OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
126,392 Commits 9 Branches 1 Tag
b84dbd29369c47215c7d25c52319b65c4d48c239
Commit Graph

126392 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Marek Olšák
b84dbd2936 radeonsi: reorder code in update_gs_ring_buffers and init_tess_factor_ring 
to reduce the churn when adding codepaths for shadowed registers

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
 2020-07-22 12:08:19 -04:00
Marek Olšák
babd87f2e0 radeonsi: make cs_preamble_state optional 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
 2020-07-22 12:08:19 -04:00
Marek Olšák
7a6af4c5ed winsys/amdgpu: make amdgpu_bo_unmap non-static 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
 2020-07-22 12:08:19 -04:00
Marek Olšák
5a5467ccc8 ac: add tables for CP register shadowing 
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
 2020-07-22 12:08:19 -04:00
Marek Olšák
dc3dade475 ac: add helper ac_get_register_name 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
 2020-07-22 12:08:19 -04:00
Marek Olšák
976edae839 radeonsi: sort registers in si_init_cs_preamble_state according to GPU gen 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
 2020-07-22 12:08:19 -04:00
Marek Olšák
88fe9dea7a radeonsi: sort registers in si_emit_initial_compute_regs according to GPU gen 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
 2020-07-22 12:08:19 -04:00
Marek Olšák
1c6eca23fd radeonsi/gfx10: set the correct value for OFFCHIP_BUFFERING 
Copied from PAL. Higher values break tessellation, which I was only able
to reproduce with register shadowing enabled.

Fixes: 0bf3e6fae7 "radeonsi/gfx10: double the number of tessellation offchip buffers per SE"

Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
 2020-07-22 12:08:19 -04:00
Marek Olšák
d244a25c07 radeonsi: add missing initialization of registers 
(random initial gfx10 commit:)
Fixes: 78cdf9a99f - amd/addrlib: add gfx10 support

Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
 2020-07-22 12:08:19 -04:00
Erik Faye-Lund
fd20e98624 docs: add some very basic documentation about zink 
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Reviewed-by: Marcin Ślusarz <marcin.slusarz@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5967>
 2020-07-22 15:20:00 +00:00
Samuel Pitoiset
202592a398 radv/winsys: be more robust when a CS failed during recording 
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/5872>
 2020-07-22 15:06:20 +00:00
Samuel Pitoiset
f82eb7af87 radv/winsys: return a Vulkan error code when binding virtual buffers/images 
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/5872>
 2020-07-22 15:06:20 +00:00
Samuel Pitoiset
4b58e35a2a radv/winsys: remove useless check when binding virtual buffers/images 
Size must be greater than 0.

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/5872>
 2020-07-22 15:06:20 +00:00
Samuel Pitoiset
f0112fa13c radv/winsys: check more allocation failures 
While we are at it, use local variables first to make sure to
not leak memory if something bad happens.

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/5872>
 2020-07-22 15:06:20 +00:00
Samuel Pitoiset
7a61e31d7b radv: add missing return values check for some winsys calls 
Make sure to handle errors properly.

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/5872>
 2020-07-22 15:06:20 +00:00
Danylo Piliaiev
348e8b5618 nir/tests: Add tests for opt_if_simplification 
Test cases:

opt_if_simplification - the most trivial test case.

opt_if_simplification_single_source_phi_after_if - tests that
opt_if_simplification correctly handles single-source phis after
the if, found in https://gitlab.freedesktop.org/mesa/mesa/-/issues/3282

Signed-off-by: Danylo Piliaiev <danylo.piliaiev@globallogic.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5945>
 2020-07-22 14:20:21 +00:00
Danylo Piliaiev
6f94b3da11 nir/opt_if: Fix opt_if_simplification when else branch has jump 
Consider the following case:

 if ssa_1 {
    block block_2:
    /* succs: block_4 */
 } else {
    block block_3:
    ...
    break
    /* succs: block_5 */
 }

 block block_4:
 vec1 32 ssa_100 = phi block_2: ssa_2

After block_3 extraction and reinsertion, phi->pred becomes invalid
and isn't updated by reinsertion since it is unreachable from block_3.

Call nir_opt_remove_phis_block before moving block to eliminate single
source phis after the if.

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3282
Fixes: e3e929f8c3
Signed-off-by: Danylo Piliaiev <danylo.piliaiev@globallogic.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5945>
 2020-07-22 14:20:21 +00:00
Mike Blumenkrantz
3f783a3c50 zink: omit Lod image operand in ntv when not using an image texture dim 
according to spec, this is invalid (and it's not being used anyway)

Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5911>
 2020-07-22 14:01:29 +00:00
Mike Blumenkrantz
0ef5e19874 zink: add some asserts for building access chains in ntv 
we're never going to pass a 0 here, and it's going to be an error if we do

Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5911>
 2020-07-22 14:01:29 +00:00
Mike Blumenkrantz
2af22051c0 zink: handle texelFetchOffset with offsets 
we need to explicitly add the offset in this case since it's not available
as a spirv param

fixes spec@glsl-1.30@execution@fs-texelfetchoffset-2d

Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5911>
 2020-07-22 14:01:29 +00:00
Mike Blumenkrantz
6587f41e11 zink: use helper function to handle uvec/bvec types 
bit_size of 1 means we use a bool type here, 32 means uint, so we can just
handle that automatically for all relevant cases

ref shaders@glsl-vs-continue-in-switch-in-do-while

Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5911>
 2020-07-22 14:01:29 +00:00
Daniel Schürmann
7015d2c249 aco: fix scratch loads which cross element_size boundaries 
Previously, we've set element_size == 16 which causes loads from
packed vec3 arrays to cross the boundary and return wrong data.
This patch sets element_size = 4 and splits loads into single channel.
Fixes all of dEQP-VK.subgroups.ballot_broadcast.*

Cc: 20.1 <mesa-stable@lists.freedesktop.org>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5977>
 2020-07-22 13:12:25 +00:00
Erik Faye-Lund
c33e8d7d52 mesa/program: fix shadow property for samplers 
When creating a sampler-type, we need to pass the correct vaclue for
the "is_shadow"-parameter to glsl_sampler_type(), otherwise the compiler
backend will have no clue about this being a shadow-sampler.

Fixes: 1c0f92d8a8 ("nir: Create sampler variables in prog_to_nir.")
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5986>
 2020-07-22 12:51:51 +00:00
Tomeu Vizoso
4b04800efa ci: Disable trace testing on Mali T760 
The machine is showing random mis-renderings and we don't have time now
to investigate. Comment it out for now so CI pipelines don't fail due to
it.

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6023>
 2020-07-22 12:31:57 +00:00
Samuel Pitoiset
6c1108d25b radv: advertise VK_EXT_shader_atomic_float 
No hw support for float atomic add for buffer and (sparse) images.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6000>
 2020-07-22 10:20:58 +02:00
Samuel Pitoiset
b8517e5ef9 ac/nir: add support for nir_intrinsic_shared_atomic_fadd 
Only LLVM 10+ has support.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6000>
 2020-07-22 10:20:53 +02:00
Samuel Pitoiset
7615f2d690 aco: add support for nir_intrinsic_shared_atomic_fadd 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6000>
 2020-07-22 10:01:59 +02:00
Tomeu Vizoso
97482c6f92 ci: Test with more traces 
Use some more traces from traces-db in the existing jobs.

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Andres Gomez <agomez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6008>
 2020-07-22 05:57:41 +00:00
Tomeu Vizoso
87e0b2c1c2 ci: Prefix tracie artifacts with the device name 
Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Andres Gomez <agomez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6008>
 2020-07-22 05:57:41 +00:00
Tomeu Vizoso
ed5374ff50 ci: Use smaller glxgears trace 
A smaller version of this trace has been pushed to traces-db, so update
to use this instead.

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Andres Gomez <agomez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6008>
 2020-07-22 05:57:41 +00:00
Tomeu Vizoso
dfe394bac4 ci: Upload images of failed replays to MinIO 
For the llvmpipe and virgl jobs.

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Andres Gomez <agomez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6008>
 2020-07-22 05:57:41 +00:00
Rhys Kidd
7dc4fe6fb4 nvc0: add documentation for nve4+ (Kepler) COPY class 
Has been utilised within nouveau in place of the former M2MF class, which was
dropped for Kepler in PGRAPH in favour of:

  - a new P2MF object that only does simple upload; and
  - PCOPY took over responsibility of M2MF's other DMA functions.

Autogenerated headers from envytools commit 32659e654170cb03038ccf2cb165decd3a2409d6

NVIDIA documentation released at:
  https://github.com/NVIDIA/open-gpu-doc/blob/master/classes/dma-copy/cla0b5.h

Signed-off-by: Rhys Kidd <rhyskidd@gmail.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5982>
 2020-07-22 05:49:08 +00:00
Rhys Kidd
203d565b19 nvc0: fix macro define for NVE4_COPY() 
Fixes: e44089b2f7 ("nvc0: add initial support for nve4+ (Kepler) chipsets")
Signed-off-by: Rhys Kidd <rhyskidd@gmail.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5982>
 2020-07-22 05:49:08 +00:00
Lionel Landwerlin
3a4024e776 anv: properly handle fence import of sync_fd = -1 
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 43e8808b82 ("anv: Add support for the SYNC_FD handle type for fences")
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5964>
 2020-07-22 05:07:05 +00:00
Bas Nieuwenhuizen
323d5bbfd9 meson: Add mising git_sha1.h dependency. 
Fixes: 606dff1b73 "vulkan/overlay: Add support for a control socket."
Reviewed-by: Dylan Baker <dylan.c.baker@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6019>
 2020-07-22 00:02:26 +00:00
Rhys Perry
12b99d2581 aco: fix includes in aco_ir.cpp 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3300
Fixes: e75946cfef ('aco: move some setup code into helpers')
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6015>
 2020-07-21 22:15:55 +00:00
Jonathan Marek
8fff8afb13 turnip: disable tiling for NV12/IYUV formats 
The last change to my previous MR to disable UBWC for the formats ended up
breaking a few tests for A640 at least, because tiled-but-not-UBWC can be
broken in some cases.

Fixes: 1a83279da5 ("turnip: enable 420_UNORM formats")

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5817>
 2020-07-21 20:08:07 +00:00
Connor Abbott
b559d26c74 freedreno/ir3: Fix SSBO size for bindless SSBO's 
We theoretically could push these sizes to the const file
opportunistically, which appears to be what the blob does, but the
maximum number of SSBO's is way too big to do that unconditionally. Just
use resinfo to get the size for now.

Fixes on turnip: dEQP-VK.ssbo.unsized_array_length.*

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6012>
 2020-07-21 19:53:32 +00:00
Rhys Perry
c11c4d8d4c aco: fix copy of uninitialized boolean 
This should be harmless but UBSan seems to complain.

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/6013>
 2020-07-21 19:38:43 +00:00
Rhys Perry
40b65a86a4 radv: fix invalid conversion warnings in vk_format.h 
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/6013>
 2020-07-21 19:38:43 +00:00
Rhys Perry
fcd8f69113 aco: print ACO IR before scheduling instead of after 
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/6013>
 2020-07-21 19:38:43 +00:00
Rhys Perry
bf4b377b9b aco: make validate() usable in tests 
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/6013>
 2020-07-21 19:38:43 +00:00
Rhys Perry
e75946cfef aco: move some setup code into helpers 
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/6013>
 2020-07-21 19:38:43 +00:00
Luigi Santivetti
2907faee7a egl/dri2: try to bind old context if bindContext failed 
This change mostly touches error handling code paths, where a
bug was found when the DRI driver failed to bind a new DRI
context. Specifically, the reason for it to fail was the window
system unable (for whatever reason) to provide the DRI drawable
with a buffer. In this instance, Mesa un-does the EGL bindings,
but doesn't restore the old DRI context, hence remaining in a
funny state. It's worth mentioning that despite trying, there
is no guarantee that the old DRI context can be restored,
depending on the runtime.

Before this change, if bindContext() failed then
dri2_make_current() would rebind the old EGL context and
surfaces and return EGL_BAD_MATCH. However, it wouldn't rebind
the DRI context and surfaces, thus leaving it in an
inconsistent and unrecoverable state.

After this change, dri2_make_current() tries to bind the old
DRI context and surfaces when bindContext() failed. If unable
to do so, it leaves EGL and the DRI driver in a consistent
state, it reports an error and returns EGL_BAD_MATCH.

Fixes: 4e8f95f64d ("egl_dri2: Always unbind old contexts")

Signed-off-by: Luigi Santivetti <luigi.santivetti@imgtec.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Acked-by: Eric Engestrom <eric@engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5707>
 2020-07-21 18:42:03 +00:00
Luigi Santivetti
8b0b6f907d dri2: do not conflate unbind and bindContext() failure 
dri2_make_current() has become hard to follow, address this by
splitting the semantic of needing a call to bindContext() and
its failure.

Cc: mesa-stable
Signed-off-by: Luigi Santivetti <luigi.santivetti@imgtec.com>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5707>
 2020-07-21 18:42:03 +00:00
Luigi Santivetti
6b12999ef7 dri2: dri2_make_current() fold multiple if blocks 
dri2_make_current() has become long and convoluted. Address
this by folding together multiple if blocks checking for the
same variable.

Cc: mesa-stable
Signed-off-by: Luigi Santivetti <luigi.santivetti@imgtec.com>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5707>
 2020-07-21 18:42:03 +00:00
Rhys Perry
29c39aeaab aco: use nir_addition_might_overflow to combine additions into SMEM 
fossil-db (Navi):
Totals from 24656 (18.14% of 135946) affected shaders:
CodeSize: 120077160 -> 118877304 (-1.00%); split: -1.01%, +0.01%
Instrs: 23192657 -> 22979553 (-0.92%); split: -0.94%, +0.02%
VMEM: 165151115 -> 151861460 (-8.05%); split: +0.14%, -8.19%
SMEM: 18133265 -> 16709635 (-7.85%); split: +0.28%, -8.13%
VClause: 385011 -> 384447 (-0.15%); split: -0.16%, +0.02%
SClause: 954884 -> 838266 (-12.21%); split: -12.34%, +0.12%

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/2720>
 2020-07-21 18:25:35 +00:00
Rhys Perry
72ac3f6026 nir: add nir_unsigned_upper_bound and nir_addition_might_overflow 
This adds a nir_unsigned_upper_bound() helper which does something similar
to nir_analyze_range() except it tries to obtain the largest possible
value instead of it's relation to zero.

It also adds nir_addition_might_overflow(), which uses this helper to try
to prove that an unsigned addition does not wrap around.

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/2720>
 2020-07-21 18:25:35 +00:00
Rhys Perry
2694a34aa2 aco: add NUW flag 
This (combined with a pass to actually set the corresponding NIR flags)
should help fix a lot of the regressions from the SMEM addition combining
change.

fossil-db (Navi):
Totals from 12 (0.01% of 135946) affected shaders:
CodeSize: 12376 -> 12304 (-0.58%)
Instrs: 2436 -> 2422 (-0.57%)
VMEM: 1105 -> 1096 (-0.81%)
SClause: 133 -> 130 (-2.26%)

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/2720>
 2020-07-21 18:25:35 +00:00
Rhys Perry
3a4847179b aco: allow overflow for some SMEM instructions 
fossil-db (Navi):
Totals from 10184 (7.49% of 135946) affected shaders:
CodeSize: 83419748 -> 82430824 (-1.19%); split: -1.19%, +0.01%
Instrs: 16054612 -> 15908523 (-0.91%); split: -0.93%, +0.02%
VMEM: 1608018 -> 1581829 (-1.63%); split: +0.20%, -1.83%
SMEM: 577031 -> 563492 (-2.35%); split: +0.10%, -2.45%
VClause: 242643 -> 242512 (-0.05%); split: -0.06%, +0.00%
SClause: 640966 -> 569897 (-11.09%)

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/2720>
 2020-07-21 18:25:35 +00:00