InvestorsHub Logo

chipguy

09/07/07 9:03 PM

#47619 RE: mas #47618

Houston, we just lost HPC ;-)

Nah, AMD lost everything but HPC. Fortunately for AMD
it was far more successful with Opteron in HPC than any
other x86 server segment so Barcelona's short comings
will mainly prevent expansion outside its existing HPC
customer base rather than accelerate its erosion.

The real problem for AMD is when it tries to migrate its
K10 design to the client space. A shortage of shippable
GHz will be very painful there.

tecate

09/07/07 9:12 PM

#47620 RE: mas #47618

I'm sure AMD will find niche.

wbmw

09/07/07 10:02 PM

#47621 RE: mas #47618

Re: Houston, we just lost HPC ;-)

Mas, what is that, the last message from AMD to Michael?

Time to tell Hector that Dell is in Austin. <VBG>

imho

09/07/07 10:28 PM

#47623 RE: mas #47618

mas,

Houston, we just lost HPC ;-)

You mean, "Austin, we just lost..........come in Austin..... Austin come in..."

;-))

IMHO

mas

09/09/07 2:44 PM

#47680 RE: mas #47618

IBM posts LS-DYNA benchmark results for quad-core x3455 server
September 10, 2007 ... IBM® today announced results for the IBM System x™ 3455 running the
LS-DYNA benchmark with the 3cars (3 vehicle collision) workload.
The x3455 server achieved an elapsed time of 31,526 seconds, which is better than the 32,578
seconds of elapsed time achieved by a single-node 8-core blade system using the Quad-Core
Intel® Xeon® X5355 processor at 2.66GHz. (1) Improved LS-DYNA performance can result in
quicker simulations by industry users, which in turn can result in delivery of better and safer
products to the marketplace in less time.

These are the first LS-DYNA benchmark results published for the x3455 using the AMD
Opteron™ Model 2347 quad-core processor. For this benchmark, the single-node x3455 system
was configured with the AMD Opteron Model 2347 quad-core processor (1.9GHz, 512KB L2
cache per core) and eight 2GB PC2-5300 ECC DDR2 memory. (2)


ftp://ftp.software.ibm.com/eserver/benchmarks/news/newsblurb_x3455_ls-dyna_091007.pdf