[Qemu-devel] [PATCH 2/2] qemu-common.h: optimise muldiv64 for x86_64 architecture

[Frediano Ziglio]

As this platform can do multiply/divide using 128 bit precision use
these instructions to implement it.

Signed-off-by: Frediano Ziglio <address@hidden>
---
 include/qemu-common.h | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/qemu-common.h b/include/qemu-common.h
index f3033ae..880659d 100644
--- a/include/qemu-common.h
+++ b/include/qemu-common.h
@@ -370,11 +370,23 @@ static inline uint8_t from_bcd(uint8_t val)
 }
 
 /* compute with 96 bit intermediate result: (a*b)/c */
-#ifdef CONFIG_INT128
+#if defined(CONFIG_INT128) && !defined(__x86_64__)
 static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c)
 {
     return (__int128)a * b / c;
 }
+#elif defined(__x86_64__)
+/* Optimised x64 version. This assume that a*b/c fits in 64 bit */
+static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c)
+{
+    uint64_t res;
+
+    asm ("mulq %2\n\tdivq %3"
+         : "=a"(res)
+         : "a"(a), "qm"((uint64_t) b), "qm"((uint64_t)c)
+         : "rdx", "cc");
+    return res;
+}
 #else
 static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c)
 {
-- 
1.9.1