Alexandros Frantzis [Wed, 8 May 2019 13:17:53 +0000 (16:17 +0300)]
virgl: Support copy transfers
Support transfers that use a different resource as the source of data to
transfer. This will be used in upcoming commits to send data to host
buffers through a transfer upload buffer, in order to avoid waiting
when the buffer resource is busy.
Note that we don't support queueing copy transfers in the transfer
queue. Copy transfers should be emitted directly in the command queue,
allowing us to avoid flushes before them and leads to better
performance.
Signed-off-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Alexandros Frantzis [Tue, 14 May 2019 09:38:24 +0000 (12:38 +0300)]
virgl: Add copy_transfer3d definitions
Introduce definitions for the copy_transfer3d protocol command and virgl
capability. This command transfers data to the host by copying through
another resource, and will be used in upcoming commits to avoid waiting
when transferring data for busy resources.
Signed-off-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Alexandros Frantzis [Tue, 4 Jun 2019 13:43:31 +0000 (16:43 +0300)]
virgl: Make VIRGL_BIND_STAGING resources cacheable
This could help performance when trying to recreate such resources for
copy transfers.
Signed-off-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Alexandros Frantzis [Mon, 20 May 2019 10:00:38 +0000 (13:00 +0300)]
virgl: Support VIRGL_BIND_STAGING
Support a new virgl bind type for staging buffers which don't require
dedicated host-side storage. These will be used to implement copy
transfers.
Signed-off-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Alexandros Frantzis [Thu, 23 May 2019 18:16:48 +0000 (21:16 +0300)]
virgl: Avoid unfinished transfer_get with PIPE_TRANSFER_DONTBLOCK
If we are not allowed to block, and we know that we will have to wait,
either because the resource is busy, or because it will become busy due
to a readback, return early to avoid performing an incomplete
transfer_get. Such an incomplete transfer_get may finish at any time,
during which another unsynchronized map could write to the resource
contents, leaving the contents in an undefined state.
Signed-off-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Suggested-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Alexandros Frantzis [Tue, 4 Jun 2019 13:40:33 +0000 (16:40 +0300)]
virgl: Deduplicate checks for resource caching
Also fixes a missed check for VIRGL_BIND_CUSTOM in one of the duplicate
code snippets.
Note that legacy fences also use VIRGL_BIND_CUSTOM, but we ensured they
don't go through the cache in the previous commit.
Signed-off-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Alexandros Frantzis [Wed, 5 Jun 2019 07:32:01 +0000 (10:32 +0300)]
virgl: Don't try to use cached resources for legacy fences
Resources for fences should not be from the cache, since we are basing
the fence status on the resource creation busy status.
Signed-off-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Alexandros Frantzis [Thu, 23 May 2019 11:58:46 +0000 (14:58 +0300)]
virgl: More info about chosen alignment value
Add more info about why the value of VIRGL_MAP_BUFFER_ALIGNMENT.
Signed-off-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Chia-I Wu [Thu, 16 May 2019 22:01:36 +0000 (15:01 -0700)]
virgl: store all info about atomic buffers
We will need the full info. This also speeds up
virgl_attach_res_atomic_buffers and fixes resource leaks when the
context is destroyed.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Chia-I Wu [Thu, 16 May 2019 21:33:15 +0000 (14:33 -0700)]
virgl: add shader images to virgl_shader_binding_state
It replaces virgl_context::images.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Chia-I Wu [Thu, 16 May 2019 21:33:15 +0000 (14:33 -0700)]
virgl: add SSBOs to virgl_shader_binding_state
It replaces virgl_context::ssbos.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Chia-I Wu [Thu, 16 May 2019 21:00:54 +0000 (14:00 -0700)]
virgl: add UBOs to virgl_shader_binding_state
It replaces virgl_context::ubos.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Chia-I Wu [Thu, 16 May 2019 20:32:18 +0000 (13:32 -0700)]
virgl: add virgl_shader_binding_state
virgl_shader_binding_state will be used to manage all per-stage
shader bindings. For now, it manages only sampler views.
This replaces virgl_textures_info and fixes some issues
- start_slot is now honored
- views outside of [start_slot, slart_slot+count) are unmodified
- views are released when the context is destroyed
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Kenneth Graunke [Fri, 7 Jun 2019 19:41:28 +0000 (12:41 -0700)]
iris: Zero shs->cbuf0 when binding a passthrough TCS
Fixes valgrind errors when running two CTS tests back to back:
- KHR-GL45.shader_image_load_store.basic-allTargets-loadStoreT*
(The first test has an actual TCS, the second uses passthrough.)
Jason Ekstrand [Fri, 7 Jun 2019 20:13:30 +0000 (15:13 -0500)]
intel/blorp: Only double the fast-clear rect alignment on HSW
This restriction was accidentally added to the BSpec/PRM as an
unrestricted restriction starting with the HSW docs and it was never
removed. However, it only ever applied to HSW and actually potentially
causes problems on BDW and above where we have mipmapped fast-clears.
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Rob Clark [Thu, 6 Jun 2019 16:55:33 +0000 (09:55 -0700)]
freedreno/a6xx: re-arrange program stageobj/group
Split out a separate program config state group to run early before the
other groups.
This seems to help w/ intermittent "missed tiles" (although I had
assumed that was a mem2gmem issue), or at least I can't reproduce that
issue with this patch, but can without.
It has the benefit of HLSQ_VS_CNTL.CONSTLEN matching for VS and BS.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Rob Clark [Thu, 6 Jun 2019 17:22:04 +0000 (10:22 -0700)]
freedreno/a6xx: fix hangs with newer sqe fw
With the newer (v1.76) fw, we were getting hangs (compared to older
v1.66 fw). Re-work the GMEM code to structure things a bit closer to
the blob. This moves some PKT7 packets from IB2 to IB1, which I think
is what was confusing SQE and causing it to get stuck in an infinite
loop. But in general structuring things at least closer to the same way
blob does makes it easier to compare cmdstream.
Note: this is a bit on the large side for what I'd normally consider for
stable.. but right now it is looking like it is the newer fw that is
headed for linux-firmware. This should defn have some soak time on
master, but probably a good idea for this patch to end up in distro mesa
builds by the time a630_sqe.fw hits linux-firmware.
Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Rob Clark [Thu, 6 Jun 2019 17:19:07 +0000 (10:19 -0700)]
freedreno/a6xx: WFI before RB_CCU_CNTL writes
This seems to be in a block of non buffered/context regs. Blob always
WFIs before write, so probably a good idea.
Annoyingly, compared to ealier gens, it is a bit harder to tell from the
register offset whether it is a buffered reg, it isn't as simple as
everything below 0x2000, it seems.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Rob Clark [Thu, 6 Jun 2019 16:53:15 +0000 (09:53 -0700)]
freedreno/a6xx: don't pre-dispatch texture fetch on accident
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Rob Clark [Thu, 6 Jun 2019 16:45:25 +0000 (09:45 -0700)]
freedreno/a6xx: fix issues with gallium HUD
In some cases the draw for the text wasn't working. This seems to be
fixed by resyncing some of the "golded registers" from blob (initial
values were based on somewhat older blob version).
Perhaps good to have a bit of soak time on master, but would be good
to eventually land in 19.x stable branches.
Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Nanley Chery [Wed, 24 Oct 2018 21:50:32 +0000 (14:50 -0700)]
anv/cmd_buffer: Initalize the clear color struct for CNL+
On CNL+, the clear color struct is composed of RGBA channel values and
fields which are either reserved by the HW or used to control
fast-clears. Currently anv initializes the channel values to zero and
allows the other fields to be undefined.
Satisfy the MBZ field requirements by removing an optimization that
doesn't hold true for CNL+ and pulling in the number of dwords to
initialize from ISL.
Cc: <mesa-stable@lists.freedesktop.org>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Jon Turney [Thu, 6 Jun 2019 15:44:08 +0000 (16:44 +0100)]
glx/windows: Fix compilation with -Werror-format
Fix compilation where the DWORD type is used with a format, after
-Werror-format added by
c9c1e261.
Some Win32 API types are different fundamental types in the 32-bit and
64-bit versions. This problem is then further compounded by the fact
that whilst both 32-bit Cygwin and 32-bit MinGW use the ILP32 data
model, 64-bit MinGW uses the LLP64 data model, but 64-bit Cygwin uses
the LP64 data model. This makes it near impossible to write printf
format specifiers which are correct for all those targets.
In the Win32 API, DWORD is an unsigned, 32-bit type. So, it is defined
in terms of an unsigned long, except in the LP64 data model used by
64-bit Cygwin, where it is an unsigned int.
It should always be safe to cast it to unsigned int and use %u or %x.
Reviewed-by: Eric Anholt <eric@anholt.net>
Kenneth Graunke [Fri, 7 Jun 2019 18:26:20 +0000 (11:26 -0700)]
iris: Rename bind_state to bind_shader_state.
bind_state is possibly the worst name ever. For create, we used
create_shader_state, which is more descriptive. Put shader in the name.
Kenneth Graunke [Fri, 7 Jun 2019 00:36:09 +0000 (17:36 -0700)]
isl: Mark enum isl_channel_select packed so it becomes 1 byte.
I recently discovered that the following code lead to valgrind errors:
struct isl_swizzle swizzle = ISL_SWIZZLE_IDENTITY;
VALGRIND_CHECK_MEM_IS_DEFINED(&swizzle, sizeof(swizzle));
which is surprising, because struct isl_swizzle is simply:
struct isl_swizzle {
enum isl_channel_select r:4;
enum isl_channel_select g:4;
enum isl_channel_select b:4;
enum isl_channel_select a:4;
};
and the above code initializes all of them with a C99 initializer.
Iván Briano reminded me that C99 initializers don't necessarily zero
padding. A quick inspection revealed that sizeof(struct isl_swizzle)
was 4 (rather than the expected 2). Ian Romanick suggested changing
it to uint16_t, since this is essentially dicing up an unsigned, and
that worked.
This patch marks enum isl_channel_select packed, changing its size
from 4 bytes to 1 byte. This then makes struct isl_swizzle 2 bytes,
with no bogus padding fields. This eliminates valgrind undefined
memory warnings.
These isl_swizzle values become part of our BLORP blit program keys,
which are then hashed. This undefined padding was being included in
the hashing, possibly leading to issues. I originally saw this error
when running KHR-GL45.texture_size_promotion.functional in iris under
valgrind.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Alyssa Rosenzweig [Thu, 6 Jun 2019 19:04:16 +0000 (12:04 -0700)]
panfrost/ci: Texture wrap tests are legitimately fixed
These depended on the wallpaper reload.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Alyssa Rosenzweig [Thu, 6 Jun 2019 18:58:57 +0000 (11:58 -0700)]
panfrost/midgard: Lower inot to inor with 0
We were previously lowering to inand, but the second arg was not
duplicated so inot would always return ~0. Oops.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Alyssa Rosenzweig [Thu, 6 Jun 2019 18:20:21 +0000 (11:20 -0700)]
panfrost/midgard: Cleanup tag fetch in disassembler
Trivial.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Alyssa Rosenzweig [Thu, 6 Jun 2019 18:19:44 +0000 (11:19 -0700)]
panfrost/midgard: Use fancy iterator
Trivial cleanup.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Alyssa Rosenzweig [Thu, 6 Jun 2019 18:19:13 +0000 (11:19 -0700)]
panfrost/midgard: Cull dead branches
This fixes bugs with complex control flow.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Alyssa Rosenzweig [Thu, 6 Jun 2019 18:18:30 +0000 (11:18 -0700)]
panfrost/midgard: Add mir_print_bundle helper
This helps with debugging scheduling/emission.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Alyssa Rosenzweig [Thu, 6 Jun 2019 17:21:57 +0000 (10:21 -0700)]
panfrost/midgard/disasm: Pretty-print branch tags
Just makes it a little more obvious what's going on.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Alyssa Rosenzweig [Thu, 6 Jun 2019 16:42:23 +0000 (09:42 -0700)]
panfrost/ci: Note some since-fixed tests
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Alyssa Rosenzweig [Thu, 6 Jun 2019 16:15:26 +0000 (09:15 -0700)]
panfrost/midgard: Vectorize I/O
This uses the new mesa/st functionality for NIR I/O vectorization, which
eliminates a number of corner cases (resulting in assorted dEQP
failures and regressions) and should improve performance substantial due
to lessened pressure on the load/store pipe.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Alyssa Rosenzweig [Thu, 6 Jun 2019 15:21:27 +0000 (08:21 -0700)]
panfrost/midgard: Remove varyings delay pass
This pass interfered with the more delicate path required for
non-vectorized I/O. It's also ugly and duplicating the job of an actual
honest-to-goodness scheduler.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Alyssa Rosenzweig [Thu, 6 Jun 2019 15:16:04 +0000 (08:16 -0700)]
panfrost/midgard: Apply component to load_input
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Eric Engestrom [Fri, 7 Jun 2019 15:04:25 +0000 (16:04 +0100)]
nir: fix s/&&/||/ typo
Fixes: cd73b6174b093b75f581 "nir/lower_to_source_mods: Stop turning add, sat, and neg into mov"
Signed-off-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kristian H. Kristensen [Fri, 7 Jun 2019 03:29:38 +0000 (20:29 -0700)]
freedreno/a6xx: Drop struct stage array
This now boils down to just picking between binning or vertex shader
and dummy_fs or real fs, which we can do in a couple of lines of code
instead. The constlen logic isn't doing what it thinks it's doing,
both constlens at this point
MAX2(s[VS].constlen, align(state->bs->constlen, 4));
are binning shader constlens. We'll have to revisit the constlen
logic, but this commit doesn't change how it works.
Reviewed-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Kristian H. Kristensen [Tue, 4 Jun 2019 20:44:48 +0000 (13:44 -0700)]
freedreno/a6xx: Drop support for SS6_DIRECT shader upload
a6xx only supports indirect shaders.
Reviewed-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Kristian H. Kristensen [Thu, 6 Jun 2019 04:35:35 +0000 (21:35 -0700)]
freedreno/a6xx: Share shader_t_to_opcode
We have a similar function in fd6_program.c. Move to fd6_emit.h and
share.
Reviewed-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Kristian H. Kristensen [Mon, 3 Jun 2019 21:12:59 +0000 (14:12 -0700)]
freedreno/a6xx: Consolidate more of dword 0 building in fd6_draw_vbo
There's already a bit of duplicated logic here and tessellation will
add more. Build up dword 0 in fd6_draw_vbo() and drop the a4xx in the
process.
Reviewed-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Kristian H. Kristensen [Mon, 3 Jun 2019 21:01:14 +0000 (14:01 -0700)]
freedreno: Move fd4_size2indextype() helper to freedreno_util.h
In preparation for refactoring fd6_draw.c a bit.
Reviewed-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Samuel Pitoiset [Thu, 30 May 2019 07:58:01 +0000 (09:58 +0200)]
radv: enable VK_EXT_sample_locations
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Thu, 30 May 2019 08:26:43 +0000 (10:26 +0200)]
radv: enable HTILE for images that might need variable sample locations
This is now supported.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Thu, 30 May 2019 10:27:29 +0000 (12:27 +0200)]
radv: handle sample locations during automatic layout transitions
From the Vulkan spec 1.1.109:
"Some implementations may need to evaluate depth image values
while performing image layout transitions. To accommodate this,
instances of the VkSampleLocationsInfoEXT structure can be
specified for each situation where an explicit or automatic
layout transition has to take place. [...] and
VkRenderPassSampleLocationsBeginInfoEXT can be chained from
VkRenderPassBeginInfo to provide sample locations for layout
transitions performed implicitly by a render pass instance."
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Thu, 30 May 2019 12:10:42 +0000 (14:10 +0200)]
radv: determine the first subpass id for every attachments
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Thu, 30 May 2019 10:23:21 +0000 (12:23 +0200)]
radv: handle sample locations during explicit depth/stencil transitions
From the Vulkan spec 1.1.109,
"Some implementations may need to evaluate depth image values
while performing image layout transitions. To accommodate this,
instances of the VkSampleLocationsInfoEXT structure can be
specified for each situation where an explicit or automatic
layout transition has to take place. VkSampleLocationsInfoEXT
can be chained from VkImageMemoryBarrier structures to provide
sample locations for layout transitions performed by
vkCmdWaitEvents and vkCmdPipelineBarrier calls."
This handles explicit depth/stencil layout transitions performed
with CmdWaitEvents() or CmdPipelineBarrier().
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Thu, 30 May 2019 10:20:12 +0000 (12:20 +0200)]
radv: allow the depth decompress pass to emit dynamic sample locations
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Thu, 30 May 2019 09:52:56 +0000 (11:52 +0200)]
radv: allow to set dynamic sample locations to the depth decompress pass
If VK_EXT_sample_locations is used, the driver might need to emit
the sample locations specified during layout transitions.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Thu, 30 May 2019 09:50:22 +0000 (11:50 +0200)]
radv: allow to save/restore sample locations during meta operations
This will be used for the depth decompress pass that might need
to emit variable sample locations during layout transitions.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Kenneth Graunke [Fri, 7 Jun 2019 07:57:25 +0000 (00:57 -0700)]
iris: Sweep the NIR in iris_create_uncompiled_shader().
We run a ton of backend specific passes here (mostly brw_preprocess_nir)
and ought to sweep up any unused memory at this point, since we're going
to hang on to this NIR for as long as the linked program lives.
Eduardo Lima Mitev [Sun, 12 May 2019 22:33:57 +0000 (00:33 +0200)]
ir3: Use the new NIR lowering pass for integer multiplication
Shader-db stats courtesy of Eric Anholt:
total instructions in shared programs:
6480215 ->
6475457 (-0.07%)
instructions in affected programs: 662105 -> 657347 (-0.72%)
helped: 1209
HURT: 13
total constlen in shared programs:
1432704 ->
1427769 (-0.34%)
constlen in affected programs: 100063 -> 95128 (-4.93%)
helped: 512
HURT: 0
total max_sun in shared programs: 875561 -> 873387 (-0.25%)
max_sun in affected programs: 46179 -> 44005 (-4.71%)
helped: 1087
HURT: 0
Reviewed-by: Eric Anholt <eric@anholt.net>
Eduardo Lima Mitev [Sun, 12 May 2019 22:23:58 +0000 (00:23 +0200)]
ir3/nir: Add new NIR AlgebraicPass for lowering imul
Currently, ir3 backend compiler is lowering integer multiplication from:
dst = a * b
to:
dst = (al * bl) + (ah * bl << 16) + (al * bh << 16)
by emitting this code:
mull.u tmp0, a, b ; mul low, i.e. al * bl
madsh.m16 tmp1, a, b, tmp0 ; mul-add shift high mix, i.e. ah * bl << 16
madsh.m16 dst, b, a, tmp1 ; i.e. al * bh << 16
which at that point has very low chances of being optimized.
This patch adds a new nir_algebraic.AlgebraicPass to performs this
lowering during NIR algebraic optimization passes, giving it a better
chance for optimizing the resulting code.
Reviewed-by: Eric Anholt <eric@anholt.net>
Eduardo Lima Mitev [Sun, 12 May 2019 22:09:38 +0000 (00:09 +0200)]
nir_algebraic: Add basic optimizations for umul_low and imadsh_mix16
For umul_low (al * bl), zero is returned if the low 16-bits word of either
source is zero.
for imadsh_mix16 (ah * bl << 16 + c), c is returned if either 'ah' or 'bl'
is zero.
A couple of nir_search_helpers are added:
is_upper_half_zero() returns true if the highest word of all components of
an integer NIR alu src are zero.
is_lower_half_zero() returns true if the lowest word of all components of
an integer nir alu src are zero.
Reviewed-by: Eric Anholt <eric@anholt.net>
Eduardo Lima Mitev [Sun, 12 May 2019 19:12:59 +0000 (21:12 +0200)]
ir3/compiler: Handle new alu opcodes 'umul_low' and 'imadsh_mix16'
They directly emit ir3_MULL_U and ir3_MADSH_M16 respectively.
Reviewed-by: Eric Anholt <eric@anholt.net>
Eduardo Lima Mitev [Fri, 29 Mar 2019 09:49:12 +0000 (10:49 +0100)]
nir/opcodes: Add new 'umul_low' and 'imadsh_mix16' opcodes
'umul_low' is the low 32-bits of unsigned integer multiply. It maps
directly to ir3's MULL_U.
'imadsh_mix16' is multiply add with shift and mix, an ir3 specific
instruction that maps directly to ir3's IMADSH_M16.
Both are necessary for the lowering of integer multiplication on
Freedreno, which will be introduced later in this series.
Reviewed-by: Eric Anholt <eric@anholt.net>
Iago Toral Quiroga [Thu, 6 Jun 2019 08:04:27 +0000 (10:04 +0200)]
v3d: don't emit point coordinates varyings if the FS doesn't read them
We still need to emit them in V3D 3.x since there there is no mechanism to
disable them.
Reviewed-by: Eric Anholt <eric@anholt.net>
Iago Toral Quiroga [Thu, 6 Jun 2019 07:41:33 +0000 (09:41 +0200)]
v3d: add a helper to track variables that need point coordinates
Reviewed-by: Eric Anholt <eric@anholt.net>
Kenneth Graunke [Fri, 7 Jun 2019 05:17:06 +0000 (22:17 -0700)]
egl/x11: calloc dri2_surf so it's properly zeroed
Commit
2282ec0a refactored drawable creation across various platforms
into a new dri2_create_drawable helper function.
The GBM code in platform_drm.c code passed in dri2_surf->gbm_surf as the
loaderPrivate, while most other backends passed in dri2_surf directly.
To try and handle this, the patch checked if dri2_surf->gbm_surf was
non-NULL, and if so, presumed that the caller is the DRM platform and
we should use the dri2_surf->gbm_surf pointer.
This worked for most platforms, which calloc their dri2_surf structure,
zeroing the data. Unfortunately, platform_x11.c used malloc, leaving
most of the dri2_surf as garbage. In particular, dri2_surf->gbm_surf
was often non-NULL, causing dri2_create_drawable to try and use it,
passing a garbage pointer to the createNewDrawable hook, usually leading
to a SIGBUS or SIGSEGV when trying to dereference that bad pointer.
Since most callers calloc the data, make platform_x11.c follow suit.
Fixes crashes with i915_dri.so when running dEQP-GLES2.
Reviewed-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Mark Janes [Thu, 6 Jun 2019 05:48:41 +0000 (22:48 -0700)]
tests/graw: use C99 print conversion specifier for 32 bit builds
Fixes formatting errors for 32 bit compilations, eg:
error: format specifies type 'unsigned long' but the argument has
type 'uint64_t' (aka 'unsigned long long') [-Werror,-Wformat]
printf("result1 = %lu result2 = %lu\n", res1.u64, res2.u64);
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Alyssa Rosenzweig [Thu, 6 Jun 2019 15:15:23 +0000 (08:15 -0700)]
panfrost/midgard: Fix crash with unused SSA values
Crash introduced in "
b38dab101ca7e0896255dccbd85fd510c47d84d1" but not
adding a Fixes tag since it's our bug anyway.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Boris Brezillon [Thu, 6 Jun 2019 16:44:09 +0000 (18:44 +0200)]
panfrost: Report sRGB colorspace as not supported
The driver does not support sRGB yet, so let's report it as unsupported.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Erik Faye-Lund [Thu, 6 Jun 2019 09:19:08 +0000 (11:19 +0200)]
docs: do not use div for line-breaking
HTML has the <p>-tag for this purpose. It adds some margins, but that
just makes this read better, IMO.
Signed-off-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Erik Faye-Lund [Thu, 6 Jun 2019 08:11:31 +0000 (10:11 +0200)]
docs: fixup code-tag positioning
This reads better if we include the asterisk in the code-block, as it's
part of the function-reference, even though it's not technically
speaking code. But as the <code>-tag isn't purely for code, this should
be fine.
Signed-off-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Erik Faye-Lund [Thu, 6 Jun 2019 08:16:36 +0000 (10:16 +0200)]
docs: add missing code-tags
Looks like I missed a few cases when I recently added more code-tags
here. So let's add these cases as well.
Signed-off-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Erik Faye-Lund [Thu, 6 Jun 2019 09:01:54 +0000 (11:01 +0200)]
docs: add accidentally dropped "at"
When rewriting
20c56e18c21 after review, I accidentally dropped the "at"
here. Sorry for that, and let's fix it up!
Signed-off-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Fixes: 20c56e18c21 ("docs: use proper links instead of code-tags")
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Gurchetan Singh [Wed, 5 Jun 2019 16:51:07 +0000 (09:51 -0700)]
anv: allow NV12 <--> AHARDWAREBUFFER_FORMAT_Y8Cb8Cr8_420 inter-op
AHARDWAREBUFFER_FORMAT_Y8Cb8Cr8_420 is an implementation defined
flexible YUV format. Most of the times, it's NV12 or YV12.
On Intel, NV12 is preferred since it can be used by the display
engine.
This API adds a dependency between gralloc and buffer consumers,
unfortunately. Right now, the code seems to work for i915 gralloc,
but not cros_gralloc. Add a preprocessor flag to fix this.
TEST=android.graphics.cts.MediaVulkanGpuTest#testMediaImportAndRendering
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Connor Abbott [Wed, 5 Jun 2019 14:54:24 +0000 (16:54 +0200)]
ac/nir: Remove stale TODO
While we're here, copy the comment explaining this from radeonsi.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Connor Abbott [Wed, 5 Jun 2019 10:37:46 +0000 (12:37 +0200)]
radeonsi: Don't force dcc disable for loads
When
e9d935ed0e2 added force_dcc_off(), we forced it off for any
preloaded image descriptor which had stores associated with them, since
the same preloaded descriptors were used for loads and stores. However,
when the preloading was removed in
16be87c9042, the existing logic was
kept despite it not being necessary anymore. The comment above
force_dcc_off() only mentions stores, so only force DCC off for stores.
Cc: Nicolai Hähnle <nicolai.haehnle@amd.com>
Cc: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Gert Wollny [Sat, 11 May 2019 15:48:18 +0000 (17:48 +0200)]
mesa/main: Expose EXT_clip_control and related enums and the function
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Gert Wollny [Sat, 11 May 2019 15:44:17 +0000 (17:44 +0200)]
mapi/glapi/registry: Update gl.xml to latest upstream version
The old copy didn't include EXT_clip_control, so update it.
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Gert Wollny [Tue, 7 May 2019 17:50:46 +0000 (19:50 +0200)]
virgl: Enable CAP_CLIP_HALFZ if host supports it
On according hosts this enables the piglits as "pass":
arb_clip_control-*
v2: sync flag with host
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com> (v1)
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Charmaine Lee [Tue, 7 May 2019 21:07:50 +0000 (14:07 -0700)]
svga: Remove unnecessary check for the pre flush bit for setting vertex buffers
This fixes the missing rebind when the can_pre_flush bit
is not set and the vertex buffers are the same as what have been sent.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Neha Bhende <bhenden@vmware.com>
Signed-off-by: Charmaine Lee <charmainel@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Deepak Rawat [Wed, 9 May 2018 22:50:39 +0000 (15:50 -0700)]
winsys/svga/drm: Fix 32-bit RPCI send message
Depending on whether compiled with frame-pointer or not, the temporary
memory location used for the bp parameter in these macros are referenced
relative to the stack pointer or the frame pointer.
Hence we can never reference that parameter when we've modified either
the stack pointer or the frame pointer, because then the compiler would
generate an incorrect stack reference.
Fix this by pushing the temporary memory parameter on a known location on
the stack before modifying the stack- and frame pointers.
Also in case of failuire RPCI channel is not closed which lead to vmx
running out of channels.
Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Samuel Pitoiset [Thu, 30 May 2019 13:13:59 +0000 (15:13 +0200)]
radv: set the subpass before any initial subpass transitions
This might fix initial subpass transitions when multiview is used.
Noticed while implementing sample locations during layout transitions.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Nataraj Deshpande [Wed, 5 Jun 2019 19:32:01 +0000 (12:32 -0700)]
anv: Fix check for isl_fmt in assert
Checking isl_fmt returned value in assert seems appropriate
instead of format variable.
Fixes: f1654fa7e31 "anv/android: support creating images from external format"
Signed-off-by: Nataraj Deshpande <nataraj.deshpande@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Iago Toral Quiroga [Wed, 5 Jun 2019 06:53:10 +0000 (08:53 +0200)]
v3d: fix scheduling dependency tracking for ALU with small immediates
We were not accountint for small immediates in the B mux so the scheduler
was interpreting these are regular register file accesses, which could
lead to additional (incorrect) write-read dependencies.
Shader-db changes:
total instructions in shared programs:
9163664 ->
9137263 (-0.29%)
instructions in affected programs:
3931035 ->
3904634 (-0.67%)
helped: 12457
HURT: 2563
total max-temps in shared programs:
1325787 ->
1325597 (-0.01%)
max-temps in affected programs: 5746 -> 5556 (-3.31%)
helped: 186
HURT: 16
helped stats (abs) min: 1 max: 4 x̄: 1.12 x̃: 1
helped stats (rel) min: 1.45% max: 22.22% x̄: 4.42% x̃: 3.28%
HURT stats (abs) min: 1 max: 3 x̄: 1.12 x̃: 1
HURT stats (rel) min: 2.86% max: 10.00% x̄: 5.76% x̃: 5.88%
95% mean confidence interval for max-temps value: -1.04 -0.84
95% mean confidence interval for max-temps %-change: -4.16% -3.07%
Max-temps are helped.
Reviewed-by: Eric Anholt <eric@anholt.net>
Vasily Khoruzhick [Tue, 4 Jun 2019 15:56:38 +0000 (08:56 -0700)]
lima/ppir: add missing handling of min/max ops for vec4 add slot
Signed-off-by: Vasily Khoruzhick <anarsoul@gmail.com>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Vasily Khoruzhick [Sat, 1 Jun 2019 05:30:54 +0000 (22:30 -0700)]
lima/ppir: fix crash when program uses no registers at all
Program may need no regalloc at all, e.g. in case when program consists
of single discard op.
Signed-off-by: Vasily Khoruzhick <anarsoul@gmail.com>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Jason Ekstrand [Wed, 5 Jun 2019 22:30:47 +0000 (17:30 -0500)]
util/hash_table: Assert that keys are not reserved pointers
If we insert a NULL key, it will appear to succeed but will mess up
entry counting. Similar errors can occur if someone accidentally
inserts the deleted key. The later is highly unlikely but technically
possible so we should guard against it too.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Jason Ekstrand [Wed, 5 Jun 2019 21:56:20 +0000 (16:56 -0500)]
util/set: Assert that keys are not reserved pointers
If we insert a NULL key, it will appear to succeed but will mess up
entry counting. Similar errors can occur if someone accidentally
inserts the deleted key. The later is highly unlikely but technically
possible so we should guard against it too.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Jason Ekstrand [Wed, 5 Jun 2019 23:35:14 +0000 (18:35 -0500)]
glsl/loop_analysis: Don't search for NULL variables in the hash table
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Jason Ekstrand [Wed, 5 Jun 2019 21:54:40 +0000 (16:54 -0500)]
nir/propagate_invariant: Don't add NULL vars to the hash table
Fixes: 8410cf66d "nir/propagate_invariant: Skip unknown vars"
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Ian Romanick [Tue, 4 Jun 2019 19:16:55 +0000 (12:16 -0700)]
intel/compiler: Treat b32csel as potentially producing a Boolean result for resolve analysis
If the 2nd and 3rd source are both Boolean values, we can potentially
avoid a resolve by only resolving the result of the b32csel.
No changes on any Gen6+ Intel platform.
v2: Use ?: instead of cast from bool to unsigned. Suggested by Caio.
Iron Lake
total instructions in shared programs:
8142729 ->
8142677 (<.01%)
instructions in affected programs: 12890 -> 12838 (-0.40%)
helped: 26
HURT: 0
helped stats (abs) min: 2 max: 2 x̄: 2.00 x̃: 2
helped stats (rel) min: 0.25% max: 0.74% x̄: 0.45% x̃: 0.38%
95% mean confidence interval for instructions value: -2.00 -2.00
95% mean confidence interval for instructions %-change: -0.52% -0.39%
Instructions are helped.
total cycles in shared programs:
188549632 ->
188549394 (<.01%)
cycles in affected programs: 60754 -> 60516 (-0.39%)
helped: 25
HURT: 1
helped stats (abs) min: 2 max: 26 x̄: 9.92 x̃: 8
helped stats (rel) min: 0.07% max: 2.23% x̄: 0.59% x̃: 0.27%
HURT stats (abs) min: 10 max: 10 x̄: 10.00 x̃: 10
HURT stats (rel) min: 0.70% max: 0.70% x̄: 0.70% x̃: 0.70%
95% mean confidence interval for cycles value: -12.91 -5.40
95% mean confidence interval for cycles %-change: -0.84% -0.23%
Cycles are helped.
GM45
total instructions in shared programs:
5013119 ->
5013093 (<.01%)
instructions in affected programs: 6764 -> 6738 (-0.38%)
helped: 13
HURT: 0
helped stats (abs) min: 2 max: 2 x̄: 2.00 x̃: 2
helped stats (rel) min: 0.24% max: 0.68% x̄: 0.43% x̃: 0.36%
95% mean confidence interval for instructions value: -2.00 -2.00
95% mean confidence interval for instructions %-change: -0.52% -0.34%
Instructions are helped.
total cycles in shared programs:
128977804 ->
128977700 (<.01%)
cycles in affected programs: 37738 -> 37634 (-0.28%)
helped: 13
HURT: 0
helped stats (abs) min: 8 max: 8 x̄: 8.00 x̃: 8
helped stats (rel) min: 0.18% max: 0.46% x̄: 0.30% x̃: 0.26%
95% mean confidence interval for cycles value: -8.00 -8.00
95% mean confidence interval for cycles %-change: -0.36% -0.24%
Cycles are helped.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Tue, 21 May 2019 00:25:01 +0000 (17:25 -0700)]
intel/fs: Improve discard_if code generation
Previously we would blindly emit an sequence like:
mov(1) f0.1<1>UW g1.14<0,1,0>UW
...
cmp.l.f0(16) g7<1>F g5<8,8,1>F 0x41700000F /* 15F */
(+f0.1) cmp.z.f0.1(16) null<1>D g7<8,8,1>D 0D
The first move sets the flags based on the initial execution mask.
Later discard sequences contain a predicated compare that can only
remove more SIMD channels. Often times the only user of the result from
the first compare is the second compare. Instead, generate a sequence
like
mov(1) f0.1<1>UW g1.14<0,1,0>UW
...
cmp.l.f0(16) g7<1>F g5<8,8,1>F 0x41700000F /* 15F */
(+f0.1) cmp.ge.f0.1(8) null<1>F g5<8,8,1>F 0x41700000F /* 15F */
If the results stored in g7 and f0.0 are not used, the comparison will
be eliminated. This removes an instruction and potentially reduces
register pressure.
v2: Major re-write of the commit message (including fixing the assembly
code). Suggested by Matt.
All Gen8+ platforms had similar results. (Ice Lake shown)
total instructions in shared programs:
17224434 ->
17198659 (-0.15%)
instructions in affected programs:
2908125 ->
2882350 (-0.89%)
helped: 18891
HURT: 5
helped stats (abs) min: 1 max: 12 x̄: 1.38 x̃: 1
helped stats (rel) min: 0.03% max: 25.00% x̄: 1.76% x̃: 1.02%
HURT stats (abs) min: 9 max: 105 x̄: 51.40 x̃: 35
HURT stats (rel) min: 0.43% max: 4.92% x̄: 2.34% x̃: 1.56%
95% mean confidence interval for instructions value: -1.39 -1.34
95% mean confidence interval for instructions %-change: -1.79% -1.73%
Instructions are helped.
total cycles in shared programs:
361468458 ->
361170679 (-0.08%)
cycles in affected programs:
38470116 ->
38172337 (-0.77%)
helped: 16202
HURT: 1456
helped stats (abs) min: 1 max: 4473 x̄: 26.24 x̃: 18
helped stats (rel) min: <.01% max: 28.44% x̄: 2.90% x̃: 2.18%
HURT stats (abs) min: 1 max: 5982 x̄: 87.51 x̃: 28
HURT stats (rel) min: <.01% max: 51.29% x̄: 5.48% x̃: 1.64%
95% mean confidence interval for cycles value: -18.24 -15.49
95% mean confidence interval for cycles %-change: -2.26% -2.14%
Cycles are helped.
total spills in shared programs: 12147 -> 12176 (0.24%)
spills in affected programs: 175 -> 204 (16.57%)
helped: 8
HURT: 5
total fills in shared programs: 25262 -> 25292 (0.12%)
fills in affected programs: 269 -> 299 (11.15%)
helped: 8
HURT: 5
Haswell
total instructions in shared programs:
13530316 ->
13502647 (-0.20%)
instructions in affected programs:
2507824 ->
2480155 (-1.10%)
helped: 18859
HURT: 10
helped stats (abs) min: 1 max: 12 x̄: 1.48 x̃: 1
helped stats (rel) min: 0.03% max: 27.78% x̄: 2.38% x̃: 1.41%
HURT stats (abs) min: 5 max: 39 x̄: 25.70 x̃: 31
HURT stats (rel) min: 0.22% max: 1.66% x̄: 1.09% x̃: 1.31%
95% mean confidence interval for instructions value: -1.49 -1.44
95% mean confidence interval for instructions %-change: -2.42% -2.34%
Instructions are helped.
total cycles in shared programs:
377865412 ->
377639034 (-0.06%)
cycles in affected programs:
40169572 ->
39943194 (-0.56%)
helped: 15550
HURT: 1938
helped stats (abs) min: 1 max: 2482 x̄: 25.67 x̃: 18
helped stats (rel) min: <.01% max: 37.77% x̄: 3.00% x̃: 2.25%
HURT stats (abs) min: 1 max: 4862 x̄: 89.17 x̃: 35
HURT stats (rel) min: <.01% max: 67.67% x̄: 6.16% x̃: 2.75%
95% mean confidence interval for cycles value: -14.42 -11.47
95% mean confidence interval for cycles %-change: -2.05% -1.91%
Cycles are helped.
total spills in shared programs: 26769 -> 26814 (0.17%)
spills in affected programs: 826 -> 871 (5.45%)
helped: 9
HURT: 10
total fills in shared programs: 38383 -> 38425 (0.11%)
fills in affected programs: 834 -> 876 (5.04%)
helped: 9
HURT: 10
LOST: 5
GAINED: 10
Ivy Bridge
total instructions in shared programs:
12079250 ->
12044139 (-0.29%)
instructions in affected programs:
2409680 ->
2374569 (-1.46%)
helped: 16135
HURT: 0
helped stats (abs) min: 1 max: 23 x̄: 2.18 x̃: 2
helped stats (rel) min: 0.07% max: 37.50% x̄: 2.72% x̃: 1.68%
95% mean confidence interval for instructions value: -2.21 -2.14
95% mean confidence interval for instructions %-change: -2.76% -2.67%
Instructions are helped.
total cycles in shared programs:
180116747 ->
179900405 (-0.12%)
cycles in affected programs:
25439823 ->
25223481 (-0.85%)
helped: 13817
HURT: 1499
helped stats (abs) min: 1 max: 1886 x̄: 26.40 x̃: 18
helped stats (rel) min: <.01% max: 38.84% x̄: 2.57% x̃: 1.97%
HURT stats (abs) min: 1 max: 3684 x̄: 98.99 x̃: 52
HURT stats (rel) min: <.01% max: 97.01% x̄: 6.37% x̃: 3.42%
95% mean confidence interval for cycles value: -15.68 -12.57
95% mean confidence interval for cycles %-change: -1.77% -1.63%
Cycles are helped.
LOST: 8
GAINED: 10
Sandy Bridge
total instructions in shared programs:
10878990 ->
10863659 (-0.14%)
instructions in affected programs:
1806702 ->
1791371 (-0.85%)
helped: 13023
HURT: 0
helped stats (abs) min: 1 max: 5 x̄: 1.18 x̃: 1
helped stats (rel) min: 0.07% max: 13.79% x̄: 1.65% x̃: 1.10%
95% mean confidence interval for instructions value: -1.18 -1.17
95% mean confidence interval for instructions %-change: -1.68% -1.62%
Instructions are helped.
total cycles in shared programs:
154082878 ->
153862810 (-0.14%)
cycles in affected programs:
20199374 ->
19979306 (-1.09%)
helped: 12048
HURT: 510
helped stats (abs) min: 1 max: 323 x̄: 20.57 x̃: 18
helped stats (rel) min: 0.03% max: 17.78% x̄: 2.05% x̃: 1.52%
HURT stats (abs) min: 1 max: 448 x̄: 54.39 x̃: 16
HURT stats (rel) min: 0.02% max: 37.98% x̄: 4.13% x̃: 1.17%
95% mean confidence interval for cycles value: -17.97 -17.08
95% mean confidence interval for cycles %-change: -1.84% -1.75%
Cycles are helped.
LOST: 1
GAINED: 0
Iron Lake
total instructions in shared programs:
8155075 ->
8142729 (-0.15%)
instructions in affected programs: 949495 -> 937149 (-1.30%)
helped: 5810
HURT: 0
helped stats (abs) min: 1 max: 8 x̄: 2.12 x̃: 2
helped stats (rel) min: 0.10% max: 16.67% x̄: 2.53% x̃: 1.85%
95% mean confidence interval for instructions value: -2.14 -2.11
95% mean confidence interval for instructions %-change: -2.59% -2.48%
Instructions are helped.
total cycles in shared programs:
188584610 ->
188549632 (-0.02%)
cycles in affected programs:
17274446 ->
17239468 (-0.20%)
helped: 3881
HURT: 90
helped stats (abs) min: 2 max: 168 x̄: 9.08 x̃: 6
helped stats (rel) min: <.01% max: 23.53% x̄: 0.83% x̃: 0.30%
HURT stats (abs) min: 2 max: 10 x̄: 2.80 x̃: 2
HURT stats (rel) min: <.01% max: 0.60% x̄: 0.10% x̃: 0.07%
95% mean confidence interval for cycles value: -9.35 -8.27
95% mean confidence interval for cycles %-change: -0.85% -0.77%
Cycles are helped.
GM45
total instructions in shared programs:
5019308 ->
5013119 (-0.12%)
instructions in affected programs: 489028 -> 482839 (-1.27%)
helped: 2912
HURT: 0
helped stats (abs) min: 1 max: 8 x̄: 2.13 x̃: 2
helped stats (rel) min: 0.10% max: 16.67% x̄: 2.46% x̃: 1.81%
95% mean confidence interval for instructions value: -2.14 -2.11
95% mean confidence interval for instructions %-change: -2.54% -2.39%
Instructions are helped.
total cycles in shared programs:
129002592 ->
128977804 (-0.02%)
cycles in affected programs:
12669152 ->
12644364 (-0.20%)
helped: 2759
HURT: 37
helped stats (abs) min: 2 max: 168 x̄: 9.03 x̃: 4
helped stats (rel) min: <.01% max: 21.43% x̄: 0.75% x̃: 0.31%
HURT stats (abs) min: 2 max: 10 x̄: 3.62 x̃: 4
HURT stats (rel) min: <.01% max: 0.41% x̄: 0.10% x̃: 0.04%
95% mean confidence interval for cycles value: -9.53 -8.20
95% mean confidence interval for cycles %-change: -0.79% -0.70%
Cycles are helped.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Tue, 21 May 2019 19:09:42 +0000 (12:09 -0700)]
intel/fs: Add need_dest parameter to fs_visitor::nir_emit_alu
This is the same as the need_dest parameter to
prepare_alu_destination_and_sources. This allows us to not change the
register that is expected to hold an result if an instruction is
re-emitted. This is particularly a problem if the re-emitted
instruction is a partial write. A later patch will use this feature.
No shader-db changes on any Intel platform.
v2: Don't do the Boolean resolve when there is no destination. If the
ALU instruction didn't write a register, there's nothing to resolve.
This replaces an earlier patch "intel/fs: Allocate dummy destination
register when need_dest is false".
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Wed, 22 May 2019 19:32:03 +0000 (12:32 -0700)]
intel/fs: Allow cmod propagation across reads and writes of different flags
This also helps a later patch (intel/fs: Improve discard_if code
generation) on about 200 shaders.
v2: Document that other instruction sequences are also valid in
subtract_merge_with_compare_intervening_mismatch_flag_write. Suggested
by Caio.
All Intel platforms had similar results. (Ice Lake shown)
total instructions in shared programs:
17224438 ->
17224434 (<.01%)
instructions in affected programs: 296 -> 292 (-1.35%)
helped: 4
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 0.99% max: 1.92% x̄: 1.43% x̃: 1.40%
95% mean confidence interval for instructions value: -1.00 -1.00
95% mean confidence interval for instructions %-change: -2.04% -0.81%
Instructions are helped.
total cycles in shared programs:
361468455 ->
361468458 (<.01%)
cycles in affected programs: 2862 -> 2865 (0.10%)
helped: 2
HURT: 2
helped stats (abs) min: 2 max: 2 x̄: 2.00 x̃: 2
helped stats (rel) min: 0.24% max: 0.39% x̄: 0.31% x̃: 0.31%
HURT stats (abs) min: 3 max: 4 x̄: 3.50 x̃: 3
HURT stats (rel) min: 0.32% max: 0.70% x̄: 0.51% x̃: 0.51%
95% mean confidence interval for cycles value: -4.34 5.84
95% mean confidence interval for cycles %-change: -0.70% 0.90%
Inconclusive result (value mean confidence interval includes 0).
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Wed, 22 May 2019 17:18:06 +0000 (10:18 -0700)]
intel/fs: Fix flag_subreg handling in cmod propagation
There were two errors. First, the pass could propagate conditional
modifiers from an instruction that writes on flag register to an
instruction that writes a different flag register. For example,
cmp.nz.f0.0(16) null:F, vgrf6:F, vgrf5:F
cmp.nz.f0.1(16) null:F, vgrf6:F, vgrf5:F
could be come
cmp.nz.f0.0(16) null:F, vgrf6:F, vgrf5:F
Second, if an instruction writes f0.1 has it's condition propagated, the
modified instruction will incorrectly write flag f0.0. For example,
linterp(16) vgrf6:F, g2:F, attr0:F
cmp.z.f0.1(16) null:F, vgrf6:F, vgrf5:F
(-f0.1) discard_jump(16) (null):UD
could become
linterp.z.f0.0(16) vgrf6:F, g2:F, attr0:F
(-f0.1) discard_jump(16) (null):UD
None of these cases will occur currently. The only time we use f0.1 is
for generating discard intrinsics. In all those cases, we generate a
squence like:
cmp.nz.f0.0(16) vgrf7:F, vgrf6:F, vgrf5:F
(+f0.1) cmp.z(16) null:D, vgrf7:D, 0d
(-f0.1) discard_jump(16) (null):UD
Due to the mixed types and incompatible conditions, this sequence would
never see any cmod propagation. The next patch will change this.
No shader-db changes on any Intel platform.
v2: Fix typo in comment in test case subtract_delete_compare_other_flag.
Noticed by Caio.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Wed, 22 May 2019 18:06:19 +0000 (11:06 -0700)]
intel/fs: Add missing tests for cmod_propagate_not
Tests like this should have been added in
4467040cb65 ("i965/fs:
Propagate conditional modifiers from not instructions").
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Kenneth Graunke [Wed, 5 Jun 2019 06:19:22 +0000 (23:19 -0700)]
i965: Allow signed/unsigned integer conversions in miptree up/download
BLORP now handles this so there's no reason to fall back.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Wed, 5 Jun 2019 06:18:45 +0000 (23:18 -0700)]
intel/blorp: Handle SINT/UINT clamping on blits.
This patch makes blorp_blit handle SINT<->UINT blit value clamping.
After reading the source's integer data (which is expanded to 32-bit),
we either IMAX with 0 (for SINT -> UINT, to clamp negative numbers) or
UMIN with (1 << 31) - 1 (for UINT -> SINT, to clamp positive numbers
outside of the representable range).
Such blits are not allowed by the OpenGL or Vulkan APIs directly:
The Vulkan 1.1 spec for vkCmdBlitImage says:
"Integer formats can only be converted to other integer formats with
the same signedness."
The GL 4.5 spec for glBlitFramebuffer says:
"An INVALID_OPERATION error is generated if format conversions are
not supported, which occurs under any of the following conditions:
[...]
* The read buffer contains unsigned integer values and any draw
buffer does not contain unsigned integer values.
* The read buffer contains signed integer values and any draw buffer
does not contain signed integer values."
However, they are useful for other operations, such as texture upload
and download, which typically are implemented via blorp_blit(). i965
has code to fall back in this case (which the next commit will delete),
and Gallium expects blit() to handle this case for texture upload.
Fixes the following tests on iris:
- GTF-GL46.gtf32.GL3Tests.packed_pixels.packed_pixels
- GTF-GL46.gtf32.GL3Tests.packed_pixels.packed_pixels_pbo
- GTF-GL46.gtf32.GL3Tests.packed_pixels.packed_pixels_pixelstore
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Caio Marcelo de Oliveira Filho [Thu, 30 May 2019 23:55:19 +0000 (16:55 -0700)]
anv/pipeline: Move lowering of nir_var_mem_global later
This let deref optimizations apply to globals before lowering them.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Fri, 17 May 2019 05:41:13 +0000 (22:41 -0700)]
st/nir: Don't use GLSL IR's MOD_TO_FLOOR lowering when using NIR.
Both GLSL IR and NIR perform the same mod -> floor lowering for 32-bit
types. But nir_lower_double_ops is slightly more defensive against
lowered drcp precision loss, and handles mod(x, x) = 0 directly. This
works well...assuming nir_lower_double_ops actually gets an fmod op to
lower in the first place.
The previous patches enabled NIR-based lowering for the remaining
drivers, so we can stop using the GLSL IR lowering when using NIR.
Fixes KHR-GL45.gpu_shader_fp64.builtin.mod_dvec[234] on iris.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Kenneth Graunke [Mon, 3 Jun 2019 20:40:05 +0000 (13:40 -0700)]
radeonsi: Enable NIR's lower_fmod option.
Currently, st/mesa is always calling the GLSL IR lower_instructions()
pass with MOD_TO_FLOOR set, so mod operations will be lowered before
ever reaching NIR. This enables the same lowering at the NIR level,
which will let me shut off the GLSL IR path for NIR-based drivers.
The AMD NIR backend also has code to handle fmod, so we could
potentially skip this and still be fine. I don't have an opinion
on that.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Kenneth Graunke [Tue, 4 Jun 2019 06:06:49 +0000 (23:06 -0700)]
vc4: Enable NIR's lower_fmod option.
Currently, st/mesa is always calling the GLSL IR lower_instructions()
pass with MOD_TO_FLOOR set, so mod operations will be lowered before
ever reaching NIR. This enables the same lowering at the NIR level,
which will let me shut off the GLSL IR path for NIR-based drivers.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Eric Anholt <eric@anholt.net>
Kenneth Graunke [Mon, 3 Jun 2019 20:36:56 +0000 (13:36 -0700)]
v3d: Enable NIR's lower_fmod option.
Currently, st/mesa is always calling the GLSL IR lower_instructions()
pass with MOD_TO_FLOOR set, so mod operations will be lowered before
ever reaching NIR. This enables the same lowering at the NIR level,
which will let me shut off the GLSL IR path for NIR-based drivers.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Eric Anholt <eric@anholt.net>
Kenneth Graunke [Mon, 3 Jun 2019 20:18:55 +0000 (13:18 -0700)]
nir: Combine lower_fmod16/32 back into a single lower_fmod.
We originally had a single lower_fmod option. In commit
2ab2d2e5, Sam
split 32 and 64-bit lowering into separate flags, with the rationale
that some drivers might want different options there. This left 16-bit
unhandled, so Iago added a lower_fmod16 option in commit
ca31df6f.
Now that lower_fmod64 is gone (in favor of nir_lower_doubles and
nir_lower_dmod), we re-combine lower_fmod16 and lower_fmod32 into a
single lower_fmod flag again. I'm not aware of any hardware which
need lowering for one bitsize and not the other.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Kenneth Graunke [Mon, 3 Jun 2019 20:15:49 +0000 (13:15 -0700)]
nir: Drop lower_fmod64 option.
nir_lower_doubles offers a wide variety of fp64 lowering, including
lowering fmod@64. The version there also better handles imprecisions
due to lowered frcp@64. Let's consolidate on one version.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Kenneth Graunke [Mon, 3 Jun 2019 18:54:21 +0000 (11:54 -0700)]
panfrost: Switch to nir_lower_doubles instead of lower_fmod64.
I don't think panfrost actually does doubles yet, but it at least
claims to support PIPE_CAP_DOUBLES, so at least pretend to switch
to the new lowering.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Kenneth Graunke [Mon, 3 Jun 2019 18:43:38 +0000 (11:43 -0700)]
nouveau: Use nir_lower_doubles instead of lower_fmod64 on nvc0.
We currently have two duplicate mechanisms for lowering fmod@64.
One is a nir_opt_algebraic rule keyed off of options->lower_fmod64,
and the other is nir_lower_doubles, which offers a full gamut of
fp64 lowering. The latter works slightly better in some corner cases,
so I'm trying to eliminate lower_fmod64 and drop the redundancy.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Kenneth Graunke [Mon, 3 Jun 2019 18:41:37 +0000 (11:41 -0700)]
gallium: Drop lower_fmod64 from drivers that don't support doubles.
Neither freedreno nor nv50 expose PIPE_CAP_DOUBLES, so there's no
fmod64 to be lowered.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>