summaryrefslogtreecommitdiffstats
path: root/src/gallium
Commit message (Collapse)AuthorAgeFilesLines
* radeon/llvm: document LLVM commitChristian König2013-03-071-0/+1
| | | | | | We need at least that revision to work correctly now. Signed-off-by: Christian König <[email protected]>
* radeon/llvm: enable LICM and DCE pass v2Christian König2013-03-071-0/+2
| | | | | | | | | | | | | LICM stands for Loop Invariant Code Motion. Instructions that does not depend of loop index are moved outside of loop body. DCE is DeadCodeElimination. v2: updated commit msg, thx to Vincent. Signed-off-by: Christian König <[email protected]> Reviewed-by: Vincent Lejeune <vljn at ovi.com> Reviewed-by: Tom Stellard <[email protected]>
* radeonsi: add LLVMNoUnwindAttribute to intrinsicChristian König2013-03-071-1/+1
| | | | | | | So LLVM can better eliminate dead code. Signed-off-by: Christian König <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* radeonsi: rework input interpolationChristian König2013-03-072-34/+72
| | | | | Signed-off-by: Christian König <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* radeonsi: remove SI.vs.load.buffer.indexChristian König2013-03-072-10/+12
| | | | | Signed-off-by: Christian König <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* radeon/llvm: make SGPRs proper function arguments v2Christian König2013-03-075-83/+63
| | | | | | | v2: remove unrelated changes Signed-off-by: Christian König <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* radeon/llvm: replace shader type intrinsic with function attributeChristian König2013-03-073-12/+26
| | | | | Signed-off-by: Christian König <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* radeonsi: switch to v*i8 for resources and samplers v2Christian König2013-03-071-18/+12
| | | | | | | v2: remove unrelated changes Signed-off-by: Christian König <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* r600g/llvm: Update CONSTANT_BUFFER address space definitionChristian König2013-03-071-1/+1
| | | | | | To match recent LLVM changes. Signed-off-by: Christian König <[email protected]>
* draw/llvm: fix inputs to the geometry shaderZack Rusin2013-03-051-4/+9
| | | | | | | | | | We can't clip and viewport transform the vertices before we let the geometry shader process them. Lets make sure the generated vertex shader has both disabled if geometry shader is present. Signed-off-by: Zack Rusin <[email protected]> Reviewed-by: Brian Paul <[email protected]> Reviewed-by: José Fonseca <[email protected]>
* draw: use geometry shader info in clip_init_state if appropriateBryan Cain2013-03-051-6/+9
| | | | | | Reviewed-by: Zack Rusin <[email protected]> Reviewed-by: Brian Paul <[email protected]> Reviewed-by: José Fonseca <[email protected]>
* draw: account for separate shader objects in geometry shader codeBryan Cain2013-03-054-4/+32
| | | | | | | | | | | | | | | | The geometry shader code seems to have been originally written with the assumptions that there are the same number of VS outputs as GS outputs and that VS outputs are in the same order as their corresponding GS inputs. Since TGSI uses separate shader objects, these are both wrong assumptions. This was causing several valid vertex/geometry shader combinations to either render incorrectly or trigger an assertion. Conflicts: src/gallium/auxiliary/draw/draw_gs.c Reviewed-by: Zack Rusin <[email protected]> Reviewed-by: Brian Paul <[email protected]> Reviewed-by: José Fonseca <[email protected]>
* llvmpipe: fix incorrect 'j' array index in dummy texture codeBrian Paul2013-03-061-3/+3
| | | | | | Use 0 instead. Reviewed-by: Roland Scheidegger <[email protected]>
* llvmpipe: remove unused cmd_block_list structBrian Paul2013-03-061-4/+0
|
* llvmpipe: add some scene limit sanity check assertionsBrian Paul2013-03-061-0/+22
| | | | | | Note: This is a candidate for the stable branches. Reviewed-by: José Fonseca <[email protected]>
* llvmpipe: tweak CMD_BLOCK_MAX and LP_SCENE_MAX_SIZEBrian Paul2013-03-061-2/+8
| | | | | | | | | | | | | | | | | | | | We advertise a max texture/surfaces size of 8K x 8K but the old values for these limits didn't actually allow us to handle that surface size. For 8K x 8K we'll have 16384 bins. Each bin needs at least one cmd_block object which was 2192 bytes in size. Since 16384 * 2192 exceeded LP_SCENE_MAX_SIZE we'd silently fail in lp_scene_new_data_block() and not draw the complete scene. By reducing CMD_BLOCK_MAX to 29 we get nice 512-byte cmd_blocks. And by increasing LP_SCENE_MAX_SIZE to 9 MB we can allocate enough command blocks for 8K x 8K, plus a few regular data blocks. Fixes the (improved) piglit fbo-maxsize test. Note: This is a candidate for the stable branches. Reviewed-by: José Fonseca <[email protected]>
* radeon/llvm: fix trivial warningsChristian König2013-03-061-4/+3
| | | | Signed-off-by: Christian König <[email protected]>
* radeonsi: fix trivial warningChristian König2013-03-061-1/+0
| | | | Signed-off-by: Christian König <[email protected]>
* scons: Provide shorthand aliases for software winsyses.José Fonseca2013-03-053-0/+3
|
* tgsi: handle projection modifier for array textures.Roland Scheidegger2013-03-051-3/+11
| | | | | | | | | | | | | | This partly reverts 6ace2e41da7dded630d932d03bacb7e14a93d47a. Apparently with GL_MESA_texture_array fixed-function texturing with texture arrays is possible, and hence we have to handle TXP. (Though noone seems to know the semantics, softpipe now does what it did before, which is to NOT project the array coord, llvmpipe for instance however indeed does project the array coord. Unlike before it will project the comparison coord for shadow1d array, as that clearly was an error.) This fixes https://bugs.freedesktop.org/show_bug.cgi?id=61828. Reviewed-by: Brian Paul <[email protected]>
* u_blitter: don't create illegal shaders for 1D/3D/RECT/CUBE MSAADave Airlie2013-03-041-0/+5
| | | | | Reviewed-by: Marek Olšák <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* vdpau-softpipe: Build correct source file - vl_winsys_xsp.cJakub Bogusz2013-03-031-1/+1
| | | | | | Copy-and-paste problem introduced by commit 7f24483e. Reviewed-by: Matt Turner <[email protected]>
* r600g: Check comp_mask before merging export instructionsVincent Lejeune2013-03-031-0/+1
| | | | | Fixes a llvm uncovered (rare) bug where consecutive exports were merged even if they have incompatible mask.
* r600g: fix check_and_set_bank_swizzle for caymanVadim Girlin2013-03-031-7/+3
| | | | | Tested-by: Vincent Lejeune <vljn at ovi.com> Reviewed-by: Vincent Lejeune <vljn at ovi.com>
* tgsi: add texel offsets and derivatives to sampler interfaceRoland Scheidegger2013-03-023-80/+194
| | | | | | | | | | | | | | | | | | | | | | | | Something I never got around to implement, but this is the tgsi execution side for implementing texel offsets (for ordinary texturing) and explicit derivatives for sampling (though I guess the ordering of the components for the derivs parameters is debatable). There is certainly a runtime cost associated with this. Unless there are different interfaces used depending on the "complexity" of the texture instructions, this is impossible to avoid. Offsets are always active (I think checking if they are active or not is probably not worth it since it should mostly be an add), whereas the sampler_control is extended for explicit derivatives. For now softpipe (the only user of this) just drops all those new values on the floor (which is the part I never implemented...). Additionally this also fixes (discovered by accident) inconsistent projective divide for the comparison coord - the code did do the projection for shadow2d targets, but not shadow1d ones. This also drops checking for projection modifier on array targets, since they aren't possible in any extension I know of (hence we don't actually know if the array layer should also be divided or not). Reviewed-by: Brian Paul <[email protected]>
* draw: additional fix for the no-position case with llvmRoland Scheidegger2013-03-021-20/+20
| | | | | | | | Similar fix to what is done for the non-llvm case, we could otherwise still hit the stages (near certainly with gs) which crash. It is probably a much better idea to skip trying to draw at that point anyway. Reviewed-by: Brian Paul <[email protected]>
* draw: fix no position output in non-llvm pipeline.Roland Scheidegger2013-03-021-19/+19
| | | | | | | | | | It seems easiest (and best) if we simply skip all the later stages (after stream output). (This is different to the llvm case at least for now where we will simply try to render garbage, though both behaviors should be correct.) Fixes piglit glsl-1.40-tf-no-position with softpipe. Reviewed-by: Brian Paul <[email protected]>
* draw/llvm: skip clipping and viewport transform if there's no position outputRoland Scheidegger2013-03-021-26/+31
| | | | | | | | | | | | | With glsl 1.40 writing position is not required (useful for transform feedback, though in fact it's still possible to rasterize such geometry even if the results aren't too well defined). Prevents crashes in that case. Fixes piglit glsl-1.40-tf-no-position. Not quite sure this is 100% correct as it also skips clipdistance clipping which could still work (but not sure if the result would really be needed?) Reviewed-by: Jose Fonseca <[email protected] Reviewed-by: Brian Paul <[email protected]>
* llvmpipe: don't assert on illegal surface creation.Roland Scheidegger2013-03-022-4/+4
| | | | | | | | | | | | Since c8eb2d0e829d0d2aea6a982620da0d3cfb5982e2 llvmpipe checks if it's actually legal to create a surface. The opengl state tracker doesn't quite obey this so for now just warn instead of assert. Also warn instead of disabled assert when creating sampler views (same reasoning). Addresses https://bugs.freedesktop.org/show_bug.cgi?id=61647. Reviewed-by: Jose Fonseca <[email protected]>
* llvmpipe: bump glsl version to 140Roland Scheidegger2013-03-022-12/+5
| | | | | | | | | | | | | texel offsets should have been the last missing feature for 130, and in fact 140 as well (last there were texture buffers). In any case we still don't do OpenGL 3.0 (missing MSAA which will be difficult, plus EXT_packed_float, ARB_depth_buffer_float and EXT_framebuffer_sRGB). v2: bump to 140 instead - we have everything except we crash when not writing to gl_Position (but softpipe crashes as well) so let's just say this is a bug instead. Also (by Dave Airlie's suggestion) update llvm-todo.txt. Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: add support for texel offsets for ordinary texturing.Roland Scheidegger2013-03-023-53/+210
| | | | | | | | | | | | | | | | | | This was previously only handled for texelFetch (much easier). Depending on the wrap mode this works slightly differently (for somewhat efficient implementation), hence have to do that separately in all roughly 137 places - it is easy if we use fixed point coords for wrapping, however some wrapping modes are near impossible with fixed point (the repeat stuff) hence we have to normalize the offsets if we can't do the wrapping in unnormalized space (which is a division which is slow but should still be much better than the alternative, which would be integer modulo for wrapping which is just unusable). This should still give accurate results in all cases that really matter, though it might be not quite conformant behavior for some apis (but we have much worse problems there anyway even without using offsets). (Untested, no piglit test.) Reviewed-by: Jose Fonseca <[email protected]>
* svga: always link with C++Brian Paul2013-03-011-5/+1
| | | | | | | | | Even when we don't have LLVM since there's other C++ code in the resulting DRI driver object. Note: This is a candidate for the stable branches. Reviewed-by: Matt Turner <[email protected]>
* winsys/radeon: Only add bo to hash table when creating flinkMartin Andersson2013-03-011-4/+4
| | | | | | | | | | | | | The problem is that we mix bo handles and flinked names in the hash table. Because kms type handles are not flinked they should not be added to the hash table. If we do that we will sooner or later get a situation where we will overwrite a correct entry because the bo handle was the same as a flinked name. Note: this is a candidate for the stable branches. Reviewed-by: Jerome Glisse <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
* r600g: enable CP DMA on 6xxAlex Deucher2013-03-011-1/+1
| | | | | | Tested across several 6xx parts, no piglit regressions. Signed-off-by: Alex Deucher <[email protected]>
* r600g: don't require dword alignment with CP DMA for buffer transfersMarek Olšák2013-03-015-11/+9
| | | | | | which is a leftover from the days when we used streamout to copy buffers Tested-by: Andreas Boll <[email protected]>
* r600g: always map uninitialized buffer range as unsynchronizedMarek Olšák2013-03-016-0/+45
| | | | | | | | | | Any driver can implement this simple and efficient optimization. Team Fortress 2 hits it always. The DISCARD_RANGE codepath is not even used with TF2 anymore, so we avoid a ton of useless buffer copies. Tested-by: Andreas Boll <[email protected]> NOTE: This is a candidate for the 9.1 branch.
* gallium/util: add helper code for 1D integer rangeMarek Olšák2013-03-011-0/+89
| | | | | | | | | | Reviewed-by: Brian Paul <[email protected]> v2: cosmetic changes based on Brian's review Tested-by: Andreas Boll <[email protected]> NOTE: This is a candidate for the 9.1 branch. (the next patch depends on it)
* r600g: cleanup deprecated register tablesMarek Olšák2013-03-013-45/+14
| | | | | | These registers are either already emitted elsewhere or moved to start_cs. Tested-by: Andreas Boll <[email protected]>
* r600g: unify vgt statesMarek Olšák2013-03-015-26/+9
| | | | | | | The states were split because we thought it caused a hardlock. Now we know the hardlock was caused by something else and has since been fixed. Tested-by: Andreas Boll <[email protected]>
* r600g: flush and invalidate htile cache when appropriateMarek Olšák2013-03-016-1/+21
| | | | | | Tested-by: Andreas Boll <[email protected]> NOTE: This is a candidate for the 9.1 branch.
* r600g: atomize streamout enablingMarek Olšák2013-03-019-87/+96
| | | | | | | | | | | | This doesn't fix any issue we know of, but there indeed is a week spot in draw_vbo where streamout can fail. After streamout is enabled, the need_cs_space call can flush the context, which causes the streamout to be disabled right after it was enabled and bad things happen. One way to fix it is to atomize the beginning part, so that no context flush can happen between streamout enabling and the first drawing. Tested-by: Andreas Boll <[email protected]>
* r600g: use async DMA with a non-zero src offsetMarek Olšák2013-03-011-1/+1
| | | | | | | | probably a typo Tested-by: Andreas Boll <[email protected]> NOTE: This is a candidate for the 9.1 branch.
* r600g: pad the DMA CS to a multiple of 8 dwordsMarek Olšák2013-03-011-2/+14
| | | | | | Tested-by: Andreas Boll <[email protected]> NOTE: This is a candidate for the 9.1 branch.
* clover: Fix build with LLVM 3.3 v2Tom Stellard2013-02-282-9/+40
| | | | | | | | v2: - Fix order that the clang libraries are passed to the linker to avoid missing symbol errors. Acked-by: Francisco Jerez <[email protected]>
* r600g: workaround hyperz lockup on evergreenJerome Glisse2013-02-284-2/+23
| | | | | | | | | | | This work around disable hyperz if write to zbuffer is disabled. Somehow using hyperz when not writting to the zbuffer trigger GPU lockup. See : https://bugs.freedesktop.org/show_bug.cgi?id=60848 Candidate for 9.1 Signed-off-by: Jerome Glisse <[email protected]>
* llvmpipe: check buffers in llvmpipe_is_resource_referenced.Roland Scheidegger2013-02-283-8/+24
| | | | | | | | | | | Now that buffers can be used as textures or render targets make sure they aren't skipped. Fix suggested by Jose Fonseca. v2: added a couple of assertions so we can actually guarantee we check the resources and don't skip them. Also added some comments that this is actually a lie due to the way the opengl buffer api works.
* llvmpipe: support rendering to buffer render targets.Roland Scheidegger2013-02-284-47/+61
| | | | | | | | | | Unfortunately not usable from OpenGL, and no cap bit. Pretty similar to a 1d texture, though allows specifying a start element. v2: also fix up renderbuffer width (which will get promoted to fb width) to be the number of elements Reviewed-by: Jose Fonseca <[email protected]>
* util: fix issues with util_clear_render_target.Roland Scheidegger2013-02-281-9/+46
| | | | | | | | For PIPE_BUFFER we need coord adjustments for the transfer. And for pure integer formats util_pack_color just crashes, need to handle that differently due to clear colors being ints/uints. Reviewed-by: Jose Fonseca <[email protected]>
* softpipe/draw/tgsi: simplify driver/tgsi sampler interfaceRoland Scheidegger2013-02-2815-189/+249
| | | | | | | | | | | | | | | Use a single sampler adapter instead of per-sampler-unit samplers, and just pass along texture unit and sampler unit in the calls. The reason is that for dx10-style sample opcodes pre-wired samplers including all the texture state aren't really feasible (and for sample_i/sviewinfo we don't even have samplers). Of course right now softpipe doesn't actually do anything more than just look up all its pre-wired per-texunit/per-samplerunit sampler as it did before so this doesn't really achieve much except one more function call, however this is now all softpipe's fault (fixing that in a way which doesn't suck is still an unsolved problem). Reviewed-by: Jose Fonseca <[email protected]>
* gallivm: fix mis-matching AOS instruction emissionMaxence Le Doré2013-02-271-1/+1
| | | | Signed-off-by: José Fonseca <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 10:28:13 +0000