209413 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
David Rosca	f4436d606e	radeonsi: Add missing DEBUG_NAMED_VALUE_END to radeonsi_shader_debug_options ... AddressSanitizer: global-buffer-overflow ../src/util/u_debug.c:331 in debug_parse_flags_option Fixes: 5c92fe45a1 ("radeonsi: support more than 64 options for AMD_DEBUG") Reviewed-by: Qiang Yu <yuq825@gmail.com> Reviewed-by: Marek Olšák <marek.olsak@amd.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36434>	2025-07-30 08:33:10 +00:00
Lionel Landwerlin	60932e8fae	brw: always ensure coarse pixel is disabled on Gfx9 ... No HW support there. Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Ivan Briano <ivan.briano@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36457>	2025-07-30 07:57:19 +00:00
Lionel Landwerlin	aa6810b706	brw: consider LOAD_PAYLOAD fully defined ... It's mostly used for SEND messages and fully defines the register data (that's its purpose after all). Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Ivan Briano <ivan.briano@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36457>	2025-07-30 07:57:19 +00:00
Lionel Landwerlin	9371e8d370	brw: fixup coarse_z computation ... The delivered values in the coarse pixel size are 0 when coarse pixel dispatch is disabled and that is screwing up our half pixel offset adjustment. Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: mesa-stable Reviewed-by: Ivan Briano <ivan.briano@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36457>	2025-07-30 07:57:19 +00:00
Lionel Landwerlin	9dac7dda87	brw: fixup source depth enabling with coarse pixel shading ... Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: mesa-stable Reviewed-by: Ivan Briano <ivan.briano@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36457>	2025-07-30 07:57:18 +00:00
Lionel Landwerlin	68c50d129e	brw: fix NIR metadata invalidation with closest-hit shaders ... Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: mesa-stable Reviewed-by: Ivan Briano <ivan.briano@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36457>	2025-07-30 07:57:18 +00:00
Lionel Landwerlin	9430a1ed00	anv: remove unused helper arguments ... Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Caio Oliveira <caio.oliveira@intel.com> Reviewed-by: Ivan Briano <ivan.briano@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36457>	2025-07-30 07:57:18 +00:00
Lionel Landwerlin	fcd06aa8c3	anv: reuse runtime descriptor set layout base object ... Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Caio Oliveira <caio.oliveira@intel.com> Reviewed-by: Ivan Briano <ivan.briano@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36457>	2025-07-30 07:57:18 +00:00
Georg Lehmann	e43ef6533b	nir/opt_algebraic: remove 8bit roundtrip when vectorizing i2i16(unpack_4x8(a).zw) ... Explicit 16bit instructions are nicer to vectorize. Helps FSR4 on GFX11 marginally. Foz-DB Navi31: Totals from 10 out of 14 FSR4 shaders: Instrs: 59781 -> 58518 (-2.11%) CodeSize: 413428 -> 404156 (-2.24%) Latency: 193770 -> 190768 (-1.55%) InvThroughput: 226274 -> 221628 (-2.05%) VClause: 796 -> 793 (-0.38%); split: -1.01%, +0.63% Copies: 3342 -> 3008 (-9.99%); split: -11.01%, +1.02% PreSGPRs: 312 -> 305 (-2.24%) VALU: 51448 -> 50213 (-2.40%) SALU: 1074 -> 1048 (-2.42%) VOPD: 1783 -> 1718 (-3.65%); split: +0.95%, -4.60% Reviewed-by: Rhys Perry <pendingchaos02@gmail.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36117>	2025-07-30 07:25:51 +00:00
Georg Lehmann	4683187f49	radv/nir/lower_cmat: load gfx11 8bit ACC using the B layout to get aligned loads ... This allows us to use aligned loads that can be vectorized, without any downside as 8bit scalar loads always write 16bits of a register. Foz-DB Navi31: Totals from 10 out of 14 FSR4 shader: MaxWaves: 71 -> 68 (-4.23%) Instrs: 60146 -> 59781 (-0.61%); split: -0.67%, +0.06% CodeSize: 412448 -> 413428 (+0.24%); split: -0.11%, +0.35% VGPRs: 2112 -> 2160 (+2.27%) SpillVGPRs: 89 -> 68 (-23.60%) Scratch: 11776 -> 8704 (-26.09%) Latency: 196628 -> 193770 (-1.45%); split: -2.62%, +1.17% InvThroughput: 224944 -> 226274 (+0.59%); split: -0.02%, +0.61% VClause: 862 -> 796 (-7.66%) Copies: 3166 -> 3342 (+5.56%); split: -6.22%, +11.78% Branches: 37 -> 38 (+2.70%) PreSGPRs: 311 -> 312 (+0.32%) PreVGPRs: 2153 -> 2214 (+2.83%); split: -1.35%, +4.18% VALU: 51073 -> 51448 (+0.73%); split: -0.03%, +0.77% SALU: 1072 -> 1074 (+0.19%) VMEM: 3275 -> 2765 (-15.57%) VOPD: 1739 -> 1783 (+2.53%); split: +7.99%, -5.46% Reviewed-by: Rhys Perry <pendingchaos02@gmail.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36117>	2025-07-30 07:25:51 +00:00
Georg Lehmann	92cf02ee23	nir/search: support swizzles on expressions in replacement patterns ... Before this wasn't a compile time error, but it also didn't do anything. Reviewed-by: Rhys Perry <pendingchaos02@gmail.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36117>	2025-07-30 07:25:51 +00:00
Mel Henning	4be68b119e	loader: Don't load nouveau GL on nvidia kmd ... The vulkan driver already has a check for this. This prevents the GL driver from loading too. Reviewed-by: Karol Herbst <kherbst@redhat.com> Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/13484 Fixes: e99446fc ("egl: Add EGL_EXT_device_query_name and EGL_EXT_device_persistent_id") Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36449>	2025-07-29 23:52:32 +00:00
Timothy Arceri	6a217a06d9	util: remove recursion from bitset helpers ... Recursion can cause a stack overflow when the range is very large. Fixes: cb558b2b88 ("glsl: add mark_array_elements_referenced() fast path") Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/13617 Reviewed-by: Gert Wollny <gert.wollny@collabora.com> Reviewed-by: Caio Oliveira <caio.oliveira@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36430>	2025-07-29 23:07:12 +00:00
Sagar Ghuge	3a9157a10b	anv: Use thread group preemption granularity ... Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com> Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36337>	2025-07-29 22:47:56 +00:00
Sagar Ghuge	9ae09d521c	intel/genxml: Update CS_CHICKEN1 register field ... Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com> Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36337>	2025-07-29 22:47:56 +00:00
Roland Scheidegger	47c9c1869c	llvmpipe: Fix attribute interpolation setup when rendering lines with msaa ... If multisampling is enabled, we effectively always use pixel offset 0 for the purposes of setup, overriding half pixel center. However, line setup (and by the looks of it rectangle as well), while honoring this for the purposes of setting up the rasterization planes, it forgot to do this adjustment when setting up attribute interpolation, hence attribute interpolation for lines ended up wrong. Rather than fixing this up in line setup, just override pixel_offset in setup context when using msaa, since this is what we actually do, which simplifies the logic (do the same for the key for the setup jit function as well). Reviewed-by: Brian Paul <brian.paul@broadcom.com> Reviewed-by: Lucas Fryzek <lfryzek@igalia.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36435>	2025-07-29 21:52:01 +00:00
Marek Olšák	d61edf079b	nir: add nir_move_only_convergent/divergent ... This will be needed by nir_opt_move_reorder_loads, which will use the move flags. Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36357>	2025-07-29 16:20:53 -04:00
Marek Olšák	35bbc8405b	nir: add more nir_move_options ... Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36357>	2025-07-29 16:20:51 -04:00
Marek Olšák	44d78c4451	nir: handle load_input_vertex in nir_can_move_instr ... Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36357>	2025-07-29 16:20:49 -04:00
Marek Olšák	8d3e76c250	nir: split nir_move_load_frag_coord from nir_move_load_input ... It's a pure system value on AMD, not an input. Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36357>	2025-07-29 16:20:48 -04:00
Marek Olšák	5083769fcb	nir: renumber nir_move_options ... for future commits Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36357>	2025-07-29 16:20:46 -04:00
Marek Olšák	8d584586f5	nir: handle can_reorder robustly in nir_can_move_instr ... Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36357>	2025-07-29 16:20:44 -04:00
Marek Olšák	c229c93540	nir: change how can_mov_out_of_loop is set for intrinsics in nir_can_move_instr ... Set to false first, then set to true when needed. More intrinsics will set false. Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36357>	2025-07-29 16:20:42 -04:00
Marek Olšák	ad1cfcc841	nir: mark inverse_ballot & is_subgroup_invocation_lt_amd as CAN_REORDER ... nir_can_move_instr already ignores that this flag isn't set. Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36357>	2025-07-29 16:20:39 -04:00
Marek Olšák	2eea9b968d	nir/group_loads: rename to nir_opt_group_loads ... It's meant to be an optimization pass. Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:59 +00:00
Marek Olšák	3bceb7b622	nir/group_loads: don't use pass_flags to store the indirection level ... no change in behavior Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:59 +00:00
Marek Olšák	7b9acabe89	nir/group_loads: store our custom instr->index in an array ... we'll put more stuff in the new structure Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:58 +00:00
Marek Olšák	821dc611c5	nir/group_loads: use nir_instr_next/prev ... Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:58 +00:00
Marek Olšák	318a57c57c	nir/group_loads: make is_grouped_load use get_load_resource ... and unify get_intrinsic_resource & get_uniform_inst_resource into the new helper get_load_resource. Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:57 +00:00
Marek Olšák	b9f7dc5d26	nir/group_loads: remove mostly duplicated function is_memory_load ... is_grouped_load does the same thing Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:57 +00:00
Marek Olšák	ef0a5e1a65	nir/group_loads: invert the return value of can_move to reflect its true meaning ... The previous commit handles non-reorderable instructions better, so this is no longer needed. Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:56 +00:00
Marek Olšák	ad8b5325d4	nir/group_loads: group any reorderable intrinsics regardless of barriers ... Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:56 +00:00
Marek Olšák	e0d8979dea	nir/group_loads: split is_barrier into is_barrier + is_terminate ... and handle demote Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:56 +00:00
Marek Olšák	7d9aca2235	nir/group_loads: allow moving loads across instructions without defs ... It wouldn't group these: load (reordeable) store load (reordeable) Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:55 +00:00
Marek Olšák	aa732f6f30	nir/group_loads: handle more loads ... Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36100>	2025-07-29 19:28:55 +00:00
Lucas Fryzek	ab52889d28	anv: Enable compression on astc emulation plane ... Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/11108 Reviewed-by: Nanley Chery <nanley.g.chery@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30592>	2025-07-29 19:10:34 +00:00
Mike Blumenkrantz	f68cae3e13	kopper: fix initial swapinterval setting ... setting the mode here is harmless even on weirdo cts swapchain cases Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/13568 cc: mesa-stable Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36452>	2025-07-29 14:47:56 -04:00
Eric Engestrom	a8e9af2ce9	wsi/display: pass the plane's modifiers to the image ... This should cause us to choose a better-than-linear format modifier automatically based on the intersection of the driver's support and the display plane's support. Signed-off-by: Eric Engestrom <eric.engestrom@intel.com> Reviewed-by: Daniel Stone <daniels@collabora.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36341>	2025-07-29 16:44:04 +00:00
Emma Anholt	0c0d9c05e0	wsi/display: Do connector setup before swapchain init. ... The connector setup decides on a CRTC/plane, and can be done early. We're going to need that to get the modifiers list before we have swapchain init create the images. Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36341>	2025-07-29 16:44:04 +00:00
Emma Anholt	fe7652eae9	wsi/display: Pull DRM format translation up a level. ... Saves doing it multiple times, but more importantly we want to know it before wsi_swapchain_init() soon. Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36341>	2025-07-29 16:44:03 +00:00
Eric Engestrom	b16a6a56d8	wsi/display: pass the image's DRM modifiers to the kernel ... Signed-off-by: Eric Engestrom <eric.engestrom@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36341>	2025-07-29 16:44:02 +00:00
Yiwei Zhang	00d0f2bec5	nvk: clean up direct u_gralloc dep ... The u_gralloc fallback backend exists as a best effort attempt and it does log in the Android logcat so can be easily identified if not WAI. So far there's no Vulkan impl in mesa could reasonably work with the fallback backend alone, so if that becomes a real pain, we can exclude it from inside vk_android_get_ugralloc runtime helper. Also drop redundant ANB header. Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36386>	2025-07-29 16:29:58 +00:00
Yiwei Zhang	0d5a2f92ca	nak: do not hide drm header on Android ... libdrm exists on Android and drm header is needed as well. The proper way for cross-compile now is to use "-Dallow-fallback-for=libdrm" so that the subproject can be fetched accordingly. Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36386>	2025-07-29 16:29:58 +00:00
Yiwei Zhang	1e0c3529e7	nvk: clean up existing nvk_android frontend ... 1. No need custom nvk_AcquireImageANDROID to wait for the HWC release fence, since nvk is able to properly import the sync file. 2. Document the nvk_QueueSignalReleaseImageANDROID behavior. 3. Drop redundant header and includes. Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36386>	2025-07-29 16:29:58 +00:00
José Roberto de Souza	07f5b53dd7	intel/brw: Remove duplicated implementation of brw_imm_uq/brw_imm_u64() ... Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Signed-off-by: José Roberto de Souza <jose.souza@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36448>	2025-07-29 16:05:54 +00:00
José Roberto de Souza	14386eb7e5	intel/brw: Add comment to reg_unit() ... Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Signed-off-by: José Roberto de Souza <jose.souza@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36448>	2025-07-29 16:05:54 +00:00
José Roberto de Souza	7981a18df2	intel/brw: Nuke unused brw_message_desc_header_present() ... Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Signed-off-by: José Roberto de Souza <jose.souza@intel.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36448>	2025-07-29 16:05:53 +00:00
Pavel Ondračka	116bd1848e	r300/ci: remove emulated swtcl testing ... Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36436>	2025-07-29 15:50:59 +00:00
Pavel Ondračka	1035098a78	r300/ci: add RS740 piglit and dEQP testing ... Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36436>	2025-07-29 15:50:59 +00:00
Thomas H.P. Andersen	f8741cc344	anti-lag: pass a proper dataSize ... dataSize was passed as sizeof(uint64_t) From spec: dataSize is the size in bytes of the buffer pointed to by pData. dataSize must be large enough to contain the result of each query The NVK driver checks that the dataSize is large enough and hit an assert. This patch changes dataSize to sizeof(struct query) * num_timestamps. Reviewed-by: Daniel Schürmann <daniel@schuermann.dev> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36402>	2025-07-29 15:24:14 +00:00