[PATCH 2/3] i386/memset: do not fetch fill char from memory again

[Denys Vlasenko <vda.linux@googlemail.com>]

 shl $16,%edx
 mov 8(%esp),%dl
 mov 8(%esp),%dh

The above code has two register merge stalls, and it goes to load unit
to fetch the data. I don't know what's worse. Both are not pleasant.

Replace them with IMUL. It has ~3 cycle latency, but no stalls.
Move it a bit up to hide its latency.

   text	   data	    bss	    dec	    hex	filename
    182	      0	      0	    182	     b6	memset1.o
    177	      0	      0	    177	     b1	memset2.o

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
CC: Rich Felker <dalias@libc.org>
CC: musl@lists.openwall.com
---
 src/string/i386/memset.s | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/src/string/i386/memset.s b/src/string/i386/memset.s
index d6118c7..cd13f41 100644
--- a/src/string/i386/memset.s
+++ b/src/string/i386/memset.s
@@ -19,13 +19,10 @@ memset:
 
 	mov %dx,1(%eax)
 	mov %dx,(-1-2)(%eax,%ecx)
+	imul $0x10001,%edx
 	cmp $6,%ecx
 	jbe 1f
 
-	shl $16,%edx
-	mov 8(%esp),%dl
-	mov 8(%esp),%dh
-
 	mov %edx,(1+2)(%eax)
 	mov %edx,(-1-2-4)(%eax,%ecx)
 	cmp $14,%ecx
-- 
1.8.1.4