Is CPUTYPE=cortex-A7 supposed to work?

[Mark Millard]

On 2017-Mar-5, at 2:01 AM, Andrew Gierth <andrew at tao11.riddles.org.uk> wrote:

>>>>>> "Mark" == Mark Millard <markmi at dsl-only.net> writes:
> 
>>> 3. The errors aren't consistent at all. For example, sometimes I run
>>> openssl speed rsa512 and it succeeds without error. When testing
>>> with git, the failures were not always at the same place.
> 
> Mark> Interesting. My context had MALLOC_PRODUCTION. I wonder if
> Mark> without that and having junk filled in systematically might
> Mark> produce more stable results. (I've no specific evidence that this
> Mark> would make a difference.)
> 
> I don't think this can explain my results with git; openssl's sha1
> doesn't call malloc (or any library function other than memcpy, memset,
> OPENSSL_cleanse), and I have logs of the data being hashed that show the
> wrong results returned. Also, I've checked that while these hashes are
> being done, there are no other threads in the process.
> 
> -- 
> Andrew.

FYI:

I've updated to -r314687 (so now clang 4.0 based) and
openssl speed still gets the same failures. (By contrast
a pine64+ 2 GiByte [an arm64] worked fine.)

I have not tried a normal build without the -mcpu=cortex-a7
use (or equivalent). Have you?

===
Mark Millard
markmi at dsl-only.net