Gurchetan Singh
|
03a35024a6
|
gfxstream: make sure by default descriptor is negative
Otherwise, another valid fd may be closed.
Cc: mesa-stable
Reviewed-by: Aaron Ruby <aruby@qnx.com
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34885>
|
2025-05-08 18:29:03 +00:00 |
|
Samuel Pitoiset
|
b7d2cdd2b4
|
radv: ignore radv_disable_dcc_stores on GFX12
macOS-CI / macOS-CI (dri) (push) Waiting to run
macOS-CI / macOS-CI (xlib) (push) Waiting to run
It's not necessary because DCC is completely transparent to the
userspace driver. Also it's causing issues with scanout.
This fixes rendering issues with scanout in Indiana Jones.
Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/12924
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34859>
|
2025-05-08 17:17:28 +02:00 |
|
Sil Vilerino
|
154c3934d6
|
d3d12: Add missing offset to encode slice metadata in the get_feedback function
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 10:42:17 -04:00 |
|
Sil Vilerino
|
245be20fa1
|
d3d12: Add fallback to ID3D12VideoEncodeCommandList2 if ID3D12VideoEncodeCommandList4 not available in underlying OS
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
e30a534f29
|
d3d12: Add missing D3D12_VIDEO_USE_NEW_ENCODECMDLIST4_INTERFACE guards
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
be33edbdf1
|
d3d12: Set HEVC slice mode state before calling d3d12_video_encoder_negotiate_requested_features_and_d3d12_driver_caps
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Pohsiang (John) Hsu
|
2939604248
|
d3d12: fix configuration flag for D3D12_VIDEO_ENCODER_CODEC_CONFIGURATION_HEVC_FLAG_DISABLE_LOOP_FILTER_ACROSS_SLICES
Signed-off-by: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Sil Vilerino <sivileri@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
2ff18b2757
|
d3d12: Remove more nir dependencies when with_gallium_d3d12_graphics disabled
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
27829d7ffe
|
d3d12: Do not build microsoft/compiler when graphics, gl or vk disabled
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
5051140c32
|
d3d12: Report pipe_enc_cap_dirty_info.supports_require_sao/loop_filter_disabled
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
64f1a365e5
|
pipe: Add pipe_enc_cap_dirty_info.supports_require_sao/loop_filter_disabled
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
922f8a7d07
|
d3d12: Implement H264/HEVC PIPE_VIDEO_SLICE_MODE_AUTO for gallium driver auto-partition
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
0ee4b77ec9
|
pipe: Add PIPE_VIDEO_SLICE_MODE_AUTO for gallium driver auto-partition
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
7dfc7e1b1d
|
d3d12: Reports pipe_enc_cap_dirty_info.supports_require_auto_slice_mode
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
ffe9cec740
|
pipe: Add pipe_enc_cap_dirty_info.supports_require_auto_slice_mode
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
1c31fc3091
|
d3d12: Implement GPU Input Motion vectors
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
143087dadd
|
d3d12: Make d3d12_video_encode_support_caps in/out param capEncoderSupportData1 pointer members an external allocation to outlive the stack of the method call
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
7312db4827
|
pipe: Add support for (GPU Input) motion maps
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
2c193547ca
|
d3d12: Implement PIPE_VIDEO_CAP_ENC_QP_MAPS and CPU/GPU input QPMaps
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
5810c39978
|
pipe: Add (GPU input) PIPE_VIDEO_CAP_ENC_QP_MAPS and input_gpu_qpmap GPU input support
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
5cb4979875
|
d3d12: Add GPU input dirty rect support
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
86d521db4f
|
pipe: Add (GPU input) PIPE_VIDEO_CAP_ENC_DIRTY_MAPS and pipe_enc_move_rects GPU input support
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
064e07b26a
|
d3d12: deduplicate code with helpers: get_dirty_rects_support, get_move_rects_support, get_gpu_output_stats_support, get_sliced_encode_support
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
19cbb13255
|
d3d12: Support slice NAL prefixes on slice notifications mode
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
df995c9631
|
d3d12: Implement multi-slice notifications
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
bedd423893
|
d3d12: Prepare d3d12_video_encoder_encode_bitstream for sliced encoding. Checked working with single slice buffer at this point
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
555a13661a
|
pipe: Add sliced encoding API and caps
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
c5f5ee41c8
|
d3d12: Add support for QP, SATD and RC bits output stats
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
25726509ff
|
pipe: Add PIPE_VIDEO_CAP_ENC_GPU_STATS_* and pipe_resource textures in H264/H265 encode pic params
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
56bbfb9598
|
d3d12: Add support for pipe_enc_move_rects for H264/H265 encode
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
7c490bb860
|
pipe: Add PIPE_VIDEO_CAP_ENC_MOVE_RECTS and pipe_enc_move_rects for H264/H265 encode
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
6d81bc0cdd
|
d3d12: Add support for pipe_enc_dirty_rects for H264/H265 encode
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
700c6fff58
|
pipe: Add PIPE_VIDEO_CAP_ENC_DIRTY_RECTS and pipe_enc_dirty_rects for H264/H265 encode
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
4e632ed891
|
d3d12: Use D3D12_FEATURE_VIDEO_ENCODER_SUPPORT2 when D3D12_VIDEO_USE_NEW_ENCODECMDLIST4_INTERFACE is set
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
731bc92e87
|
d3d12: Add #if guards for using new ID3D12VideoEncodeCommandList4
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
2465dcf4cc
|
d3d12: Fix reporting for PIPE_VIDEO_CAP_ENC_MAX_DPB_CAPACITY
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
0577c77a4c
|
d3d12: Report pipe_enc_cap_roi.log2_roi_min_block_pixel_size
Reviewed-By: Pohsiang Hsu <pohhsu@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Sil Vilerino
|
17cdbc5729
|
pipe: Add pipe_enc_cap_roi.log2_roi_min_block_pixel_size
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Pohsiang (John) Hsu
|
295ecc8d96
|
d3d12: enable D3D12_VIDEO_ENCODER_CODEC_CONFIGURATION_HEVC_FLAG_ENABLE_LONG_TERM_REFERENCES when max_num_ltr_frames > 0
Signed-off-by: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Sil Vilerino <sivileri@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Pohsiang (John) Hsu
|
ebd82f39f8
|
d3d12: Add support for retreiving PIPE_VIDEO_CAP_ENC_MAX_DPB_CAPACITY for H264/H265 encode
Signed-off-by: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Sil Vilerino <sivileri@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:22 +00:00 |
|
Pohsiang (John) Hsu
|
7557ce41be
|
pipe: add PIPE_VIDEO_CAP_ENC_MAX_DPB_CAPACITY for H264/H265 encode
Signed-off-by: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Sil Vilerino <sivileri@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:21 +00:00 |
|
Pohsiang (John) Hsu
|
ea7ef6d575
|
d3d12: Add support for retrieving PIPE_VIDEO_CAP_ENC_MAX_LONG_TERM_REFERENCES_PER_FRAME for H264/H265 encode
Signed-off-by: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Sil Vilerino <sivileri@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:21 +00:00 |
|
Pohsiang (John) Hsu
|
743f0a8df1
|
pipe: add PIPE_VIDEO_CAP_ENC_MAX_LONG_TERM_REFERENCES_PER_FRAME for H264/H265 encode
Signed-off-by: Pohsiang Hsu <pohhsu@microsoft.com>
Reviewed-by: Sil Vilerino <sivileri@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34844>
|
2025-05-08 14:17:21 +00:00 |
|
Rhys Perry
|
2704a30df0
|
radv: perform nir_opt_access before the first radv_optimize_nir
macOS-CI / macOS-CI (dri) (push) Waiting to run
macOS-CI / macOS-CI (xlib) (push) Waiting to run
Two lowered loads might not be CSE'd after nir_lower_explicit_io if one of
them is shrinked. This doesn't happen for deref loads, but it needs the
CAN_REORDER flag first.
fossil-db (gfx1201):
Totals from 556 (0.70% of 79377) affected shaders:
MaxWaves: 14936 -> 14940 (+0.03%); split: +0.05%, -0.03%
Instrs: 2140334 -> 2140942 (+0.03%); split: -0.07%, +0.10%
CodeSize: 11137948 -> 11145416 (+0.07%); split: -0.07%, +0.13%
SpillSGPRs: 2385 -> 2527 (+5.95%); split: -0.34%, +6.29%
Latency: 12310570 -> 12305011 (-0.05%); split: -0.08%, +0.04%
InvThroughput: 2136142 -> 2135516 (-0.03%); split: -0.06%, +0.03%
VClause: 47419 -> 47420 (+0.00%); split: -0.01%, +0.01%
SClause: 58423 -> 58290 (-0.23%); split: -0.36%, +0.14%
Copies: 160626 -> 161321 (+0.43%); split: -0.25%, +0.68%
Branches: 69693 -> 69710 (+0.02%); split: -0.04%, +0.06%
PreSGPRs: 34824 -> 34945 (+0.35%); split: -0.24%, +0.58%
PreVGPRs: 28682 -> 28649 (-0.12%); split: -0.36%, +0.24%
VALU: 1080800 -> 1081171 (+0.03%); split: -0.04%, +0.08%
SALU: 353112 -> 353770 (+0.19%); split: -0.15%, +0.34%
SMEM: 81587 -> 81364 (-0.27%)
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/34162>
|
2025-05-08 13:30:50 +00:00 |
|
Rhys Perry
|
18a53230eb
|
aco: don't check dst_bitsize in apply_load_extract
I don't think this is necessary.
fossil-db (gfx1201):
Totals from 12 (0.02% of 79377) affected shaders:
Instrs: 73041 -> 72669 (-0.51%); split: -0.51%, +0.00%
CodeSize: 417376 -> 413852 (-0.84%); split: -0.85%, +0.00%
Latency: 1301862 -> 1301533 (-0.03%); split: -0.03%, +0.00%
InvThroughput: 599874 -> 599723 (-0.03%)
VClause: 1344 -> 1346 (+0.15%)
Copies: 15855 -> 15832 (-0.15%); split: -0.37%, +0.23%
VALU: 42138 -> 41883 (-0.61%); split: -0.61%, +0.00%
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/34162>
|
2025-05-08 13:30:50 +00:00 |
|
Rhys Perry
|
eb95f7cc0e
|
aco: support sign extension in apply_load_extract
fossil-db (gfx1201):
Totals from 10 (0.01% of 79377) affected shaders:
Instrs: 28954 -> 28938 (-0.06%)
CodeSize: 164552 -> 164472 (-0.05%)
Latency: 1249341 -> 1247037 (-0.18%)
InvThroughput: 297077 -> 296618 (-0.15%)
VALU: 15951 -> 15941 (-0.06%)
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/34162>
|
2025-05-08 13:30:50 +00:00 |
|
Rhys Perry
|
0de0fd38b4
|
aco: support more opcodes in apply_ds_extract
fossil-db (gfx1201):
Totals from 320 (0.40% of 79377) affected shaders:
Instrs: 3439754 -> 3432384 (-0.21%)
CodeSize: 18008696 -> 17973180 (-0.20%); split: -0.20%, +0.00%
VGPRs: 16016 -> 15404 (-3.82%)
Latency: 20246168 -> 20295740 (+0.24%); split: -0.08%, +0.33%
InvThroughput: 4462916 -> 4478546 (+0.35%); split: -0.08%, +0.43%
VClause: 87123 -> 87099 (-0.03%)
Copies: 261779 -> 261948 (+0.06%); split: -0.05%, +0.12%
Branches: 94611 -> 94601 (-0.01%); split: -0.01%, +0.00%
VALU: 1870695 -> 1865738 (-0.26%)
SALU: 488351 -> 487557 (-0.16%)
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/34162>
|
2025-05-08 13:30:50 +00:00 |
|
Rhys Perry
|
3b42626973
|
ac/nir: allow 8/16-bit smem loads
fossil-db (gfx1201):
Totals from 295 (0.37% of 79377) affected shaders:
Instrs: 314018 -> 313355 (-0.21%); split: -0.22%, +0.00%
CodeSize: 1697996 -> 1696528 (-0.09%); split: -0.11%, +0.02%
Latency: 4197719 -> 4197106 (-0.01%)
InvThroughput: 1258891 -> 1258744 (-0.01%)
PreSGPRs: 12232 -> 12230 (-0.02%)
SALU: 66762 -> 66269 (-0.74%)
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/34162>
|
2025-05-08 13:30:50 +00:00 |
|
Rhys Perry
|
5b116c4de9
|
ac/nir: allow vectorization of unsupported 8/16-bit loads
These can later be lowered to a vectorized 32-bit load.
fossil-db (gfx1201):
Totals from 1259 (1.59% of 79377) affected shaders:
MaxWaves: 36821 -> 36817 (-0.01%)
Instrs: 4363702 -> 4355749 (-0.18%); split: -0.23%, +0.05%
CodeSize: 22779980 -> 22706504 (-0.32%); split: -0.37%, +0.05%
VGPRs: 69672 -> 69792 (+0.17%); split: -0.02%, +0.19%
SpillSGPRs: 675 -> 673 (-0.30%)
Latency: 26684053 -> 26663819 (-0.08%); split: -0.11%, +0.03%
InvThroughput: 5617687 -> 5614798 (-0.05%); split: -0.10%, +0.04%
VClause: 106830 -> 106654 (-0.16%); split: -0.17%, +0.00%
SClause: 75523 -> 75495 (-0.04%); split: -0.04%, +0.01%
Copies: 323199 -> 323525 (+0.10%); split: -0.10%, +0.20%
Branches: 109475 -> 109480 (+0.00%); split: -0.00%, +0.01%
PreSGPRs: 55036 -> 55040 (+0.01%)
PreVGPRs: 47538 -> 47582 (+0.09%); split: -0.12%, +0.21%
VALU: 2377777 -> 2389977 (+0.51%); split: -0.02%, +0.53%
SALU: 578272 -> 578385 (+0.02%); split: -0.02%, +0.04%
VMEM: 190065 -> 181204 (-4.66%)
SMEM: 99709 -> 99565 (-0.14%)
VOPD: 244 -> 243 (-0.41%); split: +0.41%, -0.82%
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/34162>
|
2025-05-08 13:30:50 +00:00 |
|
Rhys Perry
|
6dbf44ad9c
|
ac/nir: allow less than one register of overfetch
This is to allow vectorization of 8/16-bit loads, which can later be
cheaply lowered to a 32-bit load.
fossil-db (gfx1201):
Totals from 178 (0.22% of 79377) affected shaders:
MaxWaves: 4138 -> 4102 (-0.87%)
Instrs: 619714 -> 617917 (-0.29%); split: -0.32%, +0.03%
CodeSize: 3364396 -> 3352724 (-0.35%); split: -0.38%, +0.03%
VGPRs: 12896 -> 12980 (+0.65%); split: -0.19%, +0.84%
SpillSGPRs: 546 -> 545 (-0.18%)
Latency: 7589585 -> 7406076 (-2.42%); split: -2.45%, +0.04%
InvThroughput: 1926356 -> 1879866 (-2.41%); split: -2.42%, +0.00%
VClause: 12301 -> 11750 (-4.48%)
SClause: 13614 -> 13583 (-0.23%); split: -0.45%, +0.22%
Copies: 82207 -> 82265 (+0.07%); split: -0.10%, +0.17%
Branches: 19284 -> 19266 (-0.09%)
PreSGPRs: 9525 -> 9457 (-0.71%)
PreVGPRs: 12366 -> 12421 (+0.44%)
VALU: 347928 -> 348020 (+0.03%); split: -0.01%, +0.04%
SALU: 82620 -> 82519 (-0.12%); split: -0.19%, +0.07%
VMEM: 22248 -> 21430 (-3.68%)
SMEM: 17951 -> 17843 (-0.60%)
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/34162>
|
2025-05-08 13:30:50 +00:00 |
|