1d67fa4d73
ac/surface: add tests for CmaskAddrFromCoord on GFX10+
...
Signed-off-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/12182 >
2021-08-05 06:37:09 +00:00
0926b268fc
amd/addrlib: expose CMASK address equations to drivers on GFX10+
...
Signed-off-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/12182 >
2021-08-05 06:37:09 +00:00
19670129c5
ci: Update canvas_text trace
...
The previous one had all rendering and setup in a single frame, so
repeatedly replaying it for performance tracking was reaching OOM due to
the repeated creation of resources that weren't being released.
Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com >
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com >
Reviewed-by: Emma Anholt <emma@anholt.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12195 >
2021-08-05 05:44:57 +00:00
c886ce2991
zink: simplify else clause for mem info gathering
...
it doesn't matter if this is host-visible, it just has to not be device-local
Fixes: 73f6bff07fhaochengho12907@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12199 >
2021-08-04 14:07:58 -04:00
42442a0d4e
zink: sum available memory heaps instead of assigning
...
this is supposed to accumulate now
Fixes: 73f6bff07fhaochengho12907@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12199 >
2021-08-04 14:07:58 -04:00
8cfa6b4d75
ci/freedreno: Mark border_color as passing on a5xx.
...
They're marked as flaky, but they're all passing on my board, and maybe in
CI too. Let's see if CI still sees them as flaky once the expectations
are right.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12192 >
2021-08-04 17:21:43 +00:00
1f66fcf5a6
freedreno/a5xx: Don't try to emit FS images in binning command streams.
...
We don't have a compiled FS in that case, so the shader deref fails. We
don't need the state, anyway.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12192 >
2021-08-04 17:21:43 +00:00
c20287f8e4
freedreno/a5xx: Disable TF when pausing or transitioning to non-TF.
...
This is not as clean as on a6xx where we just re-emit the SO state, but it
cleans up our dEQP results a ton.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12192 >
2021-08-04 17:21:43 +00:00
1f89ea419d
ci/freedreno: Clear out TF API errors xfails.
...
These tests are flaky and sometimes segfault in CI, but usually pass. We
hadn't noticed their change due to the test being marked as flaky.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12192 >
2021-08-04 17:21:43 +00:00
8918a809ce
ac: Remove deprecated use_late_alloc field as nobody uses it anymore.
...
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Marek Olšák <marek.olsak@amd.com >
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11905 >
2021-08-04 15:37:05 +00:00
d911259c3a
radv: Use ac_compute_late_alloc in radv_pipeline.
...
This aligns RADV with RadeonSI in how it handles late alloc,
making it easier for us to deal with deadlocks and such.
Also move setting the RSRC3 registers for VS, GS and NGG
into radv_pipeline.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Marek Olšák <marek.olsak@amd.com >
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11905 >
2021-08-04 15:37:05 +00:00
61eb3debcf
radv: Don't toggle PC oversubscription for NGG culling.
...
We are going to add this directly to the pipeline.
If a pipeline has such a shader, NGG culling is turned on
most of the time, so it's not useful to toggle this setting.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Marek Olšák <marek.olsak@amd.com >
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11905 >
2021-08-04 15:37:05 +00:00
448592b9ae
aco: Use Navi 10 empty NGG output workaround on NGG culling shaders.
...
Navi 10 can hang when an NGG workgroup has no output,
so we work around that by always exporting a single zero-area
triangle with a single vertex that has all-NaN coordinates.
Thus far, we only employed this for NGG GS, because on all
other stages, the output can't be empty.
However, with NGG culling, the output can be empty, so let's
apply the same workaround there too.
Cc: mesa-stable
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com >
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12169 >
2021-08-04 12:28:34 +00:00
566970f273
aco: use image_dim and image_array intrinsic indices
...
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12190 >
2021-08-04 12:09:07 +00:00
39db5a569b
radv: set image_dim and image_array intrinsic indices
...
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com >
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12190 >
2021-08-04 12:09:07 +00:00
513f9b5dc9
ci: bump to latest virglrenderer for anisotropic support
...
Update ci results
Reviewed-by: Gert Wollny <gert.wollny@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11944 >
2021-08-04 10:49:55 +00:00
2116a4f5cc
virgl: add support for anisotropic texture filtering
...
This is the guest side for adding correct anisotropic filtering support
Reviewed-by: Gert Wollny <gert.wollny@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11944 >
2021-08-04 10:49:55 +00:00
e831c4a537
virgl: disable anisotropic filtering.
...
virgl doesn't yet support anisotropic filtering so don't advertise it.
Fixes: a8987b88ffgert.wollny@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11944 >
2021-08-04 10:49:55 +00:00
d16b9b27b0
iris: Fix Null pointer dereferences
...
Fix the error from Coverity report: CID 1489765
Signed-off-by: Sergii Melikhov <sergii.v.melikhov@globallogic.com >
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12179 >
2021-08-04 07:52:35 +00:00
6751d832c5
aux/draw: Check for preferred IR to take nir-to-tgsi path in draw module
...
When a vertex program is translated to nir, it uses
nir_to_tgsi_compile_options for drivers with only nir-to-tgsi based
NIR support. But this compile option might not be the same as the NIR
compile option from llvmpipe, hence when the nir shader is bound
to the draw module, it hits an assertion in do_alu_action() when
encounters nir_op_fdot3.
With this patch, draw will take the nir-to-tgsi path if preferred IR
from the driver is TGSI.
Fixes assert running Maya on SVGA device.
Reviewed-by: Emma Anholt <emma@anholt.net >
Reviewed-by: Neha Bhende <bhenden@vmware.com >
Reviewed-by: Roland Scheidegger <sroland@vmware.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12176 >
2021-08-03 22:13:10 +00:00
0ddac113f8
nir: Removing uses of SSA defs destroys SSA liveness
...
The liveness information will be a superset of real liveness so it's
unlikely something will explode if it tries to use it. However, it is
out-of-date and should be re-run if someone really wants it.
Reviewed-by: Emma Anholt <emma@anholt.net >
Reviewed-by: Alyssa Rosenzweig <alyssa@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12186 >
2021-08-03 21:36:53 +00:00
9dfe7fbc6b
isl: Use CLAMP macro instead of MIN of MAX
...
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12177 >
2021-08-03 12:55:11 -07:00
72259a870f
util: Add and use functions to calculate min and max int for a size
...
Many places need to know the maximum or minimum possible value for a
given size integer... so everyone just open-codes their favorite
version. There is some potential to hit either undefined or
implementation-defined behavior, so having one version that Just Works
seems beneficial.
v2: Fix copy-and-pasted bug (INT64_MAX instead of INT64_MIN) in
u_intmin. Noticed by CI. Lol. Rename functions
`s/u_(uint|int)(min|max)/u_\1N_\2/g`. Suggested by Jason. Add some
unit tests that would have caught the copy-and-paste bug before wasting
CI time. Change the implementation of u_intN_min to use the same
pattern as stdint.h. This avoids the integer division. Noticed by
Jason.
v3: Add changes to convert_clear_color
(src/gallium/drivers/iris/iris_clear.c). Suggested by Nanley.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net >
Suggested-by: Jason Ekstrand <jason@jlekstrand.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12177 >
2021-08-03 12:55:02 -07:00
08d6361591
ci: Update piglit to 4545a28cd8fea03fbab0e5f90bfbd812c32f3be1
...
Brings in duplicate subtest fixes, gpu_shader4 tests, and more. This
shuffles the radeonsi fractional test run, so we get to catch up with more
failing subtests.
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com >
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12110 >
2021-08-03 18:32:01 +00:00
f04f8ac692
ci/zink: Use deqp-runner suite support to reduce the CI job count.
...
The tests were passing so quickly, and the 1/4th GLES3 subset changed on
the transition to multiple testsuites, so I promoted it to a full run.
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com >
Acked-by: Tomeu Vizoso <tomeu.vizoso@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12110 >
2021-08-03 18:32:01 +00:00
55bd582598
ci/virgl: Use deqp-runner suite support to reduce CI job count.
...
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com >
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12110 >
2021-08-03 18:32:01 +00:00
cd3b6689b2
ci: Save dEQP results on all tests.
...
Everyone can get artifacts now. Let's make those artifacts useful.
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com >
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12110 >
2021-08-03 18:32:01 +00:00
ad2995d1e1
ci/i915g: Merge the two dEQP runs together.
...
Fewer buttons for me to have to click for manual MR testing.
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com >
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12110 >
2021-08-03 18:32:01 +00:00
6f7a921c99
ci/llvmpipe: Use the deqp-runner suite support to consolidate jobs.
...
5 jobs become 2, plus we add KHR-GLES3 and 31 to the test set since
it's cheap.
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com >
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12110 >
2021-08-03 18:32:01 +00:00
4658a9a479
ci: Uprev deqp-runner and use "suite" support to merge softpipe runs.
...
The deqp-runner "suite" support lets us specify all the deqp variants at
once and shard them across gitlab jobs, so we reduce docker overhead and
get fewer jobs to review the output of.
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com >
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12110 >
2021-08-03 18:32:01 +00:00
1bdab45594
ci/i915: Update deqp expectations for another test passing.
...
!11411 made this one start passing thanks to reducing instruction counts.
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com >
Acked-by: Tomeu Vizoso <tomeu.vizoso@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12110 >
2021-08-03 18:32:01 +00:00
97be8e42e4
intel/disasm: fix missing oword index decoding
...
Also switch to array of strings to show high/low dwords.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Fixes: daba2894ffcaio.oliveira@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12183 >
2021-08-03 17:26:37 +00:00
b4e5bf0637
clover/nir: Set constant buffer pointer size to host
...
The `argument::size` is supposed to represent the size of a pointer on
the host and not on the device (for which argument::target_size`
exists).
v3: Use `sizeof(buf)` instead of `marg.size`. (Francisco Jerez)
Fixes: 7c6f1d3bf9currojerez@riseup.net >
Signed-off-by: Pierre Moreau <dev@pmoreau.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10256 >
2021-08-03 16:43:49 +00:00
54dcccd535
clover/api: Interleave details in dispatch table
...
By adding comments regarding which version or extension introduced the
following dispatched functions, it makes it easier to glance at the
table and see which functions are missing for a particular version, but
more importantly makes it easier to compare against cl_icd.h and see if
anything is missing.
Reviewed-by: Karol Herbst <kherbst@redhat.com >
Signed-off-by: Pierre Moreau <dev@pmoreau.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10256 >
2021-08-03 16:43:48 +00:00
a6c26a6ad9
clover/spirv: Properly size 3-component vector args
...
This resolves clover returning `CL_INVALID_ARG_SIZE` whenever the OpenCL
CTS called `clSetKernelArg()` for 3-component vectors.
Fixes: 2147386505kherbst@redhat.com >
Signed-off-by: Pierre Moreau <dev@pmoreau.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10256 >
2021-08-03 16:43:48 +00:00
f69d1c1c56
clover/spirv: Increase max amount of function args
...
OpenCL only has an upper limit on the size taken by all arguments to a
kernel (implementation-defined, but at least 1024 bytes), and not on the
count of those arguments.
This fixes OpenCL-CTS’s api.min_max_parameter_size.
v2: Use `numeric_limits<>::max()` instead of hardcoded value.
Reviewed-by: Karol Herbst <kherbst@redhat.com >
Signed-off-by: Pierre Moreau <dev@pmoreau.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10256 >
2021-08-03 16:43:48 +00:00
5ffe059fd2
clover: Local memory needs to be aligned.
...
Fixes a couple of OpenCL CTS tests.
v3:
* Add a comment in module.hpp explaining that target_align means
something different for arguments of type local (Francisco Jerez)
* Squash in the fix for the LLVM backend.
Reviewed-by: Francisco Jerez <currojerez@riseup.net >
Signed-off-by: Pierre Moreau <dev@pmoreau.org >
Signed-off-by: Karol Herbst <kherbst@redhat.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10256 >
2021-08-03 16:43:48 +00:00
8061dfef6b
clover: Do not advertise OpenCL x.y when unsupported
...
Instead of hardcoding a fixed version for all devices, compute the
highest version supported by a device based on the different constraints
mandated by each new version.
For example, besides new functionalities, OpenCL 1.1 also increases the
minimum limits regarding the amount of local memory and the amount of
bytes taken by all arguments to a kernel. Some hardware (such as all
GPUs from NVIDIA’s Tesla micro-architecture) can support the additional
features but do not pass those new minimums.
v3:
* Change `get_highest_supported_version()` to return the version instead
of modifying the version components passed as arguments. (Francisco
Jerez)
* Tweak the line wrapping for `has_extension()`. (Francisco Jerez)
v2:
* Invert the ordering of OpenCL and OpenCL C version, to restrict OpenCL
version based on supported OpenCL C version.
* Rename `get_supported_version()` to `get_highest_supported_version()`;
* Use device methods to query parameters instead of manually executing
them;
* Clarify that the limit checking is only for non-custom devices
supporting the full profile.
* Check for mandatory extensions as well;
* Validate CL_DEVICE_MEM_BASE_ADDR_ALIGN;
* Fix the OpenCL>=1.1 minimum limit for CL_DEVICE_LOCAL_MEM_SIZE, from
32 * 1000 to 32 * 1024;
* Restrict to OpenCL 1.0 if OpenCL C 1.1 is not supported.
* Compute the highest supported version based on constraints (ignoring
2.x versions).
Reviewed-by: Karol Herbst <kherbst@redhat.com >
Signed-off-by: Pierre Moreau <dev@pmoreau.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10256 >
2021-08-03 16:43:48 +00:00
cd79351f02
d3d12: split up root parameter update and set
...
SRV descriptors can require state-transitions before it's legal to set
them on the command-list. We used to just set them right away, and get
away with is, because the validator didn't verify this because we used
to flag the parameters as volatile.
Now that we don't, we trigger validation errors when setting a root
parameter that needs a transition first.
So let's split up the logic a bit, so we can prepare the tables, then do
the transision, and finally set the tables. We do this for all tables
instead of just the SRVs, just because it makes the logic a bit easier to
follow. We leave root constants alone, because they will never require
this, and doing them late would just compilcate things.
Fixes: 1208290558jenatali@microsoft.com >
Reviewed-by: Bill Kristiansen <billkris@microsoft.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12187 >
2021-08-03 16:17:11 +00:00
06edc6adc8
ci: Use crosvm to run dEQP tests for virgl
...
Allows to use virtio-gpu to actually test the virgl driver.
Signed-off-by: Corentin Noël <corentin.noel@collabora.com >
Acked-by: Gert Wollny <gert.wollny@collabora.com >
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11320 >
2021-08-03 14:24:08 +00:00
10541d1fad
gallium/hud: initialize query
...
Most of the drivers don't set up the maximum value in the query info. So
when later hud_pane_set_max_value() is invoked, we are using a rather
"random" number.
Turns out that in some 32bit cases, this random number is big enough
that `leftmost_digit` is 0 because DIV_ROUND_UP() overflows, aborting
with an assertion.
Fixes: c91cf7d7d2michael.blumenkrantz@gmail.com >
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12181 >
2021-08-03 14:05:32 +00:00
ad83c06a5f
radv: fix missing cache flushes when clearing HTILE levels on GFX10+
...
The driver should accumulate the cache flush bits because if it uses
CP DMA for clearing the last level, it won't flush.
Found by inspection.
Cc: 21.2 mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com >
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12170 >
2021-08-03 12:59:57 +00:00
ebea075feb
radv: fix selecting the first active CU when profiling with SQTT
...
Fixes: d26bcc0f5csamuel.pitoiset@gmail.com >
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12167 >
2021-08-03 12:30:41 +00:00
f395057a82
gallivm: remove pointless no_filter_hacks flag
...
This flag now does the same thing as the no_quad_lod flag, so let's get
rid of it to reduce confusion.
Reviewed-by: Roland Scheidegger <sroland@vmware.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12125 >
2021-08-03 12:08:38 +00:00
4f56ded362
ci: Stop disabling filter hacks for llvmpipe.
...
Now that we've disabled brilinear and have per-pixel cube derivatives, we
can use the same rendering paths that end users will see.
In a few cases, we switch to the no_quad_lod option instead, because
otherwise we get a piglit failure.
Reviewed-by: Roland Scheidegger <sroland@vmware.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12125 >
2021-08-03 12:08:38 +00:00
34423391e0
gallivm: make rho-approximation opt-in instead of opt-out
...
The RHO approximation code has issues passing the OpenGL ES 3.0 CTS, so
let's make correctness the default instead.
Reviewed-by: Roland Scheidegger <sroland@vmware.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12125 >
2021-08-03 12:08:38 +00:00
6538b3e566
nir: add heuristic for instructions in loops with GCM
...
Moving instructions out of large loops tends to cause excessive
spilling. This appears to be a good limit.
In future it might make sense to make this a NIR options so
other drivers can set their own limits.
Tiger Lake
total instructions in shared programs: 20930180 -> 20926952 (-0.02%)
instructions in affected programs: 280768 -> 277540 (-1.15%)
helped: 734
HURT: 192
helped stats (abs) min: 1 max: 61 x̄: 5.16 x̃: 4
helped stats (rel) min: 0.04% max: 10.64% x̄: 3.23% x̃: 3.14%
HURT stats (abs) min: 1 max: 52 x̄: 2.90 x̃: 1
HURT stats (rel) min: 0.03% max: 9.76% x̄: 1.13% x̃: 0.61%
95% mean confidence interval for instructions value: -3.89 -3.08
95% mean confidence interval for instructions %-change: -2.49% -2.16%
Instructions are helped.
total cycles in shared programs: 841825217 -> 838817552 (-0.36%)
cycles in affected programs: 122088078 -> 119080413 (-2.46%)
helped: 941
HURT: 100
helped stats (abs) min: 1 max: 160080 x̄: 3274.31 x̃: 2660
helped stats (rel) min: <.01% max: 41.64% x̄: 5.50% x̃: 4.80%
HURT stats (abs) min: 1 max: 41856 x̄: 734.62 x̃: 26
HURT stats (rel) min: <.01% max: 7.29% x̄: 0.44% x̃: 0.27%
95% mean confidence interval for cycles value: -3236.56 -2541.85
95% mean confidence interval for cycles %-change: -5.26% -4.60%
Cycles are helped.
total sends in shared programs: 977905 -> 977782 (-0.01%)
sends in affected programs: 2279 -> 2156 (-5.40%)
helped: 119
HURT: 0
helped stats (abs) min: 1 max: 4 x̄: 1.03 x̃: 1
helped stats (rel) min: 0.60% max: 14.29% x̄: 6.93% x̃: 6.67%
95% mean confidence interval for sends value: -1.09 -0.98
95% mean confidence interval for sends %-change: -7.42% -6.45%
Sends are helped.
LOST: 2
GAINED: 0
Ice Lake
total instructions in shared programs: 19865361 -> 19861747 (-0.02%)
instructions in affected programs: 185789 -> 182175 (-1.95%)
helped: 593
HURT: 47
helped stats (abs) min: 1 max: 27 x̄: 6.17 x̃: 4
helped stats (rel) min: 0.19% max: 8.65% x̄: 4.53% x̃: 4.60%
HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.03% max: 0.23% x̄: 0.11% x̃: 0.04%
95% mean confidence interval for instructions value: -5.93 -5.37
95% mean confidence interval for instructions %-change: -4.32% -4.06%
Instructions are helped.
total loops in shared programs: 6120 -> 6117 (-0.05%)
loops in affected programs: 6 -> 3 (-50.00%)
helped: 3
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
total cycles in shared programs: 961777176 -> 959404350 (-0.25%)
cycles in affected programs: 172224180 -> 169851354 (-1.38%)
helped: 936
HURT: 80
helped stats (abs) min: 1 max: 9566 x̄: 2621.08 x̃: 2550
helped stats (rel) min: <.01% max: 41.77% x̄: 4.22% x̃: 3.84%
HURT stats (abs) min: 1 max: 59146 x̄: 1006.34 x̃: 24
HURT stats (rel) min: <.01% max: 3.78% x̄: 0.44% x̃: 0.25%
95% mean confidence interval for cycles value: -2513.72 -2157.20
95% mean confidence interval for cycles %-change: -4.13% -3.57%
Cycles are helped.
total sends in shared programs: 1019995 -> 1019872 (-0.01%)
sends in affected programs: 2283 -> 2160 (-5.39%)
helped: 119
HURT: 0
helped stats (abs) min: 1 max: 4 x̄: 1.03 x̃: 1
helped stats (rel) min: 0.60% max: 14.29% x̄: 6.91% x̃: 6.67%
95% mean confidence interval for sends value: -1.09 -0.98
95% mean confidence interval for sends %-change: -7.39% -6.42%
Sends are helped.
LOST: 4
GAINED: 0
Skylake
total instructions in shared programs: 17994337 -> 17993846 (<.01%)
instructions in affected programs: 146294 -> 145803 (-0.34%)
helped: 190
HURT: 47
helped stats (abs) min: 1 max: 12 x̄: 2.83 x̃: 3
helped stats (rel) min: 0.14% max: 4.29% x̄: 1.08% x̃: 0.90%
HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.03% max: 0.22% x̄: 0.11% x̃: 0.04%
95% mean confidence interval for instructions value: -2.30 -1.84
95% mean confidence interval for instructions %-change: -0.95% -0.74%
Instructions are helped.
total loops in shared programs: 6029 -> 6023 (-0.10%)
loops in affected programs: 12 -> 6 (-50.00%)
helped: 6
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
95% mean confidence interval for loops value: -1.00 -1.00
95% mean confidence interval for loops %-change: -50.00% -50.00%
Loops are helped.
total cycles in shared programs: 939062940 -> 938023548 (-0.11%)
cycles in affected programs: 169671482 -> 168632090 (-0.61%)
helped: 980
HURT: 134
helped stats (abs) min: 1 max: 25000 x̄: 1075.57 x̃: 1052
helped stats (rel) min: <.01% max: 42.75% x̄: 2.51% x̃: 1.32%
HURT stats (abs) min: 1 max: 837 x̄: 109.45 x̃: 20
HURT stats (rel) min: <.01% max: 5.71% x̄: 0.73% x̃: 0.21%
95% mean confidence interval for cycles value: -1005.89 -860.17
95% mean confidence interval for cycles %-change: -2.39% -1.84%
Cycles are helped.
total sends in shared programs: 1026848 -> 1026724 (-0.01%)
sends in affected programs: 2302 -> 2178 (-5.39%)
helped: 120
HURT: 0
helped stats (abs) min: 1 max: 4 x̄: 1.03 x̃: 1
helped stats (rel) min: 0.60% max: 14.29% x̄: 6.91% x̃: 6.67%
95% mean confidence interval for sends value: -1.09 -0.98
95% mean confidence interval for sends %-change: -7.40% -6.43%
Sends are helped.
LOST: 1
GAINED: 1
Broadwell
total instructions in shared programs: 17605621 -> 17605154 (<.01%)
instructions in affected programs: 145691 -> 145224 (-0.32%)
helped: 184
HURT: 48
helped stats (abs) min: 1 max: 12 x̄: 2.83 x̃: 3
helped stats (rel) min: 0.13% max: 4.29% x̄: 1.09% x̃: 0.93%
HURT stats (abs) min: 1 max: 7 x̄: 1.12 x̃: 1
HURT stats (rel) min: 0.03% max: 0.48% x̄: 0.12% x̃: 0.04%
95% mean confidence interval for instructions value: -2.26 -1.77
95% mean confidence interval for instructions %-change: -0.95% -0.73%
Instructions are helped.
total loops in shared programs: 5968 -> 5963 (-0.08%)
loops in affected programs: 10 -> 5 (-50.00%)
helped: 5
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
95% mean confidence interval for loops value: -1.00 -1.00
95% mean confidence interval for loops %-change: -50.00% -50.00%
Loops are helped.
total cycles in shared programs: 1000679489 -> 998592756 (-0.21%)
cycles in affected programs: 173421234 -> 171334501 (-1.20%)
helped: 993
HURT: 153
helped stats (abs) min: 1 max: 766608 x̄: 2118.49 x̃: 1080
helped stats (rel) min: <.01% max: 54.61% x̄: 2.61% x̃: 1.73%
HURT stats (abs) min: 1 max: 2200 x̄: 110.61 x̃: 11
HURT stats (rel) min: <.01% max: 5.68% x̄: 0.63% x̃: 0.06%
95% mean confidence interval for cycles value: -3191.23 -450.54
95% mean confidence interval for cycles %-change: -2.47% -1.89%
Cycles are helped.
total sends in shared programs: 996341 -> 996222 (-0.01%)
sends in affected programs: 2151 -> 2032 (-5.53%)
helped: 115
HURT: 0
helped stats (abs) min: 1 max: 4 x̄: 1.03 x̃: 1
helped stats (rel) min: 0.60% max: 14.29% x̄: 7.07% x̃: 6.67%
95% mean confidence interval for sends value: -1.09 -0.98
95% mean confidence interval for sends %-change: -7.55% -6.58%
Sends are helped.
Haswell
total instructions in shared programs: 16038375 -> 16038121 (<.01%)
instructions in affected programs: 216797 -> 216543 (-0.12%)
helped: 185
HURT: 217
helped stats (abs) min: 1 max: 12 x̄: 2.84 x̃: 3
helped stats (rel) min: 0.13% max: 4.23% x̄: 1.30% x̃: 1.20%
HURT stats (abs) min: 1 max: 6 x̄: 1.25 x̃: 1
HURT stats (rel) min: 0.03% max: 5.66% x̄: 0.61% x̃: 0.40%
95% mean confidence interval for instructions value: -0.85 -0.41
95% mean confidence interval for instructions %-change: -0.40% -0.14%
Instructions are helped.
total loops in shared programs: 5947 -> 5942 (-0.08%)
loops in affected programs: 10 -> 5 (-50.00%)
helped: 5
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
95% mean confidence interval for loops value: -1.00 -1.00
95% mean confidence interval for loops %-change: -50.00% -50.00%
Loops are helped.
total cycles in shared programs: 967655093 -> 965746713 (-0.20%)
cycles in affected programs: 197288924 -> 195380544 (-0.97%)
helped: 950
HURT: 195
helped stats (abs) min: 1 max: 782820 x̄: 2274.79 x̃: 1260
helped stats (rel) min: <.01% max: 54.26% x̄: 3.02% x̃: 1.71%
HURT stats (abs) min: 1 max: 15790 x̄: 1295.73 x̃: 21
HURT stats (rel) min: <.01% max: 119.85% x̄: 7.76% x̃: 0.11%
95% mean confidence interval for cycles value: -3014.22 -319.19
95% mean confidence interval for cycles %-change: -1.83% -0.55%
Cycles are helped.
total sends in shared programs: 934894 -> 934765 (-0.01%)
sends in affected programs: 2192 -> 2063 (-5.89%)
helped: 115
HURT: 2
helped stats (abs) min: 1 max: 4 x̄: 1.14 x̃: 1
helped stats (rel) min: 0.60% max: 28.57% x̄: 7.68% x̃: 6.67%
HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel) min: 16.67% max: 16.67% x̄: 16.67% x̃: 16.67%
95% mean confidence interval for sends value: -1.23 -0.98
95% mean confidence interval for sends %-change: -8.28% -6.24%
Sends are helped.
LOST: 1
GAINED: 18
Ivy Bridge
total instructions in shared programs: 15269357 -> 15269398 (<.01%)
instructions in affected programs: 190484 -> 190525 (0.02%)
helped: 77
HURT: 206
helped stats (abs) min: 1 max: 6 x̄: 2.47 x̃: 3
helped stats (rel) min: 0.14% max: 5.31% x̄: 1.46% x̃: 1.65%
HURT stats (abs) min: 1 max: 3 x̄: 1.12 x̃: 1
HURT stats (rel) min: 0.03% max: 2.38% x̄: 0.42% x̃: 0.40%
95% mean confidence interval for instructions value: -0.06 0.35
95% mean confidence interval for instructions %-change: -0.21% 0.03%
Inconclusive result (value mean confidence interval includes 0).
total loops in shared programs: 4001 -> 3996 (-0.12%)
loops in affected programs: 10 -> 5 (-50.00%)
helped: 5
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
95% mean confidence interval for loops value: -1.00 -1.00
95% mean confidence interval for loops %-change: -50.00% -50.00%
Loops are helped.
total cycles in shared programs: 562045564 -> 561063543 (-0.17%)
cycles in affected programs: 200924872 -> 199942851 (-0.49%)
helped: 748
HURT: 160
helped stats (abs) min: 2 max: 14926 x̄: 1692.94 x̃: 1620
helped stats (rel) min: <.01% max: 53.29% x̄: 3.17% x̃: 1.87%
HURT stats (abs) min: 2 max: 15726 x̄: 1776.86 x̃: 36
HURT stats (rel) min: <.01% max: 114.43% x̄: 10.66% x̃: 0.21%
95% mean confidence interval for cycles value: -1237.33 -925.71
95% mean confidence interval for cycles %-change: -1.54% 0.08%
Inconclusive result (%-change mean confidence interval includes 0).
total sends in shared programs: 893348 -> 893330 (<.01%)
sends in affected programs: 187 -> 169 (-9.63%)
helped: 14
HURT: 0
helped stats (abs) min: 1 max: 2 x̄: 1.29 x̃: 1
helped stats (rel) min: 4.08% max: 22.22% x̄: 11.70% x̃: 10.10%
95% mean confidence interval for sends value: -1.56 -1.02
95% mean confidence interval for sends %-change: -14.92% -8.48%
Sends are helped.
LOST: 1
GAINED: 19
Sandy Bridge
total instructions in shared programs: 11785227 -> 11785774 (<.01%)
instructions in affected programs: 78403 -> 78950 (0.70%)
helped: 65
HURT: 505
helped stats (abs) min: 1 max: 4 x̄: 2.22 x̃: 3
helped stats (rel) min: 0.14% max: 4.17% x̄: 1.19% x̃: 1.38%
HURT stats (abs) min: 1 max: 5 x̄: 1.37 x̃: 1
HURT stats (rel) min: 0.24% max: 3.33% x̄: 1.57% x̃: 1.72%
95% mean confidence interval for instructions value: 0.85 1.07
95% mean confidence interval for instructions %-change: 1.16% 1.36%
Instructions are HURT.
total loops in shared programs: 2441 -> 2437 (-0.16%)
loops in affected programs: 8 -> 4 (-50.00%)
helped: 4
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
95% mean confidence interval for loops value: -1.00 -1.00
95% mean confidence interval for loops %-change: -50.00% -50.00%
Loops are helped.
total cycles in shared programs: 497178796 -> 496669298 (-0.10%)
cycles in affected programs: 51483322 -> 50973824 (-0.99%)
helped: 476
HURT: 137
helped stats (abs) min: 2 max: 7502 x̄: 1079.36 x̃: 1260
helped stats (rel) min: <.01% max: 42.50% x̄: 2.31% x̃: 0.86%
HURT stats (abs) min: 2 max: 754 x̄: 31.23 x̃: 18
HURT stats (rel) min: <.01% max: 3.01% x̄: 0.09% x̃: 0.02%
95% mean confidence interval for cycles value: -901.99 -760.32
95% mean confidence interval for cycles %-change: -2.20% -1.36%
Cycles are helped.
total sends in shared programs: 642919 -> 642915 (<.01%)
sends in affected programs: 32 -> 28 (-12.50%)
helped: 4
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 11.11% max: 14.29% x̄: 12.70% x̃: 12.70%
95% mean confidence interval for sends value: -1.00 -1.00
95% mean confidence interval for sends %-change: -15.61% -9.78%
Sends are helped.
Iron Lake
total instructions in shared programs: 8180061 -> 8180248 (<.01%)
instructions in affected programs: 65004 -> 65191 (0.29%)
helped: 59
HURT: 253
helped stats (abs) min: 1 max: 4 x̄: 2.24 x̃: 3
helped stats (rel) min: 0.16% max: 2.23% x̄: 1.04% x̃: 1.29%
HURT stats (abs) min: 1 max: 5 x̄: 1.26 x̃: 1
HURT stats (rel) min: 0.21% max: 3.85% x̄: 0.93% x̃: 0.60%
95% mean confidence interval for instructions value: 0.43 0.77
95% mean confidence interval for instructions %-change: 0.45% 0.68%
Instructions are HURT.
total loops in shared programs: 863 -> 861 (-0.23%)
loops in affected programs: 4 -> 2 (-50.00%)
helped: 2
HURT: 0
total cycles in shared programs: 239357490 -> 238907668 (-0.19%)
cycles in affected programs: 17314006 -> 16864184 (-2.60%)
helped: 176
HURT: 34
helped stats (abs) min: 4 max: 13400 x̄: 2558.05 x̃: 2920
helped stats (rel) min: 0.01% max: 35.58% x̄: 3.76% x̃: 2.69%
HURT stats (abs) min: 2 max: 14 x̄: 11.59 x̃: 14
HURT stats (rel) min: <.01% max: 0.06% x̄: 0.03% x̃: 0.03%
95% mean confidence interval for cycles value: -2440.68 -1843.34
95% mean confidence interval for cycles %-change: -3.78% -2.51%
Cycles are helped.
GM45
total instructions in shared programs: 4985293 -> 4985401 (<.01%)
instructions in affected programs: 58807 -> 58915 (0.18%)
helped: 57
HURT: 202
helped stats (abs) min: 1 max: 4 x̄: 2.26 x̃: 3
helped stats (rel) min: 0.15% max: 2.23% x̄: 1.06% x̃: 1.29%
HURT stats (abs) min: 1 max: 5 x̄: 1.17 x̃: 1
HURT stats (rel) min: 0.21% max: 3.85% x̄: 0.76% x̃: 0.48%
95% mean confidence interval for instructions value: 0.22 0.61
95% mean confidence interval for instructions %-change: 0.24% 0.48%
Instructions are HURT.
total loops in shared programs: 639 -> 638 (-0.16%)
loops in affected programs: 2 -> 1 (-50.00%)
helped: 1
HURT: 0
total cycles in shared programs: 153794236 -> 153546274 (-0.16%)
cycles in affected programs: 9947778 -> 9699816 (-2.49%)
helped: 110
HURT: 31
helped stats (abs) min: 4 max: 13400 x̄: 2257.51 x̃: 1796
helped stats (rel) min: 0.01% max: 35.58% x̄: 4.33% x̃: 2.45%
HURT stats (abs) min: 2 max: 14 x̄: 11.74 x̃: 14
HURT stats (rel) min: <.01% max: 0.06% x̄: 0.03% x̃: 0.03%
95% mean confidence interval for cycles value: -2113.77 -1403.42
95% mean confidence interval for cycles %-change: -4.27% -2.47%
Cycles are helped.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2899
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12064 >
2021-08-03 10:54:50 +00:00
a7f2e683de
nir: move nir_block_ends_in_break() to nir.h
...
Will be used in a following commit.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12064 >
2021-08-03 10:54:50 +00:00
a9ed4538ab
nir: add indirect loop unrolling to compiler options
...
This is where it should be rather than having to pass it into the
optimisation pass every time.
It also allows us to call the loop analysis pass without having to
duplicate these options which we will do later in this series.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12064 >
2021-08-03 10:54:50 +00:00
a654e39f15
intel/compiler: make sure swizzle is applied to if condition
...
This fixes a hang in the following piglit test when GCM moves a
UBO load outside of the loop.
tests/shaders/ssa/fs-if-def-else-break.shader_test
The end NIR ends up looking like this:
vec2 32 ssa_3 = intrinsic load_ubo (ssa_2, ssa_0) (0, 1073741824, 0, 0, 8)
vec1 32 ssa_4 = mov ssa_3.x
vec1 32 ssa_5 = inot ssa_3.y
/* succs: block_1 */
loop {
...
if ssa_5 { }
}
Fixes: 1edf67fc3fian.d.romanick@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12064 >
2021-08-03 10:54:50 +00:00
Samuel Pitoiset