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