AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
185,552 Commits 1 Branch 0 Tags
259cdc549650a08a548befc69964e0d9f998f113
Commit Graph

2124 Commits

Author SHA1 Message Date
Mike Blumenkrantz
3aea0e31a4 winsys/sw: propagate nboxes to displaytarget_display() 
only a single box region is used

Acked-by: Daniel Stone <daniels@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27703>
 2024-02-29 01:15:22 +00:00
Mike Blumenkrantz
3cca761934 gallium: add a nboxes param to flush_frontbuffer 
this allows conveying damage regions through the sw presentation interface

Acked-by: Daniel Stone <daniels@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27703>
 2024-02-29 01:15:22 +00:00
Ruijing Dong
5663221bdb radeonsi/vcn: data structure av1 enc long term reference. 
Here it borrowed the term "long term reference" to represent
the customized reference frame rather than the default ones used.

To enable that, it needs application to leverage VAAPI existing
interface to mark a frame as "long term reference", and then
it will be preserved in the DPB for later usage. This preserved
frame later could be refered to by having its signature used in
the ref_frame_idx[] list, and the index can be indicated by
RefFrameCtrl index2, which has not been used for other purpose.

Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27771>
 2024-02-27 20:20:45 +00:00
Antonio Gomes
12f1a4c311 gallium: Add new PIPE_CAP_CL_GL_SHARING 
We have a situation where some drivers have all the required features,
but they are not working with gl_sharing, so we end up advertising it
wrongly. Add this cap to ensure this driver was tested to work with
cl_khr_gl_sharing.

Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26071>
 2024-02-23 13:29:00 +00:00
Timothy Arceri
1098afd7fb gallium: add PIPE_CAP_FP16 for AMD_gpu_shader_half_float 
Acked-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18540>
 2024-02-12 13:23:14 +00:00
Marek Olšák
47c1f389ed gallium: remove take_ownership from set_vertex_buffers, assume it's true 
This removes the take_ownership parameter and defines the behavior as if
take_ownership was always true, which is the fast path. This way, we don't
have to have 2 codepaths in set_vertex_buffers of every driver.

The old behavior is optionally available through util_set_vertex_buffers.

It also documents a new constraint that count in set_vertex_buffers must be
equal to the number of vertex buffers referenced by vertex elements or 0.

Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27492>
 2024-02-07 09:19:42 +00:00
Marek Olšák
f0b31858e1 gallium: always set vertex elements before setting vertex buffers 
Drivers can use this constraint to merge vertex elements and vertex
buffers in set_vertex_buffers instead of in draw_vbo.

Suggested by: https://gitlab.freedesktop.org/mesa/mesa/-/issues/8142

Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27492>
 2024-02-07 09:19:41 +00:00
Sil Vilerino
9710fca612 frontends/va, d3d12: Fix PIPE_VIDEO_SLICE_MODE_MAX_SLICE_SICE -> PIPE_VIDEO_SLICE_MODE_MAX_SLICE_SIZE typo 
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27342>
 2024-01-29 20:19:42 +00:00
Marek Olšák
386822c1b0 gallium: rename PIPE_.._PIN_THREADS_TO_L3_CACHE -> .._UPDATE_THREAD_SCHEDULING 
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27247>
 2024-01-29 19:40:46 +00:00
Marek Olšák
d230434ae3 mesa,gallium: move the thread scheduler to src/util 
The only change in behavior is that setting the affinity mask is skipped
when it has no effect, which happens when the app thread hasn't been moved
under a different L3 cache by the kernel (the sched_state variable tracks
that). This improves performance because setting the affinity mask incurs
measurable CPU overhead even if it has no effect.

Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27247>
 2024-01-29 19:40:46 +00:00
Tomeu Vizoso
af199e0ff0 teflon: Initial commit 
Teflon is a Gallium frontend that TensorFlow Lite can load to delegate
the execution of operations in a neural network model.

See docs for more.

Acked-by: Christian Gmeiner <cgmeiner@igalia.com>
Acked-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25714>
 2024-01-24 10:02:10 +00:00
Marek Olšák
a94319d29b winsys/amdgpu: don't clear buffer list elements after IB submission 
amdgpu_winsys_bo_reference(dst, NULL) sets *dst to NULL, but we never read
*dst again because we set num_buffers to 0. So don't touch the buffer list
elements and only decrement the BO refcount. It makes a difference when you
have 10k BOs.

The CS thread overhead in VP2020/Catia1: 9.23% -> 8.74%

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27060>
 2024-01-15 23:21:25 +00:00
Marek Olšák
eb20ef9277 gallium: remove unbind_trailing_count from set_vertex_buffers 
It should implicitly unbind all bound buffers after "count".
This also slightly simplies u_vbuf.

This is a cleanup suggested by:
    https://gitlab.freedesktop.org/mesa/mesa/-/issues/8142

Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io> (asahi & panfrost)
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26309>
 2024-01-14 21:55:19 +00:00
Marek Olšák
6d7a76595d winsys/amdgpu: remove dependency_flags parameter from cs_add_fence_dependency 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26643>
 2024-01-06 20:55:30 +00:00
Marek Olšák
6d913a2bcc r300,r600,radeonsi: switch to pb_buffer_lean 
to remove pb_buffer::vtbl from all buffer structures

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26643>
 2024-01-06 20:55:30 +00:00
Marek Olšák
39c1311766 gallium/pb_buffer: define pb_buffer_lean without vtbl, inherit it by pb_buffer 
amdgpu doesn't need vtbl.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26643>
 2024-01-06 20:55:30 +00:00
Marek Olšák
49bf2545fe winsys/amdgpu: add amdgpu_bo_real_reusable slab for the backing buffer 
Add contents of amdgpu_bo_slab into it. This will allow removing the "real"
pointer from amdgpu_bo_slab_entry because "(char*)entry.slab" is now
pointing next to it.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26643>
 2024-01-06 20:55:30 +00:00
Marek Olšák
643f390de5 radeon_winsys: add struct radeon_winsys* parameter into fence_reference 
Since the radeon winsys implements fences as buffers, we need radeon_winsys*
to destroy them. This will enable the removal of pb_cache_entry::mgr.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26643>
 2024-01-06 20:55:30 +00:00
Marek Olšák
523a4f71f2 winsys/amdgpu: stop using pb_buffer::vtbl 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26643>
 2024-01-06 20:55:29 +00:00
Ruijing Dong
6c758000fb frontends/va: remove some TODOs in hevc encoding 
Remove some TODOs in va hevc encoding sps parsing.

Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26770>
 2024-01-03 19:23:08 +00:00
Pierre-Eric Pelloux-Prayer
a2cfd4186f radeonsi/winsys: add cs_get_ip_type function 
Will be used in the next commit.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26774>
 2023-12-20 12:23:27 +00:00
Ruijing Dong
d6da63071e frontends/va: add ROI feature 
ROI (region of interest) feature implementation
in va.

It does not support ROI priority, and supports
qp delta, and the maximum number of supported
region is defined as 32, the region sequence implies
the priority, the lower the sequence number, the higher
the region priority, when region overlapping happened,
the higher priority region overwrites the lower
priority one.

And specifically for AV1, the adjust step will be
rounded by 5 when rate control is used, for example,
if qp_delta (q index) is 6, it will use 5, if
qp_delta is 8, it will use 10.

For AVC/HEVC (RC/CQP) and AV1 CQP mode, the
qp_delta granularity is 1.

Reviewed-by: Boyuan Zhang <boyuan.zhang@amd.com>
Signed-off-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26659>
 2023-12-15 14:06:34 +00:00
Sathishkumar S
cd8ccba814 frontends/va: use va interface for jpeg partial decode 
add support to check jpeg crop decode cap and to set the crop
rectangle. the interface is avialble on libva 1.21.0 and higher.

v2: (Ruijing)
enclose the entire case block within VA_CHECK_VERSION
if attr unsupported set the return value to VA_ATTRIB_NOT_SUPPORTED

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26588>
 2023-12-13 14:18:05 +00:00
Alyssa Rosenzweig
f217d267d3 gallium: add PIPE_IMAGE_ACCESS_DRIVER_INTERNAL 
for e.g. driver internal blits that can use special paths wrt comporession.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26613>
 2023-12-12 19:44:41 -04:00
Yogesh Mohan Marimuthu
a9064837f8 winsys/radeon: remove unused gpu_address variable from struct radeon_cmdbuf 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26612>
 2023-12-12 06:14:23 +00:00
Marek Olšák
9ab59574ef gallium: add typedef pipe_draw_func matching the draw_vbo signature and use it 
We've copied the signature too many times already. This will also be used
more.

It intentionally deviates from the name by not including the "_vbo" part.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26619>
 2023-12-10 06:20:14 +00:00
Sil Vilerino
0c1ff82bc8 frontend/va: Add h264 encode ip_period param 
Reviewed-by: Boyuan Zhang <Boyuan.Zhang@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26456>
 2023-12-06 03:58:53 +00:00
Sil Vilerino
413b466aea pipe: Add PIPE_H264_MAX_REFERENCES 
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26456>
 2023-12-06 03:58:53 +00:00
Sil Vilerino
92b73aeb16 pipe: Add PIPE_VIDEO_CAP_ENC_H264_SUPPORTS_CABAC_ENCODE 
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26456>
 2023-12-06 03:58:53 +00:00
Sil Vilerino
c954830132 pipe: Add PIPE_VIDEO_FEEDBACK_METADATA_TYPE_AVERAGE_FRAME_QP 
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26456>
 2023-12-06 03:58:53 +00:00
Sil Vilerino
3f07c8c321 pipe: Add p_video_codec.get_encode_headers for out of band VPS, SPS, PPS 
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26456>
 2023-12-06 03:58:53 +00:00
Sil Vilerino
34d45cf7ed pipe: Add fence_get_win32_handle to get HANDLE from pipe_fence_handle 
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26456>
 2023-12-06 03:58:52 +00:00
Sil Vilerino
d9bbae6a0c pipe: Add get_feedback_fence for encode async waiting on pipe_feedback_fence 
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26456>
 2023-12-06 03:58:52 +00:00
Sil Vilerino
3ab25d6fb3 pipe: Support inserting new headers on each H264/HEVC IDR frame 
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26456>
 2023-12-06 03:58:52 +00:00
Peyton Lee
6b441ef6ab frontends, va: add new parameters of post processor 
Signed-off-by: Peyton Lee <peytolee@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25713>
 2023-12-01 00:23:38 +00:00
Boyuan Zhang
ffdc83e9dd frontend/va: add support for multi slices reflist 
According to codec spec, hevc supports different reference picture lists
for multi slices case. For example, each slice can have it's own ref pic
list. Add this support to pipe, and modify both frontend/va and radeonsi
accordingly.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26081>
 2023-11-30 08:39:28 -05:00
Boyuan Zhang
26237b9807 gallium/pipe: define hevc max slices number 
No logic change, just use define instead of hardcoded number to make
it more clear.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26081>
 2023-11-30 08:39:25 -05:00
Marek Olšák
7a7285bc69 gallium: add PIPE_CAP_PERFORMANCE_MONITOR for GL_AMD_performance_monitor 
Use a CAP instead of guessing it. radeonsi won't expose it.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26262>
 2023-11-28 17:34:26 +00:00
Marek Olšák
6073a149b9 gallium/docs: make CAP doc order match definition order 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26262>
 2023-11-28 17:34:26 +00:00
Alyssa Rosenzweig
301f57a17c gallium: drop pipe_shader_state_from_nir 
It is a bad api and now unused.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Eric Engestrom <eric@igalia.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26272>
 2023-11-21 20:14:35 +00:00
Sil Vilerino
bee4a3683c frontend/va: Add log2_max_frame_num_minus4 and log2_max_pic_order_cnt_lsb_minus4 for h264enc 
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26223>
 2023-11-20 17:18:59 +00:00
Sil Vilerino
9ce17de1fd pipe: Add max_slice_bytes for H264, HEVC encoding 
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26223>
 2023-11-20 17:18:59 +00:00
Sil Vilerino
6b4010b906 pipe: Add HEVC VUI encode params 
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26223>
 2023-11-20 17:18:59 +00:00
Sil Vilerino
0c312c5c59 pipe: Add H264 VUI encode params 
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26223>
 2023-11-20 17:18:59 +00:00
Sil Vilerino
10eb9296fe pipe: Add PIPE_VIDEO_CAP_ENC_INTRA_REFRESH_MAX_DURATION 
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26223>
 2023-11-20 17:18:59 +00:00
Sil Vilerino
44a3bfcc67 pipe: Add PIPE_VIDEO_CAP_ENC_H264_DISABLE_DBK_FILTER_MODES_SUPPORTED 
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26223>
 2023-11-20 17:18:59 +00:00
Sil Vilerino
be4287c3aa pipe: Extend get_feedback with additional metadata 
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26223>
 2023-11-20 17:18:59 +00:00
Ruijing Dong
5524faa22c radeonsi/vcn: change intra-ref name 
1. change structure name from intra-ref to intra-refresh
2. add need_sequence_header variable
3. add intra-refresh cap enum

Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Boyuan Zhang <Boyuan.Zhang@amd.com>
Signed-off-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26133>
 2023-11-13 14:29:40 +00:00
Ruijing Dong
66c75b0ca2 radeonsi/vcn: preparation for enc intra-refresh 
This is a prepration for adding intra-refresh
in vcn encoders. Intra-refresh is a feature for
smoothing out fluctuation in bitrate by replacing
a whole intra frame by several intra strips distributed
in several continous frames, it is also used in
suppressing error propagation situation.

Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Boyuan Zhang <Boyuan.Zhang@amd.com>
Signed-off-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26133>
 2023-11-13 14:29:40 +00:00
David Rosca
9e82c5d864 frontends/va: Parse H264 SPS for max_num_reorder_frames 
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25565>
 2023-10-25 01:03:58 +00:00