intel/fs: shuffle_from_32bit_read for 64-bit do_untyped_vector_read

do_untyped_vector_read is used at load_ssbo and load_shared.

The previous MOVs are removed because shuffle_from_32bit_read
can handle storing the shuffle results in the expected destination
just using the proper offset.

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>

diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp
index 01c560e59f8eeb8e844d5fec3e94deaa4e336059..81c26321ed2108c90e23d7256543e319602018ba 100644 (file)
--- a/src/intel/compiler/brw_fs_nir.cpp
+++ b/src/intel/compiler/brw_fs_nir.cpp
@@ -2434,16 +2434,8 @@ do_untyped_vector_read(const fs_builder &bld,
                                                 BRW_PREDICATE_NONE);
 
          /* Shuffle the 32-bit load result into valid 64-bit data */
-         const fs_reg packed_result = bld.vgrf(dest.type, iter_components);
-         shuffle_32bit_load_result_to_64bit_data(
-            bld, packed_result, read_result, iter_components);
-
-         /* Move each component to its destination */
-         read_result = retype(read_result, BRW_REGISTER_TYPE_DF);
-         for (int c = 0; c < iter_components; c++) {
-            bld.MOV(offset(dest, bld, it * 2 + c),
-                    offset(packed_result, bld, c));
-         }
+         shuffle_from_32bit_read(bld, offset(dest, bld, it * 2),
+                                 read_result, 0, iter_components);
 
          bld.ADD(read_offset, read_offset, brw_imm_ud(16));
       }