Skip to content
Navigation Menu
{{ message }}
forked from microsoft/DirectXMesh
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathDirectXMeshVBWriter.cpp
More file actions
810 lines (675 loc) · 26.3 KB
/
Copy pathDirectXMeshVBWriter.cpp
File metadata and controls
810 lines (675 loc) · 26.3 KB
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
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
//-------------------------------------------------------------------------------------
// DirectXMeshVBWriter.cpp
//
// DirectX Mesh Geometry Library - Vertex Buffer Writer
//
// Copyright (c) Microsoft Corporation.
// Licensed under the MIT License.
//
// http://go.microsoft.com/fwlink/?LinkID=324981
//-------------------------------------------------------------------------------------
#include "DirectXMeshP.h"
using namespace DirectX;
using namespace DirectX::PackedVector;
#ifndef _WIN32
#define _stricmp strcasecmp
#endif
namespace
{
constexpr size_t c_MaxSlot = 32;
constexpr size_t c_MaxStride = 2048;
enum INPUT_CLASSIFICATION
{
PER_VERTEX_DATA = 0,
PER_INSTANCE_DATA = 1
};
struct InputElementDesc
{
const char* SemanticName;
unsigned int SemanticIndex;
DXGI_FORMAT Format;
unsigned int InputSlot;
unsigned int AlignedByteOffset;
INPUT_CLASSIFICATION InputSlotClass;
unsigned int InstanceDataStepRate;
};
#if defined(__d3d11_h__) || defined(__d3d11_x_h__)
static_assert(sizeof(InputElementDesc) == sizeof(D3D11_INPUT_ELEMENT_DESC), "D3D11 mismatch");
static_assert(static_cast<int>(PER_VERTEX_DATA) == static_cast<int>(D3D11_INPUT_PER_VERTEX_DATA), "D3D11 mismatch");
static_assert(static_cast<int>(PER_INSTANCE_DATA) == static_cast<int>(D3D11_INPUT_PER_INSTANCE_DATA), "D3D11 mismatch");
static_assert(c_MaxSlot == D3D11_IA_VERTEX_INPUT_RESOURCE_SLOT_COUNT, "D3D11 mismatch");
static_assert(c_MaxStride == D3D11_REQ_MULTI_ELEMENT_STRUCTURE_SIZE_IN_BYTES, "D3D11 mismatch");
#endif
#if defined(__d3d12_h__) || defined(__d3d12_x_h__) || defined(__XBOX_D3D12_X__)
static_assert(sizeof(InputElementDesc) == sizeof(D3D12_INPUT_ELEMENT_DESC), "D3D12 mismatch");
static_assert(static_cast<int>(PER_VERTEX_DATA) == static_cast<int>(D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA), "D3D12 mismatch");
static_assert(static_cast<int>(PER_INSTANCE_DATA) == static_cast<int>(D3D12_INPUT_CLASSIFICATION_PER_INSTANCE_DATA), "D3D12 mismatch");
static_assert(c_MaxSlot == D3D12_IA_VERTEX_INPUT_RESOURCE_SLOT_COUNT, "D3D12 mismatch");
static_assert(c_MaxStride == D3D12_REQ_MULTI_ELEMENT_STRUCTURE_SIZE_IN_BYTES, "D3D12 mismatch");
#endif
}
class VBWriter::Impl
{
public:
Impl() noexcept :
mStrides{},
mBuffers{},
mVerts{},
mDefaultStrides{},
mTempSize(0) {}
Impl(const Impl&) = delete;
Impl& operator=(const Impl&) = delete;
Impl(Impl&&) = default;
Impl& operator=(Impl&&) = default;
HRESULT Initialize(_In_reads_(nDecl) const InputElementDesc* vbDecl, size_t nDecl);
HRESULT AddStream(_Out_writes_bytes_(stride*nVerts) void* vb, size_t nVerts, size_t inputSlot, size_t stride) noexcept;
HRESULT Write(_In_reads_(count) const XMVECTOR* buffer, _In_z_ const char* semanticName, unsigned int semanticIndex, size_t count, bool x2bias) const;
void Release() noexcept
{
mInputDesc.clear();
mSemantics.clear();
memset(mStrides, 0, sizeof(mStrides));
memset(mBuffers, 0, sizeof(mBuffers));
memset(mVerts, 0, sizeof(mVerts));
memset(mDefaultStrides, 0, sizeof(mDefaultStrides));
mTempBuffer.reset();
}
const InputElementDesc* GetElement(_In_z_ const char* semanticName, _In_ unsigned int semanticIndex) const
{
auto range = mSemantics.equal_range(semanticName);
auto it = range.first;
for (; it != range.second; ++it)
{
if (mInputDesc[it->second].SemanticIndex == semanticIndex)
break;
}
if (it == range.second)
return nullptr;
return &mInputDesc[it->second];
}
XMVECTOR* GetTemporaryBuffer(size_t count) const noexcept
{
if (!mTempBuffer || (mTempSize < count))
{
mTempSize = count;
for (size_t j = 0; j < c_MaxSlot; ++j)
{
if (mVerts[j] > mTempSize)
mTempSize = mVerts[j];
}
auto temp = make_AlignedArrayXMVECTOR(mTempSize);
if (!temp)
mTempSize = 0;
mTempBuffer.swap(temp);
}
return mTempBuffer.get();
}
private:
using SemanticMap = std::multimap<std::string, uint32_t>;
std::vector<InputElementDesc> mInputDesc;
SemanticMap mSemantics;
uint32_t mStrides[c_MaxSlot];
void* mBuffers[c_MaxSlot];
size_t mVerts[c_MaxSlot];
uint32_t mDefaultStrides[c_MaxSlot];
mutable size_t mTempSize;
mutable ScopedAlignedArrayXMVECTOR mTempBuffer;
};
//-------------------------------------------------------------------------------------
_Use_decl_annotations_
HRESULT VBWriter::Impl::Initialize(const InputElementDesc* vbDecl, size_t nDecl)
{
Release();
uint32_t offsets[c_MaxSlot] = {};
#if defined(__d3d12_h__) || defined(__d3d12_x_h__) || defined(__XBOX_D3D12_X__)
{
if (nDecl > D3D12_IA_VERTEX_INPUT_STRUCTURE_ELEMENT_COUNT)
return E_INVALIDARG;
D3D12_INPUT_LAYOUT_DESC desc = { reinterpret_cast<const D3D12_INPUT_ELEMENT_DESC*>(vbDecl), UINT(nDecl) };
if (!IsValid(desc))
return E_INVALIDARG;
ComputeInputLayout(desc, offsets, mDefaultStrides);
}
#else
if (!IsValid(reinterpret_cast<const D3D11_INPUT_ELEMENT_DESC*>(vbDecl), nDecl))
return E_INVALIDARG;
assert(nDecl <= 32 /*D3D11_IA_VERTEX_INPUT_STRUCTURE_ELEMENT_COUNT*/);
_Analysis_assume_(nDecl <= 32 /*D3D11_IA_VERTEX_INPUT_STRUCTURE_ELEMENT_COUNT*/);
ComputeInputLayout(reinterpret_cast<const D3D11_INPUT_ELEMENT_DESC*>(vbDecl), nDecl, offsets, mDefaultStrides);
#endif
for (size_t j = 0; j < nDecl; ++j)
{
if (vbDecl[j].InputSlotClass == PER_INSTANCE_DATA)
{
// Does not currently support instance data layouts
Release();
return HRESULT_E_NOT_SUPPORTED;
}
mInputDesc.push_back(vbDecl[j]);
mInputDesc[j].AlignedByteOffset = offsets[j];
auto decl = SemanticMap::value_type(vbDecl[j].SemanticName, static_cast<uint32_t>(j));
mSemantics.insert(decl);
// Add common aliases
if (_stricmp(vbDecl[j].SemanticName, "POSITION") == 0)
{
auto decl2 = SemanticMap::value_type("SV_Position", static_cast<uint32_t>(j));
mSemantics.insert(decl2);
}
else if (_stricmp(vbDecl[j].SemanticName, "SV_Position") == 0)
{
auto decl2 = SemanticMap::value_type("POSITION", static_cast<uint32_t>(j));
mSemantics.insert(decl2);
}
}
return S_OK;
}
//-------------------------------------------------------------------------------------
_Use_decl_annotations_
HRESULT VBWriter::Impl::AddStream(void* vb, size_t nVerts, size_t inputSlot, size_t stride) noexcept
{
if (!vb || !nVerts)
return E_INVALIDARG;
if (nVerts >= UINT32_MAX)
return E_INVALIDARG;
if (inputSlot >= c_MaxSlot)
return E_INVALIDARG;
if (stride > c_MaxStride)
return E_INVALIDARG;
mStrides[inputSlot] = (stride > 0) ? uint32_t(stride) : mDefaultStrides[inputSlot];
mBuffers[inputSlot] = vb;
mVerts[inputSlot] = nVerts;
return S_OK;
}
//-------------------------------------------------------------------------------------
#define STORE_VERTS( type, func )\
for(size_t icount = 0; icount < count; ++icount)\
{\
if ((ptr + sizeof(type)) > eptr)\
return E_UNEXPECTED;\
func(reinterpret_cast<type*>(ptr), *buffer++);\
ptr += stride;\
}\
break;
#define STORE_VERTS_X2( type, func, x2bias )\
for(size_t icount = 0; icount < count; ++icount)\
{\
if ((ptr + sizeof(type)) > eptr)\
return E_UNEXPECTED;\
XMVECTOR v = *buffer++;\
if (x2bias)\
{\
v = XMVectorClamp(v, g_XMNegativeOne, g_XMOne);\
v = XMVectorMultiplyAdd(v, g_XMOneHalf, g_XMOneHalf);\
}\
func(reinterpret_cast<type*>(ptr), v);\
ptr += stride;\
}\
break;
_Use_decl_annotations_
HRESULT VBWriter::Impl::Write(const XMVECTOR* buffer, const char* semanticName, unsigned int semanticIndex, size_t count, bool x2bias) const
{
if (!buffer || !semanticName || !count)
return E_INVALIDARG;
auto range = mSemantics.equal_range(semanticName);
auto it = range.first;
for (; it != range.second; ++it)
{
if (mInputDesc[it->second].SemanticIndex == semanticIndex)
break;
}
if (it == range.second)
return HRESULT_E_INVALID_NAME;
uint32_t inputSlot = mInputDesc[it->second].InputSlot;
auto vb = static_cast<uint8_t*>(mBuffers[inputSlot]);
if (!vb)
return E_FAIL;
if (count > mVerts[inputSlot])
return E_BOUNDS;
uint32_t stride = mStrides[inputSlot];
if (!stride)
return E_UNEXPECTED;
const uint8_t* eptr = vb + stride * mVerts[inputSlot];
uint8_t* ptr = vb + mInputDesc[it->second].AlignedByteOffset;
switch (static_cast<int>(mInputDesc[it->second].Format))
{
case DXGI_FORMAT_R32G32B32A32_FLOAT:
STORE_VERTS(XMFLOAT4, XMStoreFloat4)
case DXGI_FORMAT_R32G32B32A32_UINT:
STORE_VERTS(XMUINT4, XMStoreUInt4)
case DXGI_FORMAT_R32G32B32A32_SINT:
STORE_VERTS(XMINT4, XMStoreSInt4)
case DXGI_FORMAT_R32G32B32_FLOAT:
STORE_VERTS(XMFLOAT3, XMStoreFloat3)
case DXGI_FORMAT_R32G32B32_UINT:
STORE_VERTS(XMUINT3, XMStoreUInt3)
case DXGI_FORMAT_R32G32B32_SINT:
STORE_VERTS(XMINT3, XMStoreSInt3)
case DXGI_FORMAT_R16G16B16A16_FLOAT:
STORE_VERTS(XMHALF4, XMStoreHalf4)
case DXGI_FORMAT_R16G16B16A16_UNORM:
STORE_VERTS_X2(XMUSHORTN4, XMStoreUShortN4, x2bias)
case DXGI_FORMAT_R16G16B16A16_UINT:
STORE_VERTS(XMUSHORT4, XMStoreUShort4)
case DXGI_FORMAT_R16G16B16A16_SNORM:
STORE_VERTS(XMSHORTN4, XMStoreShortN4)
case DXGI_FORMAT_R16G16B16A16_SINT:
STORE_VERTS(XMSHORT4, XMStoreShort4)
case DXGI_FORMAT_R32G32_FLOAT:
STORE_VERTS(XMFLOAT2, XMStoreFloat2)
case DXGI_FORMAT_R32G32_UINT:
STORE_VERTS(XMUINT2, XMStoreUInt2)
case DXGI_FORMAT_R32G32_SINT:
STORE_VERTS(XMINT2, XMStoreSInt2)
case DXGI_FORMAT_R10G10B10A2_UNORM:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(XMUDECN4)) > eptr)
return E_UNEXPECTED;
XMVECTOR v = *buffer++;
if (x2bias)
{
XMVECTOR v2 = XMVectorClamp(v, g_XMNegativeOne, g_XMOne);
v2 = XMVectorMultiplyAdd(v2, g_XMOneHalf, g_XMOneHalf);
v = XMVectorSelect(v, v2, g_XMSelect1110);
}
XMStoreUDecN4(reinterpret_cast<XMUDECN4*>(ptr), v);
ptr += stride;
}
break;
case DXGI_FORMAT_R10G10B10A2_UINT:
STORE_VERTS(XMUDEC4, XMStoreUDec4)
case DXGI_FORMAT_R11G11B10_FLOAT:
STORE_VERTS_X2(XMFLOAT3PK, XMStoreFloat3PK, x2bias)
case DXGI_FORMAT_R8G8B8A8_UNORM:
STORE_VERTS_X2(XMUBYTEN4, XMStoreUByteN4, x2bias)
case DXGI_FORMAT_R8G8B8A8_UINT:
STORE_VERTS(XMUBYTE4, XMStoreUByte4)
case DXGI_FORMAT_R8G8B8A8_SNORM:
STORE_VERTS(XMBYTEN4, XMStoreByteN4)
case DXGI_FORMAT_R8G8B8A8_SINT:
STORE_VERTS(XMBYTE4, XMStoreByte4)
case DXGI_FORMAT_R16G16_FLOAT:
STORE_VERTS(XMHALF2, XMStoreHalf2)
case DXGI_FORMAT_R16G16_UNORM:
STORE_VERTS_X2(XMUSHORTN2, XMStoreUShortN2, x2bias)
case DXGI_FORMAT_R16G16_UINT:
STORE_VERTS(XMUSHORT2, XMStoreUShort2)
case DXGI_FORMAT_R16G16_SNORM:
STORE_VERTS(XMSHORTN2, XMStoreShortN2)
case DXGI_FORMAT_R16G16_SINT:
STORE_VERTS(XMSHORT2, XMStoreShort2)
case DXGI_FORMAT_R32_FLOAT:
STORE_VERTS(float, XMStoreFloat)
case DXGI_FORMAT_R32_UINT:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(uint32_t)) > eptr)
return E_UNEXPECTED;
const XMVECTOR v = XMConvertVectorFloatToUInt(*buffer++, 0);
XMStoreInt(reinterpret_cast<uint32_t*>(ptr), v);
ptr += stride;
}
break;
case DXGI_FORMAT_R32_SINT:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(int32_t)) > eptr)
return E_UNEXPECTED;
const XMVECTOR v = XMConvertVectorFloatToInt(*buffer++, 0);
XMStoreInt(reinterpret_cast<uint32_t*>(ptr), v);
ptr += stride;
}
break;
case DXGI_FORMAT_R8G8_UNORM:
STORE_VERTS_X2(XMUBYTEN2, XMStoreUByteN2, x2bias)
case DXGI_FORMAT_R8G8_UINT:
STORE_VERTS(XMUBYTE2, XMStoreUByte2)
case DXGI_FORMAT_R8G8_SNORM:
STORE_VERTS(XMBYTEN2, XMStoreByteN2)
case DXGI_FORMAT_R8G8_SINT:
STORE_VERTS(XMBYTE2, XMStoreByte2)
case DXGI_FORMAT_R16_FLOAT:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(HALF)) > eptr)
return E_UNEXPECTED;
const float f = XMVectorGetX(*buffer++);
*reinterpret_cast<HALF*>(ptr) = XMConvertFloatToHalf(f);
ptr += stride;
}
break;
case DXGI_FORMAT_R16_UNORM:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(uint16_t)) > eptr)
return E_UNEXPECTED;
float f = XMVectorGetX(*buffer++);
if (x2bias)
{
f = std::max<float>(std::min<float>(f, 1.f), -1.f);
f = f * 0.5f + 0.5f;
}
else
{
f = std::max<float>(std::min<float>(f, 1.f), 0.f);
}
*reinterpret_cast<uint16_t*>(ptr) = static_cast<uint16_t>(f*65535.f + 0.5f);
ptr += stride;
}
break;
case DXGI_FORMAT_R16_UINT:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(uint16_t)) > eptr)
return E_UNEXPECTED;
float f = XMVectorGetX(*buffer++);
f = std::max<float>(std::min<float>(f, 65535.f), 0.f);
*reinterpret_cast<uint16_t*>(ptr) = static_cast<uint16_t>(f);
ptr += stride;
}
break;
case DXGI_FORMAT_R16_SNORM:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(int16_t)) > eptr)
return E_UNEXPECTED;
float f = XMVectorGetX(*buffer++);
f = std::max<float>(std::min<float>(f, 1.f), -1.f);
*reinterpret_cast<int16_t*>(ptr) = static_cast<int16_t>(f * 32767.f);
ptr += stride;
}
break;
case DXGI_FORMAT_R16_SINT:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(int16_t)) > eptr)
return E_UNEXPECTED;
float f = XMVectorGetX(*buffer++);
f = std::max<float>(std::min<float>(f, 32767.f), -32767.f);
*reinterpret_cast<int16_t*>(ptr) = static_cast<int16_t>(f);
ptr += stride;
}
break;
case DXGI_FORMAT_R8_UNORM:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(uint8_t)) > eptr)
return E_UNEXPECTED;
float f = XMVectorGetX(*buffer++);
if (x2bias)
{
f = std::max<float>(std::min<float>(f, 1.f), -1.f);
f = f * 0.5f + 0.5f;
}
else
{
f = std::max<float>(std::min<float>(f, 1.f), 0.f);
}
*ptr = static_cast<uint8_t>(f * 255.f);
ptr += stride;
}
break;
case DXGI_FORMAT_R8_UINT:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(uint8_t)) > eptr)
return E_UNEXPECTED;
float f = XMVectorGetX(*buffer++);
f = std::max<float>(std::min<float>(f, 255.f), 0.f);
*ptr = static_cast<uint8_t>(f);
ptr += stride;
}
break;
case DXGI_FORMAT_R8_SNORM:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(int8_t)) > eptr)
return E_UNEXPECTED;
float f = XMVectorGetX(*buffer++);
f = std::max<float>(std::min<float>(f, 1.f), -1.f);
*reinterpret_cast<int8_t*>(ptr) = static_cast<int8_t>(f * 127.f);
ptr += stride;
}
break;
case DXGI_FORMAT_R8_SINT:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(int8_t)) > eptr)
return E_UNEXPECTED;
float f = XMVectorGetX(*buffer++);
f = std::max<float>(std::min<float>(f, 127.f), -127.f);
*reinterpret_cast<int8_t*>(ptr) = static_cast<int8_t>(f);
ptr += stride;
}
break;
case DXGI_FORMAT_B5G6R5_UNORM:
{
static const XMVECTORF32 s_Scale = { { { 31.f, 63.f, 31.f, 1.f } } };
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(XMU565)) > eptr)
return E_UNEXPECTED;
XMVECTOR v = XMVectorSwizzle<2, 1, 0, 3>(*buffer++);
if (x2bias)
{
v = XMVectorClamp(v, g_XMNegativeOne, g_XMOne);
v = XMVectorMultiplyAdd(v, g_XMOneHalf, g_XMOneHalf);
}
#if defined(_M_ARM) || defined(_M_ARM64) || defined(_M_HYBRID_X86_ARM64) || defined(_M_ARM64EC) || __arm__ || __aarch64__
v = XMVectorMultiplyAdd(v, s_Scale, g_XMOneHalf);
#else
v = XMVectorMultiply(v, s_Scale);
#endif
XMStoreU565(reinterpret_cast<XMU565*>(ptr), v);
ptr += stride;
}
}
break;
case DXGI_FORMAT_B5G5R5A1_UNORM:
{
static const XMVECTORF32 s_Scale = { { { 31.f, 31.f, 31.f, 1.f } } };
#if defined(_M_ARM) || defined(_M_ARM64) || defined(_M_HYBRID_X86_ARM64) || defined(_M_ARM64EC) || __arm__ || __aarch64__
static const XMVECTORF32 s_OneHalfXYZ = { { { 0.5f, 0.5f, 0.5f, 0.f } } };
#endif
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(XMU555)) > eptr)
return E_UNEXPECTED;
XMVECTOR v = XMVectorSwizzle<2, 1, 0, 3>(*buffer++);
if (x2bias)
{
XMVECTOR v2 = XMVectorClamp(v, g_XMNegativeOne, g_XMOne);
v2 = XMVectorMultiplyAdd(v2, g_XMOneHalf, g_XMOneHalf);
v = XMVectorSelect(v, v2, g_XMSelect1110);
}
#if defined(_M_ARM) || defined(_M_ARM64) || defined(_M_HYBRID_X86_ARM64) || defined(_M_ARM64EC) || __arm__ || __aarch64__
v = XMVectorMultiplyAdd(v, s_Scale, s_OneHalfXYZ);
#else
v = XMVectorMultiply(v, s_Scale);
#endif
XMStoreU555(reinterpret_cast<XMU555*>(ptr), v);
reinterpret_cast<XMU555*>(ptr)->w = (XMVectorGetW(v) > 0.5f) ? 1u : 0u;
ptr += stride;
}
}
break;
case DXGI_FORMAT_B8G8R8A8_UNORM:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(XMUBYTEN4)) > eptr)
return E_UNEXPECTED;
XMVECTOR v = XMVectorSwizzle<2, 1, 0, 3>(*buffer++);
if (x2bias)
{
v = XMVectorClamp(v, g_XMNegativeOne, g_XMOne);
v = XMVectorMultiplyAdd(v, g_XMOneHalf, g_XMOneHalf);
}
XMStoreUByteN4(reinterpret_cast<XMUBYTEN4*>(ptr), v);
ptr += stride;
}
break;
case DXGI_FORMAT_B8G8R8X8_UNORM:
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(XMUBYTEN4)) > eptr)
return E_UNEXPECTED;
XMVECTOR v = XMVectorSwizzle<2, 1, 0, 3>(*buffer++);
if (x2bias)
{
v = XMVectorClamp(v, g_XMNegativeOne, g_XMOne);
v = XMVectorMultiplyAdd(v, g_XMOneHalf, g_XMOneHalf);
}
v = XMVectorSelect(g_XMZero, v, g_XMSelect1110);
XMStoreUByteN4(reinterpret_cast<XMUBYTEN4*>(ptr), v);
ptr += stride;
}
break;
case DXGI_FORMAT_B4G4R4A4_UNORM:
{
static const XMVECTORF32 s_Scale = { { { 15.f, 15.f, 15.f, 15.f } } };
for (size_t icount = 0; icount < count; ++icount)
{
if ((ptr + sizeof(XMUNIBBLE4)) > eptr)
return E_UNEXPECTED;
XMVECTOR v = XMVectorSwizzle<2, 1, 0, 3>(*buffer++);
if (x2bias)
{
v = XMVectorClamp(v, g_XMNegativeOne, g_XMOne);
v = XMVectorMultiplyAdd(v, g_XMOneHalf, g_XMOneHalf);
}
#if defined(_M_ARM) || defined(_M_ARM64) || defined(_M_HYBRID_X86_ARM64) || defined(_M_ARM64EC) || __arm__ || __aarch64__
v = XMVectorMultiplyAdd(v, s_Scale, g_XMOneHalf);
#else
v = XMVectorMultiply(v, s_Scale);
#endif
XMStoreUNibble4(reinterpret_cast<XMUNIBBLE4*>(ptr), v);
ptr += stride;
}
}
break;
case XBOX_DXGI_FORMAT_R10G10B10_SNORM_A2_UNORM:
// Xbox One specific format
STORE_VERTS(XMXDECN4, XMStoreXDecN4)
default:
return E_FAIL;
}
return S_OK;
}
//=====================================================================================
// Entry-points
//=====================================================================================
// Public constructor.
VBWriter::VBWriter() noexcept(false)
: pImpl(std::make_unique<Impl>())
{
}
VBWriter::VBWriter(VBWriter&&) noexcept = default;
VBWriter& VBWriter::operator= (VBWriter&&) noexcept = default;
VBWriter::~VBWriter() = default;
//-------------------------------------------------------------------------------------
#if defined(__d3d11_h__) || defined(__d3d11_x_h__)
_Use_decl_annotations_
HRESULT VBWriter::Initialize(const D3D11_INPUT_ELEMENT_DESC* vbDecl, size_t nDecl)
{
return pImpl->Initialize(reinterpret_cast<const InputElementDesc*>(vbDecl), nDecl);
}
#endif
#if defined(__d3d12_h__) || defined(__d3d12_x_h__) || defined(__XBOX_D3D12_X__)
HRESULT VBWriter::Initialize(const D3D12_INPUT_LAYOUT_DESC& vbDecl)
{
return pImpl->Initialize(reinterpret_cast<const InputElementDesc*>(vbDecl.pInputElementDescs), vbDecl.NumElements);
}
#endif
//-------------------------------------------------------------------------------------
_Use_decl_annotations_
HRESULT VBWriter::AddStream(void* vb, size_t nVerts, size_t inputSlot, size_t stride) noexcept
{
return pImpl->AddStream(vb, nVerts, inputSlot, stride);
}
//-------------------------------------------------------------------------------------
_Use_decl_annotations_
HRESULT VBWriter::Write(const XMVECTOR* buffer, const char* semanticName, unsigned int semanticIndex, size_t count, bool x2bias) const
{
return pImpl->Write(buffer, semanticName, semanticIndex, count, x2bias);
}
//-------------------------------------------------------------------------------------
_Use_decl_annotations_
HRESULT VBWriter::Write(const float* buffer, const char* semanticName, unsigned int semanticIndex, size_t count, bool x2bias) const
{
XMVECTOR* temp = pImpl->GetTemporaryBuffer(count);
if (!temp)
return E_OUTOFMEMORY;
XMVECTOR* dptr = temp;
const float* sptr = buffer;
for (size_t j = 0; j < count; ++j)
{
XMVECTOR v = XMLoadFloat(sptr++);
*(dptr)++ = v;
}
return pImpl->Write(temp, semanticName, semanticIndex, count, x2bias);
}
_Use_decl_annotations_
HRESULT VBWriter::Write(const XMFLOAT2* buffer, const char* semanticName, unsigned int semanticIndex, size_t count, bool x2bias) const
{
XMVECTOR* temp = pImpl->GetTemporaryBuffer(count);
if (!temp)
return E_OUTOFMEMORY;
XMVECTOR* dptr = temp;
const XMFLOAT2* sptr = buffer;
for (size_t j = 0; j < count; ++j)
{
XMVECTOR v = XMLoadFloat2(sptr++);
*(dptr)++ = v;
}
return pImpl->Write(temp, semanticName, semanticIndex, count, x2bias);
}
_Use_decl_annotations_
HRESULT VBWriter::Write(const XMFLOAT3* buffer, const char* semanticName, unsigned int semanticIndex, size_t count, bool x2bias) const
{
XMVECTOR* temp = pImpl->GetTemporaryBuffer(count);
if (!temp)
return E_OUTOFMEMORY;
XMVECTOR* dptr = temp;
const XMFLOAT3* sptr = buffer;
for (size_t j = 0; j < count; ++j)
{
XMVECTOR v = XMLoadFloat3(sptr++);
*(dptr)++ = v;
}
return pImpl->Write(temp, semanticName, semanticIndex, count, x2bias);
}
_Use_decl_annotations_
HRESULT VBWriter::Write(const XMFLOAT4* buffer, const char* semanticName, unsigned int semanticIndex, size_t count, bool x2bias) const
{
XMVECTOR* temp = pImpl->GetTemporaryBuffer(count);
if (!temp)
return E_OUTOFMEMORY;
XMVECTOR* dptr = temp;
const XMFLOAT4* sptr = buffer;
for (size_t j = 0; j < count; ++j)
{
XMVECTOR v = XMLoadFloat4(sptr++);
*(dptr)++ = v;
}
return pImpl->Write(temp, semanticName, semanticIndex, count, x2bias);
}
//-------------------------------------------------------------------------------------
void VBWriter::Release() noexcept
{
pImpl->Release();
}
//-------------------------------------------------------------------------------------
#if defined(__d3d11_h__) || defined(__d3d11_x_h__)
_Use_decl_annotations_
const D3D11_INPUT_ELEMENT_DESC* VBWriter::GetElement11(const char* semanticName, unsigned int semanticIndex) const
{
return reinterpret_cast<const D3D11_INPUT_ELEMENT_DESC*>(pImpl->GetElement(semanticName, semanticIndex));
}
#endif
#if defined(__d3d12_h__) || defined(__d3d12_x_h__) || defined(__XBOX_D3D12_X__)
_Use_decl_annotations_
const D3D12_INPUT_ELEMENT_DESC* VBWriter::GetElement12(const char* semanticName, unsigned int semanticIndex) const
{
return reinterpret_cast<const D3D12_INPUT_ELEMENT_DESC*>(pImpl->GetElement(semanticName, semanticIndex));
}
#endif
You can’t perform that action at this time.