Re: Re: CRC - Mailing list pgsql-hackers

From Bruce Guenter
Subject Re: Re: CRC
Date
Msg-id 20001208145430.A11989@em.ca
Whole thread Raw
In response to Re: CRC  (ncm@zembu.com (Nathan Myers))
Responses Re: Re: CRC  (Tom Lane <tgl@sss.pgh.pa.us>)
List pgsql-hackers
On Fri, Dec 08, 2000 at 11:10:19AM -0800, Nathan Myers wrote:
> This is very interesting.  MD4 is faster than MD5.  (MD5, described as
> "MD4 with suspenders on", does some extra stuff to protect against more-
> obscure attacks, of no interest to us.)  Which 64-bit CRC code did you
> use, Mark Mitchell's?

Yes.

> Are you really saying MD5 was faster than CRC-32?

Yes.  I expect it's because the operations used in MD5 are easily
parallelized, and operate on blocks of 64-bytes at a time, while the CRC
is mostly non-parallelizable, uses a table lookup, and operates on
single bytes.
--
Bruce Guenter <bruceg@em.ca>                       http://em.ca/~bruceg/

pgsql-hackers by date:

Previous
From: ncm@zembu.com (Nathan Myers)
Date:
Subject: Re: Re: CRC
Next
From: Tom Lane
Date:
Subject: Re: Re: CRC