[MPlayer-dev-eng] [PATCH] cpu detection for core2
Loren Merritt
lorenm at u.washington.edu
Sun Jun 3 07:33:46 CEST 2007
The configure code to detect core2 in 64bit mode was different from 32bit
mode, and didn't work on my core2. This changes it to be the same as
32-bit mode, which works.
Also, -march=k8 is faster than -march=nocona when run on a core2. Or
should it be -mtune=k8 with no -march, to avoid amd-specific instructions?
-march=k8 works for me, but that doesn't mean it's theoretically correct.
(Of course -march=core2 is the most appropriate, but that's only in gcc
>=4.2)
--Loren Merritt
-------------- next part --------------
--- configure (revision 23457)
+++ configure (working copy)
-1845,13 +1845,13 @@
AuthenticAMD)
proc=k8;;
GenuineIntel)
- case "$pmodel" in
- 6) proc=core2;;
- *)
+ if test "$pfamily" -eq 6 -a "$pmodel" -ge 15; then
+ proc=core2
+ else
# 64-bit prescotts exist, but as far as GCC is concerned they
# have the same capabilities as a nocona.
- proc=nocona;;
- esac
+ proc=nocona
+ fi
;;
*)
proc=error;;
@@ -1876,6 +1876,9 @@
fi
# --- Intel processors ---
if test "$proc" = "core2"; then
+ cc_check -march=$proc $cpuopt=$proc || proc=k8
+ fi
+ if test "$proc" = "k8"; then
cc_check -march=$proc $cpuopt=$proc || proc=nocona
fi
if test "$proc" = "nocona"; then
More information about the MPlayer-dev-eng
mailing list