SpecInt/SpecFP - Intel vs AMD

[Kronos]

Why do you bother to come here and hang with we "Ignoramousess"? Obviously we are far too redundant to aquire any benefit from such as yourself. Why cast pearls before swine? Better you take your words of wisdom and profanity to another site than to waste any further time here. While YOUR infatuation with Intel is understandable...we of lesser wallets require a bigger bang for the buck and for the majority here that is AMD. Sorry.

I want to die like my Grandfather...in my sleep...not screaming in terror like his passengers.

 

[Kelledin]

Oh, we eventually got past it. Once we got the necessary setup to update the firmware on the drives, we had no more problems. Until we got that worked out, though, we were strongly considering switching to a different source for hard drives. It left such a bad taste in my mouth that I'm not willing to put Seagate hard drives in my <A HREF="http://www.anandtech.com/mysystemrig.html?rigid=5092" target="_new">own system.</A>

Kelledin
"Happiness is a loaded weapon."

 

[Guest]

How have your Seagates compared to others on physical level at your work?

"Cock-a-doodle-do" is what I say to my girl when I wake her UP in the morning!!

 

[Kelledin]

Performance of IBM drives in a RAID5 was slightly lower than the fully updated Seagate drives. The engineers responsible for parts validation wouldn't even hear of trying Quantums--one for the sole reason that he didn't trust a company that named one of its hard drives "fireball." Nice and sensible, I know.

I did have the opportunity to compare WinBench scores between Quantum Atlas 10K's (my own drives) and the Cheetah U160 drives at the time. In a 3-drive RAID5, the Cheetahs got whipped--41MB/sec to 31MB/sec.

I should mention, though, that one of the Quantums lasted only a year before it had a mechanical failure. Of course, with three drives, the probability of failure goes up, but I still think that's a little short-lived for a hard drive.

Since then, the later versions of WinBench somehow produce oddly inconsistent results. My latest set of ten drives only gets 27MB/sec in WinBench, no matter what RAID arrangement I put them in or what stripe size I choose. It seems the people at Storage Review have the same problems--WinBench99 just doesn't produce accurate results for RAID arrays. They (and I) have switched over to IOmeter for benchmarking drives. Now I just have to get the guys in charge to implement IOmeter at work...

Kelledin
"Happiness is a loaded weapon."

 

[kurokaze]

wow.. algortihms and data structures were sort my speciality back in school so I have a fairly good idea of what you're talking about, however I gotta re-read this thing again to understand it

 

[Guest]

well intel has more mhz so they beat amd..but amd is cheaper whore