Previously, the shuffle function had a source/destination overlap that
needs to be avoided to use shuffle_from_32bit_read. As we can use for
the shuffle destination the destination of removed MOVs.
This change also avoids the internal MOVs done by the previous shuffle
to deal with possible overlaps.
---
src/intel/compiler/brw_fs_nir.cpp | 22 ++++++++--------------
1 file changed, 8 insertions(+), 14 deletions(-)
diff --git a/src/intel/compiler/brw_fs_nir.cpp
b/src/intel/compiler/brw_fs_nir.cpp
index fedf3bf5a83..11b707e57a8 100644
--- a/src/intel/compiler/brw_fs_nir.cpp
+++ b/src/intel/compiler/brw_fs_nir.cpp
@@ -2662,13 +2662,10 @@ fs_visitor::nir_emit_tcs_intrinsic(const fs_builder
&bld,
* or SSBOs.
*/
if (type_sz(dst.type) == 8) {
- shuffle_32bit_load_result_to_64bit_data(
- bld, dst, retype(dst, BRW_REGISTER_TYPE_F), num_components);
-
- for (unsigned c = 0; c < num_components; c++) {
- bld.MOV(offset(orig_dst, bld, iter * 2 + c),
- offset(dst, bld, c));
- }
+ shuffle_from_32bit_read(bld,
+ offset(orig_dst, bld, iter * 2),
+ retype(dst, BRW_REGISTER_TYPE_D),
+ 0, num_components);
}
/* Copy the temporary to the destination to deal with writemasking.
@@ -3011,13 +3008,10 @@ fs_visitor::nir_emit_tes_intrinsic(const fs_builder
&bld,
* or SSBOs.
*/
if (type_sz(dest.type) == 8) {
- shuffle_32bit_load_result_to_64bit_data(
- bld, dest, retype(dest, BRW_REGISTER_TYPE_F),
num_components);
-
- for (unsigned c = 0; c < num_components; c++) {
- bld.MOV(offset(orig_dest, bld, iter * 2 + c),
- offset(dest, bld, c));
- }
+ shuffle_from_32bit_read(bld,
+ offset(orig_dest, bld, iter * 2),
+ retype(dest, BRW_REGISTER_TYPE_D),
+ 0, num_components);
}
/* If we are loading double data and we need a second read message
--
2.17.1
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
