Rhys Perry 6fc2622abd aco: don't skip VS->TCS barrier if TCS output vertices doesn't match input ...

TCS invocations correspond to output patch vertices, not input. If they
differ, TCS invocations can be in a different subgroup than VS invocations
of the input patch.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/6564
Fixes: 152092b8ea ("aco: skip s_barrier if TCS patches are within subgroup")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17174>

2022-06-23 10:08:02 +00:00

..

addrlib

amd: Initialize Gfx11Lib members in constructor.

2022-05-31 03:36:53 +00:00

ci

ci/radv: add a missing flake

2022-06-21 13:11:05 +03:00

common

radeonsi/vcn: prepare for unified queue in vcn4

2022-06-16 03:30:47 +00:00

compiler

aco: don't skip VS->TCS barrier if TCS output vertices doesn't match input

2022-06-23 10:08:02 +00:00

drm-shim

Use proper types for meson objects

2022-04-18 13:03:08 +03:00

llvm

ac/llvm: fix tcs_wave_id unpacking on gfx11

2022-06-15 20:52:42 +00:00

registers

amd/gfx11: add PixelWaitSync packet fields

2022-06-15 20:52:42 +00:00

vulkan

radv/llvm: always emit a null export even if the FS doesn't discard

2022-06-22 08:31:30 +02:00

.clang-format

radv: allow holes in inline push constants

2022-04-12 11:44:30 +00:00

meson.build

r300/r600: Add drm-shim support.

2022-02-02 00:59:08 +00:00