Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sun, 1 Apr 2012 23:02:10 +0300
From: Milen Rangelov <>
Subject: Re: fast hashes on GPU

Well, those are profiler stats from my sha256 and sha512 kernels:

sha256 (using uint4 vectors):

Used GPRs = 36
ALU ops = 1654

sha512 (using uint2 vectors):

Used GPRs = 51
ALU ops = 5283

So in fact SHA512 is doing ~3.2x more ALU operations to process 2x less
hashes. GPR utilization of 51 badly  hampers occupancy as well.

On Sun, Apr 1, 2012 at 7:16 AM, Solar Designer <> wrote:

> Yes, I expected that SHA-512 would be less efficient on AMD/ATI GPUs
> compared to many other hash types on the same hardware.  10x slower than
> SHA-256 is extreme, though.  I thought/think that the difference should
> be less.
> > On NVidia, situation is somewhat better though.
> Yes, that's my expectation, although it's largely due to other
> ("competing") hash types being less efficient there (no rotate and
> bitselect anyway).  I think the only major reason why SHA-512 may be
> more than twice slower than SHA-256 on current Nvidia GPUs is the
> increased register pressure.  Right?
> As you probably recall, we picked raw SHA-512 (and its salted variants)
> for one of the first "fast" hashes to experiment with precisely because
> it is on the slower side of the fast hashes and thus should fit in the
> current formats interface better.  For faster fast hashes, we'll need to
> proceed with more invasive changes.
> Alexander

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.