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 | ||
29 | #define VX(n) (n < 3 ? psxRegs.CP2D.p[n << 1].sw.l : psxRegs.CP2D.p[9].sw.l) | |
30 | #define VY(n) (n < 3 ? psxRegs.CP2D.p[n << 1].sw.h : psxRegs.CP2D.p[10].sw.l) | |
31 | #define VZ(n) (n < 3 ? psxRegs.CP2D.p[(n << 1) + 1].sw.l : psxRegs.CP2D.p[11].sw.l) | |
32 | #define MX11(n) (n < 3 ? psxRegs.CP2C.p[(n << 3)].sw.l : 0) | |
33 | #define MX12(n) (n < 3 ? psxRegs.CP2C.p[(n << 3)].sw.h : 0) | |
34 | #define MX13(n) (n < 3 ? psxRegs.CP2C.p[(n << 3) + 1].sw.l : 0) | |
35 | #define MX21(n) (n < 3 ? psxRegs.CP2C.p[(n << 3) + 1].sw.h : 0) | |
36 | #define MX22(n) (n < 3 ? psxRegs.CP2C.p[(n << 3) + 2].sw.l : 0) | |
37 | #define MX23(n) (n < 3 ? psxRegs.CP2C.p[(n << 3) + 2].sw.h : 0) | |
38 | #define MX31(n) (n < 3 ? psxRegs.CP2C.p[(n << 3) + 3].sw.l : 0) | |
39 | #define MX32(n) (n < 3 ? psxRegs.CP2C.p[(n << 3) + 3].sw.h : 0) | |
40 | #define MX33(n) (n < 3 ? psxRegs.CP2C.p[(n << 3) + 4].sw.l : 0) | |
41 | #define CV1(n) (n < 3 ? (s32)psxRegs.CP2C.r[(n << 3) + 5] : 0) | |
42 | #define CV2(n) (n < 3 ? (s32)psxRegs.CP2C.r[(n << 3) + 6] : 0) | |
43 | #define CV3(n) (n < 3 ? (s32)psxRegs.CP2C.r[(n << 3) + 7] : 0) | |
44 | ||
45 | #define fSX(n) ((psxRegs.CP2D.p)[((n) + 12)].sw.l) | |
46 | #define fSY(n) ((psxRegs.CP2D.p)[((n) + 12)].sw.h) | |
47 | #define fSZ(n) ((psxRegs.CP2D.p)[((n) + 17)].w.l) /* (n == 0) => SZ1; */ | |
48 | ||
49 | #define gteVXY0 (psxRegs.CP2D.r[0]) | |
50 | #define gteVX0 (psxRegs.CP2D.p[0].sw.l) | |
51 | #define gteVY0 (psxRegs.CP2D.p[0].sw.h) | |
52 | #define gteVZ0 (psxRegs.CP2D.p[1].sw.l) | |
53 | #define gteVXY1 (psxRegs.CP2D.r[2]) | |
54 | #define gteVX1 (psxRegs.CP2D.p[2].sw.l) | |
55 | #define gteVY1 (psxRegs.CP2D.p[2].sw.h) | |
56 | #define gteVZ1 (psxRegs.CP2D.p[3].sw.l) | |
57 | #define gteVXY2 (psxRegs.CP2D.r[4]) | |
58 | #define gteVX2 (psxRegs.CP2D.p[4].sw.l) | |
59 | #define gteVY2 (psxRegs.CP2D.p[4].sw.h) | |
60 | #define gteVZ2 (psxRegs.CP2D.p[5].sw.l) | |
61 | #define gteRGB (psxRegs.CP2D.r[6]) | |
62 | #define gteR (psxRegs.CP2D.p[6].b.l) | |
63 | #define gteG (psxRegs.CP2D.p[6].b.h) | |
64 | #define gteB (psxRegs.CP2D.p[6].b.h2) | |
65 | #define gteCODE (psxRegs.CP2D.p[6].b.h3) | |
66 | #define gteOTZ (psxRegs.CP2D.p[7].w.l) | |
67 | #define gteIR0 (psxRegs.CP2D.p[8].sw.l) | |
68 | #define gteIR1 (psxRegs.CP2D.p[9].sw.l) | |
69 | #define gteIR2 (psxRegs.CP2D.p[10].sw.l) | |
70 | #define gteIR3 (psxRegs.CP2D.p[11].sw.l) | |
71 | #define gteSXY0 (psxRegs.CP2D.r[12]) | |
72 | #define gteSX0 (psxRegs.CP2D.p[12].sw.l) | |
73 | #define gteSY0 (psxRegs.CP2D.p[12].sw.h) | |
74 | #define gteSXY1 (psxRegs.CP2D.r[13]) | |
75 | #define gteSX1 (psxRegs.CP2D.p[13].sw.l) | |
76 | #define gteSY1 (psxRegs.CP2D.p[13].sw.h) | |
77 | #define gteSXY2 (psxRegs.CP2D.r[14]) | |
78 | #define gteSX2 (psxRegs.CP2D.p[14].sw.l) | |
79 | #define gteSY2 (psxRegs.CP2D.p[14].sw.h) | |
80 | #define gteSXYP (psxRegs.CP2D.r[15]) | |
81 | #define gteSXP (psxRegs.CP2D.p[15].sw.l) | |
82 | #define gteSYP (psxRegs.CP2D.p[15].sw.h) | |
83 | #define gteSZ0 (psxRegs.CP2D.p[16].w.l) | |
84 | #define gteSZ1 (psxRegs.CP2D.p[17].w.l) | |
85 | #define gteSZ2 (psxRegs.CP2D.p[18].w.l) | |
86 | #define gteSZ3 (psxRegs.CP2D.p[19].w.l) | |
87 | #define gteRGB0 (psxRegs.CP2D.r[20]) | |
88 | #define gteR0 (psxRegs.CP2D.p[20].b.l) | |
89 | #define gteG0 (psxRegs.CP2D.p[20].b.h) | |
90 | #define gteB0 (psxRegs.CP2D.p[20].b.h2) | |
91 | #define gteCODE0 (psxRegs.CP2D.p[20].b.h3) | |
92 | #define gteRGB1 (psxRegs.CP2D.r[21]) | |
93 | #define gteR1 (psxRegs.CP2D.p[21].b.l) | |
94 | #define gteG1 (psxRegs.CP2D.p[21].b.h) | |
95 | #define gteB1 (psxRegs.CP2D.p[21].b.h2) | |
96 | #define gteCODE1 (psxRegs.CP2D.p[21].b.h3) | |
97 | #define gteRGB2 (psxRegs.CP2D.r[22]) | |
98 | #define gteR2 (psxRegs.CP2D.p[22].b.l) | |
99 | #define gteG2 (psxRegs.CP2D.p[22].b.h) | |
100 | #define gteB2 (psxRegs.CP2D.p[22].b.h2) | |
101 | #define gteCODE2 (psxRegs.CP2D.p[22].b.h3) | |
102 | #define gteRES1 (psxRegs.CP2D.r[23]) | |
103 | #define gteMAC0 (((s32 *)psxRegs.CP2D.r)[24]) | |
104 | #define gteMAC1 (((s32 *)psxRegs.CP2D.r)[25]) | |
105 | #define gteMAC2 (((s32 *)psxRegs.CP2D.r)[26]) | |
106 | #define gteMAC3 (((s32 *)psxRegs.CP2D.r)[27]) | |
107 | #define gteIRGB (psxRegs.CP2D.r[28]) | |
108 | #define gteORGB (psxRegs.CP2D.r[29]) | |
109 | #define gteLZCS (psxRegs.CP2D.r[30]) | |
110 | #define gteLZCR (psxRegs.CP2D.r[31]) | |
111 | ||
112 | #define gteR11R12 (((s32 *)psxRegs.CP2C.r)[0]) | |
113 | #define gteR22R23 (((s32 *)psxRegs.CP2C.r)[2]) | |
114 | #define gteR11 (psxRegs.CP2C.p[0].sw.l) | |
115 | #define gteR12 (psxRegs.CP2C.p[0].sw.h) | |
116 | #define gteR13 (psxRegs.CP2C.p[1].sw.l) | |
117 | #define gteR21 (psxRegs.CP2C.p[1].sw.h) | |
118 | #define gteR22 (psxRegs.CP2C.p[2].sw.l) | |
119 | #define gteR23 (psxRegs.CP2C.p[2].sw.h) | |
120 | #define gteR31 (psxRegs.CP2C.p[3].sw.l) | |
121 | #define gteR32 (psxRegs.CP2C.p[3].sw.h) | |
122 | #define gteR33 (psxRegs.CP2C.p[4].sw.l) | |
123 | #define gteTRX (((s32 *)psxRegs.CP2C.r)[5]) | |
124 | #define gteTRY (((s32 *)psxRegs.CP2C.r)[6]) | |
125 | #define gteTRZ (((s32 *)psxRegs.CP2C.r)[7]) | |
126 | #define gteL11 (psxRegs.CP2C.p[8].sw.l) | |
127 | #define gteL12 (psxRegs.CP2C.p[8].sw.h) | |
128 | #define gteL13 (psxRegs.CP2C.p[9].sw.l) | |
129 | #define gteL21 (psxRegs.CP2C.p[9].sw.h) | |
130 | #define gteL22 (psxRegs.CP2C.p[10].sw.l) | |
131 | #define gteL23 (psxRegs.CP2C.p[10].sw.h) | |
132 | #define gteL31 (psxRegs.CP2C.p[11].sw.l) | |
133 | #define gteL32 (psxRegs.CP2C.p[11].sw.h) | |
134 | #define gteL33 (psxRegs.CP2C.p[12].sw.l) | |
135 | #define gteRBK (((s32 *)psxRegs.CP2C.r)[13]) | |
136 | #define gteGBK (((s32 *)psxRegs.CP2C.r)[14]) | |
137 | #define gteBBK (((s32 *)psxRegs.CP2C.r)[15]) | |
138 | #define gteLR1 (psxRegs.CP2C.p[16].sw.l) | |
139 | #define gteLR2 (psxRegs.CP2C.p[16].sw.h) | |
140 | #define gteLR3 (psxRegs.CP2C.p[17].sw.l) | |
141 | #define gteLG1 (psxRegs.CP2C.p[17].sw.h) | |
142 | #define gteLG2 (psxRegs.CP2C.p[18].sw.l) | |
143 | #define gteLG3 (psxRegs.CP2C.p[18].sw.h) | |
144 | #define gteLB1 (psxRegs.CP2C.p[19].sw.l) | |
145 | #define gteLB2 (psxRegs.CP2C.p[19].sw.h) | |
146 | #define gteLB3 (psxRegs.CP2C.p[20].sw.l) | |
147 | #define gteRFC (((s32 *)psxRegs.CP2C.r)[21]) | |
148 | #define gteGFC (((s32 *)psxRegs.CP2C.r)[22]) | |
149 | #define gteBFC (((s32 *)psxRegs.CP2C.r)[23]) | |
150 | #define gteOFX (((s32 *)psxRegs.CP2C.r)[24]) | |
151 | #define gteOFY (((s32 *)psxRegs.CP2C.r)[25]) | |
152 | #define gteH (psxRegs.CP2C.p[26].sw.l) | |
153 | #define gteDQA (psxRegs.CP2C.p[27].sw.l) | |
154 | #define gteDQB (((s32 *)psxRegs.CP2C.r)[28]) | |
155 | #define gteZSF3 (psxRegs.CP2C.p[29].sw.l) | |
156 | #define gteZSF4 (psxRegs.CP2C.p[30].sw.l) | |
157 | #define gteFLAG (psxRegs.CP2C.r[31]) | |
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 | ||
171 | static inline s64 BOUNDS(s64 n_value, s64 n_max, int n_maxflag, s64 n_min, int n_minflag) { | |
172 | if (n_value > n_max) { | |
173 | gteFLAG |= n_maxflag; | |
174 | } else if (n_value < n_min) { | |
175 | gteFLAG |= n_minflag; | |
176 | } | |
177 | return n_value; | |
178 | } | |
179 | ||
180 | static inline s32 LIM(s32 value, s32 max, s32 min, u32 flag) { | |
181 | s32 ret = value; | |
182 | if (value > max) { | |
183 | gteFLAG |= flag; | |
184 | ret = max; | |
185 | } else if (value < min) { | |
186 | gteFLAG |= flag; | |
187 | ret = min; | |
188 | } | |
189 | return ret; | |
190 | } | |
191 | ||
192 | #define A1(a) BOUNDS((a), 0x7fffffff, (1 << 30), -(s64)0x80000000, (1 << 31) | (1 << 27)) | |
193 | #define A2(a) BOUNDS((a), 0x7fffffff, (1 << 29), -(s64)0x80000000, (1 << 31) | (1 << 26)) | |
194 | #define A3(a) BOUNDS((a), 0x7fffffff, (1 << 28), -(s64)0x80000000, (1 << 31) | (1 << 25)) | |
195 | #define limB1(a, l) LIM((a), 0x7fff, -0x8000 * !l, (1 << 31) | (1 << 24)) | |
196 | #define limB2(a, l) LIM((a), 0x7fff, -0x8000 * !l, (1 << 31) | (1 << 23)) | |
197 | #define limB3(a, l) LIM((a), 0x7fff, -0x8000 * !l, (1 << 22)) | |
198 | #define limC1(a) LIM((a), 0x00ff, 0x0000, (1 << 21)) | |
199 | #define limC2(a) LIM((a), 0x00ff, 0x0000, (1 << 20)) | |
200 | #define limC3(a) LIM((a), 0x00ff, 0x0000, (1 << 19)) | |
201 | #define limD(a) LIM((a), 0xffff, 0x0000, (1 << 31) | (1 << 18)) | |
202 | ||
203 | static inline u32 limE(u32 result) { | |
204 | if (result > 0x1ffff) { | |
205 | gteFLAG |= (1 << 31) | (1 << 17); | |
206 | return 0x1ffff; | |
207 | } | |
208 | return result; | |
209 | } | |
210 | ||
211 | #define F(a) BOUNDS((a), 0x7fffffff, (1 << 31) | (1 << 16), -(s64)0x80000000, (1 << 31) | (1 << 15)) | |
212 | #define limG1(a) LIM((a), 0x3ff, -0x400, (1 << 31) | (1 << 14)) | |
213 | #define limG2(a) LIM((a), 0x3ff, -0x400, (1 << 31) | (1 << 13)) | |
7384197d | 214 | #define limH(a) LIM((a), 0x1000, 0x0000, (1 << 12)) |
ef79bbde P |
215 | |
216 | #include "gte_divider.h" | |
217 | ||
218 | static inline u32 MFC2(int reg) { | |
219 | switch (reg) { | |
220 | case 1: | |
221 | case 3: | |
222 | case 5: | |
223 | case 8: | |
224 | case 9: | |
225 | case 10: | |
226 | case 11: | |
227 | psxRegs.CP2D.r[reg] = (s32)psxRegs.CP2D.p[reg].sw.l; | |
228 | break; | |
229 | ||
230 | case 7: | |
231 | case 16: | |
232 | case 17: | |
233 | case 18: | |
234 | case 19: | |
235 | psxRegs.CP2D.r[reg] = (u32)psxRegs.CP2D.p[reg].w.l; | |
236 | break; | |
237 | ||
238 | case 15: | |
239 | psxRegs.CP2D.r[reg] = gteSXY2; | |
240 | break; | |
241 | ||
242 | case 28: | |
ef79bbde P |
243 | case 29: |
244 | psxRegs.CP2D.r[reg] = LIM(gteIR1 >> 7, 0x1f, 0, 0) | | |
245 | (LIM(gteIR2 >> 7, 0x1f, 0, 0) << 5) | | |
246 | (LIM(gteIR3 >> 7, 0x1f, 0, 0) << 10); | |
247 | break; | |
248 | } | |
249 | return psxRegs.CP2D.r[reg]; | |
250 | } | |
251 | ||
252 | static inline void MTC2(u32 value, int reg) { | |
253 | switch (reg) { | |
254 | case 15: | |
255 | gteSXY0 = gteSXY1; | |
256 | gteSXY1 = gteSXY2; | |
257 | gteSXY2 = value; | |
258 | gteSXYP = value; | |
259 | break; | |
260 | ||
261 | case 28: | |
262 | gteIRGB = value; | |
263 | gteIR1 = (value & 0x1f) << 7; | |
264 | gteIR2 = (value & 0x3e0) << 2; | |
265 | gteIR3 = (value & 0x7c00) >> 3; | |
266 | break; | |
267 | ||
268 | case 30: | |
269 | { | |
270 | int a; | |
271 | gteLZCS = value; | |
272 | ||
273 | a = gteLZCS; | |
274 | if (a > 0) { | |
275 | int i; | |
276 | for (i = 31; (a & (1 << i)) == 0 && i >= 0; i--); | |
277 | gteLZCR = 31 - i; | |
278 | } else if (a < 0) { | |
279 | int i; | |
280 | a ^= 0xffffffff; | |
281 | for (i = 31; (a & (1 << i)) == 0 && i >= 0; i--); | |
282 | gteLZCR = 31 - i; | |
283 | } else { | |
284 | gteLZCR = 32; | |
285 | } | |
286 | } | |
287 | break; | |
288 | ||
ef79bbde P |
289 | case 31: |
290 | return; | |
291 | ||
292 | default: | |
293 | psxRegs.CP2D.r[reg] = value; | |
294 | } | |
295 | } | |
296 | ||
297 | static inline void CTC2(u32 value, int reg) { | |
298 | switch (reg) { | |
299 | case 4: | |
300 | case 12: | |
301 | case 20: | |
302 | case 26: | |
303 | case 27: | |
304 | case 29: | |
305 | case 30: | |
306 | value = (s32)(s16)value; | |
307 | break; | |
308 | ||
309 | case 31: | |
310 | value = value & 0x7ffff000; | |
311 | if (value & 0x7f87e000) value |= 0x80000000; | |
312 | break; | |
313 | } | |
314 | ||
315 | psxRegs.CP2C.r[reg] = value; | |
316 | } | |
317 | ||
318 | void gteMFC2() { | |
319 | if (!_Rt_) return; | |
320 | psxRegs.GPR.r[_Rt_] = MFC2(_Rd_); | |
321 | } | |
322 | ||
323 | void gteCFC2() { | |
324 | if (!_Rt_) return; | |
325 | psxRegs.GPR.r[_Rt_] = psxRegs.CP2C.r[_Rd_]; | |
326 | } | |
327 | ||
328 | void gteMTC2() { | |
329 | MTC2(psxRegs.GPR.r[_Rt_], _Rd_); | |
330 | } | |
331 | ||
332 | void gteCTC2() { | |
333 | CTC2(psxRegs.GPR.r[_Rt_], _Rd_); | |
334 | } | |
335 | ||
336 | #define _oB_ (psxRegs.GPR.r[_Rs_] + _Imm_) | |
337 | ||
338 | void gteLWC2() { | |
339 | MTC2(psxMemRead32(_oB_), _Rt_); | |
340 | } | |
341 | ||
342 | void gteSWC2() { | |
343 | psxMemWrite32(_oB_, MFC2(_Rt_)); | |
344 | } | |
345 | ||
a2544c92 | 346 | #define DIVIDE DIVIDE_ |
347 | static u32 DIVIDE_(s16 n, u16 d) { | |
348 | if (n >= 0 && n < d * 2) { | |
349 | s32 n_ = n; | |
350 | return ((n_ << 16) + d / 2) / d; | |
351 | //return (u32)((float)(n_ << 16) / (float)d + (float)0.5); | |
352 | } | |
353 | return 0xffffffff; | |
354 | } | |
355 | ||
ef79bbde P |
356 | void gteRTPS() { |
357 | int quotient; | |
358 | ||
359 | #ifdef GTE_LOG | |
360 | GTE_LOG("GTE RTPS\n"); | |
361 | #endif | |
362 | gteFLAG = 0; | |
363 | ||
364 | gteMAC1 = A1((((s64)gteTRX << 12) + (gteR11 * gteVX0) + (gteR12 * gteVY0) + (gteR13 * gteVZ0)) >> 12); | |
365 | gteMAC2 = A2((((s64)gteTRY << 12) + (gteR21 * gteVX0) + (gteR22 * gteVY0) + (gteR23 * gteVZ0)) >> 12); | |
366 | gteMAC3 = A3((((s64)gteTRZ << 12) + (gteR31 * gteVX0) + (gteR32 * gteVY0) + (gteR33 * gteVZ0)) >> 12); | |
367 | gteIR1 = limB1(gteMAC1, 0); | |
368 | gteIR2 = limB2(gteMAC2, 0); | |
369 | gteIR3 = limB3(gteMAC3, 0); | |
370 | gteSZ0 = gteSZ1; | |
371 | gteSZ1 = gteSZ2; | |
372 | gteSZ2 = gteSZ3; | |
373 | gteSZ3 = limD(gteMAC3); | |
374 | quotient = limE(DIVIDE(gteH, gteSZ3)); | |
375 | gteSXY0 = gteSXY1; | |
376 | gteSXY1 = gteSXY2; | |
377 | gteSX2 = limG1(F((s64)gteOFX + ((s64)gteIR1 * quotient)) >> 16); | |
378 | gteSY2 = limG2(F((s64)gteOFY + ((s64)gteIR2 * quotient)) >> 16); | |
379 | ||
380 | gteMAC0 = F((s64)(gteDQB + ((s64)gteDQA * quotient)) >> 12); | |
381 | gteIR0 = limH(gteMAC0); | |
382 | } | |
383 | ||
384 | void gteRTPT() { | |
385 | int quotient; | |
386 | int v; | |
387 | s32 vx, vy, vz; | |
388 | ||
389 | #ifdef GTE_LOG | |
390 | GTE_LOG("GTE RTPT\n"); | |
391 | #endif | |
392 | gteFLAG = 0; | |
393 | ||
394 | gteSZ0 = gteSZ3; | |
395 | for (v = 0; v < 3; v++) { | |
396 | vx = VX(v); | |
397 | vy = VY(v); | |
398 | vz = VZ(v); | |
399 | gteMAC1 = A1((((s64)gteTRX << 12) + (gteR11 * vx) + (gteR12 * vy) + (gteR13 * vz)) >> 12); | |
400 | gteMAC2 = A2((((s64)gteTRY << 12) + (gteR21 * vx) + (gteR22 * vy) + (gteR23 * vz)) >> 12); | |
401 | gteMAC3 = A3((((s64)gteTRZ << 12) + (gteR31 * vx) + (gteR32 * vy) + (gteR33 * vz)) >> 12); | |
402 | gteIR1 = limB1(gteMAC1, 0); | |
403 | gteIR2 = limB2(gteMAC2, 0); | |
404 | gteIR3 = limB3(gteMAC3, 0); | |
405 | fSZ(v) = limD(gteMAC3); | |
406 | quotient = limE(DIVIDE(gteH, fSZ(v))); | |
407 | fSX(v) = limG1(F((s64)gteOFX + ((s64)gteIR1 * quotient)) >> 16); | |
408 | fSY(v) = limG2(F((s64)gteOFY + ((s64)gteIR2 * quotient)) >> 16); | |
409 | } | |
410 | gteMAC0 = F((s64)(gteDQB + ((s64)gteDQA * quotient)) >> 12); | |
411 | gteIR0 = limH(gteMAC0); | |
412 | } | |
413 | ||
414 | void gteMVMVA() { | |
415 | int shift = 12 * GTE_SF(gteop); | |
416 | int mx = GTE_MX(gteop); | |
417 | int v = GTE_V(gteop); | |
418 | int cv = GTE_CV(gteop); | |
419 | int lm = GTE_LM(gteop); | |
420 | s32 vx = VX(v); | |
421 | s32 vy = VY(v); | |
422 | s32 vz = VZ(v); | |
423 | ||
424 | #ifdef GTE_LOG | |
425 | GTE_LOG("GTE MVMVA\n"); | |
426 | #endif | |
427 | gteFLAG = 0; | |
428 | ||
429 | gteMAC1 = A1((((s64)CV1(cv) << 12) + (MX11(mx) * vx) + (MX12(mx) * vy) + (MX13(mx) * vz)) >> shift); | |
430 | gteMAC2 = A2((((s64)CV2(cv) << 12) + (MX21(mx) * vx) + (MX22(mx) * vy) + (MX23(mx) * vz)) >> shift); | |
431 | gteMAC3 = A3((((s64)CV3(cv) << 12) + (MX31(mx) * vx) + (MX32(mx) * vy) + (MX33(mx) * vz)) >> shift); | |
432 | ||
433 | gteIR1 = limB1(gteMAC1, lm); | |
434 | gteIR2 = limB2(gteMAC2, lm); | |
435 | gteIR3 = limB3(gteMAC3, lm); | |
436 | } | |
437 | ||
438 | void gteNCLIP() { | |
439 | #ifdef GTE_LOG | |
440 | GTE_LOG("GTE NCLIP\n"); | |
441 | #endif | |
442 | gteFLAG = 0; | |
443 | ||
444 | gteMAC0 = F((s64)gteSX0 * (gteSY1 - gteSY2) + | |
445 | gteSX1 * (gteSY2 - gteSY0) + | |
446 | gteSX2 * (gteSY0 - gteSY1)); | |
447 | } | |
448 | ||
449 | void gteAVSZ3() { | |
450 | #ifdef GTE_LOG | |
451 | GTE_LOG("GTE AVSZ3\n"); | |
452 | #endif | |
453 | gteFLAG = 0; | |
454 | ||
455 | gteMAC0 = F((s64)(gteZSF3 * gteSZ1) + (gteZSF3 * gteSZ2) + (gteZSF3 * gteSZ3)); | |
456 | gteOTZ = limD(gteMAC0 >> 12); | |
457 | } | |
458 | ||
459 | void gteAVSZ4() { | |
460 | #ifdef GTE_LOG | |
461 | GTE_LOG("GTE AVSZ4\n"); | |
462 | #endif | |
463 | gteFLAG = 0; | |
464 | ||
465 | gteMAC0 = F((s64)(gteZSF4 * (gteSZ0 + gteSZ1 + gteSZ2 + gteSZ3))); | |
466 | gteOTZ = limD(gteMAC0 >> 12); | |
467 | } | |
468 | ||
469 | void gteSQR() { | |
470 | int shift = 12 * GTE_SF(gteop); | |
471 | int lm = GTE_LM(gteop); | |
472 | ||
473 | #ifdef GTE_LOG | |
474 | GTE_LOG("GTE SQR\n"); | |
475 | #endif | |
476 | gteFLAG = 0; | |
477 | ||
478 | gteMAC1 = A1((gteIR1 * gteIR1) >> shift); | |
479 | gteMAC2 = A2((gteIR2 * gteIR2) >> shift); | |
480 | gteMAC3 = A3((gteIR3 * gteIR3) >> shift); | |
7384197d | 481 | gteIR1 = limB1(gteMAC1, lm); |
482 | gteIR2 = limB2(gteMAC2, lm); | |
483 | gteIR3 = limB3(gteMAC3, lm); | |
ef79bbde P |
484 | } |
485 | ||
486 | void gteNCCS() { | |
487 | #ifdef GTE_LOG | |
488 | GTE_LOG("GTE NCCS\n"); | |
489 | #endif | |
490 | gteFLAG = 0; | |
491 | ||
492 | gteMAC1 = A1((((s64)gteL11 * gteVX0) + (gteL12 * gteVY0) + (gteL13 * gteVZ0)) >> 12); | |
493 | gteMAC2 = A2((((s64)gteL21 * gteVX0) + (gteL22 * gteVY0) + (gteL23 * gteVZ0)) >> 12); | |
494 | gteMAC3 = A3((((s64)gteL31 * gteVX0) + (gteL32 * gteVY0) + (gteL33 * gteVZ0)) >> 12); | |
495 | gteIR1 = limB1(gteMAC1, 1); | |
496 | gteIR2 = limB2(gteMAC2, 1); | |
497 | gteIR3 = limB3(gteMAC3, 1); | |
498 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
499 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
500 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
501 | gteIR1 = limB1(gteMAC1, 1); | |
502 | gteIR2 = limB2(gteMAC2, 1); | |
503 | gteIR3 = limB3(gteMAC3, 1); | |
504 | gteMAC1 = A1(((s64)gteR * gteIR1) >> 8); | |
505 | gteMAC2 = A2(((s64)gteG * gteIR2) >> 8); | |
506 | gteMAC3 = A3(((s64)gteB * gteIR3) >> 8); | |
507 | gteIR1 = limB1(gteMAC1, 1); | |
508 | gteIR2 = limB2(gteMAC2, 1); | |
509 | gteIR3 = limB3(gteMAC3, 1); | |
510 | ||
511 | gteRGB0 = gteRGB1; | |
512 | gteRGB1 = gteRGB2; | |
513 | gteCODE2 = gteCODE; | |
514 | gteR2 = limC1(gteMAC1 >> 4); | |
515 | gteG2 = limC2(gteMAC2 >> 4); | |
516 | gteB2 = limC3(gteMAC3 >> 4); | |
517 | } | |
518 | ||
519 | void gteNCCT() { | |
520 | int v; | |
521 | s32 vx, vy, vz; | |
522 | ||
523 | #ifdef GTE_LOG | |
524 | GTE_LOG("GTE NCCT\n"); | |
525 | #endif | |
526 | gteFLAG = 0; | |
527 | ||
528 | for (v = 0; v < 3; v++) { | |
529 | vx = VX(v); | |
530 | vy = VY(v); | |
531 | vz = VZ(v); | |
532 | gteMAC1 = A1((((s64)gteL11 * vx) + (gteL12 * vy) + (gteL13 * vz)) >> 12); | |
533 | gteMAC2 = A2((((s64)gteL21 * vx) + (gteL22 * vy) + (gteL23 * vz)) >> 12); | |
534 | gteMAC3 = A3((((s64)gteL31 * vx) + (gteL32 * vy) + (gteL33 * vz)) >> 12); | |
535 | gteIR1 = limB1(gteMAC1, 1); | |
536 | gteIR2 = limB2(gteMAC2, 1); | |
537 | gteIR3 = limB3(gteMAC3, 1); | |
538 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
539 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
540 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
541 | gteIR1 = limB1(gteMAC1, 1); | |
542 | gteIR2 = limB2(gteMAC2, 1); | |
543 | gteIR3 = limB3(gteMAC3, 1); | |
544 | gteMAC1 = A1(((s64)gteR * gteIR1) >> 8); | |
545 | gteMAC2 = A2(((s64)gteG * gteIR2) >> 8); | |
546 | gteMAC3 = A3(((s64)gteB * gteIR3) >> 8); | |
547 | ||
548 | gteRGB0 = gteRGB1; | |
549 | gteRGB1 = gteRGB2; | |
550 | gteCODE2 = gteCODE; | |
551 | gteR2 = limC1(gteMAC1 >> 4); | |
552 | gteG2 = limC2(gteMAC2 >> 4); | |
553 | gteB2 = limC3(gteMAC3 >> 4); | |
554 | } | |
555 | gteIR1 = limB1(gteMAC1, 1); | |
556 | gteIR2 = limB2(gteMAC2, 1); | |
557 | gteIR3 = limB3(gteMAC3, 1); | |
558 | } | |
559 | ||
560 | void gteNCDS() { | |
561 | #ifdef GTE_LOG | |
562 | GTE_LOG("GTE NCDS\n"); | |
563 | #endif | |
564 | gteFLAG = 0; | |
565 | ||
566 | gteMAC1 = A1((((s64)gteL11 * gteVX0) + (gteL12 * gteVY0) + (gteL13 * gteVZ0)) >> 12); | |
567 | gteMAC2 = A2((((s64)gteL21 * gteVX0) + (gteL22 * gteVY0) + (gteL23 * gteVZ0)) >> 12); | |
568 | gteMAC3 = A3((((s64)gteL31 * gteVX0) + (gteL32 * gteVY0) + (gteL33 * gteVZ0)) >> 12); | |
569 | gteIR1 = limB1(gteMAC1, 1); | |
570 | gteIR2 = limB2(gteMAC2, 1); | |
571 | gteIR3 = limB3(gteMAC3, 1); | |
572 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
573 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
574 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
575 | gteIR1 = limB1(gteMAC1, 1); | |
576 | gteIR2 = limB2(gteMAC2, 1); | |
577 | gteIR3 = limB3(gteMAC3, 1); | |
578 | gteMAC1 = A1(((((s64)gteR << 4) * gteIR1) + (gteIR0 * limB1(gteRFC - ((gteR * gteIR1) >> 8), 0))) >> 12); | |
579 | gteMAC2 = A2(((((s64)gteG << 4) * gteIR2) + (gteIR0 * limB2(gteGFC - ((gteG * gteIR2) >> 8), 0))) >> 12); | |
580 | gteMAC3 = A3(((((s64)gteB << 4) * gteIR3) + (gteIR0 * limB3(gteBFC - ((gteB * gteIR3) >> 8), 0))) >> 12); | |
581 | gteIR1 = limB1(gteMAC1, 1); | |
582 | gteIR2 = limB2(gteMAC2, 1); | |
583 | gteIR3 = limB3(gteMAC3, 1); | |
584 | ||
585 | gteRGB0 = gteRGB1; | |
586 | gteRGB1 = gteRGB2; | |
587 | gteCODE2 = gteCODE; | |
588 | gteR2 = limC1(gteMAC1 >> 4); | |
589 | gteG2 = limC2(gteMAC2 >> 4); | |
590 | gteB2 = limC3(gteMAC3 >> 4); | |
591 | } | |
592 | ||
593 | void gteNCDT() { | |
594 | int v; | |
595 | s32 vx, vy, vz; | |
596 | ||
597 | #ifdef GTE_LOG | |
598 | GTE_LOG("GTE NCDT\n"); | |
599 | #endif | |
600 | gteFLAG = 0; | |
601 | ||
602 | for (v = 0; v < 3; v++) { | |
603 | vx = VX(v); | |
604 | vy = VY(v); | |
605 | vz = VZ(v); | |
606 | gteMAC1 = A1((((s64)gteL11 * vx) + (gteL12 * vy) + (gteL13 * vz)) >> 12); | |
607 | gteMAC2 = A2((((s64)gteL21 * vx) + (gteL22 * vy) + (gteL23 * vz)) >> 12); | |
608 | gteMAC3 = A3((((s64)gteL31 * vx) + (gteL32 * vy) + (gteL33 * vz)) >> 12); | |
609 | gteIR1 = limB1(gteMAC1, 1); | |
610 | gteIR2 = limB2(gteMAC2, 1); | |
611 | gteIR3 = limB3(gteMAC3, 1); | |
612 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
613 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
614 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
615 | gteIR1 = limB1(gteMAC1, 1); | |
616 | gteIR2 = limB2(gteMAC2, 1); | |
617 | gteIR3 = limB3(gteMAC3, 1); | |
618 | gteMAC1 = A1(((((s64)gteR << 4) * gteIR1) + (gteIR0 * limB1(gteRFC - ((gteR * gteIR1) >> 8), 0))) >> 12); | |
619 | gteMAC2 = A2(((((s64)gteG << 4) * gteIR2) + (gteIR0 * limB2(gteGFC - ((gteG * gteIR2) >> 8), 0))) >> 12); | |
620 | gteMAC3 = A3(((((s64)gteB << 4) * gteIR3) + (gteIR0 * limB3(gteBFC - ((gteB * gteIR3) >> 8), 0))) >> 12); | |
621 | ||
622 | gteRGB0 = gteRGB1; | |
623 | gteRGB1 = gteRGB2; | |
624 | gteCODE2 = gteCODE; | |
625 | gteR2 = limC1(gteMAC1 >> 4); | |
626 | gteG2 = limC2(gteMAC2 >> 4); | |
627 | gteB2 = limC3(gteMAC3 >> 4); | |
628 | } | |
629 | gteIR1 = limB1(gteMAC1, 1); | |
630 | gteIR2 = limB2(gteMAC2, 1); | |
631 | gteIR3 = limB3(gteMAC3, 1); | |
632 | } | |
633 | ||
634 | void gteOP() { | |
635 | int shift = 12 * GTE_SF(gteop); | |
636 | int lm = GTE_LM(gteop); | |
637 | ||
638 | #ifdef GTE_LOG | |
639 | GTE_LOG("GTE OP\n"); | |
640 | #endif | |
641 | gteFLAG = 0; | |
642 | ||
643 | gteMAC1 = A1(((s64)(gteR22 * gteIR3) - (gteR33 * gteIR2)) >> shift); | |
644 | gteMAC2 = A2(((s64)(gteR33 * gteIR1) - (gteR11 * gteIR3)) >> shift); | |
645 | gteMAC3 = A3(((s64)(gteR11 * gteIR2) - (gteR22 * gteIR1)) >> shift); | |
646 | gteIR1 = limB1(gteMAC1, lm); | |
647 | gteIR2 = limB2(gteMAC2, lm); | |
648 | gteIR3 = limB3(gteMAC3, lm); | |
649 | } | |
650 | ||
651 | void gteDCPL() { | |
652 | int lm = GTE_LM(gteop); | |
653 | ||
654 | s64 RIR1 = ((s64)gteR * gteIR1) >> 8; | |
655 | s64 GIR2 = ((s64)gteG * gteIR2) >> 8; | |
656 | s64 BIR3 = ((s64)gteB * gteIR3) >> 8; | |
657 | ||
658 | #ifdef GTE_LOG | |
659 | GTE_LOG("GTE DCPL\n"); | |
660 | #endif | |
661 | gteFLAG = 0; | |
662 | ||
663 | gteMAC1 = A1(RIR1 + ((gteIR0 * limB1(gteRFC - RIR1, 0)) >> 12)); | |
664 | gteMAC2 = A2(GIR2 + ((gteIR0 * limB1(gteGFC - GIR2, 0)) >> 12)); | |
665 | gteMAC3 = A3(BIR3 + ((gteIR0 * limB1(gteBFC - BIR3, 0)) >> 12)); | |
666 | ||
667 | gteIR1 = limB1(gteMAC1, lm); | |
668 | gteIR2 = limB2(gteMAC2, lm); | |
669 | gteIR3 = limB3(gteMAC3, lm); | |
670 | ||
671 | gteRGB0 = gteRGB1; | |
672 | gteRGB1 = gteRGB2; | |
673 | gteCODE2 = gteCODE; | |
674 | gteR2 = limC1(gteMAC1 >> 4); | |
675 | gteG2 = limC2(gteMAC2 >> 4); | |
676 | gteB2 = limC3(gteMAC3 >> 4); | |
677 | } | |
678 | ||
679 | void gteGPF() { | |
680 | int shift = 12 * GTE_SF(gteop); | |
681 | ||
682 | #ifdef GTE_LOG | |
683 | GTE_LOG("GTE GPF\n"); | |
684 | #endif | |
685 | gteFLAG = 0; | |
686 | ||
687 | gteMAC1 = A1(((s64)gteIR0 * gteIR1) >> shift); | |
688 | gteMAC2 = A2(((s64)gteIR0 * gteIR2) >> shift); | |
689 | gteMAC3 = A3(((s64)gteIR0 * gteIR3) >> shift); | |
690 | gteIR1 = limB1(gteMAC1, 0); | |
691 | gteIR2 = limB2(gteMAC2, 0); | |
692 | gteIR3 = limB3(gteMAC3, 0); | |
693 | ||
694 | gteRGB0 = gteRGB1; | |
695 | gteRGB1 = gteRGB2; | |
696 | gteCODE2 = gteCODE; | |
697 | gteR2 = limC1(gteMAC1 >> 4); | |
698 | gteG2 = limC2(gteMAC2 >> 4); | |
699 | gteB2 = limC3(gteMAC3 >> 4); | |
700 | } | |
701 | ||
702 | void gteGPL() { | |
703 | int shift = 12 * GTE_SF(gteop); | |
704 | ||
705 | #ifdef GTE_LOG | |
706 | GTE_LOG("GTE GPL\n"); | |
707 | #endif | |
708 | gteFLAG = 0; | |
709 | ||
710 | gteMAC1 = A1((((s64)gteMAC1 << shift) + (gteIR0 * gteIR1)) >> shift); | |
711 | gteMAC2 = A2((((s64)gteMAC2 << shift) + (gteIR0 * gteIR2)) >> shift); | |
712 | gteMAC3 = A3((((s64)gteMAC3 << shift) + (gteIR0 * gteIR3)) >> shift); | |
713 | gteIR1 = limB1(gteMAC1, 0); | |
714 | gteIR2 = limB2(gteMAC2, 0); | |
715 | gteIR3 = limB3(gteMAC3, 0); | |
716 | ||
717 | gteRGB0 = gteRGB1; | |
718 | gteRGB1 = gteRGB2; | |
719 | gteCODE2 = gteCODE; | |
720 | gteR2 = limC1(gteMAC1 >> 4); | |
721 | gteG2 = limC2(gteMAC2 >> 4); | |
722 | gteB2 = limC3(gteMAC3 >> 4); | |
723 | } | |
724 | ||
725 | void gteDPCS() { | |
726 | int shift = 12 * GTE_SF(gteop); | |
727 | ||
728 | #ifdef GTE_LOG | |
729 | GTE_LOG("GTE DPCS\n"); | |
730 | #endif | |
731 | gteFLAG = 0; | |
732 | ||
733 | gteMAC1 = A1(((gteR << 16) + (gteIR0 * limB1(A1((s64)gteRFC - (gteR << 4)) << (12 - shift), 0))) >> 12); | |
734 | gteMAC2 = A2(((gteG << 16) + (gteIR0 * limB2(A2((s64)gteGFC - (gteG << 4)) << (12 - shift), 0))) >> 12); | |
735 | gteMAC3 = A3(((gteB << 16) + (gteIR0 * limB3(A3((s64)gteBFC - (gteB << 4)) << (12 - shift), 0))) >> 12); | |
736 | ||
737 | gteIR1 = limB1(gteMAC1, 0); | |
738 | gteIR2 = limB2(gteMAC2, 0); | |
739 | gteIR3 = limB3(gteMAC3, 0); | |
740 | gteRGB0 = gteRGB1; | |
741 | gteRGB1 = gteRGB2; | |
742 | gteCODE2 = gteCODE; | |
743 | gteR2 = limC1(gteMAC1 >> 4); | |
744 | gteG2 = limC2(gteMAC2 >> 4); | |
745 | gteB2 = limC3(gteMAC3 >> 4); | |
746 | } | |
747 | ||
748 | void gteDPCT() { | |
749 | int v; | |
750 | ||
751 | #ifdef GTE_LOG | |
752 | GTE_LOG("GTE DPCT\n"); | |
753 | #endif | |
754 | gteFLAG = 0; | |
755 | ||
756 | for (v = 0; v < 3; v++) { | |
757 | gteMAC1 = A1((((s64)gteR0 << 16) + ((s64)gteIR0 * (limB1(gteRFC - (gteR0 << 4), 0)))) >> 12); | |
758 | gteMAC2 = A2((((s64)gteG0 << 16) + ((s64)gteIR0 * (limB1(gteGFC - (gteG0 << 4), 0)))) >> 12); | |
759 | gteMAC3 = A3((((s64)gteB0 << 16) + ((s64)gteIR0 * (limB1(gteBFC - (gteB0 << 4), 0)))) >> 12); | |
760 | ||
761 | gteRGB0 = gteRGB1; | |
762 | gteRGB1 = gteRGB2; | |
763 | gteCODE2 = gteCODE; | |
764 | gteR2 = limC1(gteMAC1 >> 4); | |
765 | gteG2 = limC2(gteMAC2 >> 4); | |
766 | gteB2 = limC3(gteMAC3 >> 4); | |
767 | } | |
768 | gteIR1 = limB1(gteMAC1, 0); | |
769 | gteIR2 = limB2(gteMAC2, 0); | |
770 | gteIR3 = limB3(gteMAC3, 0); | |
771 | } | |
772 | ||
773 | void gteNCS() { | |
774 | #ifdef GTE_LOG | |
775 | GTE_LOG("GTE NCS\n"); | |
776 | #endif | |
777 | gteFLAG = 0; | |
778 | ||
779 | gteMAC1 = A1((((s64)gteL11 * gteVX0) + (gteL12 * gteVY0) + (gteL13 * gteVZ0)) >> 12); | |
780 | gteMAC2 = A2((((s64)gteL21 * gteVX0) + (gteL22 * gteVY0) + (gteL23 * gteVZ0)) >> 12); | |
781 | gteMAC3 = A3((((s64)gteL31 * gteVX0) + (gteL32 * gteVY0) + (gteL33 * gteVZ0)) >> 12); | |
782 | gteIR1 = limB1(gteMAC1, 1); | |
783 | gteIR2 = limB2(gteMAC2, 1); | |
784 | gteIR3 = limB3(gteMAC3, 1); | |
785 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
786 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
787 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
788 | gteIR1 = limB1(gteMAC1, 1); | |
789 | gteIR2 = limB2(gteMAC2, 1); | |
790 | gteIR3 = limB3(gteMAC3, 1); | |
791 | ||
792 | gteRGB0 = gteRGB1; | |
793 | gteRGB1 = gteRGB2; | |
794 | gteCODE2 = gteCODE; | |
795 | gteR2 = limC1(gteMAC1 >> 4); | |
796 | gteG2 = limC2(gteMAC2 >> 4); | |
797 | gteB2 = limC3(gteMAC3 >> 4); | |
798 | } | |
799 | ||
800 | void gteNCT() { | |
801 | int v; | |
802 | s32 vx, vy, vz; | |
803 | ||
804 | #ifdef GTE_LOG | |
805 | GTE_LOG("GTE NCT\n"); | |
806 | #endif | |
807 | gteFLAG = 0; | |
808 | ||
809 | for (v = 0; v < 3; v++) { | |
810 | vx = VX(v); | |
811 | vy = VY(v); | |
812 | vz = VZ(v); | |
813 | gteMAC1 = A1((((s64)gteL11 * vx) + (gteL12 * vy) + (gteL13 * vz)) >> 12); | |
814 | gteMAC2 = A2((((s64)gteL21 * vx) + (gteL22 * vy) + (gteL23 * vz)) >> 12); | |
815 | gteMAC3 = A3((((s64)gteL31 * vx) + (gteL32 * vy) + (gteL33 * vz)) >> 12); | |
816 | gteIR1 = limB1(gteMAC1, 1); | |
817 | gteIR2 = limB2(gteMAC2, 1); | |
818 | gteIR3 = limB3(gteMAC3, 1); | |
819 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
820 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
821 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
822 | gteRGB0 = gteRGB1; | |
823 | gteRGB1 = gteRGB2; | |
824 | gteCODE2 = gteCODE; | |
825 | gteR2 = limC1(gteMAC1 >> 4); | |
826 | gteG2 = limC2(gteMAC2 >> 4); | |
827 | gteB2 = limC3(gteMAC3 >> 4); | |
828 | } | |
829 | gteIR1 = limB1(gteMAC1, 1); | |
830 | gteIR2 = limB2(gteMAC2, 1); | |
831 | gteIR3 = limB3(gteMAC3, 1); | |
832 | } | |
833 | ||
834 | void gteCC() { | |
835 | #ifdef GTE_LOG | |
836 | GTE_LOG("GTE CC\n"); | |
837 | #endif | |
838 | gteFLAG = 0; | |
839 | ||
840 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
841 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
842 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
843 | gteIR1 = limB1(gteMAC1, 1); | |
844 | gteIR2 = limB2(gteMAC2, 1); | |
845 | gteIR3 = limB3(gteMAC3, 1); | |
846 | gteMAC1 = A1(((s64)gteR * gteIR1) >> 8); | |
847 | gteMAC2 = A2(((s64)gteG * gteIR2) >> 8); | |
848 | gteMAC3 = A3(((s64)gteB * gteIR3) >> 8); | |
849 | gteIR1 = limB1(gteMAC1, 1); | |
850 | gteIR2 = limB2(gteMAC2, 1); | |
851 | gteIR3 = limB3(gteMAC3, 1); | |
852 | ||
853 | gteRGB0 = gteRGB1; | |
854 | gteRGB1 = gteRGB2; | |
855 | gteCODE2 = gteCODE; | |
856 | gteR2 = limC1(gteMAC1 >> 4); | |
857 | gteG2 = limC2(gteMAC2 >> 4); | |
858 | gteB2 = limC3(gteMAC3 >> 4); | |
859 | } | |
860 | ||
861 | void gteINTPL() { | |
862 | int shift = 12 * GTE_SF(gteop); | |
863 | int lm = GTE_LM(gteop); | |
864 | ||
865 | #ifdef GTE_LOG | |
866 | GTE_LOG("GTE INTPL\n"); | |
867 | #endif | |
868 | gteFLAG = 0; | |
869 | ||
870 | gteMAC1 = A1(((gteIR1 << 12) + (gteIR0 * limB1(((s64)gteRFC - gteIR1), 0))) >> shift); | |
871 | gteMAC2 = A2(((gteIR2 << 12) + (gteIR0 * limB2(((s64)gteGFC - gteIR2), 0))) >> shift); | |
872 | gteMAC3 = A3(((gteIR3 << 12) + (gteIR0 * limB3(((s64)gteBFC - gteIR3), 0))) >> shift); | |
873 | gteIR1 = limB1(gteMAC1, lm); | |
874 | gteIR2 = limB2(gteMAC2, lm); | |
875 | gteIR3 = limB3(gteMAC3, lm); | |
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 | ||
884 | void gteCDP() { | |
885 | #ifdef GTE_LOG | |
886 | GTE_LOG("GTE CDP\n"); | |
887 | #endif | |
888 | gteFLAG = 0; | |
889 | ||
890 | gteMAC1 = A1((((s64)gteRBK << 12) + (gteLR1 * gteIR1) + (gteLR2 * gteIR2) + (gteLR3 * gteIR3)) >> 12); | |
891 | gteMAC2 = A2((((s64)gteGBK << 12) + (gteLG1 * gteIR1) + (gteLG2 * gteIR2) + (gteLG3 * gteIR3)) >> 12); | |
892 | gteMAC3 = A3((((s64)gteBBK << 12) + (gteLB1 * gteIR1) + (gteLB2 * gteIR2) + (gteLB3 * gteIR3)) >> 12); | |
893 | gteIR1 = limB1(gteMAC1, 1); | |
894 | gteIR2 = limB2(gteMAC2, 1); | |
895 | gteIR3 = limB3(gteMAC3, 1); | |
896 | gteMAC1 = A1(((((s64)gteR << 4) * gteIR1) + (gteIR0 * limB1(gteRFC - ((gteR * gteIR1) >> 8), 0))) >> 12); | |
897 | gteMAC2 = A2(((((s64)gteG << 4) * gteIR2) + (gteIR0 * limB2(gteGFC - ((gteG * gteIR2) >> 8), 0))) >> 12); | |
898 | gteMAC3 = A3(((((s64)gteB << 4) * gteIR3) + (gteIR0 * limB3(gteBFC - ((gteB * gteIR3) >> 8), 0))) >> 12); | |
899 | gteIR1 = limB1(gteMAC1, 1); | |
900 | gteIR2 = limB2(gteMAC2, 1); | |
901 | gteIR3 = limB3(gteMAC3, 1); | |
902 | ||
903 | gteRGB0 = gteRGB1; | |
904 | gteRGB1 = gteRGB2; | |
905 | gteCODE2 = gteCODE; | |
906 | gteR2 = limC1(gteMAC1 >> 4); | |
907 | gteG2 = limC2(gteMAC2 >> 4); | |
908 | gteB2 = limC3(gteMAC3 >> 4); | |
909 | } |