8-core Zambezi confirmed to be priced approx. $300

[GaiaHunter]

You guys are missing my point. Since AMD is calling this an 8-core, if it were actually at least the same performance as the 2600, they would be charging a premium because they can market it as 8 core. The fact that they aren't doesn't bode well.

That depends on several circumstances and objectives.

Additionally why not apply the same logic to the 4 core bulldozer (and from your post it seems to me you believe that this is in fact a dual-core)?

The FX-4110 is rumored to cost $190, which is the same price of their current phenom II 1100T and slightly less expensive than the i5 2500K (around $220) and similar price to the i5 2400.

With the FX-4110 there is no "bazillion core shenanigans" so to sell at a similar cost to those processors the performance has to be in the same ballpark.

Now if the quad core bulldozer can compete with a 4 core SB, the 8 core BD will compete very well with the i7 2600K.

This is exactly the same logic people are applying to the octo but just from the opposite perspective.

And we also have to remember the 4870, that performed as good/or better as the GTX260, launched at $300 (while the GTX260 was $400), showing that AMD has decided in the past to sell their products for less to achieve market penetration.

So making claims of BD performance based on rumored price isn't very accurate since one can logically demonstrate opposite things.

People that believe BD is going to be inferior to SB will pick up the FX-8130 as an example how AMD even with twice has many cores is not charging a premium. People that are of the opinion BD can compete with SB will use the FX-4110 example.

 

[AtenRa]

If the bellow information is correct, my prediction will be

AMD BD 4100 will be priced between Intel SB Core i3 2120 and Core i5 2300
AMD BD 6100 will be priced between Intel SB Core i5 2400 and Core i5 2500K
AMD BD 8100 will be priced close and ~above Intel SB Core i5 2500K
AMD BD 8150 will be priced close to Intel Core i7 2600K

I expect Bulldozer to need 500-600Mz more frequency than Intel SB to be competitive in IPC EDIT: Single Thread

AMD BD 4100 could be one of the best performance/price CPUs of H2 2011 due to OC friendly unlocked multi (ZERO Intel competition) and decent power usage due to 32nm SOI HKMG.

 

[toyota]

"I expect Bulldozer to need 500-600Mz more frequency than Intel SB to be competitive in IPC"

the way you worded that makes no sense because IPC does not change with clockspeeds.

 

[jvroig]

AMD BD 4100 could be one of the best performance/price CPUs of H2 2011 due to OC friendly unlocked multi (ZERO Intel competition) and decent power usage due to 32nm SOI HKMG.

I have often skipped over that detail in my head. You are right. If Bulldozer doesn't have the Sandy Bridge handicap of not allowing overclocking except for "K" (or "unlocked") units, then certain BD SKUs may certainly prove to be a boon for enthusiasts as a throw-back to the good-old days of overclocking - cheapest reasonable performer that can then overclock to the levels of the high-end SKUs.

I hope this comes true, I guess we'll see in about two months.

 

[AtenRa]

"I expect Bulldozer to need 500-600Mz more frequency than Intel SB to be competitive in IPC"

the way you worded that makes no sense because IPC does not change with clockspeeds.

thx, fixed it

 

[Riek]

thx, fixed it

I believe they only need 10% (or in those frequency ranges ~300MHz) Just because single threaded is without shared parts in the module.

 

[notty22]

That depends on several circumstances and objectives.

Additionally why not apply the same logic to the 4 core bulldozer (and from your post it seems to me you believe that this is in fact a dual-core)?

The FX-4110 is rumored to cost $190, which is the same price of their current phenom II 1100T and slightly less expensive than the i5 2500K (around $220) and similar price to the i5 2400.

With the FX-4110 there is no "bazillion core shenanigans" so to sell at a similar cost to those processors the performance has to be in the same ballpark.

Now if the quad core bulldozer can compete with a 4 core SB, the 8 core BD will compete very well with the i7 2600K.

This is exactly the same logic people are applying to the octo but just from the opposite perspective.

And we also have to remember the 4870, that performed as good/or better as the GTX260, launched at $300 (while the GTX260 was $400), showing that AMD has decided in the past to sell their products for less to achieve market penetration.

So making claims of BD performance based on rumored price isn't very accurate since one can logically demonstrate opposite things.

People that believe BD is going to be inferior to SB will pick up the FX-8130 as an example how AMD even with twice has many cores is not charging a premium. People that are of the opinion BD can compete with SB will use the FX-4110 example.

With all the cost/performance comparisons/ or rationalizations, you can also factor in AMD's current 190 dollar quad core

AMD Phenom II X4 980 Black Edition,


So hopefully the 32nm FX-4110 can match its performance.

 

[Phynaz]

Some people like reading rumors. If you don't, just pass the thread up and try to resist posting snide comments that advance nothing but your sense of superiority.

Your thread title says "confirmed". Now you claim it's a rumor. Make up your noggin.

 

[RussianSensation]

Additionally why not apply the same logic to the 4 core bulldozer (and from your post it seems to me you believe that this is in fact a dual-core)?

That's not what he said. He implied that if AMD needs an 8 core 3.9ghz processor to compete with a 2600k, then it can't possibly have a similar IPC per core. Why does IPC matter? Because SB ships at 3.4ghz but has a nice overclocking headroom to 4.7ghz+.

Hyper-threading only adds about 4-5% to the average performance of the 2600k. In other words, AMD is going to use an 8-core processor vs. a 4 core Intel processor.

If each BD core is as fast as a single SB core, then you will essentially get an 8 core "SB" (from AMD) vs. a 4 core SB (from Intel). But not only that, but the top CPU is expected to have 4.5ghz Turbo frequency? How are people expecting an 8 core "SB" like processor clocked at 4.5ghz? :whiste: Let me get this straight for a second......Santa Clause exists.

There are only 2 realistic possibilities:

1) BD is way behind in IPC compared to SB. As a result it needs both high clock speeds and more cores to remain competitive.
2) The 2-core module setup is nowhere near as fast as 2 full fledged cores.

Otherwise, if Bulldozer were truly 30-40% faster than SB (which surely would be if it was an 8-core processor clocked at 3.9ghz @ 4.5ghz Turbo with IPC comparable to SB), then prices would reflect this.

 

[Riek]

That's not what he said. He specifically said that if AMD needs an 8 core 3.9ghz processor to compete with a 2600k, then it's not going to be competitive in less then perfectly multi-threaded apps.

Hyper-threading only adds about 4-5% to the average performance of the 2600k. In other words, AMD is going to use an 8-core processor vs. a 4 core Intel processor.

If each BD core is as fast as a single SB core, then you will essentially get an 8 core "SB" (from AMD) vs. a 4 core SB (from Intel). But not only that, but the top CPU is expected to have 4.5ghz Turbo frequency? How are people expecting an 8 core "SB" like processor clocked at 4.5ghz? :whiste: Let me get this straight for a second......Santa Clause exists.

There are only 2 realistic possibilities:

1) BD is way behind in IPC compared to SB. As a result it needs both high clock speeds and more cores to remain competitive.
2) The 2-core module setup is nowhere near as fast as 2 full fledged cores.

Otherwise, if Bulldozer were truly 30-40% faster (which surely would be if it was an 8-core processor clocked at 3.9ghz with IPC comparable to SB), then prices would reflect this.

A module is indeed not as fast as two seperate cores.... statement is 180% from the beginning. it also doesn't have the fpu throughput of two seperate cores. The only part where AMD will have a serious core advantage is in integers. and even that is limited by the shared front-end. It however is alot better than HT which is completely limitted over the whole line. That is the reason why AMD went with BD design.

that means that if BD will range from 50% faster to 0% faster in multithreading when using 8 threads compared to SB. (if you make everything else the same). I already explained this concept a gazzilion times to you, as did others. You are staring blindly at the BD concept, try reading up on it so you really understand the concept, its goal and the design choices.

AMD is not launching an FX 3.9GHz TB4.5GHz to compete with 2600.


Just like other posters mention, its better to look at the FX4 placement to determine the performance stick. If it can compete with the i5 2400(3.1->3.4Ghz) it would bode extremely well for AMD. If it is positonned against the i3 then it wouldn't bode to well.

 

[RussianSensation]

I already explained this concept a gazzilion times to you, as did others. You are staring blindly at the BD concept, try reading up on it so you really understand the concept, its goal and the design choices.

I read on BD many times. I already know that AMD stated that a 2-core Module design is only 80% as efficient as 2 full fledged cores. What if it's up to 80% as fast, but not 80% on average?

I still haven't seen a single person address the 50% IPC deficit that Phenom II has over SB. It's very convenient to keep dismissing this in all BD threads as if it doesn't matter. If BD is such a breakthrough in IPC as to match SB, then why has AMD delayed launching such a fast single-threaded processor at much lower clock speeds?

Starcraft 2 is the poster child for measuring IPC differences in games. The quad-core i5-2500 and i7-2600 spank all of the current hexacore AMD CPUs. In fact, a dual core HT i3 2100 is as fast as a hexacore 1100T Phenom.

At 1920x1080, Phenom II's minimum frames are almost 2x lower than they are of SB processors in SC2.

More cores is the new MHz myth.

AMD is not launching an FX 3.9GHz TB4.5GHz to compete with 2600.

Maybe not right away but next year. Think about it, their highest end model in September is expected to have Turbo of 4.2ghz. You expect me to believe BD IPC = SB? So we'll have 4.2ghz SB-like processor from AMD for $300 then?

I expect our forum to be dominated by Cinebench R11.5 benches shortly to highlight how much faster BD is over SB. :biggrin:

Just like other posters mention, its better to look at the FX4 placement to determine the performance stick. If it can compete with the i5 2400(3.1->3.4Ghz) it would bode extremely well for AMD.

AMD sells Phenom II X4 980 for $190. If we only looked at AMD's placement and pricing strategy for that CPU, we would expect it to be good. Yet, it's completely uncompetitive. In fact, that CPU is worse than the Core i5 750 from September of 2009.

 

[podspi]

I read on BD many times. I already know that AMD stated that a 2-core Module design is only 80% as efficient as 2 full fledged cores. What if it's up to 80% as fast, but not 80% on average?

I still haven't seen a single person address the 50% IPC deficit that Phenom II has over SB. It's very convenient to keep dismissing this in all BD threads as if it doesn't matter. If BD is such a breakthrough in IPC as to match SB, then why has AMD delayed launching such a fast single-threaded processor at much lower clock speeds?

Starcraft 2 is the poster child for CPU intensive games. The quad-core i5-2500 and i7-2600 spank all of the current hexacore AMD CPUs. In fact, a dual core HT i3 2100 is as fast as a hexacore 1100T Phenom. More cores is the new MHz myth.



Maybe not right away but next year. Think about it, their highest end model in September will already have Turbo of 4.2ghz. You expect me to believe BD IPC = SB? So we'll have 4.2ghz SB processor from AMD for $300 then?

I expect our forum to be dominated by Cinebench R11.5 benches shortly to highlight how much faster BD is over SB. :biggrin:



AMD sells Phenom II X4 980 for $190. If we only looked at AMD's placement and pricing strategy for that CPU, we would expect it to be good. Yet, it's completely uncompetitive. In fact, that CPU is worse than the Core i5 750 from September of 2009.

You are forgetting lock-in, though. There are lots of people with AM2+/AM3 boards who just want an upgrade, and so they will be willing to pay more for the CPU in order to not have to build an entirely new machine.

This isn't the case with Bulldozer, because AMD decided it wouldn't be compatible with AM3. I honestly have no idea how large the PiB market is, but that could have an effect. Do we have any idea how much Phenom's go for in the OEM market? I realize they post prices online, but are those prices actually charged, or do they have deals with each OEM?

 

[Troll Trolling]

That's not what he said. He implied that if AMD needs an 8 core 3.9ghz processor to compete with a 2600k, then it can't possibly have a similar IPC per core. Why does IPC matter? Because SB ships at 3.4ghz but has a nice overclocking headroom to 4.7ghz+.

Hyper-threading only adds about 4-5% to the average performance of the 2600k. In other words, AMD is going to use an 8-core processor vs. a 4 core Intel processor.

If each BD core is as fast as a single SB core, then you will essentially get an 8 core "SB" (from AMD) vs. a 4 core SB (from Intel). But not only that, but the top CPU is expected to have 4.5ghz Turbo frequency? How are people expecting an 8 core "SB" like processor clocked at 4.5ghz? :whiste: Let me get this straight for a second......Santa Clause exists.


There are only 2 realistic possibilities:

1) BD is way behind in IPC compared to SB. As a result it needs both high clock speeds and more cores to remain competitive.
2) The 2-core module setup is nowhere near as fast as 2 full fledged cores.

Otherwise, if Bulldozer were truly 30-40% faster than SB (which surely would be if it was an 8-core processor clocked at 3.9ghz @ 4.5ghz Turbo with IPC comparable to SB), then prices would reflect this.

So, your argument is that it is impossible to a BD core be as fast as a SB one?

For you, being "impossible" is not the consequence of a reasonable logical thinking, but the argument itself?

 

[RussianSensation]

So, your argument is that it is impossible to a BD core be as fast as a SB one?

I am not going to say that it's impossible, but highly unlikely.

For you, being "impossible" is not the consequence of a reasonable logical thinking, but the argument itself?

So you think it's more logically reasonable that AMD, which has been completely uncompetitive since C2D days, and has delayed BD for a countless number of times, will suddenly release a 3.9ghz (+ Turbo Mode) SB-like IPC 80% efficiency of a full 8-core processor for just $300? Is this like the R300 AMD HD6970 will smoke GTX580 by 30% hype all over again?

 

[Idontcare]

So, your argument is that it is impossible to a BD core be as fast as a SB one?

For you, being "impossible" is not the consequence of a reasonable logical thinking, but the argument itself?

I think the primary point motivating all of this is the thread-title itself...the fact (confirmed per thread title) that Bulldozer will "top out" at around $300 gives us indication of where the performance must fall.

As others have rightly pointed out, if bulldozer performed such that it could command a $1000 price point in a market filled with $1000 westmere and $300 sandy bridge then without doubt AMD would price it as such. They are still a for-profit business.

 

[nyker96]

To RussianSensation, I agree with most of what you say here. I think in most cases, this IPC is the bane for AMD cpus. But I heard BD does increase IPC to certain extent with some architectural improvement but nothing so drastic as to get near intel chips. still i think it will win in a multithreaded environment.

 

[dguy6789]

snip

Just to play devil's advocate: The Athlon 64 outclassed the Pentium 4 in nearly every benchmark, at every performance level. On top of that, at every single performance level, the Athlon 64 variant was almost always cheaper to buy than the equivalent Pentium 4.

 

[Bearach]

I think the primary point motivating all of this is the thread-title itself...the fact (confirmed per thread title) that Bulldozer will "top out" at around $300 gives us indication of where the performance must fall.

As others have rightly pointed out, if bulldozer performed such that it could command a $1000 price point in a market filled with $1000 westmere and $300 sandy bridge then without doubt AMD would price it as such. They are still a for-profit business.

Not aimed totally at you, but AMD doesn't state which 8 core version this is. It just states an 8 Core FX series processor. So it may be the top of the line 8 core or a lower edition. It's pretty likely it is the top tier, but we can't be sure.

7. Prizes:

Top tier prizes: Five (5) AMD FX series eight-core processors. Approximate Retail Value: $300 USD each.

Second tier prizes: One hundred (100) collectible Ruby dolls. Approximate Value: $25 USD each.

 

[Vesku]

I expect our forum to be dominated by Cinebench R11.5 benches shortly to highlight how much faster BD is over SB. :biggrin:

Don't forget the onslaught of counter posted SuperPi benches. :biggrin:

Remember folks look for numbers on your workload. It's doubtful BD will supplant SB in the gamer workload as most games are designed to work well on dual cores still, with some being coded to take advantage of quad cores if present. If Intel had released a i3-2100K it would be the king of low budget gaming.

 

[Idontcare]

Not aimed totally at you, but AMD doesn't state which 8 core version this is. It just states an 8 Core FX series processor. So it may be the top of the line 8 core or a lower edition. It's pretty likely it is the top tier, but we can't be sure.

LOL, that makes my point from post 22 all the more delicious.

So not only is this thread nothing more than about "confirming as approximately" but we don't even have a clue what it is that is being confirmed...just some random 8-core zambezi. Could be a 2GHz SKU or a 5GHz one...

The silliness, it continues.

 

[nsdjoe]

I think debating the semantics of the thread title is what's gotten silly here. We have an official AMD webpage stating that an 8-core Bulldozer chip will have a retail price of approximately $300, which is what the thread title states. Nowhere did I claim that it will be the very top end chip, nor did I claim any other specs.

You people fight like cats and dogs over the stupidest things.

 

[exar333]

I think debating the semantics of the thread title is what's gotten silly here. We have an official AMD webpage stating that an 8-core Bulldozer chip will have a retail price of approximately $300, which is what the thread title states. Nowhere did I claim that it will be the very top end chip, nor did I claim any other specs.

You people fight like cats and dogs over the stupidest things.

That's the point though. Will this be a 3.0ghz+ with a 4ghz turbo 8-core, or a sub-3ghz with a low turbo? That makes a HUGE impact on the value of this 'approx' $300 part.

 

[RussianSensation]

To RussianSensation, I agree with most of what you say here. I think in most cases, this IPC is the bane for AMD cpus. But I heard BD does increase IPC to certain extent with some architectural improvement but nothing so drastic as to get near intel chips. still i think it will win in a multithreaded environment.

I think BD will be good in the server environment, and very successful for rendering, 3D video applications and audio encoding, etc.

 

[RussianSensation]

Just to play devil's advocate: The Athlon 64 outclassed the Pentium 4 in nearly every benchmark, at every performance level. On top of that, at every single performance level, the Athlon 64 variant was almost always cheaper to buy than the equivalent Pentium 4.

Let me refresh your memory.

Pentium 4 3.2ghz vs. Athlon 64 3200+.

A64 was faster in games, but otherwise Pentium 4 3.2ghz HT competed well against it. With overclocking and onslaught of X2 processors, AMD really pulled ahead of Pentium-D. However, those X2 processors cost $400-500. The difference between a single core A64 and Pentium 4 "C" was actually fairly small at stock speeds. The gap in performance today is nothing like it was between A64 and Pentium 4. Pentium 4 didn't really have great overclocking headroom compared to Athlon 64 (on a % basis) and it didn't have leading IPC either. With SB it is an entirely different situation. You have an Intel CPU with serious overclocking headroom (nearly 35-40%) + leading IPC at the same time. So even if BD can compete at stock speeds, that's still only half way there. For enthusiasts like us, in its overclocked form it would also have to be able to compete with an overclocked SB.

Ironically, the situations where BD will likely be strong are exactly the ones where Pentium 4 outperformed A64 - Rendering, video encoding, etc. Yet, A64 proved to be superior for a lot of us since it was better for games - just like SB is today.

Also, Intel had 2 competing architectures at the time -- Pentium M and Pentium 4. Pentium M was actually superior to A64 in the mobile sector. Intel already knew that Netburst was end of the line since they miscalculated their ability to increase frequency. So the fact that A64 was better had a lot to do not only with AMD's excellent CPU, but also with Intel's failure to release a desktop Dothan/Banias Pentium M processors.

If Pentium M had been available on a desktop socket as a mainstream offering, then A64 wouldn't have been as special as it turned out.

 

[psolord]

I still haven't seen a single person address the 50% IPC deficit that Phenom II has over SB. It's very convenient to keep dismissing this in all BD threads as if it doesn't matter. If BD is such a breakthrough in IPC as to match SB, then why has AMD delayed launching such a fast single-threaded processor at much lower clock speeds?

Starcraft 2 is the poster child for measuring IPC differences in games. The quad-core i5-2500 and i7-2600 spank all of the current hexacore AMD CPUs. In fact, a dual core HT i3 2100 is as fast as a hexacore 1100T Phenom.

At 1920x1080, Phenom II's minimum frames are almost 2x lower than they are of SB processors in SC2.

More cores is the new MHz myth.



Maybe not right away but next year. Think about it, their highest end model in September is expected to have Turbo of 4.2ghz. You expect me to believe BD IPC = SB? So we'll have 4.2ghz SB-like processor from AMD for $300 then?

You are forgetting a very important thing. Phenom IIs are lacking three very important SSE instruction sets. SSSE3, SSE4.1 and SSE4.2. From what I know, 4.1 and 4.2 will be implemented in Bulldozers. Not sure about SSSE3.

Doesn't that make you wonder, what happens when these instructions are used by various apps, favoring Intel cpus and are nowhere to be found on Phenom IIs? Doesn't that make you wonder, what will happen now that the Bulldozers will support them? We could be witnessing a big performance difference compared to the Phenom II, just by these instructions alone. Not to mention the higher clocks and more cores.

I am not mentioning AVX here, since I hardly believe it would have anything to do performance wise today, being so young as it is.