Unfortunately with carefully picked demos and specs catering to its strength. Actually Intel has IDF going too but it seems that most of what is to learn there is already known.
Even after this slow roll out of info, we still have little on clock rate or actual CPU performance. It does lead one to underestimate the over all performance of this "APU". What ever happened to releasing the whole ball of wax at once?
Even with the sparse info it still looks like the Bobcats will be excellent processors for AOliR like notebooks and possibly Minis and the plastic Mac Books. Hopefully info will develop further as the week progresses. As to the Mini, even if Xacate only weny into the low end Mini it would make for an excellent and COOL mini.
The 18 watts here is very impressive even if we don't know where the clock rates live. The other thing here is just how tiny the processor is. With a process shrink the chip should be very economical and lower power yet again. Or maybe more cores in a simularly sized die. Of course my adoration might fly out the window when we find out what the clock rates are for the CPU half.
This will be one interesting week. Hopefully real hardware will be with us in a months time.
Dave
If the "fastest" Zacate isn't even better than an old 1.60GHz C2D (as per the article linked above), what's the point in using it in the Mac mini/white MB that are actually equipped with a 2.40GHz C2D + 320M chipset. Also, the test was "single threaded performance" that's not much relevant.
I believe that Ontario/Zacate will be really good competitors to Atom (and probably some ULV C2D) cpus if the price is right (the most expensive Atom is the N550 at $86), but I don't see them in any consumer Mac unless Apple decides to replace the MBA will a smaller/lighter/thinner/less powerful/cheaper model. For any other Mac, LLano will be the minimum.
Don't expect that "magically" Zacate will get more cores or will clock at 2.50GHz. Right now, the rumors are 1.20GHz max for Ontario and 1.60/1.80GHz for Zacate (both dual cores).
The other thing that doesn't favor AMD right now is the timing of the releases: Llano is postponed to Q3 2011 and Bulldozer even later, that means that Intel's mainstream SB cpus will be available for about 6 months before AMD releases Llano, it may be too late by then, especially when Intel is supposed to start releasing some 22nm Ivy Bridge cpus in H2 2011 (most likely Q4 2011).
But that won't stop me from answering some of your questions.
Quote:
.... "fastest" Zacate isn't even better than an old 1.60GHz C2D (as per the article linked above), what's the point in using it in the Mac mini/white MB that are actually equipped with a 2.40GHz C2D + 320M chipset. Also, the test was "single threaded performance" that's not much relevant.
Much will depend upon maximum clock rates that the device can achieve. Note however that that is not a parameter everybody is concerned with. Admittedly Zacate will have to hit close to 2.5 GHz to match the current machines but I do think it is possible given the markets AMD is after.
Also consider that many use the Mini as an always on HTPC and would recognize the potential power savings as a good benefit of the Zacate. The only parameter that is important here is doing 1080P well. There are similar uses where absolute CPU power isn't as important as is very low power.
Quote:
I believe that Ontario/Zacate will be really good competitors to Atom (and probably some ULV C2D) cpus if the price is right (the most expensive Atom is the N550 at $86), but I don't see them in any consumer Mac unless Apple decides to replace the MBA will a smaller/lighter/thinner/less powerful/cheaper model.
The markets AMD are targetting include thoose you describe and low end PCs.
Lets say though that Apple only use Zacate in an AIR upgrade, for AMD it is still a huge win and validates the processor. Plus in the AIR upgrade it could actually lead to far better performace over all than the current implementation. Especially if they can run without thermal throttling.
I think it is a mistake to automatically assume that AIR would be less powerful with this chip in place. Given the unknown of maximum clock rate and the benefits of the tight integration we could actually see far better performance. If battery life is folded into the equation, it could mean a whole new level of consummer satisfaction.
Quote:
For any other Mac, LLano will be the minimum.
If we assume that the chip maxs out at 1.8GHz that may very well be the case. However Apple could easily release a desktop platform for this product that is independent of the Mini and let the market decide. The reality is 1.8 Ghz is fine for many uses, especially when other parts of the chip take care of Video and graphics.
If Apple can hit the $500 mark all the better. Steve was pretty accurate back when he nade the comment about the $500 PC, it is very difficult to make such a product with low power chips from Intel. Zacate offers up the possibility of that $500 dollar Apple PC happening with respectable performance and low power.
Quote:
Don't expect that "magically" Zacate will get more cores or will clock at 2.50GHz. Right now, the rumors are 1.20GHz max for Ontario and 1.60/1.80GHz for Zacate (both dual cores).
I don't expect magic, but I do expect the line to grow in the same way that CPUs and GPUs have for the kast few years, that is more cores. Someone has already hinted that AMD implied that the GPU might be rev'ed much faster on these chips than the CPU cores. Obviously we don't know what AMD has up its sleeve with respect to cores or clock rate however do they really have any choice? Lets face it to continue to compete in the long run with Intel they will need more CPU cores. Also initial devices may be marketed at 1.8 GHz or whatever but it would have been foolish for AMD to design a chip that can't run faster at the 40nm node. It has nothing to do with magic, but rather acknowkedges where the competition will be.
Quote:
The other thing that doesn't favor AMD right now is the timing of the releases: Llano is postponed to Q3 2011 and Bulldozer even later, that means that Intel's mainstream SB cpus will be available for about 6 months before AMD releases Llano, it may be too late by then, especially when Intel is supposed to start releasing some 22nm Ivy Bridge cpus in H2 2011 (most likely Q4 2011).
AMD isn't even targeting the same market with Bobcat. Sandy Bridge is an entirely different piece of hardware targetted at higher end machines. Unless Intel wants to market SB at the same price points as the Bobcat Fusion products AMD doesn't have to worry. Intel does have to worry with respect to its ATOM line, its ULV CPUs and much of its lower end hardware line up.
A big unknown (apart from the real core performance) is the pricing of ontario/zacate/llano cpus. This also can help or hurt AMD. So we'll see...
Well I have to agree about the unknowns, it isn't just CPU core clock rate that is a factor here as the GPU clock is unknown too. It isn't even known how much flexibility a manufacture will have here. For example running the GPU at a higher clock rate for say a desktop implementation.
The fact that AMD is holding this info even after yesterdays release isn't very positive. But lets say ontario is 1.2 GHz @ 9 watts, Zacates jump to 18 watts seems huge if it is only going to 1.6GHz. I'm still optimistic but have tempered my expectations and wait for real products running this hardware.
Comments
PPS maybe the bobcat love-fest should be spun off into another thread?
Unfortunately with carefully picked demos and specs catering to its strength. Actually Intel has IDF going too but it seems that most of what is to learn there is already known.
Even after this slow roll out of info, we still have little on clock rate or actual CPU performance. It does lead one to underestimate the over all performance of this "APU". What ever happened to releasing the whole ball of wax at once?
Even with the sparse info it still looks like the Bobcats will be excellent processors for AOliR like notebooks and possibly Minis and the plastic Mac Books. Hopefully info will develop further as the week progresses. As to the Mini, even if Xacate only weny into the low end Mini it would make for an excellent and COOL mini.
The 18 watts here is very impressive even if we don't know where the clock rates live. The other thing here is just how tiny the processor is. With a process shrink the chip should be very economical and lower power yet again. Or maybe more cores in a simularly sized die. Of course my adoration might fly out the window when we find out what the clock rates are for the CPU half.
This will be one interesting week. Hopefully real hardware will be with us in a months time.
Dave
If the "fastest" Zacate isn't even better than an old 1.60GHz C2D (as per the article linked above), what's the point in using it in the Mac mini/white MB that are actually equipped with a 2.40GHz C2D + 320M chipset. Also, the test was "single threaded performance" that's not much relevant.
I believe that Ontario/Zacate will be really good competitors to Atom (and probably some ULV C2D) cpus if the price is right (the most expensive Atom is the N550 at $86), but I don't see them in any consumer Mac unless Apple decides to replace the MBA will a smaller/lighter/thinner/less powerful/cheaper model. For any other Mac, LLano will be the minimum.
Don't expect that "magically" Zacate will get more cores or will clock at 2.50GHz. Right now, the rumors are 1.20GHz max for Ontario and 1.60/1.80GHz for Zacate (both dual cores).
The other thing that doesn't favor AMD right now is the timing of the releases: Llano is postponed to Q3 2011 and Bulldozer even later, that means that Intel's mainstream SB cpus will be available for about 6 months before AMD releases Llano, it may be too late by then, especially when Intel is supposed to start releasing some 22nm Ivy Bridge cpus in H2 2011 (most likely Q4 2011).
Q1 2011 Intel mainstream SB cpus, AMD Ontario/Zacate
Q2 2011 Intel LV/ULV SB cpus
Q3 2011 Intel high-end/Xeon SB cpus, AMD LLano
Q4 2011 Intel 22nm Ivy Bridge cpus (some models), AMD Bulldozer (maybe...)
A big unknown (apart from the real core performance) is the pricing of ontario/zacate/llano cpus. This also can help or hurt AMD. So we'll see...
.... "fastest" Zacate isn't even better than an old 1.60GHz C2D (as per the article linked above), what's the point in using it in the Mac mini/white MB that are actually equipped with a 2.40GHz C2D + 320M chipset. Also, the test was "single threaded performance" that's not much relevant.
Much will depend upon maximum clock rates that the device can achieve. Note however that that is not a parameter everybody is concerned with. Admittedly Zacate will have to hit close to 2.5 GHz to match the current machines but I do think it is possible given the markets AMD is after.
Also consider that many use the Mini as an always on HTPC and would recognize the potential power savings as a good benefit of the Zacate. The only parameter that is important here is doing 1080P well. There are similar uses where absolute CPU power isn't as important as is very low power.
I believe that Ontario/Zacate will be really good competitors to Atom (and probably some ULV C2D) cpus if the price is right (the most expensive Atom is the N550 at $86), but I don't see them in any consumer Mac unless Apple decides to replace the MBA will a smaller/lighter/thinner/less powerful/cheaper model.
The markets AMD are targetting include thoose you describe and low end PCs.
Lets say though that Apple only use Zacate in an AIR upgrade, for AMD it is still a huge win and validates the processor. Plus in the AIR upgrade it could actually lead to far better performace over all than the current implementation. Especially if they can run without thermal throttling.
I think it is a mistake to automatically assume that AIR would be less powerful with this chip in place. Given the unknown of maximum clock rate and the benefits of the tight integration we could actually see far better performance. If battery life is folded into the equation, it could mean a whole new level of consummer satisfaction.
For any other Mac, LLano will be the minimum.
If we assume that the chip maxs out at 1.8GHz that may very well be the case. However Apple could easily release a desktop platform for this product that is independent of the Mini and let the market decide. The reality is 1.8 Ghz is fine for many uses, especially when other parts of the chip take care of Video and graphics.
If Apple can hit the $500 mark all the better. Steve was pretty accurate back when he nade the comment about the $500 PC, it is very difficult to make such a product with low power chips from Intel. Zacate offers up the possibility of that $500 dollar Apple PC happening with respectable performance and low power.
Don't expect that "magically" Zacate will get more cores or will clock at 2.50GHz. Right now, the rumors are 1.20GHz max for Ontario and 1.60/1.80GHz for Zacate (both dual cores).
I don't expect magic, but I do expect the line to grow in the same way that CPUs and GPUs have for the kast few years, that is more cores. Someone has already hinted that AMD implied that the GPU might be rev'ed much faster on these chips than the CPU cores. Obviously we don't know what AMD has up its sleeve with respect to cores or clock rate however do they really have any choice? Lets face it to continue to compete in the long run with Intel they will need more CPU cores. Also initial devices may be marketed at 1.8 GHz or whatever but it would have been foolish for AMD to design a chip that can't run faster at the 40nm node. It has nothing to do with magic, but rather acknowkedges where the competition will be.
The other thing that doesn't favor AMD right now is the timing of the releases: Llano is postponed to Q3 2011 and Bulldozer even later, that means that Intel's mainstream SB cpus will be available for about 6 months before AMD releases Llano, it may be too late by then, especially when Intel is supposed to start releasing some 22nm Ivy Bridge cpus in H2 2011 (most likely Q4 2011).
AMD isn't even targeting the same market with Bobcat. Sandy Bridge is an entirely different piece of hardware targetted at higher end machines. Unless Intel wants to market SB at the same price points as the Bobcat Fusion products AMD doesn't have to worry. Intel does have to worry with respect to its ATOM line, its ULV CPUs and much of its lower end hardware line up.
Q1 2011 Intel mainstream SB cpus, AMD Ontario/Zacate
Q2 2011 Intel LV/ULV SB cpus
Q3 2011 Intel high-end/Xeon SB cpus, AMD LLano
Q4 2011 Intel 22nm Ivy Bridge cpus (some models), AMD Bulldozer (maybe...)
A big unknown (apart from the real core performance) is the pricing of ontario/zacate/llano cpus. This also can help or hurt AMD. So we'll see...
Well I have to agree about the unknowns, it isn't just CPU core clock rate that is a factor here as the GPU clock is unknown too. It isn't even known how much flexibility a manufacture will have here. For example running the GPU at a higher clock rate for say a desktop implementation.
The fact that AMD is holding this info even after yesterdays release isn't very positive. But lets say ontario is 1.2 GHz @ 9 watts, Zacates jump to 18 watts seems huge if it is only going to 1.6GHz. I'm still optimistic but have tempered my expectations and wait for real products running this hardware.