fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-25 16:58:10 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
mesa/src/gallium/drivers
History
Alyssa Rosenzweig 07cb81f0fc asahi: Skip LOD bias lowering for GLES 
This reduces silliness in Dolphin ubershaders by eliminating the double
lowering. It also makes the GLES shader assembly nicer to read.

Dolphin ubershader performance at 4K on MMG improved by about 0.5%. Not massive,
but definitely noticeable and reduces the delta to macOS.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
2023-09-05 18:50:35 +00:00
..
asahi asahi: Skip LOD bias lowering for GLES 2023-09-05 18:50:35 +00:00
crocus crocus: fix GFX_VERx10 macro 2023-09-03 03:04:26 +00:00
d3d12 treewide: Use nir_before/after_impl in easy cases 2023-08-30 19:30:58 +00:00
etnaviv nir: unify lower_find_msb with has_{find_msb_rev,uclz} 2023-08-22 12:08:37 +00:00
freedreno freedreno/fdl: Set LOSSLESSCOMPEN for image when ubwc is enabled on a7xx 2023-09-05 16:19:30 +00:00
i915 nir: unify lower_bitfield_extract with has_bfe 2023-08-22 12:08:37 +00:00
iris intel/measure: track batch buffer sizes 2023-09-05 11:50:02 +00:00
lima nir: Drop most uses if nir_instr_rewrite_src() 2023-08-18 01:00:15 +00:00
llvmpipe llvmpipe/cs: further cleanups after tgsi removal. 2023-09-05 07:14:27 +00:00
nouveau nv50: Remove unused value 2023-08-26 12:17:21 -07:00
panfrost treewide: Use nir_shader_intrinsic_pass sometimes 2023-08-24 15:48:02 +00:00
r300 r300: use w channel for scalar opcodes if possible 2023-09-04 16:13:43 +00:00
r600 treewide: Use nir_shader_intrinsic_pass sometimes 2023-08-24 15:48:02 +00:00
radeonsi radeonsi/vcn: fix the incorrect dt_size 2023-09-04 22:04:58 +00:00
softpipe gallium: remove start_slot parameter from pipe_context::set_vertex_buffers 2023-08-11 06:37:22 +00:00
svga svga: fix stride used in vertex declaration 2023-08-23 09:37:38 -07:00
tegra gallium: remove start_slot parameter from pipe_context::set_vertex_buffers 2023-08-11 06:37:22 +00:00
v3d v3d,v3dv: use fquantize2f16 lowering in NIR 2023-08-30 06:26:35 +00:00
vc4 treewide: Use nir_before/after_impl for more elaborate cases 2023-08-30 19:30:58 +00:00
virgl virgl: Do not expose EXT_texture_mirror_clamp when using a GLES host 2023-08-30 12:57:58 +00:00
zink zink: fix linear modifier dmabuf imports 2023-09-05 04:58:36 +00:00