fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-20 15:38:19 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
191949 commits 66 branches 936 tags 985 MiB
Commit graph

2441 commits

Author SHA1 Message Date
Christian Gmeiner
87786a7a7e nak: Move imad late optimization to nir 
It is more or less just a code move, but I touched
is_only_used_by_iadd(..) to match the style of the other functions in
that file.

Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30099>
 2024-07-12 05:54:46 +00:00
Christian Gmeiner
e019517d6e nak: Set has_imad32 conditionally 
Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30099>
 2024-07-12 05:54:46 +00:00
Faith Ekstrand
b209fedebe nak/sm50: Fix immediates for IMnMx 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
faeb715535 nak/sm50: Re-order all the ops 
This puts them in the same order as nak/ir.rs.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
970b3e0e71 nak: Add a legalize() method to ShaderModel 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
e039b7e1ac nak/sm50: Move legalization into SM50Op 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
59f1ad581e nak/sm50: Move instruction encoding into a trait 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
99c4b90f3c nak/sm70: Move legalization into SM70Op 
This puts the legalize routine and the encoder right next to each other
in the code, making it much easier to verify that legalize() enforces
all of the constraints reqauired by encode().

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
f20b1c50b4 nak/legalize: Handle RA instructions up-front 
This pulls them out of the per-SM flow.  They're also all no-ops to
legalize since they don't take vectors and are handled directly by RA.
This also means these instructions are now getting properly handled on
Maxwell where we previously trusted in the (probably broken) maxwell
legalizing code.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
9d8d928a59 nak/legalize: Handle OpBreak and OpBSSy specially 
This lets us stop passing liveness information into the per-op
legalization code.  Long-term, I want to add a more general core
concept of destinations which are also reads but I haven't gotten
around to that yet.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
d9a9bb651c nak/legalize: Move a bunch of helpers to a trait 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
1b9b6a9529 nak/sm70: Re-organize the code a bit 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
20e1160f3f nak/sm70: Move instruction encoding into a trait 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
57667aeac8 nak: Move instruction encoding into ShaderModel 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
d4db2f43de nak: Move Instr::can_be_uniform() into ShaderModel 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
6ddb2b291d nak: Move RegFile::num_regs() into ShaderModel 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
74ac40da2d nak/ra: Move the NAK_DEBUG=spill logic into RA 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
e6b8da5427 nak: Plumb a ShaderModel trait through everywhere 
Instead of scattering number checks everywhere, this lets us actually
start splitting code paths.  This commit just adds the shader model
trait.  Later commits will add more methods.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
69bea2b49f nak/sm50: Get rid of the hand-rolled align_up/down() helpers 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
0f7ff6fbdc nak: Move encode_sm* to to sm*.rs 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:31 +00:00
Faith Ekstrand
d82a5d0f59 nak/sph: Stop storing the shader model in ShaderProgramHeader 
It's only needed for one Kepler+ check which is unlikely to ever be
relevant for NAK.  Also, that should probably be based on the SPH
version or something, not an arbitrary shader model.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30141>
 2024-07-11 22:28:30 +00:00
Christian Gmeiner
898752818c nak: Update comment about explicit padding 
The bindgen thing is not used anymore and NAK_SHADER_INFO_STAGE_UNION_SIZE
is not defined anywhere.

Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30094>
 2024-07-09 13:44:13 +00:00
Dave Airlie
fcf5946828 nvk: use 2k overallocation for shader heap. 
NVIDIA has informed us via Arthur (and Ben) that 2K
is sufficient here, so move nvk to use that.

Reviewed-by: M Henning <drawoc@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29746>
 2024-07-09 15:10:30 +10:00
Faith Ekstrand
c7c3942786 nouveau/push: Cache the last header DW to avoid read-back 
The pushbuf may live in VRAM in which case readback gets very expensive.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
1c5901c0dc nvk: Put descriptors in VRAM 
This improves frame rates in The Witness by another 5% or so.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
a342379c56 nvk: Put CB0 in VRAM 
This improves frame rates in The Witness by about 2%.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
68f1df5ebb nvk/nvkmd: Be a lot more pedantic about VA alignments 
The VA alignment now has two pieces: The bind alignment and the base
address alignment.  The caller gets to request the later but not the
former.  The bind alignment is based entirely on whether or not we know
a priori that the given VA will only ever be used for GART.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
7f45d20d2b nvk/nvkmd: Be more specific about memory alignments 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
1db57bb414 nvk/nvkmd: Rework memory placement flags 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
e04bb3dffa nvk: Drop nvk_buffer::is_local 
It was always kinda BS and we aren't even using it anymore thanks to
alignment requirements.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
2689760e38 nvk/nvkmd: Flip the script on NO_SHARED 
It's a positive flag in the kernel interface because it enables an
optimization and adds restrictions to the BO.  But from a userspace PoV,
NO_SHARE shoudd be the default with import/export being something we
expressly have to ask for.  This also reduces the number of flags we're
setting everywhere.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
1cee0c9cb7 nvk/nvkmd: Add real mem<->bo flag translation 
This way we can start to disconnect nvkmd_mem_flags from
nouveau_ws_bo_flags.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
0c024da291 nvk: Do mem maps directly in nvkmd on nouveau 
There's no point in the extra layer.  It's all just mmap() and friends.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
7bd9b9d96c nvk/nvkmd: Re-implement NVK_DEBUG=vm 
This new implementation is hooked at the nvkmd level and also works for
queued binds via a bind ctx.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
0abd7fa58a nvk/nvmkd: Plumb parent pointers through everywhere 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
d3264fdfb9 nvk: Move debug flags int nvk_debug.h 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
d96bf198b4 nvk: Move Heaps and BO binding into nvkmd 
We may want to move this even higher, into NVK at some point.  However
the wrappers in the winsys layer really aren't doing us much.  If
anything, now that nvkdm_mem::va is an nvkmd_va *, this actually makes
everything simpler because it's allocated through exactly the same paths
as sparse VA.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
0856c27dd1 nouveau/mme: Use fixed BO addresses in the MME test 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
c6c4483d0f nouveau/mme: Don't leak data_bo 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
7173ae1130 nouveau/mme: Don't dereference an empty vector 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
60c3c272ec nvk: Remove the last vestages of nouveau/winsys from core NVK 
Everything now goes through NVKMD.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
8a516394f9 nvk: Use nvkmd_ctx for queue submit 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
996b152375 nvk: Use an nvkmd_ctx for sparse binding 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
a8550862b5 nvk: Convert the upload queue to nvkmd_ctx 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
053b7f0f30 nvk/nvkmd: Implement nvkmd_ctx for nouveau 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
87ca92d881 nvk/nvkmd: Add a context interface 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
29e3b19860 nvk: Use nvkmd_mem for the zero page, VAB, and CB0 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
92ac7db7c8 nvk: Use nvkmd_mem for the nvk_queue_state::push 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
d0593bb86c nvk: Drop extra_bos from nvk_queue_submit_simple() 
We aren't using it anymore and the only reason it existed in the first
place was for providing BO lists to the old UAPI.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00
Faith Ekstrand
b86079d61e nvk: Use an nvkmd_mem for the SLM area 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30033>
 2024-07-09 01:22:23 +00:00