[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 09 Apr 2015 11:55:34 +0200
From: magnum <john.magnum@...hmail.com>
To: john-dev@...ts.openwall.com
Subject: Re: New SIMD generations, code layout
On 2015-04-09 11:50, Frank Dittrich wrote:
> On 04/09/2015 11:43 AM, magnum wrote:
>> BTW one example of intermittant bug is if there's any align(16) still in
>> there - there's a chance such thing will happen to become aligned for
>> AVX2 but less chance for MIC. Those should result in segfault though, if
>> you only got a FAIL this is probably not it.
>
> Can memdbg builds be enhanced in a way that makes sure the returned
> address matches the required alignment, but not a higher alignment?
> For that purpose, memdbg would need to allocate somewhat more memory,
> and return an appropriate pointer.
> That way, these bugs woudn't be intermittent anymore (at least for
> memdbg builds).
Good idea, memdbg should always do this. BTW my next to-do is run AVX2
with ASan and/or memdbg.
magnum
Powered by blists - more mailing lists
Confused about mailing lists and their use?
Read about mailing lists on Wikipedia
and check out these
guidelines on proper formatting of your messages.
