[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [ethmac] RE: doubt!!
i am engaging in 10GE too!
i met a problem which you have solved successfully!
i want to calculate the 64bits wide CRC32 with altera apexII device,
but the right simulation result can't be achieved,because of multi XOR in
one clock cycle.
so i try to use the fast CRC32 method described in R.J.glaise "fast crc
calculation", and then use the two-step CRC32 calculation method.
in this way, the whole CRC32 calculation can be done with a max XOR of
4 or 5, and can be realized in the apexII device.
But the big problem is i can't get the right simulation result with the
method described in the "fast crc calculation". am i missing something?
how about the initial value setting?
and are you using this algorism too?
could you desribe your algorism in calculating 64bits CRC32 for 10GE?
i will appreciate you very much ,if you answer it soon!!!
----- Original Message -----
From: "Illan Glasner" <iglasner@z... >
To: "Muthumari S - CTD, Chennai." <muthus@c... >
<ethmac@o... >
Date: Fri, 8 Feb 2002 12:58:03 -0800
Subject: [ethmac] RE: doubt!!
>
>
>
> Hi,
>
> This question I was already been asked in the past and so incase
> other looking for the same info, if you are using any interface
> which is wider than your input data you need to preload your crc
> machine with value differ than the all 1's.
>
> assumign you are working in boundary of byte than the value are :
>
> 8 (10011011111100011010100100001111)
> 16 (00001001101110010011100001011001)
> 24 (10000001011001000111010011000101)
> 32 (01000110101011110110010001001001)
> 40 (00110011100111111101111000101111)
> 48 (01101000101110010011001011110101)
> 56 (10010101010110100110000101100010)
>
> the above mean if the data have 8 bit less than the full input use
> the first line if it have 16 bit less than use the seocnd line etc
> up to 56 bit.
>
> BTW there is really no reason to developed crc machine it is a
> waste of time and lot of work using excell spread sheet. simple go
> to http://www.easics.be/webtools/crctool which put an excelent tool
> that will generate for you the crc equation and save time.
>
> have a nice day
>
> Illan
>
>
> -----Original Message-----
> From: Muthumari S - CTD, Chennai. [mailto:muthus@c... ]
> Sent: Thursday, January 10, 2002 7:18 AM
> To: Illan Glasner
> Subject: doubt!!
>
>
>
> I developed a verilog module to calculate crc-32; 64bits (8bytes)
> at a time.
> As long as i have the data width of 8 bytes i don't have any
> problem with my
> module. I am going to use this module for 10gbps ethernet
> application. so,
> if the data frame length is not multiple of 8bytes; how should i
> calculate
> crc-32. ie., if my last 8bytes, not necessarily all the bytes are
> valid.
>
> say, for example if only 3 most significant bytes are valid in my
> last
> 8bytes of data. How could i modify the data so as to get the crc-32
> value
> valid only for that 3bytes in the last 8bytes.
>
> For the past 1 week i have been browsing the internet to get answer
> for
> this, But i couldn't get anything.
>
> Can u give me an idea to get out of this problem?????
>
>
> Thanks in advance.
>
>
> Regards,
>
> S.Muthumari
> MTS
> HCL Technologies Ltd.,
> Chennai.
> Mail ID : muthus@c...
>
> Ph: 6230711( 4-lines ) Extn : 2539
> "one who desires nothing for himself, is desired by all"
>
> Disclaimer:
> This document is intended for transmission to the named recipient
> only. If
> you are not that person, you should note that legal rights reside
> in this
> document and you are not authorized to access, read, disclose,
> copy, use or
> otherwise deal with it and any such actions are prohibited and may
> be
> unlawful. The views expressed in this document are not necessarily
> those of
> HCL Technologies Ltd. Notice is hereby given that no
> representation,
> contract or other binding obligation shall be created by this
> e-mail, which
> must be interpreted accordingly. Any representations, contractual
> rights or
> obligations shall be separately communicated in writing and signed
> in the
> original by a duly authorized officer of the relevant company.
>
--
To unsubscribe from ethmac mailing list please visit http://www.opencores.org/mailinglists.shtml