With later changes to RDFFR to use subregisters we see forward prop
begin to duplicate FFR reads. This change prevents that.

gcc/ChangeLog:

        * config/aarch64/aarch64.cc (aarch64_insn_cost): Add extra costs
        for FFR reads/writes.
---
 gcc/config/aarch64/aarch64.cc | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 3041a6ee62a..e7522e49efd 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -16989,8 +16989,16 @@ aarch64_frame_allocation_cost (frame_cost_type,
 static int
 aarch64_insn_cost (rtx_insn *insn, bool speed)
 {
+  int extra_cost = 0;
+
+  /* Reads and sets to FFR are expensive. Mark them as such to prevent
+     duplication.  */
+  if (recog_memoized (insn) != -1
+      && get_attr_sve_type (insn) == SVE_TYPE_SVE_FFR)
+    extra_cost = 100;
+
   if (rtx set = single_set (insn))
-    return set_rtx_cost (set, speed);
+    return set_rtx_cost (set, speed) + extra_cost;
 
   /* If the instruction does multiple sets in parallel, use the cost
      of the most expensive set.  This copes with instructions that set
@@ -17005,10 +17013,10 @@ aarch64_insn_cost (rtx_insn *insn, bool speed)
          if (GET_CODE (x) == SET)
            max_cost = std::max (max_cost, set_rtx_cost (x, speed));
        }
-      return max_cost;
+      return max_cost + extra_cost;
     }
 
-  return pattern_cost (pat, speed);
+  return pattern_cost (pat, speed) + extra_cost;
 }
 
 /* Implement TARGET_INIT_BUILTINS.  */
-- 
2.43.0

Reply via email to