summaryrefslogtreecommitdiffstats
path: root/lib
diff options
context:
space:
mode:
authordelphij <delphij@FreeBSD.org>2010-03-12 21:14:56 +0000
committerdelphij <delphij@FreeBSD.org>2010-03-12 21:14:56 +0000
commitae5ae700daa1f69f414f6066606f705da6e0c1eb (patch)
tree2e52c4428fed96f8449eb4c352f24b2fd04bd300 /lib
parenta5e01102277b659f140548285e631c9572b8827e (diff)
downloadFreeBSD-src-ae5ae700daa1f69f414f6066606f705da6e0c1eb.zip
FreeBSD-src-ae5ae700daa1f69f414f6066606f705da6e0c1eb.tar.gz
Two optimizations to MI strlen(3) inspired by David S. Miller's
blog posting [1]. - Use word-sized test for unaligned pointer before working the hard way. Memory page boundary is always integral multiple of a word alignment boundary. Therefore, if we can access memory referenced by pointer p, then (p & ~word mask) must be also accessible. - Better utilization of multi-issue processor's ability of concurrency. The previous implementation utilized a formular that must be executed sequentially. However, the ~, & and - operations can actually be caculated at the same time when the operand were different and unrelated. The original Hacker's Delight formular also offered consistent performance regardless whether the input would contain characters with their highest-bit set, as it catches real nul characters only. These two optimizations has shown further improvements over the previous implementation on microbenchmarks on i386 and amd64 CPU including Pentium 4, Core Duo 2 and i7. [1] http://vger.kernel.org/~davem/cgi-bin/blog.cgi/2010/03/08#strlen_1 MFC after: 1 month
Diffstat (limited to 'lib')
-rw-r--r--lib/libc/string/strlen.c43
1 files changed, 31 insertions, 12 deletions
diff --git a/lib/libc/string/strlen.c b/lib/libc/string/strlen.c
index 860a988..319e44b 100644
--- a/lib/libc/string/strlen.c
+++ b/lib/libc/string/strlen.c
@@ -1,5 +1,5 @@
/*-
- * Copyright (c) 2009 Xin LI <delphij@FreeBSD.org>
+ * Copyright (c) 2009, 2010 Xin LI <delphij@FreeBSD.org>
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -43,15 +43,17 @@ __FBSDID("$FreeBSD$");
* ((x - 0x01....01) & ~x & 0x80....80)
*
* would evaluate to a non-zero value iff any of the bytes in the
- * original word is zero. However, we can further reduce ~1/3 of
- * time if we consider that strlen() usually operate on 7-bit ASCII
- * by employing the following expression, which allows false positive
- * when high bit of 1 and use the tail case to catch these case:
+ * original word is zero.
*
- * ((x - 0x01....01) & 0x80....80)
+ * On multi-issue processors, we can divide the above expression into:
+ * a) (x - 0x01....01)
+ * b) (~x & 0x80....80)
+ * c) a & b
*
- * This is more than 5.2 times as fast as the raw implementation on
- * Intel T7300 under long mode for strings longer than word length.
+ * Where, a) and b) can be partially computed in parallel.
+ *
+ * The algorithm above is found on "Hacker's Delight" by
+ * Henry S. Warren, Jr.
*/
/* Magic numbers for the algorithm */
@@ -82,15 +84,32 @@ strlen(const char *str)
{
const char *p;
const unsigned long *lp;
+ long va, vb;
- /* Skip the first few bytes until we have an aligned p */
+ /*
+ * Before trying the hard (unaligned byte-by-byte access) way
+ * to figure out whether there is a nul character, try to see
+ * if there is a nul character is within this accessible word
+ * first.
+ *
+ * p and (p & ~LONGPTR_MASK) must be equally accessible since
+ * they always fall in the same memory page, as long as page
+ * boundaries is integral multiple of word size.
+ */
+ lp = (const unsigned long *)((uintptr_t)str & ~LONGPTR_MASK);
+ va = (*lp - mask01);
+ vb = ((~*lp) & mask80);
+ if (va & vb)
+ /* Check if we have \0 in the first part */
for (p = str; (uintptr_t)p & LONGPTR_MASK; p++)
if (*p == '\0')
return (p - str);
/* Scan the rest of the string using word sized operation */
- for (lp = (const unsigned long *)p; ; lp++)
- if ((*lp - mask01) & mask80) {
+ for (lp = (const unsigned long *)p; ; lp++) {
+ va = (*lp - mask01);
+ vb = ((~*lp) & mask80);
+ if (va & vb) {
p = (const char *)(lp);
testbyte(0);
testbyte(1);
@@ -103,8 +122,8 @@ strlen(const char *str)
testbyte(7);
#endif
}
+ }
/* NOTREACHED */
return (0);
}
-
OpenPOWER on IntegriCloud