fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-20 00:28:08 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
221240 commits 66 branches 936 tags 978 MiB
Commit graph

337 commits

Author SHA1 Message Date
Marek Olšák
99546f7bad ac/nir: add ac_nir_get_io_driver_location as replacement for IO bases 
Acked-by: Pierre-Eric
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40556>
 2026-04-15 18:12:07 +00:00
Rhys Perry
7f3900ed20 ac/nir_lower_global_access: perform range analysis if useful 
fossil-db (navi31):
Totals from 1197 (0.59% of 202426) affected shaders:
Instrs: 2117283 -> 2108380 (-0.42%); split: -0.47%, +0.05%
CodeSize: 11183776 -> 11140060 (-0.39%); split: -0.42%, +0.03%
Latency: 13568247 -> 13648044 (+0.59%); split: -0.13%, +0.72%
InvThroughput: 2389746 -> 2376716 (-0.55%); split: -0.63%, +0.09%
VClause: 43337 -> 43138 (-0.46%); split: -0.51%, +0.05%
SClause: 31035 -> 31027 (-0.03%); split: -0.22%, +0.20%
Copies: 227528 -> 227002 (-0.23%); split: -0.59%, +0.36%
Branches: 29393 -> 29392 (-0.00%); split: -0.01%, +0.00%
PreSGPRs: 64238 -> 64336 (+0.15%)
PreVGPRs: 70480 -> 70468 (-0.02%)
VALU: 1387439 -> 1379274 (-0.59%); split: -0.59%, +0.00%
SALU: 185514 -> 185382 (-0.07%); split: -0.56%, +0.49%
VOPD: 4425 -> 4400 (-0.56%); split: +0.66%, -1.22%

fossil-db (navi21):
Totals from 1197 (0.59% of 202427) affected shaders:
Instrs: 1987004 -> 1974920 (-0.61%); split: -0.64%, +0.03%
CodeSize: 10803928 -> 10745204 (-0.54%); split: -0.56%, +0.01%
VGPRs: 83848 -> 83856 (+0.01%); split: -0.01%, +0.02%
SpillSGPRs: 9843 -> 9861 (+0.18%)
Latency: 14518481 -> 14534898 (+0.11%); split: -0.17%, +0.29%
InvThroughput: 3712336 -> 3698081 (-0.38%); split: -0.52%, +0.13%
VClause: 52677 -> 52546 (-0.25%); split: -0.51%, +0.27%
SClause: 31113 -> 31050 (-0.20%); split: -0.37%, +0.17%
Copies: 219723 -> 218017 (-0.78%); split: -1.05%, +0.27%
Branches: 33717 -> 33716 (-0.00%); split: -0.01%, +0.00%
PreSGPRs: 66364 -> 66480 (+0.17%)
PreVGPRs: 71048 -> 71036 (-0.02%)
VALU: 1442585 -> 1431331 (-0.78%); split: -0.78%, +0.00%
SALU: 209617 -> 208517 (-0.52%); split: -0.88%, +0.35%

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/40945>
 2026-04-15 15:13:10 +00:00
Raviraj Uppal
c5423d3e27 ac/nir: Fixed OpenGL CTS transform feedback overflow detection test case
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
The ordered atomic commits the post-add offset to memory, but overflow was computed using the pre-add offset, causing partial overflows to be missed and counters to become corrupted.

Fixes: "KHR-GL46.transform_feedback_overflow_query_ARB.multiple-streams-one-buffer-per-stream" based on the postwrite buffer offset, rather than the offset before the current workgroups writes.
Reviewed-by: Marek Olsak <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40745>
 2026-04-10 15:43:21 +00:00
Samuel Pitoiset
71b6db06e1 ac/nir: add descriptor heap support to opt_flip_if_for_mem_loads()
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40702>
 2026-04-07 06:15:24 +00:00
Samuel Pitoiset
1184610de4 ac/nir: add descriptor heap support to ac_nir_lower_image_tex() 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40702>
 2026-04-07 06:15:24 +00:00
Samuel Pitoiset
d2132ae011 ac/nir: adjust lowering of query size for descriptor heap 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40702>
 2026-04-07 06:15:24 +00:00
Karol Herbst
b7ca34db13 nir: unvendor ac_nir_lower_sin_cos 
So we can use it for Nvidia.

Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40541>
 2026-03-31 01:47:31 +02:00
Karol Herbst
5bb3c9f69c nir: rename fsin_amd and fcos_amd to a more generic name 
Nvidia implements both the same way as AMD does, so it makes sense to
allow for code sharing here.

Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40541>
 2026-03-31 01:47:29 +02:00
Georg Lehmann
5d2be211ea nir: add fp_math_ctrl to ddx/ddy 
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40630>
 2026-03-26 13:15:49 +00:00
Marek Olšák
dfbadedc02 ac/nir/meta_cs_blit: use uint16 for coordinates to fix 64K blits
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Reviewed-by: Pierre-Eric
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40565>
 2026-03-25 09:39:20 +00:00
Marek Olšák
2283244975 nir: change export_amd intrinsics to use target instead of base 
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40415>
 2026-03-23 06:10:49 +00:00
Marek Olšák
b75a3112fd nir: change export_amd intrinsics to use enabled_channels instead of write_mask 
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40415>
 2026-03-23 06:10:49 +00:00
Daniel Schürmann
d909e14f30 ac: add and lower loop continue construct for streamout buffer info loop 
We are going to disallow continue statements without
loop continue constructs.

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39942>
 2026-03-21 07:42:55 +00:00
Georg Lehmann
ec331cc48a nir: replace lower_ldexp with has_ldexp 
I can be bothered to fix all the backends that don't set lower_ldexp,
and only two backends have ldexp anyway.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33900>
 2026-03-20 08:15:08 +00:00
Georg Lehmann
87081a73c9 ac/nir/cull: make fisfinite nan/inf preserving 
Otherwise, it's meaningless.

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40291>
 2026-03-13 07:13:09 +00:00
Georg Lehmann
a25f00eaed nir: merge xfb and xfb2 into one 64bit intrinsic index 
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40299>
 2026-03-10 07:46:22 +00:00
Rhys Perry
b4dc39f632 ac/nir: fix when both dual source outputs are unwritten 
When this is the case. we shouldn't hang or crash.

Signed-off-by: Rhys Perry <pendingchaos02@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/40005>
 2026-03-05 09:38:23 +00:00
Marek Olšák
fd6941650c ac: add ac_cu_info::has_fmask, adjust FMASK checks 
Some of these should check has_fmask, others should check < GFX11.

v2: move to ac_cu_info

Reviewed-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/40022>
 2026-03-04 21:14:56 +00:00
Rhys Perry
5c3b5688a1 amd: rename ac_cu_info to ac_compiler_info 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40042>
 2026-03-03 08:50:12 +00:00
Rhys Perry
ab4b3b7737 ac/nir/ngg: add ac_cu_info shortcut 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40042>
 2026-03-03 08:50:12 +00:00
Rhys Perry
a65089dfce ac/nir: pass ac_cu_info to ac_nir_compute_tess_wg_info 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40042>
 2026-03-03 08:50:11 +00:00
Rhys Perry
8801ca188d ac/nir: don't pass radeon_info to ac_nir_set_options 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40042>
 2026-03-03 08:50:10 +00:00
Rhys Perry
5a8a7dbb22 ac/nir: don't pass radeon_info to NGG lowering 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40042>
 2026-03-03 08:50:09 +00:00
Rhys Perry
36feec61c8 ac/nir: use ac_nir_lower_ngg_options for ac_nir_lower_ngg_mesh 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40042>
 2026-03-03 08:50:09 +00:00
Rhys Perry
2c7b8e6786 ac/gpu_info: move some NGG flags to ac_cu_info 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40042>
 2026-03-03 08:50:09 +00:00
Rhys Perry
29f8237d30 amd: move various flags to ac_cu_info 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39992>
 2026-02-26 15:49:14 +00:00
Rhys Perry
78b3e07bed ac/nir: remove ac_nir_lower_ps_late_options::family 
This is unused.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39992>
 2026-02-26 15:49:12 +00:00
Rhys Perry
6d31054d86 ac/nir: remove gfx_level parameter from ac_nir_lower_indirect_derefs 
This was unused.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39992>
 2026-02-26 15:49:12 +00:00
Samuel Pitoiset
e8710152fb ac/nir: stop passing radeon_info for addr->coord helpers 
Only for gb_addr_config.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40041>
 2026-02-26 07:21:06 +00:00
Samuel Pitoiset
2eb9420061 ac/nir: fix writemask for dual source blending on GFX11+
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
This should definitely be an OR operation if MRT0 and MRT1 don't write
the same channels. This also requires to set the writemask manually
because when it's 0 (in case a dual-source output is missing), the
intrinsic computes the mask itself with the number of components.

No fossils-db changes on NAVI33.

Fixes: 45d8cd037a ("ac/nir: rewrite ac_nir_lower_ps epilog to fix dual src blending with mono PS")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/14878
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39996>
 2026-02-24 20:20:02 +00:00
Priya Hosur
0bfad39f15 ac/nir/ngg: re-enable use of known compile-time GS connectivity
Some checks are pending
macOS-CI / macOS-CI (dri) (push) Waiting to run
Details
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Details 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38075>
 2026-02-18 01:29:37 +00:00
Marek Olšák
a2309edb6b ac/nir/meta: properly align sparse buffer clears with 12-byte clear values 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39841>
 2026-02-17 14:47:41 +00:00
Marek Olšák
62cce3abcd ac/nir/meta: use the clear/copy compute shader if CP DMA doesn't support sparse 
ac_prepare_cs_clear_copy_buffer determines whether to use CP DMA, and
the driver obeys that.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39841>
 2026-02-17 14:47:41 +00:00
Marek Olšák
bbcfab9f4f ac/nir/meta: don't scalarize sparse loads if the address is aligned to load size 
This should make copying sparse faster if we get aligned buffer bounds.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39841>
 2026-02-17 14:47:41 +00:00
Rhys Perry
e4b8ade092 ac/nir,radv,radeonsi: flip branches to avoid waitcnts 
fossil-db (navi31):
Totals from 5123 (6.42% of 79825) affected shaders:
Instrs: 12712435 -> 12703672 (-0.07%); split: -0.12%, +0.05%
CodeSize: 67068852 -> 67033244 (-0.05%); split: -0.10%, +0.05%
VGPRs: 363896 -> 363956 (+0.02%)
SpillSGPRs: 5035 -> 5074 (+0.77%); split: -0.83%, +1.61%
Latency: 115048972 -> 111944013 (-2.70%); split: -2.89%, +0.19%
InvThroughput: 19102126 -> 18696069 (-2.13%); split: -2.34%, +0.22%
VClause: 258693 -> 258770 (+0.03%); split: -0.01%, +0.04%
SClause: 346271 -> 346225 (-0.01%); split: -0.02%, +0.00%
Copies: 1040815 -> 1042017 (+0.12%); split: -0.23%, +0.34%
Branches: 332467 -> 332565 (+0.03%); split: -0.04%, +0.07%
PreSGPRs: 304888 -> 304699 (-0.06%); split: -0.10%, +0.04%
PreVGPRs: 296652 -> 296654 (+0.00%)
VALU: 7591803 -> 7594601 (+0.04%); split: -0.01%, +0.05%
SALU: 1454420 -> 1455764 (+0.09%); split: -0.24%, +0.33%
VOPD: 1826 -> 1810 (-0.88%)

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/38262>
 2026-02-16 19:39:43 +00:00
Marek Olšák
a9df891bc6 nir: allow get_ssbo_size to return a 64-bit result 
to match get_ubo_size, and to support HW where SSBOs can have a 64-bit size.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39743>
 2026-02-16 12:59:36 +00:00
Marek Olšák
d1e6a5c1c8 ac: lower load_num_workgroups in NIR 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39638>
 2026-02-13 15:33:19 +00:00
Marek Olšák
1e11e83d1c ac/nir: add ac_nir_lower_intrinsics_to_args_options structure 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39638>
 2026-02-13 15:33:19 +00:00
Marek Olšák
a9e47751d2 ac: lower load_subgroup_id for ACO in NIR 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39638>
 2026-02-13 15:33:19 +00:00
Marek Olšák
0a9bdcac79 ac: lower load_workgroup_ids for ACO in NIR 
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39638>
 2026-02-13 15:33:19 +00:00
Marek Olšák
85916c8af0 ac/nir: lower buffer image_load to load_buffer_amd in NIR 
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39474>
 2026-02-02 17:56:54 +00:00
Marek Olšák
ef3d43085a ac/nir: lower buffer txf to load_buffer_amd in NIR 
This also:
- removes the sparse flag (TFE) if it has no uses
- removes trailing unused components (if not sparse) or all contiguous unused
  components before the sparse flag (if sparse)
- lowers 64-bit formatted buffer loads to 32 bits

Everything here could also be used by 64-bit non-buffer image loads
and txf if needed.

Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39474>
 2026-02-02 17:56:54 +00:00
Marek Olšák
30ee7044bc ac/nir: rename ac_nir_lower_tex -> ac_nir_lower_image_tex 
It will lower txf and buffer image loads to load_buffer_amd.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39474>
 2026-02-02 17:56:54 +00:00
Marek Olšák
61bfc298ba ac: set missing dest_type for image_deref_load 
required for lowering to load_buffer_amd

Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39474>
 2026-02-02 17:56:53 +00:00
Marek Olšák
fbfac92738 ac,radeonsi: add AC_NIR_TEX_BACKEND_FLAG_IS_IMAGE 
image_load lowered to tex will use this (descriptor loads only for now)

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39474>
 2026-02-02 17:56:53 +00:00
Marek Olšák
44bc1e6bf4 nir: add dest_type to load_buffer_amd 
for lowering the result to 16 bits

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39474>
 2026-02-02 17:56:52 +00:00
Georg Lehmann
809fb0fba3 ac/nir/lower_ps_late: emit scalar f2f16_rtz for when one half of a packed export is undef 
Foz-DB Navi48:
Totals from 7200 (8.74% of 82405) affected shaders:
Instrs: 9056391 -> 9048177 (-0.09%); split: -0.09%, +0.00%
CodeSize: 48681288 -> 48640684 (-0.08%); split: -0.09%, +0.00%
VGPRs: 413088 -> 413784 (+0.17%)
Latency: 76340711 -> 76320080 (-0.03%); split: -0.03%, +0.00%
InvThroughput: 12692959 -> 12684618 (-0.07%); split: -0.07%, +0.00%
VClause: 148823 -> 148821 (-0.00%)
Copies: 601739 -> 601874 (+0.02%); split: -0.01%, +0.03%
VALU: 5213356 -> 5207253 (-0.12%); split: -0.12%, +0.00%
SALU: 1160815 -> 1160817 (+0.00%); split: -0.00%, +0.00%
VOPD: 79520 -> 79444 (-0.10%); split: +0.09%, -0.18%

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39412>
 2026-01-26 10:54:23 +00:00
Georg Lehmann
8c895c5c61 ac/nir/lower_ps_late: CSE partial packed exports 
Foz-DB Navi48:
Totals from 425 (0.52% of 82405) affected shaders:
Instrs: 1110029 -> 1109658 (-0.03%); split: -0.03%, +0.00%
CodeSize: 6135272 -> 6133848 (-0.02%); split: -0.02%, +0.00%
VGPRs: 29856 -> 29844 (-0.04%)
Latency: 10258411 -> 10258043 (-0.00%); split: -0.00%, +0.00%
InvThroughput: 1898177 -> 1897661 (-0.03%)
Copies: 88221 -> 88173 (-0.05%)
VALU: 575276 -> 574894 (-0.07%)

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39412>
 2026-01-26 10:54:22 +00:00
Marek Olšák
ebeb904c95 ac,radeonsi: set optimal COMPUTE_DISPATCH_INTERLEAVE for buffer clears/copies 
Small buffer clears are a bit faster now.

The numbers were tuned specifically for this compute shader.

Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39290>
 2026-01-22 22:28:39 +00:00
Marek Olšák
a5e1d31dad ac/nir/meta: tune 12B clear buffer performance for gfx12 
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39290>
 2026-01-22 22:28:39 +00:00