Re: Re: CRC - Mailing list pgsql-hackers

From Tom Lane
Subject Re: Re: CRC
Date
Msg-id 3457.976311058@sss.pgh.pa.us
Whole thread Raw
In response to Re: Re: CRC  (Bruce Guenter <bruceg@em.ca>)
Responses Re: Re: CRC  (Bruce Guenter <bruceg@em.ca>)
List pgsql-hackers
Bruce Guenter <bruceg@em.ca> writes:
>> 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.

What MD5 implementation did you use?  The one I have handy (the original
RSA reference version) sure looks like it's more computation per byte
than a CRC.
        regards, tom lane


pgsql-hackers by date:

Previous
From: Tom Lane
Date:
Subject: Re: Re: CRC
Next
From: Tom Lane
Date:
Subject: Hash index on macaddr -> crash