[Bug middle-end/39677] AMD Opteron E needs workaround for lock erratum

2009-04-07 Thread bonzini at gnu dot org
--- Comment #2 from bonzini at gnu dot org 2009-04-07 15:02 --- I cannot see any better alternative, but I'll point out that saying "wrong-code" is not exact. -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=39677

[Bug middle-end/39677] AMD Opteron E needs workaround for lock erratum

2009-04-07 Thread bonzini at gnu dot org
--- Comment #1 from bonzini at gnu dot org 2009-04-07 13:42 --- More info from Solaris bug # 6323525: if (number_of_cores() < 2) then don't have bug if (family == 0xf && Model < 0x40) then have bug if (rdmsr(MSR_BU_CFG/*0xC0011023*/) & 2) then bug is masked See also http://bugzilla.ker