Fixes RADV compilation of a Cyberpunk 2077 RT pipeline with
PIPELINE_CREATE_DISABLE_OPTIMIZATION_BIT.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Fixes: dfaa3c0af6 ("aco: Flip s_cbranch / s_cselect to optimize out an s_not if possible.")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27194>
(cherry picked from commit 6dc182b6b2)
Fixes compilation of a Doom Eternal shader with
PIPELINE_CREATE_DISABLE_OPTIMIZATION_BIT.
ac_nir_lower_resinfo() was not happening because it is predicated on
uses_resource_info_query and no later optimization updated it.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Friedrich Vock <friedrich.vock@gmx.de>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27195>
(cherry picked from commit 90939e93f6)
No driver supports urol/uror on all bit sizes. Intel gen11+ only for 16
and 32 bit, Nvidia GV100+ only for 32 bit. Etnaviv can support it on 8,
16 and 32 bit.
Also turn the `lower` into a `has` option as only two drivers actually
support `uror` and `urol` at this momemt.
Fixes crashes with CL integer_rotate on iris and nouveau since we emit
urol for `rotate`.
v2: always lower 64 bit
Fixes: fe0965afa6 ("spirv: Don't use libclc for rotate")
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by (Intel and nir): Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: David Heidelberg <david.heidelberg@collabora.com>
Acked-by: Yonggang Luo <luoyonggang@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27090>
(cherry picked from commit f2b7c4ce29)
GFX10 has a hw bug and it can't handle 0-sized index buffer. The
non-indirect draw path was fine but not the indirect path where RADV
emits the index buffer.
This fixes flakes with dEQP-VK.*maintenance6* on NAVI14, and possibly
GPU hangs if there is an indirect draw with a valid index buffer right
before because it would re-use the same index buffer.
Fixes: db9816fd66 ("radv: add support for NULL index buffer")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27142>
(cherry picked from commit 783e3c096f)
GFX7 CP requires the indirect dispatch VA to be aligned to 32-bytes.
This fixes dEQP-VK.api.command_buffers.many_indirect_disps_on_secondary,
but it's unexpected that it uncovered this bug.
Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27148>
(cherry picked from commit 5c03cdbd02)
No Foz-DB changes, but this fixes some issues when the spiller inserts
scratch loads after p_logical_end for p_return.
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27119>
(cherry picked from commit 74fc2e287f)
On chordal graphs, a greedy coloring can be done in a way that never uses
more colors than are required for the largest clique. However, since we
have vector values and force phi resources into the same spill slots, the
interference graphs are not chordal, and thus, this assumption doesn't hold.
Use twice as many spill slots as upper bound.
Totals from 10 (0.01% of 79242) affected shaders: (GFX11)
MaxWaves: 52 -> 54 (+3.85%)
Instrs: 271386 -> 271779 (+0.14%)
CodeSize: 1362544 -> 1365432 (+0.21%)
VGPRs: 2536 -> 2532 (-0.16%)
SpillVGPRs: 778 -> 818 (+5.14%)
Scratch: 73472 -> 76800 (+4.53%)
Latency: 3331718 -> 3328798 (-0.09%); split: -0.14%, +0.05%
InvThroughput: 1665860 -> 1643350 (-1.35%); split: -1.40%, +0.05%
VClause: 3292 -> 3329 (+1.12%); split: -0.06%, +1.18%
Copies: 46082 -> 46257 (+0.38%)
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27011>
(cherry picked from commit e3098bb232)
the vcn enc/unified rings don't do nop packets, and hang with 0 sized
cmd buffers. This just stops submitting 0 sized cmd buffers to the hw.
Fixes hangs with dEQP-VK.video.decode.h264_i on navi3x
Cc: mesa-stable
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25932>
(cherry picked from commit f33683e4da)
The extra cmd buffer layer was done wrong, need to emit the
sq start and ends around every reset/decode packet.
Fixes dEQP-VK.video.decode.h264_i on navi3x
Fixes: d8f3060bd9 ("radv/video: start adding gfx11 vcn decoder")
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25932>
(cherry picked from commit d32f2ee7b6)
Previous commit upreved deqp only for the Android
Fixes: 1ff4687e86 ("ci: uprev deqp-runner from 0.16.1 to 0.18.0")
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
[Eric]
- rename the deqp-runner version to DEQP_RUNNER_VERSION instead of DEQP_VERSION
- update image tags
- fix expectations lists
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27062>
(cherry picked from commit 4ff77f08e4)
DOOM Eternal builds acceleration structures with inactive primitives and
tries to make them active in later AS updates. This is disallowed by the
spec and triggers a GPU hang. Fix the hang by working around the bug.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27034>
(cherry picked from commit a9831caa14)
This mirrors the changes in 69ff9c16bb ("radeonsi: never set
DISABLE_WR_CONFIRM for CP DMA clears and copies").
Cc: mesa-stable
Suggested-by: Vitaliy Triang3l Kuzmin <triang3l@yandex.ru>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27053>
(cherry picked from commit 43fb43ba2c)
The max waves for RT prolog need to be recalculated after merging the
resource usage of all shaders invoked from it.
Note that there is no need to panic, as the info was only used to
calculate maximum scratch size and with the RT prolog being low
footprint, this likely only caused overestimation rather than
underestimation.
Fixes: 533ec9843e ("radv: Precompute shader max_waves.")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26998>
(cherry picked from commit 63827751e1)
This replaces RADV_HASH_SHADER_xxx by radv_device_cache_key which is
a new struct that contains per-device compiler options. More options
will be moved there.
Blake3 is used to replace sha1.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26948>
The per-device cache key will need to be initialized before compiling
any meta shaders, so this needs to be done earlier.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26948>
Detroit: Become Human has an optimization issue where the same BO is
mapped and unmapped on a per-frame basis, which leads to massive
overhead in the kernel, both creating the mapping and taking page
faults.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26942>
This reverts commit b38c776690.
This commit seems to offend radeonsi-raven-piglit and radeonsi-stoney-gl.
Signed-off-by: Sergi Blanch Torne <sergi.blanch.torne@collabora.com>
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26941>
This is highly experimental and only recommended
for users who know what they are doing.
To fully support the spec we are going to need
gang submissions which are going to be implemented later.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26913>
The built-in tiled-to-tiled copy packet doesn't support copying
between images that don't meet certain criteria such as alignment,
micro tile format, compression state etc.
To work around this, we copy the image piece by piece to a
temporary buffer that we know is supported,
and then copy it to the intended destination.
The implementation assumes that at least one pixel row of the
image fits into the temporary buffer, and will try to copy as
many rows as fit.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26913>
When either of the images is linear then the implementation can
use the same packets as used by the buffer/image copies.
However, tiled to tiled image copies use a separate packet.
Several variations of tiled to tiled copies are not supported
by the built-in packet and need a scanline copy as a workaround,
this will be implemented by an upcoming commit.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26913>
If only one component is negated, isel does not ensure that the constant
operand is in src1 because then the negate was a fmul, not a fneg.
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26919>
