aboutsummaryrefslogtreecommitdiffstats
path: root/src/gallium
Commit message (Collapse)AuthorAgeFilesLines
* draw: fix another decompose bug affecting constant interpolated attributesRoland Scheidegger2014-12-101-2/+1
| | | | | | | | | | | Previously the first provoking vertex convention would only be used if flatshading were enabled. No matter how I look at it that cannot be possibly correct. Maybe the code getting used was somewhat simpler that way at a time where there weren't constant interpolated attributes, only flatshading... (Note that all other places including the decomposition macros already do the same.) Reviewed-by: Jose Fonseca <[email protected]>
* draw: fix flatshade stage for constant interpolated valuesRoland Scheidegger2014-12-103-69/+126
| | | | | | | | | | | | | | | | | | | | This stage only worked for traditional old-school flatshading, it did ignore constant interpolated values and only handled colors, the code probably predates using of constant interpolated values in gallium. So fix this - the clip stage apparently did this a long time ago already. Unfortunately this also means the stage needs to be invoked when flatshading isn't enabled but some other prim changing stages are - for instance with fill mode line each of the 3 lines in a tri should get the same attribute value from the leading vertex in the original tri if interpolation is constant, which did not happen before Due to that, the stage is now run in more cases, even unnecessary ones. Could in theory skip it completely if there aren't any constant interpolated attributes (and rast->flatshade isn't set), but not sure it's worth bothering, as it looks kinda complicated getting this information in advance. No piglit change (doesn't really cover this directly). Reviewed-by: Jose Fonseca <[email protected]>
* draw: copy over prim id header in flatshade stage when emitting linesRoland Scheidegger2014-12-101-3/+6
| | | | | | | | | | Just like we do for tris (det shouldn't matter at this point, however can have flags for things like line stipple reset). No piglit change, it would fail line stippling tests if the flatshade stage were run, which will happen with the next commit. Reviewed-by: Jose Fonseca <[email protected]>
* gallium/docs: clarify fragment shader position input w component.Roland Scheidegger2014-12-101-2/+4
| | | | | | | | The previous language was a bit misleading, since it sounded like w was interpolated then the reciprocal calculated which isn't what should be happening. Reviewed-by: Jose Fonseca <[email protected]>
* radeonsi: take into account NULL colorbuffers when computing CB_TARGET_MASKMarek Olšák2014-12-101-4/+12
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: only emit line stippling and provoking vertex state when it changesMarek Olšák2014-12-105-0/+9
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: fix SPI state dependency on sprite_coord_enableMarek Olšák2014-12-102-2/+4
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: fix line stippling and provoking vertex state for GS primitivesMarek Olšák2014-12-101-1/+3
| | | | | | I'm not sure if GS hw outputs line lists or line strips. Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: emit DRAW_PREAMBLE only if it changesMarek Olšák2014-12-103-8/+17
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: remove setting of VGT_DISPATCH_DRAW_INDEXMarek Olšák2014-12-101-3/+0
| | | | | | | It's used only if VGT_SHADER_STAGES_EN.DISPATCH_DRAW_EN is 1, which we don't set. Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: emit GS_OUT_PRIM_TYPE only if it changesMarek Olšák2014-12-103-1/+6
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: emit primitive restart only if it changesMarek Olšák2014-12-103-5/+22
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: emit base vertex and start instance only if they changeMarek Olšák2014-12-103-3/+38
| | | | | | v2: added a helper function for invalidation of the sh constants Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: emit clip registers only if VS, GS, or rasterizer is changedMarek Olšák2014-12-105-32/+39
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: get info about VS outputs from tgsi_shader_infoMarek Olšák2014-12-103-35/+34
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: move all shader-related functions to a new file si_state_shaders.cMarek Olšák2014-12-106-785/+810
| | | | | | This huge amount of code deserves its own file. Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: generate derived and draw-related registers directly in the CSMarek Olšák2014-12-103-75/+76
| | | | | | The big function is split into 3 smaller functions. Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: si_conv_pipe_prim shouldn't failMarek Olšák2014-12-101-11/+3
| | | | | | An assertion should suffice. Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: remove useless variable si_context::pm4_dirty_cdwordsMarek Olšák2014-12-103-11/+1
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: remove unused draw packet functionsMarek Olšák2014-12-102-87/+0
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: emit draw packets directly into the CSMarek Olšák2014-12-103-68/+95
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: add emit util functions for SH registersMarek Olšák2014-12-102-1/+18
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* tgsi: add tgsi_shader_info::writes_clipvertexMarek Olšák2014-12-102-0/+4
| | | | Reviewed-by: Brian Paul <[email protected]>
* tgsi: add clip and cull distance writemasks into tgsi_shader_infoMarek Olšák2014-12-102-0/+6
| | | | Reviewed-by: Brian Paul <[email protected]>
* tgsi: add tgsi_shader_info::writes_psizeMarek Olšák2014-12-102-0/+4
| | | | Reviewed-by: Brian Paul <[email protected]>
* cso: put cso_release_all into cso_destroy_contextMarek Olšák2014-12-108-32/+7
| | | | Reviewed-by: Brian Paul <[email protected]>
* gallium/target: Haiku softpipeAlexander von Gluck IV2014-12-101-1/+1
| | | | * Use print macro to fix warning on 64-bit systems
* gallium/aux: Avoid redefining MAXAlexander von Gluck IV2014-12-101-0/+2
| | | | * Can be redefined on some platforms through u_debug.h
* clover: Use switch when creating kernel arguments.Jan Vesely2014-12-101-25/+19
| | | | | | | | | This way we get a warning if an enum value is not handled. v2: codestyle Signed-off-by: Jan Vesely <[email protected]> Reviewed-by: Francisco Jerez <[email protected]>
* r600g: only init GS_VERT_ITEMSIZE on r600Dave Airlie2014-12-101-5/+2
| | | | | | | | | | | | On evergreen there are 4 regs, on r600/700 there is only one. Don't initialise regs and trash someone elses state. Not sure this fixes anything, but hey one less stupid. Reviewed-By: Glenn Kennard <[email protected]> Cc: "10.3 10.4" [email protected] Signed-off-by: Dave Airlie <[email protected]>
* vc4: Do QPU scheduling across uniform loads.Eric Anholt2014-12-091-28/+60
| | | | | | | | This means another pass of reordering the uniform data store, but it lets us pair up a lot more instructions. total instructions in shared programs: 44639 -> 43176 (-3.28%) instructions in affected programs: 36938 -> 35475 (-3.96%)
* vc4: Populate the delay field better, and schedule high delay first.Eric Anholt2014-12-091-1/+49
| | | | | | | This is a standard scheduling heuristic, and clearly helps. total instructions in shared programs: 46418 -> 44467 (-4.20%) instructions in affected programs: 42531 -> 40580 (-4.59%)
* vc4: Skip raddr dependencies for 32-bit immediate loads.Eric Anholt2014-12-091-2/+5
| | | | These don't have raddr fields.
* vc4: Mark VPM read setup as impacting VPM reads, not writes.Eric Anholt2014-12-091-1/+7
| | | | | Fixes assertion failures if we adjust scheduling priorities to emphasize VPM reads more.
* vc4: Refuse to merge instructions involving 32-bit immediate loads.Eric Anholt2014-12-091-0/+5
| | | | | An immediate load overwrites the mul and add operations, so you can't merge with them.
* clover: Fix build after llvm r223802Aaron Watry2014-12-091-0/+4
| | | | | Signed-off-by: Aaron Watry <awatry at gmail.com> Reviewed-by: Tom Stellard <[email protected]>
* freedreno/a4xx: frag-coord / face fixesRob Clark2014-12-091-6/+19
| | | | Signed-off-by: Rob Clark <[email protected]>
* freedreno/a4xx: fix rendering to layer != 0Rob Clark2014-12-091-1/+4
| | | | Signed-off-by: Rob Clark <[email protected]>
* freedreno/a4xx: temp hack for FLAT varyingsRob Clark2014-12-091-0/+19
| | | | Signed-off-by: Rob Clark <[email protected]>
* freedreno/ir3: lower TXP as neededRob Clark2014-12-093-3/+19
| | | | | | On a3xx, lower TXP for 3D textures, on a4xx lower all TXP. Signed-off-by: Rob Clark <[email protected]>
* freedreno/a4xx: XA gpu hang at startupRob Clark2014-12-092-1/+9
| | | | Signed-off-by: Rob Clark <[email protected]>
* freedreno/a4xx: texture fixesRob Clark2014-12-096-7/+54
| | | | Signed-off-by: Rob Clark <[email protected]>
* freedreno: cleanup slice alignment/setupRob Clark2014-12-091-36/+14
| | | | | | | | Collapse things back into a setup_slices() which takes the desired alignment as a param. This gets things ready for a4xx which has some slightly different requirements. Signed-off-by: Rob Clark <[email protected]>
* freedreno: update generated headersRob Clark2014-12-096-18/+65
| | | | Signed-off-by: Rob Clark <[email protected]>
* tgsi/lowering: add support to lower TXP (v2)Rob Clark2014-12-092-15/+34
| | | | | | | v2: actually do perspective divide for RECT/SHADOWRECT Signed-off-by: Rob Clark <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* draw: implement TGSI_PROPERTY_VS_WINDOW_SPACE_POSITIONMarek Olšák2014-12-0910-11/+49
| | | | | | | Required by Nine. Tested with util_run_tests. It's added to softpipe, llvmpipe, and r300g/swtcl. Tested-by: David Heidelberg <[email protected]>
* vc4: Reserve rb31 instead of r3 for raddr conflict spills.Eric Anholt2014-12-092-11/+45
| | | | | | | | | | This increases the cost of a raddr b conflict spill (save r3 to rb31, move src1 to r3, move rb31 back to r3 when done, instead of just move src1 to r3), but on average thanks to instruction pairing it's more worthwhile to have another accumulator. total instructions in shared programs: 46428 -> 46171 (-0.55%) instructions in affected programs: 38030 -> 37773 (-0.68%)
* vc4: Prioritize allocating accumulators to short-lived values.Eric Anholt2014-12-091-14/+59
| | | | | | | | | | | | | | | | | | The register allocator walks from the end of the nodes array looking for trivially-allocatable things to put on the stack, meaning (assuming everything is trivially colorable and gets put on the stack in a single pass) the low node numbers get allocated first. The things allocated first happen to get the lower-numbered registers, which is to say the fast accumulators that can be paired more easily. When we previously made the nodes match the temporary register numbers, we'd end up putting the shader inputs (VS or FS) in the accumulators, which are often long-lived values. By prioritizing the shortest-lived values for allocation, we can get a lot more instructions that involve accumulators, and thus fewer conflicts for raddr and WS. total instructions in shared programs: 52870 -> 46428 (-12.18%) instructions in affected programs: 52260 -> 45818 (-12.33%)
* r600g: fix regression since UCMP changeDave Airlie2014-12-091-1/+1
| | | | | | | | | | | | Since d8da6deceadf5e48201d848b7061dad17a5b7cac where the state tracker started using UCMP on cayman a number of tests regressed. this seems to be r600g is doing CNDGE_INT for UCMP which is >= 0, we should be doing CNDE_INT with reverse arguments. Reviewed-by: Glenn Kennard <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* Don't cast the return value of malloc/reallocMatt Turner2014-12-084-10/+8
| | | | | | | See commit 2b7a972e for the Coccinelle script. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Ian Romanick <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-25 13:14:35 +0000