From 0639765b2850739af1678f10fc0c5706d5827776 Mon Sep 17 00:00:00 2001 From: Brian Paul Date: Fri, 16 Apr 2010 09:10:54 -0600 Subject: Merge the lp-surface-tiling branch into master. This branch implemented dual representations of texture/drawing surfaces: one in the conventional linear layout and the other the tiled layout which is used by the fragment shader pipe. Per-tile flags indicate the layout of each image tile. In many situations this lets us avoid converting image data between the two layouts. Squashed commit of the following: commit 563a7e3cc552fdcfcaf9ac0d4b1683c3ba2ae732 Author: Brian Paul Date: Thu Apr 8 14:48:21 2010 -0600 llvmpipe: convert points/lines to triangles with draw module This isn't the most efficient way to render points/lines but it allows us to run more tests. commit a8aa763e8a717533f2b13bb6ea53cbccbede68c9 Author: Brian Paul Date: Thu Apr 8 14:47:28 2010 -0600 llvmpipe: call llvmpipe_get_texture_tile() for depth/stencil The returned pointer isn't used, but the tile status/layout info gets updated. Helps to fix glReadPixels(DEPTH / STENCIL). commit 463bc64af266194acbea71cd52e26a79b8c8a260 Author: Brian Paul Date: Thu Apr 8 10:58:48 2010 -0600 llvmpipe: add store_color to debug cmd_names list commit 784cc73fb334a9d7b7c93cbd8a1445cdf742ff58 Author: Brian Paul Date: Thu Apr 8 10:57:43 2010 -0600 llvmpipe: fix debug build commit 792c93171ec075664f55720ffed397ac2834a4fc Author: Brian Paul Date: Thu Apr 8 10:49:01 2010 -0600 llvmpipe: fix cube mapping commit 882b1035db88c3dd8aebe28dc971ac30a9ee39e3 Author: Brian Paul Date: Thu Apr 8 09:53:30 2010 -0600 llvmpipe: remove some older/unused code commit b807d32b23145301e8842824664d9f06b9c5502e Author: Brian Paul Date: Thu Apr 8 09:29:50 2010 -0600 llvmpipe: silence warning commit 7b337e64fec92836ccdf9d96216289dd58418e35 Author: Brian Paul Date: Wed Apr 7 17:06:08 2010 -0600 llvmpipe: clean-up, comments in lp_surface_copy() commit c52fa36f249cc652fa8d5fdd94d6574127c08c41 Author: Brian Paul Date: Wed Apr 7 16:51:42 2010 -0600 llvmpipe: overhaul tiled/linear memory management Now we keep per-tile layout info (linear vs. tiled (or neither or both) and convert from one layout to the other on demand. commit 4a50ccfd470547c9be0704005818a87014e9c0e9 Author: Brian Paul Date: Wed Apr 7 16:51:27 2010 -0600 llvmpipe: added tile read/write counters commit b7d0ea9c687ac8773b083791623826fa604adf21 Author: Brian Paul Date: Mon Apr 5 14:54:04 2010 -0600 llvmpipe: rename some functions commit ee45c6e5b95cbd3c8cccc9aa4d45d8aef11e20c4 Author: Brian Paul Date: Mon Apr 5 14:42:15 2010 -0600 llvmpipe: re-org some get block/tile pointer code commit 26ce97c16c0b6520ff1538803baa772d8c3b1280 Author: Brian Paul Date: Mon Apr 5 14:34:13 2010 -0600 llvmpipe: disable bad assertions commit 5c670481248c4d46f87f13bf3af5655925e7002d Author: Brian Paul Date: Fri Apr 2 16:36:11 2010 -0600 llvmpipe: add a special-case optimization to lp_surface_copy() Be more efficient when copying tiled image to linear image. Before, the fallback path was always converting the whole source image to linear. Now we can convert just a sub region. commit faa684645e64d6024b3a11e4e08da825e8220b2e Author: Brian Paul Date: Fri Apr 2 16:15:16 2010 -0600 llvmpipe: assorted texture and tile/line conversion code change s The tiled/linear conversion functions take x/y positions now to allow converting only sub-regions. More texture-related helper functions. commit baad81ec5318d44bfac1e37c7643afc0836607bb Author: Brian Paul Date: Tue Mar 30 13:18:40 2010 -0600 llvmpipe: convert tiled->linear upon PIPE_FLUSH_SWAPBUFFERS If we know we're about to do a swapbuffers we should immediately convert the tiled color tiles to linear instead of later in llvmpipe_texture_unmap() since we can take advantage of threading/ parallelism here. commit 928dd41256811daeddb7506a49a34dbad04beaf8 Author: Brian Paul Date: Tue Mar 30 09:16:58 2010 -0600 llvmpipe: polish-up the llvmpipe_flush() code commit dd6014abcf86c517d159b8175e0eaeb167ea2ef6 Author: Brian Paul Date: Tue Mar 30 09:15:17 2010 -0600 llvmpipe: SETUP_x enum clean-up commit 0b1ce6da2b28a41f3389685ab93e10b43c950f5d Author: Brian Paul Date: Fri Mar 26 10:43:37 2010 -0600 llvmpipe: remove unused vars commit 4562663480f88162ed4452cb05569eecb67f9f39 Author: Brian Paul Date: Fri Mar 26 10:31:55 2010 -0600 llvmpipe: cope with non-existant color/depth buffers The fragment jit functions always grab these pointers, even if they're not used. commit df4329edbaf204ed501f1eac0698b8198178f9af Author: Brian Paul Date: Thu Mar 25 15:20:15 2010 -0600 llvmpipe: do all render target surface mapping/unmapping in the rast code commit 3d0c25d5ba8b8f61e8366d4c97324e45d526ff41 Author: Brian Paul Date: Thu Mar 25 14:31:21 2010 -0600 llvmpipe: map z/stencil buffer on demand like color buffers Plus lots of code clean-up and loose ends taken care of. commit c3b6fddd788aef09b4b84b843b7b1272231151e8 Author: Brian Paul Date: Thu Mar 25 13:15:03 2010 -0600 llvmpipe: remove unused write_zstencil field commit 63374d97836926a6357e9d6dd24a509a8e155c56 Author: Brian Paul Date: Thu Mar 25 09:45:59 2010 -0600 llvmpipe: add missing lp_rast_end() call Fixes crash on window resize when LP_NUM_THREADS=0. commit 92fe9952161cc06f6edc58778e9e5a8b9ea447dc Author: Brian Paul Date: Wed Mar 24 10:15:19 2010 -0600 llvmpipe: add tiled/linear conversion for 16-bit Z images commit 6605fa28c147f30df351da0e4413cab33e4db5da Author: Brian Paul Date: Tue Mar 23 16:06:41 2010 -0600 llvmpipe: implement tiled/linear conversion for Z/stencil images commit 804528d84ffa292ef9d49d3666cdd3fa099ff3ff Author: Brian Paul Date: Tue Mar 23 16:05:45 2010 -0600 llvmpipe: added texture stride comment commit 66a88c012edf670c4ac887a912f02dcff93266dd Author: Brian Paul Date: Tue Mar 23 16:04:07 2010 -0600 llvmpipe: remove unused vars commit e2ca8d1328316dc8b36d5f688c16d109e49a6870 Author: Brian Paul Date: Mon Mar 22 18:53:11 2010 -0600 llvmpipe: checkpoint WIP: overhaul texture/surface mapping Conversion between tiled and linear surfaces is working everywhere now. The LP_TEXTURE_READ/READ_WRITE/WRITE_ALL flags let us avoid unnecessary image layout conversions. Still some loose ends, temporary/debug code, etc. Need to implement tiled/linear conversion for depth/stencil images. commit f2730a03839ee8984c1f537b7cbebba24961397a Author: Brian Paul Date: Mon Mar 22 14:41:58 2010 -0600 llvmpipe: rename/repurpose lp_rast_store_color() commit e192a47552c5d20d2caef452ca7697e2cd852c9b Author: Brian Paul Date: Mon Mar 22 14:38:51 2010 -0600 llvmpipe: remove lp_rast_load_color() commit 3cff0bde4b4ab980e1c3e812700419091527c76b Author: Brian Paul Date: Mon Mar 22 14:11:38 2010 -0600 llvmpipe: remove/consolidate texture image code commit 3a2f08b6a550c69ef5e874f482be30252cbf8bfa Author: Brian Paul Date: Fri Mar 19 17:03:14 2010 -0600 llvmpipe: checkpoint WIP: directly render to tiled texture buffers We're now directly writing colors into the tiled texture image buffers. This is a checkpoint commit with lots of dead code and temporary hacks. Everything will get cleaned up eventually. commit c5ca987e03870849514d4e3c99af143722a09695 Author: Brian Paul Date: Fri Mar 19 16:41:14 2010 -0600 llvmpipe: refactor code, create tile_pixel_offset() commit 2133e8273e937cbac09cd7264d6ce53af9764ddb Author: Brian Paul Date: Fri Mar 19 14:55:11 2010 -0600 llvmpipe: pass LP_TEXTURE_LINEAR/TILED flags around commit b9b9d4b82b01f4588721fdc8444740f859b4a021 Author: Brian Paul Date: Fri Mar 19 14:51:05 2010 -0600 llvmpipe: checkpoint WIP: hanlde co-existing tiled/linear texture data Cube maps are temporarily broken, maybe other things. commit 4cd322e6889940b5f155fcb69041b685b9ef9273 Author: Brian Paul Date: Fri Mar 19 11:34:43 2010 -0600 progs/demos: add other modes/patterns to dissolve demo --- src/gallium/drivers/llvmpipe/lp_rast.c | 322 +++++++++++++++++++++------------ 1 file changed, 209 insertions(+), 113 deletions(-) (limited to 'src/gallium/drivers/llvmpipe/lp_rast.c') diff --git a/src/gallium/drivers/llvmpipe/lp_rast.c b/src/gallium/drivers/llvmpipe/lp_rast.c index fccc63c28f..4574f41145 100644 --- a/src/gallium/drivers/llvmpipe/lp_rast.c +++ b/src/gallium/drivers/llvmpipe/lp_rast.c @@ -42,15 +42,15 @@ #include "lp_scene.h" -/* Begin rasterizing a scene: +/** + * Begin rasterizing a scene. + * Called once per scene by one thread. */ -static boolean +static void lp_rast_begin( struct lp_rasterizer *rast, struct lp_scene *scene ) { const struct pipe_framebuffer_state *fb = &scene->fb; - boolean write_color = fb->nr_cbufs != 0; - boolean write_zstencil = fb->zsbuf != NULL; int i; rast->curr_scene = scene; @@ -58,59 +58,147 @@ lp_rast_begin( struct lp_rasterizer *rast, LP_DBG(DEBUG_RAST, "%s\n", __FUNCTION__); rast->state.nr_cbufs = scene->fb.nr_cbufs; - rast->state.write_zstencil = write_zstencil; - rast->state.write_color = write_color; for (i = 0; i < rast->state.nr_cbufs; i++) { struct pipe_surface *cbuf = scene->fb.cbufs[i]; - rast->cbuf[i].map = scene->cbuf_map[i]; rast->cbuf[i].format = cbuf->texture->format; - rast->cbuf[i].width = cbuf->width; - rast->cbuf[i].height = cbuf->height; - rast->cbuf[i].stride = llvmpipe_resource_stride(cbuf->texture, cbuf->level); + rast->cbuf[i].tiles_per_row = align(cbuf->width, TILE_SIZE) / TILE_SIZE; + rast->cbuf[i].blocksize = + util_format_get_blocksize(cbuf->texture->format); + rast->cbuf[i].map = llvmpipe_resource_map(cbuf->texture, + cbuf->face, + cbuf->level, + cbuf->zslice, + LP_TEX_USAGE_READ_WRITE, + LP_TEX_LAYOUT_NONE); } - if (write_zstencil) { + if (fb->zsbuf) { struct pipe_surface *zsbuf = scene->fb.zsbuf; - rast->zsbuf.map = scene->zsbuf_map; rast->zsbuf.stride = llvmpipe_resource_stride(zsbuf->texture, zsbuf->level); rast->zsbuf.blocksize = util_format_get_blocksize(zsbuf->texture->format); + + rast->zsbuf.map = llvmpipe_resource_map(zsbuf->texture, + zsbuf->face, + zsbuf->level, + zsbuf->zslice, + LP_TEX_USAGE_READ_WRITE, + LP_TEX_LAYOUT_NONE); + assert(rast->zsbuf.map); } lp_scene_bin_iter_begin( scene ); - - return TRUE; } static void lp_rast_end( struct lp_rasterizer *rast ) { - int i; - - lp_scene_reset( rast->curr_scene ); + struct lp_scene *scene = rast->curr_scene; + unsigned i; - for (i = 0; i < rast->state.nr_cbufs; i++) + /* Unmap color buffers */ + for (i = 0; i < rast->state.nr_cbufs; i++) { + struct pipe_surface *cbuf = scene->fb.cbufs[i]; + llvmpipe_resource_unmap(cbuf->texture, + cbuf->face, + cbuf->level, + cbuf->zslice); rast->cbuf[i].map = NULL; + } + + /* Unmap z/stencil buffer */ + if (rast->zsbuf.map) { + struct pipe_surface *zsbuf = scene->fb.zsbuf; + llvmpipe_resource_unmap(zsbuf->texture, + zsbuf->face, + zsbuf->level, + zsbuf->zslice); + rast->zsbuf.map = NULL; + } + + lp_scene_reset( rast->curr_scene ); - rast->zsbuf.map = NULL; rast->curr_scene = NULL; + + if (0) + printf("Post render scene: tile read: %d tile write: %d\n", + tile_read_count, tile_write_count); } + /** * Begining rasterization of a tile. * \param x window X position of the tile, in pixels * \param y window Y position of the tile, in pixels */ static void -lp_rast_start_tile(struct lp_rasterizer_task *task, +lp_rast_tile_begin(struct lp_rasterizer_task *task, unsigned x, unsigned y) { + struct lp_rasterizer *rast = task->rast; + struct lp_scene *scene = rast->curr_scene; + enum lp_texture_usage usage; + unsigned buf; + LP_DBG(DEBUG_RAST, "%s %d,%d\n", __FUNCTION__, x, y); + assert(x % TILE_SIZE == 0); + assert(y % TILE_SIZE == 0); + task->x = x; task->y = y; + + if (scene->has_color_clear) + usage = LP_TEX_USAGE_WRITE_ALL; + else + usage = LP_TEX_USAGE_READ_WRITE; + + /* get pointers to color tile(s) */ + for (buf = 0; buf < rast->state.nr_cbufs; buf++) { + struct pipe_surface *cbuf = rast->curr_scene->fb.cbufs[buf]; + struct llvmpipe_resource *lpt; + assert(cbuf); + lpt = llvmpipe_resource(cbuf->texture); + task->color_tiles[buf] = llvmpipe_get_texture_tile(lpt, + cbuf->face, + cbuf->level, + usage, + x, y); + assert(task->color_tiles[buf]); + } + + /* get pointer to depth/stencil tile */ + { + struct pipe_surface *zsbuf = rast->curr_scene->fb.zsbuf; + if (zsbuf) { + struct llvmpipe_resource *lpt = llvmpipe_resource(zsbuf->texture); + + if (scene->has_depth_clear) + usage = LP_TEX_USAGE_WRITE_ALL; + else + usage = LP_TEX_USAGE_READ_WRITE; + + /* "prime" the tile: convert data from linear to tiled if necessary + * and update the tile's layout info. + */ + (void) llvmpipe_get_texture_tile(lpt, + zsbuf->face, + zsbuf->level, + usage, + x, y); + /* Get actual pointer to the tile data. Note that depth/stencil + * data is tiled differently than color data. + */ + task->depth_tile = lp_rast_get_depth_block_pointer(rast, x, y); + + assert(task->depth_tile); + } + else { + task->depth_tile = NULL; + } + } } @@ -124,7 +212,7 @@ lp_rast_clear_color(struct lp_rasterizer_task *task, { struct lp_rasterizer *rast = task->rast; const uint8_t *clear_color = arg.clear_color; - uint8_t **color_tile = task->tile.color; + unsigned i; LP_DBG(DEBUG_RAST, "%s 0x%x,0x%x,0x%x,0x%x\n", __FUNCTION__, @@ -138,7 +226,8 @@ lp_rast_clear_color(struct lp_rasterizer_task *task, clear_color[2] == clear_color[3]) { /* clear to grayscale value {x, x, x, x} */ for (i = 0; i < rast->state.nr_cbufs; i++) { - memset(color_tile[i], clear_color[0], TILE_SIZE * TILE_SIZE * 4); + uint8_t *ptr = task->color_tiles[i]; + memset(ptr, clear_color[0], TILE_SIZE * TILE_SIZE * 4); } } else { @@ -149,8 +238,9 @@ lp_rast_clear_color(struct lp_rasterizer_task *task, */ const unsigned chunk = TILE_SIZE / 4; for (i = 0; i < rast->state.nr_cbufs; i++) { - uint8_t *c = color_tile[i]; + uint8_t *c = task->color_tiles[i]; unsigned j; + for (j = 0; j < 4 * TILE_SIZE; j++) { memset(c, clear_color[0], chunk); c += chunk; @@ -161,7 +251,6 @@ lp_rast_clear_color(struct lp_rasterizer_task *task, memset(c, clear_color[3], chunk); c += chunk; } - assert(c - color_tile[i] == TILE_SIZE * TILE_SIZE * 4); } } @@ -178,23 +267,15 @@ lp_rast_clear_zstencil(struct lp_rasterizer_task *task, const union lp_rast_cmd_arg arg) { struct lp_rasterizer *rast = task->rast; - const unsigned tile_x = task->x; - const unsigned tile_y = task->y; const unsigned height = TILE_SIZE / TILE_VECTOR_HEIGHT; const unsigned width = TILE_SIZE * TILE_VECTOR_HEIGHT; - unsigned block_size = rast->zsbuf.blocksize; + const unsigned block_size = rast->zsbuf.blocksize; + const unsigned dst_stride = rast->zsbuf.stride * TILE_VECTOR_HEIGHT; uint8_t *dst; - unsigned dst_stride = rast->zsbuf.stride * TILE_VECTOR_HEIGHT; unsigned i, j; LP_DBG(DEBUG_RAST, "%s 0x%x\n", __FUNCTION__, arg.clear_zstencil); - /*assert(rast->zsbuf.map);*/ - if (!rast->zsbuf.map) - return; - - LP_DBG(DEBUG_RAST, "%s\n", __FUNCTION__); - /* * Clear the aera of the swizzled depth/depth buffer matching this tile, in * stripes of TILE_VECTOR_HEIGHT x TILE_SIZE at a time. @@ -203,7 +284,9 @@ lp_rast_clear_zstencil(struct lp_rasterizer_task *task, * TILE_VECTOR_HEIGHT x TILE_VECTOR_WIDTH pixels have consecutive offsets. */ - dst = lp_rast_depth_pointer(rast, tile_x, tile_y); + dst = task->depth_tile; + + assert(dst == lp_rast_get_depth_block_pointer(rast, task->x, task->y)); switch (block_size) { case 1: @@ -236,32 +319,73 @@ lp_rast_clear_zstencil(struct lp_rasterizer_task *task, * Load tile color from the framebuffer surface. * This is a bin command called during bin processing. */ +#if 0 void lp_rast_load_color(struct lp_rasterizer_task *task, const union lp_rast_cmd_arg arg) { struct lp_rasterizer *rast = task->rast; - const unsigned x = task->x, y = task->y; - unsigned i; + unsigned buf; + enum lp_texture_usage usage; LP_DBG(DEBUG_RAST, "%s at %u, %u\n", __FUNCTION__, x, y); - for (i = 0; i < rast->state.nr_cbufs; i++) { - if (x >= rast->cbuf[i].width || y >= rast->cbuf[i].height) - continue; + if (scene->has_color_clear) + usage = LP_TEX_USAGE_WRITE_ALL; + else + usage = LP_TEX_USAGE_READ_WRITE; + + /* Get pointers to color tile(s). + * This will convert linear data to tiled if needed. + */ + for (buf = 0; buf < rast->state.nr_cbufs; buf++) { + struct pipe_surface *cbuf = rast->curr_scene->fb.cbufs[buf]; + struct llvmpipe_texture *lpt; + assert(cbuf); + lpt = llvmpipe_texture(cbuf->texture); + task->color_tiles[buf] = llvmpipe_get_texture_tile(lpt, + cbuf->face, + cbuf->level, + usage, + task->x, task->y); + assert(task->color_tiles[buf]); + } +} +#endif - lp_tile_read_4ub(rast->cbuf[i].format, - task->tile.color[i], - rast->cbuf[i].map, - rast->cbuf[i].stride, - x, y, - TILE_SIZE, TILE_SIZE); - LP_COUNT(nr_color_tile_load); +/** + * Convert the color tile from tiled to linear layout. + * This is generally only done when we're flushing the scene just prior to + * SwapBuffers. If we didn't do this here, we'd have to convert the entire + * tiled color buffer to linear layout in the llvmpipe_texture_unmap() + * function. It's better to do it here to take advantage of + * threading/parallelism. + * This is a bin command which is stored in all bins. + */ +void +lp_rast_store_color( struct lp_rasterizer_task *task, + const union lp_rast_cmd_arg arg) +{ + struct lp_rasterizer *rast = task->rast; + struct lp_scene *scene = rast->curr_scene; + unsigned buf; + + for (buf = 0; buf < rast->state.nr_cbufs; buf++) { + struct pipe_surface *cbuf = scene->fb.cbufs[buf]; + const unsigned face = cbuf->face, level = cbuf->level; + struct llvmpipe_resource *lpt = llvmpipe_resource(cbuf->texture); + /* this will convert the tiled data to linear if needed */ + (void) llvmpipe_get_texture_tile_linear(lpt, face,level, + LP_TEX_USAGE_READ, + task->x, task->y); } } +/** + * This is a bin command called during bin processing. + */ void lp_rast_set_state(struct lp_rasterizer_task *task, const union lp_rast_cmd_arg arg) @@ -275,7 +399,6 @@ lp_rast_set_state(struct lp_rasterizer_task *task, } - /** * Run the shader on all blocks in a tile. This is used when a tile is * completely contained inside a triangle. @@ -287,7 +410,6 @@ lp_rast_shade_tile(struct lp_rasterizer_task *task, { struct lp_rasterizer *rast = task->rast; const struct lp_rast_state *state = task->current_state; - struct lp_rast_tile *tile = &task->tile; const struct lp_rast_shader_inputs *inputs = arg.shade_tile; const unsigned tile_x = task->x, tile_y = task->y; unsigned x, y; @@ -299,19 +421,17 @@ lp_rast_shade_tile(struct lp_rasterizer_task *task, for (x = 0; x < TILE_SIZE; x += 4) { uint8_t *color[PIPE_MAX_COLOR_BUFS]; uint32_t *depth; - unsigned block_offset, i; - - /* offset of the 16x16 pixel block within the tile */ - block_offset = ((y / 4) * (16 * 16) + (x / 4) * 16); + unsigned i; /* color buffer */ for (i = 0; i < rast->state.nr_cbufs; i++) - color[i] = tile->color[i] + 4 * block_offset; + color[i] = lp_rast_get_color_block_pointer(task, i, + tile_x + x, tile_y + y); /* depth buffer */ - depth = lp_rast_depth_pointer(rast, tile_x + x, tile_y + y); + depth = lp_rast_get_depth_block_pointer(rast, tile_x + x, tile_y + y); - /* run shader */ + /* run shader on 4x4 block */ state->jit_function[RAST_WHOLE]( &state->jit_context, tile_x + x, tile_y + y, inputs->facing, @@ -330,6 +450,8 @@ lp_rast_shade_tile(struct lp_rasterizer_task *task, /** * Compute shading for a 4x4 block of pixels. * This is a bin command called during bin processing. + * \param x X position of quad in window coords + * \param y Y position of quad in window coords */ void lp_rast_shade_quads( struct lp_rasterizer_task *task, const struct lp_rast_shader_inputs *inputs, @@ -338,12 +460,9 @@ void lp_rast_shade_quads( struct lp_rasterizer_task *task, { const struct lp_rast_state *state = task->current_state; struct lp_rasterizer *rast = task->rast; - struct lp_rast_tile *tile = &task->tile; uint8_t *color[PIPE_MAX_COLOR_BUFS]; void *depth; unsigned i; - unsigned ix, iy; - int block_offset; assert(state); @@ -354,28 +473,23 @@ void lp_rast_shade_quads( struct lp_rasterizer_task *task, assert((x % 4) == 0); assert((y % 4) == 0); - ix = x % TILE_SIZE; - iy = y % TILE_SIZE; - - /* offset of the 16x16 pixel block within the tile */ - block_offset = ((iy / 4) * (16 * 16) + (ix / 4) * 16); - /* color buffer */ - for (i = 0; i < rast->state.nr_cbufs; i++) - color[i] = tile->color[i] + 4 * block_offset; + for (i = 0; i < rast->state.nr_cbufs; i++) { + color[i] = lp_rast_get_color_block_pointer(task, i, x, y); + assert(lp_check_alignment(color[i], 16)); + } /* depth buffer */ - depth = lp_rast_depth_pointer(rast, x, y); + depth = lp_rast_get_depth_block_pointer(rast, x, y); - assert(lp_check_alignment(tile->color[0], 16)); assert(lp_check_alignment(state->jit_context.blend_color, 16)); assert(lp_check_alignment(inputs->step[0], 16)); assert(lp_check_alignment(inputs->step[1], 16)); assert(lp_check_alignment(inputs->step[2], 16)); - /* run shader */ + /* run shader on 4x4 block */ state->jit_function[RAST_EDGE_TEST]( &state->jit_context, x, y, inputs->facing, @@ -445,39 +559,31 @@ outline_subtiles(uint8_t *tile) /** - * Write the rasterizer's color tile to the framebuffer. + * Called when we're done writing to a color tile. */ static void -lp_rast_store_color(struct lp_rasterizer_task *task) +lp_rast_tile_end(struct lp_rasterizer_task *task) { +#if DEBUG struct lp_rasterizer *rast = task->rast; - const unsigned x = task->x, y = task->y; - unsigned i; - - for (i = 0; i < rast->state.nr_cbufs; i++) { - if (x >= rast->cbuf[i].width) - continue; - - if (y >= rast->cbuf[i].height) - continue; + unsigned buf; - LP_DBG(DEBUG_RAST, "%s [%u] %d,%d\n", __FUNCTION__, - task->thread_index, x, y); + for (buf = 0; buf < rast->state.nr_cbufs; buf++) { + uint8_t *color = lp_rast_get_color_block_pointer(task, buf, + task->x, task->y); if (LP_DEBUG & DEBUG_SHOW_SUBTILES) - outline_subtiles(task->tile.color[i]); + outline_subtiles(color); else if (LP_DEBUG & DEBUG_SHOW_TILES) - outline_tile(task->tile.color[i]); - - lp_tile_write_4ub(rast->cbuf[i].format, - task->tile.color[i], - rast->cbuf[i].map, - rast->cbuf[i].stride, - x, y, - TILE_SIZE, TILE_SIZE); - - LP_COUNT(nr_color_tile_store); + outline_tile(color); } +#else + (void) outline_subtiles; +#endif + + /* debug */ + memset(task->color_tiles, 0, sizeof(task->color_tiles)); + task->depth_tile = NULL; } @@ -512,7 +618,7 @@ rasterize_bin(struct lp_rasterizer_task *task, struct cmd_block *block; unsigned k; - lp_rast_start_tile( task, x * TILE_SIZE, y * TILE_SIZE ); + lp_rast_tile_begin( task, x * TILE_SIZE, y * TILE_SIZE ); /* simply execute each of the commands in the block list */ for (block = commands->head; block; block = block->next) { @@ -521,10 +627,7 @@ rasterize_bin(struct lp_rasterizer_task *task, } } - /* Write the rasterizer's tiles to the framebuffer. - */ - if (task->rast->state.write_color) - lp_rast_store_color(task); + lp_rast_tile_end(task); /* Free data for this bin. */ @@ -539,12 +642,12 @@ static struct { const char *name; } cmd_names[] = { - RAST(load_color), RAST(clear_color), RAST(clear_zstencil), RAST(triangle), RAST(shade_tile), RAST(set_state), + RAST(store_color), RAST(fence), }; @@ -597,8 +700,7 @@ is_empty_bin( const struct cmd_bin *bin ) } for (i = 0; i < head->count; i++) - if (head->cmd[i] != lp_rast_load_color && - head->cmd[i] != lp_rast_set_state) { + if (head->cmd[i] != lp_rast_set_state) { return FALSE; } @@ -658,6 +760,9 @@ lp_rast_queue_scene( struct lp_rasterizer *rast, rasterize_scene( &rast->tasks[0], scene ); lp_scene_reset( scene ); + + lp_rast_end( rast ); + rast->curr_scene = NULL; } else { @@ -798,7 +903,7 @@ struct lp_rasterizer * lp_rast_create( void ) { struct lp_rasterizer *rast; - unsigned i, cbuf; + unsigned i; rast = CALLOC_STRUCT(lp_rasterizer); if(!rast) @@ -808,10 +913,6 @@ lp_rast_create( void ) for (i = 0; i < Elements(rast->tasks); i++) { struct lp_rasterizer_task *task = &rast->tasks[i]; - - for (cbuf = 0; cbuf < PIPE_MAX_COLOR_BUFS; cbuf++ ) - task->tile.color[cbuf] = align_malloc(TILE_SIZE * TILE_SIZE * 4, 16); - task->rast = rast; task->thread_index = i; } @@ -829,12 +930,7 @@ lp_rast_create( void ) */ void lp_rast_destroy( struct lp_rasterizer *rast ) { - unsigned i, cbuf; - - for (i = 0; i < Elements(rast->tasks); i++) { - for (cbuf = 0; cbuf < PIPE_MAX_COLOR_BUFS; cbuf++ ) - align_free(rast->tasks[i].tile.color[cbuf]); - } + unsigned i; /* Set exit_flag and signal each thread's work_ready semaphore. * Each thread will be woken up, notice that the exit_flag is set and -- cgit v1.2.3