aboutsummaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers/radeonsi/si_buffer.c
Commit message (Collapse)AuthorAgeFilesLines
* radeonsi: check ctx->sdma_cs before using itPierre-Eric Pelloux-Prayer2020-01-081-1/+2
| | | | | | | | | | e5167a9276de1f383888714b41d3a9be2b9c1da9 disabled SDMA for gfx8. This caused 3 piglit arb_sparse_buffer tests (basic, buffer-data and commit) to crash on GFX8. Reported-by: Michel Dänzer <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Fixes: e5167a9276d ("radeonsi: disable SDMA on gfx8 to fix corruption on RX 580")
* radeonsi: move SI and CIK+ SDMA code into 1 common function for cleanupsMarek Olšák2020-01-061-3/+3
| | | | | Reviewed-by: Pierre-Eric Pelloux-Prayer <[email protected]> Reviewed-By: Timur Kristóf <[email protected]>
* radeonsi: rename dma_cs -> sdma_csMarek Olšák2020-01-061-9/+9
| | | | | Reviewed-by: Pierre-Eric Pelloux-Prayer <[email protected]> Reviewed-By: Timur Kristóf <[email protected]>
* gallium: add PIPE_RESOURCE_FLAG_SINGLE_THREAD_USE to skip util_range lockMarek Olšák2019-10-071-3/+3
| | | | | | | | | u_upload_mgr sets it, so that util_range_add can skip the lock. The time spent in tc_transfer_flush_region decreases from 0.8% to 0.2% in torcs on radeonsi. Reviewed-by: Kenneth Graunke <[email protected]>
* gallium: use MAP_DIRECTLY to mean supression of DISCARD in buffer_subdataMarek Olšák2019-07-151-5/+6
| | | | | This is needed to fix an issue with OpenGL when a buffer is mapped and BufferSubData is called. In this case, we can't invalidate the buffer range.
* ac: add radeon_info::is_amdgpu instead of checking drm_major == 3Marek Olšák2019-06-141-1/+1
| | | | | | and clean up Reviewed-by: Samuel Pitoiset <[email protected]>
* radeonsi: remove old_va parameter from si_rebind_buffer by remembering offsetsMarek Olšák2019-05-161-5/+2
| | | | | | This is a prerequisite for the next commit. Cc: 19.1 <[email protected]>
* radeonsi: use SDMA for uploading data through const_uploaderMarek Olšák2019-02-201-6/+64
| | | | | | | | v2: use tc.stream_uploader in si buffer_transfer_map if not called from the driver thread Reviewed-by: Nicolai Hähnle <[email protected]> (v1) Tested-by: Dieter Nützel <[email protected]>
* radeonsi: fix EXPLICIT_FLUSH for flush offsets > 0Marek Olšák2019-02-111-2/+5
| | | | | Cc: 18.3 19.0 <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: clear allocator_zeroed_memory with SDMAMarek Olšák2019-02-061-0/+4
| | | | | | | | so that it can be used in parallel IBs. This also removes the SO_FILLED_SIZE hack. Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: rename rbo, rbuffer to buf or bufferMarek Olšák2019-01-221-68/+68
| | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radeonsi: rename rsrc -> ssrc, rdst -> sdstMarek Olšák2019-01-221-16/+16
| | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radeonsi: rename r600_resource -> si_resourceMarek Olšák2019-01-221-24/+24
| | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]>
* radeonsi: use copy_buffer in buffer_do_flush_region directlyMarek Olšák2018-10-161-11/+4
|
* radeonsi: rename r600_transfer -> si_transferMarek Olšák2018-06-251-8/+8
| | | | Reviewed-by: Timothy Arceri <[email protected]>
* radeonsi: rename r600_texture -> si_texture, rxxx -> xxx or sxxxMarek Olšák2018-06-191-2/+2
| | | | Acked-by: Bas Nieuwenhuizen <[email protected]>
* radeonsi: ignore PIPE_RESOURCE_FLAG_MAP_COHERENTMarek Olšák2018-06-191-2/+1
| | | | | | | | We treat coherent and non-coherent buffers the same. And move external_usage for better packing. Tested-by: Dieter Nützel <[email protected]>
* radeonsi: always put persistent buffers into GTT on radeonMarek Olšák2018-06-191-1/+5
| | | | | | | This improves performance for certain games. Cc: 18.1 <[email protected]> Tested-by: Dieter Nützel <[email protected]>
* ac/gpu_info: add kernel_flushes_hdp_before_ibMarek Olšák2018-05-101-4/+2
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: use r600_resource() typecast helperMarek Olšák2018-04-271-7/+13
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: remove r600_pipe_common.hMarek Olšák2018-04-271-0/+1
| | | | Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: don't emit partial flushes for internal CS flushes onlyMarek Olšák2018-04-161-3/+3
| | | | | Tested-by: Benedikt Schemmer <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]>
* radeonsi: remove r600_common_contextMarek Olšák2018-04-051-33/+33
| | | | Acked-by: Timothy Arceri <[email protected]>
* radeonsi: move r600_buffer_common.c and r600_texture.c into radeonsiMarek Olšák2018-04-051-0/+760
| | | | Acked-by: Timothy Arceri <[email protected]>
* radeonsi: move si_upload_const_buffer to a better placeMarek Olšák2014-01-281-63/+0
| | | | | | | This gets rid of another file. Reviewed-by: Michel Dänzer <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* radeonsi: inline si_upload_index_bufferMarek Olšák2014-01-281-7/+0
| | | | | Reviewed-by: Michel Dänzer <[email protected]> Reviewed-by: Tom Stellard <[email protected]>
* radeonsi: Rename the commonly occurring rctx/r600 variables.Andreas Hartmetz2014-01-141-5/+5
| | | | | | The "r" stands for R600. Reviewed-by: Marek Olšák <[email protected]>
* radeonsi: Rename R600->SI in some remaining defines.Andreas Hartmetz2014-01-141-1/+1
| | | | | | I had previously considered that unsafe. Reviewed-by: Marek Olšák <[email protected]>
* radeonsi: Rename r600->si for functions in si_pipe.h.Andreas Hartmetz2014-01-141-2/+2
| | | | Reviewed-by: Marek Olšák <[email protected]>
* radeonsi: Rename r600->si for functions in si_resource.h.Andreas Hartmetz2014-01-141-1/+1
| | | | Reviewed-by: Marek Olšák <[email protected]>
* radeonsi: Rename r600->si for structs in si_pipe.h.Andreas Hartmetz2014-01-141-2/+2
| | | | Reviewed-by: Marek Olšák <[email protected]>
* radeonsi: Apply si_* file naming scheme.Andreas Hartmetz2014-01-141-0/+70
Reviewed-by: Marek Olšák <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-14 19:12:59 +0000