Some benchmarks of Thuban X6 1090T

[Tomasis]

@bench, im pretty sure this is the AMD section, and all "intel is better" flame baiting is bannable, so i wouldnt do it if i were you. the title for this thread is benchmarks for PII x6, yet all i see is bickering from the last day. not very enjoyable to read, this isnt the news section.

i really thought it was news section untill u mentioned

[informal]

Doesn't beat my old q6600 @ 3.7ghz

Newsflash : Phenom II X4 @3.7Ghz (3.7Ghz pretty much a walk in the park even for 940BE,the oldest one) spanks your old Q6600 across the board .Oh sorry,Super Pi excluded .

[crazydiamond]

lol cant believe people find a reason to hate on thuban already.. again price/performance is gonna be great compared to intel. oh and you can use your old mobo for it, or use your new mobo for more than 2 years

[Nintendork]

Now you don't need a $250+ mobo to run a great cpu. Except for some people, i7 quads are dead.

[FlanK3r]

omg, nice AMD. Wprime etc....

[crazydiamond]

was digging around looking for some i7 comparisons,, heres cb 11.5 64 bit, with i7 930 & phenom x6 both @ 4.2ghz

[Titan7171]

sweet performance at 4.2ghz.......it beats bloomfield. Cant wait to get one!

[TheBlueChanell]

And the point is ? AMD needs a 2 cores and 200MHz advantage to match the 1 1/2 year old i7 tech 960 ?
No matter how I try to have a look at it, I can't see any "miracles" or progress from AMD.
Intel's closing in on faster clock-per-clock processors than Gulftown and going to 8 and 10 cores ( 16 & 20 threads ) in Nov/Dec or Jan-March 2011.
AMD's at 12 Cores / 12 threads, but unless their performance clock per clock and on a core to core basis is the same with these, those will barely compete with the 8c/16t Intel CPU.

They need to work harder.

Nice performance and good prices are always nice, but they need to step up the game before they get down below ( performance-wise ).

I'm all in for performance.
Can we have an Opteron 146 and DFI LP nF4 SLI-DR de-javu anytime soon AMD please ?

There you have it.

i7 930 @ 4.2ghz = 7.20
X6 1050T @ 4.2ghz = 7.38

6 Physical Phenom 2 cores, are on par or surpass an i7 9** with 4 phsyical / 4 logical cores. (In Cinebench and hopefully other heavily threaded apps/benchmarks)

That's the first time in years, outside of gaming, that AMD has had a chip to match Intel at the same clock speed.

AMD's brute force method of throwing more cores @ i7's hyperthreading seems to have paid off.

That being said, if scaling is linear than a $295 1090T @ 3.2ghz stock should be able to perform within roughly 90-110% of the i7 960 @ 3.2 stock in heavily threaded benchmarks.

As far as gaming goes the Ph2 is pretty much equal and in some cases even faster than the i7. Bloomfield takes the cake in the more CPU aware games like Far Cry 2, or Resident Evil 5 and Thuban's 2 extra cores should help with that. For games that can only utilize 2-3 cores, The 1050/1090T's respective 3.3/3.6ghz Turbo modes should make for an extremely interesting set of numbers.

How is that not a win? What is there not to be impressed with? 2 more cores added to the same process node while maintaining the same thermal envelope as their last flagship quadcore and from what we've seen just as clockable as their quad counterparts.

Seems like a good deal to me. The greatest thing is, anyone with an AM2+ motherboard is going to be able to breathe new life into old machines.

This is just another much needed step in the right direction for AMD. Every single CPU refresh that's been released has brought performance improvements even when based on the same stepping. i.e 955 c2 vs. 965 c2 This started all the way back with 940, X3 720 came out and it was a better piece of silicon, then the 955, then the 965, then C3 and now Thuban.

I run both Intel and AMD and It's not hard to see that this is good for everyone. This should definitely rumble Intel's feathers and if anything it will give those absolutely blinded by blue some nice price drops on CPU's for their respective platforms.

I don't understand why people don't want to see AMD succeed.

[Titan7171]

all of a sudden people forgot about the 4 logical cores making a total of 8 for Intel vs 6 for AMD.......but noooo........it takes AMD 6 cores to Intels 4 now....hmmm!

[Dumo]

Which mobo though?...Other than CH4

[Zeus]

This Thuban is good, very good but it remains to be seen how it holds up against Intel in more than just one benchmark.

Either way you look at it, it is not blowing Intel away like Intel blew away Athlon 64 with their Conroe back then.

I think we should just stop making those AMD-Intel comparisations and enjoy what we're given.

[TheBlueChanell]

This Thuban is good, very good but it remains to be seen how it holds up against Intel in more than just one benchmark.

Either way you look at it, it is not blowing Intel away like Intel blew away Athlon 64 with their Conroe back then.

I think we should just stop making those AMD-Intel comparisations and enjoy what we're given.

I agree. I'm awaiting a proper review but these early results look very promising.

[Nintendork]

Following the trend, the name Bulldozer makes sense?


Too bad the NDA will expire in at least 1 week.

[donitsi]

Nice, 4,2G with retail chip?
Good Cinebench performance too

I wonder how stable it is with these clocks

[Hans de Vries]

Keep in mind that the AMD K10.5 cores are much smaller as the the
Nehalem cores. Here a compare at 32 nm



So the Nehalem cores are 10%-15% faster in single threaded applications
and another 20%-30% through the use of Hyper Threading. They achieve
that at a cost of being 1.8 times larger.


Regards, Hans

[[XC] Oj101]

I never realised that the cores were THAT tiny! Miniturisation is incredible.

[ajaidev]

Keep in mind that the AMD K10.5 cores are much smaller as the the
Nehalem cores. Here a compare at 32 nm



So the Nehalem cores are 10%-15% faster in single threaded applications
and another 20%-30% through the use of Hyper Threading. They achieve
that at a cost of being 1.8 times larger.


Regards, Hans

You have hit it on the head

This is my post where i was saying the same thing...

I do stand by my est. of dual llano < dual sandy bridge < quad llano < quad sandy in performance tough.

[informal]

Hans thanks for posting that analysis ,I've been saying similar thing for a while now in Deneb Vs Nehalem threads.Now we have your post backed up with nice images you compiled for all of us to see ,good job

[Opteron146]

Keep in mind that the AMD K10.5 cores are much smaller as the the
Nehalem cores. Here a compare at 32 nm

Could you identify if Sandy has 2x256kB L2 instead the prior 2x128kB ? I think it's bigger but I am not sure.

Thanks

Opteron146

[Dresdenboy]

So the Nehalem cores are 10%-15% faster in single threaded applications
and another 20%-30% through the use of Hyper Threading. They achieve
that at a cost of being 1.8 times larger.

Thanks for that picture. I published it on my blog with some thoughts added. Besides the likely double pumped FPU there might also be signs of a trace cache (directly below the execution units). Maybe you have an even higher res SB die shot to check this.

[Hans de Vries]

Could you identify if Sandy has 2x256kB L2 instead the prior 2x128kB ? I think it's bigger but I am not sure.

Thanks

Opteron146

The two SRAM tiles of the L2 cache are below the "B" of Sandy Bridge.
They are longer but also less wide as in case of Westmere so the area
is about the same in both cases.

Thanks for that picture. I published it on my blog with some thoughts added. Besides the likely double pumped FPU there might also be signs of a trace cache (directly below the execution units). Maybe you have an even higher res SB die shot to check this.

A good candidate for a Trace cache would be the larger square tile
below the L2 cache and above the location of the L1 instruction cache
in Westmere, which is located at the bottom edge in the middle.


Regards, Hans

A bit larger version:

[wuttz]

Posting a super pi score in the era of multicore processors is like driving your Porsche on the narrow village road going 20Km/h... (I know yup posted it to prove how "fun" that Opty was,yet Super Pi is fail from perf. evaluation POV when you count multicore MPUs).

reminds me of my old post.

SuperPi is an antiquated benchmark that assesses core performance using an antiquated fpu x87 instruction set. It is a grossly inefficient computer program that uses floating point units to calculate pi and "evaluate" processor cache performance. It's not by any means a "real world" reflection of todays modern cpu's microarch capabilities. It's like running a horse(fpu x87 instructions) down today's paved interstate(the cpu hardware), when all the while a car(newer simd's) are available.

SuperPi fails to take advantage of newer instruction sets, and hence also fails to evaluate modern-day hardware capabilities that newer processors support and are designed with. The FPU X87 instruction set was developed for an external co-processor dedicated to computing mathematical tasks and worked with the 80286/80386 microprocessors. Now if you havent heard of the 286/386, then you know SuperPi is that old.

//more at [ OCN ]