Elide expand_constructor if move by pieces is preferred

Elide expand_constructor when the constructor is static storage and not
mostly zeros and we can move it by pieces prefer to do so since that's
usually more efficient than performing a series of stores from immediates.

2021-05-21  Richard Biener  <rguenther@suse.de>
	    H.J. Lu  <hjl.tools@gmail.com>

gcc/

	PR middle-end/90773
	* expr.c (expand_constructor): Elide expand_constructor if
	move by pieces is preferred.

gcc/testsuite/

	* gcc.target/i386/pr90773-24.c: New test.
	* gcc.target/i386/pr90773-25.c: Likewise.

diff --git a/gcc/expr.c b/gcc/expr.c
index d09ee42..ba61eb9 100644 (file)
--- a/gcc/expr.c
+++ b/gcc/expr.c
@@ -8523,6 +8523,19 @@ expand_constructor (tree exp, rtx target, enum expand_modifier modifier,
       return constructor;
     }
 
+  /* If the CTOR is available in static storage and not mostly
+     zeros and we can move it by pieces prefer to do so since
+     that's usually more efficient than performing a series of
+     stores from immediates.  */
+  if (avoid_temp_mem
+      && TREE_STATIC (exp)
+      && TREE_CONSTANT (exp)
+      && tree_fits_uhwi_p (TYPE_SIZE_UNIT (type))
+      && can_move_by_pieces (tree_to_uhwi (TYPE_SIZE_UNIT (type)),
+                            TYPE_ALIGN (type))
+      && ! mostly_zeros_p (exp))
+    return NULL_RTX;
+
   /* Handle calls that pass values in multiple non-contiguous
      locations.  The Irix 6 ABI has examples of this.  */
   if (target == 0 || ! safe_from_p (target, exp, 1)

diff --git a/gcc/testsuite/gcc.target/i386/pr90773-24.c b/gcc/testsuite/gcc.target/i386/pr90773-24.c
new file mode 100644 (file)
index 0000000..7b2ea66
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr90773-24.c
@@ -0,0 +1,23 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -march=x86-64" } */
+
+struct S
+{
+  long long s1 __attribute__ ((aligned (8)));
+  unsigned s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14;
+};
+
+const struct S array[] = {
+  { 0, 60, 640, 2112543726, 39682, 48, 16, 33, 10, 96, 2, 0, 0, 4 }
+};
+
+void
+foo (struct S *x)
+{
+  x[0] = array[0];
+}
+
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, 16\\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, 32\\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, 48\\(%\[\^,\]+\\)" 1 } } */

diff --git a/gcc/testsuite/gcc.target/i386/pr90773-25.c b/gcc/testsuite/gcc.target/i386/pr90773-25.c
new file mode 100644 (file)
index 0000000..57642ea
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr90773-25.c
@@ -0,0 +1,25 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -march=x86-64" } */
+
+struct S
+{
+  long long s1 __attribute__ ((aligned (8)));
+  unsigned s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14;
+};
+
+const struct S array[] = {
+  { 0, }
+};
+
+void
+foo (struct S *x)
+{
+  x[0] = array[0];
+}
+
+/* { dg-final { scan-assembler-not "movdqa" } } */
+/* { dg-final { scan-assembler-times "pxor\[\\t \]%xmm\[0-9\]+, %xmm\[0-9\]+" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, 16\\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, 32\\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+, 48\\(%\[\^,\]+\\)" 1 } } */