The TCS inputs and outputs must always fit into the LDS,
which implies that their addresses also always fit 24 bits.
On AMD GPUs, 24-bit multiplication is much faster than 32-bit
multiplication, so we can take the opportunity to use that
for TCS I/O instead.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4536>
Previously, it was just unreachable, which means it will generate
invalid shaders when it encounters a situation when it can't allocate
registers for eg. a large load.
This commit makes it slightly easier to notice such problems without
triggering a GPU hang.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4536>
Fixes random dEQP-VK.transform_feedback.fuzz.* crashes.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: 2dc550202e
('aco: copy-propagate p_create_vector copies of vectors')
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4730>
Instead of copying the operands of the other p_create_vector and labelling
the definition with label_vec, copy the operands and label it with
label_temp so that it can be copy-propagated.
This was found while removing a redundant copy in load_input_from_temps()
which removed duplicate p_create_vector instructions.
shader-db (Navi):
Totals from 139 (0.11% of 127638) affected shaders:
VGPRs: 8472 -> 7948 (-6.19%)
CodeSize: 514592 -> 512368 (-0.43%)
MaxWaves: 1089 -> 1195 (+9.73%)
Instrs: 100214 -> 99658 (-0.55%)
Cycles: 400856 -> 398632 (-0.55%)
VMEM: 15545 -> 15338 (-1.33%)
Copies: 5140 -> 4584 (-10.82%)
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4667>
For copies like v[7:8] = v[8:9], what currently happens is:
- do_copy() will skip the second dword
- the uses of the second dword will be reduced to 0
- the copy operation will be removed from the map
and v8 will never be set to v9.
So just decrease the uses of other operations after splitting or removing
the current operation, so: "v8 = v9" will be split off, it's uses reduced
and then the new copy will be done in the next iteration.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4686>
This simplifies code and helps some shaders
Totals from affected shaders:
Code Size: 51227172 -> 51202216 (-0.05 %) bytes
Max Waves: 19955 -> 19948 (-0.04 %)
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4573>
This simplifies definition handling and
helps a few shaders
Totals from affected shaders:
Code Size: 659540 -> 659376 (-0.02 %) bytes
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4573>
The optimizer isn't yet updated to handle this, since lower_to_hw_instr
will be the only user for now.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4469>
Is simpler and helps a couple of shaders.
Totals from affected shaders: (Vega)
Code Size: 16341296 -> 16335460 (-0.04 %) bytes
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4642>
It's like the layer, it has to be exported via the pos and also
as a varying if the fragment shader reads it.
Fixes dEQP-VK.draw.shader_viewport_index.fragment_shader_*
Cc: <mesa-stable@lists.freedesktop.org>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4564>
The ISA doc is inconsistent whether this instruction writes SCC. It does.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4552>
v_frexp_exp_i16_f16 returns the two's complement for negative
exponents. For example, with 0.333252 it returns 0.666504 for
the mantissa and 65535 for the exponent (-1 in decimal).
RADV/LLVM and AMDVLK do a v_bfe_i32 and AMDGPU-PRO uses SDWA with
the sign extension bit set. The latter is probably what we want to
do in long term but for now RA doesn't support changing non-SDWA
instructions to SDWA if useful/needed.
Fixes dEQP-VK.glsl.builtin.precision_fp16_storage16b.frexp.compute.*.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4546>
These's still improvements needed for sub-dword definitions, but that's
not as simple.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4507>
Because 16-bit constants are represented with the s1 RegClass, we
have to extract the low half.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4509>
