So, the arm memcpy code of aligned data isn’t as good as it can be.

void *memcpy(void *dest, const void *src, unsigned int n);

void foo(char *dst, int i) {
  memcpy (dst, &i, sizeof (i));
}

generates horrible code, but, it we are willing to notice the src or the destination are aligned, we can do much better:

$ ./cc1 -fschedule-fusion -fdump-tree-all-all -da -march=armv7ve -mcpu=cortex-m4 -fomit-frame-pointer -quiet -O2 /tmp/t.c -o t.s
$ cat t.s
[ … ]
foo:
	@ args = 0, pretend = 0, frame = 4
	@ frame_needed = 0, uses_anonymous_args = 0
	@ link register save eliminated.
	sub	sp, sp, #4
	str	r1, [r0]	@ unaligned
	add	sp, sp, #4

Index: gcc/config/arm/arm.c
===================================================================
--- gcc/config/arm/arm.c	(revision 223842)
+++ gcc/config/arm/arm.c	(working copy)
@@ -14376,7 +14376,10 @@ arm_block_move_unaligned_straight (rtx d
 				srcoffset + j * UNITS_PER_WORD - src_autoinc);
 	  mem = adjust_automodify_address (srcbase, SImode, addr,
 					   srcoffset + j * UNITS_PER_WORD);
-	  emit_insn (gen_unaligned_loadsi (regs[j], mem));
+	  if (src_aligned)
+	    emit_move_insn (regs[j], mem);
+	  else
+	    emit_insn (gen_unaligned_loadsi (regs[j], mem));
 	}
       srcoffset += words * UNITS_PER_WORD;
     }
@@ -14395,7 +14398,10 @@ arm_block_move_unaligned_straight (rtx d
 				dstoffset + j * UNITS_PER_WORD - dst_autoinc);
 	  mem = adjust_automodify_address (dstbase, SImode, addr,
 					   dstoffset + j * UNITS_PER_WORD);
-	  emit_insn (gen_unaligned_storesi (mem, regs[j]));
+	  if (dst_aligned)
+	    emit_move_insn (mem, regs[j]);
+	  else
+	    emit_insn (gen_unaligned_storesi (mem, regs[j]));
 	}
       dstoffset += words * UNITS_PER_WORD;
     }


Ok?

Can someone spin this through an arm test suite run for me, I was doing this by inspection and cross compile on a system with no arm bits.  Bonus points if you can check it in with the test case above marked up as appropriate.