Use STRICT_ASSIGN() for exp2f() and exp2() instead of a volatile

variable hack for exp2f() only.

The volatile variable had a surprisingly large cost for exp2f() -- 19
cycles or 15% on i386 in the worst case observed.  This is only partly
explained by there being several references to the variable, only one
of which benefited from it being volatile.  Arches that have working
assignment are likely to benefit even more from not having any volatile
variable.

exp2() now has a chance of working with extra precision on i386.

exp2() has even more references to the variable, so it would have been
pessimized more by simply declaring the variable as volatile.  Even
the temporary volatile variable for STRICT_ASSIGN costs 5-10% on i386,
(A64) so I will change STRICT_ASSIGN() to do an ordinary assignment
until i386 defaults to extra precision.

2 files changed, 5 insertions, 4 deletions

diff --git a/lib/msun/src/s_exp2.c b/lib/msun/src/s_exp2.c
index 464e39c7b8d8..56554f180737 100644
--- a/lib/msun/src/s_exp2.c
+++ b/lib/msun/src/s_exp2.c
@@ -364,7 +364,7 @@ exp2(double x)
 	}
 
 	/* Reduce x, computing z, i0, and k. */
-	t = x + redux;
+	STRICT_ASSIGN(double, t, x + redux);
 	GET_LOW_WORD(i0, t);
 	i0 += TBLSIZE / 2;
 	k = (i0 >> TBLBITS) << 20;
diff --git a/lib/msun/src/s_exp2f.c b/lib/msun/src/s_exp2f.c
index 0a6142ffb431..db8542cc633d 100644
--- a/lib/msun/src/s_exp2f.c
+++ b/lib/msun/src/s_exp2f.c
@@ -27,6 +27,8 @@
 #include <sys/cdefs.h>
 __FBSDID("$FreeBSD$");
 
+#include <float.h>
+
 #include "math.h"
 #include "math_private.h"
 
@@ -91,8 +93,7 @@ float
 exp2f(float x)
 {
 	double tv;
-	float r, z;
-	volatile float t;	/* prevent gcc from using too much precision */
+	float r, t, z;
 	uint32_t hx, hr, ix, i0;
 	int32_t k;
 
@@ -115,7 +116,7 @@ exp2f(float x)
 	}
 
 	/* Reduce x, computing z, i0, and k. */
-	t = x + redux;
+	STRICT_ASSIGN(float, t, x + redux);
 	GET_FLOAT_WORD(i0, t);
 	i0 += TBLSIZE / 2;
 	k = (i0 >> TBLBITS) << 23;