summaryrefslogtreecommitdiffstats
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
* tgsi/scan: set if a fragment shader writes sample maskMarek Olšák2016-01-072-0/+3
| | | | | | This will be used by radeonsi. Reviewed-by: Nicolai Hähnle <[email protected]>
* glsl: Disallow vectorization of vector_insert/extract.Kenneth Graunke2016-01-061-0/+2
| | | | | | | | | | | | | | | | | | vector_insert takes a vector, a scalar location, and a scalar value, and produces a new vector with that component updated. As such, it can't be vectorized properly. vector_extract takes a vector and a scalar location, and returns that scalar component of the vector. Vectorization doesn't really make any sense. Treating both as horizontal operations makes sure the vectorizer won't try to touch these. Found by inspection. Signed-off-by: Kenneth Graunke <[email protected]> Reviewed-by: Matt Turner <[email protected]>
* softpipe: tell draw about the vertex layout we wantRoland Scheidegger2016-01-074-58/+105
| | | | | | | | | | | | | | | This makes it more similar to llvmpipe. It also allows us to let draw emit code handle things like getting zeros for non-existing vs outputs automatically. There probably isn't really any overhead either way, there isn't really any "simply copy everything" code in the emit path it would copy each attrib individually just the same. Likewise, we still do another mapping step in softpipe as the layout may still not match exactly (same as in llvmpipe, should probably nuke the pointless mapping in both drivers). This fixes the piglit arb_fragment_layer_viewport no_gs/no_write tests. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* llvmpipe: use ints not unsigned for slotsRoland Scheidegger2016-01-076-67/+73
| | | | | | | | | | | | | They can't actually be 0 (as position is there) but should avoid confusion. This was supposed to have been done by af7ba989fb5a39925a0a1261ed281fe7f48a16cf but I accidentally pushed an older version of the patch in the end... Also prettify slightly. And make some notes about the confusing and useless fs input "map". Reviewed-by: Jose Fonseca <[email protected]> Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* draw: nuke the interp parameter from vertex_infoRoland Scheidegger2016-01-0711-92/+72
| | | | | | | | | | | | | draw emit couldn't care less what the interpolation mode is... This somehow looked like it would matter, all drivers more or less dutifully filled that in correctly. But this is only used for emit, if draw needs to know about interpolation mode (for clipping for instance) it will get that information from the vs anyway. softpipe actually used to depend on that interpolation parameter, as it abused that structure quite a bit but no longer. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* softpipe: don't abuse the draw vertex_info struct for something differentRoland Scheidegger2016-01-075-45/+53
| | | | | | | | | | softpipe would calculate two "vertex layouts". The second one was however just used for internal purposes, draw would know nothing about it even though it looked exactly the same as the other one we tell draw about. So, store that information separately as this was just confusing. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* softpipe: fix mapping of "special" vs outputsRoland Scheidegger2016-01-071-12/+17
| | | | | | | | | | | | | Unlike llvmpipe, softpipe always tells draw to emit the vertices as-is. The two vertex layouts it calculates are a bit confusing, one which is just used to tell draw to emit vertices as-is, and the other which has draw written all over it but draw is completely unaware of and is used only to look up the correct interpolation info later in setup. Thus, the slots used are different to what llvmpipe does (I'm going to clean up the confusing two layout stuff). Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* llvmpipe: scratch some special handling of vp_index/layerRoland Scheidegger2016-01-074-38/+7
| | | | | | | | | It was actually slightly buggy (missing initialization / setup not dependent on new vs albeit I didn't see issues), but the case of non-existing attributes is now handled by draw emit code so don't need that anymore. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* draw: rework handling of non-existing outputs in emit codeRoland Scheidegger2016-01-073-23/+46
| | | | | | | | | | | | | Previously the code would just redirect requests for attributes which don't exist to use output 0. Rework this to output all zeros instead which seems more useful - in particular some extensions like ARB_fragment_layer_viewport require 0 in the fs even if it wasn't output by previous stages. That way, drivers don't have to special case this depending if the vs/gs outputs some attribute or not. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Jose Fonseca <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* mesa: Add KBL PCI IDs and platform information.Sarah Sharp2016-01-061-0/+60
| | | | | | | | | | | | | | | | | | | | | | | | | Add PCI IDs for the Intel Kabylake platforms. The IDs are taken directly from the Linux kernel patches, which are under review: http://lists.freedesktop.org/archives/intel-gfx/2015-October/078967.html http://cgit.freedesktop.org/~vivijim/drm-intel/log/?h=kbl-upstream-v2 The Kabylake PCI IDs taken from the kernel are rearranged to be in order of GT type, then PCI ID. Please note that if this patch is backported, the following fixes will need to be added before this patch: commit 28ed1e08e8ba98e "i965/skl: Remove early platform support" commit c1e38ad37042b0e "i965/skl: Use larger URB size where available." Thanks to Ben for fixing a bug around setting urb.size, and being patient with my questions about what the various fields mean. Signed-off-by: Sarah Sharp <[email protected]> Suggested-by: Ben Widawsky <[email protected]> Tested-by: Rodrigo Vivi <[email protected]> (KBL-GT2) Cc: "11.1" <[email protected]>
* svga: Rename SVGA_HINT_FLAG_DRAW_EMITTEDSinclair Yeh2016-01-066-21/+21
| | | | | | | | Rename SVGA_HINT_FLAG_DRAW_EMITTED to SVGA_HINT_FLAG_CAN_PRE_FLUSH because preemptive flush can be unblocked by more commands than draw. Reviewed-by: Brian Paul <[email protected]>
* svga: allow preemptive flushing on DMA, update, and readback commandsSinclair Yeh2016-01-062-0/+9
| | | | | | | | | | | | | | | The existing code effectively turns off preemptive flushing for all but the regions used for draws. This turns out to be overly restrictive as some memory regions, e.g. GMR, may never get a draw when used as a DMA upload staging area, causing problems for apps that upload a large amount of textures, e.g. Unigine Heaven. This patch fixes the Unigine Heaven memory allocation error and has been verified to not cause a regression in the previous extended retina display issue. Reviewed-by: Thomas Hellstrom <[email protected]> Reviewed-by: Brian Paul <[email protected]>
* svga: skip vertex attribute instruction with zero usage_maskCharmaine Lee2016-01-061-0/+5
| | | | | | | | | | | | | | | | In emit_input_declarations(), we are skipping declarations for those registers that are not being used. But in emit_vertex_attrib_instructions(), we are still emitting instructions to tweak the vertex attributes even if they are not being used. This causes an assert in the backend because an input register is not declared in the shader. This patch fixes the problem by skipping the instruction if the vertex attribute is not being used. Changes in this patch is originated from the code snippet from Jose as suggested in bug 1530161. Tested with piglit, Heaven, Turbine, glretrace. Reviewed-by: Jose Fonseca <[email protected]> Reviewed-by: Brian Paul <[email protected]>
* st/mesa: minor clean-ups in st_atom.cBrian Paul2016-01-061-14/+10
| | | | Remove useless comment. Reformat code.
* st/mesa: replace bitmap size checks with assertionBrian Paul2016-01-061-2/+2
| | | | The _mesa_Bitmap() caller already checks for zero-sized bitmaps.
* st/mesa: check texture target in allocate_full_mipmap()Brian Paul2016-01-061-0/+14
| | | | | | | Some kinds of textures never have mipmaps. 3D textures seldom have mipmaps. Reviewed-by: José Fonseca <[email protected]>
* st/mesa: move mipmap allocation check logic into a functionBrian Paul2016-01-061-12/+42
| | | | | | Better readability and easier to extend. Reviewed-by: José Fonseca <[email protected]>
* main: s/GLuint/GLbitfield for state bitmasksBrian Paul2016-01-062-3/+3
| | | | Reviewed-by: José Fonseca <[email protected]>
* vbo: s/GLuint/GLbitfield/ for state bitmasksBrian Paul2016-01-064-4/+4
| | | | Reviewed-by: José Fonseca <[email protected]>
* st/mesa: use GLbitfield in st_state_flags, add commentsBrian Paul2016-01-061-2/+2
| | | | | | Use GLbitfield instead of GLuint to be consistent with other variables. Reviewed-by: José Fonseca <[email protected]>
* s/GLuint/GLbitfield/ for st_invalidate_state() parameterBrian Paul2016-01-062-2/+2
| | | | | | To match dd_function_table::UpdateState(). Reviewed-by: José Fonseca <[email protected]>
* st/mesa: be more careful about state validation in st_Bitmap()Brian Paul2016-01-061-1/+8
| | | | | | | | | | | If the only dirty state is mesa's _NEW_PROGRAM_CONSTANTS flag, we can skip state validation before drawing a bitmap since that state doesn't effect bitmap rendering. This further increases the performance of the ipers demo on llvmpipe to about what it was before commit 36c93a6fae27561. Reviewed-by: José Fonseca <[email protected]>
* st/mesa: move bitmap cache flushing out of state validationBrian Paul2016-01-066-4/+17
| | | | | | Just do it where needed (before drawing, clearing, etc). Reviewed-by: José Fonseca <[email protected]>
* st/mesa: check state->mesa in early return check in st_validate_state()Brian Paul2016-01-061-1/+1
| | | | | | | | | | | | | | | We were checking the dirty->st flags but not the dirty->mesa flags. When we took the early return, we didn't clear the dirty->mesa flags so the next time we called st_validate_state() we'd often flush the glBitmap cache. And since st_validate_state() is called from st_Bitmap(), it meant we flushed the bitmap cache for every glBitmap() call. This change seems to recover most of the performance loss observed with the ipers demo on llvmpipe since commit commit 36c93a6fae27561. Cc: [email protected] Reviewed-by: José Fonseca <[email protected]>
* st/mesa: protect debug printf() with a conditional instead of commentBrian Paul2016-01-061-5/+5
|
* st/mesa: fix comment indentation in st_flush_bitmap_cache()Brian Paul2016-01-061-2/+2
|
* glsl: fix varying slot allocation for blocks and structs with explicit locationsTimothy Arceri2016-01-071-4/+5
| | | | | | | | | Previously each member was being counted as using a single slot, count_attribute_slots() fixes the count for array and struct members. Also don't assign a negitive to the unsigned expl_location variable. Reviewed-by: Ilia Mirkin <[email protected]>
* glsl: don't try adding built-ins to explicit locations bitmaskTimothy Arceri2016-01-071-1/+3
| | | | | Reviewed-by: Anuj Phogat <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* glsl: fix overlapping of varying locations for arrays and structsTimothy Arceri2016-01-071-12/+67
| | | | | | | | | | | | | | | | | | | | | Previously we were only reserving a single location for arrays and structs. We also didn't take into account implicit locations clashing with explicit locations when assigning locations for their arrays or structs. This patch fixes both issues. V5: fix regression for patch inputs/outputs in tessellation shaders V4: just use count_attribute_slots() to get the number of slots, also calculate the correct number of slots to reserve for gs and tess stages by making use of the new get_varying_type() helper. V3: handle arrays of structs V2: also fix for arrays of arrays and structs. Acked-by: Anuj Phogat <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* glsl: create helper to remove outer vertex index array used by some stagesTimothy Arceri2016-01-071-10/+26
| | | | | | | | This will be used in the following patch for calculating array sizes correctly when reserving explicit varying locations. Reviewed-by: Anuj Phogat <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* glsl: remove unused varyings before packing themTimothy Arceri2016-01-073-48/+54
| | | | | | | | | | | | | | | Previously we would pack varyings before trying to remove them, this relied on the packing pass not packing varyings with a location of -1 to avoid packing varyings that should be removed. However this meant unused varyings with an explicit location would be packed before they could be removed when we enable packing of them in a later patch. V2: fix regression in V1 removing unused varyings in multi-stage SSO, fix regression with single stage programs. Reviewed-by: Anuj Phogat <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]>
* gallium/r600: Replace ALIGN_DIVUP with DIV_ROUND_UPKrzysztof Sobiecki2016-01-063-3/+2
| | | | | | | | ALIGN_DIVUP is a driver specific(r600g) macro that duplicates DIV_ROUND_UP functionality. Replacing it with DIV_ROUND_UP eliminates this problems. Signed-off-by: Krzysztof A. Sobiecki <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]>
* vc4: Fix driver build from last minute rebase fix.Eric Anholt2016-01-061-21/+20
| | | | | | | I had the driver all tested for the last series, and in my last build I noticed that get_swizzled_channel was unused now, and removed it... apparently without testing to find that I removed the wrong channel swizzle function.
* vc4: Optimize out a comparison for bcsel based on an ALU comparisonEric Anholt2016-01-061-14/+59
| | | | | | | | | | | | | | | | | We routinely have code like: vec1 ssa_220 = fge ssa_104, ssa_61 vec1 ssa_199 = bcsel ssa_220, ssa_106, ssa_105 and we would compare fge's args and choose between ~0 and 0 to generate ssa_220, then compare ssa_220 to 0 and choose between bcsel's args. Instead, try to notice the pattern and compare between fge's args to select between bcsel's args. total instructions in shared programs: 88019 -> 87574 (-0.51%) instructions in affected programs: 9985 -> 9540 (-4.46%) total estimated cycles in shared programs: 245752 -> 245237 (-0.21%) estimated cycles in affected programs: 17232 -> 16717 (-2.99%)
* vc4: Add missing sRGB decode to texel fetches.Eric Anholt2016-01-061-0/+5
| | | | | We only see txf on MSAA textures, currently, and apparently this didn't impact any of our piglit tests.
* vc4: Add support for GL_ARB_texture_swizzle.Eric Anholt2016-01-061-1/+1
| | | | | We already had the code supporting it, since it's needed for the depth mode when doing shadow comparisons.
* vc4: Use NIR texture lowering for texture swizzling.Eric Anholt2016-01-062-57/+63
| | | | | | | | | | | | | | We can't use its other features currently (mostly because we don't want Newton-Raphson on rcps for texture coordinates), but it gets us started. This eliminates some comparisons with constants in GLB2.7 and ETQW traces at the QIR level by moving the comparisons into NIR, where they get constant-folded out. instructions in affected programs: 165 -> 156 (-5.45%) total uniforms in shared programs: 32087 -> 32085 (-0.01%) total estimated cycles in shared programs: 245762 -> 245752 (-0.00%) estimated cycles in affected programs: 461 -> 451 (-2.17%)
* vc4: Replace the SSA-style SEL operators with conditional MOVs.Eric Anholt2016-01-066-201/+128
| | | | | | | | | | | | | I'm moving away from QIR being SSA (since NIR is doing lots of SSA optimization for us now) and instead having QIR just be QPU operations with virtual registers. By making our SELs be composed of two MOVs, we could potentially coalesce the registers for the MOV's src and dst and eliminate the MOV. total instructions in shared programs: 88448 -> 88028 (-0.47%) instructions in affected programs: 39845 -> 39425 (-1.05%) total estimated cycles in shared programs: 246306 -> 245762 (-0.22%) estimated cycles in affected programs: 162887 -> 162343 (-0.33%)
* vc4: Don't try the SF coalescing unless it's on a def.Eric Anholt2016-01-061-3/+3
| | | | | | If you want the SF of the value of a register produced from a series of packing MOVs or conditional MOVs, we can't just SF on the last MOV into the register.
* gallium/drivers/svga: Use unsigned for loop indexEdward O'Callaghan2016-01-062-7/+7
| | | | | | | | Fix a 's/unsigned int/unsigned/' consistency case while here. Found-by: Coccinelle Signed-off-by: Edward O'Callaghan <[email protected]> Reviewed-by: Brian Paul <[email protected]>
* gallium/drivers/r600: Use unsigned for loop indexEdward O'Callaghan2016-01-061-9/+9
| | | | | | Found-by: Coccinelle Signed-off-by: Edward O'Callaghan <[email protected]> Reviewed-by: Brian Paul <[email protected]>
* gallium/drivers/ilo: Use unsigned for loop indexEdward O'Callaghan2016-01-064-16/+16
| | | | | | Found-by: Coccinelle Signed-off-by: Edward O'Callaghan <[email protected]> Reviewed-by: Brian Paul <[email protected]>
* gallium: Use unsigned for loop indexEdward O'Callaghan2016-01-061-3/+3
| | | | | | Found-by: Coccinelle Signed-off-by: Edward O'Callaghan <[email protected]> Reviewed-by: Brian Paul <[email protected]>
* gallium/drivers: Remove unnecessary semicolonsEdward O'Callaghan2016-01-0610-11/+11
| | | | | | Found-by: Coccinelle Signed-off-by: Edward O'Callaghan <[email protected]> Reviewed-by: Brian Paul <[email protected]>
* gallium: Remove unnecessary semicolonsEdward O'Callaghan2016-01-068-8/+9
| | | | | | | | | Fix silly issue with MSVC case fall-though support to need a extra 'break;' Found-by: Coccinelle Signed-off-by: Edward O'Callaghan <[email protected]> Reviewed-by: Brian Paul <[email protected]>
* llvmpipe: Optimize lp_rast_triangle_32_3_16 for POWER8Oded Gabbay2016-01-061-1/+141
| | | | | | | | | | | | | | | | | | | | | This patch converts the SSE-optimized lp_rast_triangle_32_3_16() to VMX/VSX. I measured the results on POWER8 machine with 32 cores at 3.4GHz and 16GB of RAM. FPS/Score Name Before After Delta ------------------------------------------------ openarena 16.35 16.7 2.14% xonotic 4.707 4.97 5.57% glmark2 didn't show a significant (more than 1%) difference. v2: Make sure code is build only on POWER8 LE machine Signed-off-by: Oded Gabbay <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* llvmpipe: Optimize BUILD_MASK(_LINEAR) for POWER8Oded Gabbay2016-01-061-40/+110
| | | | | | | | | | | | | | | | | | | | | This patch converts the SSE-optimized build_mask_32() and build_mask_linear_32() to VMX/VSX. I measured the results on POWER8 machine with 32 cores at 3.4GHz and 16GB of RAM. FPS/Score Name Before After Delta ------------------------------------------------ glmark2 (score) 139.8 142.7 2.07% openarena and xonotic didn't show a significant (more than 1%) difference. v2: Make sure code is build only on POWER8 LE machine Signed-off-by: Oded Gabbay <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* llvmpipe: Optimize do_triangle_ccw for POWER8Oded Gabbay2016-01-061-0/+100
| | | | | | | | | | | | | | | | | | | | | | | This patch converts the SSE optimization done in do_triangle_ccw to VMX/VSX. I measured the results on POWER8 machine with 32 cores at 3.4GHz and 16GB of RAM. FPS/Score Name Before After Delta ------------------------------------------------ glmark2 (score) 136.6 139.8 2.34% openarena 16.14 16.35 1.30% xonotic 4.655 4.707 1.11% v2: - Convert loads to use aligned loads - Make sure code is build only on POWER8 LE machine Signed-off-by: Oded Gabbay <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* llvmpipe: add POWER8 portability file - u_pwr8.hOded Gabbay2016-01-061-0/+310
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This file provides a portability layer that will make it easier to convert SSE-based functions to VMX/VSX-based functions. All the functions implemented in this file are prefixed using "vec_". Therefore, when converting from SSE-based function, one needs to simply replace the "_mm_" prefix of the SSE function being called to "vec_". Having said that, not all functions could be converted as such, due to the differences between the architectures. So, when doing such conversion hurt the performance, I preferred to implement a more ad-hoc solution. For example, converting the _mm_shuffle_epi32 needed to be done using ad-hoc masks instead of a generic function. All the functions in this file support both little-endian and big-endian but currently the file is build only on POWER8 LE machine. All of the functions are implemented using the Altivec/VMX intrinsics, except one where I needed to use inline assembly (due to missing intrinsic). v2: - Use vec_vgbbd instead of __builtin_vec_vgbbd - Add an aligned load function - Don't use typeof() - Make file build only on POWER8 LE machine Signed-off-by: Oded Gabbay <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* nir: Add a lower_fdiv option, turn fdiv into fmul/frcp.Kenneth Graunke2016-01-053-0/+3
| | | | | | | | | | | | | | | | The nir_opt_algebraic rule (('fadd', ('flog2', a), ('fneg', ('flog2', b))), ('flog2', ('fdiv', a, b))), can produce new fdiv operations, which need to be lowered on i965, as we don't actually implement fdiv. (Normally, we handle this in GLSL IR's lower_instructions pass, but in the above case we introduce an fdiv after that point. So, make NIR do it for us.) Signed-off-by: Kenneth Graunke <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]> Reviewed-by: Matt Turner <[email protected]> Cc: [email protected]
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 15:19:21 +0000