[Beowulf] CCL:Experiences with 64 bits AMD processors (fwd from marc at klingon.uab.es)

Michael Will mwill at penguincomputing.com
Wed Jun 16 09:45:02 PDT 2004


On Tuesday 15 June 2004 09:21 pm, Eugen Leitl wrote:
> From: Marc Noguera Julian <marc at klingon.uab.es>
> Date: Tue, 10 Jun 2003 19:09:00 +0200
> To: chemistry at ccl.net
> Subject: CCL:Experiences with 64 bits AMD processors
> User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.6) Gecko/20040113
>
> Hello,
> we  are interested in buying some more computational resources. In our
> group we are interested in 64 bit AMD processors, but we do not know
> about their compatibility. They are supposed, as AMD says,  to be32 bit
> compatible and therefore AMD 64 bit processor should be able to run any
> 32 bit application. Is that true? Any experience about this will help us
> a lot.
It is true. In fact you can run 32bit and 64bit processes at the same time. 

The 32bit processes will be limited to a 4G address space *each* which is more 
than what you can get on a pure 32bit system. The 64bit processes will not 
have a limit that is meaningful at the current technology level (terabytes of 
ram)

Recompiling your software in 64bit mode (which is the default, you can specify 
-m32 if you insist on 32bit executables) will make your software run faster:

    * 8 extra registers in 64bit mode can be used to toolchains advantage
    * improved calling conventions where function arguments are passed in 
registers and not on the stack.
    * fewer architectural instructions for the same source code. Code tends to 
stay within 10% of 32bit x86 code. Main reason for larger code is longer 
instructions. Number of instructions itself decreases by about 10%. Fewer 
instructions means faster execution.
    * usage of SSE2 unit for floatpoint arithmetic with flat 16 register file 
instead of x87 FPU with its cumbersome register stack.
    * bigger address space means less IO ops.
    * SuSE uses syscall (faster than int 0x80) instruction in kernel and 
libc).

Source: http://www.suse.com/en/business/products/server/sles/sles8_amd64.pdf 

> By the way, we are running mainly gaussian jobs, and have some other 32
> bit binaries like turbomole and jaguar. We have source code license for
> gaussian 03. Has anyone tried to compile Gaussian 03 for a AMD 64 bit
> machine? 

You can try that on our testcluster if you like.

> Do 32 bit pentium binaries run correctly on a 64 bit processor? 
Yes.

> which is the increase on the performance? 
Depends on what it does exactly, but I would expect about 10% if it is not 
very RAM intensive and a lot more if it is.

> Do Turbomole and Jaguar 
> binaries run on 64 bit AMD processors? anyone tried?
I test-ran jaguar on an opteron before and it looked fine.

Michael Will
-- 
Michael Will, Linux Sales Engineer
NEWS: We have moved to a larger iceberg :-)
NEWS: 300 California St., San Francisco, CA.
Tel:  415-954-2822  Toll Free:  888-PENGUIN
Fax:  415-954-2899 
www.penguincomputing.com




More information about the Beowulf mailing list