It was by pure luck that all sources (and the result) of nir_dpas_intel
had the same number of components. It is possible to support matrix
sizes where the accumlator matrix and the result matrix are larger
(e.g., 16x8 * 8x16 = 16x16).
This breaks all of the assumptions of NIR's infrastructure for code
generating intrinsics. Fix the by making the accumulator matrix be the
first source. The accumulator and the result will always have the same
dimensions (due to rules of matrix multiplication) and the same type
(due to restructions of the cooperative matrix extension). This forces
them to have the same number of components.
This doesn't fix all the potential problems. NIR expects that all
0-sized sources will have the same number of components. This just
ensures that the result has the correct number of components.
Fixes: 6b14da33ad ("intel/fs: nir: Add nir_intrinsic_dpas_intel")
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28404>
Was previously passing 1, 1, 0 as the regioning. This generated
incorrect disassembly because the encoding for a width of 1 is 0. Use
the enums to ensure the correct values are used.
Fixes: 1c92dad5cb ("intel/disasm: Disassembly support for DPAS")
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28404>
If the destination was the accumulator but is no longer, having the flag
set is not correct. On Xe2 this also causes a validation error.
v2: Reword the comment to be more clear. Suggested by Jordan.
Fixes: efa4e4bc5f ("intel/fs: Introduce regioning lowering pass.")
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28404>
The actual TCS epilog selection code is kept unchanged for now,
we'll delete it when RadeonSI also gets rid of TCS epilogs.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28408>
TCS epilogs are not needed anymore because the TCS can implement
dynamic states by itself now.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28408>
This allows the TCS to read the primitive mode and whether
TES reads the tess factors, from an SGPR arg, which lets it
decide how to store them at runtime.
For linked shaders, the conditions will be constant and
NIR optimizations can delete the dead CF.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28408>
For linked shaders, the information is available as constant,
while for unlinked shaders, the info is in a SGPR arg.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28408>
Will be needed by the ABI lowering of the new intrinsic that
tells the TCS the primitive type, if it's known.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28408>
For now, only monolithic shaders will hit the code path that will
generate these intrinsics.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28408>
These will be needed to implement some tessellation dynamic
states within the TCS as opposed to using an epilog.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28408>
We don't know what the float mode was by the end of the previous shader,
so we should always set it.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28392>
BSpec 56797:
Math operation rules when half-floats are used on both source and
destination operands and both source and destinations are packed.
The execution size must be 16.
Signed-off-by: Rohan Garg <rohan.garg@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27235>
This reverts commit be8b7980e6.
Store the cache entry so that the fast path picks up the optimized
pipeline when its available from a background optimized_compile_job().
Observed traces where it would take the fast path back and forth using
an unoptimized pipeline and never pick up the optimized pipeline leading
to >50% fps drop.
Signed-off-by: Juston Li <justonli@google.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28440>
