From: hjl <hjl@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Thu, 8 Oct 2015 18:57:11 +0000 (+0000)
Subject: Round up the SSE register save area only if needed
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=27f0420028fe07ce66eba2e48d00cf018fcd2989;p=thirdparty%2Fgcc.git

Round up the SSE register save area only if needed

There is is no point to round up the SSE register save area to 16 bytes if
the incoming stack boundary is less than 16 bytes.

	* config/i386/i386.c (ix86_compute_frame_layout): Round up the
	SSE register save area to 16 bytes only if the incoming stack
	boundary is no less than 16 bytes.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@228621 138bc75d-0d04-0410-961f-82ee72b054a4
---

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 9f84b6ef8372..428649149456 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2015-10-08  H.J. Lu  <hongjiu.lu@intel.com>
+
+	* config/i386/i386.c (ix86_compute_frame_layout): Round up the
+	SSE register save area to 16 bytes only if the incoming stack
+	boundary is no less than 16 bytes.
+
 2015-10-08  Jeff Law  <law@redhat.com>
 
 	* tree-ssa-phiopt.c (factor_out_conversion): Add missing calls to
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index a24bd26c96a0..4806a7cffa29 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -11383,9 +11383,14 @@ ix86_compute_frame_layout (struct ix86_frame *frame)
   if (frame->nsseregs)
     {
       /* 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.  */
-      offset = ROUND_UP (offset, 16);
+	 16-byte aligned default stack, and thus we don't need to be
+	 within the re-aligned local stack frame to save them.  In case
+	 incoming stack boundary is aligned to less than 16 bytes,
+	 unaligned move of SSE register will be emitted, so there is
+	 no point to round up the SSE register save area outside the
+	 re-aligned local stack frame to 16 bytes.  */
+      if (ix86_incoming_stack_boundary >= 128)
+	offset = ROUND_UP (offset, 16);
       offset += frame->nsseregs * 16;
     }
   frame->sse_reg_save_offset = offset;