SB is here. When will Bulldozer be released?

[exar333]

Hmmmmmm, what's the SB die size? We have publicly said that we will be smaller than Istanbul.

SB die size ~216mm^2

Istanbul 346 mm^2

Smaller than Istanbul is not very sepcific...how much smaller?

 

[Castiel]

3.835 Ghz=225x17, which would put the stock clock at 3.4Ghz -- if not a fake.

It doesn't show us anything. I want some Cinebench benchmarks

 

[Idontcare]

SB die size ~216mm^2

Istanbul 346 mm^2

Smaller than Istanbul is not very sepcific...how much smaller?

Charlie published a photo of a BD wafer, folks are estimating it must be right around 310-320mm^2.

 

[piesquared]

3.835 Ghz=225x17, which would put the stock clock at 3.4Ghz -- if not a fake.

why does stock have to run at 200?

 

[Wreckage]

I'm sure they want to get it out before the summer tech snoozefest sets in.

 

[tweakboy]

Well bulldozer 8 core should be faster then a 2600K 4 core.

Makes sense.

 

[PlasmaBomb]

Even if it does, LGA2011 is Q4 '11 and then IB is Q1 '12.

If BD truly stomps on SB, Intel could well move up IB.

 

[PlasmaBomb]

About the 3rd time now:

http://www.computerbase.de/artikel/p...lierungsrating

2500: 15% faster per clock in average
2600: 17%

Link doesn't work...

Seite nicht gefunden!

 

[bryanW1995]

Heres hoping that BD will offer the avg user a compelling reason to spend his $300+ CPU budget on an amd CPU.

 

[drizek]

MSI Board: http://techreport.com/discussions.x/20227

Is that a NEC USB 3.0 chip to the left of the third PCIe slot from the top? Does that imply no native USB 3 support in AM3+ chipsets?

Edit: Duh. It says "NEC USB 3.0" right on the board below the analog audio ports. That's too bad then.

 

[drizek]

If BD truly stomps on SB, Intel could well move up IB.

They don't need to move up IB with the way SB overclocks. They can just bump clockspeeds.

 

[Idontcare]

They don't need to move up IB with the way SB overclocks. They can just bump clockspeeds.

Unfortunately for AMD, this "plan B" has been available to Intel since C2D was launched.

They consistently sandbagged the clockspeed potential of their chips while maximizing yields and gross margins because AMD has yet to give them "a run for their money" since summer 2006.

And that is the sad reality for AMD...trumping today's SandyBridge SKU's with Bulldozer won't be enough because today's SB SKU's are all underclocked, immensely so.

A BD that thumps SB will simply mean lower margins for Intel as they will boost clockspeeds at each given pricepoint, thumb BD in a return salvo of gunfire, and take the yield (binning) hit.

As customers we only stand to win, but AMD is dealing with constantly shifting goalposts as they try and score a touchdown. That sucks for them, will be hard to earn a sense of accomplishment if you are on team BD.

 

[Wreckage]

They consistently sandbagged the clockspeed potential of their chips while maximizing yields and gross margins because AMD has yet to give them "a run for their money" since summer 2006.

Even back when AMD had better chips than Intel, Intel was still making a lot more money. Money which they fed into R&D. A trend that continues today.

 

[Martimus]

Unfortunately for AMD, this "plan B" has been available to Intel since C2D was launched.

They consistently sandbagged the clockspeed potential of their chips while maximizing yields and gross margins because AMD has yet to give them "a run for their money" since summer 2006.

And that is the sad reality for AMD...trumping today's SandyBridge SKU's with Bulldozer won't be enough because today's SB SKU's are all underclocked, immensely so.

A BD that thumps SB will simply mean lower margins for Intel as they will boost clockspeeds at each given pricepoint, thumb BD in a return salvo of gunfire, and take the yield (binning) hit.

As customers we only stand to win, but AMD is dealing with constantly shifting goalposts as they try and score a touchdown. That sucks for them, will be hard to earn a sense of accomplishment if you are on team BD.

This is a given, but still it will force margins down from Intel meaning a long term positive to AMD. Even so, it isn't a given that AMD can't produce a chip that has higher performance than even a top binned SB processor. I don't have a lot of faith in that, since they are lagging slightly in process technology, and most of the improvements in the BD architecture just brings them to parody to Nehalem, although they have a few clear advantages to even the SB architecture.

One they don't use a ring bus, allowing much better latency in core to core communication, along with better access to memory. Second, they have a more robust front end in many ways, and should be able to schedule tasks far more efficiently than even Sandybridge. There are a few others, but I need to go back and look to see them. Even so, none of them are really huge game changers, and if anything I expect the two architectures to have similar performance overall.

 

[deimos3428]

why does stock have to run at 200?

I suppose it doesn't, but it probably will given it will run in a socket that is backward-compatible with Phenom II.

 

[drizek]

This is a given, but still it will force margins down from Intel meaning a long term positive to AMD. Even so, it isn't a given that AMD can't produce a chip that has higher performance than even a top binned SB processor. I don't have a lot of faith in that, since they are lagging slightly in process technology, and most of the improvements in the BD architecture just brings them to parody to Nehalem, although they have a few clear advantages to even the SB architecture.

One they don't use a ring bus, allowing much better latency in core to core communication, along with better access to memory. Second, they have a more robust front end in many ways, and should be able to schedule tasks far more efficiently than even Sandybridge. There are a few others, but I need to go back and look to see them. Even so, none of them are really huge game changers, and if anything I expect the two architectures to have similar performance overall.

I'm sure the 8-core bulldozer will have a major advantage over the current batch of SBs, even the 2600K, in multithreaded tasks. But if AMD can't ship these things running in the mid-3GHz's at stock and at 4+ when overclocked, none of that will matter for us desktop users. For gaming and most daily tasks, Intel will still win, at least in the enthusiast market. If that leak is correct and 3.4Ghz is the stock speed, AMD is in pretty good shape for meainstream users and OEMs. If 3.8GHz is the max overclock though, that's not so good, particularly if Intel just starts shipping 4GHz SBs a week later.

The quad core Bulldozer might be successful in going after Clarkdale for budget systems, but I imagine it will cost more to produce than Clarkdale does. Hopefully AMD doesn't disable CPU features to differentiate their low end models.

Charlie published a photo of a BD wafer, folks are estimating it must be right around 310-320mm^2.

When AMD described Bulldozer modules as being 1.5x Phenom II, I figured that that meant that the quad-module version would end up with the same number of transistors as the X6, but with half the die area due to the process shrink. Why is it still only slightly smaller than Istanbul instead of being half the size? More Cache? Am I doing my math wrong or did I misunderstand the quote?

 

[aigomorla]

First cpuz shots and clocks around, fake or not.

You call this a leak?

WTF.. i call it a blank CPU-Z with just core speed.

At the very least he could of pulled the model number off.

Sorry, that doesnt show much to me but a guy who got the chip illegally and is half scared to get AMD security busting at his email asking for the chip back.

Well, Intel Security is scary as hell, trust me, u dont want to piss them off, never ran into AMD security.

 

[Castiel]

We need some real BD benchmarks already.

 

[Ajay]

We want some real BD benchmarks already.

FIFY.

 

[piesquared]

Unfortunately for AMD, this "plan B" has been available to Intel since C2D was launched.

They consistently sandbagged the clockspeed potential of their chips while maximizing yields and gross margins because AMD has yet to give them "a run for their money" since summer 2006.

And that is the sad reality for AMD...trumping today's SandyBridge SKU's with Bulldozer won't be enough because today's SB SKU's are all underclocked, immensely so.

A BD that thumps SB will simply mean lower margins for Intel as they will boost clockspeeds at each given pricepoint, thumb BD in a return salvo of gunfire, and take the yield (binning) hit.

As customers we only stand to win, but AMD is dealing with constantly shifting goalposts as they try and score a touchdown. That sucks for them, will be hard to earn a sense of accomplishment if you are on team BD.

Here's the thing though. If AMD decided that the very top of the market (>$500-$600) wasn't remotely worth chasing, then they could very quickly beat them on the other end of the spectrum: power consumption, efficiency and performance/watt. The fight there is much much closer and in fact AMD might actually have decent lead.

 

[Ajay]

Here's the thing though. If AMD decided that the very top of the market (>$500-$600) wasn't remotely worth chasing, then they could very quickly beat them on the other end of the spectrum: power consumption, efficiency and performance/watt. The fight there is much much closer and in fact AMD might actually have decent lead.

I'm curious as to why - I thought BD had an ~130W TDP envelope

 

[piesquared]

I'm curious as to why - I thought BD had an ~130W TDP envelope

And therefore, Bulldozer must compete very well.

 

[Maximilian]

We need some real BD benchmarks already.

This.

 

[Elixer]

On their conference call, they said bulldozer is "on track" for early summer... that means May/June release most likely.

Too bad they didn't say spring,

 

[drizek]

On their conference call, they said bulldozer is "on track" for early summer... that means May/June release most likely.

Too bad they didn't say spring,

++

That is disappointing. I really wish they get new motherboards out there in the meantime.