This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
PATCH: PR target/45483: probably wrong optimization options chosen by "-march=native"
- From: "H.J. Lu" <hongjiu dot lu at intel dot com>
- To: gcc-patches at gcc dot gnu dot org
- Cc: Uros Bizjak <ubizjak at gmail dot com>
- Date: Mon, 6 Sep 2010 08:06:56 -0700
- Subject: PATCH: PR target/45483: probably wrong optimization options chosen by "-march=native"
- Reply-to: "H.J. Lu" <hjl dot tools at gmail dot com>
We may guess best options for -march=native. We may leave out SSE3 or
SSSE3. This patch adds it. OK for trunk and 4.5?
Thanks.
H.J.
----
2010-09-06 H.J. Lu <hongjiu.lu@intel.com>
PR target/45483
* config/i386/driver-i386.c (host_detect_local_cpu): Add -mssse3
or -msse3 if needed.
diff --git a/gcc/config/i386/driver-i386.c b/gcc/config/i386/driver-i386.c
index 8a76857..d132582 100644
--- a/gcc/config/i386/driver-i386.c
+++ b/gcc/config/i386/driver-i386.c
@@ -549,6 +549,9 @@ const char *host_detect_local_cpu (int argc, const char **argv)
case 0x26:
/* Atom. */
cpu = "atom";
+ /* No need to add -mssse3, -msse3. */
+ has_sse3 = 0;
+ has_ssse3 = 0;
break;
case 0x1a:
case 0x1e:
@@ -556,20 +559,34 @@ const char *host_detect_local_cpu (int argc, const char **argv)
case 0x2e:
/* FIXME: Optimize for Nehalem. */
cpu = "core2";
+ /* No need to add -mssse3, -msse3.
+ FIXME: No need for -msse4.2. */
+ has_sse3 = 0;
+ has_ssse3 = 0;
break;
case 0x25:
case 0x2f:
/* FIXME: Optimize for Westmere. */
cpu = "core2";
+ /* No need to add -mssse3, -msse3.
+ FIXME: No need for -msse4.2. */
+ has_sse3 = 0;
+ has_ssse3 = 0;
break;
case 0x17:
case 0x1d:
/* Penryn. FIXME: -mtune=core2 is slower than -mtune=generic */
cpu = "core2";
+ /* No need to add -mssse3, -msse3. */
+ has_sse3 = 0;
+ has_ssse3 = 0;
break;
case 0x0f:
/* Merom. FIXME: -mtune=core2 is slower than -mtune=generic */
cpu = "core2";
+ /* No need to add -mssse3, -msse3. */
+ has_sse3 = 0;
+ has_ssse3 = 0;
break;
default:
if (arch)
@@ -606,6 +623,8 @@ const char *host_detect_local_cpu (int argc, const char **argv)
cpu = "nocona";
else
cpu = "prescott";
+ /* No need to add -msse3. */
+ has_sse3 = 0;
}
else
cpu = "pentium4";
@@ -693,6 +712,10 @@ const char *host_detect_local_cpu (int argc, const char **argv)
options = concat (options, " -msse4.2", NULL);
else if (has_sse4_1)
options = concat (options, " -msse4.1", NULL);
+ else if (has_ssse3)
+ options = concat (options, " -mssse3", NULL);
+ else if (has_sse3)
+ options = concat (options, " -msse3", NULL);
}
done: