summaryrefslogtreecommitdiffstats
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
* v3d: Fix the name of the "flpop" operation.Eric Anholt2018-07-236-6/+7
| | | | | Noticed while trying to sort a new op into the appropriate place to match the documentation.
* v3d: Print the instruction we're testing in the QPU disasm/pack round-trip.Eric Anholt2018-07-231-2/+3
| | | | | If we fail initial disassembly, it's good to know what instruction it was that failed.
* v3d: Drop unused vir_SAT() operation.Eric Anholt2018-07-231-8/+0
| | | | We lower saturates in NIR.
* v3d: Rotate through registers to improve post-RA scheduling options.Eric Anholt2018-07-231-0/+45
| | | | | | | | | | | Similarly to VC4's implementation, by not picking r0 immediately upon freeing it, we give the scheduler more of a chance to fit later writes in earlier. I'm not clear on whether there's any real cost to picking phys over accumulators, so keep that behavior for now. shader-db: total instructions in shared programs: 96831 -> 95669 (-1.20%) instructions in affected programs: 77254 -> 76092 (-1.50%)
* v3d: Allow reading from physical regs written in the previous instruction.Eric Anholt2018-07-231-24/+0
| | | | | | | | | This restriction existed in V3D 2.x, but lifting it was a major change in 3.x. shader-db results: total instructions in shared programs: 98117 -> 96831 (-1.31%) instructions in affected programs: 48520 -> 47234 (-2.65%)
* anv: remove unnecessary runtime copy of static stringEric Engestrom2018-07-231-2/+1
| | | | | | | | It's actually also a bit safer, since now the compiler will warn if the string is larger than the `.name` array. Signed-off-by: Eric Engestrom <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* anv: Pay attention to VK_ACCESS_MEMORY_(READ|WRITE)_BITAlex Smith2018-07-231-0/+9
| | | | | | | | | | | | | According to the spec, these should apply to all read/write access types (so would be equivalent to specifying all other access types individually). Currently, they were doing nothing. v2: Handle VK_ACCESS_MEMORY_WRITE_BIT in dstAccessMask. Signed-off-by: Alex Smith <[email protected]> Cc: [email protected] Reviewed-by: Lionel Landwerlin <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* virgl: remove unused stride-argumentsErik Faye-Lund2018-07-235-33/+5
| | | | | | | | The IOCTLs doesn't pass this along, so computing them in the first place is kinda pointless. Signed-off-by: Erik Faye-Lund <[email protected]> Reviewed-by: Gurchetan Singh <[email protected]>
* radv: print a big warning when RADV_TRACE_FILE is setSamuel Pitoiset2018-07-231-0/+4
| | | | | | | | Users shouldn't use this debugging option except when we ask them to do! Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: fix a memleak for merged shaders on GFX9Samuel Pitoiset2018-07-231-1/+1
| | | | | | | | | | modules[i] can be NULL for merged shaders but we have to free the NIR code. radv_can_dump_shader_stats() already handles if modules[i] is NULL, no need to check it twice. Cc: [email protected] Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* intel/blorp: Fix blits to R8G8B8_UNORM_SRGB sRGB harderJason Ekstrand2018-07-231-3/+11
| | | | | | | | | | | | The first fix attempt contained a nasty typo which somehow didn't get caught in review. It also didn't work as intended because the sRGB conversion was happening but then throwing away all but the red channel because it dind't know it was RGB. Really, it's my fault for trying to fix a bug without first writing tests. I've now written tests and they pass with this change. :) Fixes: 11712b9ca17 "intel/blorp: Fix blits to R8G8B8_UNORM_SRGB" Reviewed-by: Lionel Landwerlin <[email protected]>
* anv: Stop setting 3DSTATE_PS_EXTRA::PixelShaderHasUAVJason Ekstrand2018-07-221-31/+22
| | | | | | | | | | | | | | We've had several broadwell hangs that have come down to this bit just not working correctly. Most recently, we've had a pile of hangs reported with apps running under DXVK: https://github.com/doitsujin/dxvk/issues/469 Instead, use the bit that doesn't try to imply weird D3D coherency things and just force-enables the PS like we want. cc: [email protected] Reviewed-by: Kenneth Graunke <[email protected]>
* anv: Properly handle GetImageSubresourceLayout on complex imagesJason Ekstrand2018-07-221-7/+16
| | | | | | | | We support mipmapped and arrayed linear images so we need to support vkGetImageSubresourceLayout on them. Fortunately, it's just a trivial call into ISL. Reviewed-by: Lionel Landwerlin <[email protected]>
* radeonsi/nir: make use of nir_lower_load_const_to_scalar()Timothy Arceri2018-07-231-0/+2
| | | | | | | | | This allows NIR to CSE more operations. LLVM does this also so the impact is limited, however doing this in NIR allows other opts to make progress. For example some loops in Civilization Beyond Earth shaders are unrolled. Reviewed-by: Marek Olšák <[email protected]>
* anv/gen9: expose VK_EXT_post_depth_coverageIlia Mirkin2018-07-223-2/+10
| | | | | | | | | | Note that the use of ICMS_INNER_CONSERVATIVE disagrees with the GL driver. Perhaps it's more performant than ICMS_NORMAL and is otherwise permitted? Not sure, so I left it as-is. Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Lionel Landwerlin <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* spirv: add support for SPV_KHR_post_depth_coverageIlia Mirkin2018-07-222-0/+10
| | | | | | | | | Allow the capability to be exposed, and convert the new execution mode into fs state. Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Lionel Landwerlin <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* Android: fix a missing nir_intrinsics.h errorChih-Wei Huang2018-07-212-0/+3
| | | | | | | | | | | | | | | | | | | | | The commit 76dfed8ae2d5 changed nir_intrinsics.h to be a generated header, but the corresponding dependency was not updated for Android. It causes the error: [ 0% 19/4336] target C: libmesa_pipe_radeonsi <= external/mesa/src/gallium/drivers/radeonsi/si_debug.c ... In file included from external/mesa/src/gallium/drivers/radeonsi/si_debug.c:25: In file included from external/mesa/src/gallium/drivers/radeonsi/si_pipe.h:28: In file included from external/mesa/src/gallium/drivers/radeonsi/si_shader.h:140: In file included from external/mesa/src/amd/common/ac_llvm_build.h:30: external/mesa/src/compiler/nir/nir.h:966:10: fatal error: 'nir_intrinsics.h' file not found ^~~~~~~~~~~~~~~~~~ 1 error generated. Fixes: 76dfed8ae2d5 ("nir: mako all the intrinsics") Signed-off-by: Chih-Wei Huang <[email protected]> Reviewed-by: Tapani Pälli <[email protected]> Reviewed-by: Mauro Rossi <[email protected]>
* nir: Fix end of function without return warning/error.Bas Nieuwenhuizen2018-07-201-0/+2
| | | | | | | | | There always is a continue block, so let us just do unreachable. Reviewed-by: Jason Ekstrand <[email protected]> Fixes: 8cacf38f527 "nir: Do not use continue block after removing it." CC: 18.1 <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107312
* st: Sweep NIR after linking phase to free held memoryDanylo Piliaiev2018-07-201-0/+2
| | | | | | | | | | | | | | After optimization passes and many trasfromations most of memory NIR holds is a garbage which was being freed only after shader deletion. Freeing it at the end of linking will save memory which would be useful in case there are a lot of complex shaders being compiled. The common case for this issue is 32bit game running under Wine. The cost of the optimization is around ~3-5% of compilation speed with complex shaders. Signed-off-by: Danylo Piliaiev <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* st/dri: Don't require a dri_format for image creation.Eric Anholt2018-07-202-13/+1
| | | | | | | | | | | | | Nothing in EGL_KHR_gl_image.txt seems to let us deny creation based on formats, and doing so causes many failures in dEQP-EGL.functional.image.api.* The NONE value we were protecting from only gets looked at in the __DRI_IMAGE_ATTRIB_FORMAT and __DRI_IMAGE_ATTRIB_FOURCC queries, which are used from wayland and gbm (which throw an error cleanly on unknown format) and DMABUF export. Reviewed-by: Marek Olšák <[email protected]>
* egl: Refuse EGL_MESA_image_dma_buf_export if we don't have a DRM fourcc.Eric Anholt2018-07-201-0/+27
| | | | | | | | The EGL CTS expects that you can make images from all sorts of things, including things like z16 and s8, which we don't have DRM fourccs for. Just return an error when trying to export one of those. Reviewed-by: Marek Olšák <[email protected]>
* v3d: Fix incorrect handling of two fences created back-to-back.Eric Anholt2018-07-201-12/+31
| | | | | | | | | | | Recreating our context's syncobj with ALREADY_SIGNALED meant that if you created two fences in a row, then waiting on the second would succeed immediately. Instead, export a sync file in the gallium fence (since we don't have a syncobj clone ioctl), and just create a new syncobj to wait on whenever we need to. Noticed while debugging dEQP-GLES3.functional.fence_sync.client_wait_sync_finish
* v3d: Fix the timeout value passed to drmSyncobjWait().Eric Anholt2018-07-201-1/+6
| | | | | The API wants an absolute time, so we need to go add gallium's argument to CLOCK_MONOTONIC.
* v3d: Fix drmSyncobjWait() return value checking even more.Eric Anholt2018-07-201-1/+1
| | | | | | It tends to return >0 in the success case (I think the value is something like "how much of the timeout remained"). Fixes dEQP-GLES3.functional.fence_sync.client_wait_sync_finish
* v3d: Use the list_first_entry/list_last_entry macros.Eric Anholt2018-07-201-8/+8
|
* v3d: Move BO cache counting to dump time instead of cache management.Eric Anholt2018-07-202-9/+9
| | | | This is one less way to get the dump stats wrong.
* v3d: Reduce the stale BO reclamation spam with dump_stats set.Eric Anholt2018-07-201-6/+5
| | | | | This was obviously meant to be when we were actually freeing a BO, not just when there was at least one BO in the list.
* v3d: Respect a sampler view's first_layer field.Eric Anholt2018-07-201-1/+3
| | | | | Fixes texturing from EGL images created from cubemap faces, as in dEQP-EGL.functional.image.create.gles2_cubemap_negative_x_rgba_texture
* radeonsi: emit_spi_map packets optimizationSonny Jiang2018-07-204-8/+39
| | | | | | | | | v2: marek: remove an empty line before break; rename reg_val_seq -> spi_ps_input_cntl "type * x" -> "type *x" Signed-off-by: Sonny Jiang <[email protected]> Signed-off-by: Marek Olšák <[email protected]>
* virgl: Expose GL_ARB_copy_image if host supports itGert Wollny2018-07-202-1/+3
| | | | | Signed-off-by: Gert Wollny <[email protected]> Reviewed-by: Gurchetan Singh <[email protected]>
* virgl: Allow RGB32* textures only as buffer objectsGert Wollny2018-07-201-0/+7
| | | | | | | | | | | | | | | | | | When requesting a texture of the internal format GL_RGB32F Gallium will try to allocate a renderable texture and returns RGBA32F or RGBX32F, but when one requests GL_RGB32I or GL_RGB32UI the according 3-component texture will be returned. This leads to problems later, when one wants to use glCopyImageSubData to copy data between these textures that should be compatible, but given the way virgl and Gallium handle this the latter fails with an assertion, because the per-texel bit size is different. By allowing the GL_RGB32* only for texture buffers these problems are avoided without losing the ARB_tbo_rgb32 extension (thanks Ilia Mirkin). v2: Correct spelling (Gurchetan Singh) Signed-off-by: Gert Wollny <[email protected]> Reviewed-by: Gurchetan Singh <[email protected]>
* intel: tools: dump: protect against multiple calls on destructorLionel Landwerlin2018-07-201-3/+16
| | | | | | | | | | | When running gdb, make sure to pass the LD_PRELOAD variable only to the executed program, not the debugger. Otherwise the debugger will run the preloaded constructor/destructor too and bad things will happen. Suggested-by: Rafael Antognolli <[email protected]> Signed-off-by: Lionel Landwerlin <[email protected]> Reviewed-by: Rafael Antognolli <[email protected]>
* intel: tools: dump: make dump tool reliable under gdbLionel Landwerlin2018-07-202-4/+9
| | | | | | | | | | | | The problem with passing the configuration of the dump lib through a file descriptor is that it can be read only once. But under gdb you might want to rerun your program multiple times. This change hands the configuration through a temporary file that is deleted once the command line passes to intel_dump_gpu has exited. Signed-off-by: Lionel Landwerlin <[email protected]> Reviewed-by: Rafael Antognolli <[email protected]>
* radv: don't flush DB before subpass FS resolvesSamuel Pitoiset2018-07-201-2/+1
| | | | | | | That shouldn't be needed because the DB state is invalid. Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* r600: Correct evaluation of cube array index and faceGert Wollny2018-07-201-1/+33
| | | | | | | | | | | | | | | | | | | | The array index needs to be corrected and it must be insured that it is rounded and its value is non-negative before it is combined with the face id. v5: Use RNDNE instead of ADD 0.5 and FLOOR (Ilia Mirkin) v6: Fix type (Roland Scheidegger) Fixes 182 from android/cts/master/gles31-master.txt: dEQP-GLES31.functional.texture.filtering.cube_array.formats.* dEQP-GLES31.functional.texture.filtering.cube_array.sizes.* dEQP-GLES31.functional.texture.filtering.cube_array.combinations.nearest_mipmap_* dEQP-GLES31.functional.texture.filtering.cube_array.combinations.linear_mipmap_* dEQP-GLES31.functional.texture.filtering.cube_array.no_edges_visible.* Signed-off-by: Gert Wollny <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* r600: correct texture offset for array index lookupGert Wollny2018-07-201-5/+37
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Correct the array index for TEXTURE_*1D_ARRAY, and TEXTURE_*2D_ARRAY The standard says the array index is evaluated according to floor(z + 0.5) but RNDNE is sufficient also for the test cases were z is close to 1.5 and it is likely to hit 1.5, the corner case were RNDNE gives a result different from above formula. v5: - Use RNDNE instead of ADD 0.5 and FLOOR (Ilia Mirkin) - update commit message Fixes 325 tests from android/cts/master/gles3-master.txt: dEQP-GLES3.functional.shaders.texture_functions.texture.*sampler2darray* dEQP-GLES3.functional.shaders.texture_functions.textureoffset.*sampler2darray* dEQP-GLES3.functional.shaders.texture_functions.texturelod.sampler2darray* dEQP-GLES3.functional.shaders.texture_functions.texturelodoffset.*sampler2darray* dEQP-GLES3.functional.shaders.texture_functions.texturegrad.*sampler2darray* dEQP-GLES3.functional.shaders.texture_functions.texturegradoffset.*sampler2darray* dEQP-GLES3.functional.texture.filtering.2d_array.formats.* dEQP-GLES3.functional.texture.filtering.2d_array.sizes.* dEQP-GLES3.functional.texture.filtering.2d_array.combinations.* dEQP-GLES3.functional.texture.shadow.2d_array.* dEQP-GLES3.functional.texture.vertex.2d_array.* Signed-off-by: Gert Wollny <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* r600: Delay emission of texture gradients and lookup offsetsGert Wollny2018-07-201-44/+48
| | | | | | | | | | | | | | Gradients used in texture lookups and the offsets must reside in the same fetch clause (the first is imposed by the hardware and the second is expected by sb). In order to ensure that no ALU clause is inserted between emission and use of these, delay the emission of these instructions until the texture instruction using them is also emitted. This is needed in preparation for the correction of the texture array indices. Signed-off-by: Gert Wollny <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* util/disk_cache: Fix disk_cache_get_function_timestamp with disabled cache.Bas Nieuwenhuizen2018-07-201-5/+3
| | | | | | | | | | radv always needs it, so just check the header instead. Also do not declare the function if the variable is not set, so we get a nice compile error instead of failing to open a device at runtime. Fixes: b87ef9e606a "util: fix MSVC build issue in disk_cache.h" Reviewed-by: Timothy Arceri <[email protected]>
* nir: Do not use continue block after removing it.Bas Nieuwenhuizen2018-07-201-6/+25
| | | | | | | | | | | | | | | | Reinserting code directly before a jump means the block gets split and merged, removing the original block and replacing it in the process. Hence keeping a pointer to the continue block over a reinsert causes issues. This code changes nir_opt_if to simply look for the new continue block. Reviewed-by: Jason Ekstrand <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107275 CC: 18.1 <[email protected]>
* radv: simplify a condition in radv_src_access_flush()Samuel Pitoiset2018-07-201-4/+6
| | | | | Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: save current state just before resolving with FSSamuel Pitoiset2018-07-201-5/+5
| | | | | Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: don't check if a subpass has resolve attachments twiceSamuel Pitoiset2018-07-202-24/+0
| | | | | | | We already check that in radv_cmd_buffer_resolve_subpass(). Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: make use of radv_subpass_barrier() when resolving subpassesSamuel Pitoiset2018-07-204-15/+20
| | | | | | | | The goal is to use radv_barrier()/radv_subpass_barrier() as much as possible for further optimizations. Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* nv50/ir: move LateAlgebraicOpt back to right after ConstantFoldingRhys Perry2018-07-191-1/+1
| | | | | | | | | | | | total instructions in shared programs : 5480808 -> 5472107 (-0.16%) total gprs used in shared programs : 647530 -> 647532 (0.00%) total shared used in shared programs : 389120 -> 389120 (0.00%) total local used in shared programs : 21064 -> 21064 (0.00%) total bytes used in shared programs : 58551648 -> 58459352 (-0.16%) local shared gpr inst bytes helped 0 0 73 2609 2609 hurt 0 0 71 34 34
* nv50/ir: handle SHLADD in IndirectPropagationRhys Perry2018-07-191-0/+12
| | | | | | | | | | | | | | | An alternative solution to the problem fixed in 0bd83d0 ("nv50/ir: move LateAlgebraicOpt to the very end"). total instructions in shared programs : 5481195 -> 5480808 (-0.01%) total gprs used in shared programs : 647535 -> 647530 (-0.00%) total shared used in shared programs : 389120 -> 389120 (0.00%) total local used in shared programs : 21064 -> 21064 (0.00%) total bytes used in shared programs : 58555784 -> 58551648 (-0.01%) local shared gpr inst bytes helped 0 0 2 34 34 hurt 0 0 0 0 0
* gm107/ir: use CS2R for SV_CLOCKRhys Perry2018-07-193-2/+25
| | | | | | | | This instruction seems to be faster than S2R and requires no barrier, though the range of special registers it can read from is limited. Signed-off-by: Rhys Perry <[email protected]> Reviewed-by: Karol Herbst <[email protected]>
* intel: tools: dump: remove mentions of intel_aubdumpLionel Landwerlin2018-07-191-15/+15
| | | | | Signed-off-by: Lionel Landwerlin <[email protected]> Acked-by: Rafael Antognolli <[email protected]>
* intel: tools: aubwrite: fix invalid frees on finishLionel Landwerlin2018-07-191-4/+9
| | | | | Signed-off-by: Lionel Landwerlin <[email protected]> Reviewed-by: Jordan Justen <[email protected]>
* ac/nir: add a workaround for bitfield_extract when count is 0Samuel Pitoiset2018-07-191-3/+17
| | | | | | | | | | | | LLVM 7 returns incorrect results when count is 0, something has been broken since LLVM 6. Of course, the best solution is to fix LLVM but this workaround works as expected for now. Original workaround by Philippe Rebohle. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107276 Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* intel/isl/gen4: Make depth/stencil buffers Y-TiledNanley Chery2018-07-191-1/+8
| | | | | | | | | | | | | | Rendering to a linear depth buffer on gen4 is causing a GPU hang in the CI system. Until a better explanation is found, assume that errata is applicable to all gen4 platforms. Fixes fbe01625f6bf2cef6742e1ff0d3d44a2afec003e ("i965/miptree: Share tiling_flags in miptree_create"). Reported-by: Mark Janes <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107248 Tested-by: Mark Janes <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-15 17:08:05 +0000