Mesa (main): 25 new commits
GitLab Mirror
gitlab-mirror at kemper.freedesktop.org
Fri Jul 9 10:23:49 UTC 2021
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=7532a28c4e0d1bdf0724f996f21f2f4aa08f8c41
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Fri Jun 18 18:10:05 2021 +0200
dlist: skip NOP command at the head of a list
If we build a dlist starting with a NOP (for alignment purpose),
we don't have to execute the NOP.
Instead shift the start value by one.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=482db91c457284bdaee248d9ec03530d51208895
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Fri Jun 18 15:11:54 2021 +0200
dlist: remove unused _mesa_dlist_alloc
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=4f78b2f8058113ddba0bfaf9e94c7da51bf844b9
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Fri Jun 18 15:10:38 2021 +0200
dlist: remove _mesa_dlist_alloc_aligned
It was only used in _mesa_dlist_alloc_vertex_list, so inline it there
instead.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=b703d7c15f47fed9f22de55f21cfd8d9d5ff241e
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Tue Jun 15 15:42:59 2021 +0200
dlist: store all dlist in a continuous memory block
This reduces cache-misses in execute_list for apps using lots of small
dlist, like viewperf.
This is only done for small dlist (fitting in one block) because doing
this for larger ones wouldn't bring any benefit.
For instance, in vp13/snx test 10: the % of cache-misses events in
_mesa_glthread_execute_list/execute_list goes down from 17%/10% to 4%/3%.
If "struct gl_display_list" were stored in an array this would also
remove source of cache-misses since currently they're malloc-ed
individually.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=2f506e8153b778aaaf0dbf5ab55bd42d34248ec1
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Wed Jun 16 17:44:29 2021 +0200
dlist: increment/check list nesting when handling OPCODE_CALL_LIST(S)
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=764e28d238b7bd70358694428eca50a91544460c
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Wed Jun 16 10:57:19 2021 +0200
dlist: use a new OPCODE to avoid loading cold data
Also add a 'bool copy_to_current' param to vbo_save_playback_vertex_list:
this way we can decide if we need to call playback_copy_to_current without
loading any cold data.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=722e39c0080200bbd7f43f7d15ac475fcf919ce9
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Wed Jun 16 10:30:11 2021 +0200
dlist: use a separate opcode for vbo replay using loopback
Remember is the current list needs to fallback to loopback,
and patch the list in glEndList.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=cc57d097bf7e0f2c095be82198cd0b4cac0f224f
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Mon Jun 14 20:41:25 2021 +0200
dlist: split hot/cold data from vertex_list
Store data not used in the hot-path (= vbo_save_playback_vertex_list) in a
pointer, to reduce the size of vbo_save_vertex_list.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=b48998926c92f420553d49594f920eb666a4a6ef
Author: Marek Olšák <marek.olsak at amd.com>
Date: Mon May 17 16:37:15 2021 -0400
util/idalloc: add util_idalloc_alloc_range
v2: fixed infinite loop (Pierre-Eric)
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com> (v1)
Reviewed-by: Marek Olšák <marek.olsak at amd.com> (v2)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=f29823df665ace68cbbad5aae54ae66e73266038
Author: Marek Olšák <marek.olsak at amd.com>
Date: Mon May 17 15:44:50 2021 -0400
util/idalloc: add exists and foreach helpers
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=730014bd8139ddc7b96b0fb99e98b54a007d1bf0
Author: Marek Olšák <marek.olsak at amd.com>
Date: Tue May 18 05:11:41 2021 -0400
util/idalloc: hide or remove unused public functions
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=02f37cb9da36bcc52ff53c81c6609a006e2da877
Author: Marek Olšák <marek.olsak at amd.com>
Date: Mon May 17 15:43:54 2021 -0400
util/idalloc: reserving an ID that already exists should be no-op
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=6ede24cf317550ead4a1a13d38f1c4f7fbf1ad2a
Author: Marek Olšák <marek.olsak at amd.com>
Date: Mon May 17 15:38:34 2021 -0400
util/idalloc: fold the size call into init
It's required, otherwise idalloc would fail.
v2: renamed util_idalloc_(mt_)init param initial_num_ids (Pierre-Eric)
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com> (v1)
Reviewed-by: Marek Olšák <marek.olsak at amd.com> (v2)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=995f6cbd746b90eb6f1023473a20cbba0fe141f4
Author: Marek Olšák <marek.olsak at amd.com>
Date: Mon May 17 15:59:20 2021 -0400
util/idalloc: change num_elements to units of elements instead of bits
and use memset in resize().
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=a266d570def8b431bd724e1af1eb69bbd93a3a21
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Tue Jun 15 18:34:14 2021 +0200
dlist: always use merged primitive for drawing
OpenGL 4.6 compatibility profile spec, Appendix B:
21. For any GL and framebuffer state, and for any group of GL commands and
arguments, the resulting GL and framebuffer state is identical whether the
GL commands and arguments are executed normally or from a display list.
The only exception to this corollary is for built-in shader variables
gl_VertexID and gl_PrimitiveID, which are not defined when drawing
geometry within a display list.
(thanks Ian Romanick for pointing this out in piglit !419 MR)
Remove the code introduced in ebb228bec52a to determine if merged draws can be used.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=b328d8e9bc9900a0372d7c3307f18ad11d708af9
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Tue Jun 15 15:43:57 2021 +0200
dlist: use an union instead of allocating a 1-sized array
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=33fe403ccd1c901b45f114bbfb1e742cc1c67810
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Fri Jun 18 13:08:49 2021 +0200
dlist: unindent code
Use a goto instead of wrapping the main part of the function
in a if() {}
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=0843a7ebabb2305fc229e2b7cd8b214810f6d398
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Tue Jun 15 15:52:14 2021 +0200
dlist: remove InstSize
Instead store the instruction size alongside the opcode.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=c731928cf435ca8a951bd98aef2bd3c39d412026
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Tue Jun 15 12:14:22 2021 +0200
dlist: remove OPCODE_EXT_0
This should have been removed in bb108bdec73 ("dlist: remove ListExt feature")
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=2e9c8d9dc3b12f048b71fbf400b536d11c32e1e3
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Mon Jun 14 21:18:50 2021 +0200
dlist: prelock ctx->Shared->DisplayList before execute_list
Together with the glCallList change this transforms this sequence:
lock - execute - unlock - lock - execute - unlock - ...
In this sequence :
lock - execute - execute - execute - ... - unlock
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=61a1b5463fe6f7f4d30e720da22c74931b13603c
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Mon Jun 14 20:43:50 2021 +0200
dlist: add locked param to _mesa_lookup_list
This allows to take the lock once and reduce the cpu-overhead of
locking/unlocking multiple times when executing multiple lists.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=8b71fcf79526197949ffa20511ccd50ee1ca6685
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Thu Jun 17 21:49:44 2021 +0200
glthread: merge sucessive glCallList
Then unmarshalling a glCallList cmd if the next command(s) are also
glCallList, they are batched in a single glCallLists.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=b0536119f2ef785603ca8fbc59e097f344e0b1fc
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Mon Nov 30 17:32:06 2020 +0100
glthread: use custom marshal/unmarshal for CallList
Will be used in the next commit.
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=7e2d4f505d585dd00827ea912826924214258431
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Thu Jun 17 22:14:13 2021 +0200
glthread: return consumed bytes
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
URL: http://cgit.freedesktop.org/mesa/mesa/commit/?id=9a9860bd11ac9c1e9f6aaeea2b865cf90ad3cf66
Author: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer at amd.com>
Date: Thu Jun 17 21:41:33 2021 +0200
glthread: add a last parameter to unmarshal functions
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11493>
More information about the mesa-commit
mailing list