This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
[wide-int] Handle more add and sub cases inline
- From: Richard Sandiford <rsandifo at linux dot vnet dot ibm dot com>
- To: gcc-patches at gcc dot gnu dot org
- Cc: Kenneth Zadeck <zadeck at naturalbridge dot com>, Mike Stump <mikestump at comcast dot net>
- Date: Thu, 28 Nov 2013 17:38:47 +0000
- Subject: [wide-int] Handle more add and sub cases inline
- Authentication-results: sourceware.org; auth=none
Currently add and sub have no fast path for offset_int and widest_int,
they just call the out-of-line version. This patch handles the
single-HWI cases inline. At least on x86_64, this only adds one branch
per call; the fast path itself is straight-line code.
On the same fold-const.ii testcase, this reduces the number of
add_large calls from 877507 to 42459. It reduces the number of
sub_large calls from 25707 to 148.
Tested on x86_64-linux-gnu. OK to install?
Thanks,
Richard
Index: gcc/wide-int.h
===================================================================
--- gcc/wide-int.h 2013-11-28 13:34:19.596839877 +0000
+++ gcc/wide-int.h 2013-11-28 16:08:11.387731775 +0000
@@ -2234,6 +2234,17 @@ wi::add (const T1 &x, const T2 &y)
val[0] = xi.ulow () + yi.ulow ();
result.set_len (1);
}
+ else if (STATIC_CONSTANT_P (precision > HOST_BITS_PER_WIDE_INT)
+ && xi.len + yi.len == 2)
+ {
+ unsigned HOST_WIDE_INT xl = xi.ulow ();
+ unsigned HOST_WIDE_INT yl = yi.ulow ();
+ unsigned HOST_WIDE_INT resultl = xl + yl;
+ val[0] = resultl;
+ val[1] = (HOST_WIDE_INT) resultl < 0 ? 0 : -1;
+ result.set_len (1 + (((resultl ^ xl) & (resultl ^ yl))
+ >> (HOST_BITS_PER_WIDE_INT - 1)));
+ }
else
result.set_len (add_large (val, xi.val, xi.len,
yi.val, yi.len, precision,
@@ -2288,6 +2299,17 @@ wi::sub (const T1 &x, const T2 &y)
val[0] = xi.ulow () - yi.ulow ();
result.set_len (1);
}
+ else if (STATIC_CONSTANT_P (precision > HOST_BITS_PER_WIDE_INT)
+ && xi.len + yi.len == 2)
+ {
+ unsigned HOST_WIDE_INT xl = xi.ulow ();
+ unsigned HOST_WIDE_INT yl = yi.ulow ();
+ unsigned HOST_WIDE_INT resultl = xl - yl;
+ val[0] = resultl;
+ val[1] = (HOST_WIDE_INT) resultl < 0 ? 0 : -1;
+ result.set_len (1 + (((resultl ^ xl) & (xl ^ yl))
+ >> (HOST_BITS_PER_WIDE_INT - 1)));
+ }
else
result.set_len (sub_large (val, xi.val, xi.len,
yi.val, yi.len, precision,