fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-29 16:40:13 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

intel/nir/rt: fixup alignment of memcpy iterations

Browse source 
Not sure if fixes anything because it's always 16 at least, but this
is more correct.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17396>
This commit is contained in:
Lionel Landwerlin 2022-07-20 17:01:21 +03:00 • committed by Marge Bot
parent 139e8f4635
commit e76e3d9cea
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
src/intel/compiler/brw_nir_rt_builder.h
View file

@ -459,9 +459,9 @@ brw_nir_memcpy_global(nir_builder *b,
for (unsigned offset = 0; offset < size; offset += 16) {
nir_ssa_def *data =
brw_nir_rt_load(b, nir_iadd_imm(b, src_addr, offset), src_align,
brw_nir_rt_load(b, nir_iadd_imm(b, src_addr, offset), 16,
4, 32);
brw_nir_rt_store(b, nir_iadd_imm(b, dst_addr, offset), dst_align,
brw_nir_rt_store(b, nir_iadd_imm(b, dst_addr, offset), 16,
data, 0xf /* write_mask */);
}
}