[PATCH] microblaze: speedup for word-aligned memcpys

["Steven J. Magnani" <steve@digidescorp.com>]

memcpy performance was measured on a noMMU system having a barrel shifter, 
4K caches, and 32-byte write-through cachelines. In this environment, 
copying word-aligned data in word-sized chunks appears to be about 3% more 
efficient on packet-sized buffers (1460 bytes) than copying in cacheline-sized 
chunks.

Skip to word-based copying when buffers are both word-aligned.

Signed-off-by: Steven J. Magnani <steve@digidescorp.com>
---
diff -uprN a/arch/microblaze/lib/fastcopy.S b/arch/microblaze/lib/fastcopy.S
--- a/arch/microblaze/lib/fastcopy.S	2010-04-09 21:52:36.000000000 -0500
+++ b/arch/microblaze/lib/fastcopy.S	2010-04-12 15:37:44.000000000 -0500
@@ -69,37 +69,13 @@ a_dalign_done:
 	blti	r4, a_block_done
 
 a_block_xfer:
-	andi	r4, r7, 0xffffffe0	/* n = c & ~31 */
-	rsub	r7, r4, r7		/* c = c - n */
-
 	andi	r9, r6, 3		/* t1 = s & 3 */
-	/* if temp != 0, unaligned transfers needed */
-	bnei	r9, a_block_unaligned
-
-a_block_aligned:
-	lwi	r9, r6, 0		/* t1 = *(s + 0) */
-	lwi	r10, r6, 4		/* t2 = *(s + 4) */
-	lwi	r11, r6, 8		/* t3 = *(s + 8) */
-	lwi	r12, r6, 12		/* t4 = *(s + 12) */
-	swi	r9, r5, 0		/* *(d + 0) = t1 */
-	swi	r10, r5, 4		/* *(d + 4) = t2 */
-	swi	r11, r5, 8		/* *(d + 8) = t3 */
-	swi	r12, r5, 12		/* *(d + 12) = t4 */
-	lwi	r9, r6, 16		/* t1 = *(s + 16) */
-	lwi	r10, r6, 20		/* t2 = *(s + 20) */
-	lwi	r11, r6, 24		/* t3 = *(s + 24) */
-	lwi	r12, r6, 28		/* t4 = *(s + 28) */
-	swi	r9, r5, 16		/* *(d + 16) = t1 */
-	swi	r10, r5, 20		/* *(d + 20) = t2 */
-	swi	r11, r5, 24		/* *(d + 24) = t3 */
-	swi	r12, r5, 28		/* *(d + 28) = t4 */
-	addi	r6, r6, 32		/* s = s + 32 */
-	addi	r4, r4, -32		/* n = n - 32 */
-	bneid	r4, a_block_aligned	/* while (n) loop */
-	addi	r5, r5, 32		/* d = d + 32 (IN DELAY SLOT) */
-	bri	a_block_done
+	/* if temp == 0, everything is word-aligned */
+	beqi	r9, a_word_xfer
 
 a_block_unaligned:
+	andi	r4, r7, 0xffffffe0	/* n = c & ~31 */
+	rsub	r7, r4, r7		/* c = c - n */
 	andi	r8, r6, 0xfffffffc	/* as = s & ~3 */
 	add	r6, r6, r4		/* s = s + n */
 	lwi	r11, r8, 0		/* h = *(as + 0) */