[PATCH][GCC][mid-end] Allow larger copies when target supports unaligned access [Patch (1/2)]

[Tamar Christina <tamar dot christina at arm dot com>]

Hi All,

This patch allows larger bitsizes to be used as copy size
when the target does not have SLOW_UNALIGNED_ACCESS.

fun3:
	adrp	x2, .LANCHOR0
	add	x2, x2, :lo12:.LANCHOR0
	mov	x0, 0
	sub	sp, sp, #16
	ldrh	w1, [x2, 16]
	ldrb	w2, [x2, 18]
	add	sp, sp, 16
	bfi	x0, x1, 0, 8
	ubfx	x1, x1, 8, 8
	bfi	x0, x1, 8, 8
	bfi	x0, x2, 16, 8
	ret

is turned into

fun3:
	adrp	x0, .LANCHOR0
	add	x0, x0, :lo12:.LANCHOR0
	sub	sp, sp, #16
	ldrh	w1, [x0, 16]
	ldrb	w0, [x0, 18]
	strh	w1, [sp, 8]
	strb	w0, [sp, 10]
	ldr	w0, [sp, 8]
	add	sp, sp, 16
	ret

which avoids the bfi's for a simple 3 byte struct copy.

Regression tested on aarch64-none-linux-gnu and x86_64-pc-linux-gnu and no regressions.

This patch is just splitting off from the previous combined patch with AArch64 and adding
a testcase.

I assume Jeff's ACK from https://gcc.gnu.org/ml/gcc-patches/2017-08/msg01523.html is still
valid as the code did not change.

Thanks,
Tamar


gcc/
2017-11-14  Tamar Christina  <tamar.christina@arm.com>

	* expr.c (copy_blkmode_to_reg): Fix bitsize for targets
	with fast unaligned access.
	* doc/sourcebuild.texi (no_slow_unalign): New.
	
gcc/testsuite/
2017-11-14  Tamar Christina  <tamar.christina@arm.com>

	* gcc.dg/struct-simple.c: New.
	* lib/target-supports.exp
	(check_effective_target_no_slow_unalign): New.

-- 

diff --git a/gcc/doc/sourcebuild.texi b/gcc/doc/sourcebuild.texi
index 1646d0a99911aa7b2e66762e5907fbb0454ed00d..1df7a82fbd516b9bf07908bb800e441110b28ca4 100644
--- a/gcc/doc/sourcebuild.texi
+++ b/gcc/doc/sourcebuild.texi
@@ -2178,8 +2178,12 @@ Target supports @code{wchar_t} that is compatible with @code{char32_t}.
 
 @item comdat_group
 Target uses comdat groups.
+
+@item no_slow_unalign
+Target does not have slow unaligned access.
 @end table
 
+
 @subsubsection Local to tests in @code{gcc.target/i386}
 
 @table @code
diff --git a/gcc/expr.c b/gcc/expr.c
index 2f8432d92ccac17c0a548faf4a16eff0656cef1b..afcea8fef58155d0a899991c10cd485ba8af888d 100644
--- a/gcc/expr.c
+++ b/gcc/expr.c
@@ -2769,7 +2769,9 @@ copy_blkmode_to_reg (machine_mode mode, tree src)
 
   n_regs = (bytes + UNITS_PER_WORD - 1) / UNITS_PER_WORD;
   dst_words = XALLOCAVEC (rtx, n_regs);
-  bitsize = MIN (TYPE_ALIGN (TREE_TYPE (src)), BITS_PER_WORD);
+  bitsize = BITS_PER_WORD;
+  if (targetm.slow_unaligned_access (word_mode, TYPE_ALIGN (TREE_TYPE (src))))
+    bitsize = MIN (TYPE_ALIGN (TREE_TYPE (src)), BITS_PER_WORD);
 
   /* Copy the structure BITSIZE bits at a time.  */
   for (bitpos = 0, xbitpos = padding_correction;
diff --git a/gcc/testsuite/gcc.dg/struct-simple.c b/gcc/testsuite/gcc.dg/struct-simple.c
new file mode 100644
index 0000000000000000000000000000000000000000..9f218851d897421b217b0926d29845b6192982fb
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/struct-simple.c
@@ -0,0 +1,52 @@
+/* { dg-do-run } */
+/* { dg-require-effective-target no_slow_unalign } */
+/* { dg-additional-options "-fdump-rtl-final" } */
+
+/* Copyright 1996, 1999, 2007 Free Software Foundation, Inc.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 3 of the License, or
+   (at your option) any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with GCC; see the file COPYING3.  If not see
+   <http://www.gnu.org/licenses/>.
+
+   Please email any bugs, comments, and/or additions to this file to:
+   bug-gdb@prep.ai.mit.edu  */
+
+#include <stdio.h>
+
+struct struct3 { char a, b, c; };
+struct struct3 foo3 = { 'A', 'B', 'C'},  L3;
+
+struct struct3  fun3()
+{
+  return foo3;
+}
+
+#ifdef PROTOTYPES
+void Fun3(struct struct3 foo3)
+#else
+void Fun3(foo3)
+     struct struct3 foo3;
+#endif
+{
+  L3 = foo3;
+}
+
+int main()
+{
+  struct struct3 x = fun3();
+
+  printf("a:%c, b:%c, c:%c\n", x.a, x.b, x.c);
+}
+
+/* { dg-final { scan-rtl-dump-not {zero_extract:.+\[\s*foo3\s*\]} "final" } } */
+
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index b6f9e51c4817cf8235c8e33b14e2763308eb482a..690d8960002a3c38462bbe5524b419c205ba4da9 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -6037,6 +6037,30 @@ proc check_effective_target_unaligned_stack { } {
     return $et_unaligned_stack_saved
 }
 
+# Return 1 if the target plus current options does not have
+# slow unaligned access.
+#
+# This won't change for different subtargets so cache the result.
+
+proc check_effective_target_no_slow_unalign { } {
+    global et_no_slow_unalign_saved
+    global et_index
+
+    if [info exists et_no_slow_unalign_saved($et_index)] {
+        verbose "check_effective_target_no_slow_unalign: using cached result" 2
+    } else {
+        set et_no_slow_unalign_saved($et_index) 0
+        if { [istarget x86_64-*-*]
+             || [istarget aarch64*-*-*]
+           } {
+            set et_no_slow_unalign_saved($et_index) 1
+        }
+    }
+    verbose "check_effective_target_no_slow_unalign:\
+             returning $et_no_slow_unalign_saved($et_index)" 2
+    return $et_no_slow_unalign_saved($et_index)
+}
+
 # Return 1 if the target plus current options does not support a vector
 # alignment mechanism, 0 otherwise.
 #