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
|
/* ScummVM - Graphic Adventure Engine
*
* ScummVM is the legal property of its developers, whose names
* are too numerous to list here. Please refer to the COPYRIGHT
* file distributed with this source distribution.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*
*/
#include "graphics/blit.h"
#include "graphics/surface.h"
#include "backends/platform/atari/dlmalloc.h"
#include <cstdlib> // malloc
#include <cstring> // memcpy, memset
#include <mint/cookie.h>
#include "backends/graphics/atari/atari-graphics-superblitter.h"
#include "common/textconsole.h" // error
// bits 26:0
#define SV_BLITTER_SRC1 ((volatile long*)0x80010058)
#define SV_BLITTER_SRC2 ((volatile long*)0x8001005C)
#define SV_BLITTER_DST ((volatile long*)0x80010060)
// The amount of bytes that are to be copied in a horizontal line, minus 1
#define SV_BLITTER_COUNT ((volatile long*)0x80010064)
// The amount of bytes that are to be added to the line start address after a line has been copied, in order to reach the next one
#define SV_BLITTER_SRC1_OFFSET ((volatile long*)0x80010068)
#define SV_BLITTER_SRC2_OFFSET ((volatile long*)0x8001006C)
#define SV_BLITTER_DST_OFFSET ((volatile long*)0x80010070)
// bits 11:0 - The amount of horizontal lines to do
#define SV_BLITTER_MASK_AND_LINES ((volatile long*)0x80010074)
// bit 0 - busy / start
// bits 4:1 - blit mode
#define SV_BLITTER_CONTROL ((volatile long*)0x80010078)
// bit 0 - empty (read only)
// bit 1 - full (read only)
// bits 31:0 - data (write only)
#define SV_BLITTER_FIFO ((volatile long*)0x80010080)
#ifdef USE_SV_BLITTER
static bool isSuperBlitterLocked;
static void syncSuperBlitter() {
// if externally locked, let the owner decide when to sync (unlock)
if (isSuperBlitterLocked)
return;
// while FIFO not empty...
if (superVidelFwVersion >= 9)
while (!(*SV_BLITTER_FIFO & 1));
// while busy blitting...
while (*SV_BLITTER_CONTROL & 1);
}
#endif
#ifdef USE_MOVE16
static inline bool hasMove16() {
long val;
static bool hasMove16 = Getcookie(C__CPU, &val) == C_FOUND && val >= 40;
return hasMove16;
}
#endif
void lockSuperBlitter() {
#ifdef USE_SV_BLITTER
assert(!isSuperBlitterLocked);
isSuperBlitterLocked = true;
#endif
}
void unlockSuperBlitter() {
#ifdef USE_SV_BLITTER
assert(isSuperBlitterLocked);
isSuperBlitterLocked = false;
if (hasSuperVidel())
syncSuperBlitter();
#endif
}
// see osystem-atari.cpp
extern bool g_unalignedPitch;
// see atari-graphics.cpp
extern mspace g_mspace;
namespace Graphics {
constexpr size_t ALIGN = 16; // 16 bytes
// hijack surface overrides here as well as these are tightly related
// to the blitting routine below
void Surface::create(int16 width, int16 height, const PixelFormat &f) {
assert(width >= 0 && height >= 0);
free();
w = width;
h = height;
format = f;
// align pitch to a 16-byte boundary for a possible C2P conversion
pitch = g_unalignedPitch
? w * format.bytesPerPixel
: (w * format.bytesPerPixel + ALIGN - 1) & (-ALIGN);
if (width && height) {
#ifdef USE_SV_BLITTER
if (g_mspace) {
pixels = mspace_calloc(g_mspace, height * pitch, f.bytesPerPixel);
if (!pixels)
error("Not enough memory to allocate a surface");
assert(pixels >= (void *)0xA0000000);
} else {
#else
{
#endif
pixels = ::calloc(height * pitch, f.bytesPerPixel);
if (!pixels)
error("Not enough memory to allocate a surface");
assert(((uintptr)pixels & (ALIGN - 1)) == 0);
}
}
}
void Surface::free() {
#ifdef USE_SV_BLITTER
if (g_mspace)
mspace_free(g_mspace, pixels);
else
#endif
if (pixels)
::free(pixels);
pixels = nullptr;
w = h = pitch = 0;
format = PixelFormat();
}
// Function to blit a rect (version optimized for Atari Falcon with SuperVidel's SuperBlitter)
void copyBlit(byte *dst, const byte *src,
const uint dstPitch, const uint srcPitch,
const uint w, const uint h,
const uint bytesPerPixel) {
if (dst == src)
return;
#ifdef USE_SV_BLITTER
if (((uintptr)src & 0xFF000000) >= 0xA0000000 && ((uintptr)dst & 0xFF000000) >= 0xA0000000) {
if (superVidelFwVersion >= 9) {
*SV_BLITTER_FIFO = (long)src; // SV_BLITTER_SRC1
*SV_BLITTER_FIFO = 0x00000000; // SV_BLITTER_SRC2
*SV_BLITTER_FIFO = (long)dst; // SV_BLITTER_DST
*SV_BLITTER_FIFO = w * bytesPerPixel - 1; // SV_BLITTER_COUNT
*SV_BLITTER_FIFO = srcPitch; // SV_BLITTER_SRC1_OFFSET
*SV_BLITTER_FIFO = 0x00000000; // SV_BLITTER_SRC2_OFFSET
*SV_BLITTER_FIFO = dstPitch; // SV_BLITTER_DST_OFFSET
*SV_BLITTER_FIFO = h; // SV_BLITTER_MASK_AND_LINES
*SV_BLITTER_FIFO = 0x01; // SV_BLITTER_CONTROL
} else {
// make sure the blitter is idle
while (*SV_BLITTER_CONTROL & 1);
*SV_BLITTER_SRC1 = (long)src;
*SV_BLITTER_SRC2 = 0x00000000;
*SV_BLITTER_DST = (long)dst;
*SV_BLITTER_COUNT = w * bytesPerPixel - 1;
*SV_BLITTER_SRC1_OFFSET = srcPitch;
*SV_BLITTER_SRC2_OFFSET = 0x00000000;
*SV_BLITTER_DST_OFFSET = dstPitch;
*SV_BLITTER_MASK_AND_LINES = h;
*SV_BLITTER_CONTROL = 0x01;
}
syncSuperBlitter();
} else
#endif
if (dstPitch == srcPitch && dstPitch == (w * bytesPerPixel)) {
#ifdef USE_MOVE16
if (hasMove16() && ((uintptr)src & (ALIGN - 1)) == 0 && ((uintptr)dst & (ALIGN - 1)) == 0) {
__asm__ volatile(
" move.l %2,%%d0\n"
" lsr.l #4,%%d0\n"
" beq.b 3f\n"
" moveq #0x0f,%%d1\n"
" and.l %%d0,%%d1\n"
" neg.l %%d1\n"
" lsr.l #4,%%d0\n"
" jmp (2f,%%pc,%%d1.l*4)\n"
"1:\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
"2:\n"
" dbra %%d0,1b\n"
// handle also the unlikely case when 'dstPitch'
// is not divisible by 16 but 'src' and 'dst' are
"3:\n"
" moveq #0x0f,%%d0\n"
" and.l %2,%%d0\n"
" neg.l %%d0\n"
" jmp (4f,%%pc,%%d0.l*2)\n"
// only 15x move.b as 16 would be handled above
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
"4:\n"
: // outputs
: "a"(src), "a"(dst), "g"(dstPitch * h) // inputs
: "d0", "d1", "cc" AND_MEMORY
);
} else {
#else
{
#endif
memcpy(dst, src, dstPitch * h);
}
} else {
#ifdef USE_MOVE16
if (hasMove16() && ((uintptr)src & (ALIGN - 1)) == 0 && ((uintptr)dst & (ALIGN - 1)) == 0
&& (srcPitch & (ALIGN - 1)) == 0 && (dstPitch & (ALIGN - 1)) == 0) {
__asm__ volatile(
" move.l %2,%%d0\n"
" moveq #0x0f,%%d1\n"
" and.l %%d0,%%d1\n"
" neg.l %%d1\n"
" lea (4f,%%pc,%%d1.l*2),%%a0\n"
" move.l %%a0,%%a1\n"
" lsr.l #4,%%d0\n"
" beq.b 3f\n"
" moveq #0x0f,%%d1\n"
" and.l %%d0,%%d1\n"
" neg.l %%d1\n"
" lea (2f,%%pc,%%d1.l*4),%%a0\n"
" lsr.l #4,%%d0\n"
" move.l %%d0,%%d1\n"
"0:\n"
" move.l %%d1,%%d0\n"
" jmp (%%a0)\n"
"1:\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
" move16 (%0)+,(%1)+\n"
"2:\n"
" dbra %%d0,1b\n"
// handle (w * bytesPerPixel) % 16
"3:\n"
" jmp (%%a1)\n"
// only 15x move.b as 16 would be handled above
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
" move.b (%0)+,(%1)+\n"
"4:\n"
" add.l %4,%1\n"
" add.l %5,%0\n"
" dbra %3,0b\n"
: // outputs
: "a"(src), "a"(dst), "g"(w * bytesPerPixel), "d"(h - 1),
"g"(dstPitch - w * bytesPerPixel), "g"(srcPitch - w * bytesPerPixel) // inputs
: "d0", "d1", "a0", "a1", "cc" AND_MEMORY
);
} else {
#else
{
#endif
for (uint i = 0; i < h; ++i) {
memcpy(dst, src, w * bytesPerPixel);
dst += dstPitch;
src += srcPitch;
}
}
}
}
} // End of namespace Graphics
|
