summaryrefslogtreecommitdiffstats
path: root/src/mesa/drivers
Commit message (Collapse)AuthorAgeFilesLines
* r600: always emit CB baseAlex Deucher2009-08-231-1/+7
| | | | | | | Not doing so seems to cause lock-ups or rendering problems on some chips. I think there is an logic issue related to CB and VGT on some chips. We ran into similar issues in r600_demo IIRC.
* radeon: Fix compilation with legacy memory manager.Pauli Nieminen2009-08-231-1/+1
|
* radeon: Check from kernel if dma buffer is idle.Pauli Nieminen2009-08-233-1/+33
| | | | | | This makes sure that objects are leaving wait list only when they are processed by gpu. Signed-off-by: Pauli Nieminen <[email protected]>
* r600: make state emit more fine grainedAlex Deucher2009-08-224-106/+230
| | | | | Gives a nice speed boost in most apps since we only emit what state we need.
* r600: move full state to radeon state atomsAlex Deucher2009-08-229-192/+262
|
* r600: add support for RS880Alex Deucher2009-08-225-0/+19
|
* i965: Implement frag prog DPH like DP4Ian Romanick2009-08-221-3/+5
| | | | | DPH can output to any component, not just to X. This allows fpalu.c to run without hitting the assertion in emit_dph.
* Fix r300 VBO support build on big endian.Michel Dänzer2009-08-221-3/+3
|
* r600: better default state size.Alex Deucher2009-08-213-9/+15
| | | | | Hopefully suokko's emit size impovements will land soon.
* radeon: fix incorrect loop limit (warned by -O3)Brian Paul2009-08-211-1/+1
|
* radeon: Add comment to explain logic for freeing dma buffers.Pauli Nieminen2009-08-211-0/+3
|
* r600: convert to using common radeon state atomsAlex Deucher2009-08-208-233/+154
| | | | | | switches more state handling to common code. We need should be more fine grained with the state atoms eventually.
* r600: improve state emissionAlex Deucher2009-08-206-30/+182
| | | | | Slowing migrating to atom based system like the other radeon drivers.
* r600: split state emit into block specific functionsAlex Deucher2009-08-206-320/+379
| | | | | We probably want to go finer grained eventually, but this is a good start.
* r600: try and get everything in the draw in one IBAlex Deucher2009-08-201-3/+10
| | | | | fixes corruption issues with apps like teapot and geartrain.
* r600: move misc regs from general stateAlex Deucher2009-08-201-7/+9
| | | | | These regs don't use the SET_CONTEXT_REG packet, so they weren't getting set correctly.
* r600: rework emit codeAlex Deucher2009-08-204-37/+44
| | | | make sure we allocate enough space for relocs
* radeon: Update regulary cs processing info from kernel.Pauli Nieminen2009-08-203-6/+12
| | | | | | This fixes problem that dma buffers were leaking in dri1 mode. Signed-off-by: Pauli Nieminen <[email protected]>
* radeon: fix typo in last dma patchAlex Deucher2009-08-191-1/+1
|
* intel: Fix failure to commit -a --amend before last push.Eric Anholt2009-08-191-1/+1
|
* intel: Align cubemap texture height to its padding requirements.Eric Anholt2009-08-191-0/+10
|
* intel: Align untiled region height to 2 according to 965 docs.Eric Anholt2009-08-191-0/+10
| | | | | This may or may not be required pre-965, but it doesn't seem unlikely, and I'd rather be safe.
* radeon: Add debug output for dma buffer object numbers.Pauli Nieminen2009-08-191-3/+18
| | | | Signed-off-by: Pauli Nieminen <[email protected]>
* radeon: Fix dma buffer object pool to scale object sizes.Pauli Nieminen2009-08-192-11/+42
| | | | | | This fixes problems when application is using large vertex arrays for drawing. Signed-off-by: Pauli Nieminen <[email protected]>
* r600: minor cleanupAlex Deucher2009-08-191-2/+1
|
* radeon: balance dma buffer mappingPauli Nieminen2009-08-181-0/+4
| | | | | In radeonRefillCurrentDmaRegion() make sure we unmap the previous buffer.
* r300: Movde debug output from stdout to stderr in copiler.Pauli Nieminen2009-08-181-8/+8
| | | | Signed-off-by: Pauli Nieminen <[email protected]>
* r200: make use of DMA buffers for Elts a lot better.Dave Airlie2009-08-183-11/+18
| | | | | | | This allows us to return the unused portion of the dma buffer to the allocator instead of wasting nearly 16k a pop. Cherry picked and ported to new code by Pauli.
* r200: Fix missing offset from elt buffer pointer.Pauli Nieminen2009-08-181-1/+1
| | | | Signed-off-by: Pauli Nieminen <[email protected]>
* radeon: Optimize memory handling for dma operations.Pauli Nieminen2009-08-1816-93/+163
| | | | | | | | | | We keep dma buffer objects in list untill they have been unused for many draw operations. Current limit of having 100 flushes is just guess for good performance/memory trade off. Moving WARN_ONCE macro to common context because it is used in multiple drivers. Signed-off-by: Pauli Nieminen <[email protected]>
* r300: fix the build on big endianAlex Deucher2009-08-181-1/+1
|
* r600: fix buildDave Airlie2009-08-183-1/+4
|
* r300: remove warning introduced with OQDave Airlie2009-08-181-1/+0
|
* radeon/r200: fix build after OQ commitsDave Airlie2009-08-185-3/+7
|
* r300: OQ reworkDave Airlie2009-08-1816-299/+381
| | | | | | | | | | | | Move to common code base so radeon/r200 can add support for this. Make OQ start a state emitted like all normal state, and make no-tcl flushing work in proper places. Really need a generic post emit space reservation mechanism like max_state so we can reserve some space for the emit this code passes demos/arbocclude, piglit occlusion query and glean occlusion query with TCL and NO-TCL on my rv530.
* r300: fix missing BEGIN/END batchesDave Airlie2009-08-181-0/+2
|
* r300: fix big endian buildDave Airlie2009-08-181-0/+1
|
* r600: fix counting error after the last commitAlex Deucher2009-08-171-1/+1
|
* r600: make sure the number of indices is validAlex Deucher2009-08-171-1/+54
| | | | | | make sure the number of indices is valid for the requested prim type. glxgears sends invalid quad strips with only 2 indices for example.
* radeon: remove RADEON_DEBUG_BO stuffAlex Deucher2009-08-1710-237/+16
| | | | | This stuff was a vestige of the r600 bring up and now mostly serves to periodically break the build.
* r300: split vbo rendering with big drawarray caseJerome Glisse2009-08-171-4/+15
| | | | | Split vbo rendering when the number of elements requested by drawarrays is bigger than 65536.
* radeon: turn off bo debuggingDave Airlie2009-08-171-1/+1
|
* r300: disable ZTOP only when occlusion queries are usedMaciej Cencora2009-08-161-1/+3
|
* r300: enable ARB_occlusion_queryMaciej Cencora2009-08-151-0/+8
| | | | | Supported only on HW with TCL block and with proper radeon drm. Required minimum radeon drm version is 1.30 or KMS.
* radeon: add flag for drm OQ supportMaciej Cencora2009-08-152-5/+8
|
* r300: temporary occlusion query hackMaciej Cencora2009-08-151-1/+1
|
* r300: clear not_flushed OQ list after flushMaciej Cencora2009-08-153-4/+15
|
* r300/oq: add some debugging infoMaciej Cencora2009-08-151-0/+21
|
* r300: add occlusion queries supportMaciej Cencora2009-08-158-1/+308
| | | | | | | TODO: - use proper interface for checking if bo is idle when it's available - disable ZTOP only when needed - make it work under KMS
* radeon space: realign with drm space check codeDave Airlie2009-08-151-1/+1
|
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 01:50:36 +0000