PDA

View Full Version : floating point speed compare of AMD and Intel chips


Bob Fry
October 15th 07, 06:19 PM
From: ] On Behalf Of Justin Penney
Sent: Thursday, October 11, 2007 8:17 AM
To:
Subject: [Beowulf] Re: Intel quad core nodes?

I recently ran a customer's weather modeling code on a variety of
machines. This program is very sensitive to memory. The following are
the run times while running 4 processes. Please note that the Xeon,
Opteron and Barcelona numbers are from dual socket machines.

Core 2 Quad 2.4 GHz - 3h16m
Xeon Quad 2.0 GHz - 2h51m
Barcelona 2.0 GHz - 1h40m
Opteron 2220SE 2.8 GHz - 2h24m

At 8 processes:

Xeon Quad 2.0 GHz - 2h52m
Barcelona 2.0 GHz - 1h22m


--
I can envision a small cottage somewhere, with a lot of writing paper,
and a dog, and a fireplace and maybe enough money to give myself some
Irish coffee now and then and entertain my two friends.
~ Richard Van de Geer, letter, 1975, last American to die in Vietnam War, Time, 1985

Wolfie2k7
October 21st 07, 01:19 PM
On Mon, 15 Oct 2007 10:19:30 -0700, Bob Fry >
wrote:

>From: ] On Behalf Of Justin Penney
>Sent: Thursday, October 11, 2007 8:17 AM
>To:
>Subject: [Beowulf] Re: Intel quad core nodes?
>
>I recently ran a customer's weather modeling code on a variety of
>machines. This program is very sensitive to memory. The following are
>the run times while running 4 processes. Please note that the Xeon,
>Opteron and Barcelona numbers are from dual socket machines.
>
> Core 2 Quad 2.4 GHz - 3h16m
> Xeon Quad 2.0 GHz - 2h51m
> Barcelona 2.0 GHz - 1h40m
> Opteron 2220SE 2.8 GHz - 2h24m
>
>At 8 processes:
>
> Xeon Quad 2.0 GHz - 2h52m
> Barcelona 2.0 GHz - 1h22m

Sweet! Just a couple of questions - how were these chips rigged up?
How much RAM on board? What OS were you running? Details, man!
Details!

Bob Fry
October 21st 07, 11:35 PM
>>>>> "w" == wolfie2k7 > writes:

w> Sweet! Just a couple of questions - how were these chips rigged
w> up? How much RAM on board? What OS were you running? Details,
w> man! Details!

I'll ask on the email list, and post again here. Might be a few days....

--
The injury we do and the one we suffer are not weighed in the same
scale.
~ Aesop

Bob Fry
October 22nd 07, 04:25 PM
>>>>> "w" == wolfie2k7 > writes:

w> On Mon, 15 Oct 2007 10:19:30 -0700, Bob Fry
w> >
w> wrote:

>> From:
>> ] On Behalf Of Justin Penney
>> Sent: Thursday, October 11, 2007 8:17 AM To:
>> Subject: [Beowulf] Re: Intel quad core
>> nodes?
>>
>> I recently ran a customer's weather modeling code on a variety
>> of machines. This program is very sensitive to memory. The
>> following are the run times while running 4 processes. Please
>> note that the Xeon, Opteron and Barcelona numbers are from dual
>> socket machines.
>>
>> Core 2 Quad 2.4 GHz - 3h16m Xeon Quad 2.0 GHz - 2h51m Barcelona
>> 2.0 GHz - 1h40m Opteron 2220SE 2.8 GHz - 2h24m
>>
>> At 8 processes:
>>
>> Xeon Quad 2.0 GHz - 2h52m Barcelona 2.0 GHz - 1h22m

w> Sweet! Just a couple of questions - how were these chips rigged
w> up? How much RAM on board? What OS were you running? Details,
w> man! Details!

Looks like we'll have to wait a bit:

From: ] On Behalf Of Justin Penney
Sent: Monday, October 15, 2007 11:57 AM
To:
Subject: Re: [Beowulf] Re: Intel quad core nodes?

> I assume these are all one-system results?
> MPI or OpenMP?
> Looks like the Xeon Quad and Barcelona results must have been run with
> 2 processes per socket?
> Was it one executable? Compiled/optimized on what platform?
>
> Very interesting data, you may just want to provide the list with some
> additional details, so they know what to make of the data.
>
> -Tom

These are single system results with MVAPICH. They will run on
InfiniBand which is why MVAPICH was used.

The quad core runs were 2 processes per socket.

The executables were created with the latest Portland Group f90 and
the optimisation flags were used for each chip. The Barcelona binary
used "-tp barcelona-64" and the Xeon binary used "-tp core2-64."

As soon as I am able I will be running this test on Harpertown
[note: http://en.wikipedia.org/wiki/Xeon#5400-series_Harpertown_and_5200-series_Wolfdale]
processors. I should then have permission to publish the details of
the testing.

--
justin penney
email:
phone: 913.643.0300 option 2
im: http://livehelp.advancedclustering.com/

_______________________________________________
Beowulf mailing list,

--
The reasonable man adjusts himself to the world, the unreasonable one
persists in trying to adapt the world to himself; therefore all
progress depends on the unreasonable man.
~ George Bernard Shaw