st_glsl_to_tgsi only calls lower_instructions once (instead of in a
loop), so the ir_binop_carry generated would not get lowered. Fixes
assertion failure
state_tracker/st_glsl_to_tgsi.cpp:2265: void glsl_to_tgsi_visitor::visit_expression(ir_expression*, st_src_reg*): Assertion `!"Invalid ir opcode in glsl_to_tgsi_visitor::visit()"' failed.
on softpipe in 16 piglit tests:
mesa_shader_integer_functions/execution/built-in-functions/fs-imulExtended-nonuniform.shader_test
mesa_shader_integer_functions/execution/built-in-functions/fs-imulExtended-only-msb-nonuniform.shader_test
mesa_shader_integer_functions/execution/built-in-functions/fs-imulExtended-only-msb.shader_test
mesa_shader_integer_functions/execution/built-in-functions/fs-imulExtended.shader_test
mesa_shader_integer_functions/execution/built-in-functions/fs-umulExtended-nonuniform.shader_test
mesa_shader_integer_functions/execution/built-in-functions/fs-umulExtended-only-msb-nonuniform.shader_test
mesa_shader_integer_functions/execution/built-in-functions/fs-umulExtended-only-msb.shader_test
mesa_shader_integer_functions/execution/built-in-functions/fs-umulExtended.shader_test
mesa_shader_integer_functions/execution/built-in-functions/vs-imulExtended-nonuniform.shader_test
mesa_shader_integer_functions/execution/built-in-functions/vs-imulExtended-only-msb-nonuniform.shader_test
mesa_shader_integer_functions/execution/built-in-functions/vs-imulExtended-only-msb.shader_test
mesa_shader_integer_functions/execution/built-in-functions/vs-imulExtended.shader_test
mesa_shader_integer_functions/execution/built-in-functions/vs-umulExtended-nonuniform.shader_test
mesa_shader_integer_functions/execution/built-in-functions/vs-umulExtended-only-msb-nonuniform.shader_test
mesa_shader_integer_functions/execution/built-in-functions/vs-umulExtended-only-msb.shader_test
mesa_shader_integer_functions/execution/built-in-functions/vs-umulExtended.shader_test
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
This reverts commit fc03ecfeaf.
Chad had already pushed the same change between me posting the patch and Jason
pushing it: 44bcf1ffcc (".gitignore: Ignore src/compiler/spirv2nir")
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Previously, we were saving off the last nir_block in a vtn_block before
moving on so that we could find the nir_block again when it came time to
handle phi sources. Unfortunately, NIR's control flow modification code is
inconsistent when it comes to how it splits blocks so the block pointer we
saved off may point to a block somewhere else in the shader by the time we
get around to handling phi sources. In order to get around this, we insert
a nop instruction and use that as the logical end of our block. Since the
control flow manipulation code respects instructions, the nop will keeps
its place like any other instruction and we can easily find the end of our
block when we need it.
This fixes a bug triggered by a couple of vkQuake shaders.
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97233
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Tested-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This intrinsic has no destination, no sources, no variables, and can be
eliminated. In other words, it does nothing and will always get deleted by
dead code elimination. However, it does provide a quick-and-easy way to
temporarily tag a particular location in a NIR shader.
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
While the current CFG code is valid in the case where a switch break also
happens to be a loop continue, it's a bit suboptimal. Since hardware is
capable of handling the continue as a direct jump, it's better to use a
continue instruction when we can than to bother with all of the nasty
switch break lowering.
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
It is possible that the break block of a switch is actually the continue of
the loop containing the switch. In this case, we need to identify the
break block as a continue and break out of current level of CFG handling.
If we don't, the continue portion of the loop will get handled twice, once
by following after the break and a second time by the loop handling code
handling it explicitly.
This fixes 6 of the new Vulkan CTS tests:
- dEQP-VK.spirv_assembly.instruction.graphics.opphi.out_of_order*
- dEQP-VK.spirv_assembly.instruction.graphics.selection_block_order.out_of_order*
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
I found this in a shader that was doing an alpha test when alpha is fixed
at 1.0.
v2: Rebase on master (now the const value is "u32" not "u").
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> (v1)
This code provides for an on-disk cache of objects. Objects are stored
and retrieved via names that are arbitrary 20-byte sequences,
(intended to be SHA-1 hashes of something identifying for the
content). The directory used for the cache can be specified by means
of environment variables in the following priority order:
$MESA_GLSL_CACHE_DIR
$XDG_CACHE_HOME/mesa
<user-home-directory>/.cache/mesa
By default the cache will be limited to a maximum size of 1GB. The
environment variable:
$MESA_GLSL_CACHE_MAX_SIZE
can be set (at the time of GL context creation) to choose some other
size. This variable is a number that can optionally be followed by
'K', 'M', or 'G' to select a size in kilobytes, megabytes, or
gigabytes. By default, an unadorned value will be interpreted as
gigabytes.
The cache will be entirely disabled at runtime if the variable
MESA_GLSL_CACHE_DISABLE is set at the time of GL context creation.
Many thanks to Kristian Høgsberg <krh@bitplanet.net> for the initial
implementation of code that led to this patch. In particular, the idea
of using an mmapped file, (indexed by a portion of the SHA-1), for the
efficent implementation of cache_has_key was entirely his
idea. Kristian also provided some very helpful advice in discussions
regarding various race conditions to be avoided in this code.
Signed-off-by: Timothy Arceri <timothy.arceri@collabora.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
As part of the shader-cache work an upcoming change will add new
references to _mesa_add_parameter and _mesa_new_parameter_list from
the glsl code. To prepare for that, and to allow the standalone
glsl_compiler to still link, here we add mesa/program/prog_parameter.c
to the libglsl_util sources.
Then, in order to get *that* to work, we also add to stubs to
standalone_scaffolding:
_mesa_program_state_flags
_mesa_program_state_string
These functions aren't actually used by the two functions in
prog_parameter.c that we are actually calling. They are used in other
functions in the same file. So we don't care what the implementation
of these stubs is, (they won't be called by glsl_compiler). We just
need the stubs present so that it can link.
Signed-off-by: Timothy Arceri <timothy.arceri@collabora.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
This reverts commit f5a6aab403.
This broke some tests. It seems gl_transform_feedback_info gets memset
to 0 so we were losing the values in BufferStride before we used them.
Now that we generate built-in functions inline, there's no need to link
against the built-in shader, and no built-in prototypes to consider.
This lets us delete a bunch of code.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by; Ian Romanick <ian.d.romanick@intel.com>
In the past, we imported the prototypes of built-in functions, generated
calls to those, and waited until link time to resolve the calls and
import the actual code for the built-in functions.
This severely limited our compile-time optimization opportunities: even
trivial functions like dot() were represented as function calls. We
also had no way of reasoning about those calls; they could have been
1,000 line functions with side-effects for all we knew.
Practically all built-in functions are trivial translations to
ir_expression opcodes, so it makes sense to just generate those inline.
Since we eventually inline all functions anyway, we may as well just do
it for all built-in functions.
There's only one snag: built-in functions that refer to built-in global
variables need those remapped to the variables in the shader being
compiled, rather than the ones in the built-in shader. Currently,
ftransform() is the only function matching those criteria, so it seemed
easier to just make it a special case.
On Skylake:
total instructions in shared programs: 12023491 -> 12024010 (0.00%)
instructions in affected programs: 77595 -> 78114 (0.67%)
helped: 97
HURT: 309
total cycles in shared programs: 137239044 -> 137295498 (0.04%)
cycles in affected programs: 16714026 -> 16770480 (0.34%)
helped: 4663
HURT: 4923
while these statistics are in the wrong direction, the number of
hurt programs is small (309 / 41282 = 0.75%), and I don't think
anything can be done about it. A change like this significantly
alters the order in which optimizations are performed.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by; Ian Romanick <ian.d.romanick@intel.com>
We want to check prior to optimization - otherwise we might fail to
detect cases where barrier() is in control flow which is always taken
(and therefore gets optimized away).
We don't currently loop unroll if there are function calls inside;
otherwise we might have a problem detecting barrier() in loops that
get unrolled as well.
Tapani's switch handling code adds a loop around switch statements, so
even with the mess of if ladders, we'll properly reject it.
Enforcing these rules at compile time makes more sense more sense than
link time. Doing it at ast-to-hir time (rather than as an IR pass)
allows us to emit an error message with proper line numbers.
(Otherwise, I would have preferred the IR pass...)
Fixes spec/arb_tessellation_shader/compiler/barrier-switch-always.tesc.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by; Ian Romanick <ian.d.romanick@intel.com>
It makes more sense to have this here where we store the other values
from xfb qualifiers. The struct it was previously part of is now only
used to store values that come from the api.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
The expectation is that drivers will set this based on
OES_geometry_shader and ARB_viewport_array support. This is a separate
enable on the same reasoning as for OES_texture_cube_map_array.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Anuj Phogat <anuj.phogat@gmail.com>
OpAtomicLoad/Store should have pointer to images just like the rest of the
atomic operators. These couple of lines were poorly copied from the
ssbo/shared_vars cases (the only ones currently tests by the CTS).
Fixes 2afb950161 ("spirv/nir: Add support for OpAtomicLoad/Store")
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
VC4 was running into a major performance regression from enabling control
flow in the glmark2 conditionals test, because of short if statements
containing an ffract.
This pass seems like it was was trying to ensure that we only flattened
IFs that should be entirely a win by guaranteeing that there would be
fewer bcsels than there were MOVs otherwise. However, if the number of
ALU ops is small, we can avoid the overhead of branching (which itself
costs cycles) and still get a win, even if it means moving real
instructions out of the THEN/ELSE blocks.
For now, just turn on aggressive flattening on vc4. i965 will need some
tuning to avoid regressions. It does looks like this may be useful to
replace freedreno code.
Improves glmark2 -b conditionals:fragment-steps=5:vertex-steps=0 from 47
fps to 95 fps on vc4.
vc4 shader-db:
total instructions in shared programs: 101282 -> 99543 (-1.72%)
instructions in affected programs: 17365 -> 15626 (-10.01%)
total uniforms in shared programs: 31295 -> 31172 (-0.39%)
uniforms in affected programs: 3580 -> 3457 (-3.44%)
total estimated cycles in shared programs: 225182 -> 223746 (-0.64%)
estimated cycles in affected programs: 26085 -> 24649 (-5.51%)
v2: Update shader-db output.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com> (v1)
We already support all of the decorations that require this capability.
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Dave Airlie <airlied@redhat.com>
This was something that I wrote in the early days of the spirv_to_nir code
but deleted once we had a real driver. However, in the absence of a
shader_runner equivalent, it's extremely useful for debugging the
spirv_to_nir code so let's bring it back.
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
This extension is a combination of AMD_vertex_shader_viewport_index and
AMD_vertex_shader_layer, making it rather trivial to implement.
For gallium I *think* this needs a new cap because of the addition of
support in tessellation evaluation shaders, and since I don't have any
hardware to test it on, I've left that for someone else to wire up.
Signed-off-by: Dylan Baker <dylanx.c.baker@intel.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This fixes 8 fs-interpolateat* piglit crashes on radeonsi, because it can't
handle non-input operands in interpolateAt*.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
This adds support for the input attachments subpass type
to the SPIRV->NIR pass.
v1.1: drop handling from vtn_handle_texture
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
SPIR-V/Vulkan have a special image type for input attachments
called the subpass type. It has different characteristics than
other images types.
The main one being it can only be an input image to fragment
shaders and loads from it are relative to the frag coord.
This adds support for it to the GLSL types. Unfortunately
we've run out of space in the sampler dim in types, so we
need to use another bit.
v2: Fixup subpass input name (Jason)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
