Quad Opteron FP scores out

I agree all we hear is talk about benchmarks, when will we see products in the shops ???

@bird

Yes, the results for these 4 socket systems have been out for weeks. I was checking them out back then.

[ad FP scores]"So what?"

Look at the title of the article. That.

From spec.org:
http://www.spec.org/cpu2006/Docs/readme1st.html#Q15

<quote:>
Q15. What is the difference between a "rate" and a "speed" metric?

There are several different ways to measure computer performance. One way is to measure how fast the computer completes a single task; this is a speed measure. Another way is to measure how many tasks a computer can accomplish in a certain amount of time; this is called a throughput, capacity or rate measure.

* The SPEC speed metrics (e.g., SPECint2006) are used for comparing the ability of a computer to complete single tasks.
* The SPEC rate metrics (e.g., SPECint_rate2006) measure the throughput or rate of a machine carrying out a number of tasks.

For the rate metrics, multiple copies of the benchmarks are run simultaneously. Typically, the number of copies is the same as the number of CPUs on the machine, but this is not a requirement. For example, it would be perfectly acceptable to run 63 copies of the benchmarks on a 64-CPU machine (thereby leaving one CPU free to handle system overhead).

Note: a speed run which uses a parallelizing compiler to distribute one copy of a benchmark over multiple CPUs is still a speed run, and uses the speed metrics. You can identify such runs by the field "Auto Parallel".
<end quote>

You don't measure a quarter mile time of a car with three of the 4 wheels removed, so why should you benchmark the FP performance of a 4-core CPU while only using one of the cores?

I'm seeing a nearly 42% advantage for AMD, running at 2.5 ghz versus the Intel machine at 2.93. That's some pretty heavy gain over a machine that's 400mhz faster. With AMD getting out 2.8 and 3.0 ghz possibly the end of the year, they should have a very large advantage.

AMD,

Please stop talking about your quads and start making some. According to my contacts, Dell was supposed to be offering these a week ago, but not even they can get stock. Less talking, more showing!

These result have been out for weeks. And they are actually not FP scores, but FP_rate which makes quiet a difference. You can list the INT and INT_rate result to compare by opening this page:

http://www.spec.org/cgi-bin/osgresults?conf=cpu2006;op=form

Just fill in the form 16 for # Cores and 4 for # Chips then click Ftech Results at the bottom.

Intel has HDD 10krpm, DAAMIT has 7200.Intel has 64gb ram, DAAMIT has 32.Intel has 2.93Ghz, DAAMIT has 2.5.
Since when you can compare an KTM offroad version with a Honda CBR Fireblade 900?
You are a bounch of weird peoples.I bet that all those 16 cores from DAAMIT ate a lot less power than the Xeons, and still won ...even with that handicap that they put it in

How much is AMD going to sell these chips...?

This will be the most telling competition.

"These result have been out for weeks."
Not really. These are for 4U systems, earlier results were for 2U ones.

"And they are actually not FP scores, but FP_rate which makes quiet a difference."
Yes, FP scores are for a single thread, FP_rate is for that many thread as many core the system has... Now what?

Despite being a SPEC benchmark, which we already know is mainly bottlenecked by compilers. The only comparison that is really fair would be to compare SPEC results achieved with the same CPU vendor neutral compiler. That rules out the Intel compiler at least, since it still generate crippled code for non-Intel CPUs. That said, the scores are interesting and promising especially for AMD.