Jennyh, have you seen these? Phenom II vs i7 vs c2dualcore

Status
Not open for further replies.

Raidur

Distinguished
Nov 27, 2008
2,365
0
19,960
http://www.xbitlabs.com/articles/video/display/radeon-hd5870-cpu-scaling_2.html#sect0

You've seen these right jenny?

Pretty sure I remember a past argument going something like this.

Jennyh: phenom ii > i7, let alone i5

Me: Benchmarks with low resolutions show us that the i7 out-performs phenom ii when the gpu bottleneck is lifted.

Jennyh: i7 just runs better at low resolutions, it is not due to bottlenecking.

Well... now that we finally have benchmarks with a stronger gpu setup than a single 5870 (5870xfire) on resolutions most of us actually play at we can see who was right. And imagine that, once the second 5870 is added the i7 creams phenom ii. A lot of times we even see the i7 winning at 2.7 against the phenom ii at 4.1ghz.

Is this yet another site that is paid by intel to lie or would you admit defeat and stop spreading this phenom ii > i7 in games.

The only time phenom ii wins is when there is a gpu bottleneck present, and it is almost never more than a few fps (the garbage a lot of reviews show).
 

jennyh

Splendid
Jesus you are slow aren't you?

I already got banned over a thread with these benchmarks, but thanks for letting me point out the flaws once more. :)

Despite my using fast DDR2 modules in the system, the integrated memory controller of the AMD processor imposed some limitations resulting in a performance reduction. I could not use CAS Latency 4, Command Rate 1T and a step-up memory divisor. Unfortunately, I did not have two good 2GB modules and it was not right to sacrifice 2GB of RAM (by removing two modules) to benchmark modern games in Windows 7. So, I tried to squeeze what I could out of my components

I want to note that I did not deliberately slow down the AMD platform. I only tried to overclock it as best as I could with the components at hand.

LAWL.

The use of different system memory, DDR3 for the Intel Core i7 platform and DDR2 for the AMD Phenom II X4 platform, makes it impossible to compare these two platforms directly.

And finally, the main one...

One more pitfall for the AMD platform in this test session was PCI Express. The Gigabyte GA-MA790GP-DS4H mainboard is based on the AMD 790GX chipset which supports two ATI Radeon cards in CrossFireX only as PCIe x16 + PCIe x8, as opposed to both platforms from Intel which support two PCIe x16.

All of that was on the page you linked btw. Try reading your links instead of being dazzled by coloured bars mmkay?
 

Raidur

Distinguished
Nov 27, 2008
2,365
0
19,960
Yeah I wanted to mention I wasn't trying to start a flame war... just wanted to prove a point is all, and wanted to shed some light on the subject (and nay-sayers) and help anyone trying to decide between systems.

Also I'm not trying to scare people away from amd because as you can see (for the money) phenom ii is still has fantastic performance.
 

ElMoIsEviL

Distinguished


You forgot to add that using the scientific method, basic mathematics and you adding all of those shortfalls together still doesn't come close to making up for the performance deficit we see the Phenom II x4 experience in those tests.

Therefore when looking at the big picture (which architecture is faster than the other) the end result would be the same regardless of these inconsistencies. What you can't use those benchmarks for is to gauge how much faster i7 is over Phenom II X4 but you can use them to claim that i7 is indeed faster.

I think you forgot to mention that. :)
 

Upendra09

Distinguished


I am not slow you are the one who is slow you just made another personal attack, and i wonder what got you banned :sarcastic:


and wow i agree with Jennyh on those quotes
 

jennyh

Splendid


You should go apply that to your last thread, oh yeah nehalem beats opteron in folding too right? :na:
 

Raidur

Distinguished
Nov 27, 2008
2,365
0
19,960
More absent than slow. :p

Yeah I noticed the memory differences but didn't see the rest/commentary, figured 1200mhz w/ 5lat was enough. However I will mention that 8x is more than enough for a 5870. The loss is around 5%.

I can't see these things making THAT much of a difference but I guess we'll have to wait for a better review...

Btw jenny you act very bitchy, I can see why you got banned. I'm not trying to be-little you or challenge your intelligence, like you are mine.
 

jennyh

Splendid


Well last I knew being 'bitchy' wasn't a bannable offence lol.

I'd love to see how you dealt with being called out btw. And not once, or twice, but by numerous 'men'...sometimes with their friends as well. They even tried to get me banned deliberately, don't you know?

So yeah, forgive me if I treat you with the disdain you deserve. I don't think I'm better than you, I know I am.
 

Raidur

Distinguished
Nov 27, 2008
2,365
0
19,960
Btw jenny that benchmark further proves my point. The i7 obviously needs much less ghz than the phenomm ii to run the 5970 to its full capabilities. Once that is reached the phenom ii pulls ahead by only a few fps, as I mentioned.

The major flaw with this benchmark is they only used one resolution, causing the cpu to be needed even less.
 
What the Xbit benchies really show is that the 'old' E8400 is not quite ready to roll over and play dead just yet, doing it for the duelies yeah baby!
woowoo.gif
 
Well I guess you could utilize the test system the guy had for you know, the platform upgradeability that AMD touts since most people with a Phenom II did have AM2+ and DDR2.

I think its a legit benchmark. DDR3 has no performance gains over DDR2 in gaming, onlyin memory bandwidth which gaming does not need that much at all hence why a old C2Q system on the FSB with a little over half the memory bandwidth of a Phenom II can keep up in games.

As for the PCIe, x8/x8 is not enough to bottleneck anything. Multiple tests from multiple sites show that PCIe 2.0 x8/x8 loses maybe 1FPS at most and even PCIe 1.1 x16/x16 goes as fast as PCIe 2.0 x16/x16. Until that is proven otherwise x8/x8 will be fine.

in fact I am willing to bet that PCIe 3.0 x16 is out BEFORE PCIe 2.0 x16 is bottlenecked just like PCIe 1.0 x16 came out well before AGP was bottlenecked. If you can find a AGP HD3850, it does pretty much as well as a PCIe 3850.

I hope the guy gets his hands on a AM3 mobo so he can retest and see if the claims people make is true. If not having DDR3 and x16/x16 PCIe 2.0 will make up for Phenom IIs low scores or if its just a bunch of BS from people.
 
Status
Not open for further replies.