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 | ||
b3254af9 | 173 | static inline s32 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 P |
245 | |
246 | #include "gte_divider.h" | |
247 | ||
59774ed0 | 248 | #ifndef FLAGLESS |
249 | ||
ef79bbde | 250 | static inline u32 MFC2(int reg) { |
f74fb727 | 251 | psxCP2Regs *regs = (psxCP2Regs *)&psxRegs.CP2D; |
ef79bbde P |
252 | switch (reg) { |
253 | case 1: | |
254 | case 3: | |
255 | case 5: | |
256 | case 8: | |
257 | case 9: | |
258 | case 10: | |
259 | case 11: | |
260 | psxRegs.CP2D.r[reg] = (s32)psxRegs.CP2D.p[reg].sw.l; | |
261 | break; | |
262 | ||
263 | case 7: | |
264 | case 16: | |
265 | case 17: | |
266 | case 18: | |
267 | case 19: | |
268 | psxRegs.CP2D.r[reg] = (u32)psxRegs.CP2D.p[reg].w.l; | |
269 | break; | |
270 | ||
271 | case 15: | |
272 | psxRegs.CP2D.r[reg] = gteSXY2; | |
273 | break; | |
274 | ||
275 | case 28: | |
ef79bbde P |
276 | case 29: |
277 | psxRegs.CP2D.r[reg] = LIM(gteIR1 >> 7, 0x1f, 0, 0) | | |
278 | (LIM(gteIR2 >> 7, 0x1f, 0, 0) << 5) | | |
279 | (LIM(gteIR3 >> 7, 0x1f, 0, 0) << 10); | |
280 | break; | |
281 | } | |
282 | return psxRegs.CP2D.r[reg]; | |
283 | } | |
284 | ||
285 | static inline void MTC2(u32 value, int reg) { | |
f74fb727 | 286 | psxCP2Regs *regs = (psxCP2Regs *)&psxRegs.CP2D; |
ef79bbde P |
287 | switch (reg) { |
288 | case 15: | |
289 | gteSXY0 = gteSXY1; | |
290 | gteSXY1 = gteSXY2; | |
291 | gteSXY2 = value; | |
292 | gteSXYP = value; | |
293 | break; | |
294 | ||
295 | case 28: | |
296 | gteIRGB = value; | |
297 | gteIR1 = (value & 0x1f) << 7; | |
298 | gteIR2 = (value & 0x3e0) << 2; | |
299 | gteIR3 = (value & 0x7c00) >> 3; | |
300 | break; | |
301 | ||
302 | case 30: | |
303 | { | |
304 | int a; | |
305 | gteLZCS = value; | |
306 | ||
307 | a = gteLZCS; | |
308 | if (a > 0) { | |
309 | int i; | |
310 | for (i = 31; (a & (1 << i)) == 0 && i >= 0; i--); | |
311 | gteLZCR = 31 - i; | |
312 | } else if (a < 0) { | |
313 | int i; | |
314 | a ^= 0xffffffff; | |
315 | for (i = 31; (a & (1 << i)) == 0 && i >= 0; i--); | |
316 | gteLZCR = 31 - i; | |
317 | } else { | |
318 | gteLZCR = 32; | |
319 | } | |
320 | } | |
321 | break; | |
322 | ||
ef79bbde P |
323 | case 31: |
324 | return; | |
325 | ||
326 | default: | |
327 | psxRegs.CP2D.r[reg] = value; | |
328 | } | |
329 | } | |
330 | ||
331 | static inline void CTC2(u32 value, int reg) { | |
332 | switch (reg) { | |
333 | case 4: | |
334 | case 12: | |
335 | case 20: | |
336 | case 26: | |
337 | case 27: | |
338 | case 29: | |
339 | case 30: | |
340 | value = (s32)(s16)value; | |
341 | break; | |
342 | ||
343 | case 31: | |
344 | value = value & 0x7ffff000; | |
345 | if (value & 0x7f87e000) value |= 0x80000000; | |
346 | break; | |
347 | } | |
348 | ||
349 | psxRegs.CP2C.r[reg] = value; | |
350 | } | |
351 | ||
352 | void gteMFC2() { | |
353 | if (!_Rt_) return; | |
354 | psxRegs.GPR.r[_Rt_] = MFC2(_Rd_); | |
355 | } | |
356 | ||
357 | void gteCFC2() { | |
358 | if (!_Rt_) return; | |
359 | psxRegs.GPR.r[_Rt_] = psxRegs.CP2C.r[_Rd_]; | |
360 | } | |
361 | ||
362 | void gteMTC2() { | |
363 | MTC2(psxRegs.GPR.r[_Rt_], _Rd_); | |
364 | } | |
365 | ||
366 | void gteCTC2() { | |
367 | CTC2(psxRegs.GPR.r[_Rt_], _Rd_); | |
368 | } | |
369 | ||
370 | #define _oB_ (psxRegs.GPR.r[_Rs_] + _Imm_) | |
371 | ||
372 | void gteLWC2() { | |
373 | MTC2(psxMemRead32(_oB_), _Rt_); | |
374 | } | |
375 | ||
376 | void gteSWC2() { | |
377 | psxMemWrite32(_oB_, MFC2(_Rt_)); | |
378 | } | |
379 | ||
59774ed0 | 380 | #endif // FLAGLESS |
381 | ||
3ebefe71 | 382 | #if 0 |
a2544c92 | 383 | #define DIVIDE DIVIDE_ |
384 | static u32 DIVIDE_(s16 n, u16 d) { | |
385 | if (n >= 0 && n < d * 2) { | |
386 | s32 n_ = n; | |
387 | return ((n_ << 16) + d / 2) / d; | |
388 | //return (u32)((float)(n_ << 16) / (float)d + (float)0.5); | |
389 | } | |
390 | return 0xffffffff; | |
391 | } | |
3ebefe71 | 392 | #endif |
a2544c92 | 393 | |
f74fb727 | 394 | void gteRTPS(psxCP2Regs *regs) { |
ef79bbde P |
395 | int quotient; |
396 | ||
397 | #ifdef GTE_LOG | |
398 | GTE_LOG("GTE RTPS\n"); | |
399 | #endif | |
400 | gteFLAG = 0; | |
401 | ||
402 | gteMAC1 = A1((((s64)gteTRX << 12) + (gteR11 * gteVX0) + (gteR12 * gteVY0) + (gteR13 * gteVZ0)) >> 12); | |
403 | gteMAC2 = A2((((s64)gteTRY << 12) + (gteR21 * gteVX0) + (gteR22 * gteVY0) + (gteR23 * gteVZ0)) >> 12); | |
404 | gteMAC3 = A3((((s64)gteTRZ << 12) + (gteR31 * gteVX0) + (gteR32 * gteVY0) + (gteR33 * gteVZ0)) >> 12); | |
405 | gteIR1 = limB1(gteMAC1, 0); | |
406 | gteIR2 = limB2(gteMAC2, 0); | |
407 | gteIR3 = limB3(gteMAC3, 0); | |
408 | gteSZ0 = gteSZ1; | |
409 | gteSZ1 = gteSZ2; | |
410 | gteSZ2 = gteSZ3; | |
411 | gteSZ3 = limD(gteMAC3); | |
412 | quotient = limE(DIVIDE(gteH, gteSZ3)); | |
413 | gteSXY0 = gteSXY1; | |
414 | gteSXY1 = gteSXY2; | |
415 | gteSX2 = limG1(F((s64)gteOFX + ((s64)gteIR1 * quotient)) >> 16); | |
416 | gteSY2 = limG2(F((s64)gteOFY + ((s64)gteIR2 * quotient)) >> 16); | |
417 | ||
631e6f28 | 418 | gteMAC0 = F((s64)gteDQB + ((s64)gteDQA * quotient)); |
419 | gteIR0 = limH(gteMAC0 >> 12); | |
ef79bbde P |
420 | } |
421 | ||
f74fb727 | 422 | void gteRTPT(psxCP2Regs *regs) { |
ef79bbde P |
423 | int quotient; |
424 | int v; | |
425 | s32 vx, vy, vz; | |
426 | ||
427 | #ifdef GTE_LOG | |
428 | GTE_LOG("GTE RTPT\n"); | |
429 | #endif | |
430 | gteFLAG = 0; | |
431 | ||
432 | gteSZ0 = gteSZ3; | |
433 | for (v = 0; v < 3; v++) { | |
434 | vx = VX(v); | |
435 | vy = VY(v); | |
436 | vz = VZ(v); | |
437 | gteMAC1 = A1((((s64)gteTRX << 12) + (gteR11 * vx) + (gteR12 * vy) + (gteR13 * vz)) >> 12); | |
438 | gteMAC2 = A2((((s64)gteTRY << 12) + (gteR21 * vx) + (gteR22 * vy) + (gteR23 * vz)) >> 12); | |
439 | gteMAC3 = A3((((s64)gteTRZ << 12) + (gteR31 * vx) + (gteR32 * vy) + (gteR33 * vz)) >> 12); | |
440 | gteIR1 = limB1(gteMAC1, 0); | |
441 | gteIR2 = limB2(gteMAC2, 0); | |
442 | gteIR3 = limB3(gteMAC3, 0); | |
443 | fSZ(v) = limD(gteMAC3); | |
444 | quotient = limE(DIVIDE(gteH, fSZ(v))); | |
445 | fSX(v) = limG1(F((s64)gteOFX + ((s64)gteIR1 * quotient)) >> 16); | |
446 | fSY(v) = limG2(F((s64)gteOFY + ((s64)gteIR2 * quotient)) >> 16); | |
447 | } | |
631e6f28 | 448 | gteMAC0 = F((s64)gteDQB + ((s64)gteDQA * quotient)); |
449 | gteIR0 = limH(gteMAC0 >> 12); | |
ef79bbde P |
450 | } |
451 | ||
f74fb727 | 452 | void gteMVMVA(psxCP2Regs *regs) { |
ef79bbde P |
453 | int shift = 12 * GTE_SF(gteop); |
454 | int mx = GTE_MX(gteop); | |
455 | int v = GTE_V(gteop); | |
456 | int cv = GTE_CV(gteop); | |
457 | int lm = GTE_LM(gteop); | |
458 | s32 vx = VX(v); | |
459 | s32 vy = VY(v); | |
460 | s32 vz = VZ(v); | |
461 | ||
462 | #ifdef GTE_LOG | |
463 | GTE_LOG("GTE MVMVA\n"); | |
464 | #endif | |
465 | gteFLAG = 0; | |
466 | ||
467 | gteMAC1 = A1((((s64)CV1(cv) << 12) + (MX11(mx) * vx) + (MX12(mx) * vy) + (MX13(mx) * vz)) >> shift); | |
468 | gteMAC2 = A2((((s64)CV2(cv) << 12) + (MX21(mx) * vx) + (MX22(mx) * vy) + (MX23(mx) * vz)) >> shift); | |
469 | gteMAC3 = A3((((s64)CV3(cv) << 12) + (MX31(mx) * vx) + (MX32(mx) * vy) + (MX33(mx) * vz)) >> shift); | |
470 | ||
471 | gteIR1 = limB1(gteMAC1, lm); | |
472 | gteIR2 = limB2(gteMAC2, lm); | |
473 | gteIR3 = limB3(gteMAC3, lm); | |
474 | } | |
475 | ||
f74fb727 | 476 | void gteNCLIP(psxCP2Regs *regs) { |
ef79bbde P |
477 | #ifdef GTE_LOG |
478 | GTE_LOG("GTE NCLIP\n"); | |
479 | #endif | |
480 | gteFLAG = 0; | |
481 | ||
482 | gteMAC0 = F((s64)gteSX0 * (gteSY1 - gteSY2) + | |
483 | gteSX1 * (gteSY2 - gteSY0) + | |
484 | gteSX2 * (gteSY0 - gteSY1)); | |
485 | } | |
486 | ||
f74fb727 | 487 | void gteAVSZ3(psxCP2Regs *regs) { |
ef79bbde P |
488 | #ifdef GTE_LOG |
489 | GTE_LOG("GTE AVSZ3\n"); | |
490 | #endif | |
491 | gteFLAG = 0; | |
492 | ||
b3254af9 | 493 | gteMAC0 = F((s64)gteZSF3 * (gteSZ1 + gteSZ2 + gteSZ3)); |
ef79bbde P |
494 | gteOTZ = limD(gteMAC0 >> 12); |
495 | } | |
496 | ||
f74fb727 | 497 | void gteAVSZ4(psxCP2Regs *regs) { |
ef79bbde P |
498 | #ifdef GTE_LOG |
499 | GTE_LOG("GTE AVSZ4\n"); | |
500 | #endif | |
501 | gteFLAG = 0; | |
502 | ||
b3254af9 | 503 | gteMAC0 = F((s64)gteZSF4 * (gteSZ0 + gteSZ1 + gteSZ2 + gteSZ3)); |
ef79bbde P |
504 | gteOTZ = limD(gteMAC0 >> 12); |
505 | } | |
506 | ||
f74fb727 | 507 | void gteSQR(psxCP2Regs *regs) { |
ef79bbde P |
508 | int shift = 12 * GTE_SF(gteop); |
509 | int lm = GTE_LM(gteop); | |
510 | ||
511 | #ifdef GTE_LOG | |
512 | GTE_LOG("GTE SQR\n"); | |
513 | #endif | |
514 | gteFLAG = 0; | |
515 | ||
b3254af9 | 516 | gteMAC1 = (gteIR1 * gteIR1) >> shift; |
517 | gteMAC2 = (gteIR2 * gteIR2) >> shift; | |
518 | gteMAC3 = (gteIR3 * gteIR3) >> shift; | |
7384197d | 519 | gteIR1 = limB1(gteMAC1, lm); |
520 | gteIR2 = limB2(gteMAC2, lm); | |
521 | gteIR3 = limB3(gteMAC3, lm); | |
ef79bbde P |
522 | } |
523 | ||
f74fb727 | 524 | void gteNCCS(psxCP2Regs *regs) { |
ef79bbde P |
525 | #ifdef GTE_LOG |
526 | GTE_LOG("GTE NCCS\n"); | |
527 | #endif | |
528 | gteFLAG = 0; | |
529 | ||
b3254af9 | 530 | gteMAC1 = ((s64)(gteL11 * gteVX0) + (gteL12 * gteVY0) + (gteL13 * gteVZ0)) >> 12; |
531 | gteMAC2 = ((s64)(gteL21 * gteVX0) + (gteL22 * gteVY0) + (gteL23 * gteVZ0)) >> 12; | |
532 | gteMAC3 = ((s64)(gteL31 * gteVX0) + (gteL32 * gteVY0) + (gteL33 * gteVZ0)) >> 12; | |
ef79bbde P |
533 | gteIR1 = limB1(gteMAC1, 1); |
534 | gteIR2 = limB2(gteMAC2, 1); | |
535 | gteIR3 = limB3(gteMAC3, 1); | |
536 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
537 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
538 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
539 | gteIR1 = limB1(gteMAC1, 1); | |
540 | gteIR2 = limB2(gteMAC2, 1); | |
541 | gteIR3 = limB3(gteMAC3, 1); | |
b3254af9 | 542 | gteMAC1 = ((s32)gteR * gteIR1) >> 8; |
543 | gteMAC2 = ((s32)gteG * gteIR2) >> 8; | |
544 | gteMAC3 = ((s32)gteB * gteIR3) >> 8; | |
545 | gteIR1 = gteMAC1; | |
546 | gteIR2 = gteMAC2; | |
547 | gteIR3 = gteMAC3; | |
ef79bbde P |
548 | |
549 | gteRGB0 = gteRGB1; | |
550 | gteRGB1 = gteRGB2; | |
551 | gteCODE2 = gteCODE; | |
552 | gteR2 = limC1(gteMAC1 >> 4); | |
553 | gteG2 = limC2(gteMAC2 >> 4); | |
554 | gteB2 = limC3(gteMAC3 >> 4); | |
555 | } | |
556 | ||
f74fb727 | 557 | void gteNCCT(psxCP2Regs *regs) { |
ef79bbde P |
558 | int v; |
559 | s32 vx, vy, vz; | |
560 | ||
561 | #ifdef GTE_LOG | |
562 | GTE_LOG("GTE NCCT\n"); | |
563 | #endif | |
564 | gteFLAG = 0; | |
565 | ||
566 | for (v = 0; v < 3; v++) { | |
567 | vx = VX(v); | |
568 | vy = VY(v); | |
569 | vz = VZ(v); | |
b3254af9 | 570 | gteMAC1 = ((s64)(gteL11 * vx) + (gteL12 * vy) + (gteL13 * vz)) >> 12; |
571 | gteMAC2 = ((s64)(gteL21 * vx) + (gteL22 * vy) + (gteL23 * vz)) >> 12; | |
572 | gteMAC3 = ((s64)(gteL31 * vx) + (gteL32 * vy) + (gteL33 * vz)) >> 12; | |
ef79bbde P |
573 | gteIR1 = limB1(gteMAC1, 1); |
574 | gteIR2 = limB2(gteMAC2, 1); | |
575 | gteIR3 = limB3(gteMAC3, 1); | |
576 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
577 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
578 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
579 | gteIR1 = limB1(gteMAC1, 1); | |
580 | gteIR2 = limB2(gteMAC2, 1); | |
581 | gteIR3 = limB3(gteMAC3, 1); | |
b3254af9 | 582 | gteMAC1 = ((s32)gteR * gteIR1) >> 8; |
583 | gteMAC2 = ((s32)gteG * gteIR2) >> 8; | |
584 | gteMAC3 = ((s32)gteB * gteIR3) >> 8; | |
ef79bbde P |
585 | |
586 | gteRGB0 = gteRGB1; | |
587 | gteRGB1 = gteRGB2; | |
588 | gteCODE2 = gteCODE; | |
589 | gteR2 = limC1(gteMAC1 >> 4); | |
590 | gteG2 = limC2(gteMAC2 >> 4); | |
591 | gteB2 = limC3(gteMAC3 >> 4); | |
592 | } | |
b3254af9 | 593 | gteIR1 = gteMAC1; |
594 | gteIR2 = gteMAC2; | |
595 | gteIR3 = gteMAC3; | |
ef79bbde P |
596 | } |
597 | ||
f74fb727 | 598 | void gteNCDS(psxCP2Regs *regs) { |
ef79bbde P |
599 | #ifdef GTE_LOG |
600 | GTE_LOG("GTE NCDS\n"); | |
601 | #endif | |
602 | gteFLAG = 0; | |
603 | ||
b3254af9 | 604 | gteMAC1 = ((s64)(gteL11 * gteVX0) + (gteL12 * gteVY0) + (gteL13 * gteVZ0)) >> 12; |
605 | gteMAC2 = ((s64)(gteL21 * gteVX0) + (gteL22 * gteVY0) + (gteL23 * gteVZ0)) >> 12; | |
606 | gteMAC3 = ((s64)(gteL31 * gteVX0) + (gteL32 * gteVY0) + (gteL33 * gteVZ0)) >> 12; | |
ef79bbde P |
607 | gteIR1 = limB1(gteMAC1, 1); |
608 | gteIR2 = limB2(gteMAC2, 1); | |
609 | gteIR3 = limB3(gteMAC3, 1); | |
610 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
611 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
612 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
613 | gteIR1 = limB1(gteMAC1, 1); | |
614 | gteIR2 = limB2(gteMAC2, 1); | |
615 | gteIR3 = limB3(gteMAC3, 1); | |
b3254af9 | 616 | gteMAC1 = (((gteR << 4) * gteIR1) + (gteIR0 * limB1(gteRFC - ((gteR * gteIR1) >> 8), 0))) >> 12; |
617 | gteMAC2 = (((gteG << 4) * gteIR2) + (gteIR0 * limB2(gteGFC - ((gteG * gteIR2) >> 8), 0))) >> 12; | |
618 | gteMAC3 = (((gteB << 4) * gteIR3) + (gteIR0 * limB3(gteBFC - ((gteB * gteIR3) >> 8), 0))) >> 12; | |
ef79bbde P |
619 | gteIR1 = limB1(gteMAC1, 1); |
620 | gteIR2 = limB2(gteMAC2, 1); | |
621 | gteIR3 = limB3(gteMAC3, 1); | |
622 | ||
623 | gteRGB0 = gteRGB1; | |
624 | gteRGB1 = gteRGB2; | |
625 | gteCODE2 = gteCODE; | |
626 | gteR2 = limC1(gteMAC1 >> 4); | |
627 | gteG2 = limC2(gteMAC2 >> 4); | |
628 | gteB2 = limC3(gteMAC3 >> 4); | |
629 | } | |
630 | ||
f74fb727 | 631 | void gteNCDT(psxCP2Regs *regs) { |
ef79bbde P |
632 | int v; |
633 | s32 vx, vy, vz; | |
634 | ||
635 | #ifdef GTE_LOG | |
636 | GTE_LOG("GTE NCDT\n"); | |
637 | #endif | |
638 | gteFLAG = 0; | |
639 | ||
640 | for (v = 0; v < 3; v++) { | |
641 | vx = VX(v); | |
642 | vy = VY(v); | |
643 | vz = VZ(v); | |
b3254af9 | 644 | gteMAC1 = ((s64)(gteL11 * vx) + (gteL12 * vy) + (gteL13 * vz)) >> 12; |
645 | gteMAC2 = ((s64)(gteL21 * vx) + (gteL22 * vy) + (gteL23 * vz)) >> 12; | |
646 | gteMAC3 = ((s64)(gteL31 * vx) + (gteL32 * vy) + (gteL33 * vz)) >> 12; | |
ef79bbde P |
647 | gteIR1 = limB1(gteMAC1, 1); |
648 | gteIR2 = limB2(gteMAC2, 1); | |
649 | gteIR3 = limB3(gteMAC3, 1); | |
650 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
651 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
652 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
653 | gteIR1 = limB1(gteMAC1, 1); | |
654 | gteIR2 = limB2(gteMAC2, 1); | |
655 | gteIR3 = limB3(gteMAC3, 1); | |
b3254af9 | 656 | gteMAC1 = (((gteR << 4) * gteIR1) + (gteIR0 * limB1(gteRFC - ((gteR * gteIR1) >> 8), 0))) >> 12; |
657 | gteMAC2 = (((gteG << 4) * gteIR2) + (gteIR0 * limB2(gteGFC - ((gteG * gteIR2) >> 8), 0))) >> 12; | |
658 | gteMAC3 = (((gteB << 4) * gteIR3) + (gteIR0 * limB3(gteBFC - ((gteB * gteIR3) >> 8), 0))) >> 12; | |
ef79bbde P |
659 | |
660 | gteRGB0 = gteRGB1; | |
661 | gteRGB1 = gteRGB2; | |
662 | gteCODE2 = gteCODE; | |
663 | gteR2 = limC1(gteMAC1 >> 4); | |
664 | gteG2 = limC2(gteMAC2 >> 4); | |
665 | gteB2 = limC3(gteMAC3 >> 4); | |
666 | } | |
667 | gteIR1 = limB1(gteMAC1, 1); | |
668 | gteIR2 = limB2(gteMAC2, 1); | |
669 | gteIR3 = limB3(gteMAC3, 1); | |
670 | } | |
671 | ||
f74fb727 | 672 | void gteOP(psxCP2Regs *regs) { |
ef79bbde P |
673 | int shift = 12 * GTE_SF(gteop); |
674 | int lm = GTE_LM(gteop); | |
675 | ||
676 | #ifdef GTE_LOG | |
677 | GTE_LOG("GTE OP\n"); | |
678 | #endif | |
679 | gteFLAG = 0; | |
680 | ||
b3254af9 | 681 | gteMAC1 = ((gteR22 * gteIR3) - (gteR33 * gteIR2)) >> shift; |
682 | gteMAC2 = ((gteR33 * gteIR1) - (gteR11 * gteIR3)) >> shift; | |
683 | gteMAC3 = ((gteR11 * gteIR2) - (gteR22 * gteIR1)) >> shift; | |
ef79bbde P |
684 | gteIR1 = limB1(gteMAC1, lm); |
685 | gteIR2 = limB2(gteMAC2, lm); | |
686 | gteIR3 = limB3(gteMAC3, lm); | |
687 | } | |
688 | ||
f74fb727 | 689 | void gteDCPL(psxCP2Regs *regs) { |
ef79bbde P |
690 | int lm = GTE_LM(gteop); |
691 | ||
b3254af9 | 692 | s32 RIR1 = ((s32)gteR * gteIR1) >> 8; |
693 | s32 GIR2 = ((s32)gteG * gteIR2) >> 8; | |
694 | s32 BIR3 = ((s32)gteB * gteIR3) >> 8; | |
ef79bbde P |
695 | |
696 | #ifdef GTE_LOG | |
697 | GTE_LOG("GTE DCPL\n"); | |
698 | #endif | |
699 | gteFLAG = 0; | |
700 | ||
b3254af9 | 701 | gteMAC1 = RIR1 + ((gteIR0 * limB1(gteRFC - RIR1, 0)) >> 12); |
702 | gteMAC2 = GIR2 + ((gteIR0 * limB1(gteGFC - GIR2, 0)) >> 12); | |
703 | gteMAC3 = BIR3 + ((gteIR0 * limB1(gteBFC - BIR3, 0)) >> 12); | |
ef79bbde P |
704 | |
705 | gteIR1 = limB1(gteMAC1, lm); | |
706 | gteIR2 = limB2(gteMAC2, lm); | |
707 | gteIR3 = limB3(gteMAC3, lm); | |
708 | ||
709 | gteRGB0 = gteRGB1; | |
710 | gteRGB1 = gteRGB2; | |
711 | gteCODE2 = gteCODE; | |
712 | gteR2 = limC1(gteMAC1 >> 4); | |
713 | gteG2 = limC2(gteMAC2 >> 4); | |
714 | gteB2 = limC3(gteMAC3 >> 4); | |
715 | } | |
716 | ||
f74fb727 | 717 | void gteGPF(psxCP2Regs *regs) { |
ef79bbde P |
718 | int shift = 12 * GTE_SF(gteop); |
719 | ||
720 | #ifdef GTE_LOG | |
721 | GTE_LOG("GTE GPF\n"); | |
722 | #endif | |
723 | gteFLAG = 0; | |
724 | ||
b3254af9 | 725 | gteMAC1 = (gteIR0 * gteIR1) >> shift; |
726 | gteMAC2 = (gteIR0 * gteIR2) >> shift; | |
727 | gteMAC3 = (gteIR0 * gteIR3) >> shift; | |
ef79bbde P |
728 | gteIR1 = limB1(gteMAC1, 0); |
729 | gteIR2 = limB2(gteMAC2, 0); | |
730 | gteIR3 = limB3(gteMAC3, 0); | |
731 | ||
732 | gteRGB0 = gteRGB1; | |
733 | gteRGB1 = gteRGB2; | |
734 | gteCODE2 = gteCODE; | |
735 | gteR2 = limC1(gteMAC1 >> 4); | |
736 | gteG2 = limC2(gteMAC2 >> 4); | |
737 | gteB2 = limC3(gteMAC3 >> 4); | |
738 | } | |
739 | ||
f74fb727 | 740 | void gteGPL(psxCP2Regs *regs) { |
ef79bbde P |
741 | int shift = 12 * GTE_SF(gteop); |
742 | ||
743 | #ifdef GTE_LOG | |
744 | GTE_LOG("GTE GPL\n"); | |
745 | #endif | |
746 | gteFLAG = 0; | |
747 | ||
748 | gteMAC1 = A1((((s64)gteMAC1 << shift) + (gteIR0 * gteIR1)) >> shift); | |
749 | gteMAC2 = A2((((s64)gteMAC2 << shift) + (gteIR0 * gteIR2)) >> shift); | |
750 | gteMAC3 = A3((((s64)gteMAC3 << shift) + (gteIR0 * gteIR3)) >> shift); | |
751 | gteIR1 = limB1(gteMAC1, 0); | |
752 | gteIR2 = limB2(gteMAC2, 0); | |
753 | gteIR3 = limB3(gteMAC3, 0); | |
754 | ||
755 | gteRGB0 = gteRGB1; | |
756 | gteRGB1 = gteRGB2; | |
757 | gteCODE2 = gteCODE; | |
758 | gteR2 = limC1(gteMAC1 >> 4); | |
759 | gteG2 = limC2(gteMAC2 >> 4); | |
760 | gteB2 = limC3(gteMAC3 >> 4); | |
761 | } | |
762 | ||
f74fb727 | 763 | void gteDPCS(psxCP2Regs *regs) { |
ef79bbde P |
764 | int shift = 12 * GTE_SF(gteop); |
765 | ||
766 | #ifdef GTE_LOG | |
767 | GTE_LOG("GTE DPCS\n"); | |
768 | #endif | |
769 | gteFLAG = 0; | |
770 | ||
b3254af9 | 771 | gteMAC1 = ((gteR << 16) + (gteIR0 * limB1(A1((s64)gteRFC - (gteR << 4)) << (12 - shift), 0))) >> 12; |
772 | gteMAC2 = ((gteG << 16) + (gteIR0 * limB2(A2((s64)gteGFC - (gteG << 4)) << (12 - shift), 0))) >> 12; | |
773 | gteMAC3 = ((gteB << 16) + (gteIR0 * limB3(A3((s64)gteBFC - (gteB << 4)) << (12 - shift), 0))) >> 12; | |
ef79bbde P |
774 | |
775 | gteIR1 = limB1(gteMAC1, 0); | |
776 | gteIR2 = limB2(gteMAC2, 0); | |
777 | gteIR3 = limB3(gteMAC3, 0); | |
778 | gteRGB0 = gteRGB1; | |
779 | gteRGB1 = gteRGB2; | |
780 | gteCODE2 = gteCODE; | |
781 | gteR2 = limC1(gteMAC1 >> 4); | |
782 | gteG2 = limC2(gteMAC2 >> 4); | |
783 | gteB2 = limC3(gteMAC3 >> 4); | |
784 | } | |
785 | ||
f74fb727 | 786 | void gteDPCT(psxCP2Regs *regs) { |
ef79bbde P |
787 | int v; |
788 | ||
789 | #ifdef GTE_LOG | |
790 | GTE_LOG("GTE DPCT\n"); | |
791 | #endif | |
792 | gteFLAG = 0; | |
793 | ||
794 | for (v = 0; v < 3; v++) { | |
b3254af9 | 795 | gteMAC1 = ((gteR0 << 16) + (gteIR0 * limB1(gteRFC - (gteR0 << 4), 0))) >> 12; |
796 | gteMAC2 = ((gteG0 << 16) + (gteIR0 * limB1(gteGFC - (gteG0 << 4), 0))) >> 12; | |
797 | gteMAC3 = ((gteB0 << 16) + (gteIR0 * limB1(gteBFC - (gteB0 << 4), 0))) >> 12; | |
ef79bbde P |
798 | |
799 | gteRGB0 = gteRGB1; | |
800 | gteRGB1 = gteRGB2; | |
801 | gteCODE2 = gteCODE; | |
802 | gteR2 = limC1(gteMAC1 >> 4); | |
803 | gteG2 = limC2(gteMAC2 >> 4); | |
804 | gteB2 = limC3(gteMAC3 >> 4); | |
805 | } | |
806 | gteIR1 = limB1(gteMAC1, 0); | |
807 | gteIR2 = limB2(gteMAC2, 0); | |
808 | gteIR3 = limB3(gteMAC3, 0); | |
809 | } | |
810 | ||
f74fb727 | 811 | void gteNCS(psxCP2Regs *regs) { |
ef79bbde P |
812 | #ifdef GTE_LOG |
813 | GTE_LOG("GTE NCS\n"); | |
814 | #endif | |
815 | gteFLAG = 0; | |
816 | ||
b3254af9 | 817 | gteMAC1 = ((s64)(gteL11 * gteVX0) + (gteL12 * gteVY0) + (gteL13 * gteVZ0)) >> 12; |
818 | gteMAC2 = ((s64)(gteL21 * gteVX0) + (gteL22 * gteVY0) + (gteL23 * gteVZ0)) >> 12; | |
819 | gteMAC3 = ((s64)(gteL31 * gteVX0) + (gteL32 * gteVY0) + (gteL33 * gteVZ0)) >> 12; | |
ef79bbde P |
820 | gteIR1 = limB1(gteMAC1, 1); |
821 | gteIR2 = limB2(gteMAC2, 1); | |
822 | gteIR3 = limB3(gteMAC3, 1); | |
823 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
824 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
825 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
826 | gteIR1 = limB1(gteMAC1, 1); | |
827 | gteIR2 = limB2(gteMAC2, 1); | |
828 | gteIR3 = limB3(gteMAC3, 1); | |
829 | ||
830 | gteRGB0 = gteRGB1; | |
831 | gteRGB1 = gteRGB2; | |
832 | gteCODE2 = gteCODE; | |
833 | gteR2 = limC1(gteMAC1 >> 4); | |
834 | gteG2 = limC2(gteMAC2 >> 4); | |
835 | gteB2 = limC3(gteMAC3 >> 4); | |
836 | } | |
837 | ||
f74fb727 | 838 | void gteNCT(psxCP2Regs *regs) { |
ef79bbde P |
839 | int v; |
840 | s32 vx, vy, vz; | |
841 | ||
842 | #ifdef GTE_LOG | |
843 | GTE_LOG("GTE NCT\n"); | |
844 | #endif | |
845 | gteFLAG = 0; | |
846 | ||
847 | for (v = 0; v < 3; v++) { | |
848 | vx = VX(v); | |
849 | vy = VY(v); | |
850 | vz = VZ(v); | |
b3254af9 | 851 | gteMAC1 = ((s64)(gteL11 * vx) + (gteL12 * vy) + (gteL13 * vz)) >> 12; |
852 | gteMAC2 = ((s64)(gteL21 * vx) + (gteL22 * vy) + (gteL23 * vz)) >> 12; | |
853 | gteMAC3 = ((s64)(gteL31 * vx) + (gteL32 * vy) + (gteL33 * vz)) >> 12; | |
ef79bbde P |
854 | gteIR1 = limB1(gteMAC1, 1); |
855 | gteIR2 = limB2(gteMAC2, 1); | |
856 | gteIR3 = limB3(gteMAC3, 1); | |
857 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
858 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
859 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
860 | gteRGB0 = gteRGB1; | |
861 | gteRGB1 = gteRGB2; | |
862 | gteCODE2 = gteCODE; | |
863 | gteR2 = limC1(gteMAC1 >> 4); | |
864 | gteG2 = limC2(gteMAC2 >> 4); | |
865 | gteB2 = limC3(gteMAC3 >> 4); | |
866 | } | |
867 | gteIR1 = limB1(gteMAC1, 1); | |
868 | gteIR2 = limB2(gteMAC2, 1); | |
869 | gteIR3 = limB3(gteMAC3, 1); | |
870 | } | |
871 | ||
f74fb727 | 872 | void gteCC(psxCP2Regs *regs) { |
ef79bbde P |
873 | #ifdef GTE_LOG |
874 | GTE_LOG("GTE CC\n"); | |
875 | #endif | |
876 | gteFLAG = 0; | |
877 | ||
878 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
879 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
880 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
881 | gteIR1 = limB1(gteMAC1, 1); | |
882 | gteIR2 = limB2(gteMAC2, 1); | |
883 | gteIR3 = limB3(gteMAC3, 1); | |
b3254af9 | 884 | gteMAC1 = ((s32)gteR * gteIR1) >> 8; |
885 | gteMAC2 = ((s32)gteG * gteIR2) >> 8; | |
886 | gteMAC3 = ((s32)gteB * gteIR3) >> 8; | |
ef79bbde P |
887 | gteIR1 = limB1(gteMAC1, 1); |
888 | gteIR2 = limB2(gteMAC2, 1); | |
889 | gteIR3 = limB3(gteMAC3, 1); | |
890 | ||
891 | gteRGB0 = gteRGB1; | |
892 | gteRGB1 = gteRGB2; | |
893 | gteCODE2 = gteCODE; | |
894 | gteR2 = limC1(gteMAC1 >> 4); | |
895 | gteG2 = limC2(gteMAC2 >> 4); | |
896 | gteB2 = limC3(gteMAC3 >> 4); | |
897 | } | |
898 | ||
f74fb727 | 899 | void gteINTPL(psxCP2Regs *regs) { |
ef79bbde P |
900 | int shift = 12 * GTE_SF(gteop); |
901 | int lm = GTE_LM(gteop); | |
902 | ||
903 | #ifdef GTE_LOG | |
904 | GTE_LOG("GTE INTPL\n"); | |
905 | #endif | |
906 | gteFLAG = 0; | |
907 | ||
b3254af9 | 908 | gteMAC1 = ((gteIR1 << 12) + (gteIR0 * limB1(gteRFC - gteIR1, 0))) >> shift; |
909 | gteMAC2 = ((gteIR2 << 12) + (gteIR0 * limB2(gteGFC - gteIR2, 0))) >> shift; | |
910 | gteMAC3 = ((gteIR3 << 12) + (gteIR0 * limB3(gteBFC - gteIR3, 0))) >> shift; | |
ef79bbde P |
911 | gteIR1 = limB1(gteMAC1, lm); |
912 | gteIR2 = limB2(gteMAC2, lm); | |
913 | gteIR3 = limB3(gteMAC3, lm); | |
914 | gteRGB0 = gteRGB1; | |
915 | gteRGB1 = gteRGB2; | |
916 | gteCODE2 = gteCODE; | |
917 | gteR2 = limC1(gteMAC1 >> 4); | |
918 | gteG2 = limC2(gteMAC2 >> 4); | |
919 | gteB2 = limC3(gteMAC3 >> 4); | |
920 | } | |
921 | ||
f74fb727 | 922 | void gteCDP(psxCP2Regs *regs) { |
ef79bbde P |
923 | #ifdef GTE_LOG |
924 | GTE_LOG("GTE CDP\n"); | |
925 | #endif | |
926 | gteFLAG = 0; | |
927 | ||
928 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
929 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
930 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
931 | gteIR1 = limB1(gteMAC1, 1); | |
932 | gteIR2 = limB2(gteMAC2, 1); | |
933 | gteIR3 = limB3(gteMAC3, 1); | |
b3254af9 | 934 | gteMAC1 = (((gteR << 4) * gteIR1) + (gteIR0 * limB1(gteRFC - ((gteR * gteIR1) >> 8), 0))) >> 12; |
935 | gteMAC2 = (((gteG << 4) * gteIR2) + (gteIR0 * limB2(gteGFC - ((gteG * gteIR2) >> 8), 0))) >> 12; | |
936 | gteMAC3 = (((gteB << 4) * gteIR3) + (gteIR0 * limB3(gteBFC - ((gteB * gteIR3) >> 8), 0))) >> 12; | |
ef79bbde P |
937 | gteIR1 = limB1(gteMAC1, 1); |
938 | gteIR2 = limB2(gteMAC2, 1); | |
939 | gteIR3 = limB3(gteMAC3, 1); | |
940 | ||
941 | gteRGB0 = gteRGB1; | |
942 | gteRGB1 = gteRGB2; | |
943 | gteCODE2 = gteCODE; | |
944 | gteR2 = limC1(gteMAC1 >> 4); | |
945 | gteG2 = limC2(gteMAC2 >> 4); | |
946 | gteB2 = limC3(gteMAC3 >> 4); | |
947 | } |