summaryrefslogtreecommitdiff
path: root/src/gallium
AgeCommit message (Collapse)Author
2010-08-23util: fix util_fill_rect to take util_color instead of u32 paramRoland Scheidegger
util_fill_rect could not handle formats with more than 32 bits, since the fill color was a uint32_t value. Fix this by using a util_color union instead, and also expand the union so it works with formats which have up to 256 bits (the max of any format currently defined).
2010-08-23nvfx: emit bo relocations only when neededLuca Barbieri
Should improve performance, possibly significantly.
2010-08-23nvfx: match Gallium's gl_PointCoord brokennessLuca Barbieri
Gallium always puts gl_PointCoord in GENERIC[0] if point_quad_rasterization is enabled. This is silly, but for now it makes mesa-demos/glsl/pointcoord work.
2010-08-23nvfx: support clip planes sensibly and fix them on nv30Luca Barbieri
Before, we were discarding the compiled vertex program on each vertex program change. Now we compile the program as if there were 6 clip planes and dynamically patch in an "end program" bit at the right place. Also, nv30 should now work.
2010-08-23r300g: avoid stall in no-tcl drawing when mapping vboDave Airlie
the current code reuses the same vbo over and over, however after a flush we'd stall and wait for mapping on the vbo when we should just fire and forget. On a gears test this brings me from ~620 to ~750 on my rv530 in swtcl mode. Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-08-22util: implement depth blitting in u_blitMarek Olšák
Signed-off-by: Brian Paul <brianp@vmware.com>
2010-08-23nvfx: fix minor memory leakLuca Barbieri
2010-08-23nvfx: support both sprite coord originsLuca Barbieri
Now we lie less when claiming OpenGL 2 support. Also, first piglit result group is now all green, except for fdo25614-genmipmap, which seems mesa/st's fault.
2010-08-23nvfx: use 64-bit bitmasks for tempsLuca Barbieri
2010-08-22r600g: fix DB decompressionJerome Glisse
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
2010-08-22nvfx: Include missing header in nvfx_vertprog.c.Vinson Lee
Include draw_context.h for draw_*_vertex_shader symbols. Fixes the following GCC warning. nvfx_vertprog.c: In function 'nvfx_vp_state_create': nvfx_vertprog.c:1276: warning: implicit declaration of function 'draw_create_vertex_shader' nvfx_vertprog.c:1276: warning: assignment makes pointer from integer without a cast nvfx_vertprog.c: In function 'nvfx_vp_state_delete': nvfx_vertprog.c:1298: warning: implicit declaration of function 'draw_delete_vertex_shader'
2010-08-22translate_sse: add R32G32B32A32_FLOAT -> X8X8X8X8_UNORM for EMIT_4UBJakob Bornecrantz
Changed by me to use movd instead of movss to avoid penalties.
2010-08-22translate_sse: refactor constant managementLuca Barbieri
2010-08-22nvfx: refactor to support multiple fragment program versionsLuca Barbieri
2010-08-22nvfx: move stuff aroundLuca Barbieri
2010-08-22r600g: depth buffer likely needs decompression when used as textureJerome Glisse
Before using depth buffer as texture, it needs to be decompressed (tile pattern of db are different from one used for colorbuffer like texture) Signed-off-by: Jerome Glisse <jglisse@redhat.com>
2010-08-22glx/xlib: configurable strict/non-strict buffer size invalidateKeith Whitwell
Introduce a new configuration option XMESA_STRICT_INVALIDATE to switch between swapbuffers-based and glViewport-based buffer invalidation. Default strict invalidate to false, ie glViewport-based invalidation, aka ST_MANAGER_BROKEN_INVALIDATE. This means we will not call XGetGeometry after every swapbuffers, which allows swapbuffers to remain asynchronous. For apps running at 100fps with synchronous swapping, a 10% boost is typical. For gears, I see closer to 20% speedup. Note that the work of copying data on swapbuffers doesn't disappear - this change just allows the X server to execute the PutImage asynchronously without us effectively blocked until its completion. This applies even to llvmpipe's threaded rasterization as the swapbuffers operation was a large part of the serial component of an llvmpipe frame. The downside of this is correctness - applications which don't call glViewport on window resizes will get incorrect rendering, unless XMESA_STRICT_INVALIDATE is set. The ultimate solution would be to have per-frame but asynchronous invalidation. Xcb almost looks as if it could provide this, but the API doesn't seem to quite be there.
2010-08-22llvmpipe: reduce size of fragment shader variant keyKeith Whitwell
Don't spend as much time comparing them.
2010-08-22llvmpipe: remove unused member from lp_fragment_shader_variant_keyKeith Whitwell
2010-08-22llvmpipe: don't clear unused binsKeith Whitwell
If bins outside the current scene bounds are being corrupted, we'll need to fix that separately. Currently seems ok though.
2010-08-22draw: reduce the size of the llvm variant keyKeith Whitwell
2010-08-22glx/xlib: remove another XSyncKeith Whitwell
With this change, xmesa_get_window_size still does one round trip, but that's better than doing two.
2010-08-22glx/xlib: no need to call XSync from XMesaFlushKeith Whitwell
Try to eliminate some unnecessary X server round trips.
2010-08-22nvfx: simplify and correct fragment program update logicLuca Barbieri
This version should hopefully be much clearer and thus less likely to be subtly broken. Also fixes point sprites on nv40 and possibly some other bugs too.
2010-08-22nvfx: make stipple setting independent of enableLuca Barbieri
2010-08-22nvfx: fix vertex programsLuca Barbieri
2010-08-22nvfx: use relocations array for vp constantsLuca Barbieri
2010-08-22r600g: Don't blindly unmap NULL->size.Henri Verbeet
There may actually be something mapped in that range, especially for large buffers like e.g. the GL Drawable.
2010-08-22svga: Do not shortcut NULL surface relocations with SVGA3D_INVALID_ID.José Fonseca
How to cope with NULL surface relocations should be entirely at winsys' discretion.
2010-08-22libgl-xlib: Include missing header in xlib.c.Vinson Lee
Include st_api.h for st_api_create_OpenGL symbol.
2010-08-22nvfx: Silence unused variable warning.Vinson Lee
The variable is used but only in the body of an assert.
2010-08-21util: Use #ifdef instead of #if.Vinson Lee
This is a typo fix of earlier commit 0f3b3751b8643352dcc242567b3696bd1505df1d.
2010-08-21util: Define dump_cpu only for DEBUG builds.Vinson Lee
dump_cpu is used only when DEBUG is defined. Fixes the following GCC warning on builds without DEBUG defined. util/u_cpu_detect.c:76: warning: 'debug_get_option_dump_cpu' defined but not used
2010-08-21translate_sse: Silence uninitialized variable warnings.Vinson Lee
Initialize variables on error paths.
2010-08-21nvfx: Silence uninitialized variable warnings.Vinson Lee
Variables weren't initialized on the error paths.
2010-08-21i965g: Silence printf format warnings on 64-bit builds.Vinson Lee
2010-08-21nvfx: Silence uninitialized variable warnings.Vinson Lee
Silence the following i686-apple-darwin10-gcc-4.2.1 warnings. nv04_2d.c: In function 'nv04_region_copy_cpu': nv04_2d.c:560: warning: 'dswy' may be used uninitialized in this function nv04_2d.c:559: warning: 'dswx' may be used uninitialized in this function nv04_2d.c:562: warning: 'sswy' may be used uninitialized in this function nv04_2d.c:561: warning: 'sswx' may be used uninitialized in this function
2010-08-21nv50: Silence incompatible pointer type initialization warning.Vinson Lee
Silence the following GCC warning. warning: initialization from incompatible pointer type
2010-08-21nv50: Disable unused code.Vinson Lee
Disable release_hw and emit_mov_from_pred functions as they are currently not being used.
2010-08-21i965g: Fix printf format warning on 32-bit platforms.Vinson Lee
Fixes the following GCC warning on 32-bit platforms. warning: format '%li' expects type 'long int', but argument 4 has type 'int'
2010-08-21r600g: partialy fix texturing from depth buffer + initial support for untilingJerome Glisse
Partialy fix texturing from depth buffer, depth buffer is tiled following different tile organisation that color buffer. This properly set the tile type & array mode field of texture sampler when sampling from db resource. Add initial support to untiling buffer when transfering them, it's kind of broken by corruption the vertex buffer of previous draw. Signed-off-by: Jerome Glisse <jglisse@redhat.com>
2010-08-22draw: Don't assert if indices point outside vertex buffer.José Fonseca
This is valid input, and asserting here does causes the test suites that verify this to crash. Also, the assert was wrongly accepting the case max_index == vert_info->count which, IIUC, is the first vertex outside the buffer. Assuming the vert_info->count is precise (which often is not the case).
2010-08-21util: Silence uninitialized variable warnings.Vinson Lee
2010-08-21nvfx: actually fix it properlyLuca Barbieri
2010-08-21nvfx: fix incorrect assertLuca Barbieri
2010-08-21util: Move loop variable declaration outside for loop.Vinson Lee
Fixes build error with MSVC.
2010-08-21nvfx: Fix SCons build.Vinson Lee
Move declarations before code. Fix void pointer arithmetic.
2010-08-21nvfx: fix warningsLuca Barbieri
2010-08-21gallivm: Emit DIVPS instead of RCPPS.José Fonseca
See comments for detailed rationale. Thanks to Michal Krol and Zack Rusin for detecting and investigating this in detail.
2010-08-21nvfx: enable translate_sseLuca Barbieri