AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
203,590 Commits 1 Branch 0 Tags
de45676efde519f22a53a39601dc8408558cd488
Commit Graph

203590 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Georg Lehmann de45676efd aco/insert_exec: reset exec temporary after combined p_demote + p_end_wqm 
Otherwise the next divergent merge block might re-enable demoted invocations.

Fixes: 90faadae72 ("aco/insert_exec_mask: don't disable dead quads on demote in divergent CF")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/12898
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/12912
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34278>
 2025-03-31 06:43:22 +00:00
Hyunjun Ko ae75376c8f anv: Move rateControlMode to the video session. 
Signed-off-by: Hyunjun Ko <zzoon@igalia.com>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34250>
 2025-03-31 04:25:14 +00:00
Trigger Huang f03b385d4b radeonsi: Fix perfcounter start event in si_pc_emit_start 
The original typo caused performance counters to send STOP events
instead of START, leading to incorrect profiling data.

Fixes: 1a1138817c ("radeonsi: add a new PM4 helper radeon_event_write")

Signed-off-by: Trigger Huang <Trigger.Huang@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34236>
 2025-03-31 02:36:48 +00:00
Faith Ekstrand 59b01dc764 nvk: Disable 32k images on Pascal A 
While we're here, add a comment about why we have this restriction in
the first place since NVK and the proprietary driver are different here.

Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34281>
 2025-03-30 20:29:13 -05:00
Faith Ekstrand 65d06d91ca nvk: Use max_image_dimension for maxFramebufferWidth/Height 
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34281>
 2025-03-30 20:29:07 -05:00
Faith Ekstrand c1674d4dfe nvk: Disable vulkanMemoryModel on Kepler and earlier 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34281>
 2025-03-30 20:16:25 -05:00
Marek Olšák b74a6e05bd glapi: fix x86 32-bit asm dispatch regression 
shared_glapi_mapi_tmp.h must be included before asm("x86_entry_end:").

Fixes: fae087770a - glapi: simplify codegen macros
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34269>
 2025-03-29 22:36:21 +00:00
Eric Engestrom 359f69ba0c ci: add FDO_RUNNER_JOB_PRIORITY_TAG_* to control priority of generic freedesktop runners 
This affects:
- generic jobs (sanity, rustfmt, shader-db, docs, etc.)
- linux image builds
- linux mesa builds
- software renderer tests
- android tests
- virgl & venus tests

Marge pipelines get high priority, nightly pipelines get low priority,
and everything else is in between.

(Hardware test farms have their own mechanisms.)

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34264>
 2025-03-29 18:17:24 +01:00
Eric Engestrom 88f70e48f5 ci: move android's kvm requirement to .use-debian/x86_64_test-android 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34264>
 2025-03-29 18:17:24 +01:00
Eric Engestrom e45f2e6c46 ci: move aarch64 tag to .use-debian/arm64_build 
Like we do in the other `.use-debian/arm64_*`.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34264>
 2025-03-29 18:17:24 +01:00
Eric Engestrom 76a6ce40e1 ci: drop packet.net tag on git archive job 
We are no longer on that infrastructure, and we no longer need to
specify which one we are on.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34271>
 2025-03-29 10:38:03 +00:00
Aaron Ruby d64df991bb gbm/dri: Match zink autoloading from egl 
Essentially, match the Zink autoloading order that was implemented as
part of https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25640

Reviewed-by: Yiwei Zhang <zzyiwei@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34163>
 2025-03-29 09:18:47 +00:00
Mike Blumenkrantz 49aec32f57 zink: block inferred loading for swrast 
this should always load llvmpipe

Reviewed-by: Yiwei Zhang <zzyiwei@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34163>
 2025-03-29 09:18:47 +00:00
Aaron Ruby 9ee435f92a egl: Remove FallbackZink config item entirely 
Its effect was negated as part of: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29771

Reviewed-by: Yiwei Zhang <zzyiwei@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34163>
 2025-03-29 09:18:47 +00:00
David Rosca f9d7d131a4 ac/parse_ib: Parse VCN DYNAMIC_REFLIST_BUFFER 
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34262>
 2025-03-29 08:50:49 +00:00
David Rosca 5275a88174 ac/parse_ib: Fix parsing output format on VCN5 
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34262>
 2025-03-29 08:50:49 +00:00
Faith Ekstrand 8d45d3bc3d nak: Disable lea64 and f2fp.pack_ab tests pre-Volta 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34129>
 2025-03-29 04:33:10 +00:00
Faith Ekstrand bb43c665dc nak: Add a QMD heap to hw_runner 
This is needed prior to Maxwell B to avoid SKED cache issues.

Reviewed-by: Lorenzo Rossi <snowycoder@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34129>
 2025-03-29 04:33:10 +00:00
Faith Ekstrand d8fef0a26c nak: Improve WS abstractions in hw_runner 
Reviewed-by: Lorenzo Rossi <snowycoder@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34129>
 2025-03-29 04:33:10 +00:00
Mel Henning c1d64053f2 nak: Assert instr_sched matches calc_instr_deps 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32311>
 2025-03-29 04:05:05 +00:00
Mel Henning 562504f47c nak: Calc static cycle count in instr_sched 
This changes the static cycle count estimate so that it takes into
account estimated variable latency instruction delays. Statistics from
before this commit are not comparable to statistics generated after
this commit.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32311>
 2025-03-29 04:05:05 +00:00
Mel Henning 79d0f8263d nak: Add a simple postpass instruction scheduler 
To get us started, this is designed to be pretty much the simplest thing
possible. It runs post-RA so we don't need to worry about hurting
occupancy and it uses the classic textbook algorithm for local (single
block) scheduling with the usual latency-weighted-depth heuristic.

-14.22% static cycle count on shaderdb

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32311>
 2025-03-29 04:05:05 +00:00
Faith Ekstrand d06d76a0d4 nak: Box our RegTrackers 
RegTracker<T> contains over 300 copies of T.  It's probably best not to
put that on the stack.  We can probably get away with it on Linux but
Windows has small stacks.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32311>
 2025-03-29 04:05:04 +00:00
Faith Ekstrand e9ff848095 nak: Move some calc_instr_deps items to a new file 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32311>
 2025-03-29 04:05:04 +00:00
Lorenzo Rossi 0ba5d99a61 nak: Simplify shl64 lowering on Maxwell 
Signed-off-by: Lorenzo Rossi <snowycoder@gmail.com>
Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34137>
 2025-03-29 03:45:49 +00:00
Lorenzo Rossi 139a9ea526 nak: Fix SM50 rounding-mode encoding edge-case 
Signed-off-by: Lorenzo Rossi <snowycoder@gmail.com>
Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34137>
 2025-03-29 03:45:49 +00:00
Faith Ekstrand a3935c7aa2 nak,nir: Generalize nak_nir_split_64bit_conversions and move it to NIR 
This pass was originally based on a similar pass from Intel but it's
grown support for some fancy stuff like fp64 -> fp16 conversion
splitting with proper rounding.

Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Reviewed-by: Benjamin Lee <benjamin.lee@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34126>
 2025-03-29 03:02:17 +00:00
Faith Ekstrand 2d75e7dced nak/nir: Use correct rounding for fp64 -> fp16 conversions 
For up, down, and round towards zero, the rounding accumulates properly
as long as you use the same rounding mode for both.  For RTNE, however,
we need to insert a two-instruction fixup in order to guarantee correct
rounding.

Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Reviewed-by: Benjamin Lee <benjamin.lee@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34126>
 2025-03-29 03:02:17 +00:00
Faith Ekstrand d826f82ffe nak: Implement nir_intrinsic_convert_alu_types 
We can't support every single form of this instruction but at least it's
plumbed through now.  Before this will be OpenCL-ready, we'll need to
call the NIR lowering pass with an appropriate predicate function.
However, for now it lets us use it in NAK-specific NIR lowerings.

Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Reviewed-by: Benjamin Lee <benjamin.lee@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34126>
 2025-03-29 03:02:17 +00:00
Faith Ekstrand c05565ce7b compiler/rust: Add more NIR intrinsic getters 
Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Reviewed-by: Benjamin Lee <benjamin.lee@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34126>
 2025-03-29 03:02:17 +00:00
Faith Ekstrand 1355c71943 compiler/rust: Add a nir_alu_type wrapper 
Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Reviewed-by: Benjamin Lee <benjamin.lee@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34126>
 2025-03-29 03:02:17 +00:00
Lionel Landwerlin 47cfc77085 anv: expose VK_KHR_maintenance8 support 
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/33138>
 2025-03-29 02:15:19 +00:00
Lionel Landwerlin 7fca7cc721 anv: wire VkAccessFlagBits3KHR flags in internal helpers 
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/33138>
 2025-03-29 02:15:18 +00:00
Lionel Landwerlin 23de5abcb5 anv: enable non uniform texture offset lowering 
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/33138>
 2025-03-29 02:15:18 +00:00
Lionel Landwerlin 4346210ae6 brw: move texture offset packing to NIR 
That way we can deal with upcoming non constant values for
VK_KHR_maintenance8.

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/33138>
 2025-03-29 02:15:18 +00:00
Lionel Landwerlin 67ae49dede intel: move lower_texture to brw 
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/33138>
 2025-03-29 02:15:18 +00:00
Lionel Landwerlin 86773b2ba6 brw: don't lower tg4 offsets without LOD 
The problem this fixes is currently hidden because of the order in
which we run nir_lower_tex & intel_nir_lower_texture. The issue is
that nir_lower_tex removes the LOD source in some cases and the second
run of nir_lower_tex can add it back.

This is also only needed on Gfx12.5+ if the LOD is present.

Finally move all of the texture lowering to the postprocess phase. No
need to run this multiple times.

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/33138>
 2025-03-29 02:15:18 +00:00
Lionel Landwerlin b87dccc64c elk: stop using intel_nir_lower_texture 
It's not doing anything.

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/33138>
 2025-03-29 02:15:18 +00:00
Lionel Landwerlin 772beb0ebf nir: add support for lowering non uniform texture offsets 
Intel HW only has support for non-uniform offsets for TG4 operations.

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/33138>
 2025-03-29 02:15:18 +00:00
Timur Kristóf 64c6930bfc ac/nir/ngg: Remove cleanup_culling_shader_after_dce. 
Not needed anymore, now that the new concept is there.

No Fossil DB changes on Navi 21.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22073>
 2025-03-29 00:47:20 +00:00
Timur Kristóf 243a80be44 ac/nir/ngg: Use deferred info for compacted arguments. 
This means we don't have to emit dead code anymore and can only
repack the sysvals that are actually used by the deferred part.

No Fossil DB changes on Navi 21.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22073>
 2025-03-29 00:47:20 +00:00
Timur Kristóf 0b71293358 ac/nir/ngg: Gather info about what the deferred shader part uses. 
Now that the deferred shader part is prepared before emitting
the non-deferred part, we can also gather info about what sysvals
it needs.

No Fossil DB changes on Navi 21.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22073>
 2025-03-29 00:47:20 +00:00
Timur Kristóf e4c91c01e3 ac/nir/ngg: Prepare deferred shader part before adding culling code. 
The previous concept was to emit the non-deferred shader part
first, including the culling code, and then modify the
non-deferred part accordingly.

This caused some issues because it was really impossible to tell
which sysvals the deferred part needs after DCE, so we had to
run an additional cleanup pass afterwards.

The new concept is to prepare the deferred part first by applying
reusable variables (from the non-deferred part) and run DCE.
This opens the possibility to accurately gather info about what
the deferred part needs.

This idea is further expanded in the next commits.

Fossil DB stats on Navi 21:

Totals from 17 (0.02% of 79377) affected shaders:
Instrs: 18063 -> 18064 (+0.01%)
CodeSize: 93368 -> 93372 (+0.00%)
Latency: 49889 -> 49899 (+0.02%); split: -0.01%, +0.03%
SALU: 2416 -> 2417 (+0.04%)

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22073>
 2025-03-29 00:47:20 +00:00
Timur Kristóf e9e58fa412 ac/nir/ngg: Remove inputs_needed_by_* 
This information will be collected by NIR core better,
no need to do it here. It is also currently unused.

No functional changes.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22073>
 2025-03-29 00:47:20 +00:00
Timur Kristóf 1e7d28a82e ac/nir/ngg: Improve reuse of position value. 
Instead of hand-rolled code, use nir_scalar and its
helper functions to reuse the position value.
Results in more copies, which are mitigated by
copy prop from the previous commit.

This helps eliminate some instructions, especially VMEM loads
from the deferred shader part of NGG culling shaders, which
can be reused from the position values calculated by the
non-deferred part.

Fossil DB stats on Navi 21:

Totals from 2472 (3.11% of 79377) affected shaders:
MaxWaves: 78748 -> 78772 (+0.03%)
Instrs: 636342 -> 633739 (-0.41%); split: -0.45%, +0.04%
CodeSize: 3444740 -> 3427172 (-0.51%); split: -0.53%, +0.02%
VGPRs: 62552 -> 62176 (-0.60%)
Latency: 2025711 -> 2019449 (-0.31%); split: -0.73%, +0.42%
InvThroughput: 221140 -> 221946 (+0.36%); split: -0.12%, +0.49%
VClause: 5443 -> 5278 (-3.03%); split: -3.20%, +0.17%
SClause: 8369 -> 8302 (-0.80%); split: -0.82%, +0.02%
Copies: 102435 -> 101652 (-0.76%); split: -0.87%, +0.11%
PreSGPRs: 63714 -> 63533 (-0.28%)
PreVGPRs: 48555 -> 48392 (-0.34%)
VALU: 242165 -> 241457 (-0.29%); split: -0.33%, +0.04%
SALU: 197656 -> 197482 (-0.09%); split: -0.10%, +0.01%
VMEM: 7746 -> 7571 (-2.26%)
SMEM: 10822 -> 10730 (-0.85%)

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22073>
 2025-03-29 00:47:20 +00:00
Timur Kristóf f7a160d501 ac/nir/ngg: Run copy propagation. 
Helps eliminate needless copies caused by reusing variables.
Mitigates negative stats from the next commit.

Fossil DB stats on Navi 21:

Totals from 109 (0.14% of 79377) affected shaders:
Instrs: 124480 -> 124486 (+0.00%); split: -0.00%, +0.01%
CodeSize: 651444 -> 651468 (+0.00%); split: -0.00%, +0.00%
Latency: 754120 -> 754116 (-0.00%); split: -0.00%, +0.00%
InvThroughput: 174384 -> 174383 (-0.00%)

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22073>
 2025-03-29 00:47:20 +00:00
Caio Oliveira 63224f64cc brw: Remove adjust_block_ips and brw_inst::remove() with defer 
Now that the brw_ip_ranges analysis is being used, there's no
need to track start_ip/end_ips in the blocks as they are mutate.  And
also no need to call adjust_block_ips at the end of some passes.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34012>
 2025-03-29 00:25:51 +00:00
Caio Oliveira 8057cfc49d brw: Use brw_ip_ranges in liveness analysis 
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34012>
 2025-03-29 00:25:51 +00:00
Caio Oliveira a6b0783375 brw: Use brw_ip_ranges in scheduling / regalloc 
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34012>
 2025-03-29 00:25:51 +00:00
Caio Oliveira 3659d36087 brw: Use brw_ip_ranges in passes 
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34012>
 2025-03-29 00:25:50 +00:00