Fudzilla: Bulldozer performance figures are in

[Topweasel]

This is not true. It has 4 FPU's. An FPU can in certain situations execute two 128 bit calculations in one cycle, but in no way does the chip have 8 FPU's.

Exact opposite.

No its two distinct FPU's that can be be shared under specific circumstances to execute one specific calculation 256bit instruction.

 

[piesquared]

This is not true. It has 4 FPU's. An FPU can in certain situations execute two 128 bit calculations in one cycle, but in no way does the chip have 8 FPU's.

It has 4 FlexFP's that can each execute 2 128 bit instructions, or 1 256 bit instruction.

It is not half of anything on the intel side.

 

[bridito]

I think most anyone with a dual-core from the past five years has enough CPU power for 99% of typical PC users. Here on AT, we're the other 1%, and we like our benchies

I have this mad crush on benchies. I dream about them and compose love poems to them. The ones that are real anyway! (Without singling out any turkeys from Turkey...)

Has anyone read anything else about the alleged August & October split BD launch? Any further news from Dallas? Any anything?

 

[996GT2]

Almost a year late, assuming Bulldozer does release in October and is not further delayed.

With such a delay, I've honestly stopped caring if it's competitive performance-wise with Sandy Bridge. I built my SB system in Jan 2011 and I will have had it for almost a year by the time of BD's scheduled release. SB-E and Ivy Bridge are just around the corner.

Phenom II delivered the performance of Core 2 Duo/Core 2 Quad over 2 years after their release. Bulldozer honestly looks like a repeat of that: it'll deliver Nehalem/Sandy Bridge levels of performance, except it will be released much later than the Intel counterparts.

 

[Terzo]

Man, I'm having doubts again. Apparently the "bulldozer" at the [H] event was simply running Dirt on eyefinity. No benches or anything of the sort. August is in two weeks and the lack of information is frustrating me more and more. I need to stop caring.

 

[StinkyPinky]

Almost a year late, assuming Bulldozer does release in October and is not further delayed.

With such a delay, I've honestly stopped caring if it's competitive performance-wise with Sandy Bridge. I built my SB system in Jan 2011 and I will have had it for almost a year by the time of BD's scheduled release. SB-E and Ivy Bridge are just around the corner.

Phenom II delivered the performance of Core 2 Duo/Core 2 Quad over 2 years after their release. Bulldozer honestly looks like a repeat of that: it'll deliver Nehalem/Sandy Bridge levels of performance, except it will be released much later than the Intel counterparts.

Yeah, I've been enjoying my 2500k for 7 months now. Even if BD lives up to its hype it will still need to match it with Ivy Bridge (rather than its original target of Sandy Bridge) which I find very doubtful.

 

[bridito]

Man, I'm having doubts again. Apparently the "bulldozer" at the [H] event was simply running Dirt on eyefinity. No benches or anything of the sort. August is in two weeks and the lack of information is frustrating me more and more. I need to stop caring.

Great, no benchys, no nuthin'. Almost anything could have been powering that game and no one would have been the wiser. I'm very quickly getting to the point where I don't care about BD as well and I'll just eliminate it from my selection process. Just wait for SB-E and at least I'll have a 99.9% certainty that I will be owning an example of the best performing CPU family at the time!

 

[996GT2]

Great, no benchys, no nuthin'. Almost anything could have been powering that game and no one would have been the wiser. I'm very quickly getting to the point where I don't care about BD as well and I'll just eliminate it from my selection process. Just wait for SB-E and at least I'll have a 99.9% certainty that I will be owning an example of the best performing CPU family at the time!

Funnily enough many of the users over at the [H] thread about the BD event are saying the same thing as you. The frustration with Bulldozer is building up.

A selection of quotes from the [H] thread:

I was hoping to see some numbers but i'm not waiting till oct , i'm going to build a sandy bridge i7 2600 if amd doesn't give a firm date on thursday that happens by the end of the summer.

I knew no real benchmarks would be given. But I would've liked to have seen or read about seeing a demo of bulldozer next to a phenom II.Either way the longer AMD takes the closer I am to jumping on the intel bandwagon.

Like I said, an Athlon II could do that! So what was the whole point in bringing BD? If BD is confirmed for release in October, I'll be more than little disappointed (pissed). To me, that would confirm--especially after the 60-90 days after June 1 release projection from AMD---that this product's launch isn't going so smoothly.

I could have been purchased a 2500k from Microcenter and been more than satisfied.

I was really hoping for something concrete from AMD to come from this, but the lack of info just reinforces my decision to go Sandy Bridge with a Z68 chipset. I really tried to wait for AMD on this one, but I needed to upgrade and with no concrete release date, that tells me they still don't have their stuff together and we'd be lucky to see an October release at all.

I dont really see what all the BD hype was all about for this event if all it was doing was running in a demo rig that showed off the gpu..Especially if no one could even see it..Just seems lame on AMD's part.

I'm giving BD another 2 weeks for some kind of a review an then I am going SB.

 

[guskline]

Almost a year late, assuming Bulldozer does release in October and is not further delayed.

With such a delay, I've honestly stopped caring if it's competitive performance-wise with Sandy Bridge. I built my SB system in Jan 2011 and I will have had it for almost a year by the time of BD's scheduled release. SB-E and Ivy Bridge are just around the corner.

Phenom II delivered the performance of Core 2 Duo/Core 2 Quad over 2 years after their release. Bulldozer honestly looks like a repeat of that: it'll deliver Nehalem/Sandy Bridge levels of performance, except it will be released much later than the Intel counterparts.

My sentiments exactly SO..... instead of building a Bulldozer rig I built a Sandy Bridge 2500k rig (1 below) and moved my Phenom II 965 to back up. Extremely pleased with the Intel 2500k much faster than the 965

 

[Vesku]

One [H] event goer says it was running at 3.51GHz when they got a glimpse of system properties. Sadly, the only useful tidbit and it's a vaporous internet post.

 

[bridito]

Funnily enough many of the users over at the [H] thread about the BD event are saying the same thing as you. The frustration with Bulldozer is building up.

A selection of quotes from the [H] thread:

Personally, and again speaking just for me alone, I think that AMD is playing a dangerous game with enthusiasts. Sure, most computer users don't know and don't care, but IMHO the cutting edge guys like the ones here and at [H] are really losing faith by the minute. You can only play three card monte for so long until the audience just walks away. All that needed to be done at [H] is to have one BD that was even close to release specs and have people run whatever tests they wanted with it, not just use it as a mobile billboard generator. They could have placed a big disclaimer that this is not release spec yet, and a lot of people would have been much happier with them than they are now.

 

[Terzo]

Great, no benchys, no nuthin'. Almost anything could have been powering that game and no one would have been the wiser. I'm very quickly getting to the point where I don't care about BD as well and I'll just eliminate it from my selection process. Just wait for SB-E and at least I'll have a 99.9% certainty that I will be owning an example of the best performing CPU family at the time!

If I'm going Intel I'd probably just wait for Ivy Bridge...mostly because I like the name. Well, the die shrink and tri-gate transistors sound pretty appealing too.

But yeah, when Bulldozer was supposed to be release in June I was almost certain I'd buy one (mainly due to upgrade itch). Now the itch has faded and I'm thinking I really don't need an upgrade anyways, so when it comes out I'll probably pass on it.

Funnily enough many of the users over at the [H] thread about the BD event are saying the same thing as you. The frustration with Bulldozer is building up.

A selection of quotes from the [H] thread:

I think what's most frustrating is that it was purely advertisement. I figured if [H] was going to have Bulldozer, they'd have something worthy to show. If all it does is run the games then I'm disappointed, since I was expecting more than a marketing ploy from [H].

I'd say this is more damaging (with enthusiasts) than if they hadn't brought it at all.

 

[Mopetar]

I might still pick one up, but I'm waiting for the next generation of video cards (Radeon 7000 or GeForce 600 series) before I put together a new PC. If BD has a compelling offering for $200-$300 I might pick one up.

 

[bridito]

If I'm going Intel I'd probably just wait for Ivy Bridge...mostly because I like the name. Well, the die shrink and tri-gate transistors sound pretty appealing too.

But yeah, when Bulldozer was supposed to be release in June I was almost certain I'd buy one (mainly due to upgrade itch). Now the itch has faded and I'm thinking I really don't need an upgrade anyways, so when it comes out I'll probably pass on it.

I think what's most frustrating is that it was purely advertisement. I figured if [H] was going to have Bulldozer, they'd have something worthy to show. If all it does is run the games then I'm disappointed, since I was expecting more than a marketing ploy from [H].

I'd say this is more damaging (with enthusiasts) than if they hadn't brought it at all.

Yeah, I'm in the same situation. I was seriously considering BD, but now I really can't see me going for it unless it completely blows everything around into the weeds (and I'm not seeing it right now). I too agree that the [H] display was a huge misstep. I don't know what AMD was trying to accomplish there. IMHO: "Wow, BD actually does something" is not exactly the marketing positive they needed. So even if it did run at 3.51GHz so what? Lots of Prescotts etc. ran faster. Does anyone want one of them today?

 

[OVerLoRDI]

I might still pick one up, but I'm waiting for the next generation of video cards (Radeon 7000 or GeForce 600 series) before I put together a new PC. If BD has a compelling offering for $200-$300 I might pick one up.

I'm with you. I'm looking to grab one of these at that price point if they are fast enough to not hold back a tri-fire rig.

It is disappointing that AMD hasn't been able to make a processor that is fast enough to handle their own video cards in Tri-fire or quad-fire.

 

[GaiaHunter]

So you guys preferred if BD was missing in action in an event where AMD was marketing their eyefinity technology (and not for the first time - not sure if it was last year or 2 years ago that AMD and [H] held a similar event)?

Imagine what people would have said, if so close to the release, AMD hadn't brought a single BD CPU to the event.

Most of the enthusiasts that would buy SB, already did it, so it isn't as if AMD will be able to stop all the enthusiasts from jumping the gun by showing some benchmarks - that would have made sense if BD was only a few weeks later than SB.

It is similar to the 5800 series vs GTX480/470 - people that needed the latest technology bought 5870/5850 immediately (and NVIDIA actually tried to prevent people from jumping on the 5800 series by releasing white papers and what not and weren't very successful). Those that were waiting for the NVIDIA cards waited anyway, and the rest of the folk buy from what is available. Similarly, the GTX460 was a great success since it was a good jump at that price point and so people that wanted to buy at that price didn't wait for the 6850/6870, while the rest of the folk buy from whatever is available.

People buy from what is available and if it makes sense to them to upgrade (or just replace dead parts).

People that haven't jumped on SB yet didn't do so because they are waiting for BD - they didn't jump because it isn't compelling enough for them.

But when BD hits the market it makes no sense to invocate the reason "it is late" to not buy it.

 

[bridito]

So you guys preferred if BD was missing in action in an event where AMD was marketing their eyefinity technology (and not for the first time - not sure if it was last year or 2 years ago that AMD and [H] held a similar event)?

Imagine what people would have said, if so close to the release, AMD hadn't brought a single BD CPU to the event.

Most of the enthusiasts that would buy SB, already did it, so it isn't as if AMD will be able to stop all the enthusiasts from jumping the gun by showing some benchmarks - that would have made sense if BD was only a few weeks later than SB.

It is similar to the 5800 series vs GTX480/470 - people that needed the latest technology bought 5870/5850 immediately (and NVIDIA actually tried to prevent people from jumping on the 5800 series by releasing white papers and what not and weren't very successful). Those that were waiting for the NVIDIA cards waited anyway, and the rest of the folk buy from what is available. Similarly, the GTX460 was a great success since it was a good jump at that price point and so people that wanted to buy at that price didn't wait for the 6850/6870, while the rest of the folk buy from whatever is available.

People buy from what is available and if it makes sense to them to upgrade (or just replace dead parts).

People that haven't jumped on SB yet didn't do so because they are waiting for BD - they didn't jump because it isn't compelling enough for them.

But when BD hits the market it makes no sense to invocate the reason "it is late" to not buy it.

All of this IMHO: The news at [H] seemed to me at least to be BD not Eyefinity. A lot more people are interested in buying a BD than they are in spending $50,000 to turn their entire living room wall into a monitor. As for the "so close to the release" we really have to ask "really?" Both Intel and AMD have been pushing back and back and back to the point where there is significant frustration among buyers. Sure, the 2600K is a great CPU and likely will retain the performance crown even after BD's launch but the repeated delays in both BD and SB-E are pissing some people off and I know because I am one.

I think that if AMD had shown some real world benchmarks (even with a ton of disclaimers) it would have silenced the naysayers who see BD as a fancier Thuban. Unless it really is a Thuban in disguise in which case AMD has another vacation to Barcelona in their future. Regardless, the truth is going to come out sometime so I do see the [H] presentation of a BD still effectively under wraps as a shell game and I for one am borderline disappointed.

I also think that there are scenarios where BD would be too late to make any market sense. IF and it's a big IF BD really only hits the streets in late October, and Intel's recently rumored advance on their latest SB-E delay pans out (yeah, you need a scorecard to keep up), that means that there could be SB-Es running around well before Christmas. Another huge IF BD really can barely keep up with 2600K then SB-E will turn it into Thuban V2: just another CPU that may be priced well and have some good qualities but can't even hope to hold a candle to the performance king.

Given the AMD enthusiasts who have been claiming for well over a year that BD is the breakthrough to end all breakthroughs, this seems like it could be just a big bag of Catalonian hype. That would not make me happy as I am still holding out the most minute expectation that BD is going to be a great CPU and will be the basis for my next system. However, the chances of that seem to diminish by the day.

So, yeah. AMD is a day late and a dollar short. I for one had very high hopes for "something anything" to issue from [H] and it really sucks that it was just a relatively pointless game demo.

 

[Rifter]

Given the AMD enthusiasts who have been claiming for well over a year that BD is the breakthrough to end all breakthroughs, this seems like it could be just a big bag of Catalonian hype. That would not make me happy as I am still holding out the most minute expectation that BD is going to be a great CPU and will be the basis for my next system. However, the chances of that seem to diminish by the day.

So, yeah. AMD is a day late and a dollar short. I for one had very high hopes for "something anything" to issue from [H] and it really sucks that it was just a relatively pointless game demo.

Yeah this is totally looking like the Phenom 1 launch all over again. First it was going to be the best thing ever then it ends up being late because they couldnt get the clocks they wanted and still couldnt after a respin so it was released late and slower than planned, seem to be where BD is headed.

 

[bridito]

Yeah this is totally looking like the Phenom 1 launch all over again. First it was going to be the best thing ever then it ends up being late because they couldnt get the clocks they wanted and still couldnt after a respin so it was released late and slower than planned, seem to be where BD is headed.

Do you think that (if this scenario is true) AMD might as well just concentrate on the low and mid range and give up the enthusiast market to Intel?

 

[Rifter]

Do you think that (if this scenario is true) AMD might as well just concentrate on the low and mid range and give up the enthusiast market to Intel?

From a business standpoint yes, why bother spending large on R&D for high end chips when you are so far behind. Would make sense to aim for the lower end only parts.

From a enthusiast standpoint i hope AMD breaks back into the Entusiast market so Intel doesnt have a monopoly on it and has reason to push there R&D.

Right now intel has no competetion, they have no push to advance there hardware. If AMD had a high end chip out beating a 2600k you can bet Intel would have pushed higher end SB 1155 chips out by now(we all know intel has tons of clockspeed they arnt using) and probably launched SB-E by now. The way it is now they spend as little as possible on R&D and wait for AMD to almost catch up before launching anyhting new, not a ideal situation for us enthusiast buyers.

 

[PreferLinux]

Do you think that (if this scenario is true) AMD might as well just concentrate on the low and mid range and give up the enthusiast market to Intel?

No, because right now for both AMD and Intel it is simply an extension to the low end server/workstation market, in effect.

 

[dma0991]

http://obrovsky.blogspot.com/2011/07/you-were-punkd.html

OBR fooled everyone.

 

[Borealis7]

i don't think anyone is surprised by this.
what a shame for those poor people who linked to his numbers stating them as real.

 

[carnage10]

Hay guys Im having my own bulldozer event at my house. come over n watch me play dirt 2 on my pc. it will be the only program installed and u can't look inside the case or in system properties, but just take my word for it, it is powered by bulldozer n this is what it can do!!

 

[Dribble]

They might as well have just stuck up a large sign saying "Bulldozer is slower then sandy bridge". If you had the faster chip then when you brought it to a major geek event you'd be praising it to the rafters with lots of real time testing showing how much faster it was then the opposition.