summaryrefslogtreecommitdiff
path: root/src/arch/generic/vec_reg.hh
blob: b68a5886da07cad6ef3a437dc6488ef73d0fb00b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
/*
 * Copyright (c) 2015-2016 ARM Limited
 * All rights reserved
 *
 * The license below extends only to copyright in the software and shall
 * not be construed as granting a license to any other intellectual
 * property including but not limited to intellectual property relating
 * to a hardware implementation of the functionality of the software
 * licensed hereunder.  You may use the software subject to the license
 * terms below provided that you ensure that this notice is replicated
 * unmodified and in its entirety in all distributions of the software,
 * modified or unmodified, in source code or in binary form.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are
 * met: redistributions of source code must retain the above copyright
 * notice, this list of conditions and the following disclaimer;
 * redistributions in binary form must reproduce the above copyright
 * notice, this list of conditions and the following disclaimer in the
 * documentation and/or other materials provided with the distribution;
 * neither the name of the copyright holders nor the names of its
 * contributors may be used to endorse or promote products derived from
 * this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * Authors: Giacomo Gabrielli
 *          Nathanael Premillieu
 *          Rekai Gonzalez
 */

/** \file arch/generic/vec_reg.hh
 * Vector Registers layout specification.
 *
 * This register type is to be used to model the SIMD registers.
 * It takes into account the possibility that different architectural names
 * may overlap (like for ARMv8 AArch32 for example).
 *
 * The design is having a basic vector register container that holds the
 * bytes, unaware of anything else. This is implemented by VecRegContainer.
 * As the (maximum) length of the physical vector register is a compile-time
 * constant, it is defined as a template parameter.
 *
 * This file also describes two views of the container that have semantic
 * information about the bytes. The first of this views is VecRegT.
 *    A VecRegT is a view of a VecRegContainer (by reference). The VecRegT has
 *    a type (VecElem) to which bytes are casted, and the amount of such
 *    elements that the vector contains (NumElems). The size of a view,
 *    calculated as sizeof(VecElem) * NumElems must match the size of the
 *    underlying container. As VecRegT has some degree of type information it
 *    has vector semantics, and defines the index operator ([]) to get
 *    references to particular bytes understood as a VecElem.
 * The second view of a container implemented in this file is VecLaneT, which
 * is a view of a subset of the container.
 *    A VecLaneT is a view of a lane of a vector register, where a lane is
 *    identified by a type (VecElem) and an index (although the view is
 *    unaware of its index). Operations on the lane are directly applied to
 *    the corresponding bytes of the underlying VecRegContainer through a
 *    reference.
 *
 * The intended usage is requesting views to the VecRegContainer via the
 * member 'as' for VecRegT and the member 'laneView' for VecLaneT. Kindly
 * find an example of usage in the following.
 *
 *
 * // We declare 512 bits vectors
 * using Vec512 = VecRegContainer<64>;
 * ...
 * // We implement the physical vector register file
 * Vec512 physicalVecRegFile[NUM_VREGS];
 * ...
 * // Usage example, for a macro op:
 * VecFloat8Add(ExecContext* xd) {
 *    // Request source vector register to the execution context (const as it
 *    // is read only).
 *    const Vec512& vsrc1raw = xc->readVecRegOperand(this, 0);
 *    // View it as a vector of floats (we could just specify the first
 *    // template parametre, the second has a default value that works, and the
 *    // last one is derived by the constness of vsrc1raw).
 *    VecRegT<float, 8, true>& vsrc1 = vsrc1raw->as<float, 8>();
 *
 *    // Second source and view
 *    const Vec512& vsrc2raw = xc->readVecRegOperand(this, 1);
 *    VecRegT<float, 8, true>& vsrc2 = vsrc2raw->as<float, 8>();
 *
 *    // Destination and view
 *    Vec512 vdstraw;
 *    VecRegT<float, 8, false>& vdst = vdstraw->as<float, 8>();
 *
 *    for (auto i = 0; i < 8; i++) {
 *        // This asignment sets the bits in the underlying Vec512: vdstraw
 *        vdst[i] = vsrc1[i] + vsrc2[i];
 *    }
 *    xc->setWriteRegOperand(this, 0, vdstraw);
 * }
 *
 * // Usage example, for a micro op that operates over lane number _lidx:
 * VecFloatLaneAdd(ExecContext* xd) {
 *    // Request source vector register to the execution context (const as it
 *    // is read only).
 *    const Vec512& vsrc1raw = xc->readVecRegOperand(this, 0);
 *    // View it as a lane of a vector of floats (we could just specify the
 *    // first template parametre, the second is derived by the constness of
 *    // vsrc1raw).
 *    VecLaneT<float, true>& src1 = vsrc1raw->laneView<float>(this->_lidx);
 *
 *    // Second source and view
 *    const Vec512& vsrc2raw = xc->readVecRegOperand(this, 1);
 *    VecLaneT<float, true>& src2 = vsrc2raw->laneView<float>(this->_lidx);
 *
 *    // (Writable) destination and view
 *    // As this is a partial write, we need the exec context to support that
 *    // through, e.g., 'readVecRegOperandToWrite' returning a writable
 *    // reference to the register
 *    Vec512 vdstraw = xc->readVecRegOperandToWrite(this, 3);
 *    VecLaneT<float, false>& dst = vdstraw->laneView<float>(this->_lidx);
 *
 *    dst = src1 + src2;
 *    // There is no need to copy the value back into the exec context, as
 *    // the assignment to dst modifies the appropriate bytes in vdstraw which
 *    // is in turn, a reference to the register in the cpu model.
 *    // For operations that do conditional writeback, we can decouple the
 *    // write by doing:
 *    //   auto tmp = src1 + src2;
 *    //   if (test) {
 *    //       dst = tmp; // do writeback
 *    //   } else {
 *    //      // do not do writeback
 *    //   }
 * }
 *
 */

#ifndef __ARCH_GENERIC_VEC_REG_HH__
#define __ARCH_GENERIC_VEC_REG_HH__

#include <array>
#include <cassert>
#include <iostream>
#include <string>
#include <type_traits>
#include <vector>

#include "base/cprintf.hh"
#include "base/logging.hh"

template <size_t Sz>
class VecRegContainer;

/** Vector Register Abstraction
 * This generic class is a view in a particularization of MVC, to vector
 * registers. There is a VecRegContainer that implements the model, and
 * contains the data. To that model we can interpose different instantiations
 * of VecRegT to view the container as a vector of NumElems elems of type
 * VecElem.
 * @tparam VecElem Type of each element of the vector.
 * @tparam NumElems Amount of components of the vector.
 * @tparam Const Indicate if the underlying container can be modified through
 * the view.
 */
template <typename VecElem, size_t NumElems, bool Const>
class VecRegT
{
    /** Size of the register in bytes. */
    static constexpr size_t SIZE = sizeof(VecElem) * NumElems;
  public:
    /** Container type alias. */
    using Container = typename std::conditional<Const,
                                              const VecRegContainer<SIZE>,
                                              VecRegContainer<SIZE>>::type;
  private:
    /** My type alias. */
    using MyClass = VecRegT<VecElem, NumElems, Const>;
    /** Reference to container. */
    Container& container;

  public:
    /** Constructor. */
    VecRegT(Container& cnt) : container(cnt) {};

    /** Zero the container. */
    template<bool Condition = !Const>
    typename std::enable_if<Condition, void>::type
    zero() { container.zero(); }

    template<bool Condition = !Const>
    typename std::enable_if<Condition, MyClass&>::type
    operator=(const MyClass& that)
    {
        container = that.container;
        return *this;
    }

    /** Index operator. */
    const VecElem& operator[](size_t idx) const
    {
        return container.template raw_ptr<VecElem>()[idx];
    }

    /** Index operator. */
    template<bool Condition = !Const>
    typename std::enable_if<Condition, VecElem&>::type
    operator[](size_t idx)
    {
        return container.template raw_ptr<VecElem>()[idx];
    }

    /** Equality operator.
     * Required to compare thread contexts.
     */
    template<typename VE2, size_t NE2, bool C2>
    bool
    operator==(const VecRegT<VE2, NE2, C2>& that) const
    {
        return container == that.container;
    }
    /** Inequality operator.
     * Required to compare thread contexts.
     */
    template<typename VE2, size_t NE2, bool C2>
    bool
    operator!=(const VecRegT<VE2, NE2, C2>& that) const
    {
        return !operator==(that);
    }

    /** Output stream operator. */
    friend std::ostream&
    operator<<(std::ostream& os, const MyClass& vr)
    {
        /* 0-sized is not allowed */
        os << "[" << std::hex << (uint32_t)vr[0];
        for (uint32_t e = 1; e < vr.SIZE; e++)
            os << " " << std::hex << (uint32_t)vr[e];
        os << ']';
        return os;
    }

    const std::string print() const { return csprintf("%s", *this); }
    /**
     * Cast to VecRegContainer&
     * It is useful to get the reference to the container for ISA tricks,
     * because casting to reference prevents unnecessary copies.
     */
    operator Container&() { return container; }
};

/* Forward declaration. */
template <typename VecElem, bool Const>
class VecLaneT;

/**
 * Vector Register Abstraction
 * This generic class is the model in a particularization of MVC, to vector
 * registers. The model has functionality to create views of itself, or a
 * portion through the method 'as
 * @tparam Sz Size of the container in bytes.
 */
template <size_t Sz>
class VecRegContainer
{
  static_assert(Sz > 0,
          "Cannot create Vector Register Container of zero size");
  public:
    static constexpr size_t SIZE = Sz;
    using Container = std::array<uint8_t,Sz>;
  private:
    Container container;
    using MyClass = VecRegContainer<SIZE>;

  public:
    VecRegContainer() {}
    /* This is required for de-serialisation. */
    VecRegContainer(const std::vector<uint8_t>& that)
    {
        assert(that.size() >= SIZE);
        std::memcpy(container.data(), &that[0], SIZE);
    }

    /** Zero the container. */
    void zero() { memset(container.data(), 0, SIZE); }

    /** Assignment operators. */
    /** @{ */
    /** From VecRegContainer */
    MyClass& operator=(const MyClass& that)
    {
        if (&that == this)
            return *this;
        memcpy(container.data(), that.container.data(), SIZE);
        return *this;
    }

    /** From appropriately sized uint8_t[]. */
    MyClass& operator=(const Container& that)
    {
        std::memcpy(container.data(), that.data(), SIZE);
        return *this;
    }

    /** From vector<uint8_t>.
     * This is required for de-serialisation.
     * */
    MyClass& operator=(const std::vector<uint8_t>& that)
    {
        assert(that.size() >= SIZE);
        std::memcpy(container.data(), that.data(), SIZE);
        return *this;
    }
    /** @} */

    /** Copy the contents into the input buffer. */
    /** @{ */
    /** To appropriately sized uint8_t[] */
    void copyTo(Container& dst) const
    {
        std::memcpy(dst.data(), container.data(), SIZE);
    }

    /** To vector<uint8_t>
     * This is required for serialisation.
     * */
    void copyTo(std::vector<uint8_t>& dst) const
    {
        dst.resize(SIZE);
        std::memcpy(dst.data(), container.data(), SIZE);
    }
    /** @} */

    /** Equality operator.
     * Required to compare thread contexts.
     */
    template<size_t S2>
    inline bool
    operator==(const VecRegContainer<S2>& that) const
    {
        return SIZE == S2 &&
               !memcmp(container.data(), that.container.data(), SIZE);
    }
    /** Inequality operator.
     * Required to compare thread contexts.
     */
    template<size_t S2>
    bool
    operator!=(const VecRegContainer<S2>& that) const
    {
        return !operator==(that);
    }

    const std::string print() const { return csprintf("%s", *this); }
    /** Get pointer to bytes. */
    template <typename Ret>
    const Ret* raw_ptr() const { return (const Ret*)container.data(); }

    template <typename Ret>
    Ret* raw_ptr() { return (Ret*)container.data(); }

    /**
     * View interposers.
     * Create a view of this container as a vector of VecElems with an
     * optional amount of elements. If the amount of elements is provided,
     * the size of the container is checked, to test bounds. If it is not
     * provided, the length is inferred from the container size and the
     * element size.
     * @tparam VecElem Type of each element of the vector for the view.
     * @tparam NumElem Amount of elements in the view.
     */
    /** @{ */
    template <typename VecElem, size_t NumElems = SIZE/sizeof(VecElem)>
    VecRegT<VecElem, NumElems, true> as() const
    {
        static_assert(SIZE % sizeof(VecElem) == 0,
                "VecElem does not evenly divide the register size");
        static_assert(sizeof(VecElem) * NumElems <= SIZE,
                "Viewing VecReg as something bigger than it is");
        return VecRegT<VecElem, NumElems, true>(*this);
    }

    template <typename VecElem, size_t NumElems = SIZE/sizeof(VecElem)>
    VecRegT<VecElem, NumElems, false> as()
    {
        static_assert(SIZE % sizeof(VecElem) == 0,
                "VecElem does not evenly divide the register size");
        static_assert(sizeof(VecElem) * NumElems <= SIZE,
                "Viewing VecReg as something bigger than it is");
        return VecRegT<VecElem, NumElems, false>(*this);
    }

    template <typename VecElem, int LaneIdx>
    VecLaneT<VecElem, false> laneView();
    template <typename VecElem, int LaneIdx>
    VecLaneT<VecElem, true> laneView() const;
    template <typename VecElem>
    VecLaneT<VecElem, false> laneView(int laneIdx);
    template <typename VecElem>
    VecLaneT<VecElem, true> laneView(int laneIdx) const;
    /** @} */
    /**
     * Output operator.
     * Used for serialization.
     */
    friend std::ostream& operator<<(std::ostream& os, const MyClass& v)
    {
        for (auto& b: v.container) {
            os << csprintf("%02x", b);
        }
        return os;
    }
};

/** We define an auxiliary abstraction for LaneData. The ISA should care
 * about the semantics of a, e.g., 32bit element, treating it as a signed or
 * unsigned int, or a float depending on the semantics of a particular
 * instruction. On the other hand, the cpu model should only care about it
 * being a 32-bit value. */
enum class LaneSize
{
    Empty = 0,
    Byte,
    TwoByte,
    FourByte,
    EightByte,
};

/** LaneSize is an abstraction of a LS byte value for the execution and thread
 * contexts to handle values just depending on its width. That way, the ISA
 * can request, for example, the second 4 byte lane of register 5 to the model.
 * The model serves that value, agnostic of the semantics of those bits. Then,
 * it is up to the ISA to interpret those bits as a float, or as an uint.
 * To maximize the utility, this class implements the assignment operator and
 * the casting to equal-size types.
 * As opposed to a RegLaneT, LaneData is not 'backed' by a VecRegContainer.
 * The idea is:
 *  When data is passed and is susceptible to being copied, use LaneData, as
 *     copying the primitive type is build on is cheap.
 *  When data is passed as references (const or not), use RegLaneT, as all
 *     operations happen 'in place', avoiding any copies (no copies is always
 *     cheaper than cheap copies), especially when things are inlined, and
 *     references are not explicitly passed.
 */
template <LaneSize LS>
class LaneData
{
  public:
    /** Alias to the native type of the appropriate size. */
    using UnderlyingType =
        typename std::conditional<LS == LaneSize::EightByte, uint64_t,
            typename std::conditional<LS == LaneSize::FourByte, uint32_t,
                typename std::conditional<LS == LaneSize::TwoByte, uint16_t,
                    typename std::conditional<LS == LaneSize::Byte, uint8_t,
                    void>::type
                >::type
            >::type
        >::type;
  private:
    static constexpr auto ByteSz = sizeof(UnderlyingType);
    UnderlyingType _val;
    using MyClass = LaneData<LS>;

  public:
    template <typename T> explicit
    LaneData(typename std::enable_if<sizeof(T) == ByteSz, const T&>::type t)
                : _val(t) {}

    template <typename T>
    typename std::enable_if<sizeof(T) == ByteSz, MyClass&>::type
    operator=(const T& that)
    {
        _val = that;
        return *this;
    }
    template<typename T,
             typename std::enable_if<sizeof(T) == ByteSz, int>::type I = 0>
    operator T() const {
        return *static_cast<const T*>(&_val);
    }
};

/** Output operator overload for LaneData<Size>. */
template <LaneSize LS>
inline std::ostream&
operator<<(std::ostream& os, const LaneData<LS>& d)
{
    return os << static_cast<typename LaneData<LS>::UnderlyingType>(d);
}

/** Vector Lane abstraction
 * Another view of a container. This time only a partial part of it is exposed.
 * @tparam VecElem Type of each element of the vector.
 * @tparam Const Indicate if the underlying container can be modified through
 * the view.
 */
/** @{ */
/* General */
template <typename VecElem, bool Const>
class VecLaneT
{
  public:
    /** VecRegContainer friendship to access private VecLaneT constructors.
     * Only VecRegContainers can build VecLanes.
     */
    /** @{ */
    friend VecLaneT<VecElem, !Const>;

    /*template <size_t Sz>
    friend class VecRegContainer;*/
    friend class VecRegContainer<8>;
    friend class VecRegContainer<16>;
    friend class VecRegContainer<32>;
    friend class VecRegContainer<64>;
    friend class VecRegContainer<128>;

    /** My type alias. */
    using MyClass = VecLaneT<VecElem, Const>;

  private:
    using Cont = typename std::conditional<Const,
                                              const VecElem,
                                              VecElem>::type;
    static_assert(!std::is_const<VecElem>::value || Const,
            "Asked for non-const lane of const type!");
    static_assert(std::is_integral<VecElem>::value,
            "VecElem type is not integral!");
    /** Reference to data. */
    Cont& container;

    /** Constructor */
    VecLaneT(Cont& cont) : container(cont) { }

  public:
    /** Assignment operators.
     * Assignment operators are only enabled if the underlying container is
     * non-constant.
     */
    /** @{ */
    template <bool Assignable = !Const>
    typename std::enable_if<Assignable, MyClass&>::type
    operator=(const VecElem& that) {
        container = that;
        return *this;
    }
    /**
     * Generic.
     * Generic bitwise assignment. Narrowing and widening assignemnts are
     * not allowed, pre-treatment of the rhs is required to conform.
     */
    template <bool Assignable = !Const, typename T>
    typename std::enable_if<Assignable, MyClass&>::type
    operator=(const T& that) {
        static_assert(sizeof(T) >= sizeof(VecElem),
                "Attempt to perform widening bitwise copy.");
        static_assert(sizeof(T) <= sizeof(VecElem),
                "Attempt to perform narrowing bitwise copy.");
        container = static_cast<VecElem>(that);
        return *this;
    }
    /** @} */
    /** Cast to vecElem. */
    operator VecElem() const { return container; }

    /** Constification. */
    template <bool Cond = !Const, typename std::enable_if<Cond, int>::type = 0>
    operator VecLaneT<typename std::enable_if<Cond, VecElem>::type, true>()
    {
        return VecLaneT<VecElem, true>(container);
    }
};

namespace std {
    template<typename T, bool Const>
    struct add_const<VecLaneT<T, Const>> { typedef VecLaneT<T, true> type; };
}

/** View as the Nth lane of type VecElem. */
template <size_t Sz>
template <typename VecElem, int LaneIdx>
VecLaneT<VecElem, false>
VecRegContainer<Sz>::laneView()
{
    return VecLaneT<VecElem, false>(as<VecElem>()[LaneIdx]);
}

/** View as the const Nth lane of type VecElem. */
template <size_t Sz>
template <typename VecElem, int LaneIdx>
VecLaneT<VecElem, true>
VecRegContainer<Sz>::laneView() const
{
    return VecLaneT<VecElem, true>(as<VecElem>()[LaneIdx]);
}

/** View as the Nth lane of type VecElem. */
template <size_t Sz>
template <typename VecElem>
VecLaneT<VecElem, false>
VecRegContainer<Sz>::laneView(int laneIdx)
{
    return VecLaneT<VecElem, false>(as<VecElem>()[laneIdx]);
}

/** View as the const Nth lane of type VecElem. */
template <size_t Sz>
template <typename VecElem>
VecLaneT<VecElem, true>
VecRegContainer<Sz>::laneView(int laneIdx) const
{
    return VecLaneT<VecElem, true>(as<VecElem>()[laneIdx]);
}

using VecLane8 = VecLaneT<uint8_t, false>;
using VecLane16 = VecLaneT<uint16_t, false>;
using VecLane32 = VecLaneT<uint32_t, false>;
using VecLane64 = VecLaneT<uint64_t, false>;

using ConstVecLane8 = VecLaneT<uint8_t, true>;
using ConstVecLane16 = VecLaneT<uint16_t, true>;
using ConstVecLane32 = VecLaneT<uint32_t, true>;
using ConstVecLane64 = VecLaneT<uint64_t, true>;

/**
 * Calls required for serialization/deserialization
 */
/** @{ */
template <size_t Sz>
inline bool
to_number(const std::string& value, VecRegContainer<Sz>& v)
{
    int i = 0;
    while (i < Sz) {
        std::string byte = value.substr(i<<1, 2);
        v.template raw_ptr<uint8_t>()[i] = stoul(byte, 0, 16);
        i++;
    }
    return true;
}
/** @} */

#endif /* __ARCH_GENERIC_VEC_REG_HH__ */