diff --git a/exec-all.h b/exec-all.h
index 861688bd5c3ebbd55134149e1e7e4205c1266377..0ced25ca136b054feda8fd0a5a318c41f153031a 100644
--- a/exec-all.h
+++ b/exec-all.h
@@ -91,9 +91,6 @@ void optimize_flags_init(void);
 extern FILE *logfile;
 extern int loglevel;
 
-void muls64(int64_t *phigh, int64_t *plow, int64_t a, int64_t b);
-void mulu64(uint64_t *phigh, uint64_t *plow, uint64_t a, uint64_t b);
-
 int gen_intermediate_code(CPUState *env, struct TranslationBlock *tb);
 int gen_intermediate_code_pc(CPUState *env, struct TranslationBlock *tb);
 void dump_ops(const uint16_t *opc_buf, const uint32_t *opparam_buf);
diff --git a/host-utils.c b/host-utils.c
index a3c838f4dc8fa449a7b4e924982e52cce42d311f..7cd0843f94400b2a4f67185e62cf902d731d9de6 100644
--- a/host-utils.c
+++ b/host-utils.c
@@ -28,6 +28,7 @@
 //#define DEBUG_MULDIV
 
 /* Long integer helpers */
+#if !defined(__x86_64__)
 static void add128 (uint64_t *plow, uint64_t *phigh, uint64_t a, uint64_t b)
 {
     *plow += a;
@@ -69,17 +70,10 @@ static void mul64 (uint64_t *plow, uint64_t *phigh, uint64_t a, uint64_t b)
     *phigh += v;
 }
 
-
 /* Unsigned 64x64 -> 128 multiplication */
 void mulu64 (uint64_t *plow, uint64_t *phigh, uint64_t a, uint64_t b)
 {
-#if defined(__x86_64__)
-    __asm__ ("mul %0\n\t"
-             : "=d" (*phigh), "=a" (*plow)
-             : "a" (a), "0" (b));
-#else
     mul64(plow, phigh, a, b);
-#endif
 #if defined(DEBUG_MULDIV)
     printf("mulu64: 0x%016llx * 0x%016llx = 0x%016llx%016llx\n",
            a, b, *phigh, *plow);
@@ -89,11 +83,6 @@ void mulu64 (uint64_t *plow, uint64_t *phigh, uint64_t a, uint64_t b)
 /* Signed 64x64 -> 128 multiplication */
 void muls64 (uint64_t *plow, uint64_t *phigh, int64_t a, int64_t b)
 {
-#if defined(__x86_64__)
-    __asm__ ("imul %0\n\t"
-             : "=d" (*phigh), "=a" (*plow)
-             : "a" (a), "0" (b));
-#else
     int sa, sb;
 
     sa = (a < 0);
@@ -106,9 +95,9 @@ void muls64 (uint64_t *plow, uint64_t *phigh, int64_t a, int64_t b)
     if (sa ^ sb) {
         neg128(plow, phigh);
     }
-#endif
 #if defined(DEBUG_MULDIV)
     printf("muls64: 0x%016llx * 0x%016llx = 0x%016llx%016llx\n",
            a, b, *phigh, *plow);
 #endif
 }
+#endif /* !defined(__x86_64__) */
diff --git a/host-utils.h b/host-utils.h
index fe306f6e4828927342e66e40bab74fe9f33993da..234a0621824456ed2c8934af23c6ca7b745cd218 100644
--- a/host-utils.h
+++ b/host-utils.h
@@ -23,6 +23,28 @@
  * THE SOFTWARE.
  */
 
+#if defined(__x86_64__)
+#define __HAVE_FAST_MULU64__
+static always_inline void mulu64 (uint64_t *plow, uint64_t *phigh,
+                                  uint64_t a, uint64_t b)
+{
+    __asm__ ("mul %0\n\t"
+             : "=d" (*phigh), "=a" (*plow)
+             : "a" (a), "0" (b));
+}
+#define __HAVE_FAST_MULS64__
+static always_inline void muls64 (uint64_t *plow, uint64_t *phigh,
+                                  int64_t a, int64_t b)
+{
+    __asm__ ("imul %0\n\t"
+             : "=d" (*phigh), "=a" (*plow)
+             : "a" (a), "0" (b));
+}
+#else
+void muls64(int64_t *phigh, int64_t *plow, int64_t a, int64_t b);
+void mulu64(uint64_t *phigh, uint64_t *plow, uint64_t a, uint64_t b);
+#endif
+
 /* Note that some of those functions may end up calling libgcc functions,
    depending on the host machine. It is up to the target emulation to
    cope with that. */
@@ -68,34 +90,13 @@ static always_inline int clz64(uint64_t val)
 {
     int cnt = 0;
 
-    if (!(val & 0xFFFFFFFF00000000ULL)) {
+    if (!(val >> 32)) {
         cnt += 32;
-        val <<= 32;
-    }
-    if (!(val & 0xFFFF000000000000ULL)) {
-        cnt += 16;
-        val <<= 16;
-    }
-    if (!(val & 0xFF00000000000000ULL)) {
-        cnt += 8;
-        val <<= 8;
-    }
-    if (!(val & 0xF000000000000000ULL)) {
-        cnt += 4;
-        val <<= 4;
-    }
-    if (!(val & 0xC000000000000000ULL)) {
-        cnt += 2;
-        val <<= 2;
-    }
-    if (!(val & 0x8000000000000000ULL)) {
-        cnt++;
-        val <<= 1;
-    }
-    if (!(val & 0x8000000000000000ULL)) {
-        cnt++;
+    } else {
+        val >>= 32;
     }
-    return cnt;
+
+    return cnt + clz32(val);
 }
 
 static always_inline int clo64(uint64_t val)
diff --git a/target-alpha/op.c b/target-alpha/op.c
index 2a52be4f4908c1eaa00151738d10e44d52ef64c2..da93e7cdfb50f2a7bbca14b5b568d54787c33c61 100644
--- a/target-alpha/op.c
+++ b/target-alpha/op.c
@@ -22,6 +22,7 @@
 
 #include "config.h"
 #include "exec.h"
+#include "host-utils.h"
 
 #include "op_helper.h"
 
diff --git a/target-i386/helper.c b/target-i386/helper.c
index bb927f673dc6c8bdffcd2288c0a7c988743d6e33..0a75e8c33583aae202991ce6d2ee8f4fe0ef8f6e 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -18,6 +18,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 #include "exec.h"
+#include "host-utils.h"
 
 //#define DEBUG_PCALL