[PATCH v2 02/11] x86: Avoid stack realignment when copying data

[H.J. Lu via Gcc-patches]

To avoid stack realignment, use SCRATCH_SSE_REG to copy data from one
memory location to another.

gcc/

        * config/i386/i386-expand.c (ix86_expand_vector_move): Use
        SCRATCH_SSE_REG to copy data from one memory location to
        another.

gcc/testsuite/

        * gcc.target/i386/eh_return-1.c: New test.
---
 gcc/config/i386/i386-expand.c               | 16 ++++++++++++-
 gcc/testsuite/gcc.target/i386/eh_return-1.c | 26 +++++++++++++++++++++
 2 files changed, 41 insertions(+), 1 deletion(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/eh_return-1.c

diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 7f1dff6337c..09d5e5d88af 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -431,7 +431,21 @@ ix86_expand_vector_move (machine_mode mode, rtx operands[])
       && !register_operand (op0, mode)
       && !register_operand (op1, mode))
     {
-      emit_move_insn (op0, force_reg (GET_MODE (op0), op1));
+      rtx tmp;
+      mode = GET_MODE (op0);
+      if (TARGET_SSE
+         && (GET_MODE_ALIGNMENT (mode)
+             > ix86_minimum_incoming_stack_boundary (false, true)))
+       {
+         /* NB: Don't increase stack alignment requirement by using
+            a scratch SSE register to copy data from one memory
+            location to another since it doesn't require a spill.  */
+         tmp = gen_rtx_REG (mode, SCRATCH_SSE_REG);
+         emit_move_insn (tmp, op1);
+       }
+      else
+       tmp = force_reg (mode, op1);
+      emit_move_insn (op0, tmp);
       return;
     }
 
diff --git a/gcc/testsuite/gcc.target/i386/eh_return-1.c 
b/gcc/testsuite/gcc.target/i386/eh_return-1.c
new file mode 100644
index 00000000000..671ba635e88
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/eh_return-1.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=haswell -mno-avx512f" } */
+
+struct _Unwind_Context
+{
+  void *ra;
+  char array[48];
+};
+
+extern long uw_install_context_1 (struct _Unwind_Context *);
+
+void
+_Unwind_RaiseException (void)
+{
+  struct _Unwind_Context this_context, cur_context;
+  long offset = uw_install_context_1 (&this_context);
+  __builtin_memcpy (&this_context, &cur_context,
+                   sizeof (struct _Unwind_Context));
+  void *handler = __builtin_frob_return_addr ((&cur_context)->ra);
+  uw_install_context_1 (&cur_context);
+  __builtin_eh_return (offset, handler);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 4 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */
-- 
2.31.1