intel/fs: Fix MOV_INDIRECT and BROADCAST of Q types on Gen11+

The immediate case is pretty uncommon to see but it can happen, in
theory.  BROADCAST is typically used to uniformize values and those are
usually 32-bit.  However, it does come up in some subgroup ops.

Fixes: 49c21802cbca "intel/compiler: Split has_64bit_types into float/int"
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6211>

diff --git a/src/intel/compiler/brw_eu_emit.c b/src/intel/compiler/brw_eu_emit.c
index 0d5c755f9e8d36e9ee1b7db70af4b2b63fc9aed6..08d64800f7a8070b85636e858871f97c136fba5d 100644 (file)
--- a/src/intel/compiler/brw_eu_emit.c
+++ b/src/intel/compiler/brw_eu_emit.c
@@ -3361,9 +3361,18 @@ brw_broadcast(struct brw_codegen *p,
        * asserting would be mean.
        */
       const unsigned i = idx.file == BRW_IMMEDIATE_VALUE ? idx.ud : 0;
-      brw_MOV(p, dst,
-              (align1 ? stride(suboffset(src, i), 0, 1, 0) :
-               stride(suboffset(src, 4 * i), 0, 4, 1)));
+      src = align1 ? stride(suboffset(src, i), 0, 1, 0) :
+                     stride(suboffset(src, 4 * i), 0, 4, 1);
+
+      if (type_sz(src.type) > 4 && !devinfo->has_64bit_float) {
+         brw_MOV(p, subscript(dst, BRW_REGISTER_TYPE_D, 0),
+                    subscript(src, BRW_REGISTER_TYPE_D, 0));
+         brw_set_default_swsb(p, tgl_swsb_null());
+         brw_MOV(p, subscript(dst, BRW_REGISTER_TYPE_D, 1),
+                    subscript(src, BRW_REGISTER_TYPE_D, 1));
+      } else {
+         brw_MOV(p, dst, src);
+      }
    } else {
       /* From the Haswell PRM section "Register Region Restrictions":
        *
@@ -3412,7 +3421,8 @@ brw_broadcast(struct brw_codegen *p,
 
          /* Use indirect addressing to fetch the specified component. */
          if (type_sz(src.type) > 4 &&
-             (devinfo->is_cherryview || gen_device_info_is_9lp(devinfo))) {
+             (devinfo->is_cherryview || gen_device_info_is_9lp(devinfo) ||
+              !devinfo->has_64bit_float)) {
             /* From the Cherryview PRM Vol 7. "Register Region Restrictions":
              *
              *    "When source or destination datatype is 64b or operation is

diff --git a/src/intel/compiler/brw_fs_generator.cpp b/src/intel/compiler/brw_fs_generator.cpp
index bee9816d8159bd8802701d37df973aee60bc6355..5b1f28950bf31afaa4d3e96cbd7da42f425ab89c 100644 (file)
--- a/src/intel/compiler/brw_fs_generator.cpp
+++ b/src/intel/compiler/brw_fs_generator.cpp
@@ -468,7 +468,15 @@ fs_generator::generate_mov_indirect(fs_inst *inst,
 
       reg.nr = imm_byte_offset / REG_SIZE;
       reg.subnr = imm_byte_offset % REG_SIZE;
-      brw_MOV(p, dst, reg);
+      if (type_sz(reg.type) > 4 && !devinfo->has_64bit_float) {
+         brw_MOV(p, subscript(dst, BRW_REGISTER_TYPE_D, 0),
+                    subscript(reg, BRW_REGISTER_TYPE_D, 0));
+         brw_set_default_swsb(p, tgl_swsb_null());
+         brw_MOV(p, subscript(dst, BRW_REGISTER_TYPE_D, 1),
+                    subscript(reg, BRW_REGISTER_TYPE_D, 1));
+      } else {
+         brw_MOV(p, dst, reg);
+      }
    } else {
       /* Prior to Broadwell, there are only 8 address registers. */
       assert(inst->exec_size <= 8 || devinfo->gen >= 8);