Midgard has the ability to calculate addresses as part of the load/store
pipeline. We'd like to make use of this to avoid doing this work on the
ALU pipes. To do so, when emitting globals/SSBOs/shareds, we walk the
tree looking for address arithmetic to try to parse out something the
hardware can work with, letting the original instructions be DCE'd
ideally. This analysis is done at the NIR level to properly account for
some messy details of vectorization which we'd rather not poke at the
backend level. (Originally I wrote this as a MIR pass but I'm fairly
sure it was wrong.)
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3978>
The swizzles are as-if they were 32-bit regardless of the bitness of the
operation, but the source sizes can and do change depending on the
flags. Account for this in the analysis.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3978>
Many load/store ops (used for globals, SSBOs, shared memory, etc) have
the ability to compute addresses directly. Mark off which ones behave
like this.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3978>
When mixing 32/64-bit, we need to align the 32-bit registers to get the
required alignment. This isn't quite enough yet, though, since user
swizzles could bypass and will need to be lowered to 32-bit moves
(outstanding todo).
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3978>
Shared memory is implemented almost identically to global memory from an
ISA perspective, so let's handle the new intrinsics. We include a code
path for constant offsets, which doesn't come up for globals.
Fixes dEQP-GLES31.functional.compute.basic.shared_var_single_invocation
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3775>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3775>
We route it as a sysval. Fixes dEQP-GLES31.functional.compute.basic.ssbo_unsized_arr_single_invocation
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3775>
We need to lower SSBOs to globals regardless. Rather than do this in our
backend like we do now, use the common NIR pass, which will support
bounds checking.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3775>
Just use a dummy name instead.. we can't know a priori what type an
unknown op will consume, but we don't want to dereference a null
pointer.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Fixes: 24360966ab ("panfrost/midgard: Prettify embedded constant
prints")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3835>
Probably harmless but the w component doesn't appear valid so let's
match the blob... one less bit to be nervous about.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3835>
We're so close, again marking off a few edge cases is enough to allow us
to omit this data entirely. Woot!
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3835>
As long as we can disambiguate a few edge cases, we can imply next tags
entirely which cleans up the disassembly a fair bit (though not as much
as implying tags entirely would -- we'll get there!)
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3835>
We unify disparate metadata about tags into a single structure to ensure
information is not left out.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3835>
This comes up as a `return;` instruction in a compute shader. We need to
use the special tag 1 to signify "break". Fixes numerous
INSTR_INVALID_ENC faults in dEQP-GLES31.functional.compute.basic.*
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3835>
Barriers execute on the texture pipeline on Midgard, so let's
tentatively handle barrier() as conservatively as possible (forcing
memory barriers of both buffers and shared memory). Implementation isn't
quite there yet -- it doesn't look at interactions of adjacent barriers
like it's supposed to -- but the core is there.
Fixes dEQP-GLES31.functional.compute.basic.ssbo_local_barrier_single_invocation
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3835>
This patch fix these build errors with GCC 10.
/usr/bin/ld: src/gallium/drivers/panfrost/libpanfrost.a(pan_resource.c.o):src/panfrost/midgard/midgard_compile.h:52: multiple definition of `pan_sysval'; src/gallium/drivers/panfrost/libpanfrost.a(pan_screen.c.o):src/panfrost/midgard/midgard_compile.h:52: first defined here
/usr/bin/ld: src/gallium/drivers/panfrost/libpanfrost.a(pan_resource.c.o):src/panfrost/midgard/midgard_compile.h:68: multiple definition of `pan_special_attributes'; src/gallium/drivers/panfrost/libpanfrost.a(pan_screen.c.o):src/panfrost/midgard/midgard_compile.h:68: first defined here
Fixes: 7e8de5a707 ("panfrost: Implement system values")
Fixes: 306800d747 ("pan/midgard: Lower gl_VertexID/gl_InstanceID to attributes")
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3752>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3752>
ZS fragment stores are done like color fragment stores, except it's
using a different RT id (0xFF), the depth and stencil values are stored
in r1.x and r1.y.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
[Fix the scheduling part]
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3697>
Midgard can't write depth and stencil separately. It has to happen in
a single store operation containing both. Let's add a panfrost specific
intrinsic and turn all depth/stencil stores into a packed depth+stencil
one.
Note that this intrinsic is not yet handled in emit_intrinsic(), but
we'll address that later.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3697>
Allocate those instructions with ralloc() instead of using mem_dup.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3676>
There's a writeout bool storing the result of this test. Use it instead
of duplicating the test.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3676>
Let's lower bitfield extract to shifts until we figure out if it can be
natively supported.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3676>
nir_intrinsic_base() is assigned nir_variable.data.driver_location,
which is assigned a unique ID based on the variable position in the
shader variable list. There's no guarantee that this position will
match the RT id we want to pass to emit_fragment_store().
Add a search_var() helper to retrieve a nir_variable based on its driver
location, so we can pass the right RT value to emit_fragment_store().
We also make sure the shader output is color, since emit_fragment_store()
is not ready for depth/stencil stores yet.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3676>
We are about to add a special ZS render target, let's add a enum so we
can easily know which render target we're dealing with.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3676>
For constant packing, this is interesting to break down further.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3653>
To avoid hitting the assert in the default case, add a nop for this
intrinsic.
dEQP-GLES3.functional.transform_feedback.random.interleaved.lines.3
Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3625>
Until now, embedded constants were printed as all 32 bits integer or
floats, but the compiler can pack constant from different types if
severa instructions with different reg_mode and native type refer to
the constant register. Let's implement something smarter so users don't
have to do a manual conversion when looking at a trace.
Note that 8-bit constants are not decoded yet, as we're not sure how
the writemask is encoded in that case.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3536>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3536>
This way we can convert an 8-bit writemask (Midgard specific
representation) into the more common 1-bit/component representation.
8-bit mode is not supported yet, as we're not sure how the writemask is
encoded for this mode.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3536>
