Commit | Line | Data |
---|---|---|
ef79bbde P |
1 | /*************************************************************************** |
2 | * PCSX-Revolution - PlayStation Emulator for Nintendo Wii * | |
3 | * Copyright (C) 2009-2010 PCSX-Revolution Dev Team * | |
4 | * <http://code.google.com/p/pcsx-revolution/> * | |
5 | * * | |
6 | * This program is free software; you can redistribute it and/or modify * | |
7 | * it under the terms of the GNU General Public License as published by * | |
8 | * the Free Software Foundation; either version 2 of the License, or * | |
9 | * (at your option) any later version. * | |
10 | * * | |
11 | * This program is distributed in the hope that it will be useful, * | |
12 | * but WITHOUT ANY WARRANTY; without even the implied warranty of * | |
13 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * | |
14 | * GNU General Public License for more details. * | |
15 | * * | |
16 | * You should have received a copy of the GNU General Public License * | |
17 | * along with this program; if not, write to the * | |
18 | * Free Software Foundation, Inc., * | |
19 | * 51 Franklin Street, Fifth Floor, Boston, MA 02111-1307 USA. * | |
20 | ***************************************************************************/ | |
21 | ||
22 | /* | |
23 | * GTE functions. | |
24 | */ | |
25 | ||
26 | #include "gte.h" | |
27 | #include "psxmem.h" | |
28 | ||
f74fb727 | 29 | #define VX(n) (n < 3 ? regs->CP2D.p[n << 1].sw.l : regs->CP2D.p[9].sw.l) |
30 | #define VY(n) (n < 3 ? regs->CP2D.p[n << 1].sw.h : regs->CP2D.p[10].sw.l) | |
31 | #define VZ(n) (n < 3 ? regs->CP2D.p[(n << 1) + 1].sw.l : regs->CP2D.p[11].sw.l) | |
32 | #define MX11(n) (n < 3 ? regs->CP2C.p[(n << 3)].sw.l : 0) | |
33 | #define MX12(n) (n < 3 ? regs->CP2C.p[(n << 3)].sw.h : 0) | |
34 | #define MX13(n) (n < 3 ? regs->CP2C.p[(n << 3) + 1].sw.l : 0) | |
35 | #define MX21(n) (n < 3 ? regs->CP2C.p[(n << 3) + 1].sw.h : 0) | |
36 | #define MX22(n) (n < 3 ? regs->CP2C.p[(n << 3) + 2].sw.l : 0) | |
37 | #define MX23(n) (n < 3 ? regs->CP2C.p[(n << 3) + 2].sw.h : 0) | |
38 | #define MX31(n) (n < 3 ? regs->CP2C.p[(n << 3) + 3].sw.l : 0) | |
39 | #define MX32(n) (n < 3 ? regs->CP2C.p[(n << 3) + 3].sw.h : 0) | |
40 | #define MX33(n) (n < 3 ? regs->CP2C.p[(n << 3) + 4].sw.l : 0) | |
41 | #define CV1(n) (n < 3 ? (s32)regs->CP2C.r[(n << 3) + 5] : 0) | |
42 | #define CV2(n) (n < 3 ? (s32)regs->CP2C.r[(n << 3) + 6] : 0) | |
43 | #define CV3(n) (n < 3 ? (s32)regs->CP2C.r[(n << 3) + 7] : 0) | |
44 | ||
45 | #define fSX(n) ((regs->CP2D.p)[((n) + 12)].sw.l) | |
46 | #define fSY(n) ((regs->CP2D.p)[((n) + 12)].sw.h) | |
47 | #define fSZ(n) ((regs->CP2D.p)[((n) + 17)].w.l) /* (n == 0) => SZ1; */ | |
48 | ||
49 | #define gteVXY0 (regs->CP2D.r[0]) | |
50 | #define gteVX0 (regs->CP2D.p[0].sw.l) | |
51 | #define gteVY0 (regs->CP2D.p[0].sw.h) | |
52 | #define gteVZ0 (regs->CP2D.p[1].sw.l) | |
53 | #define gteVXY1 (regs->CP2D.r[2]) | |
54 | #define gteVX1 (regs->CP2D.p[2].sw.l) | |
55 | #define gteVY1 (regs->CP2D.p[2].sw.h) | |
56 | #define gteVZ1 (regs->CP2D.p[3].sw.l) | |
57 | #define gteVXY2 (regs->CP2D.r[4]) | |
58 | #define gteVX2 (regs->CP2D.p[4].sw.l) | |
59 | #define gteVY2 (regs->CP2D.p[4].sw.h) | |
60 | #define gteVZ2 (regs->CP2D.p[5].sw.l) | |
61 | #define gteRGB (regs->CP2D.r[6]) | |
62 | #define gteR (regs->CP2D.p[6].b.l) | |
63 | #define gteG (regs->CP2D.p[6].b.h) | |
64 | #define gteB (regs->CP2D.p[6].b.h2) | |
65 | #define gteCODE (regs->CP2D.p[6].b.h3) | |
66 | #define gteOTZ (regs->CP2D.p[7].w.l) | |
67 | #define gteIR0 (regs->CP2D.p[8].sw.l) | |
68 | #define gteIR1 (regs->CP2D.p[9].sw.l) | |
69 | #define gteIR2 (regs->CP2D.p[10].sw.l) | |
70 | #define gteIR3 (regs->CP2D.p[11].sw.l) | |
71 | #define gteSXY0 (regs->CP2D.r[12]) | |
72 | #define gteSX0 (regs->CP2D.p[12].sw.l) | |
73 | #define gteSY0 (regs->CP2D.p[12].sw.h) | |
74 | #define gteSXY1 (regs->CP2D.r[13]) | |
75 | #define gteSX1 (regs->CP2D.p[13].sw.l) | |
76 | #define gteSY1 (regs->CP2D.p[13].sw.h) | |
77 | #define gteSXY2 (regs->CP2D.r[14]) | |
78 | #define gteSX2 (regs->CP2D.p[14].sw.l) | |
79 | #define gteSY2 (regs->CP2D.p[14].sw.h) | |
80 | #define gteSXYP (regs->CP2D.r[15]) | |
81 | #define gteSXP (regs->CP2D.p[15].sw.l) | |
82 | #define gteSYP (regs->CP2D.p[15].sw.h) | |
83 | #define gteSZ0 (regs->CP2D.p[16].w.l) | |
84 | #define gteSZ1 (regs->CP2D.p[17].w.l) | |
85 | #define gteSZ2 (regs->CP2D.p[18].w.l) | |
86 | #define gteSZ3 (regs->CP2D.p[19].w.l) | |
87 | #define gteRGB0 (regs->CP2D.r[20]) | |
88 | #define gteR0 (regs->CP2D.p[20].b.l) | |
89 | #define gteG0 (regs->CP2D.p[20].b.h) | |
90 | #define gteB0 (regs->CP2D.p[20].b.h2) | |
91 | #define gteCODE0 (regs->CP2D.p[20].b.h3) | |
92 | #define gteRGB1 (regs->CP2D.r[21]) | |
93 | #define gteR1 (regs->CP2D.p[21].b.l) | |
94 | #define gteG1 (regs->CP2D.p[21].b.h) | |
95 | #define gteB1 (regs->CP2D.p[21].b.h2) | |
96 | #define gteCODE1 (regs->CP2D.p[21].b.h3) | |
97 | #define gteRGB2 (regs->CP2D.r[22]) | |
98 | #define gteR2 (regs->CP2D.p[22].b.l) | |
99 | #define gteG2 (regs->CP2D.p[22].b.h) | |
100 | #define gteB2 (regs->CP2D.p[22].b.h2) | |
101 | #define gteCODE2 (regs->CP2D.p[22].b.h3) | |
102 | #define gteRES1 (regs->CP2D.r[23]) | |
103 | #define gteMAC0 (((s32 *)regs->CP2D.r)[24]) | |
104 | #define gteMAC1 (((s32 *)regs->CP2D.r)[25]) | |
105 | #define gteMAC2 (((s32 *)regs->CP2D.r)[26]) | |
106 | #define gteMAC3 (((s32 *)regs->CP2D.r)[27]) | |
107 | #define gteIRGB (regs->CP2D.r[28]) | |
108 | #define gteORGB (regs->CP2D.r[29]) | |
109 | #define gteLZCS (regs->CP2D.r[30]) | |
110 | #define gteLZCR (regs->CP2D.r[31]) | |
111 | ||
112 | #define gteR11R12 (((s32 *)regs->CP2C.r)[0]) | |
113 | #define gteR22R23 (((s32 *)regs->CP2C.r)[2]) | |
114 | #define gteR11 (regs->CP2C.p[0].sw.l) | |
115 | #define gteR12 (regs->CP2C.p[0].sw.h) | |
116 | #define gteR13 (regs->CP2C.p[1].sw.l) | |
117 | #define gteR21 (regs->CP2C.p[1].sw.h) | |
118 | #define gteR22 (regs->CP2C.p[2].sw.l) | |
119 | #define gteR23 (regs->CP2C.p[2].sw.h) | |
120 | #define gteR31 (regs->CP2C.p[3].sw.l) | |
121 | #define gteR32 (regs->CP2C.p[3].sw.h) | |
122 | #define gteR33 (regs->CP2C.p[4].sw.l) | |
123 | #define gteTRX (((s32 *)regs->CP2C.r)[5]) | |
124 | #define gteTRY (((s32 *)regs->CP2C.r)[6]) | |
125 | #define gteTRZ (((s32 *)regs->CP2C.r)[7]) | |
126 | #define gteL11 (regs->CP2C.p[8].sw.l) | |
127 | #define gteL12 (regs->CP2C.p[8].sw.h) | |
128 | #define gteL13 (regs->CP2C.p[9].sw.l) | |
129 | #define gteL21 (regs->CP2C.p[9].sw.h) | |
130 | #define gteL22 (regs->CP2C.p[10].sw.l) | |
131 | #define gteL23 (regs->CP2C.p[10].sw.h) | |
132 | #define gteL31 (regs->CP2C.p[11].sw.l) | |
133 | #define gteL32 (regs->CP2C.p[11].sw.h) | |
134 | #define gteL33 (regs->CP2C.p[12].sw.l) | |
135 | #define gteRBK (((s32 *)regs->CP2C.r)[13]) | |
136 | #define gteGBK (((s32 *)regs->CP2C.r)[14]) | |
137 | #define gteBBK (((s32 *)regs->CP2C.r)[15]) | |
138 | #define gteLR1 (regs->CP2C.p[16].sw.l) | |
139 | #define gteLR2 (regs->CP2C.p[16].sw.h) | |
140 | #define gteLR3 (regs->CP2C.p[17].sw.l) | |
141 | #define gteLG1 (regs->CP2C.p[17].sw.h) | |
142 | #define gteLG2 (regs->CP2C.p[18].sw.l) | |
143 | #define gteLG3 (regs->CP2C.p[18].sw.h) | |
144 | #define gteLB1 (regs->CP2C.p[19].sw.l) | |
145 | #define gteLB2 (regs->CP2C.p[19].sw.h) | |
146 | #define gteLB3 (regs->CP2C.p[20].sw.l) | |
147 | #define gteRFC (((s32 *)regs->CP2C.r)[21]) | |
148 | #define gteGFC (((s32 *)regs->CP2C.r)[22]) | |
149 | #define gteBFC (((s32 *)regs->CP2C.r)[23]) | |
150 | #define gteOFX (((s32 *)regs->CP2C.r)[24]) | |
151 | #define gteOFY (((s32 *)regs->CP2C.r)[25]) | |
152 | #define gteH (regs->CP2C.p[26].sw.l) | |
153 | #define gteDQA (regs->CP2C.p[27].sw.l) | |
154 | #define gteDQB (((s32 *)regs->CP2C.r)[28]) | |
155 | #define gteZSF3 (regs->CP2C.p[29].sw.l) | |
156 | #define gteZSF4 (regs->CP2C.p[30].sw.l) | |
157 | #define gteFLAG (regs->CP2C.r[31]) | |
ef79bbde P |
158 | |
159 | #define GTE_OP(op) ((op >> 20) & 31) | |
160 | #define GTE_SF(op) ((op >> 19) & 1) | |
161 | #define GTE_MX(op) ((op >> 17) & 3) | |
162 | #define GTE_V(op) ((op >> 15) & 3) | |
163 | #define GTE_CV(op) ((op >> 13) & 3) | |
164 | #define GTE_CD(op) ((op >> 11) & 3) /* not used */ | |
165 | #define GTE_LM(op) ((op >> 10) & 1) | |
166 | #define GTE_CT(op) ((op >> 6) & 15) /* not used */ | |
167 | #define GTE_FUNCT(op) (op & 63) | |
168 | ||
169 | #define gteop (psxRegs.code & 0x1ffffff) | |
170 | ||
59774ed0 | 171 | #ifndef FLAGLESS |
172 | ||
e2a9a9a5 | 173 | static inline s64 BOUNDS_(psxCP2Regs *regs, s64 n_value, s64 n_max, int n_maxflag, s64 n_min, int n_minflag) { |
ef79bbde P |
174 | if (n_value > n_max) { |
175 | gteFLAG |= n_maxflag; | |
176 | } else if (n_value < n_min) { | |
177 | gteFLAG |= n_minflag; | |
178 | } | |
179 | return n_value; | |
180 | } | |
181 | ||
f74fb727 | 182 | static inline s32 LIM_(psxCP2Regs *regs, s32 value, s32 max, s32 min, u32 flag) { |
ef79bbde P |
183 | s32 ret = value; |
184 | if (value > max) { | |
185 | gteFLAG |= flag; | |
186 | ret = max; | |
187 | } else if (value < min) { | |
188 | gteFLAG |= flag; | |
189 | ret = min; | |
190 | } | |
191 | return ret; | |
192 | } | |
193 | ||
f74fb727 | 194 | static inline u32 limE_(psxCP2Regs *regs, u32 result) { |
59774ed0 | 195 | if (result > 0x1ffff) { |
196 | gteFLAG |= (1 << 31) | (1 << 17); | |
197 | return 0x1ffff; | |
198 | } | |
199 | return result; | |
200 | } | |
201 | ||
202 | #else | |
203 | ||
f74fb727 | 204 | #define BOUNDS_(regs, a, ...) (a) |
59774ed0 | 205 | |
f74fb727 | 206 | static inline s32 LIM_(psxCP2Regs *regs, s32 value, s32 max, s32 min, u32 flag_unused) { |
59774ed0 | 207 | s32 ret = value; |
208 | if (value > max) | |
209 | ret = max; | |
210 | else if (value < min) | |
211 | ret = min; | |
212 | return ret; | |
213 | } | |
214 | ||
f74fb727 | 215 | static inline u32 limE_(psxCP2Regs *regs, u32 result) { |
bedfea38 | 216 | if (result > 0x1ffff) |
217 | return 0x1ffff; | |
218 | return result; | |
219 | } | |
59774ed0 | 220 | |
221 | #endif | |
222 | ||
f74fb727 | 223 | #define BOUNDS(n_value,n_max,n_maxflag,n_min,n_minflag) \ |
224 | BOUNDS_(regs,n_value,n_max,n_maxflag,n_min,n_minflag) | |
225 | #define LIM(value,max,min,flag) \ | |
226 | LIM_(regs,value,max,min,flag) | |
227 | #define limE(result) \ | |
228 | limE_(regs,result) | |
229 | ||
ef79bbde P |
230 | #define A1(a) BOUNDS((a), 0x7fffffff, (1 << 30), -(s64)0x80000000, (1 << 31) | (1 << 27)) |
231 | #define A2(a) BOUNDS((a), 0x7fffffff, (1 << 29), -(s64)0x80000000, (1 << 31) | (1 << 26)) | |
232 | #define A3(a) BOUNDS((a), 0x7fffffff, (1 << 28), -(s64)0x80000000, (1 << 31) | (1 << 25)) | |
233 | #define limB1(a, l) LIM((a), 0x7fff, -0x8000 * !l, (1 << 31) | (1 << 24)) | |
234 | #define limB2(a, l) LIM((a), 0x7fff, -0x8000 * !l, (1 << 31) | (1 << 23)) | |
235 | #define limB3(a, l) LIM((a), 0x7fff, -0x8000 * !l, (1 << 22)) | |
236 | #define limC1(a) LIM((a), 0x00ff, 0x0000, (1 << 21)) | |
237 | #define limC2(a) LIM((a), 0x00ff, 0x0000, (1 << 20)) | |
238 | #define limC3(a) LIM((a), 0x00ff, 0x0000, (1 << 19)) | |
239 | #define limD(a) LIM((a), 0xffff, 0x0000, (1 << 31) | (1 << 18)) | |
240 | ||
ef79bbde P |
241 | #define F(a) BOUNDS((a), 0x7fffffff, (1 << 31) | (1 << 16), -(s64)0x80000000, (1 << 31) | (1 << 15)) |
242 | #define limG1(a) LIM((a), 0x3ff, -0x400, (1 << 31) | (1 << 14)) | |
243 | #define limG2(a) LIM((a), 0x3ff, -0x400, (1 << 31) | (1 << 13)) | |
7384197d | 244 | #define limH(a) LIM((a), 0x1000, 0x0000, (1 << 12)) |
ef79bbde | 245 | |
6c6c9590 | 246 | #ifndef __arm__ |
247 | #define A1U A1 | |
248 | #define A2U A2 | |
249 | #define A3U A3 | |
250 | #else | |
251 | /* these are unlikely to be hit and usually waste cycles, don't want them on ARM */ | |
252 | #define A1U(x) (x) | |
253 | #define A2U(x) (x) | |
254 | #define A3U(x) (x) | |
255 | #endif | |
256 | ||
ef79bbde P |
257 | #include "gte_divider.h" |
258 | ||
59774ed0 | 259 | #ifndef FLAGLESS |
260 | ||
6f1edc3c | 261 | u32 MFC2(int reg) { |
eac38522 | 262 | psxCP2Regs *regs = &psxRegs.CP2; |
ef79bbde P |
263 | switch (reg) { |
264 | case 1: | |
265 | case 3: | |
266 | case 5: | |
267 | case 8: | |
268 | case 9: | |
269 | case 10: | |
270 | case 11: | |
271 | psxRegs.CP2D.r[reg] = (s32)psxRegs.CP2D.p[reg].sw.l; | |
272 | break; | |
273 | ||
274 | case 7: | |
275 | case 16: | |
276 | case 17: | |
277 | case 18: | |
278 | case 19: | |
279 | psxRegs.CP2D.r[reg] = (u32)psxRegs.CP2D.p[reg].w.l; | |
280 | break; | |
281 | ||
282 | case 15: | |
283 | psxRegs.CP2D.r[reg] = gteSXY2; | |
284 | break; | |
285 | ||
286 | case 28: | |
ef79bbde P |
287 | case 29: |
288 | psxRegs.CP2D.r[reg] = LIM(gteIR1 >> 7, 0x1f, 0, 0) | | |
289 | (LIM(gteIR2 >> 7, 0x1f, 0, 0) << 5) | | |
290 | (LIM(gteIR3 >> 7, 0x1f, 0, 0) << 10); | |
291 | break; | |
292 | } | |
293 | return psxRegs.CP2D.r[reg]; | |
294 | } | |
295 | ||
6f1edc3c | 296 | void MTC2(u32 value, int reg) { |
eac38522 | 297 | psxCP2Regs *regs = &psxRegs.CP2; |
ef79bbde P |
298 | switch (reg) { |
299 | case 15: | |
300 | gteSXY0 = gteSXY1; | |
301 | gteSXY1 = gteSXY2; | |
302 | gteSXY2 = value; | |
303 | gteSXYP = value; | |
304 | break; | |
305 | ||
306 | case 28: | |
307 | gteIRGB = value; | |
308 | gteIR1 = (value & 0x1f) << 7; | |
309 | gteIR2 = (value & 0x3e0) << 2; | |
310 | gteIR3 = (value & 0x7c00) >> 3; | |
311 | break; | |
312 | ||
313 | case 30: | |
314 | { | |
315 | int a; | |
316 | gteLZCS = value; | |
317 | ||
318 | a = gteLZCS; | |
319 | if (a > 0) { | |
320 | int i; | |
321 | for (i = 31; (a & (1 << i)) == 0 && i >= 0; i--); | |
322 | gteLZCR = 31 - i; | |
323 | } else if (a < 0) { | |
324 | int i; | |
325 | a ^= 0xffffffff; | |
326 | for (i = 31; (a & (1 << i)) == 0 && i >= 0; i--); | |
327 | gteLZCR = 31 - i; | |
328 | } else { | |
329 | gteLZCR = 32; | |
330 | } | |
331 | } | |
332 | break; | |
333 | ||
ef79bbde P |
334 | case 31: |
335 | return; | |
336 | ||
337 | default: | |
338 | psxRegs.CP2D.r[reg] = value; | |
339 | } | |
340 | } | |
341 | ||
6f1edc3c | 342 | void CTC2(u32 value, int reg) { |
ef79bbde P |
343 | switch (reg) { |
344 | case 4: | |
345 | case 12: | |
346 | case 20: | |
347 | case 26: | |
348 | case 27: | |
349 | case 29: | |
350 | case 30: | |
351 | value = (s32)(s16)value; | |
352 | break; | |
353 | ||
354 | case 31: | |
355 | value = value & 0x7ffff000; | |
356 | if (value & 0x7f87e000) value |= 0x80000000; | |
357 | break; | |
358 | } | |
359 | ||
360 | psxRegs.CP2C.r[reg] = value; | |
361 | } | |
362 | ||
363 | void gteMFC2() { | |
364 | if (!_Rt_) return; | |
365 | psxRegs.GPR.r[_Rt_] = MFC2(_Rd_); | |
366 | } | |
367 | ||
368 | void gteCFC2() { | |
369 | if (!_Rt_) return; | |
370 | psxRegs.GPR.r[_Rt_] = psxRegs.CP2C.r[_Rd_]; | |
371 | } | |
372 | ||
373 | void gteMTC2() { | |
374 | MTC2(psxRegs.GPR.r[_Rt_], _Rd_); | |
375 | } | |
376 | ||
377 | void gteCTC2() { | |
378 | CTC2(psxRegs.GPR.r[_Rt_], _Rd_); | |
379 | } | |
380 | ||
381 | #define _oB_ (psxRegs.GPR.r[_Rs_] + _Imm_) | |
382 | ||
383 | void gteLWC2() { | |
384 | MTC2(psxMemRead32(_oB_), _Rt_); | |
385 | } | |
386 | ||
387 | void gteSWC2() { | |
388 | psxMemWrite32(_oB_, MFC2(_Rt_)); | |
389 | } | |
390 | ||
59774ed0 | 391 | #endif // FLAGLESS |
392 | ||
3ebefe71 | 393 | #if 0 |
a2544c92 | 394 | #define DIVIDE DIVIDE_ |
395 | static u32 DIVIDE_(s16 n, u16 d) { | |
396 | if (n >= 0 && n < d * 2) { | |
397 | s32 n_ = n; | |
398 | return ((n_ << 16) + d / 2) / d; | |
399 | //return (u32)((float)(n_ << 16) / (float)d + (float)0.5); | |
400 | } | |
401 | return 0xffffffff; | |
402 | } | |
3ebefe71 | 403 | #endif |
a2544c92 | 404 | |
f74fb727 | 405 | void gteRTPS(psxCP2Regs *regs) { |
ef79bbde | 406 | int quotient; |
e2a9a9a5 | 407 | s64 tmp; |
ef79bbde P |
408 | |
409 | #ifdef GTE_LOG | |
410 | GTE_LOG("GTE RTPS\n"); | |
411 | #endif | |
412 | gteFLAG = 0; | |
413 | ||
414 | gteMAC1 = A1((((s64)gteTRX << 12) + (gteR11 * gteVX0) + (gteR12 * gteVY0) + (gteR13 * gteVZ0)) >> 12); | |
415 | gteMAC2 = A2((((s64)gteTRY << 12) + (gteR21 * gteVX0) + (gteR22 * gteVY0) + (gteR23 * gteVZ0)) >> 12); | |
416 | gteMAC3 = A3((((s64)gteTRZ << 12) + (gteR31 * gteVX0) + (gteR32 * gteVY0) + (gteR33 * gteVZ0)) >> 12); | |
417 | gteIR1 = limB1(gteMAC1, 0); | |
418 | gteIR2 = limB2(gteMAC2, 0); | |
419 | gteIR3 = limB3(gteMAC3, 0); | |
420 | gteSZ0 = gteSZ1; | |
421 | gteSZ1 = gteSZ2; | |
422 | gteSZ2 = gteSZ3; | |
423 | gteSZ3 = limD(gteMAC3); | |
424 | quotient = limE(DIVIDE(gteH, gteSZ3)); | |
425 | gteSXY0 = gteSXY1; | |
426 | gteSXY1 = gteSXY2; | |
427 | gteSX2 = limG1(F((s64)gteOFX + ((s64)gteIR1 * quotient)) >> 16); | |
428 | gteSY2 = limG2(F((s64)gteOFY + ((s64)gteIR2 * quotient)) >> 16); | |
429 | ||
e2a9a9a5 | 430 | tmp = (s64)gteDQB + ((s64)gteDQA * quotient); |
431 | gteMAC0 = F(tmp); | |
432 | gteIR0 = limH(tmp >> 12); | |
ef79bbde P |
433 | } |
434 | ||
f74fb727 | 435 | void gteRTPT(psxCP2Regs *regs) { |
ef79bbde P |
436 | int quotient; |
437 | int v; | |
438 | s32 vx, vy, vz; | |
e2a9a9a5 | 439 | s64 tmp; |
ef79bbde P |
440 | |
441 | #ifdef GTE_LOG | |
442 | GTE_LOG("GTE RTPT\n"); | |
443 | #endif | |
444 | gteFLAG = 0; | |
445 | ||
446 | gteSZ0 = gteSZ3; | |
447 | for (v = 0; v < 3; v++) { | |
448 | vx = VX(v); | |
449 | vy = VY(v); | |
450 | vz = VZ(v); | |
451 | gteMAC1 = A1((((s64)gteTRX << 12) + (gteR11 * vx) + (gteR12 * vy) + (gteR13 * vz)) >> 12); | |
452 | gteMAC2 = A2((((s64)gteTRY << 12) + (gteR21 * vx) + (gteR22 * vy) + (gteR23 * vz)) >> 12); | |
453 | gteMAC3 = A3((((s64)gteTRZ << 12) + (gteR31 * vx) + (gteR32 * vy) + (gteR33 * vz)) >> 12); | |
454 | gteIR1 = limB1(gteMAC1, 0); | |
455 | gteIR2 = limB2(gteMAC2, 0); | |
456 | gteIR3 = limB3(gteMAC3, 0); | |
457 | fSZ(v) = limD(gteMAC3); | |
458 | quotient = limE(DIVIDE(gteH, fSZ(v))); | |
459 | fSX(v) = limG1(F((s64)gteOFX + ((s64)gteIR1 * quotient)) >> 16); | |
460 | fSY(v) = limG2(F((s64)gteOFY + ((s64)gteIR2 * quotient)) >> 16); | |
461 | } | |
e2a9a9a5 | 462 | |
463 | tmp = (s64)gteDQB + ((s64)gteDQA * quotient); | |
464 | gteMAC0 = F(tmp); | |
465 | gteIR0 = limH(tmp >> 12); | |
ef79bbde P |
466 | } |
467 | ||
f74fb727 | 468 | void gteMVMVA(psxCP2Regs *regs) { |
ef79bbde P |
469 | int shift = 12 * GTE_SF(gteop); |
470 | int mx = GTE_MX(gteop); | |
471 | int v = GTE_V(gteop); | |
472 | int cv = GTE_CV(gteop); | |
473 | int lm = GTE_LM(gteop); | |
474 | s32 vx = VX(v); | |
475 | s32 vy = VY(v); | |
476 | s32 vz = VZ(v); | |
477 | ||
478 | #ifdef GTE_LOG | |
479 | GTE_LOG("GTE MVMVA\n"); | |
480 | #endif | |
481 | gteFLAG = 0; | |
482 | ||
483 | gteMAC1 = A1((((s64)CV1(cv) << 12) + (MX11(mx) * vx) + (MX12(mx) * vy) + (MX13(mx) * vz)) >> shift); | |
484 | gteMAC2 = A2((((s64)CV2(cv) << 12) + (MX21(mx) * vx) + (MX22(mx) * vy) + (MX23(mx) * vz)) >> shift); | |
485 | gteMAC3 = A3((((s64)CV3(cv) << 12) + (MX31(mx) * vx) + (MX32(mx) * vy) + (MX33(mx) * vz)) >> shift); | |
486 | ||
487 | gteIR1 = limB1(gteMAC1, lm); | |
488 | gteIR2 = limB2(gteMAC2, lm); | |
489 | gteIR3 = limB3(gteMAC3, lm); | |
490 | } | |
491 | ||
f74fb727 | 492 | void gteNCLIP(psxCP2Regs *regs) { |
ef79bbde P |
493 | #ifdef GTE_LOG |
494 | GTE_LOG("GTE NCLIP\n"); | |
495 | #endif | |
496 | gteFLAG = 0; | |
497 | ||
498 | gteMAC0 = F((s64)gteSX0 * (gteSY1 - gteSY2) + | |
499 | gteSX1 * (gteSY2 - gteSY0) + | |
500 | gteSX2 * (gteSY0 - gteSY1)); | |
501 | } | |
502 | ||
f74fb727 | 503 | void gteAVSZ3(psxCP2Regs *regs) { |
ef79bbde P |
504 | #ifdef GTE_LOG |
505 | GTE_LOG("GTE AVSZ3\n"); | |
506 | #endif | |
507 | gteFLAG = 0; | |
508 | ||
b3254af9 | 509 | gteMAC0 = F((s64)gteZSF3 * (gteSZ1 + gteSZ2 + gteSZ3)); |
ef79bbde P |
510 | gteOTZ = limD(gteMAC0 >> 12); |
511 | } | |
512 | ||
f74fb727 | 513 | void gteAVSZ4(psxCP2Regs *regs) { |
ef79bbde P |
514 | #ifdef GTE_LOG |
515 | GTE_LOG("GTE AVSZ4\n"); | |
516 | #endif | |
517 | gteFLAG = 0; | |
518 | ||
b3254af9 | 519 | gteMAC0 = F((s64)gteZSF4 * (gteSZ0 + gteSZ1 + gteSZ2 + gteSZ3)); |
ef79bbde P |
520 | gteOTZ = limD(gteMAC0 >> 12); |
521 | } | |
522 | ||
f74fb727 | 523 | void gteSQR(psxCP2Regs *regs) { |
ef79bbde P |
524 | int shift = 12 * GTE_SF(gteop); |
525 | int lm = GTE_LM(gteop); | |
526 | ||
527 | #ifdef GTE_LOG | |
528 | GTE_LOG("GTE SQR\n"); | |
529 | #endif | |
530 | gteFLAG = 0; | |
531 | ||
b3254af9 | 532 | gteMAC1 = (gteIR1 * gteIR1) >> shift; |
533 | gteMAC2 = (gteIR2 * gteIR2) >> shift; | |
534 | gteMAC3 = (gteIR3 * gteIR3) >> shift; | |
7384197d | 535 | gteIR1 = limB1(gteMAC1, lm); |
536 | gteIR2 = limB2(gteMAC2, lm); | |
537 | gteIR3 = limB3(gteMAC3, lm); | |
ef79bbde P |
538 | } |
539 | ||
f74fb727 | 540 | void gteNCCS(psxCP2Regs *regs) { |
ef79bbde P |
541 | #ifdef GTE_LOG |
542 | GTE_LOG("GTE NCCS\n"); | |
543 | #endif | |
544 | gteFLAG = 0; | |
545 | ||
b3254af9 | 546 | gteMAC1 = ((s64)(gteL11 * gteVX0) + (gteL12 * gteVY0) + (gteL13 * gteVZ0)) >> 12; |
547 | gteMAC2 = ((s64)(gteL21 * gteVX0) + (gteL22 * gteVY0) + (gteL23 * gteVZ0)) >> 12; | |
548 | gteMAC3 = ((s64)(gteL31 * gteVX0) + (gteL32 * gteVY0) + (gteL33 * gteVZ0)) >> 12; | |
ef79bbde P |
549 | gteIR1 = limB1(gteMAC1, 1); |
550 | gteIR2 = limB2(gteMAC2, 1); | |
551 | gteIR3 = limB3(gteMAC3, 1); | |
552 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
553 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
554 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
555 | gteIR1 = limB1(gteMAC1, 1); | |
556 | gteIR2 = limB2(gteMAC2, 1); | |
557 | gteIR3 = limB3(gteMAC3, 1); | |
b3254af9 | 558 | gteMAC1 = ((s32)gteR * gteIR1) >> 8; |
559 | gteMAC2 = ((s32)gteG * gteIR2) >> 8; | |
560 | gteMAC3 = ((s32)gteB * gteIR3) >> 8; | |
561 | gteIR1 = gteMAC1; | |
562 | gteIR2 = gteMAC2; | |
563 | gteIR3 = gteMAC3; | |
ef79bbde P |
564 | |
565 | gteRGB0 = gteRGB1; | |
566 | gteRGB1 = gteRGB2; | |
567 | gteCODE2 = gteCODE; | |
568 | gteR2 = limC1(gteMAC1 >> 4); | |
569 | gteG2 = limC2(gteMAC2 >> 4); | |
570 | gteB2 = limC3(gteMAC3 >> 4); | |
571 | } | |
572 | ||
f74fb727 | 573 | void gteNCCT(psxCP2Regs *regs) { |
ef79bbde P |
574 | int v; |
575 | s32 vx, vy, vz; | |
576 | ||
577 | #ifdef GTE_LOG | |
578 | GTE_LOG("GTE NCCT\n"); | |
579 | #endif | |
580 | gteFLAG = 0; | |
581 | ||
582 | for (v = 0; v < 3; v++) { | |
583 | vx = VX(v); | |
584 | vy = VY(v); | |
585 | vz = VZ(v); | |
b3254af9 | 586 | gteMAC1 = ((s64)(gteL11 * vx) + (gteL12 * vy) + (gteL13 * vz)) >> 12; |
587 | gteMAC2 = ((s64)(gteL21 * vx) + (gteL22 * vy) + (gteL23 * vz)) >> 12; | |
588 | gteMAC3 = ((s64)(gteL31 * vx) + (gteL32 * vy) + (gteL33 * vz)) >> 12; | |
ef79bbde P |
589 | gteIR1 = limB1(gteMAC1, 1); |
590 | gteIR2 = limB2(gteMAC2, 1); | |
591 | gteIR3 = limB3(gteMAC3, 1); | |
592 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
593 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
594 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
595 | gteIR1 = limB1(gteMAC1, 1); | |
596 | gteIR2 = limB2(gteMAC2, 1); | |
597 | gteIR3 = limB3(gteMAC3, 1); | |
b3254af9 | 598 | gteMAC1 = ((s32)gteR * gteIR1) >> 8; |
599 | gteMAC2 = ((s32)gteG * gteIR2) >> 8; | |
600 | gteMAC3 = ((s32)gteB * gteIR3) >> 8; | |
ef79bbde P |
601 | |
602 | gteRGB0 = gteRGB1; | |
603 | gteRGB1 = gteRGB2; | |
604 | gteCODE2 = gteCODE; | |
605 | gteR2 = limC1(gteMAC1 >> 4); | |
606 | gteG2 = limC2(gteMAC2 >> 4); | |
607 | gteB2 = limC3(gteMAC3 >> 4); | |
608 | } | |
b3254af9 | 609 | gteIR1 = gteMAC1; |
610 | gteIR2 = gteMAC2; | |
611 | gteIR3 = gteMAC3; | |
ef79bbde P |
612 | } |
613 | ||
f74fb727 | 614 | void gteNCDS(psxCP2Regs *regs) { |
ef79bbde P |
615 | #ifdef GTE_LOG |
616 | GTE_LOG("GTE NCDS\n"); | |
617 | #endif | |
618 | gteFLAG = 0; | |
619 | ||
b3254af9 | 620 | gteMAC1 = ((s64)(gteL11 * gteVX0) + (gteL12 * gteVY0) + (gteL13 * gteVZ0)) >> 12; |
621 | gteMAC2 = ((s64)(gteL21 * gteVX0) + (gteL22 * gteVY0) + (gteL23 * gteVZ0)) >> 12; | |
622 | gteMAC3 = ((s64)(gteL31 * gteVX0) + (gteL32 * gteVY0) + (gteL33 * gteVZ0)) >> 12; | |
ef79bbde P |
623 | gteIR1 = limB1(gteMAC1, 1); |
624 | gteIR2 = limB2(gteMAC2, 1); | |
625 | gteIR3 = limB3(gteMAC3, 1); | |
626 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
627 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
628 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
629 | gteIR1 = limB1(gteMAC1, 1); | |
630 | gteIR2 = limB2(gteMAC2, 1); | |
631 | gteIR3 = limB3(gteMAC3, 1); | |
6c6c9590 | 632 | gteMAC1 = (((gteR << 4) * gteIR1) + (gteIR0 * limB1(A1U((s64)gteRFC - ((gteR * gteIR1) >> 8)), 0))) >> 12; |
633 | gteMAC2 = (((gteG << 4) * gteIR2) + (gteIR0 * limB2(A2U((s64)gteGFC - ((gteG * gteIR2) >> 8)), 0))) >> 12; | |
634 | gteMAC3 = (((gteB << 4) * gteIR3) + (gteIR0 * limB3(A3U((s64)gteBFC - ((gteB * gteIR3) >> 8)), 0))) >> 12; | |
ef79bbde P |
635 | gteIR1 = limB1(gteMAC1, 1); |
636 | gteIR2 = limB2(gteMAC2, 1); | |
637 | gteIR3 = limB3(gteMAC3, 1); | |
638 | ||
639 | gteRGB0 = gteRGB1; | |
640 | gteRGB1 = gteRGB2; | |
641 | gteCODE2 = gteCODE; | |
642 | gteR2 = limC1(gteMAC1 >> 4); | |
643 | gteG2 = limC2(gteMAC2 >> 4); | |
644 | gteB2 = limC3(gteMAC3 >> 4); | |
645 | } | |
646 | ||
f74fb727 | 647 | void gteNCDT(psxCP2Regs *regs) { |
ef79bbde P |
648 | int v; |
649 | s32 vx, vy, vz; | |
650 | ||
651 | #ifdef GTE_LOG | |
652 | GTE_LOG("GTE NCDT\n"); | |
653 | #endif | |
654 | gteFLAG = 0; | |
655 | ||
656 | for (v = 0; v < 3; v++) { | |
657 | vx = VX(v); | |
658 | vy = VY(v); | |
659 | vz = VZ(v); | |
b3254af9 | 660 | gteMAC1 = ((s64)(gteL11 * vx) + (gteL12 * vy) + (gteL13 * vz)) >> 12; |
661 | gteMAC2 = ((s64)(gteL21 * vx) + (gteL22 * vy) + (gteL23 * vz)) >> 12; | |
662 | gteMAC3 = ((s64)(gteL31 * vx) + (gteL32 * vy) + (gteL33 * vz)) >> 12; | |
ef79bbde P |
663 | gteIR1 = limB1(gteMAC1, 1); |
664 | gteIR2 = limB2(gteMAC2, 1); | |
665 | gteIR3 = limB3(gteMAC3, 1); | |
666 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
667 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
668 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
669 | gteIR1 = limB1(gteMAC1, 1); | |
670 | gteIR2 = limB2(gteMAC2, 1); | |
671 | gteIR3 = limB3(gteMAC3, 1); | |
6c6c9590 | 672 | gteMAC1 = (((gteR << 4) * gteIR1) + (gteIR0 * limB1(A1U((s64)gteRFC - ((gteR * gteIR1) >> 8)), 0))) >> 12; |
673 | gteMAC2 = (((gteG << 4) * gteIR2) + (gteIR0 * limB2(A2U((s64)gteGFC - ((gteG * gteIR2) >> 8)), 0))) >> 12; | |
674 | gteMAC3 = (((gteB << 4) * gteIR3) + (gteIR0 * limB3(A3U((s64)gteBFC - ((gteB * gteIR3) >> 8)), 0))) >> 12; | |
ef79bbde P |
675 | |
676 | gteRGB0 = gteRGB1; | |
677 | gteRGB1 = gteRGB2; | |
678 | gteCODE2 = gteCODE; | |
679 | gteR2 = limC1(gteMAC1 >> 4); | |
680 | gteG2 = limC2(gteMAC2 >> 4); | |
681 | gteB2 = limC3(gteMAC3 >> 4); | |
682 | } | |
683 | gteIR1 = limB1(gteMAC1, 1); | |
684 | gteIR2 = limB2(gteMAC2, 1); | |
685 | gteIR3 = limB3(gteMAC3, 1); | |
686 | } | |
687 | ||
f74fb727 | 688 | void gteOP(psxCP2Regs *regs) { |
ef79bbde P |
689 | int shift = 12 * GTE_SF(gteop); |
690 | int lm = GTE_LM(gteop); | |
691 | ||
692 | #ifdef GTE_LOG | |
693 | GTE_LOG("GTE OP\n"); | |
694 | #endif | |
695 | gteFLAG = 0; | |
696 | ||
b3254af9 | 697 | gteMAC1 = ((gteR22 * gteIR3) - (gteR33 * gteIR2)) >> shift; |
698 | gteMAC2 = ((gteR33 * gteIR1) - (gteR11 * gteIR3)) >> shift; | |
699 | gteMAC3 = ((gteR11 * gteIR2) - (gteR22 * gteIR1)) >> shift; | |
ef79bbde P |
700 | gteIR1 = limB1(gteMAC1, lm); |
701 | gteIR2 = limB2(gteMAC2, lm); | |
702 | gteIR3 = limB3(gteMAC3, lm); | |
703 | } | |
704 | ||
f74fb727 | 705 | void gteDCPL(psxCP2Regs *regs) { |
ef79bbde P |
706 | int lm = GTE_LM(gteop); |
707 | ||
b3254af9 | 708 | s32 RIR1 = ((s32)gteR * gteIR1) >> 8; |
709 | s32 GIR2 = ((s32)gteG * gteIR2) >> 8; | |
710 | s32 BIR3 = ((s32)gteB * gteIR3) >> 8; | |
ef79bbde P |
711 | |
712 | #ifdef GTE_LOG | |
713 | GTE_LOG("GTE DCPL\n"); | |
714 | #endif | |
715 | gteFLAG = 0; | |
716 | ||
6c6c9590 | 717 | gteMAC1 = RIR1 + ((gteIR0 * limB1(A1U((s64)gteRFC - RIR1), 0)) >> 12); |
718 | gteMAC2 = GIR2 + ((gteIR0 * limB1(A2U((s64)gteGFC - GIR2), 0)) >> 12); | |
719 | gteMAC3 = BIR3 + ((gteIR0 * limB1(A3U((s64)gteBFC - BIR3), 0)) >> 12); | |
ef79bbde P |
720 | |
721 | gteIR1 = limB1(gteMAC1, lm); | |
722 | gteIR2 = limB2(gteMAC2, lm); | |
723 | gteIR3 = limB3(gteMAC3, lm); | |
724 | ||
725 | gteRGB0 = gteRGB1; | |
726 | gteRGB1 = gteRGB2; | |
727 | gteCODE2 = gteCODE; | |
728 | gteR2 = limC1(gteMAC1 >> 4); | |
729 | gteG2 = limC2(gteMAC2 >> 4); | |
730 | gteB2 = limC3(gteMAC3 >> 4); | |
731 | } | |
732 | ||
f74fb727 | 733 | void gteGPF(psxCP2Regs *regs) { |
ef79bbde P |
734 | int shift = 12 * GTE_SF(gteop); |
735 | ||
736 | #ifdef GTE_LOG | |
737 | GTE_LOG("GTE GPF\n"); | |
738 | #endif | |
739 | gteFLAG = 0; | |
740 | ||
b3254af9 | 741 | gteMAC1 = (gteIR0 * gteIR1) >> shift; |
742 | gteMAC2 = (gteIR0 * gteIR2) >> shift; | |
743 | gteMAC3 = (gteIR0 * gteIR3) >> shift; | |
ef79bbde P |
744 | gteIR1 = limB1(gteMAC1, 0); |
745 | gteIR2 = limB2(gteMAC2, 0); | |
746 | gteIR3 = limB3(gteMAC3, 0); | |
747 | ||
748 | gteRGB0 = gteRGB1; | |
749 | gteRGB1 = gteRGB2; | |
750 | gteCODE2 = gteCODE; | |
751 | gteR2 = limC1(gteMAC1 >> 4); | |
752 | gteG2 = limC2(gteMAC2 >> 4); | |
753 | gteB2 = limC3(gteMAC3 >> 4); | |
754 | } | |
755 | ||
f74fb727 | 756 | void gteGPL(psxCP2Regs *regs) { |
ef79bbde P |
757 | int shift = 12 * GTE_SF(gteop); |
758 | ||
759 | #ifdef GTE_LOG | |
760 | GTE_LOG("GTE GPL\n"); | |
761 | #endif | |
762 | gteFLAG = 0; | |
763 | ||
764 | gteMAC1 = A1((((s64)gteMAC1 << shift) + (gteIR0 * gteIR1)) >> shift); | |
765 | gteMAC2 = A2((((s64)gteMAC2 << shift) + (gteIR0 * gteIR2)) >> shift); | |
766 | gteMAC3 = A3((((s64)gteMAC3 << shift) + (gteIR0 * gteIR3)) >> shift); | |
767 | gteIR1 = limB1(gteMAC1, 0); | |
768 | gteIR2 = limB2(gteMAC2, 0); | |
769 | gteIR3 = limB3(gteMAC3, 0); | |
770 | ||
771 | gteRGB0 = gteRGB1; | |
772 | gteRGB1 = gteRGB2; | |
773 | gteCODE2 = gteCODE; | |
774 | gteR2 = limC1(gteMAC1 >> 4); | |
775 | gteG2 = limC2(gteMAC2 >> 4); | |
776 | gteB2 = limC3(gteMAC3 >> 4); | |
777 | } | |
778 | ||
f74fb727 | 779 | void gteDPCS(psxCP2Regs *regs) { |
ef79bbde P |
780 | int shift = 12 * GTE_SF(gteop); |
781 | ||
782 | #ifdef GTE_LOG | |
783 | GTE_LOG("GTE DPCS\n"); | |
784 | #endif | |
785 | gteFLAG = 0; | |
786 | ||
6c6c9590 | 787 | gteMAC1 = ((gteR << 16) + (gteIR0 * limB1(A1U(((s64)gteRFC - (gteR << 4)) << (12 - shift)), 0))) >> 12; |
788 | gteMAC2 = ((gteG << 16) + (gteIR0 * limB2(A2U(((s64)gteGFC - (gteG << 4)) << (12 - shift)), 0))) >> 12; | |
789 | gteMAC3 = ((gteB << 16) + (gteIR0 * limB3(A3U(((s64)gteBFC - (gteB << 4)) << (12 - shift)), 0))) >> 12; | |
ef79bbde P |
790 | |
791 | gteIR1 = limB1(gteMAC1, 0); | |
792 | gteIR2 = limB2(gteMAC2, 0); | |
793 | gteIR3 = limB3(gteMAC3, 0); | |
794 | gteRGB0 = gteRGB1; | |
795 | gteRGB1 = gteRGB2; | |
796 | gteCODE2 = gteCODE; | |
797 | gteR2 = limC1(gteMAC1 >> 4); | |
798 | gteG2 = limC2(gteMAC2 >> 4); | |
799 | gteB2 = limC3(gteMAC3 >> 4); | |
800 | } | |
801 | ||
f74fb727 | 802 | void gteDPCT(psxCP2Regs *regs) { |
ef79bbde P |
803 | int v; |
804 | ||
805 | #ifdef GTE_LOG | |
806 | GTE_LOG("GTE DPCT\n"); | |
807 | #endif | |
808 | gteFLAG = 0; | |
809 | ||
810 | for (v = 0; v < 3; v++) { | |
6c6c9590 | 811 | gteMAC1 = ((gteR0 << 16) + (gteIR0 * limB1(A1U((s64)gteRFC - (gteR0 << 4)), 0))) >> 12; |
812 | gteMAC2 = ((gteG0 << 16) + (gteIR0 * limB1(A2U((s64)gteGFC - (gteG0 << 4)), 0))) >> 12; | |
813 | gteMAC3 = ((gteB0 << 16) + (gteIR0 * limB1(A3U((s64)gteBFC - (gteB0 << 4)), 0))) >> 12; | |
ef79bbde P |
814 | |
815 | gteRGB0 = gteRGB1; | |
816 | gteRGB1 = gteRGB2; | |
817 | gteCODE2 = gteCODE; | |
818 | gteR2 = limC1(gteMAC1 >> 4); | |
819 | gteG2 = limC2(gteMAC2 >> 4); | |
820 | gteB2 = limC3(gteMAC3 >> 4); | |
821 | } | |
822 | gteIR1 = limB1(gteMAC1, 0); | |
823 | gteIR2 = limB2(gteMAC2, 0); | |
824 | gteIR3 = limB3(gteMAC3, 0); | |
825 | } | |
826 | ||
f74fb727 | 827 | void gteNCS(psxCP2Regs *regs) { |
ef79bbde P |
828 | #ifdef GTE_LOG |
829 | GTE_LOG("GTE NCS\n"); | |
830 | #endif | |
831 | gteFLAG = 0; | |
832 | ||
b3254af9 | 833 | gteMAC1 = ((s64)(gteL11 * gteVX0) + (gteL12 * gteVY0) + (gteL13 * gteVZ0)) >> 12; |
834 | gteMAC2 = ((s64)(gteL21 * gteVX0) + (gteL22 * gteVY0) + (gteL23 * gteVZ0)) >> 12; | |
835 | gteMAC3 = ((s64)(gteL31 * gteVX0) + (gteL32 * gteVY0) + (gteL33 * gteVZ0)) >> 12; | |
ef79bbde P |
836 | gteIR1 = limB1(gteMAC1, 1); |
837 | gteIR2 = limB2(gteMAC2, 1); | |
838 | gteIR3 = limB3(gteMAC3, 1); | |
839 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
840 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
841 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
842 | gteIR1 = limB1(gteMAC1, 1); | |
843 | gteIR2 = limB2(gteMAC2, 1); | |
844 | gteIR3 = limB3(gteMAC3, 1); | |
845 | ||
846 | gteRGB0 = gteRGB1; | |
847 | gteRGB1 = gteRGB2; | |
848 | gteCODE2 = gteCODE; | |
849 | gteR2 = limC1(gteMAC1 >> 4); | |
850 | gteG2 = limC2(gteMAC2 >> 4); | |
851 | gteB2 = limC3(gteMAC3 >> 4); | |
852 | } | |
853 | ||
f74fb727 | 854 | void gteNCT(psxCP2Regs *regs) { |
ef79bbde P |
855 | int v; |
856 | s32 vx, vy, vz; | |
857 | ||
858 | #ifdef GTE_LOG | |
859 | GTE_LOG("GTE NCT\n"); | |
860 | #endif | |
861 | gteFLAG = 0; | |
862 | ||
863 | for (v = 0; v < 3; v++) { | |
864 | vx = VX(v); | |
865 | vy = VY(v); | |
866 | vz = VZ(v); | |
b3254af9 | 867 | gteMAC1 = ((s64)(gteL11 * vx) + (gteL12 * vy) + (gteL13 * vz)) >> 12; |
868 | gteMAC2 = ((s64)(gteL21 * vx) + (gteL22 * vy) + (gteL23 * vz)) >> 12; | |
869 | gteMAC3 = ((s64)(gteL31 * vx) + (gteL32 * vy) + (gteL33 * vz)) >> 12; | |
ef79bbde P |
870 | gteIR1 = limB1(gteMAC1, 1); |
871 | gteIR2 = limB2(gteMAC2, 1); | |
872 | gteIR3 = limB3(gteMAC3, 1); | |
873 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
874 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
875 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
876 | gteRGB0 = gteRGB1; | |
877 | gteRGB1 = gteRGB2; | |
878 | gteCODE2 = gteCODE; | |
879 | gteR2 = limC1(gteMAC1 >> 4); | |
880 | gteG2 = limC2(gteMAC2 >> 4); | |
881 | gteB2 = limC3(gteMAC3 >> 4); | |
882 | } | |
883 | gteIR1 = limB1(gteMAC1, 1); | |
884 | gteIR2 = limB2(gteMAC2, 1); | |
885 | gteIR3 = limB3(gteMAC3, 1); | |
886 | } | |
887 | ||
f74fb727 | 888 | void gteCC(psxCP2Regs *regs) { |
ef79bbde P |
889 | #ifdef GTE_LOG |
890 | GTE_LOG("GTE CC\n"); | |
891 | #endif | |
892 | gteFLAG = 0; | |
893 | ||
894 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
895 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
896 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
897 | gteIR1 = limB1(gteMAC1, 1); | |
898 | gteIR2 = limB2(gteMAC2, 1); | |
899 | gteIR3 = limB3(gteMAC3, 1); | |
b3254af9 | 900 | gteMAC1 = ((s32)gteR * gteIR1) >> 8; |
901 | gteMAC2 = ((s32)gteG * gteIR2) >> 8; | |
902 | gteMAC3 = ((s32)gteB * gteIR3) >> 8; | |
ef79bbde P |
903 | gteIR1 = limB1(gteMAC1, 1); |
904 | gteIR2 = limB2(gteMAC2, 1); | |
905 | gteIR3 = limB3(gteMAC3, 1); | |
906 | ||
907 | gteRGB0 = gteRGB1; | |
908 | gteRGB1 = gteRGB2; | |
909 | gteCODE2 = gteCODE; | |
910 | gteR2 = limC1(gteMAC1 >> 4); | |
911 | gteG2 = limC2(gteMAC2 >> 4); | |
912 | gteB2 = limC3(gteMAC3 >> 4); | |
913 | } | |
914 | ||
f74fb727 | 915 | void gteINTPL(psxCP2Regs *regs) { |
ef79bbde P |
916 | int shift = 12 * GTE_SF(gteop); |
917 | int lm = GTE_LM(gteop); | |
918 | ||
919 | #ifdef GTE_LOG | |
920 | GTE_LOG("GTE INTPL\n"); | |
921 | #endif | |
922 | gteFLAG = 0; | |
923 | ||
6c6c9590 | 924 | gteMAC1 = ((gteIR1 << 12) + (gteIR0 * limB1(A1U((s64)gteRFC - gteIR1), 0))) >> shift; |
925 | gteMAC2 = ((gteIR2 << 12) + (gteIR0 * limB2(A2U((s64)gteGFC - gteIR2), 0))) >> shift; | |
926 | gteMAC3 = ((gteIR3 << 12) + (gteIR0 * limB3(A3U((s64)gteBFC - gteIR3), 0))) >> shift; | |
ef79bbde P |
927 | gteIR1 = limB1(gteMAC1, lm); |
928 | gteIR2 = limB2(gteMAC2, lm); | |
929 | gteIR3 = limB3(gteMAC3, lm); | |
930 | gteRGB0 = gteRGB1; | |
931 | gteRGB1 = gteRGB2; | |
932 | gteCODE2 = gteCODE; | |
933 | gteR2 = limC1(gteMAC1 >> 4); | |
934 | gteG2 = limC2(gteMAC2 >> 4); | |
935 | gteB2 = limC3(gteMAC3 >> 4); | |
936 | } | |
937 | ||
f74fb727 | 938 | void gteCDP(psxCP2Regs *regs) { |
ef79bbde P |
939 | #ifdef GTE_LOG |
940 | GTE_LOG("GTE CDP\n"); | |
941 | #endif | |
942 | gteFLAG = 0; | |
943 | ||
944 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
945 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
946 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
947 | gteIR1 = limB1(gteMAC1, 1); | |
948 | gteIR2 = limB2(gteMAC2, 1); | |
949 | gteIR3 = limB3(gteMAC3, 1); | |
6c6c9590 | 950 | gteMAC1 = (((gteR << 4) * gteIR1) + (gteIR0 * limB1(A1U((s64)gteRFC - ((gteR * gteIR1) >> 8)), 0))) >> 12; |
951 | gteMAC2 = (((gteG << 4) * gteIR2) + (gteIR0 * limB2(A2U((s64)gteGFC - ((gteG * gteIR2) >> 8)), 0))) >> 12; | |
952 | gteMAC3 = (((gteB << 4) * gteIR3) + (gteIR0 * limB3(A3U((s64)gteBFC - ((gteB * gteIR3) >> 8)), 0))) >> 12; | |
ef79bbde P |
953 | gteIR1 = limB1(gteMAC1, 1); |
954 | gteIR2 = limB2(gteMAC2, 1); | |
955 | gteIR3 = limB3(gteMAC3, 1); | |
956 | ||
957 | gteRGB0 = gteRGB1; | |
958 | gteRGB1 = gteRGB2; | |
959 | gteCODE2 = gteCODE; | |
960 | gteR2 = limC1(gteMAC1 >> 4); | |
961 | gteG2 = limC2(gteMAC2 >> 4); | |
962 | gteB2 = limC3(gteMAC3 >> 4); | |
963 | } | |
6c0eefaf | 964 | |
965 | /* decomposed/parametrized versions for the recompiler */ | |
966 | ||
967 | #ifndef FLAGLESS | |
968 | ||
969 | void gteSQR_part_noshift(psxCP2Regs *regs) { | |
970 | gteFLAG = 0; | |
971 | ||
972 | gteMAC1 = gteIR1 * gteIR1; | |
973 | gteMAC2 = gteIR2 * gteIR2; | |
974 | gteMAC3 = gteIR3 * gteIR3; | |
975 | } | |
976 | ||
977 | void gteSQR_part_shift(psxCP2Regs *regs) { | |
978 | gteFLAG = 0; | |
979 | ||
980 | gteMAC1 = (gteIR1 * gteIR1) >> 12; | |
981 | gteMAC2 = (gteIR2 * gteIR2) >> 12; | |
982 | gteMAC3 = (gteIR3 * gteIR3) >> 12; | |
983 | } | |
984 | ||
985 | void gteOP_part_noshift(psxCP2Regs *regs) { | |
986 | gteFLAG = 0; | |
987 | ||
988 | gteMAC1 = (gteR22 * gteIR3) - (gteR33 * gteIR2); | |
989 | gteMAC2 = (gteR33 * gteIR1) - (gteR11 * gteIR3); | |
990 | gteMAC3 = (gteR11 * gteIR2) - (gteR22 * gteIR1); | |
991 | } | |
992 | ||
993 | void gteOP_part_shift(psxCP2Regs *regs) { | |
994 | gteFLAG = 0; | |
995 | ||
996 | gteMAC1 = ((gteR22 * gteIR3) - (gteR33 * gteIR2)) >> 12; | |
997 | gteMAC2 = ((gteR33 * gteIR1) - (gteR11 * gteIR3)) >> 12; | |
998 | gteMAC3 = ((gteR11 * gteIR2) - (gteR22 * gteIR1)) >> 12; | |
999 | } | |
1000 | ||
1001 | void gteDCPL_part(psxCP2Regs *regs) { | |
1002 | s32 RIR1 = ((s32)gteR * gteIR1) >> 8; | |
1003 | s32 GIR2 = ((s32)gteG * gteIR2) >> 8; | |
1004 | s32 BIR3 = ((s32)gteB * gteIR3) >> 8; | |
1005 | ||
1006 | gteFLAG = 0; | |
1007 | ||
1008 | gteMAC1 = RIR1 + ((gteIR0 * limB1(A1U((s64)gteRFC - RIR1), 0)) >> 12); | |
1009 | gteMAC2 = GIR2 + ((gteIR0 * limB1(A2U((s64)gteGFC - GIR2), 0)) >> 12); | |
1010 | gteMAC3 = BIR3 + ((gteIR0 * limB1(A3U((s64)gteBFC - BIR3), 0)) >> 12); | |
1011 | } | |
1012 | ||
1013 | void gteGPF_part_noshift(psxCP2Regs *regs) { | |
1014 | gteFLAG = 0; | |
1015 | ||
1016 | gteMAC1 = gteIR0 * gteIR1; | |
1017 | gteMAC2 = gteIR0 * gteIR2; | |
1018 | gteMAC3 = gteIR0 * gteIR3; | |
1019 | } | |
1020 | ||
1021 | void gteGPF_part_shift(psxCP2Regs *regs) { | |
1022 | gteFLAG = 0; | |
1023 | ||
1024 | gteMAC1 = (gteIR0 * gteIR1) >> 12; | |
1025 | gteMAC2 = (gteIR0 * gteIR2) >> 12; | |
1026 | gteMAC3 = (gteIR0 * gteIR3) >> 12; | |
1027 | } | |
1028 | ||
1029 | #endif // !FLAGLESS | |
1030 | ||
1031 | void gteGPL_part_noshift(psxCP2Regs *regs) { | |
1032 | gteFLAG = 0; | |
1033 | ||
1034 | gteMAC1 = A1((s64)gteMAC1 + (gteIR0 * gteIR1)); | |
1035 | gteMAC2 = A2((s64)gteMAC2 + (gteIR0 * gteIR2)); | |
1036 | gteMAC3 = A3((s64)gteMAC3 + (gteIR0 * gteIR3)); | |
1037 | } | |
1038 | ||
1039 | void gteGPL_part_shift(psxCP2Regs *regs) { | |
1040 | gteFLAG = 0; | |
1041 | ||
1042 | gteMAC1 = A1((s64)gteMAC1 + ((gteIR0 * gteIR1) >> 12)); | |
1043 | gteMAC2 = A2((s64)gteMAC2 + ((gteIR0 * gteIR2) >> 12)); | |
1044 | gteMAC3 = A3((s64)gteMAC3 + ((gteIR0 * gteIR3) >> 12)); | |
1045 | } | |
1046 | ||
1047 | void gteDPCS_part_noshift(psxCP2Regs *regs) { | |
1048 | int shift = 0; | |
1049 | ||
1050 | gteFLAG = 0; | |
1051 | ||
1052 | gteMAC1 = ((gteR << 16) + (gteIR0 * limB1(A1U((s64)gteRFC - (gteR << 4)) << (12 - shift), 0))) >> 12; | |
1053 | gteMAC2 = ((gteG << 16) + (gteIR0 * limB2(A2U((s64)gteGFC - (gteG << 4)) << (12 - shift), 0))) >> 12; | |
1054 | gteMAC3 = ((gteB << 16) + (gteIR0 * limB3(A3U((s64)gteBFC - (gteB << 4)) << (12 - shift), 0))) >> 12; | |
1055 | } | |
1056 | ||
1057 | void gteDPCS_part_shift(psxCP2Regs *regs) { | |
1058 | int shift = 12; | |
1059 | ||
1060 | gteFLAG = 0; | |
1061 | ||
1062 | gteMAC1 = ((gteR << 16) + (gteIR0 * limB1(A1U((s64)gteRFC - (gteR << 4)) << (12 - shift), 0))) >> 12; | |
1063 | gteMAC2 = ((gteG << 16) + (gteIR0 * limB2(A2U((s64)gteGFC - (gteG << 4)) << (12 - shift), 0))) >> 12; | |
1064 | gteMAC3 = ((gteB << 16) + (gteIR0 * limB3(A3U((s64)gteBFC - (gteB << 4)) << (12 - shift), 0))) >> 12; | |
1065 | } | |
1066 | ||
1067 | void gteINTPL_part_noshift(psxCP2Regs *regs) { | |
1068 | gteFLAG = 0; | |
1069 | ||
1070 | gteMAC1 = ((gteIR1 << 12) + (gteIR0 * limB1(A1U((s64)gteRFC - gteIR1), 0))); | |
1071 | gteMAC2 = ((gteIR2 << 12) + (gteIR0 * limB2(A2U((s64)gteGFC - gteIR2), 0))); | |
1072 | gteMAC3 = ((gteIR3 << 12) + (gteIR0 * limB3(A3U((s64)gteBFC - gteIR3), 0))); | |
1073 | } | |
1074 | ||
1075 | void gteINTPL_part_shift(psxCP2Regs *regs) { | |
1076 | gteFLAG = 0; | |
1077 | ||
1078 | gteMAC1 = ((gteIR1 << 12) + (gteIR0 * limB1(A1U((s64)gteRFC - gteIR1), 0))) >> 12; | |
1079 | gteMAC2 = ((gteIR2 << 12) + (gteIR0 * limB2(A2U((s64)gteGFC - gteIR2), 0))) >> 12; | |
1080 | gteMAC3 = ((gteIR3 << 12) + (gteIR0 * limB3(A3U((s64)gteBFC - gteIR3), 0))) >> 12; | |
1081 | } | |
1082 | ||
1083 | void gteMACtoRGB(psxCP2Regs *regs) { | |
1084 | gteRGB0 = gteRGB1; | |
1085 | gteRGB1 = gteRGB2; | |
1086 | gteCODE2 = gteCODE; | |
1087 | gteR2 = limC1(gteMAC1 >> 4); | |
1088 | gteG2 = limC2(gteMAC2 >> 4); | |
1089 | gteB2 = limC3(gteMAC3 >> 4); | |
1090 | } | |
1091 |