[PATCH 04/14] crc32: Speed up memory table access on powerpc

[Darrick J. Wong]

Replace 2D array references by pointer references in loops.
This change has no effect on X86 code but improves PPC
performance.

From: Bob Pearson <rpearson@xxxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Bob Pearson <rpearson@xxxxxxxxxxxxxxxxxxxxx>
[djwong@xxxxxxxxxx: Minor changelog tweaks]
Signed-off-by: Darrick J. Wong <djwong@xxxxxxxxxx>
---
 lib/crc32.c |   21 +++++++++++----------
 1 files changed, 11 insertions(+), 10 deletions(-)


diff --git a/lib/crc32.c b/lib/crc32.c
index 7a0e5a9..c93c9ae 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -53,20 +53,21 @@ static inline u32
 crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
 {
 # ifdef __LITTLE_ENDIAN
-#  define DO_CRC(x) crc = tab[0][(crc ^ (x)) & 255] ^ (crc >> 8)
-#  define DO_CRC4 crc = tab[3][(crc) & 255] ^ \
-		tab[2][(crc >> 8) & 255] ^ \
-		tab[1][(crc >> 16) & 255] ^ \
-		tab[0][(crc >> 24) & 255]
+#  define DO_CRC(x) (crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8))
+#  define DO_CRC4 crc = t3[(crc) & 255] ^ \
+			t2[(crc >> 8) & 255] ^ \
+			t1[(crc >> 16) & 255] ^ \
+			t0[(crc >> 24) & 255]
 # else
-#  define DO_CRC(x) crc = tab[0][((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
-#  define DO_CRC4 crc = tab[0][(crc) & 255] ^ \
-		tab[1][(crc >> 8) & 255] ^ \
-		tab[2][(crc >> 16) & 255] ^ \
-		tab[3][(crc >> 24) & 255]
+#  define DO_CRC(x) (crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8))
+#  define DO_CRC4 crc = t0[(crc) & 255] ^ \
+			t1[(crc >> 8) & 255] ^ \
+			t2[(crc >> 16) & 255] ^ \
+			t3[(crc >> 24) & 255]
 # endif
 	const u32 *b;
 	size_t    rem_len;
+	const u32 *t0 = tab[0], *t1 = tab[1], *t2 = tab[2], *t3 = tab[3];
 
 	/* Align it */
 	if (unlikely((long)buf & 3 && len)) {

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/