Support unaligned SSE moves outside realigned areahjl/unaligned

gcc/

	PR target/66697
	* config/i386/i386.c (ix86_option_override_internal): Use
	8-byte minimum stack boundary in 64-bit mode.
	(ix86_compute_frame_layout): Remove assert on
	INCOMING_STACK_BOUNDARY.
	(ix86_emit_save_reg_using_mov): Support unaligned SSE store.
	Add a REG_CFA_EXPRESSION note if needed.
	(ix86_emit_restore_sse_regs_using_mov): Support unaligned SSE
	load.
	(ix86_handle_force_align_arg_pointer_attribute): New.
	(ix86_minimum_incoming_stack_boundary): Remove TARGET_64BIT
	check.
	(ix86_attribute_table): Set ix86_force_align_arg_pointer_string
	with ix86_handle_force_align_arg_pointer_attribute.
	* config/i386/i386.h (MIN_STACK_BOUNDARY): Set to BITS_PER_WORD.

gcc/testsuite/

	PR target/66697
	* gcc.target/i386/20060512-1.c: Remove ia32 requirement.
	(PUSH): New.
	(POP): Likewise.
	(vector_using_function): Use PUSH and POP.
	* cc.target/i386/20060512-2.c: Remove ia32 requirement.

2 files changed, 56 insertions, 11 deletions

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 38953ddc4ae..0b59bfc1931 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -5209,8 +5209,7 @@ ix86_option_override_internal (bool main_args_p,
   ix86_incoming_stack_boundary = ix86_default_incoming_stack_boundary;
   if (opts_set->x_ix86_incoming_stack_boundary_arg)
     {
-      int min = (TARGET_64BIT_P (opts->x_ix86_isa_flags)
-		 ? (TARGET_SSE_P (opts->x_ix86_isa_flags) ? 4 : 3) : 2);
+      int min = TARGET_64BIT_P (opts->x_ix86_isa_flags) ? 3 : 2;
 
       if (opts->x_ix86_incoming_stack_boundary_arg < min
 	  || opts->x_ix86_incoming_stack_boundary_arg > 12)
@@ -11391,7 +11390,6 @@ ix86_compute_frame_layout (struct ix86_frame *frame)
       /* The only ABI that has saved SSE registers (Win64) also has a
          16-byte aligned default stack, and thus we don't need to be
 	 within the re-aligned local stack frame to save them.  */
-      gcc_assert (INCOMING_STACK_BOUNDARY >= 128);
       offset = ROUND_UP (offset, 16);
       offset += frame->nsseregs * 16;
     }
@@ -11616,14 +11614,26 @@ ix86_emit_save_reg_using_mov (machine_mode mode, unsigned int regno,
   struct machine_function *m = cfun->machine;
   rtx reg = gen_rtx_REG (mode, regno);
   rtx mem, addr, base, insn;
+  unsigned int align;
 
   addr = choose_baseaddr (cfa_offset);
   mem = gen_frame_mem (mode, addr);
 
-  /* For SSE saves, we need to indicate the 128-bit alignment.  */
-  set_mem_align (mem, GET_MODE_ALIGNMENT (mode));
+  /* The location is aligned up to INCOMING_STACK_BOUNDARY.  */
+  align = MIN (GET_MODE_ALIGNMENT (mode), INCOMING_STACK_BOUNDARY);
+  set_mem_align (mem, align);
+
+  /* SSE saves are not within re-aligned local stack frame.
+     In case INCOMING_STACK_BOUNDARY is misaligned, we have
+     to emit unaligned store.  */
+  if (mode == V4SFmode && align < 128)
+    {
+      rtx unspec = gen_rtx_UNSPEC (mode, gen_rtvec (1, reg), UNSPEC_STOREU);
+      insn = emit_insn (gen_rtx_SET (mem, unspec));
+    }
+  else
+    insn = emit_insn (gen_rtx_SET (mem, reg));
 
-  insn = emit_move_insn (mem, reg);
   RTX_FRAME_RELATED_P (insn) = 1;
 
   base = addr;
@@ -11670,6 +11680,8 @@ ix86_emit_save_reg_using_mov (machine_mode mode, unsigned int regno,
       mem = gen_rtx_MEM (mode, addr);
       add_reg_note (insn, REG_CFA_OFFSET, gen_rtx_SET (mem, reg));
     }
+  else
+    add_reg_note (insn, REG_CFA_EXPRESSION, gen_rtx_SET (mem, reg));
 }
 
 /* Emit code to save registers using MOV insns.
@@ -11886,6 +11898,25 @@ find_drap_reg (void)
     }
 }
 
+/* Handle a "force_align_arg_pointer" attribute.  */
+
+static tree
+ix86_handle_force_align_arg_pointer_attribute (tree *node, tree name,
+					       tree, int, bool *no_add_attrs)
+{
+  if (TREE_CODE (*node) != FUNCTION_TYPE
+      && TREE_CODE (*node) != METHOD_TYPE
+      && TREE_CODE (*node) != FIELD_DECL
+      && TREE_CODE (*node) != TYPE_DECL)
+    {
+      warning (OPT_Wattributes, "%qE attribute only applies to functions",
+	       name);
+      *no_add_attrs = true;
+    }
+
+  return NULL_TREE;
+}
+
 /* Return minimum incoming stack alignment.  */
 
 static unsigned int
@@ -11900,7 +11931,6 @@ ix86_minimum_incoming_stack_boundary (bool sibcall)
      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;
@@ -13184,11 +13214,26 @@ ix86_emit_restore_sse_regs_using_mov (HOST_WIDE_INT cfa_offset,
       {
 	rtx reg = gen_rtx_REG (V4SFmode, regno);
 	rtx mem;
+	unsigned int align;
 
 	mem = choose_baseaddr (cfa_offset);
 	mem = gen_rtx_MEM (V4SFmode, mem);
-	set_mem_align (mem, 128);
-	emit_move_insn (reg, mem);
+
+	/* The location is aligned up to INCOMING_STACK_BOUNDARY.  */
+	align = MIN (GET_MODE_ALIGNMENT (V4SFmode), INCOMING_STACK_BOUNDARY);
+	set_mem_align (mem, align);
+
+	/* SSE saves are not within re-aligned local stack frame.
+	   In case INCOMING_STACK_BOUNDARY is misaligned, we have
+	   to emit unaligned load.  */
+	if (align < 128)
+	  {
+	    rtx unspec = gen_rtx_UNSPEC (V4SFmode, gen_rtvec (1, mem),
+					 UNSPEC_LOADU);
+	    emit_insn (gen_rtx_SET (reg, unspec));
+	  }
+	else
+	  emit_insn (gen_rtx_SET (reg, mem));
 
 	ix86_add_cfa_restore_note (NULL, reg, cfa_offset);
 
@@ -48159,7 +48204,7 @@ static const struct attribute_spec ix86_attribute_table[] =
     true },
   /* force_align_arg_pointer says this function realigns the stack at entry.  */
   { (const char *)&ix86_force_align_arg_pointer_string, 0, 0,
-    false, true,  true, ix86_handle_cconv_attribute, false },
+    false, true,  true, ix86_handle_force_align_arg_pointer_attribute, false },
 #if TARGET_DLLIMPORT_DECL_ATTRIBUTES
   { "dllimport", 0, 0, false, false, false, handle_dll_attribute, false },
   { "dllexport", 0, 0, false, false, false, handle_dll_attribute, false },
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index a24dea544c6..2edc22b5677 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -755,7 +755,7 @@ extern const char *host_detect_local_cpu (int argc, const char **argv);
 #define MAIN_STACK_BOUNDARY (TARGET_64BIT ? 128 : 32)
 
 /* Minimum stack boundary.  */
-#define MIN_STACK_BOUNDARY (TARGET_64BIT ? (TARGET_SSE ? 128 : 64) : 32)
+#define MIN_STACK_BOUNDARY BITS_PER_WORD
 
 /* Boundary (in *bits*) on which the stack pointer prefers to be
    aligned; the compiler cannot rely on having this alignment.  */