summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* radeonsi: add environment variable SI_FORCE_FAMILYMarek Olšák2016-08-061-0/+32
| | | | | | | | This will be used by: amdgcn_glslc -mcpu=[family] It can also be used for shader-db if you want stats for a different family. Reviewed-by: Nicolai Hähnle <[email protected]>
* winsys/radeon: implement cs_get_next_fenceMarek Olšák2016-08-062-2/+29
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* winsys/amdgpu: implement cs_get_next_fenceMarek Olšák2016-08-062-4/+35
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: add cs_get_next_fence winsys callbackMarek Olšák2016-08-061-0/+7
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: count contextsMarek Olšák2016-08-062-0/+4
| | | | | | We don't wanna use unflushed fences when we have multiple contexts. Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: count gfx IB flushesMarek Olšák2016-08-063-1/+3
| | | | | | | This will be used as a counter for whether fence_finish needs to flush the IB. Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: move radeon_winsys::cs_memory_below_limit to driversMarek Olšák2016-08-067-52/+32
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: inline radeon_winsys::query_memory_usageMarek Olšák2016-08-064-15/+1
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon/winsyses: expose per-IB used_vram and used_gart to driversMarek Olšák2016-08-065-25/+24
| | | | | | The following patches will use this. Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon/winsyses: print CS submission error numberMarek Olšák2016-08-062-2/+2
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: flush if constant, shader, and streamout buffers use too much memoryMarek Olšák2016-08-061-15/+18
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: flush if sampler views and images use too much memoryMarek Olšák2016-08-062-19/+63
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: deal with high vertex buffer memory usage correctlyMarek Olšák2016-08-063-3/+10
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: take compute shader and dispatch indirect memory usage into accountMarek Olšák2016-08-061-0/+6
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: take scratch buffer and draw indirect memory usage into accountMarek Olšák2016-08-061-0/+6
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: check IB memory usage of CP DMA operationsMarek Olšák2016-08-061-0/+5
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* gallium/radeon: add r600_resource::vram_usage and gart_usageMarek Olšák2016-08-063-12/+19
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* mesa: Copy bitmask of VBOs in the VAO on gl{Push,Pop}Attrib.Mathias Fröhlich2016-08-061-0/+2
| | | | | | | | | | | On gl{Push,Pop}Attrib(GL_CLIENT_VERTEX_ARRAY_BIT) take care that gl_vertex_array_object::VertexAttribBufferMask matches the bound buffer object in the gl_vertex_array_object::VertexBinding array. Signed-off-by: Mathias Fröhlich <[email protected]> Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Fredrik Höglund <[email protected]>
* anv/gen7_pipeline: Set PixelShaderKillPixel for discardsNanley Chery2016-08-051-0/+1
| | | | | | | | | | According to the IVB PRM Vol2 P1, this bit must be set if a pixel shader contains a discard instruction. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97207 Cc: "12.0" <[email protected]> Signed-off-by: Nanley Chery <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* util/r11g11b10f: Whitespace cleanupsJason Ekstrand2016-08-051-14/+7
| | | | | Signed-off-by: Jason Ekstrand <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* util/format: Use explicitly sized typesJason Ekstrand2016-08-052-6/+8
| | | | | | | | | Both the rgb9e5 and r11g11b10 formats are defined based on how they are packed into a 32-bit integer. It makes sense that the functions that manipulate them take an explicitly sized type. Signed-off-by: Jason Ekstrand <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* util/rgb9e5: Get rid of the float754 unionJason Ekstrand2016-08-051-42/+27
| | | | | | | | | | | There are a number of reasons for this refactor. First, format_rgb9e5.h is not something that a user would expect to define such a generic union. Second, defining it requires checking for endianness which is ugly. Third, 90% of what we were doing with the union was float <-> uint32_t bitcasts and the remaining 10% can be done with a sinmple left-shift by 23. Signed-off-by: Jason Ekstrand <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* util/format_rgb9e5: Get rid of the rgb9e5 unionJason Ekstrand2016-08-051-32/+6
| | | | | | | | | The rgb9e5 format is a packed format defined in terms of slicing up a single 32-bit value. The bitfields are far more confusing than simple shifts and require that we check the endianness. Signed-off-by: Jason Ekstrand <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* util: Move format_r11g11b10f.h to src/utilJason Ekstrand2016-08-0510-8/+8
| | | | | | | It's used from both mesa main and gallium. Signed-off-by: Jason Ekstrand <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* util: Move format_rgb9e5.h to src/utilJason Ekstrand2016-08-0510-8/+8
| | | | | | | It's used from both mesa main and gallium. Signed-off-by: Jason Ekstrand <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* glsl: fix indentation, comments and line lengths in ast_function.cppAndres Gomez2016-08-051-406/+443
| | | | | Acked-by: Timothy Arceri <[email protected]> Signed-off-by: Andres Gomez <[email protected]>
* glsl: apply_implicit_conversion is static againAndres Gomez2016-08-052-5/+1
| | | | | Reviewed-by: Timothy Arceri <[email protected]> Signed-off-by: Andres Gomez <[email protected]>
* glsl: struct constructors/initializers only allow implicit conversionsAndres Gomez2016-08-051-49/+55
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When an argument for a structure constructor or initializer doesn't match the expected type, only Section 4.1.10 “Implicit Conversions” are allowed to try to match that expected type. From page 32 (page 38 of the PDF) of the GLSL 1.20 spec: " The arguments to the constructor will be used to set the structure's fields, in order, using one argument per field. Each argument must be the same type as the field it sets, or be a type that can be converted to the field's type according to Section 4.1.10 “Implicit Conversions.”" From page 35 (page 41 of the PDF) of the GLSL 4.20 spec: " In all cases, the innermost initializer (i.e., not a list of initializers enclosed in curly braces) applied to an object must have the same type as the object being initialized or be a type that can be converted to the object's type according to section 4.1.10 "Implicit Conversions". In the latter case, an implicit conversion will be done on the initializer before the assignment is done." v2: Remove also the now redundant constant conversion, the constant_record_constructor helper and the replacement code (Timothy). Fixes GL44-CTS.shading_language_420pack.initializer_list_negative Reviewed-by: Timothy Arceri <[email protected]> Signed-off-by: Andres Gomez <[email protected]>
* glsl: Refactor implicit conversion into its own helperAndres Gomez2016-08-051-80/+86
| | | | | | | | v2: Refactor also the conversion to constant and replacement code (Timothy). Reviewed-by: Timothy Arceri <[email protected]> Signed-off-by: Andres Gomez <[email protected]>
* glsl/types: disallow implicit conversions before GLSL 1.20Andres Gomez2016-08-051-4/+4
| | | | | | | | | Implicit conversions were added in the GLSL 1.20 spec version. v2: Join the checks for GLSL 1.10 and ESSL (Timothy). Reviewed-by: Timothy Arceri <[email protected]> Signed-off-by: Andres Gomez <[email protected]>
* i965: Rework the unlit centroid workaround.Kenneth Graunke2016-08-052-25/+33
| | | | | | | | | | | | | | | | | | | | | | | Previously, for every input, we moved the dispatch mask to the flag register, then emitted two predicated PLN instructions, one with centroid barycentric coordinates (for normal pixels), and one with pixel barycentric coordinates (for unlit helper pixels). Instead, we can simply emit a set of predicated MOVs at the top of the program which copy the pixel barycentric coordinates over the centroid ones for unlit helper pixel channels. Then, we can just use normal PLNs. On Sandybridge: total instructions in shared programs: 7538470 -> 7534500 (-0.05%) instructions in affected programs: 101268 -> 97298 (-3.92%) helped: 705 HURT: 9 (all of which are SIMD16 programs) Signed-off-by: Kenneth Graunke <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]> Reviewed-by: Matt Turner <[email protected]>
* swr: [rasterizer core] static analysis fixes for conservative rastTim Rowley2016-08-042-5/+10
| | | | Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer core] implement InnerConservative input coverageTim Rowley2016-08-046-182/+357
| | | | Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer core] remove CanEarlyZ functionTim Rowley2016-08-041-6/+0
| | | | | | Test is now in SetupPipeline. Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer core] use 32x32 macrotile for openswrTim Rowley2016-08-041-4/+4
| | | | | | Significant performance increase (up to 2x) on high geometry workloads. Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer fetch] add support for 24bit format fetchTim Rowley2016-08-041-0/+1
| | | | Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer fetch] additional fetch format supportTim Rowley2016-08-041-3/+15
| | | | | | | | Add support for 0 pitch in fetch. Add support for USCALE/SSCALE for 32bit integer fetches. Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer jitter] fix potential jit exit crashTim Rowley2016-08-041-1/+6
| | | | Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer core] update sync handlingTim Rowley2016-08-045-15/+15
| | | | | | | | Sync now uses a callback to ensure that it's called by the last thread moving past a DC. This will help with the new counter handling. Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer core] rename variableTim Rowley2016-08-041-7/+7
| | | | | | Avoid nested declarations of the same name within a single function. Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer jitter] adjust extern "C" block scopeTim Rowley2016-08-041-3/+5
| | | | Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer core] conservative rast degenerate handlingTim Rowley2016-08-045-144/+332
| | | | Signed-off-by: Tim Rowley <[email protected]>
* swr: [rasterizer core] allow hexadecimal for integer knobsTim Rowley2016-08-041-3/+6
| | | | Signed-off-by: Tim Rowley <[email protected]>
* mesa: Dynamically allocate the matrix stack.Eric Anholt2016-08-042-4/+25
| | | | | | | | | | | | | By allocating and initializing the matrices at context creation, the OS couldn't even overcommit the pages. This saves about 63k (out of 946k) of maximum memory size according to massif on simulated vc4 glsl-algebraic-add-add-1. It also means we could potentially relax the maximum stack sizes, but that should be a separate commit. v2: Drop redundant Top update, explain why the stack is small at init time. Reviewed-by: Brian Paul <[email protected]>
* state_tracker: Initialize the draw context only when needed.Eric Anholt2016-08-045-12/+36
| | | | | | | | | | | It's only used for rarely-used deprecated GL features (feedback/rasterpos), so we can skip the memory allocation and initialization for it most of the time. Saves about 659k (out of 1605k) of maximum memory size according to massif on simulated vc4 glsl-algebraic-add-add-1 Reviewed-by: Brian Paul <[email protected]>
* vc4: Move scalarizing and some lowering to link time.Eric Anholt2016-08-041-5/+12
| | | | | | | This works out to be a wash in terms of memory usage: We use more memory to store the separate ALU instructions, but we optimize out a lot of code as well. The main result, though, is that we do more of our work at link time rather than draw time.
* vc4: Avoid VS shader recompiles by keeping a set of FS inputs seen so far.Eric Anholt2016-08-043-25/+81
| | | | | | | | | | | | We don't want to bake the whole array into the FS key, because of the hashing overhead. But we can keep a set of the arrays seen, and use a pointer to the copy in as the array's proxy. Between this and the previous patch, gl-1.0-blend-func now passes on hardware, where previously it was filling the 256MB CMA area with shaders and OOMing. Drops 712 shaders from shader-db.
* vc4: Don't recompile the CS when the FS changes.Eric Anholt2016-08-041-0/+2
| | | | | | | The compiled_fs_id is a proxy for the vc4->prog.fs->input_slots[], but only the VS dereferences it. Drops 754 shaders from shader-db.
* vc4: Move FS inputs setup out to a helper function.Eric Anholt2016-08-041-34/+41
| | | | It's a pretty big block, and I was about to make it bigger.
* nir: Make nir_opt_remove_phis see through moves.Kenneth Graunke2016-08-041-1/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I found a shader in Tales of Maj'Eyal that contains: if ssa_21 { block block_1: /* preds: block_0 */ ...instructions that prevent the select peephole... vec1 32 ssa_23 = imov ssa_4 vec1 32 ssa_24 = imov ssa_4.y vec1 32 ssa_25 = imov ssa_4.z /* succs: block_3 */ } else { block block_2: /* preds: block_0 */ vec1 32 ssa_26 = imov ssa_4 vec1 32 ssa_27 = imov ssa_4.y vec1 32 ssa_28 = imov ssa_4.z /* succs: block_3 */ } block block_3: /* preds: block_1 block_2 */ vec1 32 ssa_29 = phi block_1: ssa_23, block_2: ssa_26 vec1 32 ssa_30 = phi block_1: ssa_24, block_2: ssa_27 vec1 32 ssa_31 = phi block_1: ssa_25, block_2: ssa_28 Here, copy propagation will bail because phis cannot perform swizzles, and CSE won't do anything because there is no dominance relationship between the imovs. By making nir_opt_remove_phis handle identical moves, we can eliminate the phis and rewrite everything to use ssa_4 directly, so all the moves become dead and get eliminated. I don't think we need to check "exact" - just the alu sources. Presumably phi sources should match in their exactness. On Broadwell: total instructions in shared programs: 11639872 -> 11638535 (-0.01%) instructions in affected programs: 134222 -> 132885 (-1.00%) helped: 338 HURT: 0 v2: Fix return value to be NULL, not false (caught by Iago). Signed-off-by: Kenneth Graunke <[email protected]> Reviewed-by: Iago Toral Quiroga <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-26 11:57:18 +0000