summaryrefslogtreecommitdiffstats
path: root/src/gallium
Commit message (Collapse)AuthorAgeFilesLines
* r600g: move r6xx-specific streamout flush flagging into r600gMarek Olšák2015-01-072-9/+7
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: only set BC_OPTIMIZE_DISABLE when necessaryMarek Olšák2015-01-072-6/+15
| | | | | | SPI_PS_IN_CONTROL is moved into the SPI mapping state. Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: do not define FACE as an ordinary PS inputMarek Olšák2015-01-071-1/+2
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: remove flatshade from the shader keyMarek Olšák2015-01-073-7/+7
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: remove special handling of TGSI_INTERPOLATE_COLOR in shader codegenMarek Olšák2015-01-071-6/+10
| | | | | | | | It doesn't do anything useful. And colors are floating-point, so we can use fs.interp, remove "flatshade" from the shader key, and rely on the FLAT_SHADE state only (in the next patch). Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: implement VERTEXID_NOBASE and BASEVERTEX system valuesMarek Olšák2015-01-071-0/+10
| | | | | | | | Only done for completeness. Not used by anything yet. Tested by advertising PIPE_CAP_VERTEXID_NOBASE. Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: fix VertexID for OpenGLMarek Olšák2015-01-071-2/+5
| | | | | | | This fixes all failing piglit VertexID tests. Cc: 10.4 <[email protected]> Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: clarify a hw bug in shader exportsMarek Olšák2015-01-071-5/+10
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: use ordered compares for SSG and face selectionMarek Olšák2015-01-072-3/+3
| | | | | | | | | | | Ordered compares are what you have in C. Unordered compares are the result of negating ordered compares (they return true if either argument is NaN). That special NaN behavior is completely useless here, and unordered compares produce horrible code with all stable LLVM versions. (I think that has been fixed in LLVM git) Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: remove unused and not useful variablesMarek Olšák2015-01-073-6/+1
| | | | Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: remove init config from statesMarek Olšák2015-01-076-5/+4
| | | | | | It really doesn't do anything there. Reviewed-by: Michel Dänzer <[email protected]>
* radeonsi: reduce the size of si_pm4_stateMarek Olšák2015-01-072-12/+3
| | | | | | | | - the relocs array is unused, remove it - ndw is at most 115 (init), set 140 as the maximum - compute needs 4 buffers per state, graphics only needs 1; set 4 as the maximum Reviewed-by: Michel Dänzer <[email protected]>
* tgsi: add uses_centroid into tgsi_shader_infoMarek Olšák2015-01-072-0/+4
|
* vc4: Fix scaling W projection of the Z coordinate when there's a Z offset.Eric Anholt2015-01-061-3/+3
| | | | | | Fixes piglit glsl-fs-fragcoord-zw-perspective, es3conform gl_FragCoord_z_frag, and the rest of the piglit glsl 1.10 interpolation tests.
* vc4: Fix deletion from the program cache.Eric Anholt2015-01-061-1/+1
| | | | | They key is, oddly enough, in the key field, not in the data field (which is the vc4_compiled_shader *). Fixes regular failures in fp-long-alu.
* vc4: Skip storing the Z/S contents when it's invalidated.Eric Anholt2015-01-061-0/+11
| | | | | | | Improves framerate of 5 seconds of es2gears by 1.57473% +/- 0.669409% (n=67). Reviewed-by: Jose Fonseca <[email protected]>
* gallium: Plumb the swap INVALIDATE_ANCILLARY flag through more layers.Eric Anholt2015-01-062-0/+17
| | | | | | | | | v2: Instead of telling the driver that the window system ancillaries have been invalidated (when the driver doesn't know which of its buffers are the window system's!), introduce a method for invalidating specific surfaces. Reviewed-by: Jose Fonseca <[email protected]>
* radeon/llvm: Use amdgcn triple for SI+ on LLVM >= 3.6Tom Stellard2015-01-064-16/+27
|
* radeonsi: Cache LLVMTargetMachine object in si_screenTom Stellard2015-01-066-26/+51
| | | | | | | | | | Rather than building a new one every compile. This should reduce some of the overhead of compiling shaders. One consequence of this change is that we lose the MachineInstrs dumps when dumping the shaders via R600_DEBUG. The LLVM IR and assembly is still dumped, and if you still want to see the MachineInstr dump, you can run the dumped LLVM IR through llc.
* draw: silence uninitialized variable warningBrian Paul2015-01-051-1/+1
| | | | | | v2: move initialization of llvm_gs to declaration. Reviewed-by: Roland Scheidegger <[email protected]>
* gallivm: silence a couple compiler warningsBrian Paul2015-01-052-1/+4
| | | | | | | Silence warnings about possibly uninitialized variables when making a release build. Reviewed-by: José Fonseca <[email protected]>
* gallium/util: make sure cache line size is not zeroLeonid Shatz2015-01-051-1/+5
| | | | | | | | | | The "normal" detection (querying clflush size) already made sure it is non-zero, however another method did not. This lead to crashes if this value happened to be zero (apparently can happen in virtualized environments at least). This fixes https://bugs.freedesktop.org/show_bug.cgi?id=87913 Cc: "10.4" <[email protected]>
* gallium/util: fix crash with daz detection on x86Roland Scheidegger2015-01-051-1/+1
| | | | | | | | | | The code used PIPE_ALIGN_VAR for the variable used by fxsave, however this does not work if the stack isn't aligned. Hence use PIPE_ALIGN_STACK function decoration to fix the segfault which can happen if stack alignment is only 4 bytes. This fixes https://bugs.freedesktop.org/show_bug.cgi?id=87658. Cc: "10.4" <[email protected]>
* nvc0: add name to magic numberIlia Mirkin2015-01-051-2/+2
| | | | Signed-off-by: Ilia Mirkin <[email protected]>
* nvc0: regenerate rnndb headersIlia Mirkin2015-01-0517-837/+1157
| | | | | | | | | | | | | | | The headers hadn't been regenerated in a long time and had seen a number of manual modifications. A few changes: - remove nvc0_2d entirely, use the nv50 header which has the nvc0 values too - remove 3ddefs, it's identical to the nv50 file - move macros out into a separate file Also the upstream rnndb changed the overall chip naming convention; this was fixed up manually in the generated files until a better solution is determined. Signed-off-by: Ilia Mirkin <[email protected]>
* nv50: regenerate rnndb headersIlia Mirkin2015-01-0511-358/+451
| | | | | | | | | | The headers hadn't been regenerated in a long time, and there were a few minor divergences. Among other things, rnndb has changed naming to G80/etc, for now I've not tackled switching that over and manually replaced the nvidia codenames back to the chip ids. However no other modifications of the headergen'd headers was done. Signed-off-by: Ilia Mirkin <[email protected]>
* nv50: enable texture compressionTobias Klausmann2015-01-052-3/+26
| | | | | | | | | Compression seems to be supported for only some formats. Enable it for those. Previously this was disabled for everything despite the code looking like it was actually enabled. Signed-off-by: Tobias Klausmann <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nv50/ir: enable sat modifier for OP_SUBIlia Mirkin2015-01-051-1/+1
| | | | | | | SUB is handled the same as ADD, so no reason not to allow a saturate modifier on it. Signed-off-by: Ilia Mirkin <[email protected]>
* nv50/ir: Add sat modifier for mulRoy Spliet2015-01-052-1/+7
| | | | | Signed-off-by: Roy Spliet <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nv50,nvc0: avoid doing work inside of an assertIlia Mirkin2015-01-052-2/+4
| | | | | | | | assert is compiled out in release builds - don't put logic into it. Note that this particular instance is only used for vp debugging and is normally compiled out. Signed-off-by: Ilia Mirkin <[email protected]>
* nv50/ir: fix texture offsets in release buildsIlia Mirkin2015-01-052-2/+4
| | | | | | | | | | assert's get compiled out in release builds, so they can't be relied upon to perform logic. Reported-by: Pierre Moreau <[email protected]> Signed-off-by: Ilia Mirkin <[email protected]> Tested-by: Roy Spliet <[email protected]> Cc: "10.2 10.3 10.4" <[email protected]>
* r300g: handle vertex format PIPE_FORMAT_NONEMarek Olšák2015-01-041-2/+11
|
* nv50/ir: Fold sat into madRoy Spliet2015-01-011-1/+1
| | | | | | | | | The mad instruction emitter already supported the saturate modifier, but the ModifierFolding pass never tried folding cvt sat operations in for NV50. Signed-off-by: Roy Spliet <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* nv50/ir: fold MAD when one of the multiplicands is constIlia Mirkin2015-01-011-0/+23
| | | | | | | | | | Fold MAD dst, src0, immed, src2 (or src0/immed swapped) when - immed = 0 -> MOV dst, src2 - immed = +/- 1 -> ADD dst, src0, src2 These types of MAD patterns were observed in some st/nine shaders. Signed-off-by: Ilia Mirkin <[email protected]>
* gallium/state_tracker: Rewrite Haiku's state trackerAlexander von Gluck IV2015-01-017-190/+274
| | | | | * More gallium-like * Leverage stamps properly and don't call mesa functions
* radeonsi: fix warningsMarek Olšák2015-01-012-1/+3
|
* u_primconvert: Fix leak of the upload BO on context destroy.Eric Anholt2014-12-311-0/+2
| | | | | | | v2: Conditionalize it on having done any uploads (Turns out u_upload_destroy() isn't safe with a NULL arg). Reviewed-by: Dave Airlie <[email protected]> (v1)
* vc4: Fix memory leak as of 0404e7fe0ac2a6234a11290b4b1596e8bc127a4b.Eric Anholt2014-12-311-5/+5
| | | | Can't reset the CL before looking at how much we had pupt in it.
* nv50,nvc0: set vertex id base to index_biasIlia Mirkin2014-12-305-7/+35
| | | | | | | | | | | | | | Fixes the piglits which check that gl_VertexID includes the base vertex offset: arb_draw_indirect-vertexid elements gl-3.2-basevertex-vertexid Note that this leaves out the original G80, for which this will continue to fail. It could be fixed by passing a driver constbuf value in, but that's beyond the scope of this change. Signed-off-by: Ilia Mirkin <[email protected]> Cc: "10.3 10.4" <[email protected]>
* nv50,nvc0: implement half_pixel_centerTiziano Bacocco2014-12-308-14/+11
| | | | | | | | | | LAST_LINE_PIXEL has actually been renamed to PIXEL_CENTER_INTEGER in rnndb; use that method to implement the rasterizer setting, used for st/nine. Signed-off-by: Tiziano Bacocco <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]> Cc: "10.4" <[email protected]>
* vc4: Only render tiles where the scissor ever intersected them.Eric Anholt2014-12-304-10/+52
| | | | | This gives a 2.7x improvement in x11perf -rect100, since we only end up load/storing the x11perf window, not the whole screen.
* vc4: Move draw call reset handling to a helper function.Eric Anholt2014-12-301-23/+31
| | | | | | This will be more important in the next commit, when there's more state to reset to nonzero values, and I want an early exit from the submit function.
* vc4: Drop the content of vc4_flush_resource().Eric Anholt2014-12-301-4/+4
| | | | | The callers all follow it with a flush of the context, and the flush of the context gives us more information about how things are being flushed.
* gallium/target: Drop no longer needed Haiku viewport overrideAlexander von Gluck IV2014-12-271-30/+1
| | | | | * Drop no longer needed mesa headers * Haiku LLVM pipe working with LLVM 3.5.0 on x86_64
* gallium/st: Clean up Haiku depth mapping, fix colorspace errorsAlexander von Gluck IV2014-12-271-29/+19
|
* vc4: Handle unaligned accesses in CL emits.Eric Anholt2014-12-252-26/+78
| | | | | | | As of 229bf4475ff0a5dbeb9bc95250f7a40a983c2e28 we started getting SIBGUS from unaligned accesses on the hardware, for reasons I haven't figured out. However, we should be avoiding unaligned accesses anyway, and our CL setup certainly would have produced them.
* vc4: Don't bother zero-initializing the shader reloc indices.Eric Anholt2014-12-251-2/+2
| | | | | They should all be set to real values by the time they're read, and ideally if you used valgrind you'd see uninitialized value uses.
* vc4: Fix the argument type for cl_u16().Eric Anholt2014-12-251-1/+1
| | | | It doesn't matter, since it just got truncated to 16 inside, anyway.
* radeonsi: Don't modify PA_SC_RASTER_CONFIG register value if rb_mask == 0Michel Dänzer2014-12-251-2/+4
| | | | | | | | | | | E.g. this could happen on older kernels which don't support the RADEON_INFO_SI_BACKEND_ENABLED_MASK query yet. The code in si_write_harvested_raster_configs() doesn't deal with this correctly and would probably mangle the value badly. Cc: "10.4 10.3" <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* vc4: Optimize CL emits by doing size checks up front.Eric Anholt2014-12-245-16/+66
| | | | | | | | The optimizer obviously doesn't have the ability to rewrite these to skip the size checks per call, so we have to do it manually. Improves a norast benchmark on simulation by 0.779706% +/- 0.405838% (n=6087).
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 10:28:36 +0000