[LLVMdev] [PATCH] Detect Haswell subarchitecture (i.e. using -march=native)
craig.topper at gmail.com
Thu Sep 12 23:36:46 PDT 2013
It helps that I'm the one who implemented a portion of the code in
On Thu, Sep 12, 2013 at 11:21 PM, Tim Northover <t.p.northover at gmail.com>wrote:
> > I think your real problem is that garbage went into ECX instead of 0 and
> > caused cpuid to return 0.
> Ah, that looks very likely. The value seems to come from "xorl %eax,
> %eax" in both good object files, but a previous cpuid in the bad one.
> Excellent work Craig, I suspect that would have taken me days to find.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the llvm-dev