Matt Turner [Tue, 16 Jun 2020 23:53:57 +0000 (16:53 -0700)]
intel/tools: Remove unnecessary reg number checking
a0 is the only address register, and cr0 is the only control register,
so there's no need to return the register number, espcially since the
lexer explicitly consumes "a0" and "cr0".
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5514>
Jonathan Marek [Wed, 17 Jun 2020 20:05:07 +0000 (16:05 -0400)]
turnip: move enum translation functions to a common header
Instead of having these functions sprinkled around the driver (and ending
with a duplicated tu6_compare_func for example), move everything to a
common header (using the previously unused tu_util.h).
Also applied some simplifications: using a cast when the HW enum matches
the VK enum, and using a lookup table when it makes sense (which is IMO
nicer than the switch case way).
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5538>
Rhys Perry [Thu, 18 Jun 2020 12:52:28 +0000 (13:52 +0100)]
aco: use the same regclass as the definition for undef phi operands
Subdword phis can't have SGPR operands on GFX6-8.
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/5544>
Rhys Perry [Thu, 18 Jun 2020 12:30:50 +0000 (13:30 +0100)]
aco: fix edge check with sub-dword temporaries
Fixes RA failure for a parallel-rdp shader on pitcairn.
fossil-db (Navi):
Totals from 2 (0.00% of 128733) affected shaders:
CodeSize: 203656 -> 205724 (+1.02%)
Instrs: 32267 -> 32529 (+0.81%)
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/5544>
Erik Faye-Lund [Wed, 17 Jun 2020 21:50:06 +0000 (23:50 +0200)]
mesa/main: fix inverted condition
I accidentally got one of the conditions wrong here. Sorry for the
mixup.
See ttps://gitlab.freedesktop.org/mesa/mesa/-/issues/3134 for details.
Fixes: b112e62ba48 ("mesa/main: do not allow MESA_ycbcr_texture enums on gles")
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5532>
Karol Herbst [Mon, 15 Jun 2020 23:08:39 +0000 (01:08 +0200)]
nv50/ir/nir: remove image uniform hack
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5480>
Karol Herbst [Mon, 15 Jun 2020 16:30:39 +0000 (18:30 +0200)]
nv50/ir/nir: handle image atomic inc and dec
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5480>
Karol Herbst [Mon, 15 Jun 2020 12:36:18 +0000 (14:36 +0200)]
nv50/ir/nir: move away from image_deref intrinsics
v2: fix lod source of image operation correctly
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5480>
Karol Herbst [Mon, 15 Jun 2020 16:30:12 +0000 (18:30 +0200)]
nir/lower_images: handle dec and inc
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Gert Wollny <gert.wollny@collabora.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5480>
Karol Herbst [Mon, 15 Jun 2020 16:29:58 +0000 (18:29 +0200)]
nir/lower_images: fix for array of arrays
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5480>
Karol Herbst [Mon, 15 Jun 2020 13:14:58 +0000 (15:14 +0200)]
st/mesa: lower images when needed
The "st/pbo download FS" builtin shader uses image derefs, so even with
PIPE_CAP_NIR_IMAGES_AS_DEREF set to 0 drivers ended up with those.
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Gert Wollny <gert.wollny@collabora.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5480>
Rhys Perry [Mon, 1 Jun 2020 15:19:56 +0000 (16:19 +0100)]
aco: shrink mad_info
From 24 bytes to 16 bytes.
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/5281>
Rhys Perry [Mon, 1 Jun 2020 10:27:53 +0000 (11:27 +0100)]
aco: make ssa_info::label 64-bit
We'll probably need these extra bits in the future.
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/5281>
Rhys Perry [Mon, 1 Jun 2020 15:13:09 +0000 (16:13 +0100)]
aco: shrink ssa_info
Reorder members so that it's 16 bytes instead of 24.
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/5281>
Boyuan Zhang [Thu, 11 Jun 2020 23:22:51 +0000 (19:22 -0400)]
radeon/vcn: bump vcn3.0 encode major version to 1
And add quality params for this version
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: James Zhu <James.Zhu@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5501>
Boyuan Zhang [Thu, 11 Jun 2020 23:17:03 +0000 (19:17 -0400)]
radeon/vcn/enc: Re-write PPS encoding for HEVC
Due to hardware change on VCN3
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: James Zhu <James.Zhu@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5501>
Thong Thai [Thu, 11 Jun 2020 23:02:27 +0000 (19:02 -0400)]
radeon/vcn: add vcn 3.0 encode support
Signed-off-by: Thong Thai <thong.thai@amd.com>
Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: James Zhu <James.Zhu@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5501>
Leo Liu [Thu, 11 Jun 2020 23:27:57 +0000 (19:27 -0400)]
radeon/vcn/dec: add db_aligned_height to message buffer
This is required for Sienna
Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: James Zhu <James.Zhu@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5501>
Leo Liu [Thu, 11 Jun 2020 22:40:07 +0000 (18:40 -0400)]
radeon/vcn: add Sienna to use internal register offset
And re-group them explicitly
Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: James Zhu <James.Zhu@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5501>
Leo Liu [Thu, 11 Jun 2020 22:28:25 +0000 (18:28 -0400)]
radeon/vcn: reset the decode flags from message buffer
This flag was never used by VCN previously, and now
it's used for feature that is not applied to us.
Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: James Zhu <James.Zhu@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5501>
Daniel Schürmann [Wed, 17 Jun 2020 11:41:09 +0000 (12:41 +0100)]
aco: fix WQM handling in nested loops
If on a nested loop
- the outer loop needs WQM but
- the inner loop doesn't need WQM and
- the break condition of the inner loop is computed in the outer loop
then it could happen that we transitioned to Exact before entering the inner loop
which could create an empty exec mask and lead to an infinite loop.
Fixes a GPU hang with RDR2
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/5518>
Danylo Piliaiev [Fri, 12 Jun 2020 13:04:44 +0000 (16:04 +0300)]
st/mesa: account for "loose", per-mipmap level textures in CopyImageSubData
We may have "loose", per-image gallium resources. The src_image->Level
may not match the gallium resource texture level. In such case it is
prescribed (in st_AllocTextureImageBuffer) to specify mipmap level
as zero.
Fixes: f04f13622f3e71bee057d60a6be9c53b92b56cc9
Signed-off-by: Danylo Piliaiev <danylo.piliaiev@globallogic.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5477>
Gurchetan Singh [Mon, 15 Jun 2020 17:52:57 +0000 (10:52 -0700)]
virgl: apply bgra dest swizzle and add Portal 2
Apply the destination swizzle on GLES games based on HL2 engine.
Also add Portal 2 since some people are experiencing issues with
that.
Reviewed-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5481>
Jonathan Marek [Wed, 17 Jun 2020 13:57:56 +0000 (09:57 -0400)]
turnip: set the API version
Some CTS tests don't run because of this.
Fixes: 91c757b7963f458 ("turnip: use the common code for generating extensions and dispatch tables")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5522>
Samuel Pitoiset [Sat, 13 Jun 2020 12:23:17 +0000 (14:23 +0200)]
radv: only requires LLVM 9 for GFX10 if not using ACO
In case someone links RADV with LLVM 8 and wants to use ACO.
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/5454>
Neil Armstrong [Fri, 24 Apr 2020 09:07:32 +0000 (11:07 +0200)]
Revert "CI: Disable Panfrost Mali-T820 jobs"
This reverts commit
46a32f0b6bf91279d001a4905babe4e50007696e.
The lab has recovered health, thus re-enable T820 Panfrost jobs.
Acked-by: Michel Dänzer <mdaenzer@redhat.com>
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4727>
Neil Armstrong [Fri, 24 Apr 2020 09:07:31 +0000 (11:07 +0200)]
Revert "CI: Disable Lima jobs due to lab unhealthiness"
This reverts commit
adeef43d15092a6910dceb3605f5ee3151dd2c47.
The lab has recovered health, thus re-enable Lima jobs.
Acked-by: Michel Dänzer <mdaenzer@redhat.com>
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4727>
Samuel Pitoiset [Thu, 11 Jun 2020 14:27:17 +0000 (16:27 +0200)]
radv: compute CB_SHADER_MASK from the fragment shader outputs
The fragment shader doesn't necessarily output the number of components
expected by the target format.
Fixes new dEQP-VK.draw.output_location.*.
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/5427>
Samuel Pitoiset [Thu, 11 Jun 2020 13:39:46 +0000 (15:39 +0200)]
radv: make sure to set CB_SHADER_MASK correctly for internal CB operations
It should be always set to 0xf.
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/5427>
Erik Faye-Lund [Thu, 18 Jun 2020 08:43:36 +0000 (10:43 +0200)]
docs/features: remove driver-list for forward-compatible context
This is something that's supported by the Gallium state-tracker, there's
nothing to be done per driver here.
Erik Faye-Lund [Thu, 18 Jun 2020 08:41:43 +0000 (10:41 +0200)]
docs/features: update ARB_texture_buffer_object line
This extension isn't just exposed in OpenGL 3.1 contexts any longer, and
Zink supports it. Let's mark it as such.
Erik Faye-Lund [Thu, 18 Jun 2020 08:40:27 +0000 (10:40 +0200)]
docs/features: mark GL3 as complete for zink
Samuel Pitoiset [Wed, 17 Jun 2020 14:35:05 +0000 (16:35 +0200)]
radv: lower discards to demote to workaround a RDR2 game bug
This fixes some sort of LOD issue.
Cc: 20.1 <mesa-stable@lists.freedesktop.org>
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/5525>
Rob Clark [Wed, 17 Jun 2020 00:46:43 +0000 (17:46 -0700)]
glsl_to_nir: fix vote_any/vote_all
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5505>
Rob Clark [Wed, 17 Jun 2020 00:45:59 +0000 (17:45 -0700)]
glsl_to_nir: fix shader_clock
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5505>
Rob Clark [Tue, 16 Jun 2020 23:36:32 +0000 (16:36 -0700)]
glsl_to_nir: fix is_helper_invocation
Reported-by: Karol Herbst <kherbst@redhat.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5505>
Rob Clark [Tue, 16 Jun 2020 18:23:26 +0000 (11:23 -0700)]
spirv: drop some dead code
This case is never hit, we don't have a nir intrinsic for this spirv
opcode. And when we do, I'm not sure if it would be vectorized or not.
So best just to drop this case.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5505>
Rob Clark [Tue, 16 Jun 2020 18:21:29 +0000 (11:21 -0700)]
spirv: atomic_counter_read_deref is not vectorized
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3141
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5505>
Jonathan Marek [Tue, 16 Jun 2020 14:45:58 +0000 (10:45 -0400)]
turnip: fix renderpass gmem configs when there are too many attachments
Since a value of at least "align" is used for nblocks, we might end up
with nblocks greater than the number of GMEM blocks remaining. Check for
this case and bail out, sysmem rendering will be used for such cases.
Fixes some of these tests:
dEQP-VK.pipeline.render_to_image.core.*.huge.*
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5499>
Jonathan Marek [Tue, 16 Jun 2020 13:11:02 +0000 (09:11 -0400)]
turnip: fix a sample shading case
Check pipeline's sampleShadingEnable to enable sample shading.
Also fix behavior of gl_Fragcoord with sample shading.
Fixes at least:
dEQP-VK.pipeline.multisample.min_sample_shading.min_0_5.samples_4.primitive_triangle
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5499>
Jonathan Marek [Wed, 17 Jun 2020 18:23:37 +0000 (14:23 -0400)]
turnip: fix a crash when rasterizerDiscardEnable is set
pMultisampleState needs to be ignored when rasterizerDiscardEnable, so the
current code can crash when trying to load msaa_info->pNext.
At the same time this simplifies tu_pipeline_shader_key_init a bit, by not
calling it for the compute shader case (which doesn't need to set anything
in the key struct).
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5499>
Eric Engestrom [Fri, 22 Nov 2019 14:21:05 +0000 (14:21 +0000)]
docs: remind release maintainers to sign the tarballs and publish their key
Signed-off-by: Eric Engestrom <eric.engestrom@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2857>
Eric Engestrom [Fri, 22 Nov 2019 14:10:50 +0000 (14:10 +0000)]
docs: publish our release maintainers' keys
They should be published to various key servers as well, but this
provides the authoritative source for their list.
Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2140
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2857>
Rob Clark [Sun, 14 Jun 2020 16:53:11 +0000 (09:53 -0700)]
freedreno/ir3: update obsolete comment
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5458>
Rob Clark [Sat, 13 Jun 2020 17:43:00 +0000 (10:43 -0700)]
freedreno/computerator: MERGEDREGS update
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5458>
Rob Clark [Sat, 13 Jun 2020 16:35:40 +0000 (09:35 -0700)]
turnip: set .MERGEDREGS based on variant
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5458>
Rob Clark [Sat, 13 Jun 2020 16:31:11 +0000 (09:31 -0700)]
freedreno/a6xx: set .MERGEREGS based on variant
Also set HALFREGFOOTPRINT, since in the non-mergeregs case this will be
non-zero.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5458>
Rob Clark [Sat, 13 Jun 2020 03:48:36 +0000 (20:48 -0700)]
freedreno/ir3: make mergedregs a property of the variant
Rather than assuming a6xx+ means mergedregs. We can actually (mostly?)
do splitregs on a6xx as well. And GS/DS/HS currently require it, which
might be papering over a bug, or might be something to do with how
chaining shaders works. At any rate, we should at least be consistent,
and not have the compiler thinking we are doing mergedregs when we are
actually doing splitregs.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5458>
Rob Clark [Sat, 13 Jun 2020 17:49:47 +0000 (10:49 -0700)]
freedreno/ir3: re-work assembler API
Just pass thru the variant, since it has everything we need. And
will be needed in the next patch.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5458>
Rob Clark [Sat, 13 Jun 2020 16:23:57 +0000 (09:23 -0700)]
freedreno/ir3: pass variant to postsched
Prep for the next patch.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5458>
Rob Clark [Sat, 13 Jun 2020 03:56:48 +0000 (20:56 -0700)]
freedreno/ir3: decouple regset from gpu gen
Allow different regset's to coexist, so we can make mergedregs vs split
reg file a variant property.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5458>
Rob Clark [Sat, 13 Jun 2020 03:42:36 +0000 (20:42 -0700)]
freedreno/ir3: move mergedreg state out of reg
It is only needed one place, let's move it there.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5458>
Rob Clark [Sat, 13 Jun 2020 03:33:31 +0000 (20:33 -0700)]
freedreno/ir3: convert regmask_t to struct
Prep to make merged/split register file mode a property of the regmask,
rather than the ir3_register.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5458>
Jonathan Marek [Tue, 9 Jun 2020 22:48:34 +0000 (18:48 -0400)]
freedreno/fdl6: rework layout code a bit (reduce linear align to 64 bytes)
Reduce linear alignment, and rework the layout code a bit.
This rework has a side effect of also increasing the alignment on linear
levels of tiled (non-ubwc) cpp=1 and cpp=2 layouts. Since we should be
UBWC for those cases anyway, its not a big loss.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5013>
Jonathan Marek [Tue, 12 May 2020 16:34:37 +0000 (12:34 -0400)]
freedreno/a6xx: FETCHSIZE is PITCHALIGN
"FETCHSIZE" is actually a "minimum pitch" or "pitchalign" value that's
relevant for mipmaps. The 0 value means 64-bytes. Understanding this allows
some simplifications and will make it possible to use less alignment on
linear formats.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5013>
Eric Engestrom [Fri, 5 Jun 2020 08:55:41 +0000 (10:55 +0200)]
virgl: replace all dup() with os_dupfd_cloexec()
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Fri, 5 Jun 2020 08:55:35 +0000 (10:55 +0200)]
svga: replace all dup() with os_dupfd_cloexec()
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Fri, 5 Jun 2020 08:22:47 +0000 (10:22 +0200)]
freedreno: replace all dup() with os_dupfd_cloexec()
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Fri, 5 Jun 2020 08:22:29 +0000 (10:22 +0200)]
etnaviv: replace all dup() with os_dupfd_cloexec()
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Fri, 5 Jun 2020 08:22:22 +0000 (10:22 +0200)]
egl: replace all dup() with os_dupfd_cloexec()
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Fri, 5 Jun 2020 08:55:03 +0000 (10:55 +0200)]
i965: replace all dup() with os_dupfd_cloexec()
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Fri, 5 Jun 2020 08:54:51 +0000 (10:54 +0200)]
iris: replace all dup() with os_dupfd_cloexec()
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Fri, 5 Jun 2020 08:54:43 +0000 (10:54 +0200)]
anv: replace all dup() with os_dupfd_cloexec()
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Fri, 5 Jun 2020 08:22:04 +0000 (10:22 +0200)]
radv: replace all dup() with os_dupfd_cloexec()
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Fri, 5 Jun 2020 08:55:22 +0000 (10:55 +0200)]
vulkan/wsi: replace all dup() with os_dupfd_cloexec()
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Thu, 4 Jun 2020 23:09:35 +0000 (01:09 +0200)]
replace all F_DUPFD_CLOEXEC with os_dupfd_cloexec()
All squashed into a single commit because it shouldn't have any
behaviour change, except that it might work now on platforms where it
was broken because F_DUPFD_CLOEXEC is not supported but FD_CLOEXEC is.
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Thu, 4 Jun 2020 23:08:33 +0000 (01:08 +0200)]
util: introduce os_dupfd_cloexec() helper
Adapted from wayland's wl_os_dupfd_cloexec().
Suggested-by: Kristian H. Kristensen <hoegsberg@google.com>
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Engestrom [Fri, 5 Jun 2020 10:39:28 +0000 (12:39 +0200)]
util/os_file: replace broken windows-detection code with detect_os.h
The meson-windows-vs2019 job was going down the `!defined(WIN32)` path,
leading to a broken build once that path contained non-windows code.
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5369>
Eric Anholt [Wed, 17 Jun 2020 22:29:31 +0000 (15:29 -0700)]
ci: disable the windows tests until the runner can be stabilized again
I've been getting a stream of errors from Marge today like:
FAILED: src/gallium/drivers/llvmpipe/lp_test_conv.exe
link @src/gallium/drivers/llvmpipe/lp_test_conv.exe.rsp
LINK : fatal error LNK1102: out of memory
[1080/1141] Compiling C object src/gallium/frontends/wgl/
945cc3d@@wgl@sta/stw_getprocaddress.c.obj
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5534>
Eric Engestrom [Fri, 22 May 2020 23:26:57 +0000 (01:26 +0200)]
docs: remove plain-text copy of versions.rst
There's no need to keep both, so let's clean things up a bit.
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5178>
Eric Engestrom [Fri, 22 May 2020 22:28:23 +0000 (00:28 +0200)]
khronos-update.py: add script to simplify update of Khronos headers & xml files
The idea is to have the canonical source of each of those files
available without having to remember anything, and to be able to update
all the Vulkan files by simply running `bin/khronos-update.py vulkan`.
The script also handles the fact all the EGL/GL/GLES* headers depend on
the KHR header, and the former should not be updated without updating
the latter.
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5177>
Mike Blumenkrantz [Mon, 1 Jun 2020 19:01:47 +0000 (15:01 -0400)]
zink: enable xfb extension in screen creation
switch around the feature enabling as well since extensions need the related
feature to also be enabled in order to function
fixes mesa/mesa#2868
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5163>
Mike Blumenkrantz [Wed, 3 Jun 2020 12:45:57 +0000 (08:45 -0400)]
zink: switch to passing VkPhysicalDeviceFeatures2 in VkDeviceCreateInfo
extensions need to have their feature structs passed in pNext to be enabled,
so switch to using the feature struct here in preparation for that
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5163>
Mike Blumenkrantz [Wed, 17 Jun 2020 17:47:22 +0000 (13:47 -0400)]
zink: set PIPE_CAP_VIEWPORT_TRANSFORM_LOWERED and remove POS special casing
this cap creates a different varying output which remains constant to be
emitted by xfb, allowing us to drop the special-casing code in ntv
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5163>
Mike Blumenkrantz [Mon, 1 Jun 2020 18:59:15 +0000 (14:59 -0400)]
zink: implement transform feedback support to finish off opengl 3.0
this adds:
* context hooks for gallium stream output methods
* handling for xfb-related queries
* barrier management for pausing and resuming xfb
loosely based on patches originally written by Dave Airlie <airlied@redhat.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5163>
Mike Blumenkrantz [Mon, 1 Jun 2020 18:49:44 +0000 (14:49 -0400)]
zink: implement streamout and xfb handling in ntv
this translates streamout info into xfb decorations and adds some workaround
handling for spurious gl_PointSize values
partly based on patches originally written by Dave Airlie <airlied@redhat.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5163>
Mike Blumenkrantz [Thu, 4 Jun 2020 21:01:58 +0000 (17:01 -0400)]
zink: add spirv_builder methods for OpVectorExtractDynamic and OpVectorInsertDynamic
based on spirv specs
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5163>
Mike Blumenkrantz [Mon, 1 Jun 2020 18:55:38 +0000 (14:55 -0400)]
zink: add spirv builder util functions for emitting xfb decorations
based on patches originally written by Dave Airlie <airlied@redhat.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5163>
Mike Blumenkrantz [Wed, 20 May 2020 14:08:42 +0000 (10:08 -0400)]
zink: use '2' variants for device props/feats, check features for ext enabling
technically both the extension and feature should be checked when enabling
extensions, and some features cannot be properly enabled without using
the more descriptive versions of these APIs
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5163>
Jonathan Marek [Mon, 15 Jun 2020 20:31:33 +0000 (16:31 -0400)]
turnip: use u_format for packing gmem clear values
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5485>
Erik Faye-Lund [Mon, 15 Jun 2020 09:52:42 +0000 (11:52 +0200)]
docs: fixup relnotes after rst-conversion
Acked-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5468>
Samuel Pitoiset [Fri, 5 Jun 2020 07:27:01 +0000 (09:27 +0200)]
radv/aco: enable FP16 features/extensions on GFX9+
This enables shaderFloat16, VK_AMD_gpu_shader_half_float and
VK_AMD_gpu_shader_int16.
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/5347>
Rhys Perry [Wed, 17 Jun 2020 13:50:10 +0000 (14:50 +0100)]
aco: fix validation of opsel when set for the definition
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/5521>
Jonathan Marek [Tue, 16 Jun 2020 16:34:57 +0000 (12:34 -0400)]
turnip: use draw states for input attachments
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5446>
Jonathan Marek [Mon, 15 Jun 2020 03:10:01 +0000 (23:10 -0400)]
turnip: input attachment descriptor set rework
Implement GMEM input attachments by using non-bindless texture state which
is emitted at the start of every subpass.
This achieves two things:
* More vulkan-like CmdBindDescriptorSets
* Fixing secondary command buffer input attachments with GMEM
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5446>
Jonathan Marek [Sun, 14 Jun 2020 14:52:37 +0000 (10:52 -0400)]
turnip: refactor draw states and dynamic states
This reworks dynamic states to use draw states, and reworks draw states.
This moves towards doing as little as possible in bind_draw_states.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5446>
Jonathan Marek [Sun, 14 Jun 2020 14:34:25 +0000 (10:34 -0400)]
turnip: delete dead dynamic state code
Remove unused code, split this out to reduce the diff in the next patch.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5446>
Jonathan Marek [Sun, 14 Jun 2020 14:30:10 +0000 (10:30 -0400)]
turnip: improve dirty bit handling a bit
This moves some logic out of bind_draw_states, moving towards the eventual
goal of doing very little in bind_draw_states.
Split this out as a separate patch to make the DIRTY_INPUT_ATTACHMENTS more
visible: it can be safely removed because pipelines are subpass specific,
so there will always be a pipeline change to go with the CmdBeginRenderPass
and CmdNextSubpass (the CmdBindPipeline may not be in the subpass, but the
draw that flushes the pipeline update will be).
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5446>
Jonathan Marek [Sun, 14 Jun 2020 14:17:28 +0000 (10:17 -0400)]
turnip: move descriptor set BO tracking to CmdBindDescriptorSets
This avoids the duplicated code.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5446>
Jonathan Marek [Sun, 14 Jun 2020 14:15:45 +0000 (10:15 -0400)]
turnip: compute and graphics have completely separate state
The comment about fragment shader state overwriting compute shader state
is wrong, if either path is overwriting the other's state then it is a
mistake.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5446>
Connor Abbott [Wed, 17 Jun 2020 13:39:18 +0000 (15:39 +0200)]
tu: Actually remove dead variables after io lowering
I forgot that their derefs would still be lying around, so we need to
eliminate them first.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5519>
Connor Abbott [Wed, 17 Jun 2020 09:07:26 +0000 (11:07 +0200)]
ir3: Don't calculate num_samp ourselves
In addition to duplicating what core NIR does better, this was wrong for
Vulkan, where it should be 0 as there are no non-bindless samplers.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5519>
Connor Abbott [Wed, 17 Jun 2020 13:47:29 +0000 (15:47 +0200)]
tu: Set num_components to 0 when building bindless intrinsics
Fixes: 167fa288 (" nir/validate: validate intr->num_components")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5520>
Connor Abbott [Tue, 16 Jun 2020 15:00:31 +0000 (17:00 +0200)]
tu: Remove tu_shader_compile_options
The only two fields were always true, and I don't think we'd ever have
use for them. If we want to disable optimizations then we'd need a
different approach, and I don't even know what include_binning_pass was
for.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5500>
Connor Abbott [Tue, 16 Jun 2020 09:44:23 +0000 (11:44 +0200)]
tu: Use the ir3 shader API
This will be necessary once we start compiling multiple variants due to
different const size limits, and it will also be necessary for properly
implementing the pipeline cache.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5500>
Connor Abbott [Wed, 17 Jun 2020 11:02:49 +0000 (13:02 +0200)]
tu: Remove num_samp hack
Delete the variables so that ir3 thinks there are no samplers and
images instead.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5500>
Connor Abbott [Tue, 16 Jun 2020 12:02:24 +0000 (14:02 +0200)]
ir3: Pass reserved_user_consts to ir3_shader_from_nir()
ir3_shader_from_nir() calls ir3_optimize_nir(), which currently sets up
the const state. However, we need to know the number of user consts
reserved by the driver before setting up the const state, which means
that this information needs to be passed into ir3_shader_from_nir()
somehow rather than being set in the shader.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5500>
Alyssa Rosenzweig [Fri, 12 Jun 2020 21:56:32 +0000 (17:56 -0400)]
pan/mdg: Reassociate adds for multiply-by-two
Only a single shader-db change it looks like, and not even from
scheduling, no fun.
instructions helped: shader31 MESA_SHADER_FRAGMENT: 64 -> 63 (-1.56%)
quadwords helped: shader31 MESA_SHADER_FRAGMENT: 66 -> 65 (-1.52%)
registers HURT: shader31 MESA_SHADER_FRAGMENT: 2 -> 3 (50.00%)
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5475>
Alyssa Rosenzweig [Fri, 12 Jun 2020 21:47:19 +0000 (17:47 -0400)]
pan/mdg: Canonicalize (x * 2.0) to (x + x)
This lets the previous commit kick in to schedule to either a multiply
or an add. GLES2 shader-db:
total instructions in shared programs: 50514 -> 50459 (-0.11%)
instructions in affected programs: 7436 -> 7381 (-0.74%)
helped: 14
HURT: 7
helped stats (abs) min: 2 max: 8 x̄: 5.00 x̃: 5
helped stats (rel) min: 0.95% max: 1.14% x̄: 1.07% x̃: 1.08%
HURT stats (abs) min: 2 max: 3 x̄: 2.14 x̃: 2
HURT stats (rel) min: 0.85% max: 8.57% x̄: 2.73% x̃: 1.26%
95% mean confidence interval for instructions value: -4.37 -0.87
95% mean confidence interval for instructions %-change: -0.91% 1.31%
Inconclusive result (%-change mean confidence interval includes 0).
total bundles in shared programs: 25680 -> 25573 (-0.42%)
bundles in affected programs: 6148 -> 6041 (-1.74%)
helped: 37
HURT: 7
helped stats (abs) min: 1 max: 9 x̄: 3.14 x̃: 2
helped stats (rel) min: 0.63% max: 8.33% x̄: 2.02% x̃: 2.13%
HURT stats (abs) min: 1 max: 2 x̄: 1.29 x̃: 1
HURT stats (rel) min: 0.88% max: 11.11% x̄: 3.92% x̃: 1.30%
95% mean confidence interval for bundles value: -3.32 -1.54
95% mean confidence interval for bundles %-change: -2.00% -0.14%
Bundles are helped.
total quadwords in shared programs: 40887 -> 40815 (-0.18%)
quadwords in affected programs: 14203 -> 14131 (-0.51%)
helped: 61
HURT: 2
helped stats (abs) min: 1 max: 4 x̄: 1.21 x̃: 1
helped stats (rel) min: 0.16% max: 11.11% x̄: 1.11% x̃: 0.57%
HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel) min: 2.86% max: 4.00% x̄: 3.43% x̃: 3.43%
95% mean confidence interval for quadwords value: -1.32 -0.96
95% mean confidence interval for quadwords %-change: -1.46% -0.48%
Quadwords are helped.
total registers in shared programs: 3916 -> 3913 (-0.08%)
registers in affected programs: 46 -> 43 (-6.52%)
helped: 5
HURT: 1
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 10.00% max: 33.33% x̄: 14.89% x̃: 10.00%
HURT stats (abs) min: 2 max: 2 x̄: 2.00 x̃: 2
HURT stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
95% mean confidence interval for registers value: -1.79 0.79
95% mean confidence interval for registers %-change: -33.51% 25.37%
Inconclusive result (value mean confidence interval includes 0).
total threads in shared programs: 2455 -> 2454 (-0.04%)
threads in affected programs: 5 -> 4 (-20.00%)
helped: 1
HURT: 1
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 100.00% max: 100.00% x̄: 100.00% x̃: 100.00%
HURT stats (abs) min: 2 max: 2 x̄: 2.00 x̃: 2
HURT stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
total loops in shared programs: 6 -> 6 (0.00%)
loops in affected programs: 0 -> 0
helped: 0
HURT: 0
total spills in shared programs: 168 -> 168 (0.00%)
spills in affected programs: 0 -> 0
helped: 0
HURT: 0
total fills in shared programs: 186 -> 186 (0.00%)
fills in affected programs: 0 -> 0
helped: 0
HURT: 0
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5475>
Alyssa Rosenzweig [Fri, 12 Jun 2020 21:24:02 +0000 (17:24 -0400)]
pan/mdg: Allow scheduling "x + x" to multipliers
One of the neat things with Midgard's wacky VLIW... on VADD/SADD this is
(x + x) literally, on VMUL/SMUL/VLUT this is (x * 2.0) where the 2.0 is
exactly representable in FP16 so it fits nicely as an inline constant.
So we don't need to restrict its scheduling.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5475>
projects / mesa.git / log