Add MULX intrinsics.

gcc/

2011-09-21  Kirill Yukhin  <kirill.yukhin@intel.com>

	* config/i386/bmi2intrin.h (_mulx_u64): New.
	(_mulx_u32): Ditto.

gcc/testsuite/

2011-09-21  Kirill Yukhin  <kirill.yukhin@intel.com>

	* gcc.target/i386/bmi2-mulx32-2.c: New test.
	* gcc.target/i386/bmi2-mulx32-2a.c: Ditto.
	* gcc.target/i386/bmi2-mulx64-2.c: Ditto.
	* gcc.target/i386/bmi2-mulx64-2a.c: Ditto.

From-SVN: r179050

gcc/ChangeLog

+2011-09-21  Kirill Yukhin  <kirill.yukhin@intel.com>
+
+	* config/i386/bmi2intrin.h (_mulx_u64): New.
+	(_mulx_u32): Ditto.
+
 2011-09-21  Jan Hubicka  <jh@suse.cz>
 
 	PR tree-optimization/50433

gcc/config/i386/bmi2intrin.h

@@ -76,6 +76,27 @@ _pext_u64 (unsigned long long __X, unsigned long long __Y)
   return __builtin_ia32_pext_di (__X, __Y);
 }
 
-#endif /* __x86_64__  */
+extern __inline unsigned long long
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mulx_u64 (unsigned long long __X, unsigned long long __Y,
+	   unsigned long long *__P)
+{
+  unsigned __int128 __res = (unsigned __int128) __X * __Y;
+  *__P = (unsigned long long) (__res >> 64);
+  return (unsigned long long) __res;
+}
+
+#else /* !__x86_64__ */
+
+extern __inline unsigned int
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mulx_u32 (unsigned int __X, unsigned int __Y, unsigned int *__P)
+{
+  unsigned long long __res = (unsigned long long) __X * __Y;
+  *__P = (unsigned int) (__res >> 32);
+  return (unsigned int) __res;
+}
+
+#endif /* !__x86_64__  */
 
 #endif /* _BMI2INTRIN_H_INCLUDED */

gcc/testsuite/ChangeLog

+2011-09-21  Kirill Yukhin  <kirill.yukhin@intel.com>
+
+	* gcc.target/i386/bmi2-mulx32-2.c: New test.
+	* gcc.target/i386/bmi2-mulx32-2a.c: Ditto.
+	* gcc.target/i386/bmi2-mulx64-2.c: Ditto.
+	* gcc.target/i386/bmi2-mulx64-2a.c: Ditto.
+
 2011-09-21  Eric Botcazou  <ebotcazou@adacore.com>
 
 	* gnat.dg/opt19.adb: New test.

gcc/testsuite/gcc.target/i386/bmi2-mulx32-2.c

+/* { dg-do run { target { bmi2 && { ia32 } } } } */
+/* { dg-options "-mbmi2 -O2" } */
+
+#include <x86intrin.h>
+
+#include "bmi2-check.h"
+
+__attribute__((noinline))
+unsigned long long
+calc_mul_u32 (unsigned volatile a, unsigned b)
+{
+  unsigned long long res = 0;
+  int i;
+  for (i = 0; i < b; ++i)
+    res += a;
+
+  return res;
+}
+
+__attribute__((noinline))
+unsigned calc_mulx_u32 (unsigned x, unsigned y, unsigned *res_h)
+{
+  return (unsigned) _mulx_u32 (x, y, res_h);
+}
+
+static void
+bmi2_test ()
+{
+  unsigned i;
+  unsigned a = 0xce7ace0;
+  unsigned b = 0xfacefff;
+  unsigned res_l, res_h;
+  unsigned long long res, res_ref;
+
+  for (i = 0; i < 5; ++i) {
+    a = a * (i + 1);
+    b = b / (i + 1);
+
+    res_ref = calc_mul_u32 (a, b);
+    res_l = calc_mulx_u32 (a, b, &res_h);
+
+    res = ((unsigned long long) res_h << 32) | res_l;
+
+    if (res != res_ref)
+      abort();
+  }
+}

gcc/testsuite/gcc.target/i386/bmi2-mulx32-2a.c

+/* { dg-do compile { target { ia32 } } } */
+/* { dg-options "-O2 -mbmi2" } */
+
+#include "bmi2-mulx32-2.c"
+
+/* { dg-final { scan-assembler-times "mulx\[ \\t\]+\[^\n\]*" 1 } } */

gcc/testsuite/gcc.target/i386/bmi2-mulx64-2.c

+/* { dg-do run { target { bmi2 && { ! ia32 } } } } */
+/* { dg-options "-mbmi2 -O2" } */
+
+#include <x86intrin.h>
+#include "bmi2-check.h"
+
+__attribute__((noinline))
+unsigned __int128
+calc_mul_u64 (unsigned long long volatile a, unsigned long long b)
+{
+  unsigned __int128 res = 0;
+  int i;
+  for (i = 0; i < b; ++i)
+    res += (unsigned __int128) a;
+
+  return res;
+}
+
+__attribute__((noinline))
+unsigned long long
+calc_mulx_u64 (unsigned long long x,
+	       unsigned long long y,
+	       unsigned long long *res_h)
+{
+  return _mulx_u64 (x, y, res_h);
+}
+
+
+static void
+bmi2_test ()
+{
+  unsigned i;
+  unsigned long long a = 0xce7ace0ce7ace0;
+  unsigned long long b = 0xface;
+  unsigned long long res_l, res_h;
+  unsigned __int128 res, res_ref;
+
+  for (i=0; i<5; ++i) {
+    a = a * (i + 1);
+    b = b / (i + 1);
+
+    res_ref = calc_mul_u64 (a, b);
+
+    res_l = calc_mulx_u64 (a, b, &res_h);
+
+    res = ((unsigned __int128) res_h << 64) | res_l;
+
+    if (res != res_ref)
+      abort();
+  }
+}

gcc/testsuite/gcc.target/i386/bmi2-mulx64-2a.c

+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mbmi2" } */
+
+#include "bmi2-mulx64-2.c"
+
+/* { dg-final { scan-assembler-times "mulx\[ \\t\]+\[^\n\]*" 1 } } */