diff mbox series

[COMMITTED] i386: Improve memory copy from named address space [PR111657]

Message ID CAFULd4bZgF-8HFxiU18ouCv7SCgSkks2XP2xnwiz=h+WB8AmvQ@mail.gmail.com
State New
Headers show
Series [COMMITTED] i386: Improve memory copy from named address space [PR111657] | expand

Commit Message

Uros Bizjak Oct. 5, 2023, 3:45 p.m. UTC
The stringop strategy selection algorithm falls back to a libcall strategy
when it exhausts its pool of available strategies.  The memory area copy
function (memcpy) is not available from the system library for non-default
address spaces, so the compiler emits the most trivial byte-at-a-time
copy loop instead.

The compiler should instead emit an optimized copy loop as a fallback for
non-default address spaces.

    PR target/111657

gcc/ChangeLog:

    * config/i386/i386-expand.cc (alg_usable_p): Reject libcall
    strategy for non-default address spaces.
    (decide_alg): Use loop strategy as a fallback strategy for
    non-default address spaces.

gcc/testsuite/ChangeLog:

    * gcc.target/i386/pr111657.c: New test.

Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.
diff mbox series

Patch

diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index e42ff27c6ef..9a988347200 100644
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -8320,6 +8320,11 @@  alg_usable_p (enum stringop_alg alg, bool memset, bool have_as)
 {
   if (alg == no_stringop)
     return false;
+  /* It is not possible to use a library call if we have non-default
+     address space.  We can do better than the generic byte-at-a-time
+     loop, used as a fallback.  */
+  if (alg == libcall && have_as)
+    return false;
   if (alg == vector_loop)
     return TARGET_SSE || TARGET_AVX;
   /* Algorithms using the rep prefix want at least edi and ecx;
@@ -8494,8 +8499,12 @@  decide_alg (HOST_WIDE_INT count, HOST_WIDE_INT expected_size,
 	gcc_assert (alg != libcall);
       return alg;
     }
+
+  /* Try to use some reasonable fallback algorithm.  Note that for
+     non-default address spaces we default to a loop instead of
+     a libcall.  */
   return (alg_usable_p (algs->unknown_size, memset, have_as)
-	  ? algs->unknown_size : libcall);
+	  ? algs->unknown_size : have_as ? loop : libcall);
 }
 
 /* Decide on alignment.  We know that the operand is already aligned to ALIGN
diff --git a/gcc/testsuite/gcc.target/i386/pr111657.c b/gcc/testsuite/gcc.target/i386/pr111657.c
new file mode 100644
index 00000000000..fe54fcae8cc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr111657.c
@@ -0,0 +1,9 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-rtl-expand -mno-sse" } */
+
+struct a { long arr[30]; };
+
+__seg_gs struct a m;
+void bar (struct a *dst) { *dst = m; }
+
+/* { dg-final { scan-rtl-dump-not "libcall" "expand" } } */