Mesa (20.1): 35 new commits
GitLab Mirror
gitlab-mirror at kemper.freedesktop.org
Wed Aug 5 21:08:40 UTC 2020
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=2858b432f42c841fd9f794e686d3ed5841273588
Author: Eric Engestrom <eric at engestrom.ch>
Date: Wed Aug 5 23:08:10 2020 +0200
docs/relnotes: add sha256 sums to 20.1.5
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=3ba7f954b8a4ca6a8754fec06b8c0d179f2db64a
Author: Eric Engestrom <eric at engestrom.ch>
Date: Wed Aug 5 22:33:25 2020 +0200
VERSION: bump to release 20.1.5
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=8a71ecb28bb45cd542d79c34ebe2d880d4c19b2e
Author: Eric Engestrom <eric at engestrom.ch>
Date: Wed Aug 5 22:23:43 2020 +0200
docs: add release notes for 20.1.5
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=d03bf3ece563b61d89622263508a504486b3b956
Author: Marek Olšák <marek.olsak at amd.com>
Date: Mon May 4 18:25:28 2020 -0400
radeonsi: disable SDMA on gfx9
Fixes: 9680a754895 "radeonsi/gfx9: enable SDMA buffer copying & clearing"
Acked-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4895>
(cherry picked from commit 07a49bf59766b7c40d35608a98bd4a5796dcc2fe)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=65a6b36802617e780077cae586ab83c38e4ce5bb
Author: Kristian H. Kristensen <hoegsberg at google.com>
Date: Wed Jul 29 11:02:07 2020 -0700
anv: Pass device to setup_gralloc0_usage for error reporting
Otherwise it doesn't compile.
Reviewed-by: Eric Engestrom <eric at engestrom.ch>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Fixes: aba57b11ee8c6d ("anv: support GetSwapchainGrallocUsage2ANDROID for Android")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6112>
(cherry picked from commit ff0dbf2096148ef7513baa78646809826b7f42b4)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=d1ac2ffeb6d53df59182a41e87abc086d71c79c9
Author: Jason Ekstrand <jason at jlekstrand.net>
Date: Fri Jul 24 20:27:37 2020 -0500
nir/deref: Don't try to compare derefs containing casts
One day, we may want copy_prop_vars or other passes to be able to see
through certain types of casts such as when someone casts a uint64_t to
a uvec2. However, for now we should just avoid casts all together.
Fixes: d8e3edb784d3a "nir/deref: Support casts and ptr_as_array in..."
Tested-by: Jesse Natalie <jenatali at microsoft.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira at intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6072>
(cherry picked from commit 611f654fcf715364b65ca690c0521c3e3038824f)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=d23bbc8c28b6a5cd7f4d3d03c74d8319da5d47d5
Author: Jason Ekstrand <jason at jlekstrand.net>
Date: Wed Apr 29 17:14:58 2020 -0500
intel/eu: Use non-coherent mode (BTI=253) for stateless A64 messages
We don't care about full IA coherency since we always have the
opportunity in GL or Vulkan to flush the data cache. Using IA-coherent
mode is likely just making A64 access slower than it needs to be.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira at intel.com>
Reviewed-by: Kenneth Graunke <kenneth at whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4819>
(cherry picked from commit 4985e380dd776ac65c4ae5627138211f9d9f03ce)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=8202415ebc736e739f3bb1d3ec18dde9363ecaff
Author: Alyssa Rosenzweig <alyssa.rosenzweig at collabora.com>
Date: Fri Jul 31 10:43:55 2020 -0400
pan/mdg: Test for SSA before chasing addresses
It's possible an SSA value depends on a register; in this case, chasing
the source would result in a crash as the chase helper in NIR asserts
is_ssa. Instead we should check a priori that all the argments are in
fact SSA, bailing otherwise.
In the piglit shader exhibiting this bug (by looping over the index),
bailing on the ishl instruction is -necessary-. This is not merely us
being cowardly to avoid seeing through the registers; indeed, if we
wrote away the ishl instruction, the shift itself would have to be
stored in a load/store register (r26/r27) which would preclude reading
it in the loop, creating a register allocation failure later in the
compile. So this is the correct solution due to the restricted
semantics.
Closes #3286
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig at collabora.com>
Reported-by: Icecream95 <ixn at keemail.me>
Fixes: f5401cb8866 ("pan/midgard: Add address analysis framework")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6144>
(cherry picked from commit b2f475251ed9fa8b37cb98372e64d6166d48a089)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=3be7fca3ee2662599f7bf3205f88bc3114727a32
Author: Alyssa Rosenzweig <alyssa.rosenzweig at collabora.com>
Date: Fri Jul 31 10:31:50 2020 -0400
pan/mdg: Mask spills from texture write
This prevents RA failures the results of reading multiple textures that
require less than 4 channels, as seen in a number of GL 3 WebRender shaders.
Closes: #3342
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig at collabora.com>
Reported-by: Icecream95 <ixn at keemail.me>
Tested-by: Icecream95 <ixn at keemail.me>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6144>
(cherry picked from commit b4de9e035ac0afe64ebfd58cd0eb04c1a671afce)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=440275b3e25c3a4e9e3c4b70196c46941a72eba5
Author: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>
Date: Sat Aug 1 03:13:55 2020 +0200
mesa/st: Actually free the driver part of memory objects on destruction.
_mesa_delete_memory_object(ctx, obj) == free(obj) but doesn't free the
part of the gallium driver.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/1206
Fixes: 49f4ecc6777 "mesa/st: start adding memory object support"
Reviewed-by: Timothy Arceri <tarceri at itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6148>
(cherry picked from commit 99cf9108340c2ccf7c1b05ec6f951e2e91b9c76c)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=4fb918f45606a947c3414faca75ab4632622da03
Author: Mauro Rossi <issor.oruam at gmail.com>
Date: Thu Jul 23 22:50:32 2020 +0200
radv: fix build on Android 7 (v2)
Fixes the following building error:
external/mesa/src/amd/vulkan/radv_android.c:28:10: fatal error:
'vndk/hardware_buffer.h' file not found
^~~~~~~~~~~~~~~~~~~~~~~~
(v2) use the existing preprocessor condition #if ANDROID_API_LEVEL >= 26
Fixes: f36b527 "radv/android: Add android hardware buffer queries."
Reported-and-tested-by: youling 257 <youling257 at gmail.com>
Signed-off-by: Mauro Rossi <issor.oruam at gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6051>
(cherry picked from commit 80c135e6a6ade34f451e694d1c54598a75b1243e)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=d7158dcc12bb4ed0cae4998cdd6156b87e393077
Author: Marcin Ślusarz <marcin.slusarz at intel.com>
Date: Fri Jul 24 20:13:00 2020 +0200
intel/vec4: fix out of bounds read
NIR_MAX_VEC_COMPONENTS was bumped from 4 to 16 in a8ec4082
(2019.03.09, merged 2019.12.21)
float[4] array was added in acd7796a
(2019.06.11, merged 2019.07.11)
Found by Coverity.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3014
Signed-off-by: Marcin Ślusarz <marcin.slusarz at intel.com>
Fixes: a8ec4082a41 ("nir+vtn: vec8+vec16 support")
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6067>
(cherry picked from commit cb19fe24d361991104f8dcf54d1e807998766be1)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=3af72354feef361980d0fb028e29d66f5525d8e0
Author: Marcin Ślusarz <marcin.slusarz at intel.com>
Date: Fri Jul 24 19:19:07 2020 +0200
mesa: fix out of bounds access in glGetFramebufferParameterivEXT
ColorDrawBuffer is an array of MAX_DRAW_BUFFERS == 8.
Found by Coverity.
Signed-off-by: Marcin Ślusarz <marcin.slusarz at intel.com>
Fixes: 7534c536ca0 ("mesa: add EXT_dsa (Named)Framebuffer functions")
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6067>
(cherry picked from commit 0906d5d504eb0209556787b020a6df58b4cc3069)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=f2de23e7855cd5346acd3ea32c987ea88e5545db
Author: Marcin Ślusarz <marcin.slusarz at intel.com>
Date: Fri Jul 24 18:14:24 2020 +0200
util: fix possible buffer overflow in util_get_process_exec_path
Found by Coverity.
Signed-off-by: Marcin Ślusarz <marcin.slusarz at intel.com>
Fixes: f8f1413070a ("util/u_process: add util_get_process_exec_path")
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6067>
(cherry picked from commit f13042ec7ea6842cbee81590f40b0e5c2e25a9bf)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=75e81ff0d7720d3167039593e6af8391d776b25c
Author: Marcin Ślusarz <marcin.slusarz at intel.com>
Date: Fri Jul 24 17:51:25 2020 +0200
util: fix possible fd leaks in os_socket_listen_abstract
Found by Coverity.
Signed-off-by: Marcin Ślusarz <marcin.slusarz at intel.com>
Fixes: ef5266ebd50 ("util/os_socket: Add socket related functions.")
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6067>
(cherry picked from commit eac0ba7fc193cceccd953bc4726ceef750b18085)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=d0adfbc984ab40eddeda605c43fb9acd03aded96
Author: Frank Binns <frank.binns at imgtec.com>
Date: Tue Jul 28 15:50:30 2020 +0100
egl/dri2: only take a dri2_dpy reference when binding a new context/surfaces
This effectively reverts part of 2907faee, which changed dri2_make_current() to
always take a dri2_dpy reference regardless of whether or not a new context or
surface(s) were being bound. This led to a reference count imbalance as there
was no corresponding code added to drop a reference on the dri2_dpy. As a
consequence, any application that called eglInitialize() on a default/native
display after having called eglTerminate() would always get back the old
dri2_dpy, inheriting its previous state.
As the reference count is there to prevent the dri2_dpy from being destroyed
between eglTerminate() and eglInitialize() calls when a context is still bound,
a reference should only be taken when a successful call to
dri2_dpy->core->bindContext() has been made. Fix the issue by restoring the old
reference counting behaviour.
Fixes: 4e8f95f64d004 ("egl_dri2: Always unbind old contexts")
Fixes: 2907faee7a397 ("egl/dri2: try to bind old context if bindContext failed")
Signed-off-by: Frank Binns <frank.binns at imgtec.com>
Reviewed-by: Luigi Santivetti <luigi.santivetti at imgtec.com>
Reviewed-by: Emil Velikov <emil.velikov at collabora.com>
Tested-by: Nicolas Cortes <nicolas.g.cortes at intel.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3328
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6105>
(cherry picked from commit d0e32e5f8105eccd075ebbf42594100ed663fd6e)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=17991448a2eb0930b106068bffc366946a05556e
Author: Kenneth Graunke <kenneth at whitecape.org>
Date: Wed Jun 5 13:12:58 2019 -0700
iris: Delete shader variants when deleting the API-facing shader
We were space-leaking iris_compiled_shader objects, leaving them around
basically forever - long after the associated iris_uncompiled_shader was
deleted. Perhaps even more importantly, this left the BO containing the
assembly referenced, meaning those were never reclaimed either. For
long running applications, this can leak quite a bit of memory.
Now, when freeing iris_uncompiled_shader, we hunt down any associated
iris_compiled_shader objects and pitch those (and their BO) as well.
One issue is that the shader variants can still be bound, because we
haven't done a draw that updates the compiled shaders yet. This can
cause issues because state changes want to look at the old program to
know what to flag dirty. It's a bit tricky to get right, so instead
we defer variant deletion until the shaders are properly unbound, by
stashing them on a "dead" list and tidying that each time we try and
delete some shader variants.
This ensures long running programs delete their shaders eventually.
Fixes: ed4ffb97158 ("iris: rework program cache interface")
Reviewed-by: Matt Turner <mattst88 at gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6075>
(cherry picked from commit 128cbcd3a7ba543d644ed3189dcd668900b270f4)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=414247c1ad395f48bf7919b2e070cdc14a5b37b0
Author: Daryl W. Grunau <dwg at lanl.gov>
Date: Thu Jul 23 15:39:07 2020 -0600
prevent multiply defined symbols
Without this patch applied gcc at 10.1.0 fails to compile with the following
error (note mesa at 18.3.6 but the latest release also posseses this problem):
ld: ../../../../src/gallium/auxiliary/.libs/libgallium.a(u_debug_symbol.o):/tmp/spack/spack-stage/spack-stage-mesa-18.3.6-be7kyg2dyxwktir3zrai27n6a6coadab/spack-src/src/galli um/auxiliary/util/u_debug_symbol.c:273: multiple definition of `symbols_hash'; ../../../../src/gallium/auxiliary/.libs/libgallium.a(u_debug_stack.o):/tmp/spa ck/spack-stage/spack-stage-mesa-18.3.6-be7kyg2dyxwktir3zrai27n6a6coadab/spack-src/src/gallium/auxiliary/util/u_debug_stack.c:49: first defined here
collect2: error: ld returned 1 exit status
make[4]: *** [libGL.la] Error 1
make[4]: Leaving directory `/tmp/spack/spack-stage/spack-stage-mesa-18.3.6-be7kyg2dyxwktir3zrai27n6a6coadab/spack-src/src/gallium/targets/libgl-xlib'
make[3]: *** [all-recursive] Error 1
make[3]: Leaving directory `/tmp/spack/spack-stage/spack-stage-mesa-18.3.6-be7kyg2dyxwktir3zrai27n6a6coadab/spack-src/src/gallium'
make[2]: *** [all-recursive] Error 1
make[2]: Leaving directory `/tmp/spack/spack-stage/spack-stage-mesa-18.3.6-be7kyg2dyxwktir3zrai27n6a6coadab/spack-src/src'
make[1]: *** [all] Error 2
make[1]: Leaving directory `/tmp/spack/spack-stage/spack-stage-mesa-18.3.6-be7kyg2dyxwktir3zrai27n6a6coadab/spack-src/src'
make: *** [all-recursive] Error 1
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3298
Cc: mesa-stable
Reviewed-by: Michel Dänzer <mdaenzer at redhat.com>
Reviewed-by: Eric Engestrom <eric at engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6053>
(cherry picked from commit a400c2ff2265dfabb1ed7b59c8b24aa38d0557d1)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=b1442e2a6b5cf2116ed1031d76cf20ebd0c7fe6e
Author: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Date: Mon Jul 27 12:06:17 2020 +0300
anv: fix descriptor set free
Once we start going through the free list of the descriptor set pool,
we might use a free entry larger than the descriptor set we want to
allocate. When we free that descriptor set, we use the size of the set
rather than the size of the entry that was picked. This leads to leaks
of some amount of descriptor set pool.
This fix saves the size of the entry in the descriptor set so we know
what amount of the pool needs to freed.
v2: Don't bother adding a new size field
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Reviewed-by: Danylo Piliaiev <danylo.piliaiev at globallogic.com>
Cc: <mesa-stable at lists.freedesktop.org>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3324
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6084>
(cherry picked from commit 1cdd161a30297c13908134d8d205a7a377ec807a)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=370bd3ba471ad173a694083c59cd43d431721a06
Author: Yevhenii Kolesnikov <yevhenii.kolesnikov at globallogic.com>
Date: Fri Jun 26 13:40:43 2020 +0300
nine: fix incorrect calculation of layer count for 3D textures
Volume textures don't have a concept of "layers"
v1: set last_layer to zero for 3D textures (Axel Davy)
Cc: <mesa-stable at lists.freedesktop.org>
Signed-off-by: Yevhenii Kolesnikov <yevhenii.kolesnikov at globallogic.com>
Reviewed-by: Axel Davy <davyaxel0 at gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5808>
(cherry picked from commit 845a50ee2525c6cc4e6160eda1826c0670e0daaf)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=33d59a360933a3e3017f220ea7e23ac82f885ee8
Author: Marcin Ślusarz <marcin.slusarz at intel.com>
Date: Tue Jul 28 11:55:16 2020 +0200
i965: propagate error from gen_perf_begin_query to glBeginPerfQueryINTEL
Otherwise mesa will crash in glEndPerfQueryINTEL because OA BO is NULL.
Signed-off-by: Marcin Ślusarz <marcin.slusarz at intel.com>
Cc: <mesa-stable at lists.freedesktop.org>
Reviewed-by: Mark Janes <mark.a.janes at intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6094>
(cherry picked from commit 884718313c80a2902b6f60b6ded63a6290d40ac7)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=e650150c812df4381150a5f13d59c6d60c9e657d
Author: Marcin Ślusarz <marcin.slusarz at intel.com>
Date: Mon Jul 27 21:10:25 2020 +0200
iris: propagate error from gen_perf_begin_query to glBeginPerfQueryINTEL
Otherwise mesa will crash in glEndPerfQueryINTEL because OA BO is NULL.
Signed-off-by: Marcin Ślusarz <marcin.slusarz at intel.com>
Cc: <mesa-stable at lists.freedesktop.org>
Reviewed-by: Mark Janes <mark.a.janes at intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6094>
(cherry picked from commit 627c01977c29d142d5024591bf910a1ed92814c9)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=6c1358b0248eb3a07d999ec2d20dab0cc42c25eb
Author: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>
Date: Tue Jul 28 04:14:23 2020 +0200
radv: Fix host->host signalling with legacy timeline semaphores.
Fixes: 88d41367b8a "radv: Add timelines with a VK_KHR_timeline_semaphore impl."
Reviewed-by: Dave Airlie <airlied at redhat.com>
Tested-by: Andres Rodriguez <andresx7 at gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6097>
(cherry picked from commit 05b278327066304d8822eb6414a89120c816e14a)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=92c179f52aa4541a3433529260d129ee7e1c648b
Author: Bas Nieuwenhuizen <bas at basnieuwenhuizen.nl>
Date: Fri Jul 24 21:56:04 2020 +0200
radv: Fix uninitialized variable in renderpass.
Fixes some dEQP-VK.renderpass2.* flakes. Valgrind:
Test case 'dEQP-VK.renderpass2.dedicated_allocation.attachment.8.724'..
==754520== Conditional jump or move depends on uninitialised value(s)
==754520== at 0x575B21C: radv_layout_is_htile_compressed (radv_image.c:1690)
==754520== by 0x572F470: radv_handle_depth_image_transition (radv_cmd_buffer.c:5855)
==754520== by 0x572F2F2: radv_handle_image_transition (radv_cmd_buffer.c:6123)
==754520== by 0x572EEC6: radv_handle_subpass_image_transition (radv_cmd_buffer.c:3385)
==754520== by 0x572A104: radv_cmd_buffer_begin_subpass (radv_cmd_buffer.c:4843)
==754520== by 0x572A007: radv_CmdBeginRenderPass (radv_cmd_buffer.c:4913)
==754520== by 0x572A197: radv_CmdBeginRenderPass2 (radv_cmd_buffer.c:4921)
Why false?
A renderloop happens when the same attachment is both used as input
attachment and output (color, ds) attachment in a subpass. Of course
this doesn't happen outside of a renderpass and hence we can initialize
it to false at the start of the renderpass.
Fixes: 66131ceb8bc "radv: Pass through render loop detection to internal layout decisions."
Reviewed-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Reviewed-by: Daniel Schürmann <daniel at schuermann.dev>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3074
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6068>
(cherry picked from commit 18fe130ec9e07213c5b4e1e46232e3c3c1835057)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=fcd612ba5687456fa86c20f0016d5a887560515d
Author: Daniel Schürmann <daniel at schuermann.dev>
Date: Thu Jul 23 09:41:07 2020 +0200
aco: prevent infinite recursion in RA for subdword variables
Cc: 20.1 <mesa-stable at lists.freedesktop.org>
Reviewed-by: Rhys Perry <pendingchaos02 at gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6024>
(cherry picked from commit 4c89bfc4ec0ea29ab757b0391bf646673e483668)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=692df26b7d17b85d8d0b6f331b357db76e50f1d5
Author: Daniel Schürmann <daniel at schuermann.dev>
Date: Wed Jul 22 18:41:53 2020 +0200
aco: don't split store data if it was already split into more elements
Cc: 20.1 <mesa-stable at lists.freedesktop.org>
Reviewed-by: Rhys Perry <pendingchaos02 at gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6024>
(cherry picked from commit 626081fe4bf653a18cff9e25e6da2636bc58774a)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=797ed40aa70681099d792ad7a8be699741315645
Author: Francisco Jerez <currojerez at riseup.net>
Date: Sun May 31 14:56:40 2020 -0700
intel/ir/gen12+: Work around FS performance regressions due to SIMD32 discard divergence.
This avoids some performance regressions on Gen12 platforms caused by
SIMD32 fragment shaders reported in titles like Dota2, TF2, Xonotic,
and GFXBench5 Car Chase and Aztec Ruins.
The most obvious pattern in the regressing shaders I identified among
these workloads is that they all had non-uniform discard statements,
which are handled rather optimistically by the current IR analysis
pass: No penalty is currently applied to the SIMD32 variant of the
shader in the form of differing branching weights like we do for other
control flow instructions in order to account for the greater
likelihood of divergence of a SIMD32 shader.
Simply changing that by giving the same treatment to discard
statements as we give to other branching instructions seemed to hurt
more than it helped on platforms earlier than Gen12, since it reversed
most of the improvement obtained from SIMD32 fragment shaders in
Manhattan for no measurable benefit in other workloads (Manhattan has
a handful of shaders with statically non-uniform discard statements
which actually perform better in SIMD32 mode due to their approximate
dynamic uniformity). For that reason this change is applied to Gen12+
platforms only.
I've been running a number of tests trying to understand the
difference in behavior between Gen12 and earlier platforms, and most
of the evidence I've gathered seems to point at EU fusion being the
culprit: Unlike previous generations, on Gen12 EUs are arranged in
pairs which execute instructions in lockstep, giving an effective warp
size of 64 threads in SIMD32 mode, which seems to increase the
likelihood for control flow divergence in some of the affected shaders
significantly.
Fixes: 188a3659aea6dec9acf1 "intel/ir: Import shader performance analysis pass."
Reported-by: Caleb Callaway <caleb.callaway at intel.com>
Reviewed-by: Matt Turner <mattst88 at gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5910>
(cherry picked from commit 4d73988f6fef39e9263ec0bb49cd5efff68393bc)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=33f8d25fa4ccfcf9263e7abc58d2af58c0e59d3a
Author: Eric Engestrom <eric at engestrom.ch>
Date: Thu Jul 9 01:25:39 2020 +0200
bin/gen_release_notes: automatically commit release notes
Cc: mesa-stable
Signed-off-by: Eric Engestrom <eric at engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5833>
(cherry picked from commit ae2d0457679dfa6d79faa3009daadd11d6a92f5c)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=402e0f1291f0e1050756fa2dae8663978cc47e7c
Author: Marek Olšák <marek.olsak at amd.com>
Date: Mon Jul 6 23:51:25 2020 -0400
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: 0bf3e6fae7f82b4f16fbcbb05a1ae47f7930e189 "radeonsi/gfx10: double the number of tessellation offchip buffers per SE"
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
(cherry picked from commit 1c6eca23fdd8bc112c70914100601d0e382a8154)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=684712ef7327042cc6412807d3a538f09f75de9c
Author: Marek Olšák <marek.olsak at amd.com>
Date: Mon Jul 6 22:05:00 2020 -0400
radeonsi: add missing initialization of registers
(random initial gfx10 commit:)
Fixes: 78cdf9a99f0 - amd/addrlib: add gfx10 support
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5798>
(cherry picked from commit d244a25c072557edd1133356b94557938c000f78)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=67dfe6d93298840a5cb0d119fb06ba371ea85b93
Author: Marek Olšák <marek.olsak at amd.com>
Date: Wed Feb 5 16:55:41 2020 -0500
ac: update register and packet definitions for preemption
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5095>
(cherry picked from commit 3509d3bd53e6b386e8e153e8e3f701b3f631fc8c)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=2646170bcdc95eff636d48dc07d7e5863fb54796
Author: Daniel Schürmann <daniel at schuermann.dev>
Date: Mon Jul 20 12:07:55 2020 +0200
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 at lists.freedesktop.org>
Reviewed-by: Rhys Perry <pendingchaos02 at gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5977>
(cherry picked from commit 7015d2c249e1f7814bf5681ccd049e49e4d6495c)
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=3c7d8b7f7ee97a4aa031c99f9391fad9fbe86d02
Author: Eric Engestrom <eric at engestrom.ch>
Date: Wed Jul 29 12:53:55 2020 +0200
.pick_status.json: Mark 1b3be07b5faf867f698668080b060a270c5f795e as denominated
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=aee70840d04b3c3c43f5750cf912d52c24b21f9a
Author: Eric Engestrom <eric at engestrom.ch>
Date: Wed Jul 29 12:53:54 2020 +0200
.pick_status.json: Mark bd75e9923302a3d389469b7b233968576a46f4de as denominated
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=5da36d6e69862ac55de5a8056353c57e4b170c72
Author: Eric Engestrom <eric at engestrom.ch>
Date: Wed Jul 22 23:48:12 2020 +0200
.pick_status.json: Update to caa98246a0e180a96f3fcdcd3bfcbef0b136bc11
More information about the mesa-commit
mailing list