mesa/src
Karol Herbst 6e89dc33fe nak/cmat: add optimisation to cmat load/store to do 32-bit load for f16vec2
Initial idea and code from Dave, but this is a complete rewrite of the
patch.

The Matrix layouts contain groups of values, for int8 we have vec4 groups,
for fp16, fp32 and int32 we have vec2s. With this we load and store them
as vectors getting rid of a bunch of address calculation.

Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37998>
2025-11-26 14:09:35 +00:00
..
amd radv: Check RADV_PERFTEST=sparse for image formats and sparse queue 2025-11-26 13:12:27 +00:00
android_stub
asahi poly: Make all heap allocations atomic 2025-11-25 23:20:28 +00:00
broadcom broadcom/compiler: use nir_opt_uub 2025-11-26 13:32:39 +00:00
c11 c11/threads: fix build on c23 2025-11-10 07:01:50 +10:00
compiler nir/lower_wrmasks: clean up & deprecate pass 2025-11-26 03:20:39 +00:00
drm-shim drm-shim: handle DRM_CAP_ADDFB2_MODIFIERS 2025-11-24 12:34:08 +00:00
egl egl: Disable kopper on Android 2025-11-25 10:04:51 +00:00
etnaviv ci: use $CI_TRON_JOB_PRIORITY tag on all ci-tron jobs 2025-11-24 12:02:40 +00:00
freedreno nir/lower_wrmasks: drop callback 2025-11-26 03:20:39 +00:00
gallium broadcom/compiler: enable umul24 and imul24 ALU opcodes 2025-11-26 13:32:39 +00:00
gbm mesa: replace most occurrences of getenv() with os_get_option() 2025-11-06 04:36:13 +00:00
getopt
gfxstream gfxstream: codegen: don't generate custom protocols in function table 2025-11-25 09:12:15 -08:00
glx apple_cgl.c: Fix error: call to undeclared function 'os_get_option' 2025-11-20 18:39:19 +00:00
gtest
imagination pvr: fix cleaning up failed CreateDevice 2025-11-26 08:52:27 +00:00
imgui imgui: Silence build warnings for imgui 2025-09-16 06:16:19 +00:00
intel brw: Combine output stores for TCS outputs even when unlinked 2025-11-25 22:44:03 +00:00
kosmickrisp kk: Handle memory coherency for textures and buffers 2025-11-26 02:26:21 +00:00
loader loader: Wrap nouveau_zink_predicate with HAVE_LIBDRM 2025-11-20 18:39:19 +00:00
mesa nir: rename nir_lower_indirect_derefs -> nir_lower_indirect_derefs_to_if_else_trees 2025-11-20 05:42:11 +00:00
microsoft vulkan: Optionally share one JSON manifest per driver between architectures 2025-11-24 19:05:57 +00:00
nouveau nak/cmat: add optimisation to cmat load/store to do 32-bit load for f16vec2 2025-11-26 14:09:35 +00:00
panfrost panfrost/ci: remove some out-of-date xfails 2025-11-26 12:55:41 +01:00
poly poly: Make all heap allocations atomic 2025-11-25 23:20:28 +00:00
tool pps/meson: minor refactor for pps_deps 2025-11-08 18:39:00 -08:00
util radv: add radv_hide_rebar_on_dgpu and enable for Red Dead Redemption 2 2025-11-26 10:12:45 +00:00
virtio vulkan: Optionally share one JSON manifest per driver between architectures 2025-11-24 19:05:57 +00:00
vulkan vulkan/wsi: Handle 0xFFFFFFFF special case in vk_wsi_force_swapchain_to_current_extent driconf 2025-11-25 22:10:38 +00:00
x11 treewide: strip unneeded inc_gallium inc_gallium_aux 2025-11-13 22:01:43 +00:00
.clang-format util: Add sparse bitset data structure 2025-11-06 21:34:33 +00:00
meson.build kk: Add KosmicKrisp 2025-10-20 17:46:38 +00:00