throughput of GnuPG symmetric ciphers

Henry Hertz Hobbit hhhobbit7 at
Wed Aug 3 07:47:41 CEST 2005

>Date: Mon, 1 Aug 2005 12:48:11 -0500
>From: Ryan Malayter <malayter at>
>Subject: throughput of GnuPG symmetric ciphers
>To: Gnupg-users at
>Message-ID: <5d7f074205080110486555f04d at>
>Content-Type: text/plain; charset=ISO-8859-1
>I'm reposting this because it never appeared on the list for some
>reason, even after 12 hours.
>I was going to use GnuPG for encrypting some very large backup files
>on disk (~200 GB). However, the symmetric ciphers in GnuPG seem to be
>fairly slow. Using the Windows build of 1.4.2, I only modest
>throughputs piping GPG output from a fast 7200 RPM disk to >NUL (the
>Windows equivalent of /dev/nul). (See table at end of email).
>The process is not disk bound, since it uses 100% CPU and the
>different algorithms take different times. Compression was turned off.
>I have seen references on the net to fast software implementations of
>AES that are an order of magnitude faster than GnuPG on a P4 (~1.5
>Gbps). See

I have read what you have given, but this is a tuned and specifically
tailored version of AES.  Further, it is an advertising spiel rather
than a fair, unbiased quantitative analysis of both the software version
of AES, and the Eden processor.  I suspect the actual speeds are 3-4
times of GnuPG for the software, but the hardware version is probably
signicantly faster than software.  This begs the entire question
though.  Read on and you will see why I say that.

>Has anyone made a GnuPG patch that includes faster implementations of
>the core symmetric algorithms?

I don't know the answer to this quetion.  I suspect that it has not been
done.  The problem with tailoring it for speed is that you then lock
your way onto one specific CPU chip, whereas GnuPG was meant to be
portable across a broad variety of chips from SPARC RISC, PowerPC,
Intel, etc.

>What other tools are people using for encrypting backups in datacenter
>operations (as GnuPG seems to be too slow for this task)?
>Thanks for any help,
> Ryan
>Tests encrypting a 1 GB file on a 2.4 GHz Pentium 4.
>Cipher Algorithm   Speed (Mbps)
>CAST5              153.39
>BLOWFISH           59.24
>AES                102.26
>3DES               64.59
>AES-256            81.81
>TWOFISH            124.49
>   RPM

Given the size of the files that you are encrypting, I would strongly
advise going with the Eden chip rather than a software based solution.
So you achieve a performance advantage that cuts the times to 1/4 at
best for something other than GnuPG via software.  Is that still going
to cut it for what you are doing?  You never said how often you are
going to do it, but 200 GB files are HUGE!  I strongly advise going with
the Eden or other hardware chips optimized for encryption for your

Then on the other hand, maybe somebody will optimize the algorithm for
your specific purpose for the price (I am NOT offering my services - I
leave that for others to pursue).

Key Name:  "Henry Hertz Hobbit" <hhhobbit at>
pub   1024D/E1FA6C62 2005-04-11 [expires: 2006-04-11]
Key fingerprint = ACA0 B65B E20A 552E DFE2 EE1D 75B9 D818 E1FA 6C62

Switch to Netscape Internet Service.
As low as $9.95 a month -- Sign up today at

Netscape. Just the Net You Need.

New! Netscape Toolbar for Internet Explorer
Search from anywhere on the Web and block those annoying pop-ups.
Download now at

More information about the Gnupg-users mailing list