summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* nir/algebraic: Provide descriptive asserts for bit size checksJason Ekstrand2018-10-221-9/+42
| | | | | | | This will hopefully make debugging opt_algebraic bit-size compile failures easier. Reviewed-by: Samuel Iglesias Gonsálvez <[email protected]>
* nir/algebraic: Loosen a restriction on variablesJason Ekstrand2018-10-221-2/+6
| | | | | | | | | Previously, we would fail if a variable had an assigned but unknown bit size X and we tried to assign it an actual bit size. However, this is ok because, at the time we do the search, the variable does have an actual bit size and it will match X because of the NIR rules. Reviewed-by: Samuel Iglesias Gonsálvez <[email protected]>
* nir/algebraic: A bit of validation refactoring'Jason Ekstrand2018-10-221-15/+15
| | | | | | | We rename some local variables in validate() to be more readable and plumb the var through to get/set_var_bit_class instead of the var index. Reviewed-by: Samuel Iglesias Gonsálvez <[email protected]>
* nir/algebraic: Make internal classes str-ableJason Ekstrand2018-10-221-4/+12
| | | | Reviewed-by: Samuel Iglesias Gonsálvez <[email protected]>
* nir/algebraic: Generalize an optimizationJason Ekstrand2018-10-221-1/+1
| | | | | | There's nothing boolean about (a | ~a) ~> -1 Reviewed-by: Samuel Iglesias Gonsálvez <[email protected]>
* nir/algebraic: Use bool internally instead of bool32Jason Ekstrand2018-10-222-8/+5
| | | | Reviewed-by: Samuel Iglesias Gonsálvez <[email protected]>
* intel: Fix decoding for partial STATE_BASE_ADDRESS updates.Kenneth Graunke2018-10-222-6/+42
| | | | | | | | | | | STATE_BASE_ADDRESS only modifies various bases if the "modify" bit is set. Otherwise, we want to keep the existing base address. Iris uses this for updating Surface State Base Address while leaving the others as-is. v2: Also update aubinator_viewer_decoder (caught by Lionel) Reviewed-by: Lionel Landwerlin <[email protected]>
* nir: Use nir_src_is_const and nir_src_as_* in core codeJason Ekstrand2018-10-2217-76/+56
| | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* nir/search_helpers: Use nir_src_is_const and friendsJason Ekstrand2018-10-221-27/+22
| | | | | | | This not only makes them safe for more bit sizes but it also fixes a bug in is_zero_to_one where it would return true for constant NaN. Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* nir/search: Use nir_src_is_const and friendsJason Ekstrand2018-10-221-57/+13
| | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* nir: Add some new helpers for working with const sourcesJason Ekstrand2018-10-222-0/+108
| | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* mesa/st: Only call nir_lower_io_to_scalar_early on scalar ISAsAlyssa Rosenzweig2018-10-221-1/+4
| | | | | | | | | | | | | | | | | | | | | On scalar ISAs, nir_lower_io_to_scalar_early enables significant optimizations. However, on vector ISAs, it is counterproductive and impedes optimal codegen. This patch only calls nir_lower_io_to_scalar_early for scalar ISAs. It appears that at present there are no upstreamed drivers using Gallium, NIR, and a vector ISA, so for existing code, this should be a no-op. However, this patch is necessary for the upcoming Panfrost (Midgard) and Lima (Utgard) compilers, which are vector. With this patch, Panfrost is able to consume NIR directly, rather than TGSI with the TGSI->NIR conversion. For how this affects Lima, see https://www.mail-archive.com/[email protected]/msg189216.html Signed-off-by: Alyssa Rosenzweig <[email protected]> Reviewed-by: Timothy Arceri <[email protected]> Reviewed-by: Christian Gmeiner <[email protected]>
* meson: don't require libelf for r600 without LLVMDylan Baker2018-10-221-8/+10
| | | | | | | | | | | r600 doesn't have a hard requirement on LLVM, and therefore doesn't have a hard requirement on libelf. Currently the logic doesn't allow that however. Distro-bug: https://bugs.gentoo.org/669058 Fixes: 5060c51b6f4dfb0d5358bde6523285163d3faaad ("meson: build r600 driver") Reviewed-by: Matt Turner <[email protected]>
* anv,radv: Trivially expose two new VK_GOOGLE extensionsJason Ekstrand2018-10-222-0/+4
| | | | | | | | | | | | This patch exposes support for the following two extensions: * VK_GOOGLE_decorate_string * VK_GOOGLE_hlsl_functionality1 There's nothing for the driver to do; it's all handled in spirv_to_nir. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107971 Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* spirv: Add no-op support for VK_GOOGLE_hlsl_functionality1Jason Ekstrand2018-10-222-0/+12
| | | | | | | | | | | This extension adds two new decorations which carry meaning only for HLSL shaders. They are expected to be handled by higher level layers and can be ignored by implementations. However, it does save the client a bit of work if the implementation safely ignores them instead of the client having to strip them out of the SPIR-V in order for it to be valid. Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* spirv: Add support for SPV_GOOGLE_decorate_stringJason Ekstrand2018-10-221-0/+8
| | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* android: Build kms_swrast for the Android platformRob Herring2018-10-225-3/+38
| | | | | | Signed-off-by: Rob Herring <[email protected]> Signed-off-by: Robert Foss <[email protected]> Reviewed-by: Emil Velikov <[email protected]>
* ac: Fix loading a dvec3 from an SSBOConnor Abbott2018-10-221-2/+2
| | | | | | | | | The comment was wrong, since the loop above casts to a type with the correct bitsize already. Fixes: 7e7ee82698247d8f93fe37775b99f4838b0247dd ("ac: add support for 16bit buffer loads") Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* ac: Introduce ac_build_expand()Connor Abbott2018-10-222-14/+29
| | | | | | | | And implement ac_bulid_expand_to_vec4() on top of it. Fixes: 7e7ee82698247d8f93fe37775b99f4838b0247dd ("ac: add support for 16bit buffer loads") Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* ir3/nir: Set up image_dims consts for image_deref_size intrinsic tooEduardo Lima Mitev2018-10-211-0/+1
| | | | | | | | | `nir_intrinsic_image_deref_size` is not being considered during scan for driver constants, so image constants are not emitted if a shader only ever query the size of an image (no load, store, atomic op, etc). This is unlikely, but possible. Reviewed-by: Rob Clark <[email protected]>
* nv50/ir: fix ConstantFolding::createMul for 64 bit mulsKarol Herbst2018-10-201-1/+1
| | | | | | | | Fixes: 2f52925f5c60c72c9389bfdc122c3d5f8e15b25f "nv50/ir: move a * b -> a << log2(b) code into createMul()" Reviewed-by: Rhys Perry <[email protected]> Signed-off-by: Karol Herbst <[email protected]>
* radeonsi: Disable clear_state with radeon kernel driverSonny Jiang2018-10-192-4/+7
| | | | | Signed-off-by: Sonny Jiang <[email protected]> Tested-by: Michel Dänzer <[email protected]>
* meson: Add -Werror=return-type when supported.Kenneth Graunke2018-10-191-2/+4
| | | | | | | | | | | | | | | | | | This warning detects non-void functions with a missing return statement, return statements with a value in void functions, and functions with an bogus return type that ends up defaulting to int. It's already enabled by default with -Wall. Generally, these are fairly serious bugs in the code, which developers would like to notice and fix immediately. This patch promotes it from a warning to an error, to help developers catch such mistakes early. I would not expect this warning to change much based on the compiler version, so hopefully it won't become a problem for packagers/builders. See the GCC documentation or 'man gcc' for more details: https://gcc.gnu.org/onlinedocs/gcc-7.3.0/gcc/Warning-Options.html#index-Wreturn-type Reviewed-by: Eric Engestrom <[email protected]>
* anv: Define trampolines as the weak functionsJason Ekstrand2018-10-192-49/+21
| | | | | | | | | | | | | | | | | | | | | Instead of having weak references to the anv functions and separate trampoline functions with their own dispatch table, just make the trampoline functions weak. This gets rid of a dispatch table and potentially lets the compiler delete the unused weak function. The end result is a reduction in the .text section of 5.7K and a reduction in the .data section of 1.4K. Before: text data bss dec hex filename 3190329 282232 8960 3481521 351fb1 _install/lib64/libvulkan_intel.so After: text data bss dec hex filename 3184548 280792 8960 3474300 35037c _install/lib64/libvulkan_intel.so Reviewed-by: Lionel Landwerlin <[email protected]>
* docs: fix typo in 18.2.3 release notes linkJuan A. Suarez Romero2018-10-191-1/+1
| | | | | | | Fixes: 86b4bd52dc ("docs: update calendar, add news item and link release notes for 18.2.3") Signed-off-by: Juan A. Suarez Romero <[email protected]>
* docs: update calendar, add news item and link release notes for 18.2.3Juan A. Suarez Romero2018-10-193-7/+8
| | | | Signed-off-by: Juan A. Suarez Romero <[email protected]>
* docs: add sha256 checksums for 18.2.3Juan A. Suarez Romero2018-10-191-1/+2
| | | | | Signed-off-by: Juan A. Suarez Romero <[email protected]> (cherry picked from commit 27fd12857b53ec22c0e918eee6c4c009643fccbc)
* docs: add release notes for 18.2.3Juan A. Suarez Romero2018-10-191-0/+166
| | | | | Signed-off-by: Juan A. Suarez Romero <[email protected]> (cherry picked from commit d219361b4226944835959676d1721b2a9d29da72)
* scons: Remove gles option.Jose Fonseca2018-10-1910-46/+6
| | | | | | | | It's broken, and WGL state tracker is always built with GLES support noawadays. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* radv: Fix WSI & PCI bus info initialization order.Bas Nieuwenhuizen2018-10-191-4/+9
| | | | | | | | | | Trying to access the bus info before it is initialized is not going to work. Fixes: baa38c144f6 "vulkan/wsi: Use VK_EXT_pci_bus_info for DRM fd matching" Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108491 Reviewed-by: Samuel Pitoiset <[email protected]> Tested-by: Andre Heider <[email protected]>
* radeonsi: fix a typo in a comment in emit_guardbandMarek Olšák2018-10-181-1/+1
|
* radeonsi: fix gnome-shell crashMarek Olšák2018-10-181-2/+2
| | | | | | | I wasn't expecting to get viewports with the center having negative coordinates. Broken by: 6cc79e4411f
* Revert "anv: Stop generating weak references for instance entrypoints"Jason Ekstrand2018-10-181-0/+13
| | | | | | This reverts commit 00bb42105d6edf6e432c0e3712ffb9d3eb0aece4. It was not as well thought out as I had intended and broke the build when VK_KHR_display is disabled in the build.
* radeonsi: clamp point size to the limitMarek Olšák2018-10-183-3/+5
| | | | | | | This fixes dEQP-GLES2.functional.rasterization.limits.points. Broken by: ea039f789d9b54e1bd1d644b6a29863ca3500314 Tested-by: Jakob Bornecrantz <[email protected]>
* radeonsi: fix a VGT hang with primitive restart on Polaris10 and laterMarek Olšák2018-10-181-2/+8
| | | | | Cc: 18.1 18.2 <[email protected]> Tested-by: Jakob Bornecrantz <[email protected]>
* radeonsi: fix a deadlock due to partially-initialized context on CIMarek Olšák2018-10-181-6/+8
|
* radeonsi: Bump number of allowed global buffers to 32Jan Vesely2018-10-181-1/+1
| | | | | | | | Fixes assertion failure/crash when running luxmark/luxball on clover. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108272 CC: [email protected] Signed-off-by: Jan Vesely <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* radv: fix check for perftest options sizeAndres Rodriguez2018-10-181-1/+1
| | | | | | | It was using the debug options array size. CC: [email protected] Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radeonsi: fix incorrect hw screen offset and guardband computationMarek Olšák2018-10-181-2/+2
| | | | | | It resulted in assertion failures or incorrect rendering. Broken by: 9e182b8313c5ab952498a76495f57e8420f9e5ad
* vulkan/wsi: Use VK_EXT_pci_bus_info for DRM fd matchingJason Ekstrand2018-10-1811-70/+61
| | | | | | | | This lets us avoid passing the DRM fd around all over the place and gets us closer to layer utopia. Reviewed-by: Lionel Landwerlin <[email protected]> Reviewed-by: Eric Engestrom <[email protected]>
* loader/dri3: Also wait for front buffer fence if we triggered itMichel Dänzer2018-10-181-2/+5
| | | | | | | | | | | | | In that case, we have to wait for the fence to synchronize with the corresponding drawing we triggered in the X server. Fixes incorrect display with the i965 driver and some applications, e.g. solvespace. Bugzilla: https://bugs.freedesktop.org/108097 Fixes: aefac10fecc9 "loader/dri3: Only wait for back buffer fences in dri3_get_buffer" Tested-by: Sergii Romantsov <[email protected]>
* anv: Stop generating weak references for instance entrypointsJason Ekstrand2018-10-181-13/+0
| | | | | | | | | We don't need weak references to instance entrypoints because we never have more than one of each so we don't need the NULL fall-back. This also helps us avoid forgetting things because we now get link errors for missing instance entrypoints. Reviewed-by: Lionel Landwerlin <[email protected]>
* vulkan/wsi: Implement GetPhysicalDevicePresentRectanglesKHRJason Ekstrand2018-10-188-0/+177
| | | | | | | | | | | | | | | | | | This got missed during 1.1 enabling because it was defined as an interaction between device groups and WSI and it wasn't obvious it was in the delta. The idea behind it is that it's supposed to provide a hint to the application in a multi-GPU setup to indicate which regions of the screen are being scanned out by which GPU so a multi-device split-screen rendering application can render each part of the screen on the GPU that will be presenting it and avoid extra bus traffic between GPUs. On a single-GPU setup or one which doesn't support this present mode, we need to do something. We choose to return the window size (or a max-size rect) if the compositor, X server, or crtc is associated with the given physical device and zero rectangles otherwise. Reviewed-by: Lionel Landwerlin <[email protected]>
* vulkan/wsi: Store the instance allocator in wsi_deviceJason Ekstrand2018-10-1811-27/+16
| | | | | | | | | | | | We already have wsi_device and we know the instance allocator at wsi_device_init time so there's no need to pass it into the physical device queries. This also fixes a memory allocation domain bug that can occur if CreateSwapchain gets called prior to any queries (not likely) in which case the cached connection gets allocated off the device instead of the instance. Reviewed-by: Eric Engestrom <[email protected]> Reviewed-by: Lionel Landwerlin <[email protected]>
* st/xlib: Use more appropriate include guardMichał Janiszewski2018-10-181-2/+2
| | | | | Signed-off-by: Michał Janiszewski <[email protected]> Reviewed-by: Emil Velikov <[email protected]
* gallium: Fix mismatched ifdef-guardsMichał Janiszewski2018-10-181-2/+2
| | | | | Signed-off-by: Michał Janiszewski <[email protected]> Reviewed-by: Emil Velikov <[email protected]>
* softpipe: dynamically allocate space for immediate constantsGert Wollny2018-10-182-5/+15
| | | | | | | | | | | | | | | The number of immediate constants was fixed and the size check was only done by means of an assertion. Given this a shader that emits more immediate constants would result in a memory corruption when mesa is build in release mode. Instead of using this fixed limit allocate the space dynamically, let it grow as needed, and also remove the unused ImmArray. Fixes: dEQP-GLES31.functional.ssbo.layout.random.arrays_of_arrays.1 Signed-off-by: Gert Wollny <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* radv: use nir_shrink_vec_array_vars()Timothy Arceri2018-10-181-0/+1
| | | | | | | | | | | | | | | | | | Totals from affected shaders: SGPRS: 1096 -> 1096 (0.00 %) VGPRS: 1192 -> 1056 (-11.41 %) Spilled SGPRs: 0 -> 0 (0.00 %) Spilled VGPRs: 0 -> 0 (0.00 %) Private memory VGPRs: 0 -> 0 (0.00 %) Scratch size: 0 -> 0 (0.00 %) dwords per thread Code Size: 100940 -> 94384 (-6.49 %) bytes LDS: 0 -> 0 (0.00 %) blocks Max Waves: 100 -> 112 (12.00 %) Wait states: 0 -> 0 (0.00 %) All affected shaders are from Batman Arkham City. Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: use nir_split_array_vars()Timothy Arceri2018-10-181-0/+2
| | | | | | | | | | | | | | | | | | | | | We call in the opt loop in case another pass results in an array with indirect access being turned into direct access. Totals from affected shaders: SGPRS: 512 -> 496 (-3.12 %) VGPRS: 456 -> 452 (-0.88 %) Spilled SGPRs: 0 -> 0 (0.00 %) Spilled VGPRs: 0 -> 0 (0.00 %) Private memory VGPRs: 0 -> 0 (0.00 %) Scratch size: 0 -> 0 (0.00 %) dwords per thread Code Size: 40040 -> 39664 (-0.94 %) bytes LDS: 0 -> 0 (0.00 %) blocks Max Waves: 41 -> 43 (4.88 %) Wait states: 0 -> 0 (0.00 %) All affected shaders are from Batman Arkham City. Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radv: use nir_opt_find_array_copies()Timothy Arceri2018-10-183-8/+23
| | | | | | | | | | | | | | | | | | | | | | | Totals from affected shaders: SGPRS: 1112 -> 1112 (0.00 %) VGPRS: 1492 -> 1196 (-19.84 %) Spilled SGPRs: 0 -> 0 (0.00 %) Spilled VGPRs: 0 -> 0 (0.00 %) Private memory VGPRs: 0 -> 0 (0.00 %) Scratch size: 0 -> 0 (0.00 %) dwords per thread Code Size: 112172 -> 101316 (-9.68 %) bytes LDS: 0 -> 0 (0.00 %) blocks Max Waves: 93 -> 98 (5.38 %) Wait states: 0 -> 0 (0.00 %) All affected shaders are from "Batman: Arkham City" over DXVK. The pass detects that the temporary array created by DXVK for storing TCS inputs is a copy of the input arrays and allows us to avoid copying all of the input data and then indirecting on it with if-ladders, instead we just do indirect indexing. Reviewed-by: Bas Nieuwenhuizen <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-21 17:23:44 +0000