Deneb just around the corner?

[keithlm]

Ahhhh so you are all bluster and are easily exposed when called upon it.

Face it, Deneb will clearly have less IPC than Penryn and will be lucky to equal Conroe.

Because I do not wish to open a dialog with you I am all "bluster" and "exposed".

You do realize that you are starting to look pathetic don't you?

I can't help it if you have silly ideas, including that I must be an Intel boy.

It would be hard to review this thread and NOT come to the conclusion that you are a helpless Intel fanhat.

[charged3800z24]

Well, I just hope the above mentioned "they said they had better then expected results in the revisions made to the 45nm chipset." statement from them is true this time. I remember around before the launch of the phenom they said the same thing about it and it was a let down to everyone.
Phenom has finally grown into something worthy, I think, but at first it had a stumbling jump outta the gate.

I just wonder if the above statement applys to all us enthusiasts who are hoping to 3-4ghz on air easily....vs what they(AMD) are truely internally satisfied with ie: 3.3ghz or something meager...

They have feed back from HP, and others that say the are very happy with Shanghai. They even moved up the launch, so I think it is a good sign. AMD hasn't been into talking alot lately about there products..and like the 4000 series GPU's..they just came out swinging..there was a lot of sites saying what the GPU's were supose to have in shaders etc..but no one new the real power the chips would have until they hit. As stated on here many time, no ones really knows for sure...but it is still pretty much known it is going to be a better product. Pat Patla seems pretty excited about how thing have come with the 45nm chips.. So here's to hoping we can be as excited when they come out.

[informal]

Keithlm why do you even bother with that "genius".Leave him be and he can argue with himself(i imagine he does that often).

[Chad Boga]

it is hard having an educated conversation with you as you just make stuff up and so things without fact. and i can't believe you think others need to take a more rational approach when you don't know any facts at all. just because you believe intel is better and amd is completely behind in performance doesn't mean you need to come in here when amd is releasing a new chip and acting like ehhhhh its gonna suck. you have no basis for you information other than your opinion and because of that you having nothing to say of use my friend.

I don't think it is a big stretch to suggest that Deneb will not get the kind of performance gains one would only see with the introduction of a new architecture.

Do you really find it so odd that I would seek to call into question way over the top optimism for Deneb?

If it was Bulldozer coming out and the same IPC improvements were spouted for it, that would be very believable, but for a shrink and some extra cache, that is la la land stuff.

[Chad Boga]

So stating your speculations as facts is a rational approach?

Do you think it odd that I am sceptical that Deneb will get a greater IPC boost than has been achieved at any time in the last 12+ years from just a shrink and more cache?

What is the precedent for the crazy optimism that some have for Deneb's improvement over Phenom?

[roofsniper]

i doubt it will come out with gains as good as a new architecture will. but since the original k10 architecture was very rough and needed a lot of tweaking (which has been done now) i think it will have a considerable performance enhancement over current phenoms.

[charged3800z24]

Do you think it odd that I am sceptical that Deneb will get a greater IPC boost than has been achieved at any time in the last 12+ years from just a shrink and more cache?

What is the precedent for the crazy optimism that some have for Deneb's improvement over Phenom?

It is not just a die shrink and more cache...it has improved instructions per clock and other enhancements that were not done with the agena core..the agena core was passed off as "finished" before it was finished...they had a big problem with the roll out of agena...if it would have went as planned it would have been a better contender to Intel's 65nm chips...but it had a lot of mistakes...so, that said, there is a chance to see a bigger boost for this 45nm, considering that if 65nm came out as it was supose too, the 45nm would be a meare die shrink and cache increase as you say and just a marginal boost in speed per clock, as expected from this type of transition. Maybe I am being a little more hopeful. But I am, as others, are aloud to be. And if we are let down, oh well no harm no foul. And as I stated earlier, AMD did not intend Deneb to be a Perfrormance crowned processor. So it will fall right where they expect it to. They "plan" (hope) to bring the FX brand back with AM3 in 2009 sometime. I also hope that happens also. But we'll have to see how things go.

[roofsniper]

It is not just a die shrink and more cache...it has improved instructions per clock and other enhancements that were not done with the agena core..the agena core was passed off as "finished" before it was finished...they had a big problem with the roll out of agena...

exactly because agena didn't work out so well i think they can do everything agena should have and more because of this change. it might not be as big of a change as a whole new architecture will but it will be very close because it is doing more changes than just a die shrink and they have had the first round of quad cores to test to see what they need to do differently.

[Chad Boga]

If Deneb comes with a significant IPC boost, great, everybody wins.

But I remember all the talk about how great Thunderbird was going to be too back in the day and it was what, 4 to 5% improvement.

So colour me doubtful about any statements emanating from AMD PR, I wanna see the benchmarks.

[Throwed]

If Deneb comes with a significant IPC boost, great, everybody wins.

But I remember all the talk about how great Thunderbird was going to be too back in the day and it was what, 4 to 5% improvement.

So colour me doubtful about any statements emanating from AMD PR, I wanna see the benchmarks.

Dude, calm down and try using the edit button instead of posting 3 post back to back. I don't think AMD will come to your house and make you buy a Deneb. As far as your Thunderbird comments...Well, the T-Birds were not that bad during their life cycle and the Bartons that followed were very impressive for the price.

They definatly competed well with Intels offering during that time and at a cheaper price too. If you want to give us a history lesson about CPU's, then give us one about the beggining of the whole 64Bit CPU era. The Athlon 64 performed great for years until Intel released Conroe. P4's/Pentium D's weren't worth much for gaming and AMD had the better chips for a long time. Remember that before going out on a limb like this.

At the moment AMD has been struggling. Especially after purchasing ATI. Things will level out at their camp soon. Besides the performance crown always shift between AMD and Intel anyway. Same goes for Nvidia/ATI(AMD). So, overall I don't know what you are ranting about. FYI, AMD hasn't said much of anything reguarding the performance of Denebs. Exactly what PR are you referring to?

I won't say Denebs will be the best thing since sliced bread, but I'm sure they will outperform all of AMD's current line up. No disrespect, but you are coming off very negative and rude. Maybe you should try the XS Intel boards and follow age old advice......."If you don't have anything nice to say then say nothing at all".

If you want to gripe about Denebs atleast wait until they are released.

[charged3800z24]

If Deneb comes with a significant IPC boost, great, everybody wins.

But I remember all the talk about how great Thunderbird was going to be too back in the day and it was what, 4 to 5% improvement.

So colour me doubtful about any statements emanating from AMD PR, I wanna see the benchmarks.

I second that.. I wanna see the benches also...I am going mostly off the fact AMD "knows" they can't have any mistakes. But since this change is more so to help the multi socket server areana, the Opteron's will benifit the most of course. The desktop will have higher stock clock speeds + they should over clock well to. At least this time AMD hasn't been blabbing how good they will be and not bringing it. They have been very brief as of late, and this NDA or what ever.. won't lift, so we can see what is going to be of this new desktop version.

[GenTarkin]

werent there some deneb benches out there a month or so back on a chinese site or something? I remember in almost everything it was like 10-15% faster than current Phenoms clock for clock...and it was an earlier revision of the chip too....so, hopefully those numbers can only get better.
If it was true benches.

PS. isnt 10-20% or so all AMD needs to even the gap between that and say a penryn clock for clock and a bit of clock scaling?

Not to mention if the above is the case and AMD meets that with the deneb then the i7 wont be much worth anything to gamers and single threaded stuff, since clock for clock at least in games for sure its slower then penryn benches.

[nanohead]

So lets say deneb comes out to be a dud (lets pray it doesnt) but if it does come out like the phenoms, what are the chances they go out of buisness?

Zero

[roofsniper]

i have a good feeling that amd is not going to release any benchmarks until around the week it is released. or maybe even after it is released. they have waited so long to say anything so far and there is the possibility of them coming out in 2-3 weeks. plus they were originally slated for late q4/early q1 and the day intel released a pile of nehalem benchmarks suddenly deneb was bumped up to November. i have a good feeling that amd is confident in their chip and thats why they pushed it ahead. with barcelona they obviously were not confident in it and delayed it for what 8 months? they finally just released it because they had to and not because they wanted to.

[roofsniper]

Zero

yea i don't think amd can go out of business because then intel will not have anyone to compete with and they will become a monopoly.

[Chad Boga]

Dude, calm down and try using the edit button instead of posting 3 post back to back.

I am calm.

I don't think AMD will come to your house and make you buy a Deneb.

Thank goodness for that, I was worried there for a while.

As far as your Thunderbird comments...Well, the T-Birds were not that bad during their life cycle and the Bartons that followed were very impressive for the price.

My Thunderbird comments were only made because that was the last time AMD or their supporters were claiming great things were going to happen with a shrink and cache increase and I believe it serves as a cautionary tale.

They definatly competed well with Intels offering during that time and at a cheaper price too. If you want to give us a history lesson about CPU's, then give us one about the beggining of the whole 64Bit CPU era. The Athlon 64 performed great for years until Intel released Conroe. P4's/Pentium D's weren't worth much for gaming and AMD had the better chips for a long time.

I don't know why you think I am unaware of the K7 & K8's moments in the sun.

Remember that before going out on a limb like this.

What limb have I gone out on? All I have done is be doubtful about how big an IPC increase a shrink and extra cache can bring.

I never said AMD haven't ever made good processors, which is the only way your "limb" comment would make any sense.

AMD hasn't said much of anything reguarding the performance of Denebs. Exactly what PR are you referring to?

If AMD PR isn't hyping Deneb, then where are the Deneb boosters in this thread getting their information from which suggests there will be a far greater than usual IPC boost from a shrink and more cache?

If you want to gripe about Denebs atleast wait until they are released.

If people want to make over the top optimistic performance predictions for Deneb, there is nothing wrong with me questioning those claims and pointing to historical precedents which show those kind of gains just have not been achieved before from a shrink and more cache.

[Throwed]

Zero

Agreed. I don't know why people think you have to hold the performance crown to stay in business.

The desktop retail market for CPU's is so small.

BTW, this is the link to the older Deneb article.....
http://en.hardspell.com/doc/showcont.asp?news_id=3721

If these numbers are true then I am going Deneb. Especially if priced right and with the cheaper 45nm process you can bet AMD will price them right instead of being greedy like Intel.



Chad Boga, I am not going to let you dumb me down to your level with pointless non-sense that will end up in a endless cycle of bickering.

[Chad Boga]

If these numbers are true then I am going Deneb. Especially if priced right and with the cheaper 45nm process you can bet AMD will price them right instead of being greedy like Intel.

You must not have been around when AMD were pricing their CPU's against Prescott.

[keithlm]

It appears you are one of these troubled souls who can only see people as either being an eternal Intel or AMD fan, rather than just someone who will ALWAYS buy the best processor regardless of who makes it.

Actually I was giving you the benefit of the doubt.

I shall attempt to put this in simple words that even someone with your diminished level of intelligence can understand: If you are NOT an Intel fanboy then you are something worse; you are someone trolling only for the purpose of causing negative responses and having no other purpose.

(Which you are increasingly proving to be true with each every one of your posts.)

Oh and BTW: Welcome to my ignore list. You do not have anything to contribute... therefore begone pest.

[roofsniper]

If AMD PR isn't hyping Deneb, then where are the Deneb boosters in this thread getting their information from which suggests there will be a far greater than usual IPC boost from a shrink and more cache?

amd stated themselves that there will be a 15-20% ipc boost. as far as i have seen no one here has said of any boost greater than that.

If people want to make over the top optimistic performance predictions for Deneb, there is nothing wrong with me questioning those claims and pointing to historical precedents which show those kind of gains just have not been achieved before from a shrink and more cache.

no one here has made over the top performance predictions. people are just hoping for it to be better than the current ones and to be on par if not better than current core 2 cpus. if you ask me thats not over the top. and its more than just a shrink and more cache.

[Chad Boga]

Actually I was giving you the benefit of the doubt.

I shall attempt to put this in simple words that even someone with your diminished level of intelligence can understand: If you are NOT an Intel fanboy then you are something worse; you are someone trolling only for the purpose of causing negative responses and having no other purpose.

What an atrocious understanding you have of discussion forums and debates in general.

Due to your AMD Fanaticism you are demanding that no scrutiny ever be applied to outrageously optimistic predictions about AMD products, that this forum should only be about praising AMD.

amd stated themselves that there will be a 15-20% ipc boost. as far as i have seen no one here has said of any boost greater than that.

Well I maintain that is an unrealistic expectation for across the board performance increases.

no one here has made over the top performance predictions.

Claiming 15 to 20% is over the top in my view.

and its more than just a shrink and more cache.

Everytime a company shrinks and adds cache they will do some tidy up of the existing design and it never results in major improvements, so I am sticking with my description of it just being a shrink and cache addage.

BTW, If I am wrong about how much Deneb improves, I will come on here and readily concede that.

[roofsniper]

What an atrocious understanding you have of discussion forums and debates in general.

Due to your AMD Fanaticism you are demanding that no scrutiny ever be applied to outrageously optimistic predictions about AMD products, that this forum should only be about praising AMD.



Well I maintain that is an unrealistic expectation for across the board performance increases.


Claiming 15 to 20% is over the top in my view.


Everytime a company shrinks and adds cache they will do some tidy up of the existing design and it never results in major improvements, so I am sticking with my description of it just being a shrink and cache addage.

BTW, If I am wrong about how much Deneb improves, I will come on here and readily concede that.

ok so you believe that 15-20% is excessive. amd has stated that thats what it is and i have spoken with amd employees about it and they say the same. because you have no proof that 15-20% is excessive then i don't believe you can say that others are wrong when they claim this. we all accept that you believe that the ipc will not increase by 15-20% but what we don't understand is how u can say we are all wrong without having any proof stating otherwise when everyone else here is getting all their numbers and performance predictions from facts and what amd has stated.

[charged3800z24]

You must not have been around when AMD were pricing their CPU's against Prescott.

But, they were usually a few bucks cheaper then an Intel priced the same. A FX for 999.00 and a Extreme for 1099.00. I find it more trouble some that the Intel chips could not (even OC'd like mad) compete against the AMD parts overall and were still priced high. Like Intel, back then they could charge that for them. At least AMD is pricing there chips where they need to now (they really have no choice). And any company will do this as they see fit too. And both company's know, that the sales are in the low - mid range chips anyhow. Intel does have thier current mid ranged chips priced right..And if AMD had a FX out that was worthy, they would be pricier no doubt.

[charged3800z24]

Claiming 15 to 20% is over the top in my view.

I never really looked into it, but what was the improvement overall for 65nm Core2 - 45nm core2? I thought I heard it was around 15%...I might look it up..But should expect nothing less then what Intel had..and at least some more given that of the higher priced chips showing more speed per clock with the larger cahce siaze in the Intel line up, true?

[Chad Boga]

ok so you believe that 15-20% is excessive. amd has stated that thats what it is and i have spoken with amd employees about it and they say the same. because you have no proof that 15-20% is excessive then i don't believe you can say that others are wrong when they claim this. we all accept that you believe that the ipc will not increase by 15-20% but what we don't understand is how u can say we are all wrong without having any proof stating otherwise when everyone else here is getting all their numbers and performance predictions from facts and what amd has stated.

I am casting my doubts for two reasons, and if you would care to address those reasons that would be good, and if you don't want to, that's okay too.

1. In all previous shrink + Cache increases by either side in the last 12 to 15 years at least, we haven't even come close to seeing a 15 to 20% IPC increase, what is going to make Deneb so different?

2. AMD have little to no credibility in respect of projected CPU performances for at least 18 months now.

I never really looked into it, but what was the improvement overall for 65nm Core2 - 45nm core2? I thought I heard it was around 15%...I might look it up..But should expect nothing less then what Intel had..and at least some more given that of the higher priced chips showing more speed per clock with the larger cahce siaze in the Intel line up, true?

I think Penryn across the board was about 5 to 8%.