On 12/28/2013 12:27 AM, Gordan Bobic wrote:
On 12/27/2013 04:02 PM, Richard W.M. Jones wrote:
On Fri, Dec 27, 2013 at 09:53:54AM +0000, Gordan Bobic wrote:
How is transparent alignment fixup going to give you back the
performance you lose from accesses straddling cache lines?
You can have structs straddling cache lines and causing performance
problems without alignment issues, or structs being packed too close
together causing false sharing again w/o alignment being involved.
If alignment problems cause performance issues, then we should deal
with those performance problems. If they don't, we shouldn't worry
about them.
Rich.
ObHack: I once worked with an architecture [68k-based VME hardware]
that not only faulted on unaligned access, but also on accesses of the
wrong *size* (eg. using a short-sized read instruction instead of a
word-sized read instruction). Dealing with that nonsense involved a
lot of compiler-specific massaging of code and some inline assembly ...
I'm very glad you mentioned compilers - this is in fact easily fixable
at compiler level. Intel's ICC has an option to make all arrays and
structs always aligned to a boundary (up to 16 byte, IIRC). If GCC
were to implement such a feature the problem could be made to go away
without actually addressing the underlying cause of the problem. It
might be a bodge, but since complete fix of the underlying problem
isn't going to happen anyway, a good bodge would be a lot better than
doing nothing.
Gordan
How does this in any way related to the alignment problem? All C
compilers align arrays and structures in sensible ways by default. They
have to. Its a requirement of the C language. Problems come from things
like pointing directly at elements in communication structures, which
may not be naturally aligned. They can also come from overriding the
default alignment of arrays and structures, which most compilers permit
these days, with a varierty of constructs like "#pragma pack(1)"
Regards,
Steve
_______________________________________________
arm mailing list
arm@lists.fedoraproject.org
https://admin.fedoraproject.org/mailman/listinfo/arm