AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
164,177 Commits 1 Branch 0 Tags
33c3e429fe381d4e2df299ff75d81ef6b44a8f6e
Commit Graph

10780 Commits

Author SHA1 Message Date
Friedrich Vock 568fa71ef8 radv: Handle NULL miss shaders 
Fixes reflections in DOOM Eternal.

Fixes: 85580faa ("radv: Add ray traversal loop.")
Closes: #6210
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20270>
 2022-12-12 18:52:59 +00:00
Friedrich Vock 276236ed6d radv: Change shaderGroupBaseAlignment to RADV_RT_HANDLE_SIZE 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20270>
 2022-12-12 18:52:59 +00:00
Konstantin Seurer 9492b84a68 radv: Add a driconf option to force non uniform texture sampling 
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20243>
 2022-12-12 18:18:32 +00:00
Konstantin Seurer cdd68cbafd radv/rt: Hash the pipeline key 
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20243>
 2022-12-12 18:18:32 +00:00
Konstantin Seurer 48ae92ceea radv/rt: Propagate radv_pipeline_key 
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20243>
 2022-12-12 18:18:32 +00:00
Konstantin Seurer 7b5ac0ae2a radv/rt: Work around incorrect NOT_DEFERRED handling in Portal RTX 
Allows Portal RTX to reach the main menu.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20243>
 2022-12-12 18:18:32 +00:00
Mikhail Korolev c147a35644 radv: fix assertion on gpu hang detection 
fixes assert in RADV_DECL_PIPELINE_DOWNCAST when bound pipline is a compute
pipeline

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20276>
 2022-12-12 12:55:07 +00:00
Samuel Pitoiset 13f39da71a radv: fix hashing descriptor set layout 
Shouldn't have pointers.

Fixes: 19f8d33876 ("radv: Use vk_descriptor_set_layout")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20250>
 2022-12-12 07:33:21 +00:00
Bas Nieuwenhuizen efa4e9568b radv: Use correct watermark for early loop exit. 
The previous check assumed the stack starts at offset=0, which isn't
necessarily true for ray queries.

Note that this didn't cause correctness issues, just made an optimization
not apply. Found when I accidentally made this load-bearing in a
refactor.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20265>
 2022-12-11 18:51:29 +00:00
Bas Nieuwenhuizen f0d6a1a685 radv: Rename stack_base to stack_low_watermark. 
Better covers the purpose.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20265>
 2022-12-11 18:51:29 +00:00
Rhys Perry a89755d179 radv: fix task payload lowering when shared_memory_explicit_layout=true 
If shared_memory_explicit_layout=true, we would have skipped lowering task
payload variables to explicit types.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19597>
 2022-12-09 20:56:52 +00:00
Rhys Perry e4060752e2 radv: fix mesh shaders with null winsys 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19597>
 2022-12-09 20:56:52 +00:00
Rebecca Mckeever 64d7385e61 radv: Delete VK_KHR_device_group provided entrypoints 
Delete radv_CmdDispatch, radv_CmdSetDeviceMask, and
radv_GetDeviceGroupPeerMemoryFeatures so that the vk_common_*
versions will be used instead. This will avoid repeated code.

Signed-off-by: Rebecca Mckeever <rebecca.mckeever@collabora.com>
Reviewed-by: Jason Ekstrand <jason.ekstrand@collabora.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20218>
 2022-12-09 14:07:00 -06:00
Rhys Perry c872e339a1 radv: remove some unnecessary 64-bit IO handling 
nir_lower_io() lowers these to 32-bit.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20137>
 2022-12-09 17:30:24 +00:00
Rhys Perry 6a5b615ab1 radv: fix streamout with different streams in the same varying slot 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20137>
 2022-12-09 17:30:24 +00:00
Rhys Perry 20e670d060 aco/ra: don't swap create_vector operand with definition blocker for SGPRs 
There is no SGPR swap instruction, we always need 3 XORs.

fossil-db (navi21):
Totals from 76 (0.06% of 135636) affected shaders:
Instrs: 58400 -> 58347 (-0.09%); split: -0.10%, +0.01%
CodeSize: 312580 -> 312368 (-0.07%); split: -0.08%, +0.01%
Latency: 843333 -> 843180 (-0.02%); split: -0.02%, +0.00%
InvThroughput: 126431 -> 126412 (-0.02%)
Copies: 4008 -> 3955 (-1.32%); split: -1.47%, +0.15%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20240>
 2022-12-09 15:58:43 +00:00
Rhys Perry a05dd58309 aco/ra: don't swap p_create_vector operand with definition blocker for scc 
SCC is 1-bit, and we can't copy a 32-bit value into it.

Fixes dEQP-VK.spirv_assembly.type.scalar.i32.iequal_tesse with
ACO_DEBUG=noopt.

No fossil-db changes.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: 9476986e6f ("aco/ra: special-case get_reg_for_create_vector_copy()")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20240>
 2022-12-09 15:58:43 +00:00
Samuel Pitoiset 25a5d7ac0d radv: fix re-emitting the RB+ state when dynamic color write mask change 
Found by inspection.

Fixes: a92d1d13c5 ("radv: add support for dynamic color write mask")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20204>
 2022-12-09 07:37:00 +00:00
Konstantin Seurer 4c83a96f16 radv/rt: Discard metadata after lowering intersection shaders 
We inserted some enstructions and control flow. Therefore, metadata is
not valid anymore.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19866>
 2022-12-09 07:07:10 +00:00
Konstantin Seurer 79b7ed61a8 radv/rt: Lower hit attributes to registers 
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19866>
 2022-12-09 07:07:10 +00:00
Konstantin Seurer a598263800 radv/rt: Move load_hit_attrib_amd to the top 
Make sure to load hit attributes before a trace_ray call can overwrite them.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19866>
 2022-12-09 07:07:10 +00:00
Konstantin Seurer 9f03e9c286 radv: Add nir_foreach_variable_with_modes to .clang-format 
Yet another loop macro.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19866>
 2022-12-09 07:07:10 +00:00
Samuel Pitoiset 011a0b97b2 radv,aco: move radv_ps_epilog_key to the graphics pipeline key 
To avoid redundant structs.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20199>
 2022-12-08 13:28:00 +00:00
Samuel Pitoiset 67c9497435 radv: fix PS epilogs with RADV_PERFTEST=pswave32 
This option is rarely or even never used but it was broken. While we
are at it, remove radv_ps_epilog_key::wave32 because the wave size
can only be changed globally for PS.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20199>
 2022-12-08 13:28:00 +00:00
Samuel Pitoiset b7f49de625 radv,aco: use 8-bit for color_is_int{8,10} everywhere 
Do not need 32-bits because there is only up to 8 MRTs.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20199>
 2022-12-08 13:28:00 +00:00
Samuel Pitoiset 9079bd821c radv,aco: rename color output related fields for consistency 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20199>
 2022-12-08 13:28:00 +00:00
Tatsuyuki Ishi 327c906424 aco: Migrate RA to use std::optional 
The use of std::optional simplifies expressions and would be useful for some
upcoming RA tweaks.

C++17 has been available since the merge of rusticl and should be safe to use as
far as packaging is concerned.

A few style choices are:
- Testing for emptiness uses implicit bool conversion.
- Constructing an empty value uses {}.
- Constructing a filled value uses the implicit conversion constructor.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20125>
 2022-12-08 12:08:01 +00:00
Bas Nieuwenhuizen 513442dc32 aco: Add s_delay_alu support for GFX11+ 
Roughly copied from LLVM. This facilitates better ALU usage by
switching between waves when there is an ALU stall, which isn't
automatic anymore on GFX11.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19743>
 2022-12-07 22:05:25 +00:00
Bas Nieuwenhuizen cd3bf56ace aco: Add helper to get cycle info for an instruction. 
For use in s_delay_alu tracking

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19743>
 2022-12-07 22:05:25 +00:00
Bas Nieuwenhuizen 352e492c7b aco: Add isTrans helper. 
For the s_delay_alu tracking.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19743>
 2022-12-07 22:05:25 +00:00
Samuel Pitoiset bdb7fd69d6 radv: mark extendedDynamicState3SampleLocationsEnable as not required by Zink 
Only dynamic blend equation support is still required.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19924>
 2022-12-07 16:43:17 +01:00
Samuel Pitoiset 06a65be3d4 radv: advertise extendedDynamicState3LineRasterizationMode 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19924>
 2022-12-07 16:43:15 +01:00
Samuel Pitoiset 1009276312 radv: add support for dynamic line rasterization mode 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19924>
 2022-12-07 16:43:13 +01:00
Samuel Pitoiset f992e663c7 radv: advertise extendedDynamicState3RasterizationSamples 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19924>
 2022-12-07 16:43:11 +01:00
Samuel Pitoiset a2fe4e9b04 radv: add support for dynamic rasterization samples 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19924>
 2022-12-07 16:43:09 +01:00
Samuel Pitoiset c88d4037aa radv: store the number of color/ds samples to the rendering state 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19924>
 2022-12-07 16:43:07 +01:00
Samuel Pitoiset 12f26b5e6d radv: fix guardband if the polygon mode is points or lines 
If points or lines are drawn using the polygon mode, the guardband
should be adjusted for large points/lines.

Cc: 22.3 mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20185>
 2022-12-06 19:30:51 +00:00
Rhys Perry bd30adf89d aco: apply NUW to additions for scratch access 
fossil-db (navi21):
Totals from 52 (0.04% of 135636) affected shaders:
Instrs: 79036 -> 78567 (-0.59%)
CodeSize: 431188 -> 427984 (-0.74%)
Latency: 1318142 -> 1313821 (-0.33%)
InvThroughput: 293842 -> 292836 (-0.34%)
VClause: 2555 -> 2361 (-7.59%); split: -8.06%, +0.47%
Copies: 8746 -> 8767 (+0.24%); split: -0.11%, +0.35%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20117>
 2022-12-06 15:23:38 +00:00
Rhys Perry 381de3c809 aco: more carefully apply constant offsets into scratch accesses 
Death stranding does scratch_arr[80-idx]. This doesn't seem to work if we
try to combine the subtraction into the access.

fossil-db (navi21):
Totals from 52 (0.04% of 135636) affected shaders:
Instrs: 78560 -> 79036 (+0.61%)
CodeSize: 427940 -> 431188 (+0.76%)
Latency: 1313809 -> 1318142 (+0.33%)
InvThroughput: 292833 -> 293842 (+0.34%)
VClause: 2361 -> 2555 (+8.22%); split: -0.51%, +8.73%
Copies: 8767 -> 8746 (-0.24%); split: -0.35%, +0.11%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: 0e783d687a ("aco: use scratch_* for scratch load/store on GFX9+")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/7735
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20117>
 2022-12-06 15:23:38 +00:00
Rhys Perry fae8c75ad0 radv/rt: set additions for scratch access as NUW 
No fossil-db changes.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20117>
 2022-12-06 15:23:38 +00:00
Marek Olšák b75b9d6324 ac/llvm: set invariant.load on image loads with ACCESS_CAN_REORDER 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20146>
 2022-12-06 13:27:16 +00:00
Marek Olšák de3fcc77c7 ac/llvm: inline ac_get_load_intr_attribs 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20146>
 2022-12-06 13:27:16 +00:00
Marek Olšák ce860953a6 ac/llvm: rename attribute enums 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20146>
 2022-12-06 13:27:16 +00:00
Marek Olšák ce0a83efb8 ac/llvm: use invariant.load metadata on load intrinsics instead of readnone 
readnone is illegal now and we should be using invariant.load since LLVM 15.
(suggested by Nicolai)

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20146>
 2022-12-06 13:27:16 +00:00
Marek Olšák d3a03d24fc ac/llvm: don't set "readnone" on non-memory intrinsics 
It's illegal and LLVM always knows which intrinsics don't read memory.
This started failing IR validation with LLVM 16.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20146>
 2022-12-06 13:27:16 +00:00
Marek Olšák 50bece9322 ac/llvm: don't set "convergent" on intrinsics where it's automatic 
LLVM adds the flag automatically.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20146>
 2022-12-06 13:27:16 +00:00
Marek Olšák 2b5edf96ff ac/llvm: simplify how function attributes are set 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20146>
 2022-12-06 13:27:16 +00:00
Marek Olšák 9b4142ae9f ac/llvm: simplify how call attributes are set 
set them directly in ac_build_intrinsic, the only place that sets them

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20146>
 2022-12-06 13:27:16 +00:00
Marek Olšák e94b040add ac/llvm: remove illegal function attributes READONLY and WRITEONLY 
They are only legal on parameters.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20146>
 2022-12-06 13:27:16 +00:00
Marek Olšák 5104f4d496 ac/llvm: remove unused AC_FUNC_ATTR_LEGACY 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20146>
 2022-12-06 13:27:16 +00:00