powerpc32: optimise csum_partial() loop

On the 8xx, load latency is 2 cycles and taking branches also takes
2 cycles. So let's unroll the loop.

This patch improves csum_partial() speed by around 10% on both:
* 8xx (single issue processor with parallel execution)
* 83xx (superscalar 6xx processor with dual instruction fetch
and parallel execution)

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <oss@buserror.net>

diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index 9c126028ab9c3d7c533aa613f247d2815beb3f30..0d34f47c8a5e88e2bfc982e415ec92aff08d4703 100644 (file)
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -38,10 +38,24 @@ _GLOBAL(csum_partial)
        srwi.   r6,r4,2         /* # words to do */
        adde    r5,r5,r0
        beq     3f
-1:     mtctr   r6
+1:     andi.   r6,r6,3         /* Prepare to handle words 4 by 4 */
+       beq     21f
+       mtctr   r6
 2:     lwzu    r0,4(r3)
        adde    r5,r5,r0
        bdnz    2b
+21:    srwi.   r6,r4,4         /* # blocks of 4 words to do */
+       beq     3f
+       mtctr   r6
+22:    lwz     r0,4(r3)
+       lwz     r6,8(r3)
+       lwz     r7,12(r3)
+       lwzu    r8,16(r3)
+       adde    r5,r5,r0
+       adde    r5,r5,r6
+       adde    r5,r5,r7
+       adde    r5,r5,r8
+       bdnz    22b
 3:     andi.   r0,r4,2
        beq+    4f
        lhz     r0,4(r3)