[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 16 Sep 2013 13:45:20 -0400
From: Yaniv Sapir <yaniv@...pteva.com>
To: john-dev <john-dev@...ts.openwall.com>
Subject: Re: bcrypt-parallella on 64-core (was: Katja's weekly
report #13)
BTW, in the meantime, you can try to e-read from a couple of cores and see
if the e_group_config object was updated correctly by the loader. It is
placed at 0x28. You can find its members at the e-hal header file.
On Mon, Sep 16, 2013 at 1:00 PM, Katja Malvoni <kmalvoni@...il.com> wrote:
> Hi Alexander, Yaniv,
>
> I found out why test on 64-core Epiphany failed.
> On Epiphany side I do the following to get core number:
>
> int coreID, row, col, corenum;
>
> coreID = e_get_coreid();
> row = e_group_config.core_row;
> col = e_group_config.core_col;
> corenum = row * e_group_config.group_cols + col;
>
> Based on value in corenum variable, cores know from where to fetch data
> and where to write result.
> However, when I modified hello world (/home/linaro/hello-world/) on
> 64-core system to calculate core number, all used cores returned zero as
> corenum value. Yaniv, why does this happen? Except that, some cores return
> empty buffer and I think this shouldn't happen either. This is the output:
>
> 0: Message from eCore 0x9ce ( 7, 6): "Hello World from core 0x9ce! (0)"
> 1: Message from eCore 0x84b ( 1, 3): "Hello World from core 0x84b! (0)"
> 2: Message from eCore 0x84f ( 1, 7): "Hello World from core 0x84f! (0)"
> 3: Message from eCore 0x88c ( 2, 4): ""
> 4: Message from eCore 0x84d ( 1, 5): "Hello World from core 0x84d! (0)"
> 5: Message from eCore 0x88b ( 2, 3): ""
> 6: Message from eCore 0x88b ( 2, 3): ""
> 7: Message from eCore 0x8ce ( 3, 6): "Hello World from core 0x8ce! (0)"
> 8: Message from eCore 0x90a ( 4, 2): "Hello World from core 0x90a! (0)"
> 9: Message from eCore 0x908 ( 4, 0): "Hello World from core 0x908! (0)"
> 10: Message from eCore 0x8c8 ( 3, 0): "Hello World from core 0x8c8! (0)"
> 11: Message from eCore 0x9cd ( 7, 5): "Hello World from core 0x9cd! (0)"
> 12: Message from eCore 0x98a ( 6, 2): "Hello World from core 0x98a! (0)"
> 13: Message from eCore 0x98b ( 6, 3): "Hello World from core 0x98b! (0)"
> 14: Message from eCore 0x8cf ( 3, 7): "Hello World from core 0x8cf! (0)"
> 15: Message from eCore 0x84a ( 1, 2): "Hello World from core 0x84a! (0)"
> 16: Message from eCore 0x98a ( 6, 2): "Hello World from core 0x98a! (0)"
> 17: Message from eCore 0x94f ( 5, 7): "Hello World from core 0x94f! (0)"
> 18: Message from eCore 0x848 ( 1, 0): "Hello World from core 0x848! (0)"
> 19: Message from eCore 0x8ca ( 3, 2): "Hello World from core 0x8ca! (0)"
>
> Katja
>
--
===========================================================
Yaniv Sapir
Adapteva Inc.
1666 Massachusetts Ave, Suite 14
Lexington, MA 02420
Phone: (781)-328-0513 (x104)
Email: yaniv@...pteva.com
Web: www.adapteva.com
============================================================
CONFIDENTIALITY NOTICE: This e-mail may contain information
that is confidential and proprietary to Adapteva, and Adapteva hereby
designates the information in this e-mail as confidential. The information
is
intended only for the use of the individual or entity named above. If you
are
not the intended recipient, you are hereby notified that any disclosure,
copying,
distribution or use of any of the information contained in this
transmission is
strictly prohibited and that you should immediately destroy this e-mail and
its
contents and notify Adapteva.
==============================================================
Content of type "text/html" skipped
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.
