Age | Commit message (Collapse) | Author | |
---|---|---|---|
2011-01-31 | r600g: fix OQ on evergreen | Alex Deucher | |
6xx/7xx have a max of 4 DBs, evergreen have a max of 8. Signed-off-by: Alex Deucher <alexdeucher@gmail.com> | |||
2011-01-31 | r600g: fix occlusion query results. | Dave Airlie | |
Like on some r5xx, there are multiple DB backends on the r600, we need to add up the query results from each of these to get the final correct value. So far I'm not 100% sure how to calculate the num_db, value setting it to 4 should be harmless enough until we do. This fixes occulsion_query piglit test on my rv740. Signed-off-by: Dave Airlie <airlied@redhat.com> | |||
2011-01-30 | r600g: remove some non-existent evergreen reg fields | Alex Deucher | |
Signed-off-by: Alex Deucher <alexdeucher@gmail.com> | |||
2011-01-31 | r600g: fix regression in cubemap tests since ↵ | Dave Airlie | |
eea1d8199b376f37027c14669e0bdf991a22872d Although CUBE is a reduction inst, it writes to more than just PV.X so we need to keep the dst channel. Signed-off-by: Dave Airlie <airlied@redhat.com> | |||
2011-01-31 | r600g: handle the write all cbufs property. | Dave Airlie | |
This only works on r600/r700 so far, evergreen doesn't appear to have the multiwrite enable bit in the color control, so we may have to actually do a shader rewrite on EG hardware. remove some duplicate code reg defines also. Signed-off-by: Dave Airlie <airlied@redhat.com> | |||
2011-01-30 | r600g: Update the flushed depth texture after drawing to the corresponding ↵ | Henri Verbeet | |
texture. I know Jerome will probably rewrite the way depth textures work sometime soon. For the time being this should at least make common depth texture usage for shadowing work properly though. | |||
2011-01-30 | r600g: Fix void pointer arithmetic. | Vinson Lee | |
Fixes SCons build. | |||
2011-01-30 | r600g: fixes a segfault in the piglit fbo-genmipmap-formats test. | Dave Airlie | |
should be no need to unset this ptr here and if we don't end up using the blitter we've just broken the state. | |||
2011-01-30 | r600g: upload translated indices via the uploader | Marek Olšák | |
2011-01-30 | r600g: rework vertex format fallback | Marek Olšák | |
1) Only translate the [min_index, max_index] range. 2) Upload translated vertices via the uploader. | |||
2011-01-30 | r600g: fix vertex format fallback | Marek Olšák | |
This fixes: - piglit/draw-vertices - piglit/draw-vertices-half-float | |||
2011-01-30 | r600g: rework vertex buffer uploads | Marek Olšák | |
Only upload the [min_index, max_index] range instead of [0, userbuf_size]. This an important optimization. Framerate in Lightsmark: Before: 22 fps After: 75 fps The same optimization is already in r300g. | |||
2011-01-30 | r600g: consolidate set_constant_buffer functions | Marek Olšák | |
2011-01-30 | r600g: consolidate vertex_buffer_update functions | Marek Olšák | |
2011-01-30 | r600g: consolidate draw_vbo functions (v2) | Marek Olšák | |
Added a conditional to spi_update per Dave's comment. | |||
2011-01-30 | r600g: make r600_drawl inherit pipe_draw_info | Marek Olšák | |
2011-01-30 | r600g: add back u_upload_mgr integration | Marek Olšák | |
I can't see a performance difference with this code, which means all the driver-specific code removed in this commit was unnecessary. Now we use u_upload_mgr in a slightly different way than we did before it got dropped. I am not restoring the original code "as is" due to latest u_upload_mgr changes that r300g performance benefits from. This also fixes: - piglit/fp-kil | |||
2011-01-28 | r600g: handle PIPE_CAP_ARRAY_TEXTURES | Marek Olšák | |
2011-01-25 | r600g: Implement timer queries. | Mathias Fröhlich | |
2011-01-25 | r600g: FLT_TO_INT* are vector instructions on Evergreen. | Henri Verbeet | |
FLT_TO_INT is a vector instruction, despite what the (current) documentation says. FLT_TO_INT_FLOOR and FLT_TO_INT_RPI aren't explicitly mentioned in the documentation, but those are vector instructions too. | |||
2011-01-21 | r600g: check if hardware blits are possible bevore enabling tilling | Christian König | |
2011-01-21 | r600g: FLT_TO_INT_FLOOR is trans instruction | Alex Deucher | |
Add missing evergreen FLT_TO_INT_FLOOR instruction. | |||
2011-01-19 | r600g: fix segfault if texture operand is a literal | Christian König | |
This fixes Bug 33262 | |||
2011-01-19 | r600g: fix reserve_cfile for R700+ | Christian König | |
According to R700 ISA we have only two channels for cfile constants. This patch makes piglit tests "glsl1-constant array with constant indexing" happy on RV710. | |||
2011-01-18 | r600g: Kill trailing whitespace. | Henri Verbeet | |
2011-01-18 | r600g: Remove the unused eg_states_inc.h and r600_states_inc.h. | Henri Verbeet | |
2011-01-18 | r600g: Simplify some r600_bc_add_alu_type() calls to r600_bc_add_alu(). | Henri Verbeet | |
2011-01-16 | r600g: fix PIPE_CAP_INSTANCED_DRAWING warning | Christian König | |
2011-01-16 | r600g: fix alu inst group merging for relative adressing | Christian König | |
2011-01-16 | r600d: fix some bugs added reworking literal handling | Christian König | |
If a literal slot isn't used it should be set to 0 instead of an uninitialized value. Also the channels for pre R700 trig functions were incorrect. And most important literals were not counted against ndw, resulting in an invalid force_add_cf detection. | |||
2011-01-15 | r600g: Fix some register value name typos. | Henri Verbeet | |
SFR -> SRF. | |||
2011-01-15 | r600g: Get rid of r600_translate_vertex_data_type(). | Henri Verbeet | |
This has been replaced with r600_vertex_data_type(). | |||
2011-01-14 | r600g: compiler helper opcode fixes for evergreen | Alex Deucher | |
Signed-off-by: Alex Deucher <alexdeucher@gmail.com> | |||
2011-01-14 | r600g: pass r600_bc to some addition compiler helper functions | Alex Deucher | |
needed for asic specific opcodes Signed-off-by: Alex Deucher <alexdeucher@gmail.com> | |||
2011-01-14 | r600g: Disable V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_FLT_TO_INT_FLOOR case. | Vinson Lee | |
The usage of macro V_SQ_ALU_WORD1_OP2_SQ_OP2_INST_FLT_TO_INT_FLOOR was introduced by commit 323ef3a1f07ba4333dadebab571ddcd49d95f45c but the macro is undefined. Disable this case to fix the build for now. | |||
2011-01-14 | r600g: add more missing instructions to r600_bc_get_num_operands | Christian König | |
2011-01-13 | r600g: Move declaration before code in r600_asm.c. | Vinson Lee | |
Fixes SCons build. | |||
2011-01-13 | r600g: rework literal handling | Christian König | |
2011-01-13 | r600g: merge alu groups | Christian König | |
2011-01-13 | r600g: implement replacing gpr with pv and ps | Christian König | |
2011-01-13 | r600g: add missing RECIPSQRT_CLAMPED to r600_bc_get_num_operands | Christian König | |
2011-01-13 | r600g: rework bank swizzle code | Christian König | |
2011-01-13 | r600g: fix alu slot assignment | Christian König | |
2011-01-13 | r600g: optimize away CF ALU instructions even if type doesn't match | Christian König | |
2011-01-13 | r600g: Silence uninitialized variable warnings. | Vinson Lee | |
2011-01-12 | r600g: also look at tex inst when for maximum gpu count | Christian König | |
2011-01-12 | r600g: implement output modifiers and use them to further optimize LRP | Christian König | |
2011-01-12 | r600g: use special constants for 0, 1, -1, 1.0f, 0.5f etc | Christian König | |
2011-01-12 | r600g: optimize temp register handling for LRP | Christian König | |
2011-01-12 | r600g: optimize away CF_INST_POP | Christian König | |
If last instruction is an CF_INST_ALU we don't need to emit an additional CF_INST_POP for stack clean up after an IF ELSE ENDIF. |