Eric Anholt [Mon, 11 May 2020 20:28:58 +0000 (13:28 -0700)]
freedreno: Split the fd_batch_resource_used by read vs write.
This is for an optimization I plan in a following commit. I found I had
to add likely()s to avoid a perf regression from branch prediction.
On the drawoverhead 8 UBOs test, the HW can't quite keep up with the CPU,
but if I set nohw then this change is 1.32023% +/- 0.373053% (n=10).
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4996>
Eric Anholt [Mon, 11 May 2020 20:53:48 +0000 (13:53 -0700)]
freedreno: Add a nohw flag to skip submitting to the kernel.
For some CPU-side-only optimizations, it can be nice to disable rendering
so that we can see what the impact is even on cases where the GPU can't
quite keep up.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4996>
Brian Ho [Mon, 4 May 2020 20:55:06 +0000 (13:55 -0700)]
turnip: Execute ir3_nir_lower_gs pass again
This commit fixes a GS regression introduced in !4562 where
ir3's GS lowering pass was moved from common code (ir3_nir) to
freedreno-specific code (ir3_shader). For GS support in turnip, we
need to add the GS lowering pass back in, this time in tu_shader.
As for the nir_gather_info change, the GS lowering pass has always
introduced a discard_if intrinsic into the GS. Previously, we simply
ran nir_shader_gather_info before GS lowering, but now since we lower
the GS before we need to remove the assertion that only a FS can use
the discard_if intrinsic.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4892>
Rob Clark [Fri, 8 May 2020 23:35:29 +0000 (16:35 -0700)]
freedreno/gmem: rework gmem layout algo
And try a bit harder to find an optimal layout. Improves on a sub-
optimal layout we arrive at in the 4 MRT pass in manhattan, picking
up a bit more than 3%.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4976>
Rob Clark [Sat, 9 May 2020 16:42:14 +0000 (09:42 -0700)]
freedreno/gmem: relax alignment on a6xx
The blob only uses single page alignment, and empirically that appears
to work just fine.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4976>
Rob Clark [Sat, 9 May 2020 20:19:14 +0000 (13:19 -0700)]
freedreno: add gmemtool
A simple standalone thing to run through a bunch of GMEM layouts for a
given gpu.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4976>
Rob Clark [Sat, 9 May 2020 16:38:02 +0000 (09:38 -0700)]
freedreno/gmem: add helper to dump GMEM layout
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4976>
Rob Clark [Fri, 8 May 2020 23:13:59 +0000 (16:13 -0700)]
freedreno/gmem: add div_align() helper
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4976>
Rob Clark [Sat, 9 May 2020 19:31:20 +0000 (12:31 -0700)]
freedreno: initialize max_scissor
Somehow the initialization of this got lost somewhere along the way,
resulting in assuming minx/miny are always zero.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4976>
Rob Clark [Sat, 9 May 2020 19:29:43 +0000 (12:29 -0700)]
freedreno/gmem: don't assume scissor opt when estimating # of bins
We potentially don't know yet what the resulting scissor bounds are, so
we can't assume this when estimating number of bins per pipe for VSC
size calculations.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4976>
Jason Ekstrand [Fri, 8 May 2020 07:06:26 +0000 (02:06 -0500)]
vulkan: Handle vkGet/SetPrivateDataEXT on Android swapchains
There is an annoying spec corner on Android. Because VkSwapchain is
implemented in the Vulkan loader on Android which may not know about
this extension, we have to handle it as a special case inside the
driver. We only have to do this on Android and only for VkSwapchainKHR.
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4882>
Jason Ekstrand [Tue, 21 Apr 2020 21:31:25 +0000 (16:31 -0500)]
anv,vulkan: Implement VK_EXT_private_data
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4882>
Jonathan Marek [Tue, 12 May 2020 15:28:51 +0000 (11:28 -0400)]
turnip: enable tiling for compressed formats
Now that layout code supports this, we can enable it.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5009>
Jonathan Marek [Tue, 12 May 2020 15:26:05 +0000 (11:26 -0400)]
turnip: update "fetchsize" value to match fdl6_layout changes
It seems this is actually a "minimum pitch" value. For example
TFETCH6_2_BYTE means a minimum pitch of 128 bytes for mipmap levels.
This fixes breakage with compressed formats. For example this test:
dEQP-VK.pipeline.sampler.view_type.2d.format.eac_r11_snorm_block.mipmap.linear.lod.equal_min_3_max_3
Fixes: a34b3fa198a4f ("freedreno/fdl: Align after dividing by block size")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5009>
Eric Anholt [Mon, 11 May 2020 18:18:02 +0000 (11:18 -0700)]
freedreno: Fix non-constbuf-upload UBO block indices and count.
The nir_analyze_ubo_ranges pass removes all UBO block 0 loads to reverse
what nir_lower_uniforms_to_ubo() had done, and we only upload UBO pointers
to the HW for UBO block 1-N, so let's just fix up the shader state.
Fixes an off by one in const state layout setup, and some really dodgy
register addressing trying to deal with dynamic UBO indices when the UBO
pointers happen to be at the start of the constbuf.
There's no fixes tag, though this fixes a bug from September, because it
would require the num_ubos fix in nir_lower_uniforms_to_ubo.
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4992>
Eric Anholt [Mon, 11 May 2020 18:53:22 +0000 (11:53 -0700)]
nir: Fix count when we didn't lower load_uniforms but did shift load_ubos.
The fixed commit was really nice in mostly fixing num_ubos to reflect the
shader after lowering, but for
dEQP-GLES31.functional.compute.basic.ubo_to_ssbo_single_invocation there
are no default uniforms and so we skipped the increment, even though we
shifted the block index up.
Fixes: 4777ee1a62f0 ("nir: Always create UBO variable when lowering uniforms to ubo")
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4992>
Eric Anholt [Mon, 11 May 2020 16:46:03 +0000 (09:46 -0700)]
freedreno: Drop the "write" arg to emit_const_bo now relocs don't care.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4967>
Eric Anholt [Fri, 8 May 2020 19:39:36 +0000 (12:39 -0700)]
freedreno: Replace OUT_RELOCW with OUT_RELOC.
Final cleanup commit now that they're the same.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4967>
Eric Anholt [Fri, 8 May 2020 19:28:08 +0000 (12:28 -0700)]
freedreno: Tell the kernel that all BOs are for writing.
Using non-write flags is pretty dubious -- it means the kernel tracking an
array of read-only consumers of the BO and having exclusive consumers wait
on each reader's fence. It allows multiple readers through dma-bufs to do
work in parallel, but at the cost of kernel CPU time and memory management
of the shared array. Other drivers have dropped this distinction since
dma-buf sharing is usually producer-consumer, not producer-two-consumers,
and the userspace and kernel space tracking is expensive.
For us, this lets us drop the flags passed in for relocs and tracked in
the ringbuffer reloc lists. The end result of the flags reduction work is
drawoverhead uniforms test throughput 2.37195% +/- 0.365579% (n=15)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4967>
Eric Anholt [Fri, 8 May 2020 18:28:14 +0000 (11:28 -0700)]
freedreno: Mark all ringbuffer BOs as to be dumped on crash.
We can avoid passing these flags around in the DRM backends by just
marking ring BOs up front.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4967>
Eric Anholt [Fri, 8 May 2020 18:24:12 +0000 (11:24 -0700)]
freedreno: Replace OUT_RELOCD with permanently flagging shader BOs for it.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4967>
Eric Anholt [Fri, 8 May 2020 18:20:07 +0000 (11:20 -0700)]
freedreno: Start moving relocs flags into the BOs.
It's silly to have all the reloc emitters passing around FD_RELOC_READ
when you have to have it set on all relocs (that don't include WRITE,
which implies read) for the kernel to actually track the fences on the BO.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4967>
Samuel Pitoiset [Thu, 2 Apr 2020 15:41:36 +0000 (17:41 +0200)]
aco: optimize add/sub(a, cndmask(b, 0, 1, cond)) -> addc/subbrev_co(0, a, b)
v2: outline into a separate function and also optimize additions (by Daniel Schürmann)
Totals from affected shaders: (VEGA)
SGPRS: 938888 -> 941496 (0.28 %)
VGPRS: 832068 -> 831532 (-0.06 %)
Spilled SGPRs: 618 -> 618 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 3696 -> 3696 (0.00 %) dwords per thread
Code Size:
72893900 ->
72558928 (-0.46 %) bytes
LDS: 18201 -> 18201 (0.00 %) blocks
Max Waves: 64256 -> 64268 (0.02 %)
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Co-authored-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4419>
Daniel Schürmann [Thu, 7 May 2020 17:19:54 +0000 (18:19 +0100)]
aco: coalesce parallelcopies during register allocation
These are the result of lowering to CSSA, and should be removed if possible
Totals from affected shaders: (VEGA)
SGPRS: 544544 -> 544544 (0.00 %)
VGPRS: 418224 -> 418224 (0.00 %)
Spilled SGPRs: 141826 -> 141826 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 0 -> 0 (0.00 %) dwords per thread
Code Size:
65853740 ->
64703380 (-1.75 %) bytes
LDS: 0 -> 0 (0.00 %) blocks
Max Waves: 13669 -> 13669 (0.00 %)
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4952>
Jon Turney [Wed, 6 May 2020 15:09:56 +0000 (16:09 +0100)]
glthread: Fix use of alloca() without #include "c99_alloca.h"
../src/mesa/main/glthread_draw.c: In function ‘_mesa_marshal_MultiDrawElementsBaseVertex’:
../src/mesa/main/glthread_draw.c:812:36: error: implicit declaration of function ‘alloca’; did you mean ‘malloc’? [-Werror=implicit-function-declaration]
812 | const GLvoid **out_indices = alloca(sizeof(indices[0]) * draw_count);
| ^~~~~~
| malloc
../src/mesa/main/glthread_draw.c:812:36: error: initialization of ‘const GLvoid **’ {aka ‘const void **’} from ‘int’ makes pointer from integer without a cast [-Werror=int-conversion]
cc1: some warnings being treated as errors
Include c99_alloca.h to portably make the alloca() prototype available.
Fixes: 2840bc30
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4920>
Lucas Stach [Thu, 6 Feb 2020 16:11:03 +0000 (17:11 +0100)]
etnaviv: generalize FE stall before loading shader and sampler states
It seems that some of the new shader and sampler states added with
Halti0 are not self-synchronizing anymore. Make sure to stall the FE
before loading those new states to avoid corruption of the in-flight
draw state.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3963>
Daniel Stone [Tue, 12 May 2020 10:33:06 +0000 (11:33 +0100)]
CI: Re-enable Panfrost T7x0 jobs
The hardware issue in the lab preventing jobs from being run on those
machines (and limiting T820 availability), leading to them being
disabled in !4965, has been fixed.
Signed-off-by: Daniel Stone <daniels@collabora.com>
Fixes: 696bafac40f5 ("CI: Disable Panfrost T7x0 jobs")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5006>
Samuel Pitoiset [Mon, 11 May 2020 10:04:51 +0000 (12:04 +0200)]
radv: update the list of allowed Android extensions
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4985>
Samuel Pitoiset [Mon, 11 May 2020 09:58:26 +0000 (11:58 +0200)]
radv: handle different Vulkan API versions correctly
Loosely based on ANV.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4985>
Samuel Pitoiset [Mon, 11 May 2020 08:52:18 +0000 (10:52 +0200)]
radv: limit the Vulkan version to 1.1 for Android
Vulkan 1.2 seems rejected. This hardcodes the Android version to
1.1.107.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2936
Fixes: 7f5462e349a ("radv: enable Vulkan 1.2")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4985>
Gert Wollny [Mon, 11 May 2020 07:03:41 +0000 (09:03 +0200)]
r600: Fix nir compiler options, i.e. don't lower IO to temps for TESS
Also fix alignments and add umad24 and umul24 options.
Fixes: 6747a984f59ea9a2dd74b98d59cb8fdb028969ae
r600: Enable tesselation for NIR
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4982>
Alejandro Piñeiro [Thu, 7 May 2020 09:46:25 +0000 (11:46 +0200)]
v3d/tex: use TMUSLOD register if possible
TMUSLOD register is the same that TMUS but having the same effect that
setting disable_autolod on the TMU configuration parameter 2.
So using that register is potentially more efficient, as in several
cases we would be able to skip writing P2.
One case where we can't use it is for texture cube maps, as we need to
use TMUSCM.
v2: don't put a comment in the middle of the conditions (Iago)
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4962>
Alejandro Piñeiro [Wed, 29 Apr 2020 08:29:50 +0000 (10:29 +0200)]
v3d/tex: set up default values for Configuration Parameter 1 if possible
Texture access has three configuration parameters, P0 (texture), P1
(sampler) and P2(lookup). P1 and P2 are optional, but if P2 is needed
(like for example to set the offset for texelFetchOffset), then you
need to set P1.
But until now when setting up P1 we were asking the driver to fill up
the address with the shader state. But in that case we can just fill
that address with the default value NULL.
So let's avoid asking the driver to fill that default values, and do
it directly on the compiler. This is a good-to-have on OpenGL, and
likely would be needed on Vulkan.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4962>
Alejandro Piñeiro [Tue, 28 Apr 2020 22:33:47 +0000 (00:33 +0200)]
v3d/tex: only look up the 2nd texture gather offset for 1d non-arrays
Commit
1bc71e8b655f2f02b3e3a0af34c7cad12b9cb83d already did that for
the 3rd offset, but it also needs to do it for the 2nd (to handle 1d
array).
Fixes assertion failures with Vulkan CTS tests using 1darray
targets. Seems that there isn't too many 1darray tests on OpenGL CTS,
and OpenGL-ES don't support 1d arrays, but the same problem could
arise eventually on OpenGL.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4962>
Ani [Mon, 11 May 2020 14:45:47 +0000 (14:45 +0000)]
drirc: Enable glthread for rpcs3
Closes: #2939
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4988>
Icecream95 [Mon, 11 May 2020 22:16:31 +0000 (10:16 +1200)]
pan/midgard: Fix old style shadows
This fixes the sky being red in OpenMW, as well as some of the Mesa
demos using shadows (shadowtex, shadow_sampler).
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4997>
Axel Davy [Sun, 10 May 2020 18:12:56 +0000 (20:12 +0200)]
gallium/util: Fix leak in the live shader cache
When the nir backend is used, the create_shader
call is supposed to release state->ir.nir.
When the cache hits, create_shader is not called,
thus state->ir.nir should be freed.
There is nothing to be done for the TGSI case as the
tokens release is done by the caller.
This fixes a leak noticed in:
https://gitlab.freedesktop.org/mesa/mesa/-/issues/2931
Fixes: 4bb919b0b8b4ed6f6a7049c3f8d294b74b50e198
Signed-off-by: Axel Davy <davyaxel0@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4980>
Ian Romanick [Tue, 31 Mar 2020 23:57:03 +0000 (16:57 -0700)]
nir/algebraic: Eliminate useless extract before unpack
The shader helped for spills and fills is the big compute shader in Dirt
Showdown. One of the shaders hurt for spills and fills on Broadwell is
the big compute shader in Bioshock Infinite, but combined with the
previous commit, it's still an impovement.
Tiger Lake
total instructions in shared programs:
21833218 ->
21832449 (<.01%)
instructions in affected programs: 66104 -> 65335 (-1.16%)
helped: 106
HURT: 14
helped stats (abs) min: 1 max: 67 x̄: 7.87 x̃: 5
helped stats (rel) min: 0.19% max: 5.76% x̄: 1.27% x̃: 0.95%
HURT stats (abs) min: 1 max: 14 x̄: 4.64 x̃: 1
HURT stats (rel) min: 0.19% max: 4.12% x̄: 1.41% x̃: 0.19%
95% mean confidence interval for instructions value: -8.51 -4.30
95% mean confidence interval for instructions %-change: -1.23% -0.69%
Instructions are helped.
total cycles in shared programs:
506180109 ->
506196314 (<.01%)
cycles in affected programs:
1671429 ->
1687634 (0.97%)
helped: 37
HURT: 84
helped stats (abs) min: 1 max: 490 x̄: 73.27 x̃: 24
helped stats (rel) min: 0.02% max: 7.98% x̄: 1.25% x̃: 0.41%
HURT stats (abs) min: 1 max: 5000 x̄: 225.19 x̃: 8
HURT stats (rel) min: 0.03% max: 10.22% x̄: 1.22% x̃: 0.42%
95% mean confidence interval for cycles value: 2.85 265.00
95% mean confidence interval for cycles %-change: 0.04% 0.88%
Cycles are HURT.
Ice Lake and Skylake had similar results. (Ice Lake shown)
total instructions in shared programs:
19961317 ->
19960543 (<.01%)
instructions in affected programs: 30268 -> 29494 (-2.56%)
helped: 39
HURT: 0
helped stats (abs) min: 1 max: 142 x̄: 19.85 x̃: 7
helped stats (rel) min: 0.19% max: 7.87% x̄: 2.33% x̃: 2.31%
95% mean confidence interval for instructions value: -29.46 -10.23
95% mean confidence interval for instructions %-change: -2.95% -1.71%
Instructions are helped.
total cycles in shared programs:
498863755 ->
498865843 (<.01%)
cycles in affected programs:
1831136 ->
1833224 (0.11%)
helped: 57
HURT: 65
helped stats (abs) min: 1 max: 1400 x̄: 128.93 x̃: 25
helped stats (rel) min: 0.05% max: 3.49% x̄: 0.89% x̃: 0.71%
HURT stats (abs) min: 1 max: 1887 x̄: 145.18 x̃: 15
HURT stats (rel) min: 0.02% max: 9.88% x̄: 1.83% x̃: 0.73%
95% mean confidence interval for cycles value: -58.30 92.53
95% mean confidence interval for cycles %-change: 0.16% 0.97%
Inconclusive result (value mean confidence interval includes 0).
total spills in shared programs: 8774 -> 8773 (-0.01%)
spills in affected programs: 20 -> 19 (-5.00%)
helped: 1
HURT: 0
total fills in shared programs: 9496 -> 9494 (-0.02%)
fills in affected programs: 40 -> 38 (-5.00%)
helped: 1
HURT: 0
Broadwell
total instructions in shared programs:
17859373 ->
17858548 (<.01%)
instructions in affected programs: 38452 -> 37627 (-2.15%)
helped: 31
HURT: 0
helped stats (abs) min: 1 max: 143 x̄: 26.61 x̃: 10
helped stats (rel) min: 0.19% max: 7.87% x̄: 2.57% x̃: 2.69%
95% mean confidence interval for instructions value: -39.79 -13.44
95% mean confidence interval for instructions %-change: -3.25% -1.89%
Instructions are helped.
total cycles in shared programs:
525858109 ->
525869236 (<.01%)
cycles in affected programs:
2058597 ->
2069724 (0.54%)
helped: 44
HURT: 75
helped stats (abs) min: 2 max: 1330 x̄: 187.84 x̃: 23
helped stats (rel) min: 0.04% max: 31.31% x̄: 2.13% x̃: 0.85%
HURT stats (abs) min: 1 max: 3915 x̄: 258.56 x̃: 47
HURT stats (rel) min: 0.02% max: 10.53% x̄: 2.81% x̃: 2.21%
95% mean confidence interval for cycles value: -26.06 213.07
95% mean confidence interval for cycles %-change: 0.19% 1.78%
Inconclusive result (value mean confidence interval includes 0).
total spills in shared programs: 25744 -> 25730 (-0.05%)
spills in affected programs: 1578 -> 1564 (-0.89%)
helped: 4
HURT: 2
total fills in shared programs: 31710 -> 31689 (-0.07%)
fills in affected programs: 4346 -> 4325 (-0.48%)
helped: 3
HURT: 3
Haswell
total instructions in shared programs:
16228399 ->
16227783 (<.01%)
instructions in affected programs: 22201 -> 21585 (-2.77%)
helped: 27
HURT: 0
helped stats (abs) min: 1 max: 68 x̄: 22.81 x̃: 11
helped stats (rel) min: 0.19% max: 7.87% x̄: 2.92% x̃: 2.86%
95% mean confidence interval for instructions value: -31.96 -13.66
95% mean confidence interval for instructions %-change: -3.68% -2.15%
Instructions are helped.
total cycles in shared programs:
538613967 ->
538701354 (0.02%)
cycles in affected programs:
1653044 ->
1740431 (5.29%)
helped: 36
HURT: 81
helped stats (abs) min: 2 max: 708 x̄: 104.50 x̃: 17
helped stats (rel) min: <.01% max: 15.01% x̄: 1.67% x̃: 0.65%
HURT stats (abs) min: 1 max: 30100 x̄: 1125.30 x̃: 304
HURT stats (rel) min: 0.02% max: 16.21% x̄: 8.98% x̃: 11.60%
95% mean confidence interval for cycles value: 23.78 1470.01
95% mean confidence interval for cycles %-change: 4.29% 7.12%
Cycles are HURT.
total spills in shared programs: 23418 -> 23409 (-0.04%)
spills in affected programs: 177 -> 168 (-5.08%)
helped: 2
HURT: 0
total fills in shared programs: 25919 -> 25896 (-0.09%)
fills in affected programs: 568 -> 545 (-4.05%)
helped: 3
HURT: 0
Ivy Bridge
total instructions in shared programs:
15265983 ->
15265759 (<.01%)
instructions in affected programs: 8418 -> 8194 (-2.66%)
helped: 5
HURT: 0
helped stats (abs) min: 18 max: 99 x̄: 44.80 x̃: 26
helped stats (rel) min: 1.74% max: 4.26% x̄: 3.12% x̃: 3.00%
95% mean confidence interval for instructions value: -86.29 -3.31
95% mean confidence interval for instructions %-change: -4.43% -1.81%
Instructions are helped.
total cycles in shared programs:
422930336 ->
422929589 (<.01%)
cycles in affected programs: 59347 -> 58600 (-1.26%)
helped: 3
HURT: 2
helped stats (abs) min: 72 max: 1060 x̄: 433.33 x̃: 168
helped stats (rel) min: 1.14% max: 3.48% x̄: 2.23% x̃: 2.06%
HURT stats (abs) min: 265 max: 288 x̄: 276.50 x̃: 276
HURT stats (rel) min: 4.79% max: 5.64% x̄: 5.22% x̃: 5.22%
95% mean confidence interval for cycles value: -829.08 530.28
95% mean confidence interval for cycles %-change: -4.43% 5.93%
Inconclusive result (value mean confidence interval includes 0).
total spills in shared programs: 4953 -> 4946 (-0.14%)
spills in affected programs: 344 -> 337 (-2.03%)
helped: 2
HURT: 0
total fills in shared programs: 5548 -> 5521 (-0.49%)
fills in affected programs: 838 -> 811 (-3.22%)
helped: 2
HURT: 0
No shader-db changes on any earlier Intel platform.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4515>
Ian Romanick [Thu, 2 Apr 2020 19:20:57 +0000 (12:20 -0700)]
nir/algebraic: Add some half packing optimizations for pack_half_2x16_split
Like
1f72857739b ("nir/algebraic: add some half packing optimizations"),
but for the pack_half_2x16_split variant.
The shader helped for spills and fills is the big compute shader in
Bioshock Infinite.
Tiger Lake
total instructions in shared programs:
21834539 ->
21833218 (<.01%)
instructions in affected programs: 60119 -> 58798 (-2.20%)
helped: 105
HURT: 0
helped stats (abs) min: 5 max: 50 x̄: 12.58 x̃: 9
helped stats (rel) min: 0.86% max: 26.46% x̄: 2.58% x̃: 1.70%
95% mean confidence interval for instructions value: -14.35 -10.81
95% mean confidence interval for instructions %-change: -3.20% -1.97%
Instructions are helped.
total cycles in shared programs:
506215169 ->
506180109 (<.01%)
cycles in affected programs:
1445088 ->
1410028 (-2.43%)
helped: 97
HURT: 8
helped stats (abs) min: 1 max: 16882 x̄: 387.76 x̃: 26
helped stats (rel) min: 0.05% max: 18.31% x̄: 1.77% x̃: 1.34%
HURT stats (abs) min: 21 max: 635 x̄: 319.12 x̃: 212
HURT stats (rel) min: 0.39% max: 20.08% x̄: 8.96% x̃: 4.46%
95% mean confidence interval for cycles value: -782.96 115.15
95% mean confidence interval for cycles %-change: -1.74% -0.16%
Inconclusive result (value mean confidence interval includes 0).
Ice Lake, Skylake, and Broadwell had similar results. (Ice Lake shown)
total instructions in shared programs:
19962974 ->
19961317 (<.01%)
instructions in affected programs: 63471 -> 61814 (-2.61%)
helped: 105
HURT: 0
helped stats (abs) min: 6 max: 82 x̄: 15.78 x̃: 11
helped stats (rel) min: 1.11% max: 28.65% x̄: 3.17% x̃: 2.16%
95% mean confidence interval for instructions value: -18.38 -13.18
95% mean confidence interval for instructions %-change: -3.86% -2.48%
Instructions are helped.
total cycles in shared programs:
498908953 ->
498863755 (<.01%)
cycles in affected programs:
1566998 ->
1521800 (-2.88%)
helped: 89
HURT: 15
helped stats (abs) min: 2 max: 17502 x̄: 532.19 x̃: 69
helped stats (rel) min: 0.07% max: 18.54% x̄: 4.71% x̃: 3.12%
HURT stats (abs) min: 3 max: 661 x̄: 144.47 x̃: 16
HURT stats (rel) min: 0.14% max: 20.57% x̄: 4.29% x̃: 0.30%
95% mean confidence interval for cycles value: -903.93 34.74
95% mean confidence interval for cycles %-change: -4.50% -2.32%
Inconclusive result (value mean confidence interval includes 0).
total spills in shared programs: 8776 -> 8774 (-0.02%)
spills in affected programs: 25 -> 23 (-8.00%)
helped: 1
HURT: 0
total fills in shared programs: 9500 -> 9496 (-0.04%)
fills in affected programs: 46 -> 42 (-8.70%)
helped: 1
HURT: 0
Haswell
total instructions in shared programs:
16229912 ->
16228399 (<.01%)
instructions in affected programs: 61257 -> 59744 (-2.47%)
helped: 105
HURT: 0
helped stats (abs) min: 6 max: 51 x̄: 14.41 x̃: 11
helped stats (rel) min: 0.77% max: 28.65% x̄: 3.08% x̃: 2.15%
95% mean confidence interval for instructions value: -16.14 -12.68
95% mean confidence interval for instructions %-change: -3.77% -2.40%
Instructions are helped.
total cycles in shared programs:
538654481 ->
538613967 (<.01%)
cycles in affected programs:
1448966 ->
1408452 (-2.80%)
helped: 58
HURT: 47
helped stats (abs) min: 9 max: 22604 x̄: 957.00 x̃: 74
helped stats (rel) min: 0.40% max: 18.81% x̄: 6.22% x̃: 3.03%
HURT stats (abs) min: 5 max: 3720 x̄: 318.98 x̃: 49
HURT stats (rel) min: 0.20% max: 34.50% x̄: 5.05% x̃: 2.12%
95% mean confidence interval for cycles value: -999.84 228.14
95% mean confidence interval for cycles %-change: -2.86% 0.51%
Inconclusive result (value mean confidence interval includes 0).
Ivy Bridge
total instructions in shared programs:
15266086 ->
15265983 (<.01%)
instructions in affected programs: 7272 -> 7169 (-1.42%)
helped: 3
HURT: 0
helped stats (abs) min: 21 max: 41 x̄: 34.33 x̃: 41
helped stats (rel) min: 0.66% max: 5.43% x̄: 2.44% x̃: 1.23%
total cycles in shared programs:
422930883 ->
422930336 (<.01%)
cycles in affected programs: 49259 -> 48712 (-1.11%)
helped: 3
HURT: 0
helped stats (abs) min: 106 max: 221 x̄: 182.33 x̃: 220
helped stats (rel) min: 0.71% max: 5.95% x̄: 2.46% x̃: 0.72%
No changes on any earilier Intel platforms.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4515>
Ian Romanick [Thu, 2 Apr 2020 19:14:12 +0000 (12:14 -0700)]
nir/algebraic: Optimize ushr of pack_half, not ishr
When a = -1.0, pack_half_2x16(vec2(0x0000, 0xBC00)) will produce
0xBC000000. The ishr will produce 0xFFFFBC00. The replacement
pack_half_2x16(vec2(0xBC00, 0x0000)) will produce 0x0000BC00.
Fixes: 1f72857739b ("nir/algebraic: add some half packing optimizations")
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Cc: Connor Abbott <cwabbott0@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4515>
Kenneth Graunke [Fri, 8 May 2020 19:51:11 +0000 (12:51 -0700)]
intel: Delete hardcoded devinfo->urb.size values for Gen7+ (sans DG1).
On all Gen7+ platforms except DG1, the URB is a subsection of the
configurable L3 cache, and so the size can vary. The size listed
in the documentation on those platforms is an "example size", picked
by calculating it based on an arbitrarily chosen L3 config.
Hardcoding a value for those platforms provides no value and only
confuses people trying to fill out these tables when doing hardware
enabling. anv and iris never use this field. i965 uses it to
initialize brw->urb.size, but then updates that in update_urb_size()
to be the correct value, so the initial value doesn't matter.
Delete the values for Gen7+ and update the comment accordingly.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4969>
Abhishek Kumar [Thu, 7 May 2020 16:32:02 +0000 (22:02 +0530)]
egl: Limit the EGL ver for android
Android support EGL 1.5 from Q onwards,
so limit EGL ver to 1.4 for P and below.
Closes: #2892
Signed-off-by: Abhishek Kumar <abhishek4.kumar@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4951>
Serge Martin [Sun, 10 May 2020 16:23:25 +0000 (18:23 +0200)]
amd/common: Fix incorrect use of asprintf instead of vasprintf
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Erik Faye-Lund [Thu, 30 Apr 2020 18:01:22 +0000 (20:01 +0200)]
docs/features: mark GL_NV_conditional_render as done for zink
Requires VK_EXT_conditional_rendering.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4835>
Dave Airlie [Sun, 14 Oct 2018 23:15:50 +0000 (00:15 +0100)]
zink: enable conditional rendering if available
This doesn't seem to work perfect, but I'm not sure what is possible
in GL vs Vulkan here
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2867
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4835>
Erik Faye-Lund [Fri, 8 May 2020 10:07:48 +0000 (12:07 +0200)]
zink: add a GET_PROC_ADDR macro to simplify load_device_extensions
This doesn't do much for now, but it will keep thing cleaner in the next
commit.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4835>
Erik Faye-Lund [Thu, 30 Apr 2020 17:06:51 +0000 (19:06 +0200)]
zink: load vk_GetMemoryFdKHR while creating screen
We're about to load some more extension-pointers as well, so let's
create a separate place for doing this.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4835>
Pierre-Eric Pelloux-Prayer [Thu, 7 May 2020 19:45:49 +0000 (21:45 +0200)]
radeonsi: do not use cmask with encrypted texture
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Tue, 25 Feb 2020 20:56:12 +0000 (21:56 +0100)]
radeonsi: determine secure flag must be set for gfx IB
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Fri, 28 Feb 2020 10:54:41 +0000 (11:54 +0100)]
amdgpu: use AMDGPU_IB_FLAGS_SECURE when requested
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Fri, 6 Dec 2019 09:33:56 +0000 (10:33 +0100)]
radeonsi: add support for PIPE_RESOURCE_FLAG_ENCRYPTED
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Mon, 27 Apr 2020 09:21:35 +0000 (11:21 +0200)]
gallium: PIPE_RESOURCE_FLAG_ENCRYPTED
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Fri, 6 Dec 2019 09:29:31 +0000 (10:29 +0100)]
radeonsi/sdma: implement tmz support
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Fri, 28 Feb 2020 16:10:45 +0000 (17:10 +0100)]
radeonsi: force using staging texture when uploading to secure texture
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Fri, 6 Dec 2019 09:40:02 +0000 (10:40 +0100)]
amdgpu: add encrypted slabs support
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Fri, 28 Feb 2020 13:25:54 +0000 (14:25 +0100)]
radeonsi: allocate framebuffer texture as secure when using tmz
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Fri, 6 Dec 2019 09:33:43 +0000 (10:33 +0100)]
radeon: add RADEON_CREATE_ENCRYPTED flag
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Fri, 28 Feb 2020 13:24:29 +0000 (14:24 +0100)]
radeonsi: add AMD_DEBUG=tmz option
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Fri, 6 Dec 2019 09:28:10 +0000 (10:28 +0100)]
amdgpu/radeon: add secure api
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4401>
Pierre-Eric Pelloux-Prayer [Mon, 11 May 2020 07:18:49 +0000 (09:18 +0200)]
ac/surface: remove shadowing declaration
Fixes: 7691de0dcef ("ac/surface,radeonsi: move the set/get_bo_metadata code to ac_surface.c")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2929
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4983>
Samuel Pitoiset [Mon, 4 May 2020 14:03:35 +0000 (16:03 +0200)]
aco: prevent invalid loads/stores vectorization if robustness is enabled
Only UBO, SSBO, global and push constants accesses should matter.
This fixes a bunch of new robustness2 failures. Note that RADV/LLVM
isn't affected because it relies on LLVM for loads/stores
vectorization and LLVM doesn't vectorize in this situation as well.
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/4881>
Samuel Pitoiset [Mon, 4 May 2020 14:02:38 +0000 (16:02 +0200)]
nir: do not vectorize load/store if offset can overflow and robustness enabled
This prevents vectorization for loads/stores that can overflow if
the low offset is negative and the range greater or equal than 0.
The caller can pass the list of variable modes that matter for
robust access.
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/4881>
Samuel Pitoiset [Wed, 6 May 2020 13:34:07 +0000 (15:34 +0200)]
aco: fix 64-bit trunc with negative exponents on GFX6
v_frexp_exp returns the exponent as an unsigned value.
Also, v_ashr returns either 0 or -1 depending on the sign of the
source operand, but what we want is only the sign bit.
Fixes a bunch of recent dEQP-VK.glsl.builtin.precision_double.* tests.
Cc: <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/4921>
Guido Günther [Thu, 23 Jan 2020 08:20:00 +0000 (09:20 +0100)]
etnaviv: drm: Normalize nano seconds
Make sure the nano second part is less than one second. This matches
what clock_settime expects and allows for more concise kernel
interfaces.
Signed-off-by: Guido Günther <guido.gunther@puri.sm>
Reviewed-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3534>
Guido Günther [Thu, 23 Jan 2020 08:17:07 +0000 (09:17 +0100)]
etnaviv: drm: Use NSEC_PER_SEC
Signed-off-by: Guido Günther <agx@sigxcpu.org>
Reviewed-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3534>
Mauro Rossi [Sat, 9 May 2020 11:59:02 +0000 (13:59 +0200)]
freedreno: android: add adreno-pm4-pack.xml.h generation to android build
Fixes the following building errors:
In file included from external/mesa/src/gallium/drivers/freedreno/a6xx/fd6_blitter.c:40:
external/mesa/src/gallium/drivers/freedreno/a6xx/fd6_pack.h:42:10: fatal error: 'adreno-pm4-pack.xml.h' file not found
^~~~~~~~~~~~~~~~~~~~~~~
1 error generated.
In file included from external/mesa/src/gallium/drivers/freedreno/a6xx/fd6_blend.c:36:
external/mesa/src/gallium/drivers/freedreno/a6xx/fd6_pack.h:42:10: fatal error: 'adreno-pm4-pack.xml.h' file not found
^~~~~~~~~~~~~~~~~~~~~~~
1 error generated.
In file included from external/mesa/src/gallium/drivers/freedreno/a6xx/fd6_const.c:26:
external/mesa/src/gallium/drivers/freedreno/a6xx/fd6_pack.h:42:10: fatal error: 'adreno-pm4-pack.xml.h' file not found
^~~~~~~~~~~~~~~~~~~~~~~
1 error generated.
Fixes: ee293160 "freedreno/a6xx: add OUT_PKT()"
Signed-off-by: Mauro Rossi <issor.oruam@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4973>
Mauro Rossi [Sat, 9 May 2020 07:44:35 +0000 (09:44 +0200)]
freedreno/drm: android: add libfreedreno_registers static dependency
The dependency is required to get the necessary generated headers
Fixes the following building error:
In file included from external/mesa/src/freedreno/drm/msm_bo.c:27:
In file included from external/mesa/src/freedreno/drm/msm_priv.h:30:
In file included from external/mesa/src/freedreno/drm/freedreno_priv.h:51:
external/mesa/src/freedreno/drm/freedreno_ringbuffer.h:35:10: fatal error: 'adreno_common.xml.h' file not found
#include "adreno_common.xml.h"
^~~~~~~~~~~~~~~~~~~~~
1 error generated.
Fixes: 6c688ae8 ("freedreno: Deduplicate ringbuffer macros with computerator/fdperf")
Signed-off-by: Mauro Rossi <issor.oruam@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4973>
Erico Nunes [Tue, 14 Apr 2020 00:54:56 +0000 (02:54 +0200)]
lima/ppir: rework select conditions
This is yet another simple optimization that attemts to save the
insertion of an unnecessary mov for a large number of cases.
If the node outputting the condition for select satisfies a few
requirements (which are common in the case of comparison conditions),
it can just be changed to pipeline output and used directly.
In case of difficult corner cases, just fall back to the mov as before.
The sel_cond op is removed as the scheduler can be smart enough to place
nodes that output to ^fmul in the ALU_SCL_MUL slot, and as there can be
alu ops other than just mov.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4632>
Erico Nunes [Tue, 14 Apr 2020 00:52:48 +0000 (02:52 +0200)]
lima/ppir: add fallback mov option for const scheduler
It turns out that with more aggressive combining, there can be cases
where the available const slots are not enough for one instruction.
In particular, fcsel can take up to two consts, and a previous alu slot,
such as a comparison condition, might require an additional const.
So add a fallback for it like for uniforms.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4632>
Erico Nunes [Tue, 14 Apr 2020 00:45:38 +0000 (02:45 +0200)]
lima/ppir: rework store output
In many cases, it is possible to avoid creating a mov for the store
output node.
Additionally, nodes other than alu, such as load varying, can be valid
store output nodes too.
This is another small optimization, but helps a vast majority of
programs by 1 instruction.
Shaders with discard easily become complicated to handle properly.
Some example issues: ppir has to rely on instruction ordering; or a
node with ssa output could be required both before a discard_if (as a
condition) and after it (as the instruction with the 'stop' bit set).
So don't try to handle them here.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4632>
Erico Nunes [Thu, 13 Feb 2020 19:21:00 +0000 (20:21 +0100)]
lima/ppir: rework emit nir to ppir
The previous code assumed that a ppir node would be created for each nir
instr and used that to add it to the list of nodes and verify success.
This didn't make much sense anymore since some emit paths create
multiple nodes anyway, and this didn't allow for an emit call to not
create any new ppir node while still returning success.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4632>
Erico Nunes [Mon, 13 Apr 2020 14:04:26 +0000 (16:04 +0200)]
lima/ppir: remove unused clone functions
With the previous refactors moving these lowering steps to a nir pass,
these are no longer needed.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4535>
Erico Nunes [Mon, 13 Apr 2020 13:32:01 +0000 (15:32 +0200)]
lima/ppir: duplicate consts in nir
Move the duplicate consts step to a nir pass.
This makes the nir representation closer to what ppir will have in the
result.
Additionally, it handles the case where a const is used multiple times
by a single node (which can happen in instructions like fcsel). The new
implementation will only emit a single load const for that case.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4535>
Erico Nunes [Mon, 13 Apr 2020 13:30:25 +0000 (15:30 +0200)]
lima/ppir: duplicate intrinsics in nir
Move the duplicate uniform and varying steps to a nir pass, along with
some changes in the duplicating strategy.
Node duplication is now done per user of the varying/uniform. This is
inspired by what the offline shader compiler seems to usually do, and as
usual aims to reduce register pressure and better utilize the ld_uni and
ld_var instruction slots.
It is worth noting that due to a bug/feature, ppir was already
duplicating uniforms per successor in ppir_node_add_src even if the
comment indicated it was meant to be per-block.
Additionally, ppir was duplicating load uniform nodes twice for nodes
that use the same uniform in more than one source, resulting in one
unnecessary (and unpipelineable) load. This new implementation in nir
only creates one load in that case.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4535>
Erico Nunes [Mon, 13 Apr 2020 13:26:16 +0000 (15:26 +0200)]
lima/ppir: combine varying loads in node_to_instr
Varying loads with a single successor have a high potential to be
combined with its successor node, like ppir does for uniforms, rather
than being in a separate instruction.
Even if ppir becomes capable of combining instructions in a separate
step, combining varying loads during node_to_instr is trivial enough
that it seems to be worth doing it in this stage, and this benefits
pretty much every program that uses varyings.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4535>
Erico Nunes [Mon, 13 Apr 2020 13:24:35 +0000 (15:24 +0200)]
lima/ppir: do not assume single src for pipeline outputs
Even if a node has pipeline output and a single successor, it is still
valid for that successor to have multiple references to that pipeline
node. A trivial example is add(u.x,u.y) where u is a uniform.
It is even possible for this to occur with consts as operands of fcsel.
So remove uses of ppir_node_get_src_for_pred as that would assume a
single src in the node that uses the pipeline.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4535>
Erico Nunes [Mon, 13 Apr 2020 13:22:53 +0000 (15:22 +0200)]
lima/ppir: fix lod bias register codegen
The lod bias register is correctly run through the entire compilation
process, but in the end its allocated register value was never being
added to the instruction.
It seems that most programs were lucky enough that lod bias was assigned
register 0.x so that things worked anyway.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4535>
Erico Nunes [Mon, 13 Apr 2020 13:21:52 +0000 (15:21 +0200)]
lima/ppir: introduce liveness internal live set
The current solution for handling registers that live and die within a
single instruction does not handle all cases. In particular, these
intra-instruction use register also conflict with registers that are
part of the live_in set.
Unfortunately, adding them to the live_in set is not an easy solution as
that would cause them to be propagated upwards. So, add a separate set
to handle these registers in the particular instructions, without
propagating them.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4535>
Lionel Landwerlin [Tue, 5 May 2020 09:43:35 +0000 (12:43 +0300)]
genxml: pack: deal with default field not being simple integers
Storing integers into enums doesn't seem to cause issues in C, but
with our builder tests written in C++ this causes warnings/errors.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4938>
Lionel Landwerlin [Thu, 30 Apr 2020 12:43:01 +0000 (15:43 +0300)]
genxml: factor out utility functions
v2: Use the regexp version (Jordan)
Also fix regexp that missed the ' character replacement (Lionel)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4938>
Lionel Landwerlin [Wed, 29 Apr 2020 16:39:06 +0000 (19:39 +0300)]
genxml: fix invalid end value for video fields
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4938>
Lionel Landwerlin [Thu, 7 May 2020 09:05:23 +0000 (12:05 +0300)]
genxml: run sorting script
Helps running diff/meld between generations :)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4938>
Jordan Justen [Tue, 14 Jan 2020 22:36:25 +0000 (14:36 -0800)]
intel/dev: Add device info for RKL
Cc: 20.1 <mesa-stable@lists.freedesktop.org>
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by : Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4955>
Jordan Justen [Mon, 4 May 2020 20:29:32 +0000 (13:29 -0700)]
intel/dev: Split .num_subslices out of GEN12_FEATURES macro
The .num_subslices field makes it problematic to reuse the
GEN12_FEATURES macro in other macros.
This also fixes the number of L3 banks for tgl gt1, except that this
was already fixed by Jason (dynamically) in:
86f67952d31 ("intel/devinfo: Compute the correct L3$ size for Gen12")
Cc: 20.1 <mesa-stable@lists.freedesktop.org>
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by : Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4955>
Qiang Yu [Fri, 24 Apr 2020 08:20:25 +0000 (16:20 +0800)]
panfrost: don't always build bifrost_compiler
src/panfrost/shared is shared with lima driver, build
bifrost_compiler for lima driver is meaningless and
get link error when only lima driver is enabled.
So only build bifrost_compiler when configued with:
meson -Dtools=panfrost
Fixes: ec2a59cd7aa4 "panfrost: Move non-Gallium files outside of Gallium"
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4960>
Qiang Yu [Fri, 24 Apr 2020 08:27:03 +0000 (16:27 +0800)]
radeonsi: remove emacs style config file
As radeonsi has synced the code style with main mesa,
remove the orginal radeonsi spec emacs config file and
use the top level dir .dir-locals.el
Acked-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4961>
D Scott Phillips [Fri, 8 May 2020 21:37:06 +0000 (14:37 -0700)]
intel/dump_gpu: Fix name of LD_PRELOAD in env append logic
Checking for the wrong environment variable name to be set causes
us to stomp any pre-existing LD_PRELOAD.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4970>
Marek Olšák [Fri, 8 May 2020 20:12:56 +0000 (16:12 -0400)]
ac/surface: fix broken pitch override on gfx8
Fixes: 441eaef6a9e - amd: unify code for overriding offset and stride for imported buffers
Closes: #2920
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4968>
Eric Anholt [Thu, 7 May 2020 23:58:25 +0000 (16:58 -0700)]
freedreno: Initialize the bo's iova at creation time.
Avoids repeated conditionals at reloc time checking if we need to go ask
the kernel.
No statistically significant difference on the drawoverhead case I'm
looking at (n=300).
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4957>
Eric Anholt [Thu, 7 May 2020 23:40:52 +0000 (16:40 -0700)]
freedreno: Rename append_bo() in case it doesn't get inlined.
In a debugoptimized build, it wasn't inlined and so I wasn't noticing
where a bunch of CPU usage was going in the DRM functions.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4957>
Eric Anholt [Thu, 7 May 2020 23:34:35 +0000 (16:34 -0700)]
freedreno: Clean up tests around ORing in the reloc flags.
gcc was surprisingly not seeing through this to just do an AND and an OR.
Improves drawoverhead's few uniforms / 1 change throughput 1.64141% +/-
0.188152% (n=60).
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4957>
Eric Anholt [Thu, 7 May 2020 22:40:52 +0000 (15:40 -0700)]
freedreno: Deduplicate ringbuffer macros with computerator/fdperf
They're sugar around freedreno_ringbuffer.h, so put them there and reuse them.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4957>
Hyunjun Ko [Thu, 7 May 2020 06:06:59 +0000 (06:06 +0000)]
freedreno,tu: Don't request fragcoord components not being read.
v1. Replace the existed bool type with new bitfield and edit register
files to take a mask instead of duplicating codes to do masking.
v2. Use fragcoord_compmask != 0 instead of fragcoord_compmask > 0 since
it represents a bitfield.
Tested with
dEQP-VK.glsl.builtin_var.simple.fragcoord_xyz/w
dEQP-GLES2.functional.shaders.builtin_variable.fragcoord_xyz/w
Closes: #2680
Signed-off-by: Hyunjun Ko <zzoon@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4723>
Jason Ekstrand [Fri, 8 May 2020 01:07:14 +0000 (20:07 -0500)]
vulkan/object: Always include the type
This was causing problems for some of the ANV unit tests when run in
release mode. Having a public struct whose layout depends on NDEBUG
seems kind-of sketchy anyway.
Fixes: 32f20783a51 "vulkan: Add run-time object type asserts in..."
Closes: #2903
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4959>
Jason Ekstrand [Mon, 4 May 2020 22:27:22 +0000 (17:27 -0500)]
anv/allocator: Add a start_offset to anv_state_pool
This allows a pool's allocations to start somewhere other than the base
address. Our first real use of this will be to use a negative offset
for the binding table pool to make it so that the offset is baked into
the pool and the code in anv_batch_chain.c doesn't have to understand
pool offsetting.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4897>
pal1000 [Fri, 24 Apr 2020 14:06:01 +0000 (17:06 +0300)]
util: Make process_test path compatible with mingw native toolchains
v2: Make sure we require winepath when using mingw crosscompilers
v3: Also take into account mingw clang toolchains
Acked-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Daniel Stone <daniels@collabora.com>
Fixes: f8f14130 ("util/u_process: add util_get_process_exec_path")
Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2788
CC: "20.1" <mesa-stable@lists.freedesktop.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4731>
Daniel Stone [Fri, 8 May 2020 13:18:52 +0000 (14:18 +0100)]
CI: Disable Panfrost T7x0 jobs
One of the dispatchers in the office (with all the T7x0 boards) has gone
AWOL, and we don't have physical access to restore it. Disable it until
we can get in and fix it.
Signed-off-by: Daniel Stone <daniels@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4965>
Con Kolivas [Wed, 6 May 2020 08:03:37 +0000 (18:03 +1000)]
Linux: Change minimum priority threads from SCHED_IDLE to nice 19 SCHED_BATCH.
SCHED_IDLE on linux can lead to extraordinarily long periods of no scheduling
leading to starvation of minimum priority threads for such an extended period
that it can eventually lead to GUI stalls. Switch to renicing the threads to
the lowest priority and use the SCHED_BATCH scheduling policy which is a hint
to the scheduler that this is latency insensitive thread instead. This change
has been confirmed to address unexpected GUI related stalls in mesa
applications across a range of different linux kernels.
Signed-off-by: Con Kolivas <kernel@kolivas.org>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4912>
Erik Faye-Lund [Wed, 6 May 2020 09:42:39 +0000 (11:42 +0200)]
docs/features: add zink features
This is base on the exported extension strings, with some known-bad
extensions removed. There might be more that should be removed, as their
support isn't per-spec, but this gives us some more information, at
least.
There's also a few features that seems to be trivial to enable, simply
by flipping a cap. But let's document what is expected to work first.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2075
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4963>
Lionel Landwerlin [Thu, 7 May 2020 09:25:50 +0000 (12:25 +0300)]
anv: fix alignments for uniform buffers
We were not consistent with minimums reported in the physical device
properties.
Fixes a few CTS tests :
dEQP-VK.memory.requirements.dedicated_allocation.buffer.regular
dEQP-VK.memory.requirements.extended.buffer.regular
dEQP-VK.memory.requirements.core.buffer.regular
v2: Use define for the limit
v3: Rename define
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: a0de2e0090535b ("anv: increase minUniformBufferOffsetAlignment to 64")
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4940>