For multi-pass rendering, it is common to keep the same depth buffer
from previous pass, to discard geometry that would be hidden by later
draws. In the later passes with depth-test enabled, but depth-write
disabled, there is no reason to do gmem2mem resolve.
TODO probably do something similar for stencil.. although stencil
buffer isn't used as commonly these days
Signed-off-by: Rob Clark <robdclark@gmail.com>
After trying multiple times to merge if-statements with phis
between them I've come to the conclusion that it cannot be done
without regressions. The problem is for some shaders we end up
with a whole bunch of phis for the merged ifs resulting in
increased register pressure.
So this patch just merges ifs that have no phis between them.
This seems to be consistent with what LLVM does so for radeonsi
we only see a change (although its a large change) in a single
shader.
Shader-db results i965 (SKL):
total instructions in shared programs: 13098176 -> 13098152 (<.01%)
instructions in affected programs: 1326 -> 1302 (-1.81%)
helped: 4
HURT: 0
total cycles in shared programs: 332032989 -> 332037583 (<.01%)
cycles in affected programs: 60665 -> 65259 (7.57%)
helped: 0
HURT: 4
The cycles estimates reported by shader-db for i965 seem inaccurate
as the only difference in the final code is the removal of the
redundent condition evaluations and jumps.
Also the biggest code reduction (~7%) for radeonsi was in a tomb
raider tressfx shader but for some reason this does not get merged
for i965.
Shader-db results radeonsi (VEGA):
Totals from affected shaders:
SGPRS: 232 -> 232 (0.00 %)
VGPRS: 164 -> 164 (0.00 %)
Spilled SGPRs: 59 -> 59 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 0 -> 0 (0.00 %) dwords per thread
Code Size: 14584 -> 13520 (-7.30 %) bytes
LDS: 0 -> 0 (0.00 %) blocks
Max Waves: 13 -> 13 (0.00 %)
Wait states: 0 -> 0 (0.00 %)
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Before, I had per-stage entryoints with some helpers shared between them.
As I extended for compute shaders and shader-db, it turned out that the
other common code in the middle wanted to be shared too.
Loops will be trickier, since we need some analysis to figure out if the
breaks/continues inside are uniform. Until we get that in NIR, this gets
us some quick wins.
total instructions in shared programs: 6192844 -> 6174162 (-0.30%)
instructions in affected programs: 487781 -> 469099 (-3.83%)
I wanted to reuse the comparison stuff for nir_ifs, but for that I just
want the flags and no destination value. Splitting the conditions from
the destinations ended up cleaning the existing code up, anyway.
We'll still fail at draw time, but this avoids a regression in shader-db
execution once I enable TLB writes in precompiles.
Fixes: b38e4d313f ("v3d: Create a state uploader for packing our shaders together.")
Makes debugging easier when we care about the deref chain and not the
deref instruction itself. To make it take a const pointer, constify
some of the static functions in nir_print.c.
Reviewed-by: Eric Anholt <eric@anholt.net>
Nouveau requires rtti. Often LLVM is configured without rtti, and code
with and without cannot be linked safely. Lets just error out if nouveau
is requested and llvm is built without rtti.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109202
Fixes: c5a97d658e
("meson: fix builds against LLVM built without rtti")
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
The 16-bit polynomial execution doesn't meet Khronos precision requirements.
Also, the half-float denorm range starts at 2^(-14) and with asin taking input
values in the range [0, 1], polynomial approximations can lead to flushing
relatively easy.
An alternative is to use the atan2 formula to compute asin, which is the
reference taken by Khronos to determine precision requirements, but that
ends up generating too many additional instructions when compared to the
polynomial approximation. Specifically, for the Intel case, doing this
adds +41 instructions to the program for each asin/acos call, which looks
like an undesirable trade off.
So for now we take the easy way out and fallback to using the 32-bit
polynomial approximation, which is better (faster) than the 16-bit atan2
implementation and gives us better precision that matches Khronos
requirements.
v2:
- Fallback to 32-bit using recursion (Jason).
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
v2:
- use nir_fadd_imm and nir_fmul_imm helpers (Jason)
v3:
- since we need to define one for fsub use it for fdiv too (Jason)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
v2:
- fix huge_val for 16-bit, it was mean't to be 2^14 not 10^14.
v3:
- rebase on top of new bool sized opcodes
- use nir_b2f helper
- use nir_fmul_imm helper
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
v2:
- use nir_fadd_imm and nir_fmul_imm helpers (Jason)
- rebased on top of new sized boolean opcodes
- use nir_b2f helper
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
v2:
- use nir_fmul_imm and nir_fadd_imm helpers (Jason)
v3:
- missed one case where we need to replace nir_imm_float
with nir_imm_floatN_t (Jason)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This just cleans things up a little and make things more safe for
derefs.
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
Reviewed-by: Eric Anholt <eric@anholt.net>
This will be reused by the following patch.
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
The following patches will add support for an additional
optimisation so this function will no longer just optimise varying
constants.
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
This will help the new opt introduced in the following patches
allowing us to remove extra duplicate varyings.
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
The following patch will use this with the radeonsi NIR backend
but I've added it to ac so we can use it with RADV in future.
This is a NIR implementation of the tgsi function
tgsi_scan_tess_ctrl().
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
The previous code used a do while loop and continues after walking
a nested loop/if-statement. This means we end up evaluating the
last instruction from the nested block against the while condition
and potentially exit early if it matches the exit condition of the
outer block.
Fixes: 386d165d8d ("tgsi/scan: add a new pass that analyzes tess factor writes")
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
This just happened not to crash/assert because all loops have at
least 1 if-statement and due to a second bug we end up matching
the same ENDIF to exit both the iteration over the if-statment
and the loop.
The second bug is fixed in the following patch.
Fixes: 386d165d8d ("tgsi/scan: add a new pass that analyzes tess factor writes")
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
There's no way to tell the 3D engine about swizzling on such textures.
While rendering to NPOT ones may be possible, there's no great way to
expose that in gallium, nor would there be any practical benefit.
Fixes the non-compressed-format "copyteximage 3D" failures. Something
odd going on with the compressed formats.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
This caused random failures for two conditional rendering tests:
dEQP-VK.conditional_rendering.draw_clear.draw.update_with_rendering_discard
dEQP-VK.conditional_rendering.draw_clear.draw.update_with_rendering_no_discard
These wrote the predicate with the vertex shader, did a barrier and then
started the conditional rendering. However the cache flushes for the barrier
only happen on first draw, so after the predicate has been read.
Fixes: e45ba51ea4 "radv: add support for VK_EXT_conditional_rendering"
Reviewed-by: Dave Airlie <airlied@redhat.com>
Without this, I get the following error when building the tests with
autotools on i686:
---8<---
src/intel/common/gen_clflush.h: In function ‘gen_clflush_range’:
src/intel/common/gen_clflush.h:37:7: warning: implicit declaration of function ‘__builtin_ia32_clflush’; did you mean ‘__builtin_ia32_pause’? [-Wimplicit-function-declaration]
__builtin_ia32_clflush(p);
^~~~~~~~~~~~~~~~~~~~~~
__builtin_ia32_pause
src/intel/common/gen_clflush.h: In function ‘gen_flush_range’:
src/intel/common/gen_clflush.h:45:4: warning: implicit declaration of function ‘__builtin_ia32_mfence’; did you mean ‘__builtin_ia32_fnclex’? [-Wimplicit-function-declaration]
__builtin_ia32_mfence();
^~~~~~~~~~~~~~~~~~~~~
__builtin_ia32_fnclex
---8<---
The erros are generated for each of these files:
- mesa/src/intel/vulkan/tests/state_pool_no_free.c
- mesa/src/intel/vulkan/tests/state_pool.c
- mesa/src/intel/vulkan/tests/block_pool_no_free.c
- mesa/src/intel/vulkan/tests/state_pool_free_list_only.c
This is obviously because gen_clflush.h contains code that uses
intrinsics that are only available with SSE3. Since the driver already
uses SSE3, it seems reasonable to add this to the tests as well.
Signed-off-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Acked-by: Eric Engeström <eric@engestrom.ch>
Without this, I get the following error when building the tests using
meson on i686:
---8<---
In file included from ../../../mesa/src/intel/vulkan/anv_private.h:46,
from ../../../mesa/src/intel/vulkan/tests/state_pool_no_free.c:26:
../../../mesa/src/intel/common/gen_clflush.h: In function ‘gen_clflush_range’:
../../../mesa/src/intel/common/gen_clflush.h:37:7: error: implicit declaration of function ‘__builtin_ia32_clflush’; did you mean ‘__builtin_ia32_pause’? [-Werror=implicit-function-declaration]
__builtin_ia32_clflush(p);
^~~~~~~~~~~~~~~~~~~~~~
__builtin_ia32_pause
../../../mesa/src/intel/common/gen_clflush.h: In function ‘gen_flush_range’:
../../../mesa/src/intel/common/gen_clflush.h:45:4: error: implicit declaration of function ‘__builtin_ia32_mfence’; did you mean ‘__builtin_ia32_fnclex’? [-Werror=implicit-function-declaration]
__builtin_ia32_mfence();
^~~~~~~~~~~~~~~~~~~~~
__builtin_ia32_fnclex
---8<---
The errors are generated for each of these files:
- mesa/src/intel/vulkan/tests/state_pool_no_free.c
- mesa/src/intel/vulkan/tests/state_pool.c
- mesa/src/intel/vulkan/tests/block_pool_no_free.c
- mesa/src/intel/vulkan/tests/state_pool_free_list_only.c
This is obviously because gen_clflush.h contains code that uses
intrinsics that are only available with SSE3. Since the driver already
uses SSE3, it seems reasonable to add this to the tests as well.
Signed-off-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Eric Engeström <eric@engestrom.ch>
s3tc layouts are a bit finicky - they're packed, but not swizzled.
Adjust logic to allow for that case:
- Don't set a uniform pitch for POT-sized compressed textures
- Adjust define_rect API to be less confused about block sizes
- Only mark a texture as linear if it has a uniform pitch set
This has been tested to fix xonotic (as well as the s3tc-* piglits)
on nv3x and keeps it working on nv4x.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
This doesn't matter since all compressed formats supported by this
hardware use square blocks, but best to use the correct helper.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>