1/**************************************************************************
2 *
3 * Copyright 2010 Christian König
4 * All Rights Reserved.
5 *
6 * Permission is hereby granted, free of charge, to any person obtaining a
7 * copy of this software and associated documentation files (the
8 * "Software"), to deal in the Software without restriction, including
9 * without limitation the rights to use, copy, modify, merge, publish,
10 * distribute, sub license, and/or sell copies of the Software, and to
11 * permit persons to whom the Software is furnished to do so, subject to
12 * the following conditions:
13 *
14 * The above copyright notice and this permission notice (including the
15 * next paragraph) shall be included in all copies or substantial portions
16 * of the Software.
17 *
18 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
19 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
20 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
21 * IN NO EVENT SHALL VMWARE AND/OR ITS SUPPLIERS BE LIABLE FOR
22 * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
23 * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
24 * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
25 *
26 **************************************************************************/
27
28#include <assert.h>
29
30#include "pipe/p_context.h"
31#include "pipe/p_screen.h"
32
33#include "util/u_draw.h"
34#include "util/u_sampler.h"
35#include "util/u_memory.h"
36
37#include "tgsi/tgsi_ureg.h"
38
39#include "vl_defines.h"
40#include "vl_types.h"
41#include "vl_vertex_buffers.h"
42#include "vl_idct.h"
43
44enum VS_OUTPUT
45{
46   VS_O_VPOS = 0,
47   VS_O_L_ADDR0 = 0,
48   VS_O_L_ADDR1,
49   VS_O_R_ADDR0,
50   VS_O_R_ADDR1
51};
52
53/**
54 * The DCT matrix stored as hex representation of floats. Equal to the following equation:
55 * for (i = 0; i < 8; ++i)
56 *    for (j = 0; j < 8; ++j)
57 *       if (i == 0) const_matrix[i][j] = 1.0f / sqrtf(8.0f);
58 *       else const_matrix[i][j] = sqrtf(2.0f / 8.0f) * cosf((2 * j + 1) * i * M_PI / (2.0f * 8.0f));
59 */
60static const uint32_t const_matrix[8][8] = {
61   { 0x3eb504f3, 0x3eb504f3, 0x3eb504f3, 0x3eb504f3, 0x3eb504f3, 0x3eb504f3, 0x3eb504f3, 0x3eb504f3 },
62   { 0x3efb14be, 0x3ed4db31, 0x3e8e39da, 0x3dc7c5c4, 0xbdc7c5c2, 0xbe8e39d9, 0xbed4db32, 0xbefb14bf },
63   { 0x3eec835f, 0x3e43ef15, 0xbe43ef14, 0xbeec835e, 0xbeec835f, 0xbe43ef1a, 0x3e43ef1b, 0x3eec835f },
64   { 0x3ed4db31, 0xbdc7c5c2, 0xbefb14bf, 0xbe8e39dd, 0x3e8e39d7, 0x3efb14bf, 0x3dc7c5d0, 0xbed4db34 },
65   { 0x3eb504f3, 0xbeb504f3, 0xbeb504f4, 0x3eb504f1, 0x3eb504f3, 0xbeb504f0, 0xbeb504ef, 0x3eb504f4 },
66   { 0x3e8e39da, 0xbefb14bf, 0x3dc7c5c8, 0x3ed4db32, 0xbed4db34, 0xbdc7c5bb, 0x3efb14bf, 0xbe8e39d7 },
67   { 0x3e43ef15, 0xbeec835f, 0x3eec835f, 0xbe43ef07, 0xbe43ef23, 0x3eec8361, 0xbeec835c, 0x3e43ef25 },
68   { 0x3dc7c5c4, 0xbe8e39dd, 0x3ed4db32, 0xbefb14c0, 0x3efb14be, 0xbed4db31, 0x3e8e39ce, 0xbdc7c596 },
69};
70
71static void
72calc_addr(struct ureg_program *shader, struct ureg_dst addr[2],
73          struct ureg_src tc, struct ureg_src start, bool right_side,
74          bool transposed, float size)
75{
76   unsigned wm_start = (right_side == transposed) ? TGSI_WRITEMASK_X : TGSI_WRITEMASK_Y;
77   unsigned sw_start = right_side ? TGSI_SWIZZLE_Y : TGSI_SWIZZLE_X;
78
79   unsigned wm_tc = (right_side == transposed) ? TGSI_WRITEMASK_Y : TGSI_WRITEMASK_X;
80   unsigned sw_tc = right_side ? TGSI_SWIZZLE_X : TGSI_SWIZZLE_Y;
81
82   /*
83    * addr[0..1].(start) = right_side ? start.x : tc.x
84    * addr[0..1].(tc) = right_side ? tc.y : start.y
85    * addr[0..1].z = tc.z
86    * addr[1].(start) += 1.0f / scale
87    */
88   ureg_MOV(shader, ureg_writemask(addr[0], wm_start), ureg_scalar(start, sw_start));
89   ureg_MOV(shader, ureg_writemask(addr[0], wm_tc), ureg_scalar(tc, sw_tc));
90
91   ureg_ADD(shader, ureg_writemask(addr[1], wm_start), ureg_scalar(start, sw_start), ureg_imm1f(shader, 1.0f / size));
92   ureg_MOV(shader, ureg_writemask(addr[1], wm_tc), ureg_scalar(tc, sw_tc));
93}
94
95static void
96increment_addr(struct ureg_program *shader, struct ureg_dst daddr[2],
97               struct ureg_src saddr[2], bool right_side, bool transposed,
98               int pos, float size)
99{
100   unsigned wm_start = (right_side == transposed) ? TGSI_WRITEMASK_X : TGSI_WRITEMASK_Y;
101   unsigned wm_tc = (right_side == transposed) ? TGSI_WRITEMASK_Y : TGSI_WRITEMASK_X;
102
103   /*
104    * daddr[0..1].(start) = saddr[0..1].(start)
105    * daddr[0..1].(tc) = saddr[0..1].(tc)
106    */
107
108   ureg_MOV(shader, ureg_writemask(daddr[0], wm_start), saddr[0]);
109   ureg_ADD(shader, ureg_writemask(daddr[0], wm_tc), saddr[0], ureg_imm1f(shader, pos / size));
110   ureg_MOV(shader, ureg_writemask(daddr[1], wm_start), saddr[1]);
111   ureg_ADD(shader, ureg_writemask(daddr[1], wm_tc), saddr[1], ureg_imm1f(shader, pos / size));
112}
113
114static void
115fetch_four(struct ureg_program *shader, struct ureg_dst m[2], struct ureg_src addr[2],
116           struct ureg_src sampler, bool resource3d)
117{
118   ureg_TEX(shader, m[0], resource3d ? TGSI_TEXTURE_3D : TGSI_TEXTURE_2D, addr[0], sampler);
119   ureg_TEX(shader, m[1], resource3d ? TGSI_TEXTURE_3D : TGSI_TEXTURE_2D, addr[1], sampler);
120}
121
122static void
123matrix_mul(struct ureg_program *shader, struct ureg_dst dst, struct ureg_dst l[2], struct ureg_dst r[2])
124{
125   struct ureg_dst tmp;
126
127   tmp = ureg_DECL_temporary(shader);
128
129   /*
130    * tmp.xy = dot4(m[0][0..1], m[1][0..1])
131    * dst = tmp.x + tmp.y
132    */
133   ureg_DP4(shader, ureg_writemask(tmp, TGSI_WRITEMASK_X), ureg_src(l[0]), ureg_src(r[0]));
134   ureg_DP4(shader, ureg_writemask(tmp, TGSI_WRITEMASK_Y), ureg_src(l[1]), ureg_src(r[1]));
135   ureg_ADD(shader, dst,
136      ureg_scalar(ureg_src(tmp), TGSI_SWIZZLE_X),
137      ureg_scalar(ureg_src(tmp), TGSI_SWIZZLE_Y));
138
139   ureg_release_temporary(shader, tmp);
140}
141
142static void *
143create_mismatch_vert_shader(struct vl_idct *idct)
144{
145   struct ureg_program *shader;
146   struct ureg_src vpos;
147   struct ureg_src scale;
148   struct ureg_dst t_tex;
149   struct ureg_dst o_vpos, o_addr[2];
150
151   shader = ureg_create(PIPE_SHADER_VERTEX);
152   if (!shader)
153      return NULL;
154
155   vpos = ureg_DECL_vs_input(shader, VS_I_VPOS);
156
157   t_tex = ureg_DECL_temporary(shader);
158
159   o_vpos = ureg_DECL_output(shader, TGSI_SEMANTIC_POSITION, VS_O_VPOS);
160
161   o_addr[0] = ureg_DECL_output(shader, TGSI_SEMANTIC_GENERIC, VS_O_L_ADDR0);
162   o_addr[1] = ureg_DECL_output(shader, TGSI_SEMANTIC_GENERIC, VS_O_L_ADDR1);
163
164   /*
165    * scale = (VL_BLOCK_WIDTH, VL_BLOCK_HEIGHT) / (dst.width, dst.height)
166    *
167    * t_vpos = vpos + 7 / VL_BLOCK_WIDTH
168    * o_vpos.xy = t_vpos * scale
169    *
170    * o_addr = calc_addr(...)
171    *
172    */
173
174   scale = ureg_imm2f(shader,
175      (float)VL_BLOCK_WIDTH / idct->buffer_width,
176      (float)VL_BLOCK_HEIGHT / idct->buffer_height);
177
178   ureg_MAD(shader, ureg_writemask(o_vpos, TGSI_WRITEMASK_XY), vpos, scale, scale);
179   ureg_MOV(shader, ureg_writemask(o_vpos, TGSI_WRITEMASK_ZW), ureg_imm1f(shader, 1.0f));
180
181   ureg_MUL(shader, ureg_writemask(t_tex, TGSI_WRITEMASK_XY), vpos, scale);
182   calc_addr(shader, o_addr, ureg_src(t_tex), ureg_src(t_tex), false, false, idct->buffer_width / 4);
183
184   ureg_release_temporary(shader, t_tex);
185
186   ureg_END(shader);
187
188   return ureg_create_shader_and_destroy(shader, idct->pipe);
189}
190
191static void *
192create_mismatch_frag_shader(struct vl_idct *idct)
193{
194   struct ureg_program *shader;
195
196   struct ureg_src addr[2];
197
198   struct ureg_dst m[8][2];
199   struct ureg_dst fragment;
200
201   unsigned i;
202
203   shader = ureg_create(PIPE_SHADER_FRAGMENT);
204   if (!shader)
205      return NULL;
206
207   addr[0] = ureg_DECL_fs_input(shader, TGSI_SEMANTIC_GENERIC, VS_O_L_ADDR0, TGSI_INTERPOLATE_LINEAR);
208   addr[1] = ureg_DECL_fs_input(shader, TGSI_SEMANTIC_GENERIC, VS_O_L_ADDR1, TGSI_INTERPOLATE_LINEAR);
209
210   fragment = ureg_DECL_output(shader, TGSI_SEMANTIC_COLOR, 0);
211
212   for (i = 0; i < 8; ++i) {
213      m[i][0] = ureg_DECL_temporary(shader);
214      m[i][1] = ureg_DECL_temporary(shader);
215   }
216
217   for (i = 0; i < 8; ++i) {
218      increment_addr(shader, m[i], addr, false, false, i, idct->buffer_height);
219   }
220
221   for (i = 0; i < 8; ++i) {
222      struct ureg_src s_addr[2];
223      s_addr[0] = ureg_src(m[i][0]);
224      s_addr[1] = ureg_src(m[i][1]);
225      fetch_four(shader, m[i], s_addr, ureg_DECL_sampler(shader, 0), false);
226   }
227
228   for (i = 1; i < 8; ++i) {
229      ureg_ADD(shader, m[0][0], ureg_src(m[0][0]), ureg_src(m[i][0]));
230      ureg_ADD(shader, m[0][1], ureg_src(m[0][1]), ureg_src(m[i][1]));
231   }
232
233   ureg_ADD(shader, m[0][0], ureg_src(m[0][0]), ureg_src(m[0][1]));
234   ureg_DP4(shader, m[0][0], ureg_abs(ureg_src(m[0][0])), ureg_imm1f(shader, 1 << 14));
235
236   ureg_MUL(shader, ureg_writemask(m[0][0], TGSI_WRITEMASK_W), ureg_abs(ureg_src(m[7][1])), ureg_imm1f(shader, 1 << 14));
237   ureg_FRC(shader, m[0][0], ureg_src(m[0][0]));
238   ureg_SGT(shader, m[0][0], ureg_imm1f(shader, 0.5f), ureg_abs(ureg_src(m[0][0])));
239
240   ureg_CMP(shader, ureg_writemask(m[0][0], TGSI_WRITEMASK_W), ureg_negate(ureg_src(m[0][0])),
241            ureg_imm1f(shader, 1.0f / (1 << 15)), ureg_imm1f(shader, -1.0f / (1 << 15)));
242   ureg_MUL(shader, ureg_writemask(m[0][0], TGSI_WRITEMASK_W), ureg_src(m[0][0]),
243            ureg_scalar(ureg_src(m[0][0]), TGSI_SWIZZLE_X));
244
245   ureg_MOV(shader, ureg_writemask(fragment, TGSI_WRITEMASK_XYZ), ureg_src(m[7][1]));
246   ureg_ADD(shader, ureg_writemask(fragment, TGSI_WRITEMASK_W), ureg_src(m[0][0]), ureg_src(m[7][1]));
247
248   for (i = 0; i < 8; ++i) {
249      ureg_release_temporary(shader, m[i][0]);
250      ureg_release_temporary(shader, m[i][1]);
251   }
252
253   ureg_END(shader);
254
255   return ureg_create_shader_and_destroy(shader, idct->pipe);
256}
257
258static void *
259create_stage1_vert_shader(struct vl_idct *idct)
260{
261   struct ureg_program *shader;
262   struct ureg_src vrect, vpos;
263   struct ureg_src scale;
264   struct ureg_dst t_tex, t_start;
265   struct ureg_dst o_vpos, o_l_addr[2], o_r_addr[2];
266
267   shader = ureg_create(PIPE_SHADER_VERTEX);
268   if (!shader)
269      return NULL;
270
271   vrect = ureg_DECL_vs_input(shader, VS_I_RECT);
272   vpos = ureg_DECL_vs_input(shader, VS_I_VPOS);
273
274   t_tex = ureg_DECL_temporary(shader);
275   t_start = ureg_DECL_temporary(shader);
276
277   o_vpos = ureg_DECL_output(shader, TGSI_SEMANTIC_POSITION, VS_O_VPOS);
278
279   o_l_addr[0] = ureg_DECL_output(shader, TGSI_SEMANTIC_GENERIC, VS_O_L_ADDR0);
280   o_l_addr[1] = ureg_DECL_output(shader, TGSI_SEMANTIC_GENERIC, VS_O_L_ADDR1);
281
282   o_r_addr[0] = ureg_DECL_output(shader, TGSI_SEMANTIC_GENERIC, VS_O_R_ADDR0);
283   o_r_addr[1] = ureg_DECL_output(shader, TGSI_SEMANTIC_GENERIC, VS_O_R_ADDR1);
284
285   /*
286    * scale = (VL_BLOCK_WIDTH, VL_BLOCK_HEIGHT) / (dst.width, dst.height)
287    *
288    * t_vpos = vpos + vrect
289    * o_vpos.xy = t_vpos * scale
290    * o_vpos.zw = vpos
291    *
292    * o_l_addr = calc_addr(...)
293    * o_r_addr = calc_addr(...)
294    *
295    */
296
297   scale = ureg_imm2f(shader,
298      (float)VL_BLOCK_WIDTH / idct->buffer_width,
299      (float)VL_BLOCK_HEIGHT / idct->buffer_height);
300
301   ureg_ADD(shader, ureg_writemask(t_tex, TGSI_WRITEMASK_XY), vpos, vrect);
302   ureg_MUL(shader, ureg_writemask(t_tex, TGSI_WRITEMASK_XY), ureg_src(t_tex), scale);
303
304   ureg_MOV(shader, ureg_writemask(o_vpos, TGSI_WRITEMASK_XY), ureg_src(t_tex));
305   ureg_MOV(shader, ureg_writemask(o_vpos, TGSI_WRITEMASK_ZW), ureg_imm1f(shader, 1.0f));
306
307   ureg_MUL(shader, ureg_writemask(t_start, TGSI_WRITEMASK_XY), vpos, scale);
308
309   calc_addr(shader, o_l_addr, ureg_src(t_tex), ureg_src(t_start), false, false, idct->buffer_width / 4);
310   calc_addr(shader, o_r_addr, vrect, ureg_imm1f(shader, 0.0f), true, true, VL_BLOCK_WIDTH / 4);
311
312   ureg_release_temporary(shader, t_tex);
313   ureg_release_temporary(shader, t_start);
314
315   ureg_END(shader);
316
317   return ureg_create_shader_and_destroy(shader, idct->pipe);
318}
319
320static void *
321create_stage1_frag_shader(struct vl_idct *idct)
322{
323   struct ureg_program *shader;
324   struct ureg_src l_addr[2], r_addr[2];
325   struct ureg_dst l[4][2], r[2];
326   struct ureg_dst *fragment;
327   unsigned i;
328   int j;
329
330   shader = ureg_create(PIPE_SHADER_FRAGMENT);
331   if (!shader)
332      return NULL;
333
334   fragment = MALLOC(idct->nr_of_render_targets * sizeof(struct ureg_dst));
335
336   l_addr[0] = ureg_DECL_fs_input(shader, TGSI_SEMANTIC_GENERIC, VS_O_L_ADDR0, TGSI_INTERPOLATE_LINEAR);
337   l_addr[1] = ureg_DECL_fs_input(shader, TGSI_SEMANTIC_GENERIC, VS_O_L_ADDR1, TGSI_INTERPOLATE_LINEAR);
338
339   r_addr[0] = ureg_DECL_fs_input(shader, TGSI_SEMANTIC_GENERIC, VS_O_R_ADDR0, TGSI_INTERPOLATE_LINEAR);
340   r_addr[1] = ureg_DECL_fs_input(shader, TGSI_SEMANTIC_GENERIC, VS_O_R_ADDR1, TGSI_INTERPOLATE_LINEAR);
341
342   for (i = 0; i < idct->nr_of_render_targets; ++i)
343       fragment[i] = ureg_DECL_output(shader, TGSI_SEMANTIC_COLOR, i);
344
345   for (i = 0; i < 4; ++i) {
346      l[i][0] = ureg_DECL_temporary(shader);
347      l[i][1] = ureg_DECL_temporary(shader);
348   }
349
350   r[0] = ureg_DECL_temporary(shader);
351   r[1] = ureg_DECL_temporary(shader);
352
353   for (i = 0; i < 4; ++i) {
354      increment_addr(shader, l[i], l_addr, false, false, i - 2, idct->buffer_height);
355   }
356
357   for (i = 0; i < 4; ++i) {
358      struct ureg_src s_addr[2];
359      s_addr[0] = ureg_src(l[i][0]);
360      s_addr[1] = ureg_src(l[i][1]);
361      fetch_four(shader, l[i], s_addr, ureg_DECL_sampler(shader, 0), false);
362   }
363
364   for (i = 0; i < idct->nr_of_render_targets; ++i) {
365      struct ureg_src s_addr[2];
366
367      increment_addr(shader, r, r_addr, true, true, i - (signed)idct->nr_of_render_targets / 2, VL_BLOCK_HEIGHT);
368
369      s_addr[0] = ureg_src(r[0]);
370      s_addr[1] = ureg_src(r[1]);
371      fetch_four(shader, r, s_addr, ureg_DECL_sampler(shader, 1), false);
372
373      for (j = 0; j < 4; ++j) {
374         matrix_mul(shader, ureg_writemask(fragment[i], TGSI_WRITEMASK_X << j), l[j], r);
375      }
376   }
377
378   for (i = 0; i < 4; ++i) {
379      ureg_release_temporary(shader, l[i][0]);
380      ureg_release_temporary(shader, l[i][1]);
381   }
382   ureg_release_temporary(shader, r[0]);
383   ureg_release_temporary(shader, r[1]);
384
385   ureg_END(shader);
386
387   FREE(fragment);
388
389   return ureg_create_shader_and_destroy(shader, idct->pipe);
390}
391
392void
393vl_idct_stage2_vert_shader(struct vl_idct *idct, struct ureg_program *shader,
394                           unsigned first_output, struct ureg_dst tex)
395{
396   struct ureg_src vrect, vpos;
397   struct ureg_src scale;
398   struct ureg_dst t_start;
399   struct ureg_dst o_l_addr[2], o_r_addr[2];
400
401   vrect = ureg_DECL_vs_input(shader, VS_I_RECT);
402   vpos = ureg_DECL_vs_input(shader, VS_I_VPOS);
403
404   t_start = ureg_DECL_temporary(shader);
405
406   --first_output;
407
408   o_l_addr[0] = ureg_DECL_output(shader, TGSI_SEMANTIC_GENERIC, first_output + VS_O_L_ADDR0);
409   o_l_addr[1] = ureg_DECL_output(shader, TGSI_SEMANTIC_GENERIC, first_output + VS_O_L_ADDR1);
410
411   o_r_addr[0] = ureg_DECL_output(shader, TGSI_SEMANTIC_GENERIC, first_output + VS_O_R_ADDR0);
412   o_r_addr[1] = ureg_DECL_output(shader, TGSI_SEMANTIC_GENERIC, first_output + VS_O_R_ADDR1);
413
414   scale = ureg_imm2f(shader,
415      (float)VL_BLOCK_WIDTH / idct->buffer_width,
416      (float)VL_BLOCK_HEIGHT / idct->buffer_height);
417
418   ureg_MUL(shader, ureg_writemask(tex, TGSI_WRITEMASK_Z),
419      ureg_scalar(vrect, TGSI_SWIZZLE_X),
420      ureg_imm1f(shader, VL_BLOCK_WIDTH / idct->nr_of_render_targets));
421   ureg_MUL(shader, ureg_writemask(t_start, TGSI_WRITEMASK_XY), vpos, scale);
422
423   calc_addr(shader, o_l_addr, vrect, ureg_imm1f(shader, 0.0f), false, false, VL_BLOCK_WIDTH / 4);
424   calc_addr(shader, o_r_addr, ureg_src(tex), ureg_src(t_start), true, false, idct->buffer_height / 4);
425
426   ureg_MOV(shader, ureg_writemask(o_r_addr[0], TGSI_WRITEMASK_Z), ureg_src(tex));
427   ureg_MOV(shader, ureg_writemask(o_r_addr[1], TGSI_WRITEMASK_Z), ureg_src(tex));
428}
429
430void
431vl_idct_stage2_frag_shader(struct vl_idct *idct, struct ureg_program *shader,
432                           unsigned first_input, struct ureg_dst fragment)
433{
434   struct ureg_src l_addr[2], r_addr[2];
435
436   struct ureg_dst l[2], r[2];
437
438   --first_input;
439
440   l_addr[0] = ureg_DECL_fs_input(shader, TGSI_SEMANTIC_GENERIC, first_input + VS_O_L_ADDR0, TGSI_INTERPOLATE_LINEAR);
441   l_addr[1] = ureg_DECL_fs_input(shader, TGSI_SEMANTIC_GENERIC, first_input + VS_O_L_ADDR1, TGSI_INTERPOLATE_LINEAR);
442
443   r_addr[0] = ureg_DECL_fs_input(shader, TGSI_SEMANTIC_GENERIC, first_input + VS_O_R_ADDR0, TGSI_INTERPOLATE_LINEAR);
444   r_addr[1] = ureg_DECL_fs_input(shader, TGSI_SEMANTIC_GENERIC, first_input + VS_O_R_ADDR1, TGSI_INTERPOLATE_LINEAR);
445
446   l[0] = ureg_DECL_temporary(shader);
447   l[1] = ureg_DECL_temporary(shader);
448   r[0] = ureg_DECL_temporary(shader);
449   r[1] = ureg_DECL_temporary(shader);
450
451   fetch_four(shader, l, l_addr, ureg_DECL_sampler(shader, 1), false);
452   fetch_four(shader, r, r_addr, ureg_DECL_sampler(shader, 0), true);
453
454   matrix_mul(shader, fragment, l, r);
455
456   ureg_release_temporary(shader, l[0]);
457   ureg_release_temporary(shader, l[1]);
458   ureg_release_temporary(shader, r[0]);
459   ureg_release_temporary(shader, r[1]);
460}
461
462static bool
463init_shaders(struct vl_idct *idct)
464{
465   idct->vs_mismatch = create_mismatch_vert_shader(idct);
466   if (!idct->vs_mismatch)
467      goto error_vs_mismatch;
468
469   idct->fs_mismatch = create_mismatch_frag_shader(idct);
470   if (!idct->fs_mismatch)
471      goto error_fs_mismatch;
472
473   idct->vs = create_stage1_vert_shader(idct);
474   if (!idct->vs)
475      goto error_vs;
476
477   idct->fs = create_stage1_frag_shader(idct);
478   if (!idct->fs)
479      goto error_fs;
480
481   return true;
482
483error_fs:
484   idct->pipe->delete_vs_state(idct->pipe, idct->vs);
485
486error_vs:
487   idct->pipe->delete_vs_state(idct->pipe, idct->vs_mismatch);
488
489error_fs_mismatch:
490   idct->pipe->delete_vs_state(idct->pipe, idct->fs);
491
492error_vs_mismatch:
493   return false;
494}
495
496static void
497cleanup_shaders(struct vl_idct *idct)
498{
499   idct->pipe->delete_vs_state(idct->pipe, idct->vs_mismatch);
500   idct->pipe->delete_fs_state(idct->pipe, idct->fs_mismatch);
501   idct->pipe->delete_vs_state(idct->pipe, idct->vs);
502   idct->pipe->delete_fs_state(idct->pipe, idct->fs);
503}
504
505static bool
506init_state(struct vl_idct *idct)
507{
508   struct pipe_blend_state blend;
509   struct pipe_rasterizer_state rs_state;
510   struct pipe_sampler_state sampler;
511   unsigned i;
512
513   assert(idct);
514
515   memset(&rs_state, 0, sizeof(rs_state));
516   rs_state.point_size = 1;
517   rs_state.half_pixel_center = true;
518   rs_state.bottom_edge_rule = true;
519   rs_state.depth_clip_near = 1;
520   rs_state.depth_clip_far = 1;
521
522   idct->rs_state = idct->pipe->create_rasterizer_state(idct->pipe, &rs_state);
523   if (!idct->rs_state)
524      goto error_rs_state;
525
526   memset(&blend, 0, sizeof blend);
527
528   blend.independent_blend_enable = 0;
529   blend.rt[0].blend_enable = 0;
530   blend.rt[0].rgb_func = PIPE_BLEND_ADD;
531   blend.rt[0].rgb_src_factor = PIPE_BLENDFACTOR_ONE;
532   blend.rt[0].rgb_dst_factor = PIPE_BLENDFACTOR_ONE;
533   blend.rt[0].alpha_func = PIPE_BLEND_ADD;
534   blend.rt[0].alpha_src_factor = PIPE_BLENDFACTOR_ONE;
535   blend.rt[0].alpha_dst_factor = PIPE_BLENDFACTOR_ONE;
536   blend.logicop_enable = 0;
537   blend.logicop_func = PIPE_LOGICOP_CLEAR;
538   /* Needed to allow color writes to FB, even if blending disabled */
539   blend.rt[0].colormask = PIPE_MASK_RGBA;
540   blend.dither = 0;
541   idct->blend = idct->pipe->create_blend_state(idct->pipe, &blend);
542   if (!idct->blend)
543      goto error_blend;
544
545   for (i = 0; i < 2; ++i) {
546      memset(&sampler, 0, sizeof(sampler));
547      sampler.wrap_s = PIPE_TEX_WRAP_REPEAT;
548      sampler.wrap_t = PIPE_TEX_WRAP_REPEAT;
549      sampler.wrap_r = PIPE_TEX_WRAP_REPEAT;
550      sampler.min_img_filter = PIPE_TEX_FILTER_NEAREST;
551      sampler.min_mip_filter = PIPE_TEX_MIPFILTER_NONE;
552      sampler.mag_img_filter = PIPE_TEX_FILTER_NEAREST;
553      sampler.compare_mode = PIPE_TEX_COMPARE_NONE;
554      sampler.compare_func = PIPE_FUNC_ALWAYS;
555      sampler.normalized_coords = 1;
556      idct->samplers[i] = idct->pipe->create_sampler_state(idct->pipe, &sampler);
557      if (!idct->samplers[i])
558         goto error_samplers;
559   }
560
561   return true;
562
563error_samplers:
564   for (i = 0; i < 2; ++i)
565      if (idct->samplers[i])
566         idct->pipe->delete_sampler_state(idct->pipe, idct->samplers[i]);
567
568   idct->pipe->delete_rasterizer_state(idct->pipe, idct->rs_state);
569
570error_blend:
571   idct->pipe->delete_blend_state(idct->pipe, idct->blend);
572
573error_rs_state:
574   return false;
575}
576
577static void
578cleanup_state(struct vl_idct *idct)
579{
580   unsigned i;
581
582   for (i = 0; i < 2; ++i)
583      idct->pipe->delete_sampler_state(idct->pipe, idct->samplers[i]);
584
585   idct->pipe->delete_rasterizer_state(idct->pipe, idct->rs_state);
586   idct->pipe->delete_blend_state(idct->pipe, idct->blend);
587}
588
589static bool
590init_source(struct vl_idct *idct, struct vl_idct_buffer *buffer)
591{
592   struct pipe_resource *tex;
593   struct pipe_surface surf_templ;
594
595   assert(idct && buffer);
596
597   tex = buffer->sampler_views.individual.source->texture;
598
599   buffer->fb_state_mismatch.width = tex->width0;
600   buffer->fb_state_mismatch.height = tex->height0;
601   buffer->fb_state_mismatch.nr_cbufs = 1;
602
603   memset(&surf_templ, 0, sizeof(surf_templ));
604   surf_templ.format = tex->format;
605   surf_templ.u.tex.first_layer = 0;
606   surf_templ.u.tex.last_layer = 0;
607   buffer->fb_state_mismatch.cbufs[0] = idct->pipe->create_surface(idct->pipe, tex, &surf_templ);
608
609   buffer->viewport_mismatch.scale[0] = tex->width0;
610   buffer->viewport_mismatch.scale[1] = tex->height0;
611   buffer->viewport_mismatch.scale[2] = 1;
612   buffer->viewport_mismatch.swizzle_x = PIPE_VIEWPORT_SWIZZLE_POSITIVE_X;
613   buffer->viewport_mismatch.swizzle_y = PIPE_VIEWPORT_SWIZZLE_POSITIVE_Y;
614   buffer->viewport_mismatch.swizzle_z = PIPE_VIEWPORT_SWIZZLE_POSITIVE_Z;
615   buffer->viewport_mismatch.swizzle_w = PIPE_VIEWPORT_SWIZZLE_POSITIVE_W;
616
617   return true;
618}
619
620static void
621cleanup_source(struct vl_idct_buffer *buffer)
622{
623   assert(buffer);
624
625   pipe_surface_reference(&buffer->fb_state_mismatch.cbufs[0], NULL);
626
627   pipe_sampler_view_reference(&buffer->sampler_views.individual.source, NULL);
628}
629
630static bool
631init_intermediate(struct vl_idct *idct, struct vl_idct_buffer *buffer)
632{
633   struct pipe_resource *tex;
634   struct pipe_surface surf_templ;
635   unsigned i;
636
637   assert(idct && buffer);
638
639   tex = buffer->sampler_views.individual.intermediate->texture;
640
641   buffer->fb_state.width = tex->width0;
642   buffer->fb_state.height = tex->height0;
643   buffer->fb_state.nr_cbufs = idct->nr_of_render_targets;
644   for(i = 0; i < idct->nr_of_render_targets; ++i) {
645      memset(&surf_templ, 0, sizeof(surf_templ));
646      surf_templ.format = tex->format;
647      surf_templ.u.tex.first_layer = i;
648      surf_templ.u.tex.last_layer = i;
649      buffer->fb_state.cbufs[i] = idct->pipe->create_surface(
650         idct->pipe, tex, &surf_templ);
651
652      if (!buffer->fb_state.cbufs[i])
653         goto error_surfaces;
654   }
655
656   buffer->viewport.scale[0] = tex->width0;
657   buffer->viewport.scale[1] = tex->height0;
658   buffer->viewport.scale[2] = 1;
659   buffer->viewport.swizzle_x = PIPE_VIEWPORT_SWIZZLE_POSITIVE_X;
660   buffer->viewport.swizzle_y = PIPE_VIEWPORT_SWIZZLE_POSITIVE_Y;
661   buffer->viewport.swizzle_z = PIPE_VIEWPORT_SWIZZLE_POSITIVE_Z;
662   buffer->viewport.swizzle_w = PIPE_VIEWPORT_SWIZZLE_POSITIVE_W;
663
664   return true;
665
666error_surfaces:
667   for(i = 0; i < idct->nr_of_render_targets; ++i)
668      pipe_surface_reference(&buffer->fb_state.cbufs[i], NULL);
669
670   return false;
671}
672
673static void
674cleanup_intermediate(struct vl_idct_buffer *buffer)
675{
676   unsigned i;
677
678   assert(buffer);
679
680   for(i = 0; i < PIPE_MAX_COLOR_BUFS; ++i)
681      pipe_surface_reference(&buffer->fb_state.cbufs[i], NULL);
682
683   pipe_sampler_view_reference(&buffer->sampler_views.individual.intermediate, NULL);
684}
685
686struct pipe_sampler_view *
687vl_idct_upload_matrix(struct pipe_context *pipe, float scale)
688{
689   struct pipe_resource tex_templ, *matrix;
690   struct pipe_sampler_view sv_templ, *sv;
691   struct pipe_transfer *buf_transfer;
692   unsigned i, j, pitch;
693   float *f;
694
695   struct pipe_box rect =
696   {
697      0, 0, 0,
698      VL_BLOCK_WIDTH / 4,
699      VL_BLOCK_HEIGHT,
700      1
701   };
702
703   assert(pipe);
704
705   memset(&tex_templ, 0, sizeof(tex_templ));
706   tex_templ.target = PIPE_TEXTURE_2D;
707   tex_templ.format = PIPE_FORMAT_R32G32B32A32_FLOAT;
708   tex_templ.last_level = 0;
709   tex_templ.width0 = 2;
710   tex_templ.height0 = 8;
711   tex_templ.depth0 = 1;
712   tex_templ.array_size = 1;
713   tex_templ.usage = PIPE_USAGE_IMMUTABLE;
714   tex_templ.bind = PIPE_BIND_SAMPLER_VIEW;
715   tex_templ.flags = 0;
716
717   matrix = pipe->screen->resource_create(pipe->screen, &tex_templ);
718   if (!matrix)
719      goto error_matrix;
720
721   f = pipe->texture_map(pipe, matrix, 0,
722                                     PIPE_MAP_WRITE |
723                                     PIPE_MAP_DISCARD_RANGE,
724                                     &rect, &buf_transfer);
725   if (!f)
726      goto error_map;
727
728   pitch = buf_transfer->stride / sizeof(float);
729
730   for(i = 0; i < VL_BLOCK_HEIGHT; ++i)
731      for(j = 0; j < VL_BLOCK_WIDTH; ++j)
732         // transpose and scale
733         f[i * pitch + j] = ((const float (*)[8])const_matrix)[j][i] * scale;
734
735   pipe->texture_unmap(pipe, buf_transfer);
736
737   memset(&sv_templ, 0, sizeof(sv_templ));
738   u_sampler_view_default_template(&sv_templ, matrix, matrix->format);
739   sv = pipe->create_sampler_view(pipe, matrix, &sv_templ);
740   pipe_resource_reference(&matrix, NULL);
741   if (!sv)
742      goto error_map;
743
744   return sv;
745
746error_map:
747   pipe_resource_reference(&matrix, NULL);
748
749error_matrix:
750   return NULL;
751}
752
753bool vl_idct_init(struct vl_idct *idct, struct pipe_context *pipe,
754                  unsigned buffer_width, unsigned buffer_height,
755                  unsigned nr_of_render_targets,
756                  struct pipe_sampler_view *matrix,
757                  struct pipe_sampler_view *transpose)
758{
759   assert(idct && pipe);
760   assert(matrix && transpose);
761
762   idct->pipe = pipe;
763   idct->buffer_width = buffer_width;
764   idct->buffer_height = buffer_height;
765   idct->nr_of_render_targets = nr_of_render_targets;
766
767   pipe_sampler_view_reference(&idct->matrix, matrix);
768   pipe_sampler_view_reference(&idct->transpose, transpose);
769
770   if(!init_shaders(idct))
771      return false;
772
773   if(!init_state(idct)) {
774      cleanup_shaders(idct);
775      return false;
776   }
777
778   return true;
779}
780
781void
782vl_idct_cleanup(struct vl_idct *idct)
783{
784   cleanup_shaders(idct);
785   cleanup_state(idct);
786
787   pipe_sampler_view_reference(&idct->matrix, NULL);
788   pipe_sampler_view_reference(&idct->transpose, NULL);
789}
790
791bool
792vl_idct_init_buffer(struct vl_idct *idct, struct vl_idct_buffer *buffer,
793                    struct pipe_sampler_view *source,
794                    struct pipe_sampler_view *intermediate)
795{
796   assert(buffer && idct);
797   assert(source && intermediate);
798
799   memset(buffer, 0, sizeof(struct vl_idct_buffer));
800
801   pipe_sampler_view_reference(&buffer->sampler_views.individual.matrix, idct->matrix);
802   pipe_sampler_view_reference(&buffer->sampler_views.individual.source, source);
803   pipe_sampler_view_reference(&buffer->sampler_views.individual.transpose, idct->transpose);
804   pipe_sampler_view_reference(&buffer->sampler_views.individual.intermediate, intermediate);
805
806   if (!init_source(idct, buffer))
807      return false;
808
809   if (!init_intermediate(idct, buffer))
810      return false;
811
812   return true;
813}
814
815void
816vl_idct_cleanup_buffer(struct vl_idct_buffer *buffer)
817{
818   assert(buffer);
819
820   cleanup_source(buffer);
821   cleanup_intermediate(buffer);
822
823   pipe_sampler_view_reference(&buffer->sampler_views.individual.matrix, NULL);
824   pipe_sampler_view_reference(&buffer->sampler_views.individual.transpose, NULL);
825}
826
827void
828vl_idct_flush(struct vl_idct *idct, struct vl_idct_buffer *buffer, unsigned num_instances)
829{
830   assert(buffer);
831
832   idct->pipe->bind_rasterizer_state(idct->pipe, idct->rs_state);
833   idct->pipe->bind_blend_state(idct->pipe, idct->blend);
834
835   idct->pipe->bind_sampler_states(idct->pipe, PIPE_SHADER_FRAGMENT,
836                                   0, 2, idct->samplers);
837
838   idct->pipe->set_sampler_views(idct->pipe, PIPE_SHADER_FRAGMENT, 0, 2, 0,
839                                 false, buffer->sampler_views.stage[0]);
840
841   /* mismatch control */
842   idct->pipe->set_framebuffer_state(idct->pipe, &buffer->fb_state_mismatch);
843   idct->pipe->set_viewport_states(idct->pipe, 0, 1, &buffer->viewport_mismatch);
844   idct->pipe->bind_vs_state(idct->pipe, idct->vs_mismatch);
845   idct->pipe->bind_fs_state(idct->pipe, idct->fs_mismatch);
846   util_draw_arrays_instanced(idct->pipe, PIPE_PRIM_POINTS, 0, 1, 0, num_instances);
847
848   /* first stage */
849   idct->pipe->set_framebuffer_state(idct->pipe, &buffer->fb_state);
850   idct->pipe->set_viewport_states(idct->pipe, 0, 1, &buffer->viewport);
851   idct->pipe->bind_vs_state(idct->pipe, idct->vs);
852   idct->pipe->bind_fs_state(idct->pipe, idct->fs);
853   util_draw_arrays_instanced(idct->pipe, PIPE_PRIM_QUADS, 0, 4, 0, num_instances);
854}
855
856void
857vl_idct_prepare_stage2(struct vl_idct *idct, struct vl_idct_buffer *buffer)
858{
859   assert(buffer);
860
861   /* second stage */
862   idct->pipe->bind_rasterizer_state(idct->pipe, idct->rs_state);
863   idct->pipe->bind_sampler_states(idct->pipe, PIPE_SHADER_FRAGMENT,
864                                   0, 2, idct->samplers);
865   idct->pipe->set_sampler_views(idct->pipe, PIPE_SHADER_FRAGMENT,
866                                 0, 2, 0, false, buffer->sampler_views.stage[1]);
867}
868
869