Optimize -mstackrealign.

gcc/

2009-10-30  H.J. Lu  <hongjiu.lu@intel.com>

	PR target/40836
	* cfgexpand.c (expand_stack_alignment): Call update_stack_boundary
	first.  Move assert on stack_alignment_estimated just before
	setting stack_realign_needed.
	(gimple_expand_cfg): Initialize stack_alignment_estimated to 0.
	Don't call update_stack_boundary.

	* config/i386/i386.c (ix86_minimum_incoming_stack_boundary): New.
	(verride_options): Don't check ix86_force_align_arg_pointer here.
	(ix86_function_ok_for_sibcall): Use it.
	(ix86_update_stack_boundary): Likewise.

	* config/i386/i386.h (STACK_REALIGN_DEFAULT): Update comments.

gcc/testsuite/

2009-10-30  H.J. Lu  <hongjiu.lu@intel.com>

	PR target/40838
	* gcc.target/i386/incoming-6.c: New.
	* gcc.target/i386/incoming-7.c: Likewise.
	* gcc.target/i386/incoming-8.c: Likewise.
	* gcc.target/i386/incoming-9.c: Likewise.
	* gcc.target/i386/incoming-10.c: Likewise.
	* gcc.target/i386/incoming-11.c: Likewise.
	* gcc.target/i386/incoming-12.c: Likewise.
	* gcc.target/i386/incoming-13.c: Likewise.
	* gcc.target/i386/incoming-14.c: Likewise.
	* gcc.target/i386/incoming-15.c: Likewise.
	* gcc.target/i386/pr37843-4.c: Likewise.

From-SVN: r153750

16 files changed, 274 insertions, 44 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index c060b6f..af36bc6 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,19 @@
+2009-10-30  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR target/40836
+	* cfgexpand.c (expand_stack_alignment): Call update_stack_boundary
+	first.  Move assert on stack_alignment_estimated just before
+	setting stack_realign_needed.
+	(gimple_expand_cfg): Initialize stack_alignment_estimated to 0.
+	Don't call update_stack_boundary.
+
+	* config/i386/i386.c (ix86_minimum_incoming_stack_boundary): New.
+	(verride_options): Don't check ix86_force_align_arg_pointer here.
+	(ix86_function_ok_for_sibcall): Use it.
+	(ix86_update_stack_boundary): Likewise.
+
+	* config/i386/i386.h (STACK_REALIGN_DEFAULT): Update comments.
+
 2009-10-30  Richard Earnshaw  <rearnsha@arm.com>
 
 	* arm.md (QHSI): New mode iterator.
@@ -13,9 +29,9 @@
 	PR debug/41700
 	* dwarf2out.c (dwarf2_debug_hooks): Add entries for new hook (two
 	locations in the source).
-        (store_vcall_insn): New function.
-        (lookup_vcall_insn): New function.
-        (dwarf2out_virtual_call_token): Use store_vcall_insn.
+	(store_vcall_insn): New function.
+	(lookup_vcall_insn): New function.
+	(dwarf2out_virtual_call_token): Use store_vcall_insn.
 	(dwarf2out_copy_call_info): New function.
 	(dwarf2out_virtual_call): Use lookup_vcall_insn.
 	* emit-rtl.c (try_split): Call copy_call_info debug hook.
diff --git a/gcc/cfgexpand.c b/gcc/cfgexpand.c
index fdc4de5..33e7579 100644
--- a/gcc/cfgexpand.c
+++ b/gcc/cfgexpand.c
@@ -3447,8 +3447,18 @@ expand_stack_alignment (void)
       || crtl->has_nonlocal_goto)
     crtl->need_drap = true;
 
-  gcc_assert (crtl->stack_alignment_needed
-	      <= crtl->stack_alignment_estimated);
+  /* Call update_stack_boundary here again to update incoming stack
+     boundary.  It may set incoming stack alignment to a different
+     value after RTL expansion.  TARGET_FUNCTION_OK_FOR_SIBCALL may
+     use the minimum incoming stack alignment to check if it is OK
+     to perform sibcall optimization since sibcall optimization will
+     only align the outgoing stack to incoming stack boundary.  */
+  if (targetm.calls.update_stack_boundary)
+    targetm.calls.update_stack_boundary ();
+
+  /* The incoming stack frame has to be aligned at least at
+     parm_stack_boundary.  */
+  gcc_assert (crtl->parm_stack_boundary <= INCOMING_STACK_BOUNDARY);
 
   /* Update crtl->stack_alignment_estimated and use it later to align
      stack.  We check PREFERRED_STACK_BOUNDARY if there may be non-call
@@ -3464,6 +3474,9 @@ expand_stack_alignment (void)
   if (preferred_stack_boundary > crtl->stack_alignment_needed)
     crtl->stack_alignment_needed = preferred_stack_boundary;
 
+  gcc_assert (crtl->stack_alignment_needed
+	      <= crtl->stack_alignment_estimated);
+
   crtl->stack_realign_needed
     = INCOMING_STACK_BOUNDARY < crtl->stack_alignment_estimated;
   crtl->stack_realign_tried = crtl->stack_realign_needed;
@@ -3540,7 +3553,7 @@ gimple_expand_cfg (void)
   targetm.expand_to_rtl_hook ();
   crtl->stack_alignment_needed = STACK_BOUNDARY;
   crtl->max_used_stack_slot_alignment = STACK_BOUNDARY;
-  crtl->stack_alignment_estimated = STACK_BOUNDARY;
+  crtl->stack_alignment_estimated = 0;
   crtl->preferred_stack_boundary = STACK_BOUNDARY;
   cfun->cfg->max_jumptable_ents = 0;
 
@@ -3604,23 +3617,6 @@ gimple_expand_cfg (void)
   if (crtl->stack_protect_guard)
     stack_protect_prologue ();
 
-  /* Update stack boundary if needed.  */
-  if (SUPPORTS_STACK_ALIGNMENT)
-    {
-      /* Call update_stack_boundary here to update incoming stack
-	 boundary before TARGET_FUNCTION_OK_FOR_SIBCALL is called.
-	 TARGET_FUNCTION_OK_FOR_SIBCALL needs to know the accurate
-	 incoming stack alignment to check if it is OK to perform
-	 sibcall optimization since sibcall optimization will only
-	 align the outgoing stack to incoming stack boundary.  */
-      if (targetm.calls.update_stack_boundary)
-	targetm.calls.update_stack_boundary ();
-      
-      /* The incoming stack frame has to be aligned at least at
-	 parm_stack_boundary.  */
-      gcc_assert (crtl->parm_stack_boundary <= INCOMING_STACK_BOUNDARY);
-    }
-
   expand_phi_nodes (&SA);
 
   /* Register rtl specific functions for cfg.  */
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 349df7a..5d6eb0f 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -1905,6 +1905,7 @@ static bool ix86_valid_target_attribute_p (tree, tree, tree, int);
 static bool ix86_valid_target_attribute_inner_p (tree, char *[]);
 static bool ix86_can_inline_p (tree, tree);
 static void ix86_set_current_function (tree);
+static unsigned int ix86_minimum_incoming_stack_boundary (bool);
 
 static enum calling_abi ix86_function_abi (const_tree);
 
@@ -3239,12 +3240,10 @@ override_options (bool main_args_p)
   if (ix86_force_align_arg_pointer == -1)
     ix86_force_align_arg_pointer = STACK_REALIGN_DEFAULT;
 
+  ix86_default_incoming_stack_boundary = PREFERRED_STACK_BOUNDARY;
+
   /* Validate -mincoming-stack-boundary= value or default it to
      MIN_STACK_BOUNDARY/PREFERRED_STACK_BOUNDARY.  */
-  if (ix86_force_align_arg_pointer)
-    ix86_default_incoming_stack_boundary = MIN_STACK_BOUNDARY;
-  else
-    ix86_default_incoming_stack_boundary = PREFERRED_STACK_BOUNDARY;
   ix86_incoming_stack_boundary = ix86_default_incoming_stack_boundary;
   if (ix86_incoming_stack_boundary_string)
     {
@@ -4277,7 +4276,8 @@ ix86_function_ok_for_sibcall (tree decl, tree exp)
 
   /* If we need to align the outgoing stack, then sibcalling would
      unalign the stack, which may break the called function.  */
-  if (ix86_incoming_stack_boundary < PREFERRED_STACK_BOUNDARY)
+  if (ix86_minimum_incoming_stack_boundary (true)
+      < PREFERRED_STACK_BOUNDARY)
     return false;
 
   if (decl)
@@ -8196,37 +8196,58 @@ find_drap_reg (void)
     }
 }
 
-/* Update incoming stack boundary and estimated stack alignment.  */
+/* Return minimum incoming stack alignment.  */
 
-static void
-ix86_update_stack_boundary (void)
+static unsigned int
+ix86_minimum_incoming_stack_boundary (bool sibcall)
 {
+  unsigned int incoming_stack_boundary;
+
   /* Prefer the one specified at command line. */
-  ix86_incoming_stack_boundary 
-    = (ix86_user_incoming_stack_boundary
-       ? ix86_user_incoming_stack_boundary
-       : ix86_default_incoming_stack_boundary);
+  if (ix86_user_incoming_stack_boundary)
+    incoming_stack_boundary = ix86_user_incoming_stack_boundary;
+  /* In 32bit, use MIN_STACK_BOUNDARY for incoming stack boundary
+     if -mstackrealign is used, it isn't used for sibcall check and 
+     estimated stack alignment is 128bit.  */
+  else if (!sibcall
+	   && !TARGET_64BIT
+	   && ix86_force_align_arg_pointer
+	   && crtl->stack_alignment_estimated == 128)
+    incoming_stack_boundary = MIN_STACK_BOUNDARY;
+  else
+    incoming_stack_boundary = ix86_default_incoming_stack_boundary;
 
   /* Incoming stack alignment can be changed on individual functions
      via force_align_arg_pointer attribute.  We use the smallest
      incoming stack boundary.  */
-  if (ix86_incoming_stack_boundary > MIN_STACK_BOUNDARY
+  if (incoming_stack_boundary > MIN_STACK_BOUNDARY
       && lookup_attribute (ix86_force_align_arg_pointer_string,
 			   TYPE_ATTRIBUTES (TREE_TYPE (current_function_decl))))
-    ix86_incoming_stack_boundary = MIN_STACK_BOUNDARY;
+    incoming_stack_boundary = MIN_STACK_BOUNDARY;
 
   /* The incoming stack frame has to be aligned at least at
      parm_stack_boundary.  */
-  if (ix86_incoming_stack_boundary < crtl->parm_stack_boundary)
-    ix86_incoming_stack_boundary = crtl->parm_stack_boundary;
+  if (incoming_stack_boundary < crtl->parm_stack_boundary)
+    incoming_stack_boundary = crtl->parm_stack_boundary;
 
   /* Stack at entrance of main is aligned by runtime.  We use the
      smallest incoming stack boundary. */
-  if (ix86_incoming_stack_boundary > MAIN_STACK_BOUNDARY
+  if (incoming_stack_boundary > MAIN_STACK_BOUNDARY
       && DECL_NAME (current_function_decl)
       && MAIN_NAME_P (DECL_NAME (current_function_decl))
       && DECL_FILE_SCOPE_P (current_function_decl))
-    ix86_incoming_stack_boundary = MAIN_STACK_BOUNDARY;
+    incoming_stack_boundary = MAIN_STACK_BOUNDARY;
+
+  return incoming_stack_boundary;
+}
+
+/* Update incoming stack boundary and estimated stack alignment.  */
+
+static void
+ix86_update_stack_boundary (void)
+{
+  ix86_incoming_stack_boundary
+    = ix86_minimum_incoming_stack_boundary (false);
 
   /* x86_64 vararg needs 16byte stack alignment for register save
      area.  */
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 33a5077..22187a9 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -706,9 +706,7 @@ enum target_cpu_default
    generate an alternate prologue and epilogue that realigns the
    runtime stack if nessary.  This supports mixing codes that keep a
    4-byte aligned stack, as specified by i386 psABI, with codes that
-   need a 16-byte aligned stack, as required by SSE instructions.  If
-   STACK_REALIGN_DEFAULT is 1 and PREFERRED_STACK_BOUNDARY_DEFAULT is
-   128, stacks for all functions may be realigned.  */
+   need a 16-byte aligned stack, as required by SSE instructions.  */
 #define STACK_REALIGN_DEFAULT 0
 
 /* Boundary (in *bits*) on which the incoming stack is aligned.  */
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 0df4a2f..29676c6 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,18 @@
+2009-10-30  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR target/40838
+	* gcc.target/i386/incoming-6.c: New.
+	* gcc.target/i386/incoming-7.c: Likewise.
+	* gcc.target/i386/incoming-8.c: Likewise.
+	* gcc.target/i386/incoming-9.c: Likewise.
+	* gcc.target/i386/incoming-10.c: Likewise.
+	* gcc.target/i386/incoming-11.c: Likewise.
+	* gcc.target/i386/incoming-12.c: Likewise.
+	* gcc.target/i386/incoming-13.c: Likewise.
+	* gcc.target/i386/incoming-14.c: Likewise.
+	* gcc.target/i386/incoming-15.c: Likewise.
+	* gcc.target/i386/pr37843-4.c: Likewise.
+
 2009-10-30  Dodji Seketeli  <dodji@redhat.com>
 
 	PR c++/41863
diff --git a/gcc/testsuite/gcc.target/i386/incoming-10.c b/gcc/testsuite/gcc.target/i386/incoming-10.c
new file mode 100644
index 0000000..31d9e61
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/incoming-10.c
@@ -0,0 +1,19 @@
+/* PR target/40838 */
+/* { dg-do compile { target { { ! *-*-darwin* } && ilp32 } } } */
+/* { dg-options "-w -mstackrealign -fomit-frame-pointer -O3 -march=barcelona -mpreferred-stack-boundary=4" } */
+
+struct s {
+	int x[8];
+};
+
+void g(struct s *);
+
+void f()
+{
+	int i;
+	struct s s;
+	for (i = 0; i < sizeof(s.x) / sizeof(*s.x); i++) s.x[i] = 0;
+	g(&s);
+}
+
+/* { dg-final { scan-assembler "andl\[\\t \]*\\$-16,\[\\t \]*%esp" } } */
diff --git a/gcc/testsuite/gcc.target/i386/incoming-11.c b/gcc/testsuite/gcc.target/i386/incoming-11.c
new file mode 100644
index 0000000..e5787af
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/incoming-11.c
@@ -0,0 +1,18 @@
+/* PR target/40838 */
+/* { dg-do compile { target { { ! *-*-darwin* } && ilp32 } } } */
+/* { dg-options "-w -mstackrealign -fomit-frame-pointer -O3 -march=barcelona -mpreferred-stack-boundary=4" } */
+
+void g();
+
+int p[100];
+int q[100];
+
+void f()
+{
+	int i;
+	for (i = 0; i < 100; i++) p[i] = 0;
+	g();
+	for (i = 0; i < 100; i++) q[i] = 0;
+}
+
+/* { dg-final { scan-assembler "andl\[\\t \]*\\$-16,\[\\t \]*%esp" } } */
diff --git a/gcc/testsuite/gcc.target/i386/incoming-12.c b/gcc/testsuite/gcc.target/i386/incoming-12.c
new file mode 100644
index 0000000..d7ef103
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/incoming-12.c
@@ -0,0 +1,20 @@
+/* PR target/40838 */
+/* { dg-do compile { target { { ! *-*-darwin* } && ilp32 } } } */
+/* { dg-options "-w -mstackrealign -O2 -msse2 -mpreferred-stack-boundary=4" } */
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+struct x {
+       v4si v;
+       v4si w;
+};
+
+void y(void *);
+
+v4si x(void)
+{
+       struct x x;
+       y(&x);
+}
+
+/* { dg-final { scan-assembler "andl\[\\t \]*\\$-16,\[\\t \]*%esp" } } */
diff --git a/gcc/testsuite/gcc.target/i386/incoming-13.c b/gcc/testsuite/gcc.target/i386/incoming-13.c
new file mode 100644
index 0000000..bbc8993
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/incoming-13.c
@@ -0,0 +1,15 @@
+/* PR target/40838 */
+/* { dg-do compile { target { { ! *-*-darwin* } && ilp32 } } } */
+/* { dg-options "-w -mstackrealign -O2 -mpreferred-stack-boundary=4" } */
+
+extern double y(double *s3);
+
+extern double s1, s2;
+
+double x(void)
+{
+  double s3 = s1 + s2;
+  return y(&s3);
+}
+
+/* { dg-final { scan-assembler-not "andl\[\\t \]*\\$-16,\[\\t \]*%esp" } } */
diff --git a/gcc/testsuite/gcc.target/i386/incoming-14.c b/gcc/testsuite/gcc.target/i386/incoming-14.c
new file mode 100644
index 0000000..d27179d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/incoming-14.c
@@ -0,0 +1,15 @@
+/* PR target/40838 */
+/* { dg-do compile { target { { ! *-*-darwin* } && ilp32 } } } */
+/* { dg-options "-w -mstackrealign -O2 -mpreferred-stack-boundary=4" } */
+
+extern int y(int *s3);
+
+extern int s1, s2;
+
+int x(void)
+{
+  int s3 = s1 + s2;
+  return y(&s3);
+}
+
+/* { dg-final { scan-assembler-not "andl\[\\t \]*\\$-16,\[\\t \]*%esp" } } */
diff --git a/gcc/testsuite/gcc.target/i386/incoming-15.c b/gcc/testsuite/gcc.target/i386/incoming-15.c
new file mode 100644
index 0000000..e6a1749
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/incoming-15.c
@@ -0,0 +1,15 @@
+/* PR target/40838 */
+/* { dg-do compile { target { { ! *-*-darwin* } && ilp32 } } } */
+/* { dg-options "-w -mstackrealign -O2 -mpreferred-stack-boundary=4" } */
+
+extern long long y(long long *s3);
+
+extern long long s1, s2;
+
+long long x(void)
+{
+  long long s3 = s1 + s2;
+  return y(&s3);
+}
+
+/* { dg-final { scan-assembler-not "andl\[\\t \]*\\$-16,\[\\t \]*%esp" } } */
diff --git a/gcc/testsuite/gcc.target/i386/incoming-6.c b/gcc/testsuite/gcc.target/i386/incoming-6.c
new file mode 100644
index 0000000..5cc4ab3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/incoming-6.c
@@ -0,0 +1,17 @@
+/* PR target/40838 */
+/* { dg-do compile { target { { ! *-*-darwin* } && ilp32 } } } */
+/* { dg-options "-w -mstackrealign -O2 -msse2 -mpreferred-stack-boundary=4" } */
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+extern v4si y(v4si *s3);
+
+extern v4si s1, s2;
+
+v4si x(void)
+{
+  v4si s3 = s1 + s2;
+  return y(&s3);
+}
+
+/* { dg-final { scan-assembler "andl\[\\t \]*\\$-16,\[\\t \]*%esp" } } */
diff --git a/gcc/testsuite/gcc.target/i386/incoming-7.c b/gcc/testsuite/gcc.target/i386/incoming-7.c
new file mode 100644
index 0000000..cdd6037
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/incoming-7.c
@@ -0,0 +1,16 @@
+/* PR target/40838 */
+/* { dg-do compile { target { { ! *-*-darwin* } && ilp32 } } } */
+/* { dg-options "-w -mstackrealign -O2 -msse2 -mpreferred-stack-boundary=4" } */
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+extern v4si y(v4si, v4si, v4si, v4si, v4si);
+
+extern v4si s1, s2;
+
+v4si x(void)
+{
+  return y(s1, s2, s1, s2, s2);
+}
+
+/* { dg-final { scan-assembler "andl\[\\t \]*\\$-16,\[\\t \]*%esp" } } */
diff --git a/gcc/testsuite/gcc.target/i386/incoming-8.c b/gcc/testsuite/gcc.target/i386/incoming-8.c
new file mode 100644
index 0000000..2dd8800
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/incoming-8.c
@@ -0,0 +1,18 @@
+/* PR target/40838 */
+/* { dg-do compile { target { { ! *-*-darwin* } && ilp32 } } } */
+/* { dg-options "-w -mstackrealign -O3 -msse2 -mpreferred-stack-boundary=4" } */
+
+float
+foo (float f)
+{
+  float array[128];
+  float x;
+  int i;
+  for (i = 0; i < sizeof(array) / sizeof(*array); i++)
+    array[i] = f;
+  for (i = 0; i < sizeof(array) / sizeof(*array); i++)
+    x += array[i];
+  return x;
+}
+
+/* { dg-final { scan-assembler "andl\[\\t \]*\\$-16,\[\\t \]*%esp" } } */
diff --git a/gcc/testsuite/gcc.target/i386/incoming-9.c b/gcc/testsuite/gcc.target/i386/incoming-9.c
new file mode 100644
index 0000000..e43cbd6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/incoming-9.c
@@ -0,0 +1,18 @@
+/* PR target/40838 */
+/* { dg-do compile { target { { ! *-*-darwin* } && ilp32 } } } */
+/* { dg-options "-w -mstackrealign -O3 -mno-sse -mpreferred-stack-boundary=4" } */
+
+float
+foo (float f)
+{
+  float array[128];
+  float x;
+  int i;
+  for (i = 0; i < sizeof(array) / sizeof(*array); i++)
+    array[i] = f;
+  for (i = 0; i < sizeof(array) / sizeof(*array); i++)
+    x += array[i];
+  return x;
+}
+
+/* { dg-final { scan-assembler-not "andl\[\\t \]*\\$-16,\[\\t \]*%esp" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr37843-4.c b/gcc/testsuite/gcc.target/i386/pr37843-4.c
new file mode 100644
index 0000000..8e5f51f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr37843-4.c
@@ -0,0 +1,13 @@
+/* Test for stack alignment with sibcall optimization.  */
+/* { dg-do compile { target { ilp32 && nonpic } } } */
+/* { dg-options "-O2 -msse2 -mpreferred-stack-boundary=4 -mstackrealign" } */
+/* { dg-final { scan-assembler-not "andl\[\\t \]*\\$-16,\[\\t \]*%\[re\]?sp" } } */
+/* { dg-final { scan-assembler-not "call\[\\t \]*foo" } } */
+/* { dg-final { scan-assembler "jmp\[\\t \]*foo" } } */
+
+extern int foo (void);
+
+int bar (void)
+{
+    return foo();
+}