lanewise(VectorOperators.Binary,Vector,VectorMask)
1534      *    lanewise}{@code (}{@link VectorOperators#ADD
1535      *    ADD}{@code , v, m)}.
1536      *
1537      * <p>
1538      * As a full-service named operation, this method
1539      * comes in masked and unmasked overloadings, and
1540      * (in subclasses) also comes in scalar-broadcast
1541      * overloadings (both masked and unmasked).
1542      *
1543      * @param v the second input vector
1544      * @param m the mask controlling lane selection
1545      * @return the result of adding this vector to the given vector
1546      * @see #add(Vector)
1547      * @see IntVector#add(int,VectorMask)
1548      * @see VectorOperators#ADD
1549      * @see #lanewise(VectorOperators.Binary,Vector,VectorMask)
1550      * @see IntVector#lanewise(VectorOperators.Binary,int,VectorMask)
1551      */
1552     public abstract Vector<E> add(Vector<E> v, VectorMask<E> m);
1553 
1554     /**
1555      * Subtracts a second input vector from this vector.
1556      *
1557      * This is a lane-wise binary operation which applies
1558      * the primitive subtraction operation ({@code -})
1559      * to each pair of corresponding lane values.
1560      *
1561      * This method is also equivalent to the expression
1562      * {@link #lanewise(VectorOperators.Binary,Vector)
1563      *    lanewise}{@code (}{@link VectorOperators#SUB
1564      *    SUB}{@code , v)}.
1565      *
1566      * <p>
1567      * As a full-service named operation, this method
1568      * comes in masked and unmasked overloadings, and
1569      * (in subclasses) also comes in scalar-broadcast
1570      * overloadings (both masked and unmasked).
1571      *
1572      * @param v a second input vector
1573      * @return the result of subtracting the second input vector from this vector
1574      * @see #sub(Vector,VectorMask)
1575      * @see IntVector#sub(int)
1576      * @see VectorOperators#SUB
1577      * @see #lanewise(VectorOperators.Binary,Vector)
1578      * @see IntVector#lanewise(VectorOperators.Binary,int)
1579      */
1580     public abstract Vector<E> sub(Vector<E> v);
1581 
1582     /**
1583      * Subtracts a second input vector from this vector
1584      * under the control of a mask.
1585      *
1586      * This is a masked lane-wise binary operation which applies
1587      * the primitive subtraction operation ({@code -})
1588      * to each pair of corresponding lane values.
1589      *
1590      * For any lane unset in the mask, the primitive operation is
1591      * suppressed and this vector retains the original value stored in
1592      * that lane.
1593      *
1594      * This method is also equivalent to the expression
1595      * {@link #lanewise(VectorOperators.Binary,Vector,VectorMask)
1596      *    lanewise}{@code (}{@link VectorOperators#SUB
1597      *    SUB}{@code , v, m)}.
1598      *
1599      * <p>
1600      * As a full-service named operation, this method
1601      * comes in masked and unmasked overloadings, and
1602      * (in subclasses) also comes in scalar-broadcast
1603      * overloadings (both masked and unmasked).
1604      *
1605      * @param v the second input vector
1606      * @param m the mask controlling lane selection
1607      * @return the result of subtracting the second input vector from this vector
1608      * @see #sub(Vector)
1609      * @see IntVector#sub(int,VectorMask)
1610      * @see VectorOperators#SUB
1611      * @see #lanewise(VectorOperators.Binary,Vector,VectorMask)
1612      * @see IntVector#lanewise(VectorOperators.Binary,int,VectorMask)
1613      */
1614     public abstract Vector<E> sub(Vector<E> v, VectorMask<E> m);
1615 
1616     /**
1617      * Multiplies this vector by a second input vector.
1618      *
1619      * This is a lane-wise binary operation which applies
1620      * the primitive multiplication operation ({@code *})
1621      * to each pair of corresponding lane values.
1622      *
1623      * This method is also equivalent to the expression
1624      * {@link #lanewise(VectorOperators.Binary,Vector)
1625      *    lanewise}{@code (}{@link VectorOperators#MUL
1626      *    MUL}{@code , v)}.
1627      *
1628      * <p>
1629      * As a full-service named operation, this method
1630      * comes in masked and unmasked overloadings, and
1631      * (in subclasses) also comes in scalar-broadcast
1632      * overloadings (both masked and unmasked).
1633      *
1634      * @param v a second input vector
1635      * @return the result of multiplying this vector by the second input vector
1636      * @see #mul(Vector,VectorMask)
1637      * @see IntVector#mul(int)
1638      * @see VectorOperators#MUL
1639      * @see #lanewise(VectorOperators.Binary,Vector)
1640      * @see IntVector#lanewise(VectorOperators.Binary,int)
1641      */
1642     public abstract Vector<E> mul(Vector<E> v);
1643 
1644     /**
1645      * Multiplies this vector by a second input vector
1646      * under the control of a mask.
1647      *
1648      * This is a lane-wise binary operation which applies
1649      * the primitive multiplication operation ({@code *})
1650      * to each pair of corresponding lane values.
1651      *
1652      * For any lane unset in the mask, the primitive operation is
1653      * suppressed and this vector retains the original value stored in
1654      * that lane.
1655      *
1656      * This method is also equivalent to the expression
1657      * {@link #lanewise(VectorOperators.Binary,Vector,VectorMask)
1658      *    lanewise}{@code (}{@link VectorOperators#MUL
1659      *    MUL}{@code , v, m)}.
1660      *
1661      * <p>
1662      * As a full-service named operation, this method
1663      * comes in masked and unmasked overloadings, and
1664      * (in subclasses) also comes in scalar-broadcast
1665      * overloadings (both masked and unmasked).
1666      *
1667      * @param v the second input vector
1668      * @param m the mask controlling lane selection
1669      * @return the result of multiplying this vector by the given vector
1670      * @see #mul(Vector)
1671      * @see IntVector#mul(int,VectorMask)
1672      * @see VectorOperators#MUL
1673      * @see #lanewise(VectorOperators.Binary,Vector,VectorMask)
1674      * @see IntVector#lanewise(VectorOperators.Binary,int,VectorMask)
1675      */
1676     public abstract Vector<E> mul(Vector<E> v, VectorMask<E> m);
1677 
1678     /**
1679      * Divides this vector by a second input vector.
1680      *
1681      * This is a lane-wise binary operation which applies
1682      * the primitive division operation ({@code /})
1683      * to each pair of corresponding lane values.
1684      *
1685      * This method is also equivalent to the expression
1686      * {@link #lanewise(VectorOperators.Binary,Vector)
1687      *    lanewise}{@code (}{@link VectorOperators#DIV
1688      *    DIV}{@code , v)}.
1689      *
1690      * <p>
1691      * As a full-service named operation, this method
1692      * comes in masked and unmasked overloadings, and
1693      * (in subclasses) also comes in scalar-broadcast
1694      * overloadings (both masked and unmasked).
1695      *
1696      * @apiNote If the underlying scalar operator does not support
1697      * division by zero, but is presented with a zero divisor,
1698      * an {@code ArithmeticException} will be thrown.
1699      *
1700      * @param v a second input vector
1701      * @return the result of dividing this vector by the second input vector
1702      * @throws ArithmeticException if any lane
1703      *         in {@code v} is zero
1704      *         and {@code ETYPE} is not {@code float} or {@code double}.
1705      * @see #div(Vector,VectorMask)
1706      * @see DoubleVector#div(double)
1707      * @see VectorOperators#DIV
1708      * @see #lanewise(VectorOperators.Binary,Vector)
1709      * @see IntVector#lanewise(VectorOperators.Binary,int)
1710      */
1711     public abstract Vector<E> div(Vector<E> v);
1712 
1713     /**
1714      * Divides this vector by a second input vector
1715      * under the control of a mask.
1716      *
1717      * This is a lane-wise binary operation which applies
1718      * the primitive division operation ({@code /})
1719      * to each pair of corresponding lane values.
1720      *
1721      * For any lane unset in the mask, the primitive operation is
1722      * suppressed and this vector retains the original value stored in
1723      * that lane.
1724      *
1725      * This method is also equivalent to the expression
1726      * {@link #lanewise(VectorOperators.Binary,Vector,VectorMask)
1727      *    lanewise}{@code (}{@link VectorOperators#DIV
1728      *    DIV}{@code , v, m)}.
1729      *
1730      * <p>
1731      * As a full-service named operation, this method
1732      * comes in masked and unmasked overloadings, and
1733      * (in subclasses) also comes in scalar-broadcast
1734      * overloadings (both masked and unmasked).
1735      *
1736      * @apiNote If the underlying scalar operator does not support
1737      * division by zero, but is presented with a zero divisor,
1738      * an {@code ArithmeticException} will be thrown.
1739      *
1740      * @param v a second input vector
1741      * @param m the mask controlling lane selection
1742      * @return the result of dividing this vector by the second input vector
1743      * @throws ArithmeticException if any lane selected by {@code m}
1744      *         in {@code v} is zero
1745      *         and {@code ETYPE} is not {@code float} or {@code double}.
1746      * @see #div(Vector)
1747      * @see DoubleVector#div(double,VectorMask)
1748      * @see VectorOperators#DIV
1749      * @see #lanewise(VectorOperators.Binary,Vector,VectorMask)
1750      * @see DoubleVector#lanewise(VectorOperators.Binary,double,VectorMask)
1751      */
1752     public abstract Vector<E> div(Vector<E> v, VectorMask<E> m);
1753 
1754     /// END OF FULL-SERVICE BINARY METHODS
1755 
1756     /// Non-full-service unary ops: NEG, ABS
1757 
1758     /**
1759      * Negates this vector.
1760      *
1761      * This is a lane-wise unary operation which applies
1762      * the primitive negation operation ({@code -x})
1763      * to each input lane.
1764      *
1765      * This method is also equivalent to the expression
1766      * {@link #lanewise(VectorOperators.Unary)
1767      *    lanewise}{@code (}{@link VectorOperators#NEG
1768      *    NEG}{@code )}.
1769      *
1770      * @apiNote
1771      * This method has no masked variant, but the corresponding
1772      * masked operation can be obtained from the
1773      * {@linkplain #lanewise(VectorOperators.Unary,VectorMask)
1774      * lanewise method}.
1775      *
1776      * @return the negation of this vector
1777      * @see VectorOperators#NEG
1778      * @see #lanewise(VectorOperators.Unary)
1779      * @see #lanewise(VectorOperators.Unary,VectorMask)
1780      */
1781     public abstract Vector<E> neg();
1782 
1783     /**
1784      * Returns the absolute value of this vector.
1785      *
1786      * This is a lane-wise unary operation which applies
1787      * the method {@code Math.abs}
1788      * to each input lane.
1789      *
1790      * This method is also equivalent to the expression
1791      * {@link #lanewise(VectorOperators.Unary)
1792      *    lanewise}{@code (}{@link VectorOperators#ABS
1793      *    ABS}{@code )}.
1794      *
1795      * @apiNote
1796      * This method has no masked variant, but the corresponding
1797      * masked operation can be obtained from the
1798      * {@linkplain #lanewise(VectorOperators.Unary,VectorMask)
1799      * lanewise method}.
1800      *
1801      * @return the absolute value of this vector
1802      * @see VectorOperators#ABS
1803      * @see #lanewise(VectorOperators.Unary)
1804      * @see #lanewise(VectorOperators.Unary,VectorMask)
1805      */
1806     public abstract Vector<E> abs();
1807 
1808     /// Non-full-service binary ops: MIN, MAX
1809 
1810     /**
1811      * Computes the smaller of this vector and a second input vector.
1812      *
1813      * This is a lane-wise binary operation which applies the
1814      * operation {@code Math.min()} to each pair of
1815      * corresponding lane values.
1816      *
1817      * This method is also equivalent to the expression
1818      * {@link #lanewise(VectorOperators.Binary,Vector)
1819      *    lanewise}{@code (}{@link VectorOperators#MIN
1820      *    MIN}{@code , v)}.
1821      *
1822      * @apiNote
1823      * This is not a full-service named operation like
1824      * {@link #add(Vector) add()}.  A masked version of
1825      * this operation is not directly available
1826      * but may be obtained via the masked version of
1827      * {@code lanewise}.  Subclasses define an additional
1828      * scalar-broadcast overloading of this method.
1829      *
1830      * @param v a second input vector
1831      * @return the lanewise minimum of this vector and the second input vector
1832      * @see IntVector#min(int)
1833      * @see VectorOperators#MIN
1834      * @see #lanewise(VectorOperators.Binary,Vector)
1835      * @see #lanewise(VectorOperators.Binary,Vector,VectorMask)
1836      */
1837     public abstract Vector<E> min(Vector<E> v);
1838 
1839     /**
1840      * Computes the larger of this vector and a second input vector.
1841      *
1842      * This is a lane-wise binary operation which applies the
1843      * operation {@code Math.max()} to each pair of
1844      * corresponding lane values.
1845      *
1846      * This method is also equivalent to the expression
1847      * {@link #lanewise(VectorOperators.Binary,Vector)
1848      *    lanewise}{@code (}{@link VectorOperators#MAX
1849      *    MAX}{@code , v)}.
1850      *
1851      * <p>
1852      * This is not a full-service named operation like
1853      * {@link #add(Vector) add()}.  A masked version of
1854      * this operation is not directly available
1855      * but may be obtained via the masked version of
1856      * {@code lanewise}.  Subclasses define an additional
1857      * scalar-broadcast overloading of this method.
1858      *
1859      * @param v a second input vector
1860      * @return the lanewise maximum of this vector and the second input vector
1861      * @see IntVector#max(int)
1862      * @see VectorOperators#MAX
1863      * @see #lanewise(VectorOperators.Binary,Vector)
1864      * @see #lanewise(VectorOperators.Binary,Vector,VectorMask)
1865      */
1866     public abstract Vector<E> max(Vector<E> v);
1867 
1868     // Reductions
1869 
1870     /**
1871      * Returns a value accumulated from all the lanes of this vector.
1872      *
1873      * This is an associative cross-lane reduction operation which
1874      * applies the specified operation to all the lane elements.
1875      * The return value will be equal to this expression:
1876      * {@code (long) ((EVector)this).reduceLanes(op)}, where {@code EVector}
1877      * is the vector class specific to this vector's element type
1878      * {@code ETYPE}.
1879      * <p>
1880      * In the case of operations {@code ADD} and {@code MUL},
1881      * when {@code ETYPE} is {@code float} or {@code double},
1882      * the precise result, before casting, will reflect the choice
1883      * of an arbitrary order of operations, which may even vary over time.
1884      * For further details see the section
1885      * <a href="VectorOperators.html#fp_assoc">Operations on floating point vectors</a>.
1886      *
1887      * @apiNote
1888      * If the {@code ETYPE} is {@code float} or {@code double},
1889      * this operation can lose precision and/or range, as a
1890      * normal part of casting the result down to {@code long}.
1891      *
1892      * Usually
1893      * {@linkplain IntVector#reduceLanes(VectorOperators.Associative)
1894      * strongly typed access}
1895      * is preferable, if you are working with a vector
1896      * subtype that has a known element type.
1897      *
1898      * @param op the operation used to combine lane values
1899      * @return the accumulated result, cast to {@code long}
1900      * @throws UnsupportedOperationException if this vector does
1901      *         not support the requested operation
1902      * @see #reduceLanesToLong(VectorOperators.Associative,VectorMask)
1903      * @see IntVector#reduceLanes(VectorOperators.Associative)
1904      * @see FloatVector#reduceLanes(VectorOperators.Associative)
1905      */
1906     public abstract long reduceLanesToLong(VectorOperators.Associative op);
1907 
1908     /**
1909      * Returns a value accumulated from selected lanes of this vector,
1910      * controlled by a mask.
1911      *
1912      * This is an associative cross-lane reduction operation which
1913      * applies the specified operation to the selected lane elements.
1914      * The return value will be equal to this expression:
1915      * {@code (long) ((EVector)this).reduceLanes(op, m)}, where {@code EVector}
1916      * is the vector class specific to this vector's element type
1917      * {@code ETYPE}.
1918      * <p>
1919      * If no elements are selected, an operation-specific identity
1920      * value is returned.
1921      * <ul>
1922      * <li>
1923      * If the operation is {@code ADD}, {@code XOR}, or {@code OR},
1924      * then the identity value is zero.
1925      * <li>
1926      * If the operation is {@code MUL},
1927      * then the identity value is one.
1928      * <li>
1929      * If the operation is {@code AND},
1930      * then the identity value is minus one (all bits set).
1931      * <li>
1932      * If the operation is {@code MAX},
1933      * then the identity value is the {@code MIN_VALUE}
1934      * of the vector's native {@code ETYPE}.
1935      * (In the case of floating point types, the value
1936      * {@code NEGATIVE_INFINITY} is used, and will appear
1937      * after casting as {@code Long.MIN_VALUE}.
1938      * <li>
1939      * If the operation is {@code MIN},
1940      * then the identity value is the {@code MAX_VALUE}
1941      * of the vector's native {@code ETYPE}.
1942      * (In the case of floating point types, the value
1943      * {@code POSITIVE_INFINITY} is used, and will appear
1944      * after casting as {@code Long.MAX_VALUE}.
1945      * </ul>
1946      * <p>
1947      * In the case of operations {@code ADD} and {@code MUL},
1948      * when {@code ETYPE} is {@code float} or {@code double},
1949      * the precise result, before casting, will reflect the choice
1950      * of an arbitrary order of operations, which may even vary over time.
1951      * For further details see the section
1952      * <a href="VectorOperators.html#fp_assoc">Operations on floating point vectors</a>.
1953      *
1954      * @apiNote
1955      * If the {@code ETYPE} is {@code float} or {@code double},
1956      * this operation can lose precision and/or range, as a
1957      * normal part of casting the result down to {@code long}.
1958      *
1959      * Usually
1960      * {@linkplain IntVector#reduceLanes(VectorOperators.Associative,VectorMask)
1961      * strongly typed access}
1962      * is preferable, if you are working with a vector
1963      * subtype that has a known element type.
1964      *
1965      * @param op the operation used to combine lane values
1966      * @param m the mask controlling lane selection
1967      * @return the reduced result accumulated from the selected lane values
1968      * @throws UnsupportedOperationException if this vector does
1969      *         not support the requested operation
1970      * @see #reduceLanesToLong(VectorOperators.Associative)
1971      * @see IntVector#reduceLanes(VectorOperators.Associative,VectorMask)
1972      * @see FloatVector#reduceLanes(VectorOperators.Associative,VectorMask)
1973      */
1974     public abstract long reduceLanesToLong(VectorOperators.Associative op,
1975                                            VectorMask<E> m);
1976 
1977     // Lanewise unary tests
1978 
1979     /**
1980      * Tests the lanes of this vector
1981      * according to the given operation.
1982      *
1983      * This is a lane-wise unary test operation which applies
1984      * the given test operation
1985      * to each lane value.
1986      * @param op the operation used to test lane values
1987      * @return the mask result of testing the lanes of this vector,
1988      *         according to the selected test operator
1989      * @see VectorOperators.Comparison
1990      * @see #test(VectorOperators.Test, VectorMask)
1991      * @see #compare(VectorOperators.Comparison, Vector)
1992      */
1993     public abstract VectorMask<E> test(VectorOperators.Test op);
1994 
1995     /**
1996      * Test selected lanes of this vector,
1997      * according to the given operation.
1998      *
1999      * This is a masked lane-wise unary test operation which applies
2000      * the given test operation
2001      * to each lane value.
2002      *
2003      * The returned result is equal to the expression
2004      * {@code test(op).and(m)}.
2005      *
2006      * @param op the operation used to test lane values
2007      * @param m the mask controlling lane selection
2008      * @return the mask result of testing the lanes of this vector,
2009      *         according to the selected test operator,
2010      *         and only in the lanes selected by the mask
2011      * @see #test(VectorOperators.Test)
2012      */
2013     public abstract VectorMask<E> test(VectorOperators.Test op,
2014                                        VectorMask<E> m);
2015 
2016     // Comparisons
2017 
2018     /**
2019      * Tests if this vector is equal to another input vector.
2020      *
2021      * This is a lane-wise binary test operation which applies
2022      * the primitive equals operation ({@code ==})
2023      * to each pair of corresponding lane values.
2024      * The result is the same as {@code compare(VectorOperators.EQ, v)}.
2025      *
2026      * @param v a second input vector
2027      * @return the mask result of testing lane-wise if this vector
2028      *         equal to the second input vector
2029      * @see #compare(VectorOperators.Comparison,Vector)
2030      * @see VectorOperators#EQ
2031      * @see #equals
2032      */
2033     public abstract VectorMask<E> eq(Vector<E> v);
2034 
2035     /**
2036      * Tests if this vector is less than another input vector.
2037      *
2038      * This is a lane-wise binary test operation which applies
2039      * the primitive less-than operation ({@code <}) to each lane.
2040      * The result is the same as {@code compare(VectorOperators.LT, v)}.
2041      *
2042      * @param v a second input vector
2043      * @return the mask result of testing lane-wise if this vector
2044      *         is less than the second input vector
2045      * @see #compare(VectorOperators.Comparison,Vector)
2046      * @see VectorOperators#LT
2047      */
2048     public abstract VectorMask<E> lt(Vector<E> v);
2049 
2050     /**
2051      * Tests this vector by comparing it with another input vector,
2052      * according to the given comparison operation.
2053      *
2054      * This is a lane-wise binary test operation which applies
2055      * the given comparison operation
2056      * to each pair of corresponding lane values.
2057      *
2058      * @param op the operation used to compare lane values
2059      * @param v a second input vector
2060      * @return the mask result of testing lane-wise if this vector
2061      *         compares to the input, according to the selected
2062      *         comparison operator
2063      * @see #eq(Vector)
2064      * @see #lt(Vector)
2065      * @see VectorOperators.Comparison
2066      * @see #compare(VectorOperators.Comparison, Vector, VectorMask)
2067      * @see #test(VectorOperators.Test)
2068      */
2069     public abstract VectorMask<E> compare(VectorOperators.Comparison op,
2070                                           Vector<E> v);
2071 
2072     /**
2073      * Tests this vector by comparing it with another input vector,
2074      * according to the given comparison operation,
2075      * in lanes selected by a mask.
2076      *
2077      * This is a masked lane-wise binary test operation which applies
2078      * the given comparison operation
2079      * to each pair of corresponding lane values.
2080      *
2081      * The returned result is equal to the expression
2082      * {@code compare(op,v).and(m)}.
2083      *
2084      * @param op the operation used to compare lane values
2085      * @param v a second input vector
2086      * @param m the mask controlling lane selection
2087      * @return the mask result of testing lane-wise if this vector
2088      *         compares to the input, according to the selected
2089      *         comparison operator,
2090      *         and only in the lanes selected by the mask
2091      * @see #compare(VectorOperators.Comparison, Vector)
2092      */
2093     public abstract VectorMask<E> compare(VectorOperators.Comparison op,
2094                                           Vector<E> v,
2095                                           VectorMask<E> m);
2096 
2097     /**
2098      * Tests this vector by comparing it with an input scalar,
2099      * according to the given comparison operation.
2100      *
2101      * This is a lane-wise binary test operation which applies
2102      * the given comparison operation
2103      * to each lane value, paired with the broadcast value.
2104      *
2105      * <p>
2106      * The result is the same as
2107      * {@code this.compare(op, this.broadcast(e))}.
2108      * That is, the scalar may be regarded as broadcast to
2109      * a vector of the same species, and then compared
2110      * against the original vector, using the selected
2111      * comparison operation.
2112      *
2113      * @apiNote
2114      * The {@code long} value {@code e} must be accurately
2115      * representable by the {@code ETYPE} of this vector's species,
2116      * so that {@code e==(long)(ETYPE)e}.  This rule is enforced
2117      * by the implicit call to {@code broadcast()}.
2118      * <p>
2119      * Subtypes improve on this method by sharpening
2120      * the type of the scalar parameter {@code e}.
2121      *
2122      * @param op the operation used to compare lane values
2123      * @param e the input scalar
2124      * @return the mask result of testing lane-wise if this vector
2125      *         compares to the input, according to the selected
2126      *         comparison operator
2127      * @throws IllegalArgumentException
2128      *         if the given {@code long} value cannot
2129      *         be represented by the vector's {@code ETYPE}
2130      * @see #broadcast(long)
2131      * @see #compare(VectorOperators.Comparison,Vector)
2132      */
2133     public abstract VectorMask<E> compare(VectorOperators.Comparison op,
2134                                           long e);
2135 
2136     /**
2137      * Tests this vector by comparing it with an input scalar,
2138      * according to the given comparison operation,
2139      * in lanes selected by a mask.
2140      *
2141      * This is a masked lane-wise binary test operation which applies
2142      * the given comparison operation
2143      * to each lane value, paired with the broadcast value.
2144      *
2145      * The returned result is equal to the expression
2146      * {@code compare(op,e).and(m)}.
2147      *
2148      * @apiNote
2149      * The {@code long} value {@code e} must be accurately
2150      * representable by the {@code ETYPE} of this vector's species,
2151      * so that {@code e==(long)(ETYPE)e}.  This rule is enforced
2152      * by the implicit call to {@code broadcast()}.
2153      * <p>
2154      * Subtypes improve on this method by sharpening
2155      * the type of the scalar parameter {@code e}.
2156      *
2157      * @param op the operation used to compare lane values
2158      * @param e the input scalar
2159      * @param m the mask controlling lane selection
2160      * @return the mask result of testing lane-wise if this vector
2161      *         compares to the input, according to the selected
2162      *         comparison operator,
2163      *         and only in the lanes selected by the mask
2164      * @throws IllegalArgumentException
2165      *         if the given {@code long} value cannot
2166      *         be represented by the vector's {@code ETYPE}
2167      * @see #broadcast(long)
2168      * @see #compare(VectorOperators.Comparison,Vector)
2169      */
2170     public abstract VectorMask<E> compare(VectorOperators.Comparison op,
2171                                           long e,
2172                                           VectorMask<E> m);
2173 
2174     /**
2175      * Replaces selected lanes of this vector with
2176      * corresponding lanes from a second input vector
2177      * under the control of a mask.
2178      *
2179      * This is a masked lane-wise binary operation which
2180      * selects each lane value from one or the other input.
2181      *
2182      * <ul>
2183      * <li>
2184      * For any lane <em>set</em> in the mask, the new lane value
2185      * is taken from the second input vector, and replaces
2186      * whatever value was in the that lane of this vector.
2187      * <li>
2188      * For any lane <em>unset</em> in the mask, the replacement is
2189      * suppressed and this vector retains the original value stored in
2190      * that lane.
2191      * </ul>
2192      *
2193      * The following pseudocode illustrates this behavior:
2194      * <pre>{@code
2195      * Vector<E> a = ...;
2196      * VectorSpecies<E> species = a.species();
2197      * Vector<E> b = ...;
2198      * b.check(species);
2199      * VectorMask<E> m = ...;
2200      * ETYPE[] ar = a.toArray();
2201      * for (int i = 0; i < ar.length; i++) {
2202      *     if (m.laneIsSet(i)) {
2203      *         ar[i] = b.lane(i);
2204      *     }
2205      * }
2206      * return EVector.fromArray(s, ar, 0);
2207      * }</pre>
2208      *
2209      * @param v the second input vector, containing replacement lane values
2210      * @param m the mask controlling lane selection from the second input vector
2211      * @return the result of blending the lane elements of this vector with
2212      *         those of the second input vector
2213      */
2214     public abstract Vector<E> blend(Vector<E> v, VectorMask<E> m);
2215 
2216     /**
2217      * Replaces selected lanes of this vector with
2218      * a scalar value
2219      * under the control of a mask.
2220      *
2221      * This is a masked lane-wise binary operation which
2222      * selects each lane value from one or the other input.
2223      *
2224      * The returned result is equal to the expression
2225      * {@code blend(broadcast(e),m)}.
2226      *
2227      * @apiNote
2228      * The {@code long} value {@code e} must be accurately
2229      * representable by the {@code ETYPE} of this vector's species,
2230      * so that {@code e==(long)(ETYPE)e}.  This rule is enforced
2231      * by the implicit call to {@code broadcast()}.
2232      * <p>
2233      * Subtypes improve on this method by sharpening
2234      * the type of the scalar parameter {@code e}.
2235      *
2236      * @param e the input scalar, containing the replacement lane value
2237      * @param m the mask controlling lane selection of the scalar
2238      * @return the result of blending the lane elements of this vector with
2239      *         the scalar value
2240      */
2241     public abstract Vector<E> blend(long e, VectorMask<E> m);
2242 
2243     /**
2244      * Adds the lanes of this vector to their corresponding
2245      * lane numbers, scaled by a given constant.
2246      *
2247      * This is a lane-wise unary operation which, for
2248      * each lane {@code N}, computes the scaled index value
2249      * {@code N*scale} and adds it to the value already
2250      * in lane {@code N} of the current vector.
2251      *
2252      * <p> The scale must not be so large, and the element size must
2253      * not be so small, that that there would be an overflow when
2254      * computing any of the {@code N*scale} or {@code VLENGTH*scale},
2255      * when the the result is represented using the vector
2256      * lane type {@code ETYPE}.
2257      *
2258      * <p>
2259      * The following pseudocode illustrates this behavior:
2260      * <pre>{@code
2261      * Vector<E> a = ...;
2262      * VectorSpecies<E> species = a.species();
2263      * ETYPE[] ar = a.toArray();
2264      * for (int i = 0; i < ar.length; i++) {
2265      *     long d = (long)i * scale;
2266      *     if (d != (ETYPE) d)  throw ...;
2267      *     ar[i] += (ETYPE) d;
2268      * }
2269      * long d = (long)ar.length * scale;
2270      * if (d != (ETYPE) d)  throw ...;
2271      * return EVector.fromArray(s, ar, 0);
2272      * }</pre>
2273      *
2274      * @param scale the number to multiply by each lane index
2275      *        {@code N}, typically {@code 1}
2276      * @return the result of incrementing each lane element by its
2277      *         corresponding lane index {@code N}, scaled by {@code scale}
2278      * @throws IllegalArgumentException
2279      *         if the values in the interval
2280      *         {@code [0..VLENGTH*scale]}
2281      *         are not representable by the {@code ETYPE}
2282      */
2283     public abstract Vector<E> addIndex(int scale);
2284 
2285     // Slicing segments of adjacent lanes
2286 
2287     /**
2288      * Slices a segment of adjacent lanes, starting at a given
2289      * {@code origin} lane in the current vector, and continuing (as
2290      * needed) into an immediately following vector.  The block of
2291      * {@code VLENGTH} lanes is extracted into its own vector and
2292      * returned.
2293      *
2294      * <p> This is a cross-lane operation that shifts lane elements
2295      * to the front, from the current vector and the second vector.
2296      * Both vectors can be viewed as a combined "background" of length
2297      * {@code 2*VLENGTH}, from which a slice is extracted.
2298      *
2299      * The lane numbered {@code N} in the output vector is copied
2300      * from lane {@code origin+N} of the input vector, if that
2301      * lane exists, else from lane {@code origin+N-VLENGTH} of
2302      * the second vector (which is guaranteed to exist).
2303      *
2304      * <p> The {@code origin} value must be in the inclusive range
2305      * {@code 0..VLENGTH}.  As limiting cases, {@code v.slice(0,w)}
2306      * and {@code v.slice(VLENGTH,w)} return {@code v} and {@code w},
2307      * respectively.
2308      *
2309      * @apiNote
2310      *
2311      * This method may be regarded as the inverse of
2312      * {@link #unslice(int,Vector,int) unslice()},
2313      * in that the sliced value could be unsliced back into its
2314      * original position in the two input vectors, without
2315      * disturbing unrelated elements, as in the following
2316      * pseudocode:
2317      * <pre>{@code
2318      * EVector slice = v1.slice(origin, v2);
2319      * EVector w1 = slice.unslice(origin, v1, 0);
2320      * EVector w2 = slice.unslice(origin, v2, 1);
2321      * assert v1.equals(w1);
2322      * assert v2.equals(w2);
2323      * }</pre>
2324      *
2325      * <p> This method also supports a variety of cross-lane shifts and
2326      * rotates as follows:
2327      * <ul>
2328      *
2329      * <li>To shift lanes forward to the front of the vector, supply a
2330      * zero vector for the second operand and specify the shift count
2331      * as the origin.  For example: {@code v.slice(shift, v.broadcast(0))}.
2332      *
2333      * <li>To shift lanes backward to the back of the vector, supply a
2334      * zero vector for the <em>first</em> operand, and specify the
2335      * negative shift count as the origin (modulo {@code VLENGTH}.
2336      * For example: {@code v.broadcast(0).slice(v.length()-shift, v)}.
2337      *
2338      * <li>To rotate lanes forward toward the front end of the vector,
2339      * cycling the earliest lanes around to the back, supply the same
2340      * vector for both operands and specify the rotate count as the
2341      * origin.  For example: {@code v.slice(rotate, v)}.
2342      *
2343      * <li>To rotate lanes backward toward the back end of the vector,
2344      * cycling the latest lanes around to the front, supply the same
2345      * vector for both operands and specify the negative of the rotate
2346      * count (modulo {@code VLENGTH}) as the origin.  For example:
2347      * {@code v.slice(v.length() - rotate, v)}.
2348      *
2349      * <li>
2350      * Since {@code origin} values less then zero or more than
2351      * {@code VLENGTH} will be rejected, if you need to rotate
2352      * by an unpredictable multiple of {@code VLENGTH}, be sure
2353      * to reduce the origin value into the required range.
2354      * The {@link VectorSpecies#loopBound(int) loopBound()}
2355      * method can help with this.  For example:
2356      * {@code v.slice(rotate - v.species().loopBound(rotate), v)}.
2357      *
2358      * </ul>
2359      *
2360      * @param origin the first input lane to transfer into the slice
2361      * @param v1 a second vector logically concatenated with the first,
2362      *        before the slice is taken (if omitted it defaults to zero)
2363      * @return a contiguous slice of {@code VLENGTH} lanes, taken from
2364      *         this vector starting at the indicated origin, and
2365      *         continuing (as needed) into the second vector
2366      * @throws ArrayIndexOutOfBoundsException if {@code origin}
2367      *         is negative or greater than {@code VLENGTH}
2368      * @see #slice(int,Vector,VectorMask)
2369      * @see #slice(int)
2370      * @see #unslice(int,Vector,int)
2371      */
2372     public abstract Vector<E> slice(int origin, Vector<E> v1);
2373 
2374     /**
2375      * Slices a segment of adjacent lanes
2376      * under the control of a mask,
2377      * starting at a given
2378      * {@code origin} lane in the current vector, and continuing (as
2379      * needed) into an immediately following vector.  The block of
2380      * {@code VLENGTH} lanes is extracted into its own vector and
2381      * returned.
2382      *
2383      * The resulting vector will be zero in all lanes unset in the
2384      * given mask.  Lanes set in the mask will contain data copied
2385      * from selected lanes of {@code this} or {@code v1}.
2386      *
2387      * <p> This is a cross-lane operation that shifts lane elements
2388      * to the front, from the current vector and the second vector.
2389      * Both vectors can be viewed as a combined "background" of length
2390      * {@code 2*VLENGTH}, from which a slice is extracted.
2391      *
2392      * The returned result is equal to the expression
2393      * {@code broadcast(0).blend(slice(origin,v1),m)}.
2394      *
2395      * @apiNote
2396      * This method may be regarded as the inverse of
2397      * {@code #unslice(int,Vector,int,VectorMask) unslice()},
2398      * in that the sliced value could be unsliced back into its
2399      * original position in the two input vectors, without
2400      * disturbing unrelated elements, as in the following
2401      * pseudocode:
2402      * <pre>{@code
2403      * EVector slice = v1.slice(origin, v2, m);
2404      * EVector w1 = slice.unslice(origin, v1, 0, m);
2405      * EVector w2 = slice.unslice(origin, v2, 1, m);
2406      * assert v1.equals(w1);
2407      * assert v2.equals(w2);
2408      * }</pre>
2409      *
2410      * @param origin the first input lane to transfer into the slice
2411      * @param v1 a second vector logically concatenated with the first,
2412      *        before the slice is taken (if omitted it defaults to zero)
2413      * @param m the mask controlling lane selection into the resulting vector
2414      * @return a contiguous slice of {@code VLENGTH} lanes, taken from
2415      *         this vector starting at the indicated origin, and
2416      *         continuing (as needed) into the second vector
2417      * @throws ArrayIndexOutOfBoundsException if {@code origin}
2418      *         is negative or greater than {@code VLENGTH}
2419      * @see #slice(int,Vector)
2420      * @see #unslice(int,Vector,int,VectorMask)
2421      */
2422     // This doesn't pull its weight, but its symmetrical with
2423     // masked unslice, and might cause questions if missing.
2424     // It could make for clearer code.
2425     public abstract Vector<E> slice(int origin, Vector<E> v1, VectorMask<E> m);
2426 
2427     /**
2428      * Slices a segment of adjacent lanes, starting at a given
2429      * {@code origin} lane in the current vector.  A block of
2430      * {@code VLENGTH} lanes, possibly padded with zero lanes, is
2431      * extracted into its own vector and returned.
2432      *
2433      * This is a convenience method which slices from a single
2434      * vector against an extended background of zero lanes.
2435      * It is equivalent to
2436      * {@link #slice(int,Vector) slice}{@code
2437      * (origin, }{@link #broadcast(long) broadcast}{@code (0))}.
2438      * It may also be viewed simply as a cross-lane shift
2439      * from later to earlier lanes, with zeroes filling
2440      * in the vacated lanes at the end of the vector.
2441      * In this view, the shift count is {@code origin}.
2442      *
2443      * @param origin the first input lane to transfer into the slice
2444      * @return the last {@code VLENGTH-origin} input lanes,
2445      *         placed starting in the first lane of the ouput,
2446      *         padded at the end with zeroes
2447      * @throws ArrayIndexOutOfBoundsException if {@code origin}
2448      *         is negative or greater than {@code VLENGTH}
2449      * @see #slice(int,Vector)
2450      * @see #unslice(int,Vector,int)
2451      */
2452     // This API point pulls its weight as a teaching aid,
2453     // though it's a one-off and broadcast(0) is easy.
2454     public abstract Vector<E> slice(int origin);
2455 
2456     /**
2457      * Reverses a {@linkplain #slice(int,Vector) slice()}, inserting
2458      * the current vector as a slice within another "background" input
2459      * vector, which is regarded as one or the other input to a
2460      * hypothetical subsequent {@code slice()} operation.
2461      *
2462      * <p> This is a cross-lane operation that permutes the lane
2463      * elements of the current vector toward the back and inserts them
2464      * into a logical pair of background vectors.  Only one of the
2465      * pair will be returned, however.  The background is formed by
2466      * duplicating the second input vector.  (However, the output will
2467      * never contain two duplicates from the same input lane.)
2468      *
2469      * The lane numbered {@code N} in the input vector is copied into
2470      * lane {@code origin+N} of the first background vector, if that
2471      * lane exists, else into lane {@code origin+N-VLENGTH} of the
2472      * second background vector (which is guaranteed to exist).
2473      *
2474      * The first or second background vector, updated with the
2475      * inserted slice, is returned.  The {@code part} number of zero
2476      * or one selects the first or second updated background vector.
2477      *
2478      * <p> The {@code origin} value must be in the inclusive range
2479      * {@code 0..VLENGTH}.  As limiting cases, {@code v.unslice(0,w,0)}
2480      * and {@code v.unslice(VLENGTH,w,1)} both return {@code v}, while
2481      * {@code v.unslice(0,w,1)} and {@code v.unslice(VLENGTH,w,0)}
2482      * both return {@code w}.
2483      *
2484      * @apiNote
2485      * This method supports a variety of cross-lane insertion
2486      * operations as follows:
2487      * <ul>
2488      *
2489      * <li>To insert near the end of a background vector {@code w}
2490      * at some offset, specify the offset as the origin and
2491      * select part zero. For example: {@code v.unslice(offset, w, 0)}.
2492      *
2493      * <li>To insert near the end of a background vector {@code w},
2494      * but capturing the overflow into the next vector {@code x},
2495      * specify the offset as the origin and select part one.
2496      * For example: {@code v.unslice(offset, x, 1)}.
2497      *
2498      * <li>To insert the last {@code N} items near the beginning
2499      * of a background vector {@code w}, supply a {@code VLENGTH-N}
2500      * as the origin and select part one.
2501      * For example: {@code v.unslice(v.length()-N, w)}.
2502      *
2503      * </ul>
2504      *
2505      * @param origin the first output lane to receive the slice
2506      * @param w the background vector that (as two copies) will receive
2507      *        the inserted slice
2508      * @param part the part number of the result (either zero or one)
2509      * @return either the first or second part of a pair of
2510      *         background vectors {@code w}, updated by inserting
2511      *         this vector at the indicated origin
2512      * @throws ArrayIndexOutOfBoundsException if {@code origin}
2513      *         is negative or greater than {@code VLENGTH},
2514      *         or if {@code part} is not zero or one
2515      * @see #slice(int,Vector)
2516      * @see #unslice(int,Vector,int,VectorMask)
2517      */
2518     public abstract Vector<E> unslice(int origin, Vector<E> w, int part);
2519 
2520     /**
2521      * Reverses a {@linkplain #slice(int,Vector) slice()}, inserting
2522      * (under the control of a mask)
2523      * the current vector as a slice within another "background" input
2524      * vector, which is regarded as one or the other input to a
2525      * hypothetical subsequent {@code slice()} operation.
2526      *
2527      * <p> This is a cross-lane operation that permutes the lane
2528      * elements of the current vector forward and inserts its lanes
2529      * (when selected by the mask) into a logical pair of background
2530      * vectors.  As with the
2531      * {@linkplain #unslice(int,Vector,int) unmasked version} of this method,
2532      * only one of the pair will be returned, as selected by the
2533      * {@code part} number.
2534      *
2535      * For each lane {@code N} selected by the mask, the lane value
2536      * is copied into
2537      * lane {@code origin+N} of the first background vector, if that
2538      * lane exists, else into lane {@code origin+N-VLENGTH} of the
2539      * second background vector (which is guaranteed to exist).
2540      * Background lanes retain their original values if the
2541      * corresponding input lanes {@code N} are unset in the mask.
2542      *
2543      * The first or second background vector, updated with set lanes
2544      * of the inserted slice, is returned.  The {@code part} number of
2545      * zero or one selects the first or second updated background
2546      * vector.
2547      *
2548      * @param origin the first output lane to receive the slice
2549      * @param w the background vector that (as two copies) will receive
2550      *        the inserted slice, if they are set in {@code m}
2551      * @param part the part number of the result (either zero or one)
2552      * @param m the mask controlling lane selection from the current vector
2553      * @return either the first or second part of a pair of
2554      *         background vectors {@code w}, updated by inserting
2555      *         selected lanes of this vector at the indicated origin
2556      * @throws ArrayIndexOutOfBoundsException if {@code origin}
2557      *         is negative or greater than {@code VLENGTH},
2558      *         or if {@code part} is not zero or one
2559      * @see #unslice(int,Vector,int)
2560      * @see #slice(int,Vector)
2561      */
2562     public abstract Vector<E> unslice(int origin, Vector<E> w, int part, VectorMask<E> m);
2563 
2564     /**
2565      * Reverses a {@linkplain #slice(int) slice()}, inserting
2566      * the current vector as a slice within a "background" input
2567      * of zero lane values.  Compared to other {@code unslice()}
2568      * methods, this method only returns the first of the
2569      * pair of background vectors.
2570      *
2571      * This is a convenience method which returns the result of
2572      * {@link #unslice(int,Vector,int) unslice}{@code
2573      * (origin, }{@link #broadcast(long) broadcast}{@code (0), 0)}.
2574      * It may also be viewed simply as a cross-lane shift
2575      * from earlier to later lanes, with zeroes filling
2576      * in the vacated lanes at the beginning of the vector.
2577      * In this view, the shift count is {@code origin}.
2578      *
2579      * @param origin the first output lane to receive the slice
2580      * @return the first {@code VLENGTH-origin} input lanes,
2581      *         placed starting at the given origin,
2582      *         padded at the beginning with zeroes
2583      * @throws ArrayIndexOutOfBoundsException if {@code origin}
2584      *         is negative or greater than {@code VLENGTH}
2585      * @see #unslice(int,Vector,int)
2586      * @see #slice(int)
2587      */
2588     // This API point pulls its weight as a teaching aid,
2589     // though it's a one-off and broadcast(0) is easy.
2590     public abstract Vector<E> unslice(int origin);
2591 
2592     // ISSUE: Add a slice which uses a mask instead of an origin?
2593     //public abstract Vector<E> slice(VectorMask<E> support);
2594 
2595     // ISSUE: Add some more options for questionable edge conditions?
2596     // We might define enum EdgeOption { ERROR, ZERO, WRAP } for the
2597     // default of throwing AIOOBE, or substituting zeroes, or just
2598     // reducing the out-of-bounds index modulo VLENGTH.  Similar
2599     // concerns also apply to general Shuffle operations.  For now,
2600     // just support ERROR, since that is safest.
2601 
2602     /**
2603      * Rearranges the lane elements of this vector, selecting lanes
2604      * under the control of a specific shuffle.
2605      *
2606      * This is a cross-lane operation that rearranges the lane
2607      * elements of this vector.
2608      *
2609      * For each lane {@code N} of the shuffle, and for each lane
2610      * source index {@code I=s.laneSource(N)} in the shuffle,
2611      * the output lane {@code N} obtains the value from
2612      * the input vector at lane {@code I}.
2613      *
2614      * @param s the shuffle controlling lane index selection
2615      * @return the rearrangement of the lane elements of this vector
2616      * @throws IndexOutOfBoundsException if there are any exceptional
2617      *        source indexes in the shuffle
2618      * @see #rearrange(VectorShuffle,VectorMask)
2619      * @see #rearrange(VectorShuffle,Vector)
2620      * @see VectorShuffle#laneIsValid()
2621      */
2622     public abstract Vector<E> rearrange(VectorShuffle<E> s);
2623 
2624     /**
2625      * Rearranges the lane elements of this vector, selecting lanes
2626      * under the control of a specific shuffle and a mask.
2627      *
2628      * This is a cross-lane operation that rearranges the lane
2629      * elements of this vector.
2630      *
2631      * For each lane {@code N} of the shuffle, and for each lane
2632      * source index {@code I=s.laneSource(N)} in the shuffle,
2633      * the output lane {@code N} obtains the value from
2634      * the input vector at lane {@code I} if the mask is set.
2635      * Otherwise the output lane {@code N} is set to zero.
2636      *
2637      * <p> This method returns the value of this pseudocode:
2638      * <pre>{@code
2639      * Vector<E> r = this.rearrange(s.wrapIndexes());
2640      * VectorMask<E> valid = s.laneIsValid();
2641      * if (m.andNot(valid).anyTrue()) throw ...;
2642      * return broadcast(0).blend(r, m);
2643      * }</pre>
2644      *
2645      * @param s the shuffle controlling lane index selection
2646      * @param m the mask controlling application of the shuffle
2647      * @return the rearrangement of the lane elements of this vector
2648      * @throws IndexOutOfBoundsException if there are any exceptional
2649      *        source indexes in the shuffle where the mask is set
2650      * @see #rearrange(VectorShuffle)
2651      * @see #rearrange(VectorShuffle,Vector)
2652      * @see VectorShuffle#laneIsValid()
2653      */
2654     public abstract Vector<E> rearrange(VectorShuffle<E> s, VectorMask<E> m);
2655 
2656     /**
2657      * Rearranges the lane elements of two vectors, selecting lanes
2658      * under the control of a specific shuffle, using both normal and
2659      * exceptional indexes in the shuffle to steer data.
2660      *
2661      * This is a cross-lane operation that rearranges the lane
2662      * elements of the two input vectors (the current vector
2663      * and a second vector {@code v}).
2664      *
2665      * For each lane {@code N} of the shuffle, and for each lane
2666      * source index {@code I=s.laneSource(N)} in the shuffle,
2667      * the output lane {@code N} obtains the value from
2668      * the first vector at lane {@code I} if {@code I>=0}.
2669      * Otherwise, the exceptional index {@code I} is wrapped
2670      * by adding {@code VLENGTH} to it and used to index
2671      * the <em>second</em> vector, at index {@code I+VLENGTH}.
2672      *
2673      * <p> This method returns the value of this pseudocode:
2674      * <pre>{@code
2675      * Vector<E> r1 = this.rearrange(s.wrapIndexes());
2676      * // or else: r1 = this.rearrange(s, s.laneIsValid());
2677      * Vector<E> r2 = v.rearrange(s.wrapIndexes());
2678      * return r2.blend(r1,s.laneIsValid());
2679      * }</pre>
2680      *
2681      * @param s the shuffle controlling lane selection from both input vectors
2682      * @param v the second input vector
2683      * @return the rearrangement of lane elements of this vector and
2684      *         a second input vector
2685      * @see #rearrange(VectorShuffle)
2686      * @see #rearrange(VectorShuffle,VectorMask)
2687      * @see VectorShuffle#laneIsValid()
2688      * @see #slice(int,Vector)
2689      */
2690     public abstract Vector<E> rearrange(VectorShuffle<E> s, Vector<E> v);
2691 
2692     /**
2693      * Using index values stored in the lanes of this vector,
2694      * assemble values stored in second vector {@code v}.
2695      * The second vector thus serves as a table, whose
2696      * elements are selected by indexes in the current vector.
2697      *
2698      * This is a cross-lane operation that rearranges the lane
2699      * elements of the argument vector, under the control of
2700      * this vector.
2701      *
2702      * For each lane {@code N} of this vector, and for each lane
2703      * value {@code I=this.lane(N)} in this vector,
2704      * the output lane {@code N} obtains the value from
2705      * the argument vector at lane {@code I}.
2706      *
2707      * In this way, the result contains only values stored in the
2708      * argument vector {@code v}, but presented in an order which
2709      * depends on the index values in {@code this}.
2710      *
2711      * The result is the same as the expression
2712      * {@code v.rearrange(this.toShuffle())}.
2713      *
2714      * @param v the vector supplying the result values
2715      * @return the rearrangement of the lane elements of {@code v}
2716      * @throws IndexOutOfBoundsException if any invalid
2717      *         source indexes are found in {@code this}
2718      * @see #rearrange(VectorShuffle)
2719      */
2720     public abstract Vector<E> selectFrom(Vector<E> v);
2721 
2722     /**
2723      * Using index values stored in the lanes of this vector,
2724      * assemble values stored in second vector, under the control
2725      * of a mask.
2726      * Using index values stored in the lanes of this vector,
2727      * assemble values stored in second vector {@code v}.
2728      * The second vector thus serves as a table, whose
2729      * elements are selected by indexes in the current vector.
2730      * Lanes that are unset in the mask receive a
2731      * zero rather than a value from the table.
2732      *
2733      * This is a cross-lane operation that rearranges the lane
2734      * elements of the argument vector, under the control of
2735      * this vector and the mask.
2736      *
2737      * The result is the same as the expression
2738      * {@code v.rearrange(this.toShuffle(), m)}.
2739      *
2740      * @param v the vector supplying the result values
2741      * @param m the mask controlling selection from {@code v}
2742      * @return the rearrangement of the lane elements of {@code v}
2743      * @throws IndexOutOfBoundsException if any invalid
2744      *         source indexes are found in {@code this},
2745      *         in a lane which is set in the mask
2746      * @see #selectFrom(Vector)
2747      * @see #rearrange(VectorShuffle,VectorMask)
2748      */
2749     public abstract Vector<E> selectFrom(Vector<E> v, VectorMask<E> m);
2750 
2751     // Conversions
2752 
2753     /**
2754      * Returns a vector of the same species as this one
2755      * where all lane elements are set to
2756      * the primitive value {@code e}.
2757      *
2758      * The contents of the current vector are discarded;
2759      * only the species is relevant to this operation.
2760      *
2761      * <p> This method returns the value of this expression:
2762      * {@code EVector.broadcast(this.species(), (ETYPE)e)}, where
2763      * {@code EVector} is the vector class specific to this
2764      * vector's element type {@code ETYPE}.
2765      *
2766      * <p>
2767      * The {@code long} value {@code e} must be accurately
2768      * representable by the {@code ETYPE} of this vector's species,
2769      * so that {@code e==(long)(ETYPE)e}.
2770      *
2771      * If this rule is violated the problem is not detected
2772      * statically, but an {@code IllegalArgumentException} is thrown
2773      * at run-time.  Thus, this method somewhat weakens the static
2774      * type checking of immediate constants and other scalars, but it
2775      * makes up for this by improving the expressiveness of the
2776      * generic API.  Note that an {@code e} value in the range
2777      * {@code [-128..127]} is always acceptable, since every
2778      * {@code ETYPE} will accept every {@code byte} value.
2779      *
2780      * @apiNote
2781      * Subtypes improve on this method by sharpening
2782      * the method return type and
2783      * and the type of the scalar parameter {@code e}.
2784      *
2785      * @param e the value to broadcast
2786      * @return a vector where all lane elements are set to
2787      *         the primitive value {@code e}
2788      * @throws IllegalArgumentException
2789      *         if the given {@code long} value cannot
2790      *         be represented by the vector's {@code ETYPE}
2791      * @see VectorSpecies#broadcast(long)
2792      * @see IntVector#broadcast(int)
2793      * @see FloatVector#broadcast(float)
2794      */
2795     public abstract Vector<E> broadcast(long e);
2796 
2797     /**
2798      * Returns a mask of same species as this vector,
2799      * where each lane is set or unset according to given
2800      * single boolean, which is broadcast to all lanes.
2801      * <p>
2802      * This method returns the value of this expression:
2803      * {@code species().maskAll(bit)}.
2804      *
2805      * @param bit the given mask bit to be replicated
2806      * @return a mask where each lane is set or unset according to
2807      *         the given bit
2808      * @see VectorSpecies#maskAll(boolean)
2809      */
2810     public abstract VectorMask<E> maskAll(boolean bit);
2811 
2812     /**
2813      * Converts this vector into a shuffle, converting the lane values
2814      * to {@code int} and regarding them as source indexes.
2815      * <p>
2816      * This method behaves as if it returns the result of creating a shuffle
2817      * given an array of the vector elements, as follows:
2818      * <pre>{@code
2819      * long[] a = this.toLongArray();
2820      * int[] sa = new int[a.length];
2821      * for (int i = 0; i < a.length; i++) {
2822      *     sa[i] = (int) a[i];
2823      * }
2824      * return VectorShuffle.fromValues(this.species(), sa);
2825      * }</pre>
2826      *
2827      * @return a shuffle representation of this vector
2828      * @see VectorShuffle#fromValues(VectorSpecies,int...)
2829      */
2830     public abstract VectorShuffle<E> toShuffle();
2831 
2832     // Bitwise preserving
2833 
2834     /**
2835      * Transforms this vector to a vector of the given species of
2836      * element type {@code F}, reinterpreting the bytes of this
2837      * vector without performing any value conversions.
2838      *
2839      * <p> Depending on the selected species, this operation may
2840      * either <a href="Vector.html#expansion">expand or contract</a>
2841      * its logical result, in which case a non-zero {@code part}
2842      * number can further control the selection and steering of the
2843      * logical result into the physical output vector.
2844      *
2845      * <p>
2846      * The underlying bits of this vector are copied to the resulting
2847      * vector without modification, but those bits, before copying,
2848      * may be truncated if the this vector's bit-size is greater than
2849      * desired vector's bit size, or filled with zero bits if this
2850      * vector's bit-size is less than desired vector's bit-size.
2851      *
2852      * <p> If the old and new species have different shape, this is a
2853      * <em>shape-changing</em> operation, and may have special
2854      * implementation costs.
2855      *
2856      * <p> The method behaves as if this vector is stored into a byte
2857      * buffer or array using little-endian byte ordering and then the
2858      * desired vector is loaded from the same byte buffer or array
2859      * using the same ordering.
2860      *
2861      * <p> The following pseudocode illustrates the behavior:
2862      * <pre>{@code
2863      * int domSize = this.byteSize();
2864      * int ranSize = species.vectorByteSize();
2865      * int M = (domSize > ranSize ? domSize / ranSize : ranSize / domSize);
2866      * assert Math.abs(part) < M;
2867      * assert (part == 0) || (part > 0) == (domSize > ranSize);
2868      * byte[] ra = new byte[Math.max(domSize, ranSize)];
2869      * if (domSize > ranSize) {  // expansion
2870      *     this.intoByteArray(ra, 0, ByteOrder.native());
2871      *     int origin = part * ranSize;
2872      *     return species.fromByteArray(ra, origin, ByteOrder.native());
2873      * } else {  // contraction or size-invariant
2874      *     int origin = (-part) * domSize;
2875      *     this.intoByteArray(ra, origin, ByteOrder.native());
2876      *     return species.fromByteArray(ra, 0, ByteOrder.native());
2877      * }
2878      * }</pre>
2879      *
2880      * @apiNote Although this method is defined as if the vectors in
2881      * question were loaded or stored into memory, memory semantics
2882      * has little to do or nothing with the actual implementation.
2883      * The appeal to little-endian ordering is simply a shorthand
2884      * for what could otherwise be a large number of detailed rules
2885      * concerning the mapping between lane-structured vectors and
2886      * byte-structured vectors.
2887      *
2888      * @param species the desired vector species
2889      * @param part the <a href="Vector.html#expansion">part number</a>
2890      *        of the result, or zero if neither expanding nor contracting
2891      * @param <F> the boxed element type of the species
2892      * @return a vector transformed, by shape and element type, from this vector
2893      * @see Vector#convertShape(VectorOperators.Conversion,VectorSpecies,int)
2894      * @see Vector#castShape(VectorSpecies,int)
2895      * @see VectorSpecies#partLimit(VectorSpecies,boolean)
2896      */
2897     public abstract <F> Vector<F> reinterpretShape(VectorSpecies<F> species, int part);
2898 
2899     /**
2900      * Views this vector as a vector of the same shape
2901      * and contents but a lane type of {@code byte},
2902      * where the bytes are extracted from the lanes
2903      * according to little-endian order.
2904      * It is a convenience method for the expression
2905      * {@code reinterpretShape(species().withLanes(byte.class))}.
2906      * It may be considered an inverse to the various
2907      * methods which consolidate bytes into larger lanes
2908      * within the same vector, such as
2909      * {@link Vector#reinterpretAsInts()}.
2910      *
2911      * @return a {@code ByteVector} with the same shape and information content
2912      * @see Vector#reinterpretShape(VectorSpecies,int)
2913      * @see IntVector#intoByteArray(byte[], int, ByteOrder)
2914      * @see FloatVector#intoByteArray(byte[], int, ByteOrder)
2915      * @see VectorSpecies#withLanes(Class)
2916      */
2917     public abstract ByteVector reinterpretAsBytes();
2918 
2919     /**
2920      * Reinterprets this vector as a vector of the same shape
2921      * and contents but a lane type of {@code short},
2922      * where the lanes are assembled from successive bytes
2923      * according to little-endian order.
2924      * It is a convenience method for the expression
2925      * {@code reinterpretShape(species().withLanes(short.class))}.
2926      * It may be considered an inverse to {@link Vector#reinterpretAsBytes()}.
2927      *
2928      * @return a {@code ShortVector} with the same shape and information content
2929      */
2930     public abstract ShortVector reinterpretAsShorts();
2931 
2932     /**
2933      * Reinterprets this vector as a vector of the same shape
2934      * and contents but a lane type of {@code int},
2935      * where the lanes are assembled from successive bytes
2936      * according to little-endian order.
2937      * It is a convenience method for the expression
2938      * {@code reinterpretShape(species().withLanes(int.class))}.
2939      * It may be considered an inverse to {@link Vector#reinterpretAsBytes()}.
2940      *
2941      * @return a {@code IntVector} with the same shape and information content
2942      */
2943     public abstract IntVector reinterpretAsInts();
2944 
2945     /**
2946      * Reinterprets this vector as a vector of the same shape
2947      * and contents but a lane type of {@code long},
2948      * where the lanes are assembled from successive bytes
2949      * according to little-endian order.
2950      * It is a convenience method for the expression
2951      * {@code reinterpretShape(species().withLanes(long.class))}.
2952      * It may be considered an inverse to {@link Vector#reinterpretAsBytes()}.
2953      *
2954      * @return a {@code LongVector} with the same shape and information content
2955      */
2956     public abstract LongVector reinterpretAsLongs();
2957 
2958     /**
2959      * Reinterprets this vector as a vector of the same shape
2960      * and contents but a lane type of {@code float},
2961      * where the lanes are assembled from successive bytes
2962      * according to little-endian order.
2963      * It is a convenience method for the expression
2964      * {@code reinterpretShape(species().withLanes(float.class))}.
2965      * It may be considered an inverse to {@link Vector#reinterpretAsBytes()}.
2966      *
2967      * @return a {@code FloatVector} with the same shape and information content
2968      */
2969     public abstract FloatVector reinterpretAsFloats();
2970 
2971     /**
2972      * Reinterprets this vector as a vector of the same shape
2973      * and contents but a lane type of {@code double},
2974      * where the lanes are assembled from successive bytes
2975      * according to little-endian order.
2976      * It is a convenience method for the expression
2977      * {@code reinterpretShape(species().withLanes(double.class))}.
2978      * It may be considered an inverse to {@link Vector#reinterpretAsBytes()}.
2979      *
2980      * @return a {@code DoubleVector} with the same shape and information content
2981      */
2982     public abstract DoubleVector reinterpretAsDoubles();
2983 
2984     /**
2985      * Views this vector as a vector of the same shape, length, and
2986      * contents, but a lane type that is not a floating-point type.
2987      *
2988      * This is a lane-wise reinterpretation cast on the lane values.
2989      * As such, this method does not change {@code VSHAPE} or
2990      * {@code VLENGTH}, and there is no change to the bitwise contents
2991      * of the vector.  If the vector's {@code ETYPE} is already an
2992      * integral type, the same vector is returned unchanged.
2993      *
2994      * This method returns the value of this expression:
2995      * {@code convert(conv,0)}, where {@code conv} is
2996      * {@code VectorOperators.Conversion.ofReinterpret(E.class,F.class)},
2997      * and {@code F} is the non-floating-point type of the
2998      * same size as {@code E}.
2999      *
3000      * @apiNote
3001      * Subtypes improve on this method by sharpening
3002      * the return type.
3003      *
3004      * @return the original vector, reinterpreted as non-floating point
3005      * @see VectorOperators.Conversion#ofReinterpret(Class,Class)
3006      * @see Vector#convert(VectorOperators.Conversion,int)
3007      */
3008     public abstract Vector<?> viewAsIntegralLanes();
3009 
3010     /**
3011      * Views this vector as a vector of the same shape, length, and
3012      * contents, but a lane type that is a floating-point type.
3013      *
3014      * This is a lane-wise reinterpretation cast on the lane values.
3015      * As such, there this method does not change {@code VSHAPE} or
3016      * {@code VLENGTH}, and there is no change to the bitwise contents
3017      * of the vector.  If the vector's {@code ETYPE} is already a
3018      * float-point type, the same vector is returned unchanged.
3019      *
3020      * If the vector's element size does not match any floating point
3021      * type size, an {@code IllegalArgumentException} is thrown.
3022      *
3023      * This method returns the value of this expression:
3024      * {@code convert(conv,0)}, where {@code conv} is
3025      * {@code VectorOperators.Conversion.ofReinterpret(E.class,F.class)},
3026      * and {@code F} is the floating-point type of the
3027      * same size as {@code E}, if any.
3028      *
3029      * @apiNote
3030      * Subtypes improve on this method by sharpening
3031      * the return type.
3032      *
3033      * @return the original vector, reinterpreted as floating point
3034      * @throws UnsupportedOperationException if there is no floating point
3035      *         type the same size as the lanes of this vector
3036      * @see VectorOperators.Conversion#ofReinterpret(Class,Class)
3037      * @see Vector#convert(VectorOperators.Conversion,int)
3038      */
3039     public abstract Vector<?> viewAsFloatingLanes();
3040 
3041     /**
3042      * Convert this vector to a vector of the same shape and a new
3043      * element type, converting lane values from the current {@code ETYPE}
3044      * to a new lane type (called {@code FTYPE} here) according to the
3045      * indicated {@linkplain VectorOperators.Conversion conversion}.
3046      *
3047      * This is a lane-wise shape-invariant operation which copies
3048      * {@code ETYPE} values from the input vector to corresponding
3049      * {@code FTYPE} values in the result.  Depending on the selected
3050      * conversion, this operation may either
3051      * <a href="Vector.html#expansion">expand or contract</a> its
3052      * logical result, in which case a non-zero {@code part} number
3053      * can further control the selection and steering of the logical
3054      * result into the physical output vector.
3055      *
3056      * <p> Each specific conversion is described by a conversion
3057      * constant in the class {@link VectorOperators}.  Each conversion
3058      * operator has a specified {@linkplain
3059      * VectorOperators.Conversion#domainType() domain type} and
3060      * {@linkplain VectorOperators.Conversion#rangeType() range type}.
3061      * The domain type must exactly match the lane type of the input
3062      * vector, while the range type determines the lane type of the
3063      * output vectors.
3064      *
3065      * <p> A conversion operator may be classified as (respectively)
3066      * in-place, expanding, or contracting, depending on whether the
3067      * bit-size of its domain type is (respectively) equal, less than,
3068      * or greater than the bit-size of its range type.
3069      *
3070      * <p> Independently, conversion operations can also be classified
3071      * as reinterpreting or value-transforming, depending on whether
3072      * the conversion copies representation bits unchanged, or changes
3073      * the representation bits in order to retain (part or all of)
3074      * the logical value of the input value.
3075      *
3076      * <p> If a reinterpreting conversion contracts, it will truncate the
3077      * upper bits of the input.  If it expands, it will pad upper bits
3078      * of the output with zero bits, when there are no corresponding
3079      * input bits.
3080      *
3081      * <p> An expanding conversion such as {@code S2I} ({@code short}
3082      * value to {@code int}) takes a scalar value and represents it
3083      * in a larger format (always with some information redundancy).
3084      *
3085      * A contracting conversion such as {@code D2F} ({@code double}
3086      * value to {@code float}) takes a scalar value and represents it
3087      * in a smaller format (always with some information loss).
3088      *
3089      * Some in-place conversions may also include information loss,
3090      * such as {@code L2D} ({@code long} value to {@code double})
3091      * or {@code F2I}  ({@code float} value to {@code int}).
3092      *
3093      * Reinterpreting in-place conversions are not lossy, unless the
3094      * bitwise value is somehow not legal in the output type.
3095      * Converting the bit-pattern of a {@code NaN} may discard bits
3096      * from the {@code NaN}'s significand.
3097      *
3098      * <p> This classification is important, because, unless otherwise
3099      * documented, conversion operations <em>never change vector
3100      * shape</em>, regardless of how they may change <em>lane sizes</em>.
3101      *
3102      * Therefore an <em>expanding</em> conversion cannot store all of its
3103      * results in its output vector, because the output vector has fewer
3104      * lanes of larger size, in order to have the same overall bit-size as
3105      * its input.
3106      *
3107      * Likewise, a contracting conversion must store its relatively small
3108      * results into a subset of the lanes of the output vector, defaulting
3109      * the unused lanes to zero.
3110      *
3111      * <p> As an example, a conversion from {@code byte} to {@code long}
3112      * ({@code M=8}) will discard 87.5% of the input values in order to
3113      * convert the remaining 12.5% into the roomy {@code long} lanes of
3114      * the output vector. The inverse conversion will convert back all of
3115      * the large results, but will waste 87.5% of the lanes in the output
3116      * vector.
3117      *
3118      * <em>In-place</em> conversions ({@code M=1}) deliver all of
3119      * their results in one output vector, without wasting lanes.
3120      *
3121      * <p> To manage the details of these
3122      * <a href="Vector.html#expansion">expansions and contractions</a>,
3123      * a non-zero {@code part} parameter selects partial results from
3124      * expansions, or steers the results of contractions into
3125      * corresponding locations, as follows:
3126      *
3127      * <ul>
3128      * <li> expanding by {@code M}: {@code part} must be in the range
3129      * {@code [0..M-1]}, and selects the block of {@code VLENGTH/M} input
3130      * lanes starting at the <em>origin lane</em> at {@code part*VLENGTH/M}.
3131 
3132      * <p> The {@code VLENGTH/M} output lanes represent a partial
3133      * slice of the whole logical result of the conversion, filling
3134      * the entire physical output vector.
3135      *
3136      * <li> contracting by {@code M}: {@code part} must be in the range
3137      * {@code [-M+1..0]}, and steers all {@code VLENGTH} input lanes into
3138      * the output located at the <em>origin lane</em> {@code -part*VLENGTH}.
3139      * There is a total of {@code VLENGTH*M} output lanes, and those not
3140      * holding converted input values are filled with zeroes.
3141      *
3142      * <p> A group of such output vectors, with logical result parts
3143      * steered to disjoint blocks, can be reassembled using the
3144      * {@linkplain VectorOperators#OR bitwise or} or (for floating
3145      * point) the {@link VectorOperators#FIRST_NONZERO FIRST_NONZERO}
3146      * operator.
3147      *
3148      * <li> in-place ({@code M=1}): {@code part} must be zero.
3149      * Both vectors have the same {@code VLENGTH}.  The result is
3150      * always positioned at the <em>origin lane</em> of zero.
3151      *
3152      * </ul>
3153      *
3154      * <p> This method is a restricted version of the more general
3155      * but less frequently used <em>shape-changing</em> method
3156      * {@link #convertShape(VectorOperators.Conversion,VectorSpecies,int)
3157      * convertShape()}.
3158      * The result of this method is the same as the expression
3159      * {@code this.convertShape(conv, rsp, this.broadcast(part))},
3160      * where the output species is
3161      * {@code rsp=this.species().withLanes(FTYPE.class)}.
3162      *
3163      * @param conv the desired scalar conversion to apply lane-wise
3164      * @param part the <a href="Vector.html#expansion">part number</a>
3165      *        of the result, or zero if neither expanding nor contracting
3166      * @param <F> the boxed element type of the species
3167      * @return a vector converted by shape and element type from this vector
3168      * @throws ArrayIndexOutOfBoundsException unless {@code part} is zero,
3169      *         or else the expansion ratio is {@code M} and
3170      *         {@code part} is positive and less than {@code M},
3171      *         or else the contraction ratio is {@code M} and
3172      *         {@code part} is negative and greater {@code -M}
3173      *
3174      * @see VectorOperators#I2L
3175      * @see VectorOperators.Conversion#ofCast(Class,Class)
3176      * @see VectorSpecies#partLimit(VectorSpecies,boolean)
3177      * @see #viewAsFloatingLanes()
3178      * @see #viewAsIntegralLanes()
3179      * @see #convertShape(VectorOperators.Conversion,VectorSpecies,int)
3180      * @see #reinterpretShape(VectorSpecies,int)
3181      */
3182     public abstract <F> Vector<F> convert(VectorOperators.Conversion<E,F> conv, int part);
3183 
3184     /**
3185      * Converts this vector to a vector of the given species, shape and
3186      * element type, converting lane values from the current {@code ETYPE}
3187      * to a new lane type (called {@code FTYPE} here) according to the
3188      * indicated {@linkplain VectorOperators.Conversion conversion}.
3189      *
3190      * This is a lane-wise operation which copies {@code ETYPE} values
3191      * from the input vector to corresponding {@code FTYPE} values in
3192      * the result.
3193      *
3194      * <p> If the old and new species have the same shape, the behavior
3195      * is exactly the same as the simpler, shape-invariant method
3196      * {@link #convert(VectorOperators.Conversion,int) convert()}.
3197      * In such cases, the simpler method {@code convert()} should be
3198      * used, to make code easier to reason about.
3199      * Otherwise, this is a <em>shape-changing</em> operation, and may
3200      * have special implementation costs.
3201      *
3202      * <p> As a combined effect of shape changes and lane size changes,
3203      * the input and output species may have different lane counts, causing
3204      * <a href="Vector.html#expansion">expansion or contraction</a>.
3205      * In this case a non-zero {@code part} parameter selects
3206      * partial results from an expanded logical result, or steers
3207      * the results of a contracted logical result into a physical
3208      * output vector of the required output species.
3209      *
3210      * <p >The following pseudocode illustrates the behavior of this
3211      * method for in-place, expanding, and contracting conversions.
3212      * (This pseudocode also applies to the shape-invariant method,
3213      * but with shape restrictions on the output species.)
3214      * Note that only one of the three code paths is relevant to any
3215      * particular combination of conversion operator and shapes.
3216      *
3217      * <pre>{@code
3218      * FTYPE scalar_conversion_op(ETYPE s);
3219      * EVector a = ...;
3220      * VectorSpecies<F> rsp = ...;
3221      * int part = ...;
3222      * VectorSpecies<E> dsp = a.species();
3223      * int domlen = dsp.length();
3224      * int ranlen = rsp.length();
3225      * FTYPE[] logical = new FTYPE[domlen];
3226      * for (int i = 0; i < domlen; i++) {
3227      *   logical[i] = scalar_conversion_op(a.lane(i));
3228      * }
3229      * FTYPE[] physical;
3230      * if (domlen == ranlen) { // in-place
3231      *     assert part == 0; //else AIOOBE
3232      *     physical = logical;
3233      * } else if (domlen > ranlen) { // expanding
3234      *     int M = domlen / ranlen;
3235      *     assert 0 <= part && part < M; //else AIOOBE
3236      *     int origin = part * ranlen;
3237      *     physical = Arrays.copyOfRange(logical, origin, origin + ranlen);
3238      * } else { // (domlen < ranlen) // contracting
3239      *     int M = ranlen / domlen;
3240      *     assert 0 >= part && part > -M; //else AIOOBE
3241      *     int origin = -part * domlen;
3242      *     System.arraycopy(logical, 0, physical, origin, domlen);
3243      * }
3244      * return FVector.fromArray(ran, physical, 0);
3245      * }</pre>
3246      *
3247      * @param conv the desired scalar conversion to apply lane-wise
3248      * @param rsp the desired output species
3249      * @param part the <a href="Vector.html#expansion">part number</a>
3250      *        of the result, or zero if neither expanding nor contracting
3251      * @param <F> the boxed element type of the output species
3252      * @return a vector converted by element type from this vector
3253      * @see #convert(VectorOperators.Conversion,int)
3254      * @see #castShape(VectorSpecies,int)
3255      * @see #reinterpretShape(VectorSpecies,int)
3256      */
3257     public abstract <F> Vector<F> convertShape(VectorOperators.Conversion<E,F> conv, VectorSpecies<F> rsp, int part);
3258 
3259     /**
3260      * Convenience method for converting a vector from one lane type
3261      * to another, reshaping as needed when lane sizes change.
3262      *
3263      * This method returns the value of this expression:
3264      * {@code convertShape(conv,rsp,part)}, where {@code conv} is
3265      * {@code VectorOperators.Conversion.ofCast(E.class,F.class)}.
3266      *
3267      * <p> If the old and new species have different shape, this is a
3268      * <em>shape-changing</em> operation, and may have special
3269      * implementation costs.
3270      *
3271      * @param rsp the desired output species
3272      * @param part the <a href="Vector.html#expansion">part number</a>
3273      *        of the result, or zero if neither expanding nor contracting
3274      * @param <F> the boxed element type of the output species
3275      * @return a vector converted by element type from this vector
3276      * @see VectorOperators.Conversion#ofCast(Class,Class)
3277      * @see Vector#convertShape(VectorOperators.Conversion,VectorSpecies,int)
3278      */
3279     // Does this carry its weight?
3280     public abstract <F> Vector<F> castShape(VectorSpecies<F> rsp, int part);
3281 
3282     /**
3283      * Checks that this vector has the given element type,
3284      * and returns this vector unchanged.
3285      * The effect is similar to this pseudocode:
3286      * {@code elementType == species().elementType()
3287      *        ? this
3288      *        : throw new ClassCastException()}.
3289      *
3290      * @param elementType the required lane type
3291      * @param <F> the boxed element type of the required lane type
3292      * @return the same vector
3293      * @throws ClassCastException if the vector has the wrong element type
3294      * @see VectorSpecies#check(Class)
3295      * @see VectorMask#check(Class)
3296      * @see Vector#check(VectorSpecies)
3297      * @see VectorShuffle#check(VectorSpecies)
3298      */
3299     public abstract <F> Vector<F> check(Class<F> elementType);
3300 
3301     /**
3302      * Checks that this vector has the given species,
3303      * and returns this vector unchanged.
3304      * The effect is similar to this pseudocode:
3305      * {@code species == species()
3306      *        ? this
3307      *        : throw new ClassCastException()}.
3308      *
3309      * @param species the required species
3310      * @param <F> the boxed element type of the required species
3311      * @return the same vector
3312      * @throws ClassCastException if the vector has the wrong species
3313      * @see Vector#check(Class)
3314      * @see VectorMask#check(VectorSpecies)
3315      * @see VectorShuffle#check(VectorSpecies)
3316      */
3317     public abstract <F> Vector<F> check(VectorSpecies<F> species);
3318 
3319     //Array stores
3320 
3321     /**
3322      * Stores this vector into a byte array starting at an offset
3323      * using explicit byte order.
3324      * <p>
3325      * Bytes are extracted from primitive lane elements according
3326      * to the specified byte ordering.
3327      * The lanes are stored according to their
3328      * <a href="Vector.html#lane-order">memory ordering</a>.
3329      * <p>
3330      * This method behaves as if it calls
3331      * {@link #intoByteBuffer(ByteBuffer,int,ByteOrder,VectorMask)
3332      * intoByteBuffer()} as follows:
3333      * <pre>{@code
3334      * var bb = ByteBuffer.wrap(a);
3335      * var m = maskAll(true);
3336      * intoByteBuffer(bb, offset, bo, m);
3337      * }</pre>
3338      *
3339      * @param a the byte array
3340      * @param offset the offset into the array
3341      * @param bo the intended byte order
3342      * @throws IndexOutOfBoundsException
3343      *         if {@code offset+N*ESIZE < 0}
3344      *         or {@code offset+(N+1)*ESIZE > a.length}
3345      *         for any lane {@code N} in the vector
3346      */
3347     public abstract void intoByteArray(byte[] a, int offset,
3348                                        ByteOrder bo);
3349 
3350     /**
3351      * Stores this vector into a byte array starting at an offset
3352      * using explicit byte order and a mask.
3353      * <p>
3354      * Bytes are extracted from primitive lane elements according
3355      * to the specified byte ordering.
3356      * The lanes are stored according to their
3357      * <a href="Vector.html#lane-order">memory ordering</a>.
3358      * <p>
3359      * This method behaves as if it calls
3360      * {@link #intoByteBuffer(ByteBuffer,int,ByteOrder,VectorMask)
3361      * intoByteBuffer()} as follows:
3362      * <pre>{@code
3363      * var bb = ByteBuffer.wrap(a);
3364      * intoByteBuffer(bb, offset, bo, m);
3365      * }</pre>
3366      *
3367      * @param a the byte array
3368      * @param offset the offset into the array
3369      * @param bo the intended byte order
3370      * @param m the mask controlling lane selection
3371      * @throws IndexOutOfBoundsException
3372      *         if {@code offset+N*ESIZE < 0}
3373      *         or {@code offset+(N+1)*ESIZE > a.length}
3374      *         for any lane {@code N} in the vector
3375      *         where the mask is set
3376      */
3377     public abstract void intoByteArray(byte[] a, int offset,
3378                                        ByteOrder bo,
3379                                        VectorMask<E> m);
3380 
3381     /**
3382      * Stores this vector into a byte buffer starting at an offset
3383      * using explicit byte order.
3384      * <p>
3385      * Bytes are extracted from primitive lane elements according
3386      * to the specified byte ordering.
3387      * The lanes are stored according to their
3388      * <a href="Vector.html#lane-order">memory ordering</a>.
3389      * <p>
3390      * This method behaves as if it calls
3391      * {@link #intoByteBuffer(ByteBuffer,int,ByteOrder,VectorMask)
3392      * intoByteBuffer()} as follows:
3393      * <pre>{@code
3394      * var m = maskAll(true);
3395      * intoByteBuffer(bb, offset, bo, m);
3396      * }</pre>
3397      *
3398      * @param bb the byte buffer
3399      * @param offset the offset into the array
3400      * @param bo the intended byte order
3401      * @throws IndexOutOfBoundsException
3402      *         if {@code offset+N*ESIZE < 0}
3403      *         or {@code offset+(N+1)*ESIZE > bb.limit()}
3404      *         for any lane {@code N} in the vector
3405      * @throws java.nio.ReadOnlyBufferException
3406      *         if the byte buffer is read-only
3407      */
3408     public abstract void intoByteBuffer(ByteBuffer bb, int offset, ByteOrder bo);
3409 
3410     /**
3411      * Stores this vector into a byte buffer starting at an offset
3412      * using explicit byte order and a mask.
3413      * <p>
3414      * Bytes are extracted from primitive lane elements according
3415      * to the specified byte ordering.
3416      * The lanes are stored according to their
3417      * <a href="Vector.html#lane-order">memory ordering</a>.
3418      * <p>
3419      * The following pseudocode illustrates the behavior, where
3420      * the primitive element type is not of {@code byte},
3421      * {@code EBuffer} is the primitive buffer type, {@code ETYPE} is the
3422      * primitive element type, and {@code EVector} is the primitive
3423      * vector type for this vector:
3424      * <pre>{@code
3425      * EBuffer eb = bb.duplicate()
3426      *     .position(offset)
3427      *     .order(bo).asEBuffer();
3428      * ETYPE[] a = this.toArray();
3429      * for (int n = 0; n < a.length; n++) {
3430      *     if (m.laneIsSet(n)) {
3431      *         eb.put(n, a[n]);
3432      *     }
3433      * }
3434      * }</pre>
3435      * When the primitive element type is of {@code byte} the primitive
3436      * byte buffer is obtained as follows, where operation on the buffer
3437      * remains the same as in the prior pseudocode:
3438      * <pre>{@code
3439      * ByteBuffer eb = bb.duplicate()
3440      *     .position(offset);
3441      * }</pre>
3442      *
3443      * @implNote
3444      * This operation is likely to be more efficient if
3445      * the specified byte order is the same as
3446      * {@linkplain ByteOrder#nativeOrder()
3447      * the platform native order},
3448      * since this method will not need to reorder
3449      * the bytes of lane values.
3450      * In the special case where {@code ETYPE} is
3451      * {@code byte}, the byte order argument is
3452      * ignored.
3453      *
3454      * @param bb the byte buffer
3455      * @param offset the offset into the array
3456      * @param bo the intended byte order
3457      * @param m the mask controlling lane selection
3458      * @throws IndexOutOfBoundsException
3459      *         if {@code offset+N*ESIZE < 0}
3460      *         or {@code offset+(N+1)*ESIZE > bb.limit()}
3461      *         for any lane {@code N} in the vector
3462      *         where the mask is set
3463      * @throws java.nio.ReadOnlyBufferException
3464      *         if the byte buffer is read-only
3465      */
3466     public abstract void intoByteBuffer(ByteBuffer bb, int offset,
3467                                         ByteOrder bo, VectorMask<E> m);
3468 
3469     /**
3470      * Returns a packed array containing all the lane values.
3471      * The array length is the same as the vector length.
3472      * The element type of the array is the same as the element
3473      * type of the vector.
3474      * The array elements are stored in lane order.
3475      * Overrides of this method on subtypes of {@code Vector}
3476      * which specify the element type have an accurately typed
3477      * array result.
3478      *
3479      * @apiNote
3480      * Usually {@linkplain FloatVector#toArray() strongly typed access}
3481      * is preferable, if you are working with a vector
3482      * subtype that has a known element type.
3483      *
3484      * @return an accurately typed array containing
3485      *         the lane values of this vector
3486      * @see ByteVector#toArray()
3487      * @see IntVector#toArray()
3488      * @see DoubleVector#toArray()
3489      */
3490     public abstract Object toArray();
3491 
3492     /**
3493      * Returns an {@code int[]} array containing all
3494      * the lane values, converted to the type {@code int}.
3495      * The array length is the same as the vector length.
3496      * The array elements are converted as if by casting
3497      * and stored in lane order.
3498      *
3499      * This operation may fail if the vector element type is {@code
3500      * float} or {@code double}, when lanes contain fractional or
3501      * out-of-range values.  If any vector lane value is not
3502      * representable as an {@code int}, an exception is thrown.
3503      *
3504      * @apiNote
3505      * Usually {@linkplain FloatVector#toArray() strongly typed access}
3506      * is preferable, if you are working with a vector
3507      * subtype that has a known element type.
3508      *
3509      * @return an {@code int[]} array containing
3510      *         the lane values of this vector
3511      * @throws UnsupportedOperationException
3512      *         if any lane value cannot be represented as an
3513      *         {@code int} array element
3514      * @see #toArray()
3515      * @see #toLongArray()
3516      * @see #toDoubleArray()
3517      * @see IntVector#toArray()
3518      */
3519     public abstract int[] toIntArray();
3520 
3521     /**
3522      * Returns a {@code long[]} array containing all
3523      * the lane values, converted to the type {@code long}.
3524      * The array length is the same as the vector length.
3525      * The array elements are converted as if by casting
3526      * and stored in lane order.
3527      *
3528      * This operation may fail if the vector element type is {@code
3529      * float} or {@code double}, when lanes contain fractional or
3530      * out-of-range values.  If any vector lane value is not
3531      * representable as a {@code long}, an exception is thrown.
3532      *
3533      * @apiNote
3534      * Usually {@linkplain FloatVector#toArray() strongly typed access}
3535      * is preferable, if you are working with a vector
3536      * subtype that has a known element type.
3537      *
3538      * @return a {@code long[]} array containing
3539      *         the lane values of this vector
3540      * @throws UnsupportedOperationException
3541      *         if any lane value cannot be represented as a
3542      *         {@code long} array element
3543      * @see #toArray()
3544      * @see #toIntArray()
3545      * @see #toDoubleArray()
3546      * @see LongVector#toArray()
3547      */
3548     public abstract long[] toLongArray();
3549 
3550     /**
3551      * Returns a {@code double[]} array containing all
3552      * the lane values, converted to the type {@code double}.
3553      * The array length is the same as the vector length.
3554      * The array elements are converted as if by casting
3555      * and stored in lane order.
3556      * This operation can lose precision
3557      * if the vector element type is {@code long}.
3558      *
3559      * @apiNote
3560      * Usually {@link FloatVector#toArray() strongly typed access}
3561      * is preferable, if you are working with a vector
3562      * subtype that has a known element type.
3563      *
3564      * @return a {@code double[]} array containing
3565      *         the lane values of this vector,
3566      *         possibly rounded to representable
3567      *         {@code double} values
3568      * @see #toArray()
3569      * @see #toIntArray()
3570      * @see #toLongArray()
3571      * @see DoubleVector#toArray()
3572      */
3573     public abstract double[] toDoubleArray();
3574 
3575     /**
3576      * Returns a string representation of this vector, of the form
3577      * {@code "[0,1,2...]"}, reporting the lane values of this
3578      * vector, in lane order.
3579      *
3580      * The string is produced as if by a call to
3581      * {@link Arrays#toString(int[]) Arrays.toString()},
3582      * as appropriate to the array returned by
3583      * {@link #toArray() this.toArray()}.
3584      *
3585      * @return a string of the form {@code "[0,1,2...]"}
3586      * reporting the lane values of this vector
3587      */
3588     @Override
3589     public abstract String toString();
3590 
3591     /**
3592      * Indicates whether this vector is identical to some other object.
3593      * Two vectors are identical only if they have the same species
3594      * and same lane values, in the same order.
3595      * <p>The comparison of lane values is produced as if by a call to
3596      * {@link Arrays#equals(int[],int[]) Arrays.equals()},
3597      * as appropriate to the arrays returned by
3598      * {@link #toArray toArray()} on both vectors.
3599      *
3600      * @return whether this vector is identical to some other object
3601      * @see #eq
3602      */
3603     @Override
3604     public abstract boolean equals(Object obj);
3605 
3606     /**
3607      * Returns a hash code value for the vector.
3608      * based on the lane values and the vector species.
3609      *
3610      * @return  a hash code value for this vector
3611      */
3612     @Override
3613     public abstract int hashCode();
3614 
3615     // ==== JROSE NAME CHANGES ====
3616 
3617     // RAISED FROM SUBCLASSES (with generalized type)
3618     // * toArray() -> ETYPE[] <: Object (erased return type for interop)
3619     // * toString(), equals(Object), hashCode() (documented)
3620     // ADDED
3621     // * compare(OP,v) to replace most of the comparison methods
3622     // * maskAll(boolean) to replace maskAllTrue/False
3623     // * toLongArray(), toDoubleArray() (generic unboxed access)
3624     // * check(Class), check(VectorSpecies) (static type-safety checks)
3625     // * enum Comparison (enum of EQ, NE, GT, LT, GE, LE)
3626     // * zero(VS), broadcast(long) (basic factories)
3627     // * reinterpretAsEs(), viewAsXLanes (bytewise reinterpreting views)
3628     // * addIndex(int) (iota function)
3629 
3630 }