X-Git-Url: http://drtracing.org/?a=blobdiff_plain;f=lib%2Fgcd.c;h=135ee6407a5e4f0a6f7fc8da85f38a74ea37ed38;hb=0e6f98cb6269c7f5810509fc965e09049060d675;hp=3657f129d7b8c5db0bee11a94a97d5d4bf251b52;hpb=b7838c2b91a5aae09d24e1110002097283055fb8;p=deliverable%2Flinux.git

diff --git a/lib/gcd.c b/lib/gcd.c
index 3657f129d7b8..135ee6407a5e 100644
--- a/lib/gcd.c
+++ b/lib/gcd.c
@@ -2,20 +2,77 @@
 #include <linux/gcd.h>
 #include <linux/export.h>
 
-/* Greatest common divisor */
+/*
+ * This implements the binary GCD algorithm. (Often attributed to Stein,
+ * but as Knuth has noted, appears in a first-century Chinese math text.)
+ *
+ * This is faster than the division-based algorithm even on x86, which
+ * has decent hardware division.
+ */
+
+#if !defined(CONFIG_CPU_NO_EFFICIENT_FFS) && !defined(CPU_NO_EFFICIENT_FFS)
+
+/* If __ffs is available, the even/odd algorithm benchmarks slower. */
 unsigned long gcd(unsigned long a, unsigned long b)
 {
-	unsigned long r;
+	unsigned long r = a | b;
+
+	if (!a || !b)
+		return r;
 
-	if (a < b)
-		swap(a, b);
+	b >>= __ffs(b);
+	if (b == 1)
+		return r & -r;
 
-	if (!b)
-		return a;
-	while ((r = a % b) != 0) {
-		a = b;
-		b = r;
+	for (;;) {
+		a >>= __ffs(a);
+		if (a == 1)
+			return r & -r;
+		if (a == b)
+			return a << __ffs(r);
+
+		if (a < b)
+			swap(a, b);
+		a -= b;
 	}
-	return b;
 }
+
+#else
+
+/* If normalization is done by loops, the even/odd algorithm is a win. */
+unsigned long gcd(unsigned long a, unsigned long b)
+{
+	unsigned long r = a | b;
+
+	if (!a || !b)
+		return r;
+
+	/* Isolate lsbit of r */
+	r &= -r;
+
+	while (!(b & r))
+		b >>= 1;
+	if (b == r)
+		return r;
+
+	for (;;) {
+		while (!(a & r))
+			a >>= 1;
+		if (a == r)
+			return r;
+		if (a == b)
+			return a;
+
+		if (a < b)
+			swap(a, b);
+		a -= b;
+		a >>= 1;
+		if (a & r)
+			a += b;
+		a >>= 1;
+	}
+}
+
+#endif
+
 EXPORT_SYMBOL_GPL(gcd);