intel/fs: Fix destination suboffset calculations for non-trivial strides in SHUFFLE...

One of the two SHUFFLE implementations wasn't taking into account the
destination stride at all, and the other (more commonly used) one was
taking it into account incorrectly since brw_reg::hstride represents
the stride logarithmically, so we need to use a left-shift operator
instead of product.  Found by inspection.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14273>

diff --git a/src/intel/compiler/brw_fs_generator.cpp b/src/intel/compiler/brw_fs_generator.cpp
index 2158bba..cfc9657 100644 (file)
--- a/src/intel/compiler/brw_fs_generator.cpp
+++ b/src/intel/compiler/brw_fs_generator.cpp
@@ -631,7 +631,7 @@ fs_generator::generate_shuffle(fs_inst *inst,
           */
          const unsigned i = idx.file == BRW_IMMEDIATE_VALUE ? idx.ud : 0;
          struct brw_reg group_src = stride(suboffset(src, i), 0, 1, 0);
-         struct brw_reg group_dst = suboffset(dst, group);
+         struct brw_reg group_dst = suboffset(dst, group << (dst.hstride - 1));
          if (type_sz(src.type) > 4 && !devinfo->has_64bit_float) {
             brw_MOV(p, subscript(group_dst, BRW_REGISTER_TYPE_UD, 0),
                        subscript(group_src, BRW_REGISTER_TYPE_UD, 0));
@@ -743,7 +743,7 @@ fs_generator::generate_shuffle(fs_inst *inst,
             brw_MOV(p, byte_offset(dst_d, 4),
                     retype(brw_VxH_indirect(0, 4), BRW_REGISTER_TYPE_D));
          } else {
-            brw_MOV(p, suboffset(dst, group * dst.hstride),
+            brw_MOV(p, suboffset(dst, group << (dst.hstride - 1)),
                     retype(brw_VxH_indirect(0, 0), src.type));
          }
       }