This option (CPUCFG word 0x3 bit 23) means "the hardware guarantee that
two loads on the same address won't be reordered with each other".  Thus
we can omit the "load-load" barrier dbar 0x700.

This is only a micro-optimization because dbar 0x700 is already treated
as nop if the hardware supports LD_SEQ_SA.

gcc/ChangeLog:

        * config/loongarch/loongarch.cc (loongarch_print_operand): Don't
        print dbar 0x700 if TARGET_LD_SEQ_SA.
        * config/loongarch/sync.md (atomic_load<mode>): Likewise.
---
 gcc/config/loongarch/loongarch.cc | 2 +-
 gcc/config/loongarch/sync.md      | 9 +++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/gcc/config/loongarch/loongarch.cc 
b/gcc/config/loongarch/loongarch.cc
index b4bb2b6eeb5..5d3282c5e93 100644
--- a/gcc/config/loongarch/loongarch.cc
+++ b/gcc/config/loongarch/loongarch.cc
@@ -6057,7 +6057,7 @@ loongarch_print_operand (FILE *file, rtx op, int letter)
       if (loongarch_cas_failure_memorder_needs_acquire (
            memmodel_from_int (INTVAL (op))))
        fputs ("dbar\t0b10100", file);
-      else
+      else if (!TARGET_LD_SEQ_SA)
        fputs ("dbar\t0x700", file);
       break;
 
diff --git a/gcc/config/loongarch/sync.md b/gcc/config/loongarch/sync.md
index 67848d72b87..ce3ce89a61d 100644
--- a/gcc/config/loongarch/sync.md
+++ b/gcc/config/loongarch/sync.md
@@ -119,13 +119,14 @@ (define_insn "atomic_load<mode>"
     case MEMMODEL_SEQ_CST:
       return "dbar\t0x11\\n\\t"
             "ld.<size>\t%0,%1\\n\\t"
-            "dbar\t0x14\\n\\t";
+            "dbar\t0x14";
     case MEMMODEL_ACQUIRE:
       return "ld.<size>\t%0,%1\\n\\t"
-            "dbar\t0x14\\n\\t";
+            "dbar\t0x14";
     case MEMMODEL_RELAXED:
-      return "ld.<size>\t%0,%1\\n\\t"
-            "dbar\t0x700\\n\\t";
+      return TARGET_LD_SEQ_SA ? "ld.<size>\t%0,%1\\n\\t"
+                             : "ld.<size>\t%0,%1\\n\\t"
+                               "dbar\t0x700";
 
     default:
       /* The valid memory order variants are __ATOMIC_RELAXED, 
__ATOMIC_SEQ_CST,
-- 
2.42.1

Reply via email to