AMD Phenom II X6 1055T & 1090T Reviews

[wuttz]

we noticed that too. did he calibrate his xmeter?



amdzone

[dartaz]

This is respond to vardirox

Guru3d and Tom's Hardware pretty much shows the 1090T beating the i7 930 in most benchmarks

I didn't see i7 930 in Guru3d.

1090T did not beat i7 930 in most benchmark in Tom's Hardware review. And for some reason i7 930 was not tested in the gaming benchmarks and some other benchmarks. It not a complete review for i7 930 vs 1090T

Anandtech which has i7 860 benchmarked shows it beating 1090T in most benchmarks

Techspot which has i7 930 benchmarked shows it beating 1090T in most benchmarks. What is your opinion about these reviews ? Or are those reviews are not reliable because it doesn't support your opinion ?

[qcmadness]

This is respond to vardirox











Yet, Guru3d and Tom's Hardware didn't have i7 930 benchmarked.

This make me think that you didn't look at any of these reviews

Anandtech which has i7 860 benchmarked shows it beating 1090T in most benchmarks

Techspot which has i7 930 benchmarked shows it beating 1090T in most benchmarks. What is your opinion about these reviews ? Or are those reviews are not reliable because it doesn't support your opinion ?

The tests you are quoting are not using the extre 2-core

[dartaz]

The tests you are quoting are not using the extre 2-core

Are you saying that we should all look only at benchmarks that use the extra two cores ? Why ?

I say we should look at all real world benchmarks, not only the ones that favor Phenom II X6. And as you noticed, i7 performs better in many real world applications such as winrar or photoshop and gaming. Should we ignore these real world app just because it not very well optimized for six cores ?

[wuttz]

why bother with six-core benchmarks.
they forgot to run superpi.

[BoredByLife]

For intel yes but for AMD it's not true.

It's the difference between exclusive and inclusive disign.

The real total cache of intel is the last cache and AMD this include all caches.

The Phenom X6 has in fact 6MB + 6*512kB + 128kB*6 = 9984KB

Ok, thanks for clearing up

Just leaves less memory bandwidth per core as an argument, and faster L3 pollution, because more cores utilize it.

[richierich]

Are you saying that we should all look only at benchmarks that use the extra two cores ? Why ?

I say we should look at all real world benchmarks, not only the ones that favor Phenom II X6. And as you noticed, i7 performs better in many real world applications such as winrar or photoshop and gaming. Should we ignore these real world app just because it not very well optimized for six cores ?

Who uses winrar anymore? 7zip ftw!

[wuttz]

Ok, thanks for clearing up

Just leaves less memory bandwidth per core as an argument, and faster L3 pollution, because more cores utilize it.

id say intel's cache thrashing is a bigger problem than amd's six cores competing for a "smaller" L3-cache.

[BoredByLife]

Who uses winrar anymore? 7zip ftw!

Most things you find on the net are still normal zip, don't forget that.
Rar's are also heavily used in filesharing.

[wuttz]

This is respond to vardirox

sometimes, i really cant tell if anand purposely skews his results for intel marketing $$.

[ridney]

and everyone can afford photoshop

[superrugal]

emmmm, I was confused about these strange result. Very strange.

[dartaz]

Who uses winrar anymore? 7zip ftw!

I think worldwide, there are much more people who use winrar than 7-zip. Thats doesn't mean winrar is better though

[ajaidev]

Observations:

1. i7 930 < 1090T < i7 870 "In two tests" & 1055T close to i7 920
2. 1090T < i7 870 < 1090T "In x264 test" & 1055T close to i7 930
3. Idle power consumption lower than Bloomfields "i7 920/930" and higher than Lynfields "i7 870"
4. Loaded power consumption closer to Lynfields "i7 870" than the Bloomfields "i7 920/930"

[dartaz]

sometimes, i really cant tell if anand purposely skews his results for intel marketing $$.

"sometimes, i really cant tell if the neoseeker purposely skews his results for AMD marketing $$"



tomshardware shows similar result to anandtech

Are tomshardware payed by Intel as well ?

EDIT: What about this ?



Three review that shows similar results ! Do you trust one review over three ?

[wuttz]

Three review that shows similar results ! Do you trust one review over three ?

if you had a little bit more candor, you wouldn't omit this:

WinRAR didn't fully utilize the processor resources offered by the Phenom II X6 1090T, but it was still able to outpace the Phenom II X4 965 due to the effectiveness of AMD's Turbo CORE technology.

.. and picking the optimum file size for intel to "stay ahead" in charts really is clever. not.

unless all real-world file compressions are only ~300MB.

[informal]

Observations:

1. i7 930 < 1090T < i7 870 "In two tests" & 1055T close to i7 920
2. 1090T < i7 870 < 1090T "In x264 test" & 1055T close to i7 930
3. Idle power consumption lower than Bloomfields "i7 920/930" and higher than Lynfields "i7 870"
4. Loaded power consumption closer to Lynfields "i7 870" than the Bloomfields "i7 920/930"

Thanks for the summary,Thuban is showing a great perf. at a very good power draw level .Perf. between 930 and 870 i7s with power draw at the level of 955BE and 870 i7,excellent! 6x 45nm Deneb class cores draw as much as 4x Nehalem SMT cores(Lynnfield,Bloomfield just suck in this regard).
Amazing AMD managed to cram in 6 cores @ 3.2Ghz with under 85W of total CPU power draw:

[wuttz]

Amazing AMD managed to cram in 6 cores @ 3.2Ghz with under 85W of total CPU power draw:

dont forget its still at 45nm.
so whos the brand with the better process now?

well, if they hadnt spun off GF.

[behrouz]

ajaidev Good , you take here for Image!!!

[kl0012]

Overclocking-wise, pretty well sumarized :

Strange as it might seem, but a quad-core CPU on Intel Nehalem microarchitecture with Hyper-Threading technology overclocked to 4.0 GHz almost always outperforms six-core CPU from AMD. At the same time I can’t say that Thuban’s frequency potential is higher that of Core i7 CPUs on Lynnfield and Bloomfield cores. Therefore, there is only one possible conclusion here: microarchitecture of contemporary Intel processors makes them faster than AMD processors working at the same clock frequency. And even a 1.5 times increase in the number of computational cores can’t make up for that. That is why we again arrive to the same conclusion that AMD’s only weapon in the battle for consumers is their pricing policy.

1.5 years later old, good i7-920 (which also can do 4.0 GHz) is still an upper-mainstram king.

[richierich]

Most things you find on the net are still normal zip, don't forget that.
Rar's are also heavily used in filesharing.

huh? 7zip can open up zip files as well.

[BoredByLife]

huh? 7zip can open up zip files as well.

I know...

You stated .rar wasn't used much, well it is. But normal zips are even more used then rars. 7zips are not very common, altough they have superior compression.

[dartaz]

Overclocking-wise, pretty well sumarized :





1.5 years later old, good i7-920 (which also can do 4.0 GHz) is still an upper-mainstram king.

Thank you for posting this

[ajaidev]

The 1090T does very good in video transcoding in most case it beats out a i7 930 "stock".

The only negative point is low resolution gaming so if that's your thing better pick up at i7

Overclocking-wise, pretty well summarized :

[IMG]http://www.xbitlabs.com/images/cpu/phenom-ii-x6-1090t/table-3.png[/IG]



1.5 years later old, good i7-920 (which also can do 4.0 GHz) is still an upper-mainstram king.

1090T is 3.2Ghz stock and the Intel 3.2ghz stock i7 is well more than triple the price.

Besides most tests in the list are synthetic the only two tests that do matter are winrar and x264. As we already know winrar does not take much advantage of the added cores and as for the x264 the difference is very little.

BTW The games are on Medium Quality..

EDIT: Proof




Games:

http://www.guru3d.com/article/phenom...090t-review/16
http://www.guru3d.com/article/phenom...090t-review/17

At 1600*1200 its same all same all, even if its GPU limitation you cant be expected to play at 1080P in MQ or 1024*768 in HQ??

[wuttz]

Therefore, there is only one possible conclusion here: microarchitecture of contemporary Intel processors makes them faster than AMD processors working at the same clock frequency. And even a 1.5 times increase in the number of computational cores can’t make up for that. That is why we again arrive to the same conclusion that AMD’s only weapon in the battle for consumers is their pricing policy.

right.....