AMD FX-8120P benchmark from Coolaler

[Arkaign]

I'm actually not as pessimistic as some here are. I think that after overclocking to mid-4ghz range that these will be pretty decent performers. The question is how power-hungry and hot they will be at that range. I'm guessing probably more than stock cooling would allow or that OEMs would accept in terms of PSU requirement for midrange boxes, so the stock clocks are much lower.

I guess we'll know soon enough, but man it's irritating waiting so long.

 

[BlueBlazer]

At any rate, I take MM's word over Collaler's leaked benchmark. If MM has seen the benches and he's willing to go public to say they will impress then that is all I need to hear as reassurance that BD is still going to deliver as JFAMD guided us to expect (IPC increases, not decreases).

Leaked benches must be bogus or useless for any number of reasons. Time to move on from this thread.

Movieman gave a single vague hint, I have better hints here. :sneaky:

 

[Gloomy]

I'm going to be building a general purpose computer for school within a few months. So I'm interested.

I just need an ergonomic keyboard, chair, and mousepad really but this is as good excuse as any to build a computer at this point.

 

[Arzachel]

At any rate, I take MM's word over Collaler's leaked benchmark. If MM has seen the benches and he's willing to go public to say they will impress then that is all I need to hear as reassurance that BD is still going to deliver as JFAMD guided us to expect (IPC increases, not decreases).

Leaked benches must be bogus or useless for any number of reasons. Time to move on from this thread.

Hey, lets not get logic and sanity involved, that isn't the way its done with BD threads!

IPC DECREASES 8 CORE BD WORSE THAN X6 THUBAN APPLES MAKE YOU FAT LADY GAGA IS THE REINCARNATION OF SANTA CLAUS

Now to mock up a bench and everything will be back to same old

 

[RussianSensation]

It would be the greatest trick if AMD purposely shipped broken engineering sample CPUs to everyone who is leaking these benchmarks and the real performance is 50-100% greater on launch date.

 

[Arkaign]

It would be the greatest trick if AMD purposely shipped broken engineering sample CPUs to everyone who is leaking these benchmarks and the real performance is 50-100% greater on launch date.

That would go down in internet legend immediately.

 

[Spikesoldier]

It would be the greatest trick if AMD purposely shipped broken engineering sample CPUs to everyone who is leaking these benchmarks and the real performance is 50-100% greater on launch date.

i c wut u did there.

this assumption deserved to be moved into its own post.

eyebrow raised.

btw: wont be the first time AMD used these kind of tactics. for example, giving different info to sources, to discover who is leaking the info out.

 

[BlueBlazer]

It would be the greatest trick if AMD purposely shipped broken engineering sample CPUs to everyone who is leaking these benchmarks and the real performance is 50-100% greater on launch date.

50% to 100% puts it past Intel Core i7 990X. Then launch with prices that undercuts Intel top gun ($300/$266 vs $999)? That sounds like logic gone out the window!

 

[Gloomy]

IPC DECREASES 8 CORE BD WORSE THAN X6 THUBAN APPLES MAKE YOU FAT LADY GAGA IS THE REINCARNATION OF SANTA CLAUS

This is incorrect. Lady Gaga is Joseph Stalin. He fled when he foresaw the collapse of the Soviet Union leaving a body double behind. In reality he is a reptilian extraterrestial attempting to undermine the foundation of the world goverments through various means... once politically and this time through subliminal messaging.

The goal is to make the earth a softer target for a future invasion.

...where do you get your info?? Stop spreading lies.

 

[Idontcare]

It would be the greatest trick if AMD purposely shipped broken engineering sample CPUs to everyone who is leaking these benchmarks and the real performance is 50-100% greater on launch date.

Coolaler is Intel's sanctioned leaker, it would not surprise me if he were actually on their payroll. When it comes to anything-AMD, I trust Coolaler about as much as I trust OBR.

If it were a leaked Ivy Bridge bench though I'd take it as gospel truth from Coolaler because he is tied in closer to the wafers than a foup.

If I were AMD and feeling my oats, I'd set him up good to be punked, what's to lose?

 

[drizek]

Guys,

You know that overclocked 8.4GHz CPU? You know how they said it was only a single module?

What if...

It was actually 4 modules, each running at 2.1GHz, but with reverse hyperthreading to make it look like an 8.4GHz dual core? And all the smoke from the liquid nitrogen was just that, smoke and mirrors. It was cooled with the stock HSF.

 

[BlueBlazer]

Coolaler is Intel's sanctioned leaker, it would not surprise me if he were actually on their payroll. When it comes to anything-AMD, I trust Coolaler about as much as I trust OBR.

If it were a leaked Ivy Bridge bench though I'd take it as gospel truth from Coolaler because he is tied in closer to the wafers than a foup.

That begs to question..... Have Coolaler leaked fakes before? If he had released fakes then wouldn't that ruin his reputation? Is he aware of being set up?

If I were AMD and feeling my oats, I'd set him up good to be punked, what's to lose?

Coolaler isn't the only one, what about the others (in Coolaler's circle) who had previously leaked early Deneb benchmarks?

 

[Arzachel]

It's not like it hasn't happened before, a K7 ES was leaked before release and had quite underwhelming performance. Hopefully the same will be true with BD

 

[Vesku]

Don't think it's a trick, who fakes respins and delays for the sake of some misinformation? Keep in mind how long BD has been in the pipe, it may actually look ok compared to Nehalem, the architecture that they were originally looking to launch against. They are touting it's OC behavior because it will probably look 'OK' versus Sandybridge stock clock when it's OCed beyond OEM power tolerances.

As to why they wouldn't counter these "BD will suck" rumors with their own counter leaks and rumors. If BD 1st gen is as I stated in performance then it's actually beneficial to lower enthusiast expectations. That adds context to how JF-AMD has been recently characterizing it: not as bad as rumors, stressing the need for targeted binaries to get the most benefit, and 'benchmarks aren't real software' rhetoric.

 

[busydude]

Have Coolaler leaked fakes before? If he had released fakes then wouldn't that ruin his reputation? Is he aware of being set up?

Just look at the Barts(Even Cayman) rumors thread.. Coolaler was leaking all fake info regarding that GPU.

 

[GaiaHunter]

It would be the greatest trick if AMD purposely shipped broken engineering sample CPUs to everyone who is leaking these benchmarks and the real performance is 50-100% greater on launch date.

There are/were obviously problems.

The question is are/were those problems fixable.

First we heard that BD wasn't reaching target clocks, but the same guys that broke the overclocking WR also said 5 GHz on air/water with all cores was doable. They might be lying, but it isn't likely.

It is possible there are/were several problems but all are/were fixable. Here's hopping.

 

[BlueBlazer]

Don't think it's a trick, who fakes respins and delays for the sake of some misinformation? Keep in mind how long BD has been in the pipe, it may actually look ok compared to Nehalem, the architecture that they were originally looking to launch against. They are touting it's OC behavior because it will probably look 'OK' versus Sandybridge stock clock when it's OCed beyond OEM power tolerances.

And coupled that with the recent pricing leaks, a better picture emerges. :thumbsup:

Just look at the Barts(Even Cayman) rumors thread.. Coolaler was leaking all fake info regarding that GPU.

Coolaler usually deals with CPUs (as far as I know, as mostly many CPU leaks came from him and company in the past), and I hardly pay attention to GPU leaks. Can you point to this "fake info"? :hmm:

 

[Arkadrel]

There are/were obviously problems.

The question is are/were those problems fixable.

First we heard that BD wasn't reaching target clocks, but the same guys that broke the overclocking WR also said 5 GHz on air/water with all cores was doable. They might be lying, but it isn't likely.

It is possible there are/were several problems but all are/were fixable. Here's hopping.

Supposeingly "it" was done a weak or two earlier, the overclocking thing.
Also it was done on engineering samples, and final product might clock higher.
Also in the video you can see, theres like a box of cpus, with tags on them, 3 of them says 8ghz-8.2ghz or so at differnt voltages.

The 8.4ghz was done on like the 4th CPU they tested. In short, they didnt really cherry pick the CPU that hit 8.4ghz.

The world record of 8.4ghz is gonna get broken, again by bulldozer im convinced, once they have final product and start cherry picking from 1,000's of cpus instead of just picking the 4th on in the box of engineering samples.

First we heard that BD wasn't reaching target clocks,

Yeap, and now people are saying like everyone will more or less hit 5ghz on air overclocking. So it doesnt seem like its a clock speed issue.


As for people saying that IPC will be lower than Phenom II,.... what are you smokeing?
Why would you make a CPU thats slower than your last gen one? also AMD guys like JD-AMD have come out and said its IPC will be higher than phenom II (magny core, mhz pr mhz).

All the "leaked" bulldozer benchmarks are "fakes" done to get page hits as far as Im concerned.

 

[busydude]

Coolaler usually deals with CPUs (as far as I know, as mostly many CPU leaks came from him and company in the past), and I hardly pay attention to GPU leaks. Can you point to this "fake info"?

Oops.. yeah. I am confusing that with chiphell.

Anyway.. my point was that AMD knows how to keep people in the shadows. I am not saying that BD will be performing exceptionally.. rather.. I am just implying that AMD has a history of keeping a tight wrap on their ready to launch products.

 

[Vesku]

The world record of 8.4ghz is gonna get broken, again by bulldozer im convinced, once they have final product and start cherry picking from 1,000's of cpus instead of just picking the 4th on in the box of engineering samples.

Yeah, the OC event and record have probably guaranteed them a few 10s of thousands of chip sales in the search for "The One."

 

[Munky]

This seems so bad, it has to be fake.

 

[sandorski]

11 people, 11.

 

[Arkadrel]

Yeah, the OC event and record have probably guaranteed them a few 10s of thousands of chip sales in the search for "The One."

I seriously double people "buy" tons of CPUs to try and beat world records.

Im assumeing once final silicone is out, they ll (AMD) just cherry pick (from the ones they normally sell no avg joes), and keep a few of the best ones, and then call back the guys that love to overclock, and see if they wont do a new world record.

The point is just... I dont think it stops at 8.4ghz, engineering sample's and only testing like 4 to get to that record, isnt enough, theres bound to be better cpu's (with final silicone) and your bound to get a better cherry picked cpu, if u go through more than just 4 chips.

The record is gonna get beat again.

Also how cool would it be to have a "Its over 9,000!" meme thingy?

 

[Vesku]

It's not that people "buy" tons individually. It's that many "for the Hertz" OCers will decide to try their luck on a particular BD. Some others will buy->test->sell->buy BDs for OCing. Hence my saying 10s of thousands and not 100 thousand plus. Helps AMD avoid the embarrassment of low demand for a brand new uArch.

 

[intangir]

The ignorance just amazes me. All AMD needed to do is take 2 llano dies, strip out the GPU, and tie together what is left, and they would have an 8 core chip that is faster AND smaller than this BD. They would have known this for at least 6 months, but they did not do what I just suggested (as far as we know). The only logical conclusion is that BD has to be much faster than what is being shown here. Obviously. Billion dollar companies do not shovel out garbage when it would be much cheaper and faster ttm for them to produce a cookie cutter 8 core llano. You people who cant understand that need to get over yourselves.

It's not as simple as that. Project decisions probably set them on this path 5+ years ago, and their resources were committed to working on Bulldozer. If they only discovered in January that their efforts did not turn out as good as they anticipated, that's not nearly enough time to suddenly shift their efforts to Plan B. Chip projects even with a known architecture take a minimum of 2 years from start to shipping, and they had already promised their next generation in 2011. I'm pretty sure that's the only reason they're releasing Bulldozer as-is now, instead of just waiting for the next stepping in January.

Andy Glew (the original inventor of CMT) has some fascinating insights about what it's like to shift horses onto a new microarchitecture.

http://groups.google.com/group/comp.arch/msg/82efd5dc0ef96d38?hl=en

Anyway, my big problem with ILDP is that it was a microoptimization. To use it, you would basically have to throw away out-of-order CPUs, and start over. And in the first generation, you would just be playing catch up.

I've seen this many times. People think that they can get paid to re-implement an existing CPU better, with a better, newer, microarchiture. Maybe so - but remember that you are then competing with the design team that is already going over the existing design with a fine tooth comb. I've seen this several times with attempts to do a new low power microarchitecture. I think that Wmt was much like this - out-of-order done anew, rather than extending P6 OOO. The folks who pushed run-ahead were in this camp: they weren't better than OOO, just more efficient. Or so they believed. Because you also have to remember that there is risk in doing anything new - so if the new supposedly more efficient microarchitecture does not quickly make the phase change to proven to more efficient, it will get canned.