Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | r600g: fix dp2, dp3, dp4 tokens | Jerome Glisse | 2010-07-23 | 1 | -23/+64 |
| | | | | | | We need to make sure dp are all mirror accross the alu unit. Signed-off-by: Jerome Glisse <[email protected]> | ||||
* | r600g: add RSQ token support | Jerome Glisse | 2010-07-23 | 1 | -2/+28 |
| | | | | | | | Could serve as an example on how to add more token support. Signed-off-by: Jerome Glisse <[email protected]> | ||||
* | r600g: drop compiler stuff and switch over dumb tgsi assembler | Jerome Glisse | 2010-07-23 | 16 | -3323/+1277 |
| | | | | | | | | | | Writing a compiler is time consuming and error prone in order to allow r600g to further progress in the meantime i wrote a simple tgsi assembler, it does stupid thing but i would rather keep the code simple than having people trying to optimize code it does. Signed-off-by: Jerome Glisse <[email protected]> | ||||
* | softpipe: Check for NULL pointer in sp_destroy_tile_cache(). | Michal Krol | 2010-07-23 | 1 | -8/+10 |
| | |||||
* | softpipe: Check for NULL pointer in sp_destroy_tex_tile_cache(). | Michal Krol | 2010-07-23 | 1 | -11/+13 |
| | |||||
* | nv50: implement depth clamp | Christoph Bumiller | 2010-07-23 | 4 | -10/+33 |
| | |||||
* | llvmpipe: Partially fix resource texture from_handle | Jakob Bornecrantz | 2010-07-22 | 1 | -1/+35 |
| | |||||
* | llvmpipe: Don't align values already aligned | Jakob Bornecrantz | 2010-07-22 | 1 | -2/+2 |
| | |||||
* | i915g: Set total_nblocksy in from_handle | Jakob Bornecrantz | 2010-07-22 | 1 | -0/+1 |
| | |||||
* | i915g: Add some debug prints in texture code | Jakob Bornecrantz | 2010-07-22 | 1 | -6/+10 |
| | |||||
* | i915g: Ifdef out debug code on non-debug builds | Jakob Bornecrantz | 2010-07-22 | 1 | -0/+5 |
| | |||||
* | softpipe: add missing support for PIPE_FORMAT_S8_USCALED surfaces | Brian Paul | 2010-07-21 | 1 | -20/+20 |
| | | | | | | And remove checks of surface depth bits. The state tracker should not turn on depth/stencil testing if the framebuffer doesn't have depth/stencil. | ||||
* | softpipe: fix sp_tile_cache_flush_clear() regression | Brian Paul | 2010-07-21 | 1 | -5/+11 |
| | |||||
* | r600g: add support for all R6XX/R7XX asic | Jerome Glisse | 2010-07-21 | 4 | -87/+316 |
| | | | | | | | This configure some of the value properly based on asic so others asic than RV710 works too. Signed-off-by: Jerome Glisse <[email protected]> | ||||
* | r600g: add r600 compile mode to compiler. | Dave Airlie | 2010-07-21 | 4 | -13/+106 |
| | | | | | | some of the ALU instructions are different on r6xx vs r7xx, separate the alu translation to separate files, and use family to pick which compile stage to use. | ||||
* | r600g: add family retrival | Dave Airlie | 2010-07-21 | 2 | -1/+9 |
| | | | | allow pipe driver to get the family of the gpu. | ||||
* | llvmpipe: say no to depth clamp | Marek Olšák | 2010-07-21 | 1 | -0/+2 |
| | | | | The other drivers just return 0 without the assert. | ||||
* | r300g: implement depth clamp | Marek Olšák | 2010-07-21 | 2 | -1/+3 |
| | | | | | | | Depth clamping seems to be implicit if clipping is disabled. It's not perfect, but it's good enough for wine and passes the corresponding piglit tests. | ||||
* | r300g: cleanup clip state emission | Marek Olšák | 2010-07-21 | 1 | -6/+10 |
| | |||||
* | nouveau/nvfx: Add new PIPE_CAP values | Patrice Mandin | 2010-07-21 | 1 | -0/+4 |
| | | | | Signed-off-by: Patrice Mandin <[email protected]> | ||||
* | r600g: split trans unit computation | Jerome Glisse | 2010-07-20 | 2 | -7/+23 |
| | | | | Signed-off-by: Jerome Glisse <[email protected]> | ||||
* | softpipe: Support non-depth-stencil formats in sp_tile_cache_flush_clear(). | Michal Krol | 2010-07-20 | 1 | -2/+7 |
| | |||||
* | r300g: fix possible crash in destroy_context | Marek Olšák | 2010-07-19 | 1 | -2/+2 |
| | | | | | | | | | The problem is destroy_context is almost NEVER called. The only test for destroy_context I know is compiz. Reported by Vinson Lee. FDO bug #29150. | ||||
* | r300g: fix typo | Marek Olšák | 2010-07-19 | 1 | -1/+1 |
| | |||||
* | r300g: use memory pools for buffer_create and get_transfer | Marek Olšák | 2010-07-19 | 5 | -24/+101 |
| | | | | The improvement in Tremulous: 68.9 fps -> 71.1 fps. | ||||
* | r300g: u_upload optimisation | Dave Airlie | 2010-07-18 | 4 | -7/+15 |
| | | | | fix vb/ib uploads | ||||
* | llvmpipe: Remove dead initialization. | Vinson Lee | 2010-07-18 | 1 | -1/+1 |
| | |||||
* | r300g: final fix for r3xx constant buffer emission | Marek Olšák | 2010-07-17 | 1 | -1/+1 |
| | |||||
* | r300g: fix typo in r3xx constant buffer emission | Marek Olšák | 2010-07-17 | 1 | -1/+1 |
| | | | | Ooops. | ||||
* | r300g: fix constant buffer emission on r3xx | Marek Olšák | 2010-07-17 | 1 | -1/+1 |
| | | | | FDO bug #29128. | ||||
* | llvmpipe: Remove unused variable in lp_test_sincos. | Vinson Lee | 2010-07-17 | 1 | -2/+0 |
| | |||||
* | nv50: s/__func__/__FUNCTION__/ | Vinson Lee | 2010-07-16 | 1 | -1/+1 |
| | |||||
* | nouveau: s/__func__/__FUNCTION__/ | Vinson Lee | 2010-07-16 | 1 | -1/+1 |
| | |||||
* | nouveau: s/snprintf/util_snprintf/ | Vinson Lee | 2010-07-16 | 1 | -1/+2 |
| | |||||
* | r300g: Remove unnecessary header. | Vinson Lee | 2010-07-16 | 1 | -1/+0 |
| | |||||
* | nouveau: s/inline/INLINE/ | Vinson Lee | 2010-07-16 | 3 | -5/+5 |
| | |||||
* | r300g: inline winsys_buffer_destroy | Marek Olšák | 2010-07-16 | 1 | -12/+4 |
| | |||||
* | r300g: do not make copies of constant buffers, emit them directly | Marek Olšák | 2010-07-16 | 5 | -35/+27 |
| | |||||
* | llvmpipe: use single swizzled tile | Keith Whitwell | 2010-07-16 | 7 | -100/+148 |
| | | | | | | | | | | | | | Use a single swizzled tile per colorbuf (and per thread) to avoid accumulating large amounts of cached swizzled data. Now that the SSE3 code has been merged to master, the performance delta of this change is minimal, the main benefit is reduced memory usage due to no longer keeping swizzled copies of render targets. It's clear from the performance of the in-place version of this code that there is still quite a bit of time being spent swizzling & unswizzling, but it's not clear exactly how to reduce that. | ||||
* | llvmpipe: Describe _mm_shuffle_epi8() with gcc extended inline assembly when ↵ | José Fonseca | 2010-07-16 | 1 | -3/+30 |
| | | | | -mssse3 is not supported/enabled. | ||||
* | llvmpipe: Only use -mssse3 on gcc 4.3+ | José Fonseca | 2010-07-16 | 1 | -1/+5 |
| | |||||
* | i965g: Remove dead initialization in precalc_tex. | Vinson Lee | 2010-07-16 | 1 | -1/+1 |
| | |||||
* | r300g: rebuild winsys and command submission to support multiple contexts | Marek Olšák | 2010-07-16 | 16 | -299/+389 |
| | |||||
* | llvmpipe: implement instanced drawing functions | Brian Paul | 2010-07-15 | 1 | -20/+108 |
| | | | | | And express all the other drawing functions in terms of llvmpipe_draw_range_elements_instanced(). | ||||
* | softpipe: re-order drawing functions to get rid of prototype | Brian Paul | 2010-07-15 | 1 | -108/+102 |
| | |||||
* | llvmpipe: Remove redundant statement. | José Fonseca | 2010-07-15 | 1 | -1/+0 |
| | | | | Thanks to Vinson for spotting this. | ||||
* | llvmpipe: delete lp_test_*.o files with make clean | Brian Paul | 2010-07-14 | 1 | -0/+3 |
| | |||||
* | llvmpipe: Remove redundant alignments. | José Fonseca | 2010-07-14 | 2 | -3/+1 |
| | | | | | | | The lp_rast_shader_inputs' alignment is irrelevant now that it contains pointers instead of actual data. Likewise, lp_rast_triangle's size alignment is meaningless. | ||||
* | llvmpipe: Addi ssse3 swizzling for B8G8R8A8_UNORM. | Chris Li | 2010-07-14 | 3 | -3/+231 |
| | |||||
* | llvmpipe: fix comment typo | Roland Scheidegger | 2010-07-13 | 1 | -2/+2 |
| |