Minor improvement to H8 startup code

[Jeff Law]

Basically the startup code needs to clear memory from _edata to _end. 
In the past it's been done with a fairly naive copy loop.  This changes 
the code to just call memset and let memset figure out a sensible way to 
handle the operation given the size and alignment requirements.

I don't have performance data on this.  I cobbled it together some time 
ago in response to seeing some of the GCC tests with larger .bss 
sections taking an insane amount of time to just get from _start to 
main.  With the fixes to the H8 decoder in the simulator it may not 
matter nearly as much anymore.

This has been in my tester for months.  Naturally it does not cause any 
regressions in the H8 port.

OK for the trunk?

Jeff
-------------- next part --------------
diff --git a/newlib/libc/sys/h8300hms/crt0.S b/newlib/libc/sys/h8300hms/crt0.S
index 6394f6841..05634113c 100644
--- a/newlib/libc/sys/h8300hms/crt0.S
+++ b/newlib/libc/sys/h8300hms/crt0.S
@@ -9,12 +9,10 @@
 _start:
 	mov.w	#_stack,sp
 	mov.w	#_edata,r0
-	mov.w	#_end,r1
-	sub.w   r2,r2
-.Loop:	mov.w	r2,@r0
-	adds	#2,r0
-	cmp	r1,r0
-	blo	.Loop
+	mov.w	#_end,r2
+	sub.w   r1,r1
+	sub.w	r0,r2
+	jsr	@_memset
 #ifdef __ELF__
 	mov.l   #__fini,r0
 	jsr     @_atexit
@@ -43,12 +41,10 @@ _stack:	.word 	1
 _start:
 	mov.l	#_stack,sp
 	mov.l	#_edata,er0
-	mov.l	#_end,er1
-	sub.w   r2,r2           ; not sure about alignment requirements
-.Loop:	mov.w	r2,@er0		; playing it safe for now
-	adds	#2,er0
-	cmp.l	er1,er0
-	blo	.Loop
+	mov.l	#_end,er2
+	sub.w   r1,r1
+	sub.l	er0,er2
+	jsr	@_memset
 #ifdef __ELF__
 	mov.l   #__fini,er0
 	jsr     @_atexit
@@ -77,12 +73,10 @@ _stack:	.long 	1
 _start:
 	mov.l	#_stack,sp
 	mov.l	#_edata,er0
-	mov.l	#_end,er1
-	sub.w   r2,r2           ; not sure about alignment requirements
-.Loop:	mov.w	r2,@er0		; playing it safe for now
-	adds	#2,er0
-	cmp.l	er1,er0
-	blo	.Loop
+	mov.l	#_end,er2
+	sub.w   r1,r1
+	sub.l	er0,er2
+	jsr	@_memset
 #ifdef __ELF__
 	mov.l   #__fini,er0
 	jsr     @_atexit