AMD Phenom II x4 Processor 965 AM3 $183.50 w/ Free Shipping at Ewiz.com

macdeutsche said: Hm... tempted. Would this be noticeably faster than unlocked X2 550? I was always curious about this. I know it's faster, but how much... is my concern.

well it's 4 cores. So anything that takes advantage of cores (encoding etc.) will get a HUGE boost. Otherwise not much

macdeutsche said: Hm... tempted. Would this be noticeably faster than unlocked X2 550? I was always curious about this. I know it's faster, but how much... is my concern.

There are so many cpus out there. This chart has helped me a little bit when comparing them all. Check it out! http://www.cpubenchmark.net/cpu_list.php

nsdp said: Passmark is a rather trivial benchmark. Because it only uses 4k page files and the flags are set for Intel core designs it over states the performance of Intel vs a vi AMD. They don't have the required FTC disclosures listed of funds from vendors. The only 100% honest benchmarks for desktops are at Spec.org.
"The System Performance Evaluation Cooperative, now named the Standard Performance Evaluation Corporation (SPEC), was founded in 1988 by a small number of workstation vendors who realized that the marketplace was in desperate need of realistic, standardized performance tests. The key realization was that an ounce of honest data was worth more than a pound of marketing hype.
"The basic SPEC methodology is to provide the benchmarker with a standardized suite of source code based upon existing applications that has already been ported to a wide variety of platforms by its membership. The benchmarker then takes this source code, compiles it for the system in question and then can tune the system for the best results. The use of already accepted and ported source code greatly reduces the problem of making apples-to-oranges comparisons."
Plus you can see how the flags are set. Several benchmarkers have had to withdraw benchmarks because SPEC caught them cheating. The results are then independently verified. That is why Dell's spec benchmarks show the 2.5ghz Shanghai besting the 3.2ghz Harpertown by 9%. Passmark ranks the AMD 89th and the Intel 16th. So much for testing integrity.

Unless you are running multiple programs simultaneously or have an app that is written for multicore that is little to choose from vs the X550. You need stuff like Catia or Unigraphics NX to really see the difference. The fastest combo is the X4 940 with the OCZ AM2 Special memory (the above ranks it 55th good indication of flaws in the benchmarking) and any good AM2+ MB.SC09 I bet that there is no one here who knows enough to post the reason why. I'll give you a hint, Kraaken, Roadrunner, and Jaguar which are the #5, 2 and 1 fastest computers in the world. IBM has the other two slots.

I don't think anyone is saying that passmark is perfect and it should be the benchmark bible. It's there to simply give a general idea of where things fall and which cpus are in the same ballpark. Even on the site they say: "Rarely is a graph completely accurate in what it is representing. There are many factors that can skew the results and make a graph misleading. As such it is necessary to have some background understanding of the data being presented." And AFAIK, the vast majority of benchmarks on that site are user-submitted. You can hover over any graph and see the sample size too.

Either I'm an idiot and just can't find it using the search bar (entirely possible), or it simply isn't there, but I found no benchmark at all for the Intel i5 750 on SPEC. Either way, it's not good. I can't use a site that... I can't use--regardless of the reasons. We're in a thread about a $189 CPU, and if SPEC has a benchmark comparing the 965 to the i5 750 that is $150 at microcenter, I wish I could find it, but I can't. TBH I don't care which $1000 server CPU beats the other $1000 server CPU, why do you? Rank doesn't matter one bit either.

If passmark's testing methods skew towards Intel then that'd be very important to know, but do you have proof, or can you explain that to me, a layman? Calling them dishonest is a bit of an accusation. Are they one of the testers that had benchmarks pulled? Passmark says their scores are an average based on 8 tests, so what're you talking about with the 4k page file (http://www.cpubenchmark.net/cpu_test_info.html)? So either they're blatantly lying, or you're spreading some of that misinformation that you were talking about earlier, or I'm an idiot who is reading testing methods for different data (again, entirely possible). SPEC is probably more rigorous, more neutral, and lists tons more data, but none of that matters to me if I can't use that data.

With the hundreds of CPUs out there and the horrible horrible naming conventions on both sides, Passmark is a good first step (and only a first step). It lets you see if two cpus are close enough to be compared. If so, then you can go google and hope there's some real world tests out there (like photoshop for me) by somebody you can put a little faith in not being on the payroll of Intel or AMD.

edit: broken link

5 days after this is posted and they are selling at 183.50 now.
My 550 X2 is already 4 core, since I have unlocked it. For some reasons, if I OC it to 3.4ghz (4 core, so that it is matched with X4 965), it's actually slower, I am guessing that that's because I have unlocked it and it's not perfectly BE any more. I didn't want to increase the voltage, so that can be another reason.

I know X4 965 can be OC even higher, but I am not sure if 965 X4 will be significantly faster than unlocked 4 core X2 550. I know it's faster, but how much faster is unclear to me. Anyway, I guess the price of X4 965 will continue to drop now.