Slashdot stories can be listened to in audio form via an RSS feed, as read by our own robotic overlord.

 



Forgot your password?
typodupeerror

Comment: Re:Itanium vs. Ultrasparc T1 (Score 3, Informative) 272

by JonAnderson (#14577385) Attached to: Intel and HP Commit $10 billion to Boost Itanium
Your logic is based around the concept that every task is highly parallel - they're simply not.
Well, the server I am logged into right now has 358 processes running. Each of which has a least 1 lwp which equates to at least one thread. How many people have a server running one process with one thread?
Even Sun don't claim that a T1 is comparable to an Itanium/Power/Sparc for tasks which need a few fast cores, which is why they use examples like Java application servers as the primary benchmark.
Like specweb? like sap sd 2 tier? like Lotus notes? These are just the published benches.
The Ultrasparc T1 is not a high-end machine, it's a low end one designed to compete against cheap x86 machines, I think the main surprise for me is that it's not available in a blade form-factor.
Exactly. The T1 costs $26K in it's most expensive config (32GB DDR2) for a 2u system capable of beating out bigger, hotter Itanic, x86 and Power systems on certain workloads (contrary to what you think, those certain workloads represent a significant segment of what customers buy these types of machines to do). There are definite plans to have a blade version out this year.
n 90% or more of workloads out there, a 32 thread core would have about 28 cores sat idle and 4 cores working flat out.
Really? Thats sounds like total bollocks to me.

The algorithm for finding the longest path in a graph is NP-complete. For you systems people, that means it's *real slow*. -- Bart Miller

Working...