s_sinf.c: Replace floor with simple casts

Since s_sinf.c either assigns the return value of floor to integer or
passes double converted from integer to floor, this patch replaces
floor with simple casts.

Also since long == int for 32-bit targets, we can use long instead of
int to avoid 64-bit integer for 64-bit targets.

On Skylake, bench-sinf reports performance improvement:

           Before        After         Improvement
max        130.566       129.564           30%
min        7.704         7.706             0%
mean       21.8188       19.1363           30%

	* sysdeps/ieee754/flt-32/s_sinf.c (reduced): Replace long with
	int.
	(SINF_FUNC): Likewise.  Replace floor with simple casts.

diff --git a/ChangeLog b/ChangeLog
index f36d934c5237e1559f5feb9ff48df90e3d03475d..5636a571fa838c610646d60159eed6a369ec5a85 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+2017-12-05  H.J. Lu  <hongjiu.lu@intel.com>
+
+       * sysdeps/ieee754/flt-32/s_sinf.c (reduced): Replace long with
+       int.
+       (SINF_FUNC): Likewise.  Replace floor with simple casts.
+
 2017-12-05  Mike FABIAN  <mfabian@redhat.com>
 
        [BZ #22517]

diff --git a/sysdeps/ieee754/flt-32/s_sinf.c b/sysdeps/ieee754/flt-32/s_sinf.c
index 40d3d197a829c9996301daf5446de58983d65757..0b76477d227995408774bd68841a87ef0dba2f06 100644 (file)
--- a/sysdeps/ieee754/flt-32/s_sinf.c
+++ b/sysdeps/ieee754/flt-32/s_sinf.c
@@ -85,8 +85,8 @@ static const int ones[] = { +1, -1 };
    SIGNBIT is used to add the correct sign after the Chebyshev
    polynomial is computed.  */
 static inline float
-reduced (const double theta, const unsigned long int n,
-        const unsigned long int signbit)
+reduced (const double theta, const unsigned int n,
+        const unsigned int signbit)
 {
   double sx;
   const double theta2 = theta * theta;
@@ -162,14 +162,14 @@ SINF_FUNC (float x)
     }
   else                          /* |x| >= Pi/4.  */
     {
-      unsigned long int signbit = (x < 0);
+      unsigned int signbit = (x < 0);
       if (abstheta < 9 * M_PI_4)        /* |x| < 9*Pi/4.  */
        {
          /* There are cases where FE_UPWARD rounding mode can
             produce a result of abstheta * inv_PI_4 == 9,
             where abstheta < 9pi/4, so the domain for
             pio2_table must go to 5 (9 / 2 + 1).  */
-         unsigned long int n = (abstheta * inv_PI_4) + 1;
+         unsigned int n = (abstheta * inv_PI_4) + 1;
          theta = abstheta - pio2_table[n / 2];
          return reduced (theta, n, signbit);
        }
@@ -177,8 +177,8 @@ SINF_FUNC (float x)
        {
          if (abstheta < 0x1p+23)     /* |x| < 2^23.  */
            {
-             unsigned long int n = __floor (abstheta * inv_PI_4) + 1.0;
-             double x = __floor (n / 2.0);
+             unsigned int n = ((unsigned int) (abstheta * inv_PI_4)) + 1;
+             double x = n / 2;
              theta = x * PI_2_lo + (x * PI_2_hi + abstheta);
              /* Argument reduction needed.  */
              return reduced (theta, n, signbit);