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
|
/*
* Mesa 3-D graphics library
*
* Copyright 2003 VMware, Inc.
* Copyright 2009 VMware, Inc.
* All Rights Reserved.
* Copyright (C) 2016 Advanced Micro Devices, Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice (including the next
* paragraph) shall be included in all copies or substantial portions of the
* Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
* THE AUTHOR(S) AND/OR THEIR SUPPLIERS BE LIABLE FOR ANY CLAIM,
* DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
* OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
* USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#include "main/glheader.h"
#include "main/context.h"
#include "main/varray.h"
#include "main/macros.h"
#include "main/sse_minmax.h"
#include "x86/common_x86_asm.h"
/**
* Compute min and max elements by scanning the index buffer for
* glDraw[Range]Elements() calls.
* If primitive restart is enabled, we need to ignore restart
* indexes when computing min/max.
*/
static void
vbo_get_minmax_index(struct gl_context *ctx,
const struct _mesa_prim *prim,
const struct _mesa_index_buffer *ib,
GLuint *min_index, GLuint *max_index,
const GLuint count)
{
const GLboolean restart = ctx->Array._PrimitiveRestart;
const GLuint restartIndex = _mesa_primitive_restart_index(ctx, ib->type);
const int index_size = vbo_sizeof_ib_type(ib->type);
const char *indices;
GLuint i;
indices = (char *) ib->ptr + prim->start * index_size;
if (_mesa_is_bufferobj(ib->obj)) {
GLsizeiptr size = MIN2(count * index_size, ib->obj->Size);
indices = ctx->Driver.MapBufferRange(ctx, (GLintptr) indices, size,
GL_MAP_READ_BIT, ib->obj,
MAP_INTERNAL);
}
switch (ib->type) {
case GL_UNSIGNED_INT: {
const GLuint *ui_indices = (const GLuint *)indices;
GLuint max_ui = 0;
GLuint min_ui = ~0U;
if (restart) {
for (i = 0; i < count; i++) {
if (ui_indices[i] != restartIndex) {
if (ui_indices[i] > max_ui) max_ui = ui_indices[i];
if (ui_indices[i] < min_ui) min_ui = ui_indices[i];
}
}
}
else {
#if defined(USE_SSE41)
if (cpu_has_sse4_1) {
_mesa_uint_array_min_max(ui_indices, &min_ui, &max_ui, count);
}
else
#endif
for (i = 0; i < count; i++) {
if (ui_indices[i] > max_ui) max_ui = ui_indices[i];
if (ui_indices[i] < min_ui) min_ui = ui_indices[i];
}
}
*min_index = min_ui;
*max_index = max_ui;
break;
}
case GL_UNSIGNED_SHORT: {
const GLushort *us_indices = (const GLushort *)indices;
GLuint max_us = 0;
GLuint min_us = ~0U;
if (restart) {
for (i = 0; i < count; i++) {
if (us_indices[i] != restartIndex) {
if (us_indices[i] > max_us) max_us = us_indices[i];
if (us_indices[i] < min_us) min_us = us_indices[i];
}
}
}
else {
for (i = 0; i < count; i++) {
if (us_indices[i] > max_us) max_us = us_indices[i];
if (us_indices[i] < min_us) min_us = us_indices[i];
}
}
*min_index = min_us;
*max_index = max_us;
break;
}
case GL_UNSIGNED_BYTE: {
const GLubyte *ub_indices = (const GLubyte *)indices;
GLuint max_ub = 0;
GLuint min_ub = ~0U;
if (restart) {
for (i = 0; i < count; i++) {
if (ub_indices[i] != restartIndex) {
if (ub_indices[i] > max_ub) max_ub = ub_indices[i];
if (ub_indices[i] < min_ub) min_ub = ub_indices[i];
}
}
}
else {
for (i = 0; i < count; i++) {
if (ub_indices[i] > max_ub) max_ub = ub_indices[i];
if (ub_indices[i] < min_ub) min_ub = ub_indices[i];
}
}
*min_index = min_ub;
*max_index = max_ub;
break;
}
default:
unreachable("not reached");
}
if (_mesa_is_bufferobj(ib->obj)) {
ctx->Driver.UnmapBuffer(ctx, ib->obj, MAP_INTERNAL);
}
}
/**
* Compute min and max elements for nr_prims
*/
void
vbo_get_minmax_indices(struct gl_context *ctx,
const struct _mesa_prim *prims,
const struct _mesa_index_buffer *ib,
GLuint *min_index,
GLuint *max_index,
GLuint nr_prims)
{
GLuint tmp_min, tmp_max;
GLuint i;
GLuint count;
*min_index = ~0;
*max_index = 0;
for (i = 0; i < nr_prims; i++) {
const struct _mesa_prim *start_prim;
start_prim = &prims[i];
count = start_prim->count;
/* Do combination if possible to reduce map/unmap count */
while ((i + 1 < nr_prims) &&
(prims[i].start + prims[i].count == prims[i+1].start)) {
count += prims[i+1].count;
i++;
}
vbo_get_minmax_index(ctx, start_prim, ib, &tmp_min, &tmp_max, count);
*min_index = MIN2(*min_index, tmp_min);
*max_index = MAX2(*max_index, tmp_max);
}
}
|
