Great news! Better technology is coming in the future!
This kind of post always makes me laugh a bit. They could announce any upgraded processor is coming out in a year and everyone would post the exact same responses.
It's at the same time comforting that yes, the future holds smaller and faster computers and yes, apple insider posts will never change!
So, you're saying that they shouldn't report this, and we shouldn't be talking about it?
Ok, everyone, leave the thread and go do something useful. This is a waste of time!
And until last month, every reference to Penryn you could find online said that it was the refresh of Merom, the mobile processor -- not the overarching name for an entire family of refreshes. So yes, this is new, and a change (maybe this is what Intel had intended all along, but if so, all the websites with info on Penryn got it wrong).
Whatever they had said, Penryn is the name for the first line of 45 nm chips.
Quote:
Exactly, that's what I'm saying -- previously, until Intel started releasing more details last month, Penryn was supposed to be a mobile chip to be released in 2007, alongside a desktop chip with another name; now it's a "family" whose mobile variant will be released in 2008. Furthermore, that mobile Penryn, its later quad-core brother, and Nehalem, a completely new architecture, are going to all be squeezed into that one year. It just seems strange to me, enough so that I'm starting to think that the Mobile version of Nehalem will have to wait for 2009. I would point out that the very fact that mobile Penryn is coming out in '08 is a blow to the whole 2-year "tick-tock" cycle Intel has been hyping. The last "tick" was in 2006, so the "tock" was expected in 2007, but no more.
Not exactly. Penyrn is the tick, and Nehalem is the tock. You're forgetting that all of these lines overlap. The tick is still ticking while the tock starts its tocking.
Quote:
No; Core and Core 2 are the marketing names for two different architectures, whereas Penryn is a codename, like Yonah. Presumably Penryn will be marketed as Core 2 as well, since this is just a die shrink and not a new architecture. But no, as I indicated above, Penryn didn't always stand for the entire 45nm line, it had previously been just one of the chips in that line. Likewise, back when Core was the current model, we knew Intel had plans for a new microarch with three codenames, one for each chip in that line.
You're contradicting yourself. Core and Core 2 were different architectures (to a certain extent). Penyrn and Nehalen will also be different architectures as well. There are names given that are changed once the chips come out as well.
Quote:
Everything I've read indicates mid-late 2008 for Nehalem. What I'm saying is that it seems strange that they would squeeze both the (mobile) die shrink, the quad core of that die shrink, and the brand new arch into the first let's say 9 months of 2008, yet release virtually no new mobile processors in 2007 besides a speed bump when Santa Rosa comes out (2.33GHz to 2.4.. big whoop). It's just a little disappointing and confusing is all.
I'm reading early-mid. We might see the mobile Penyrn in late 2007. That would be more than a speed bump.
Quote:
I agree, but Apple apparently doesn't; they could have quad-core, 2.93GHz iMacs now if they wanted, but they prefer to stick with Merom for some reason. If it's just pin compatibility, then maybe they will upgrade when this new processor comes out. On the other hand, if they really are excessively concerned with fan noise and/or not letting their consumer desktop outperforming their pro laptop, then no.
They ARE exceffively concerned with fan noise. Actually, I would say obsessively instead. Consumers are used to hearing nothing from their Tv's audio systems, etc. Apple is trying to make their computers for the home meet that expectation.
[/quote]
This would be spot on based on what the hardware sites were reporting a few months ago, but they've now changed it and the Penryn name now covers the entire gamut of 45nm processors. Doesn't make any sense based on past precedents, but there you have it.
Are you sure Penryn will be Core 3, though? I would think they'd stick with the Core 2 brand since Penryn is just a shrunken Core 2.[/QUOTE]
And until last month, every reference to Penryn you could find online said that it was the refresh of Merom, the mobile processor -- not the overarching name for an entire family of refreshes. So yes, this is new, and a change (maybe this is what Intel had intended all along, but if so, all the websites with info on Penryn got it wrong).
I don't know, on Intel's site the code name is used to describe the whole family. It's not really important, though.
Quote:
Originally Posted by melgross
I'm reading early-mid. We might see the mobile Penyrn in late 2007. That would be more than a speed bump.
I think you're right, Intel won't refresh the CPU and the platform simultaneously. Santa Rosa will debut with Merom in May, Penryn is slated to hit production later this year and will be paired with Santa Rosa.
first half of 2006, new mobile platform: Napa (with Yonah mobile processor)
fall 2006, new microarchitecture: Merom 65nm mobile processor (in Napa platform)
first half of 2007, new mobile platform: Santa Rosa (with existing Merom mobile processor)
fall 2007, processor die shrink: Penryn 45nm (in Santa Rosa platform)
first half of 2008, new mobile platform: Montevina (with existing Penryn mobile processor)
fall 2008, new microarchitecture: Nehalem 45nm (in Montevina platform)
Whatever they had said, Penryn is the name for the first line of 45 nm chips.
I know. I'm just pointing out that, and the release date, are a change from a few months ago.
Quote:
Not exactly. Penyrn is the tick, and Nehalem is the tock. You're forgetting that all of these lines overlap. The tick is still ticking while the tock starts its tocking.
Uhh... I don't think it really matters whether we designate the die shrink the "tock" or the architecture change. Yonah was a die shrink, Merom/Conroe/Woodcrest was a new arch, Penryn will be a die shrink, Nehalem, a new arch.
Quote:
You're contradicting yourself. Core and Core 2 were different architectures (to a certain extent). Penyrn and Nehalen will also be different architectures as well. There are names given that are changed once the chips come out as well.
I'm not contradicting myself at all. Penryn is not a new arch -- it's just a shrink of an existing one. Nehalem, on the other hand, is new.
Yonah = Core = a hybrid arch of Pentium-M and new features
Penryn = a shrunken Core 2 with higher clockspeeds
Nehalem = a brand new architecture
I'm not saying Penryn is insignificant, it's just more evolution than revolution. It's just a die shrink, whereas Core->Core 2 was a new arch altogether, so I am supposing that "Core 3" will refer to a new arch, and thus Nehalem, as well. It seems pretty obvious to me.
Quote:
I'm reading early-mid. We might see the mobile Penyrn in late 2007. That would be more than a speed bump.
I hope that's true (where are you "reading" this though? All the new info suggests otherwise), I just don't understand why rumor sites and hardware sites are reporting "early 2008" for mobile Penryn without mentioning that it's a push back from the original date. Imagine the screaming if Apple announced a product and then pushed it back.. oh, wait
If there won't be a Core 3, then what's the differentiation between the lower speed/performance Core 2 parts and the new Penryn line cores?
I think Core 3 sounds logical.
It's not that there won't be a Core 3, just that it's Unlikely that Intel will name their newer chips Core 3. One reason why they named them Core was because they had one core, then Core had up to 2 Cores. Recently that numvering scheme was broken with the 4 core chips. So, it wasn't gust the itewration of two new designs.
Penyrn will have some improvements over the present chips, in addition to being a die shrink. But, nothing like what we will see with Nehalen. That will be a break with Intel's past with the on-die controller. The other major impovements (such as built-in WiMax for the mobile chips) will make these chips seriously heavy performers indeed.
Don't worry, time isn't standing still as it was with the PPC.
I don't know, on Intel's site the code name is used to describe the whole family. It's not really important, though.
I think you're right, Intel won't refresh the CPU and the platform simultaneously. Santa Rosa will debut with Merom in May, Penryn is slated to hit production later this year and will be paired with Santa Rosa.
first half of 2006, new mobile platform: Napa (with Yonah mobile processor)
fall 2006, new microarchitecture: Merom 65nm mobile processor (in Napa platform)
first half of 2007, new mobile platform: Santa Rosa (with existing Merom mobile processor)
fall 2007, processor die shrink: Penryn 45nm (in Santa Rosa platform)
first half of 2008, new mobile platform: Montevina (with existing Penryn mobile processor)
fall 2008, new microarchitecture: Nehalem 45nm (in Montevina platform)
That's about right, except that we may see some of the Nehalem chips out before that.
I know. I'm just pointing out that, and the release date, are a change from a few months ago.
Uhh... I don't think it really matters whether we designate the die shrink the "tock" or the architecture change. Yonah was a die shrink, Merom/Conroe/Woodcrest was a new arch, Penryn will be a die shrink, Nehalem, a new arch.
It doesn't matter what we think. This is Intel's ball. They do the naming, not us. They say that the die shrink is the tick, and the architecture improvements are the tock. It makes perfect sense.
Quote:
I'm not contradicting myself at all. Penryn is not a new arch -- it's just a shrink of an existing one. Nehalem, on the other hand, is new.
Yonah = Core = a hybrid arch of Pentium-M and new features
Penryn = a shrunken Core 2 with higher clockspeeds
Nehalem = a brand new architecture
I'm not saying Penryn is insignificant, it's just more evolution than revolution. It's just a die shrink, whereas Core->Core 2 was a new arch altogether, so I am supposing that "Core 3" will refer to a new arch, and thus Nehalem, as well. It seems pretty obvious to me.
Peryrn also has changes, it's not just a die shrink. There are notable improvements over the current Core 2 designs.
This is a good article detailing most of what we can expect from both Penyrn and Nehalem.
I hope that's true (where are you "reading" this though? All the new info suggests otherwise), I just don't understand why rumor sites and hardware sites are reporting "early 2008" for mobile Penryn without mentioning that it's a push back from the original date. Imagine the screaming if Apple announced a product and then pushed it back.. oh, wait
Mobile Penyrn has apparently been pushed back because of design changes which were enumerated in the Article about them that I linked to yesterday.
I'll have to look some more for articles with more about the dates if you are really interested. I don't think that 6 months is all really that important though.
Quote:
Why not?
I just don't think that Intel will continue with that naming convention.
It's not that there won't be a Core 3, just that it's Unlikely that Intel will name their newer chips Core 3. One reason why they named them Core was because they had one core, then Core had up to 2 Cores. Recently that numvering scheme was broken with the 4 core chips. So, it wasn't gust the itewration of two new designs.
Penyrn will have some improvements over the present chips, in addition to being a die shrink. But, nothing like what we will see with Nehalen. That will be a break with Intel's past with the on-die controller. The other major impovements (such as built-in WiMax for the mobile chips) will make these chips seriously heavy performers indeed.
Don't worry, time isn't standing still as it was with the PPC.
Thats not true. Core was a different architecture than Core 2. The next new architecture, Nehalem should be called Core 3 since it is distinctly different than the current Core 2.
Thats not true. Core was a different architecture than Core 2. The next new architecture, Nehalem should be called Core 3 since it is distinctly different than the current Core 2.
If you read the article I posted, you would see that Intel considered the tick not to be Core, but to be the processors before it, the last Pentium 4, Northwood. The tock was then the Core 2.
I just don't think that Intel has an interest in using "Core 3" as a product name. That's all. I'm not so sure why you think it's so important that they do.
The Nehalem is a bigger departure from, according to Intel, pretty much any other cpu design of theirs in recent years. I think they will want to differentiate it from what has gone before.
It's not that there won't be a Core 3, just that it's Unlikely that Intel will name their newer chips Core 3. One reason why they named them Core was because they had one core, then Core had up to 2 Cores. Recently that numvering scheme was broken with the 4 core chips. So, it wasn't gust the itewration of two new designs.
Penyrn will have some improvements over the present chips, in addition to being a die shrink. But, nothing like what we will see with Nehalen. That will be a break with Intel's past with the on-die controller. The other major impovements (such as built-in WiMax for the mobile chips) will make these chips seriously heavy performers indeed.
Don't worry, time isn't standing still as it was with the PPC.
Quote:
Originally Posted by MacSuperiority
Thats not true. Core was a different architecture than Core 2. The next new architecture, Nehalem should be called Core 3 since it is distinctly different than the current Core 2.
That's not true (MacSuperiority, this is my opinion, as your post *is* true but with an added bit of speculation).
There was a Core Solo (one core), a Core Duo (two cores), Core 2 Duo (two cores) and a Core 2 Quad (two cores). The Core 1 line was pretty much the Core marchatecture but w/o the L2 and VT tech. There wasn't much of a difference and Intel couldn't make a huge "Core X Duo" marketing push then change the name for the Core 2 chips because it was a different march. As Penryn is the natural progression of the line, the name Core 3 *should* make sense, then we can progress to Core 4 (yuk) or Intel SUPERPOWER X processor with the Nehalem march. With Intel saying that they want a die shrink and a marked improvement on the march (you just can't make a whole new microarchitecture in two years, they're not making a huge change on the one before it) they may/may not change the name.
For the purpose of full disclosure, I hate the Intel "Core" name. Maybe the Nehalem chips will be "Intel Nehalem 4 quad/octo" or some equally terrible name like that. Maybe I just like AMD too much.
That's not true (MacSuperiority, this is my opinion, as your post *is* true but with an added bit of speculation).
There was a Core Solo (one core), a Core Duo (two cores), Core 2 Duo (two cores) and a Core 2 Quad (two cores). The Core 1 line was pretty much the Core marchatecture but w/o the L2 and VT tech. There wasn't much of a difference and Intel couldn't make a huge "Core X Duo" marketing push then change the name for the Core 2 chips because it was a different march. As Penryn is the natural progression of the line, the name Core 3 *should* make sense, then we can progress to Core 4 (yuk) or Intel SUPERPOWER X processor with the Nehalem march. With Intel saying that they want a die shrink and a marked improvement on the march (you just can't make a whole new microarchitecture in two years, they're not making a huge change on the one before it) they may/may not change the name.
For the purpose of full disclosure, I hate the Intel "Core" name. Maybe the Nehalem chips will be "Intel Nehalem 4 quad/octo" or some equally terrible name like that. Maybe I just like AMD too much.
Yuk! I just noticed that I hadn't done spell checking.
There was a Core Solo (one core), a Core Duo (two cores), Core 2 Duo (two cores) and a Core 2 Quad (two cores). The Core 1 line was pretty much the Core marchatecture but w/o the L2 and VT tech. There wasn't much of a difference and Intel couldn't make a huge "Core X Duo" marketing push then change the name for the Core 2 chips because it was a different march. As Penryn is the natural progression of the line, the name Core 3 *should* make sense, then we can progress to Core 4 (yuk) or Intel SUPERPOWER X processor with the Nehalem march. With Intel saying that they want a die shrink and a marked improvement on the march (you just can't make a whole new microarchitecture in two years, they're not making a huge change on the one before it) they may/may not change the name.
Core 1 has VT -- the missing ingredient added in Core 2 was actually 64-bit support (EM64T/IA-32e/x86_64/whatever you want to call it). When I first installed Parallels Desktop on the Mac mini it required a firmware update to enable VT support, so I distinctly remember it's there
Core Duo= Yonah. Still based on the Pentium M architecture that spawned Dothan and Banias.
Core2 Duo- Based on the Merom core which means Conroe/Woodcrest
They are most definitely different cores. The FP units in Merom are more closely aligned with Netburst arch CPU. Intel basically took the best of Pentium M power management and took Netburst arch...bred them and voila. Merom.
Nehalem should be called a different core since it's quite a significant change as Melgross has stated.
They are most definitely different cores. The FP units in Merom are more closely aligned with Netburst arch CPU. Intel basically took the best of Pentium M power management and took Netburst arch...bred them and voila. Merom.
That's just Intel's marketing talk because they don't want to admit how much of a screw-up Netburst was. In reality, the Core 2 microarchitecture is almost entirely an evolutionary step from Pentium M.
That's just Intel's marketing talk because they don't want to admit how much of a screw-up Netburst was. In reality, the Core 2 microarchitecture is almost entirely an evolutionary step from Pentium M.
Netburst wasn't really a screwup though.
No one anticipated the leakage and other problems they would have. That affected everyone. Remember IBM's 3 GHz promise? That was due to that problem as well. We were supposed to see 4 GHz G5's, at least. IBM was talking about 5 and 6 GHz successors as well. What happened there?
AMD was lucky on two fronts. They had designs that were actually closer to the G5 in some ways, so had higher performance at lower clocks. And they were so far behind on process, that they were able to benieit from the solutions that both Intel and IBM came up with.
It hasn't helped them now though. As we can now see, their designs aren't that good. It's only the on-board memory controller that's keeping them in the race, and it was the only thing that kept them slightly ahead of Netburst back then.
It's not that there won't be a Core 3, just that it's Unlikely that Intel will name their newer chips Core 3. One reason why they named them Core was because they had one core, then Core had up to 2 Cores. Recently that numvering scheme was broken with the 4 core chips. So, it wasn't gust the itewration of two new designs.
Penyrn will have some improvements over the present chips, in addition to being a die shrink. But, nothing like what we will see with Nehalen. That will be a break with Intel's past with the on-die controller. The other major impovements (such as built-in WiMax for the mobile chips) will make these chips seriously heavy performers indeed.
Don't worry, time isn't standing still as it was with the PPC.
Core Solo - single core
Core Duo - two cores
Core Quad - four cores
Solo, Duo, Quad, Octo - to mention no of cores rite?
No one anticipated the leakage and other problems they would have. That affected everyone. Remember IBM's 3 GHz promise? That was due to that problem as well. We were supposed to see 4 GHz G5's, at least. IBM was talking about 5 and 6 GHz successors as well. What happened there?
AMD was lucky on two fronts. They had designs that were actually closer to the G5 in some ways, so had higher performance at lower clocks. And they were so far behind on process, that they were able to benieit from the solutions that both Intel and IBM came up with.
It hasn't helped them now though. As we can now see, their designs aren't that good. It's only the on-board memory controller that's keeping them in the race, and it was the only thing that kept them slightly ahead of Netburst back then.
The engineers at Intel knew there would be problems. Netburst was the bastard child of marketers who had no idea what went into chip design.
And for you to say that AMD's core design "isn't that good", you should stop acting like you know about core design, because that's entirely untrue.
The engineers at Intel knew there would be problems. Netburst was the bastard child of marketers who had no idea what went into chip design.
And for you to say that AMD's core design "isn't that good", you should stop acting like you know about core design, because that's entirely untrue.
Really? How very interesting.
So, Netburst was designed by marketing people? Perhaps you should read up on the technical history of the chip familly. At the time they were doing it, there were very few people who criticized what they were doing.
The reason why I said that AMD's design weren't very good, is because, even as Netburst failed to advance the last 18 months of its life because of the finally realised leakage problems, AMD's "superior designs, even with the on die memory controller, only managed to eck out about a 15%, on average, performance advantage.
As soon as Intel understood that Netburst was going nowhere, they changed. Even using old Pentium 3 designs, with improvements, they were able to move ahead of AMD. With Core 2, they moved well beyond AMD. As much as 40%
During the last 18 months, a long time in processor design, AMD has gone nowhere. The new socket, the updated K8, nothing has made a dent in Intel's leading position.
Barcelona is the first shot they have of catching up, and it will debut at only 2.3 GHz, because they can't get it any higher, on the same process shrink that Intel is delivering 3 GHz 4 core parts.
So, I'm not impressed with AMD's designs.
They only looked good because Intel had problems moving Netburst up in speed due to the unexpected leakage problems. Once Intel changed their direction, the poverty of AMD's design labs became apparent.
Comments
Great news! Better technology is coming in the future!
This kind of post always makes me laugh a bit. They could announce any upgraded processor is coming out in a year and everyone would post the exact same responses.
It's at the same time comforting that yes, the future holds smaller and faster computers and yes, apple insider posts will never change!
So, you're saying that they shouldn't report this, and we shouldn't be talking about it?
Ok, everyone, leave the thread and go do something useful. This is a waste of time!
And until last month, every reference to Penryn you could find online said that it was the refresh of Merom, the mobile processor -- not the overarching name for an entire family of refreshes. So yes, this is new, and a change (maybe this is what Intel had intended all along, but if so, all the websites with info on Penryn got it wrong).
Whatever they had said, Penryn is the name for the first line of 45 nm chips.
Exactly, that's what I'm saying -- previously, until Intel started releasing more details last month, Penryn was supposed to be a mobile chip to be released in 2007, alongside a desktop chip with another name; now it's a "family" whose mobile variant will be released in 2008. Furthermore, that mobile Penryn, its later quad-core brother, and Nehalem, a completely new architecture, are going to all be squeezed into that one year. It just seems strange to me, enough so that I'm starting to think that the Mobile version of Nehalem will have to wait for 2009. I would point out that the very fact that mobile Penryn is coming out in '08 is a blow to the whole 2-year "tick-tock" cycle Intel has been hyping. The last "tick" was in 2006, so the "tock" was expected in 2007, but no more.
Not exactly. Penyrn is the tick, and Nehalem is the tock. You're forgetting that all of these lines overlap. The tick is still ticking while the tock starts its tocking.
No; Core and Core 2 are the marketing names for two different architectures, whereas Penryn is a codename, like Yonah. Presumably Penryn will be marketed as Core 2 as well, since this is just a die shrink and not a new architecture. But no, as I indicated above, Penryn didn't always stand for the entire 45nm line, it had previously been just one of the chips in that line. Likewise, back when Core was the current model, we knew Intel had plans for a new microarch with three codenames, one for each chip in that line.
You're contradicting yourself. Core and Core 2 were different architectures (to a certain extent). Penyrn and Nehalen will also be different architectures as well. There are names given that are changed once the chips come out as well.
Everything I've read indicates mid-late 2008 for Nehalem. What I'm saying is that it seems strange that they would squeeze both the (mobile) die shrink, the quad core of that die shrink, and the brand new arch into the first let's say 9 months of 2008, yet release virtually no new mobile processors in 2007 besides a speed bump when Santa Rosa comes out (2.33GHz to 2.4.. big whoop). It's just a little disappointing and confusing is all.
I'm reading early-mid. We might see the mobile Penyrn in late 2007. That would be more than a speed bump.
I agree, but Apple apparently doesn't; they could have quad-core, 2.93GHz iMacs now if they wanted, but they prefer to stick with Merom for some reason. If it's just pin compatibility, then maybe they will upgrade when this new processor comes out. On the other hand, if they really are excessively concerned with fan noise and/or not letting their consumer desktop outperforming their pro laptop, then no.
They ARE exceffively concerned with fan noise. Actually, I would say obsessively instead. Consumers are used to hearing nothing from their Tv's audio systems, etc. Apple is trying to make their computers for the home meet that expectation.
[/quote]
This would be spot on based on what the hardware sites were reporting a few months ago, but they've now changed it and the Penryn name now covers the entire gamut of 45nm processors. Doesn't make any sense based on past precedents, but there you have it.
Are you sure Penryn will be Core 3, though? I would think they'd stick with the Core 2 brand since Penryn is just a shrunken Core 2.[/QUOTE]
I don't think we'll see "Core 3".
I think Core 3 sounds logical.
And until last month, every reference to Penryn you could find online said that it was the refresh of Merom, the mobile processor -- not the overarching name for an entire family of refreshes. So yes, this is new, and a change (maybe this is what Intel had intended all along, but if so, all the websites with info on Penryn got it wrong).
I don't know, on Intel's site the code name is used to describe the whole family. It's not really important, though.
I'm reading early-mid. We might see the mobile Penyrn in late 2007. That would be more than a speed bump.
I think you're right, Intel won't refresh the CPU and the platform simultaneously. Santa Rosa will debut with Merom in May, Penryn is slated to hit production later this year and will be paired with Santa Rosa.
Whatever they had said, Penryn is the name for the first line of 45 nm chips.
I know. I'm just pointing out that, and the release date, are a change from a few months ago.
Not exactly. Penyrn is the tick, and Nehalem is the tock. You're forgetting that all of these lines overlap. The tick is still ticking while the tock starts its tocking.
Uhh... I don't think it really matters whether we designate the die shrink the "tock" or the architecture change. Yonah was a die shrink, Merom/Conroe/Woodcrest was a new arch, Penryn will be a die shrink, Nehalem, a new arch.
You're contradicting yourself. Core and Core 2 were different architectures (to a certain extent). Penyrn and Nehalen will also be different architectures as well. There are names given that are changed once the chips come out as well.
I'm not contradicting myself at all. Penryn is not a new arch -- it's just a shrink of an existing one. Nehalem, on the other hand, is new.
Yonah = Core = a hybrid arch of Pentium-M and new features
Merom/Conroe/etc = Core 2 = "next generation" microarch
Penryn = a shrunken Core 2 with higher clockspeeds
Nehalem = a brand new architecture
I'm not saying Penryn is insignificant, it's just more evolution than revolution. It's just a die shrink, whereas Core->Core 2 was a new arch altogether, so I am supposing that "Core 3" will refer to a new arch, and thus Nehalem, as well. It seems pretty obvious to me.
I'm reading early-mid. We might see the mobile Penyrn in late 2007. That would be more than a speed bump.
I hope that's true (where are you "reading" this though? All the new info suggests otherwise), I just don't understand why rumor sites and hardware sites are reporting "early 2008" for mobile Penryn without mentioning that it's a push back from the original date. Imagine the screaming if Apple announced a product and then pushed it back.. oh, wait
I don't think we'll see "Core 3".
Why not?
If there won't be a Core 3, then what's the differentiation between the lower speed/performance Core 2 parts and the new Penryn line cores?
I think Core 3 sounds logical.
It's not that there won't be a Core 3, just that it's Unlikely that Intel will name their newer chips Core 3. One reason why they named them Core was because they had one core, then Core had up to 2 Cores. Recently that numvering scheme was broken with the 4 core chips. So, it wasn't gust the itewration of two new designs.
Penyrn will have some improvements over the present chips, in addition to being a die shrink. But, nothing like what we will see with Nehalen. That will be a break with Intel's past with the on-die controller. The other major impovements (such as built-in WiMax for the mobile chips) will make these chips seriously heavy performers indeed.
Don't worry, time isn't standing still as it was with the PPC.
I don't know, on Intel's site the code name is used to describe the whole family. It's not really important, though.
I think you're right, Intel won't refresh the CPU and the platform simultaneously. Santa Rosa will debut with Merom in May, Penryn is slated to hit production later this year and will be paired with Santa Rosa.
That's about right, except that we may see some of the Nehalem chips out before that.
I know. I'm just pointing out that, and the release date, are a change from a few months ago.
Uhh... I don't think it really matters whether we designate the die shrink the "tock" or the architecture change. Yonah was a die shrink, Merom/Conroe/Woodcrest was a new arch, Penryn will be a die shrink, Nehalem, a new arch.
It doesn't matter what we think. This is Intel's ball. They do the naming, not us. They say that the die shrink is the tick, and the architecture improvements are the tock. It makes perfect sense.
I'm not contradicting myself at all. Penryn is not a new arch -- it's just a shrink of an existing one. Nehalem, on the other hand, is new.
Yonah = Core = a hybrid arch of Pentium-M and new features
Merom/Conroe/etc = Core 2 = "next generation" microarch
Penryn = a shrunken Core 2 with higher clockspeeds
Nehalem = a brand new architecture
I'm not saying Penryn is insignificant, it's just more evolution than revolution. It's just a die shrink, whereas Core->Core 2 was a new arch altogether, so I am supposing that "Core 3" will refer to a new arch, and thus Nehalem, as well. It seems pretty obvious to me.
Peryrn also has changes, it's not just a die shrink. There are notable improvements over the current Core 2 designs.
This is a good article detailing most of what we can expect from both Penyrn and Nehalem.
http://www.extremetech.com/article2/...2108905,00.asp
I hope that's true (where are you "reading" this though? All the new info suggests otherwise), I just don't understand why rumor sites and hardware sites are reporting "early 2008" for mobile Penryn without mentioning that it's a push back from the original date. Imagine the screaming if Apple announced a product and then pushed it back.. oh, wait
Mobile Penyrn has apparently been pushed back because of design changes which were enumerated in the Article about them that I linked to yesterday.
I'll have to look some more for articles with more about the dates if you are really interested. I don't think that 6 months is all really that important though.
Why not?
I just don't think that Intel will continue with that naming convention.
It's not that there won't be a Core 3, just that it's Unlikely that Intel will name their newer chips Core 3. One reason why they named them Core was because they had one core, then Core had up to 2 Cores. Recently that numvering scheme was broken with the 4 core chips. So, it wasn't gust the itewration of two new designs.
Penyrn will have some improvements over the present chips, in addition to being a die shrink. But, nothing like what we will see with Nehalen. That will be a break with Intel's past with the on-die controller. The other major impovements (such as built-in WiMax for the mobile chips) will make these chips seriously heavy performers indeed.
Don't worry, time isn't standing still as it was with the PPC.
Thats not true. Core was a different architecture than Core 2. The next new architecture, Nehalem should be called Core 3 since it is distinctly different than the current Core 2.
Thats not true. Core was a different architecture than Core 2. The next new architecture, Nehalem should be called Core 3 since it is distinctly different than the current Core 2.
If you read the article I posted, you would see that Intel considered the tick not to be Core, but to be the processors before it, the last Pentium 4, Northwood. The tock was then the Core 2.
I just don't think that Intel has an interest in using "Core 3" as a product name. That's all. I'm not so sure why you think it's so important that they do.
The Nehalem is a bigger departure from, according to Intel, pretty much any other cpu design of theirs in recent years. I think they will want to differentiate it from what has gone before.
It's not that there won't be a Core 3, just that it's Unlikely that Intel will name their newer chips Core 3. One reason why they named them Core was because they had one core, then Core had up to 2 Cores. Recently that numvering scheme was broken with the 4 core chips. So, it wasn't gust the itewration of two new designs.
Penyrn will have some improvements over the present chips, in addition to being a die shrink. But, nothing like what we will see with Nehalen. That will be a break with Intel's past with the on-die controller. The other major impovements (such as built-in WiMax for the mobile chips) will make these chips seriously heavy performers indeed.
Don't worry, time isn't standing still as it was with the PPC.
Thats not true. Core was a different architecture than Core 2. The next new architecture, Nehalem should be called Core 3 since it is distinctly different than the current Core 2.
That's not true (MacSuperiority, this is my opinion, as your post *is* true but with an added bit of speculation).
There was a Core Solo (one core), a Core Duo (two cores), Core 2 Duo (two cores) and a Core 2 Quad (two cores). The Core 1 line was pretty much the Core marchatecture but w/o the L2 and VT tech. There wasn't much of a difference and Intel couldn't make a huge "Core X Duo" marketing push then change the name for the Core 2 chips because it was a different march. As Penryn is the natural progression of the line, the name Core 3 *should* make sense, then we can progress to Core 4 (yuk) or Intel SUPERPOWER X processor with the Nehalem march. With Intel saying that they want a die shrink and a marked improvement on the march (you just can't make a whole new microarchitecture in two years, they're not making a huge change on the one before it) they may/may not change the name.
For the purpose of full disclosure, I hate the Intel "Core" name. Maybe the Nehalem chips will be "Intel Nehalem 4 quad/octo" or some equally terrible name like that. Maybe I just like AMD too much.
That's not true (MacSuperiority, this is my opinion, as your post *is* true but with an added bit of speculation).
There was a Core Solo (one core), a Core Duo (two cores), Core 2 Duo (two cores) and a Core 2 Quad (two cores). The Core 1 line was pretty much the Core marchatecture but w/o the L2 and VT tech. There wasn't much of a difference and Intel couldn't make a huge "Core X Duo" marketing push then change the name for the Core 2 chips because it was a different march. As Penryn is the natural progression of the line, the name Core 3 *should* make sense, then we can progress to Core 4 (yuk) or Intel SUPERPOWER X processor with the Nehalem march. With Intel saying that they want a die shrink and a marked improvement on the march (you just can't make a whole new microarchitecture in two years, they're not making a huge change on the one before it) they may/may not change the name.
For the purpose of full disclosure, I hate the Intel "Core" name. Maybe the Nehalem chips will be "Intel Nehalem 4 quad/octo" or some equally terrible name like that. Maybe I just like AMD too much.
Yuk! I just noticed that I hadn't done spell checking.
There was a Core Solo (one core), a Core Duo (two cores), Core 2 Duo (two cores) and a Core 2 Quad (two cores). The Core 1 line was pretty much the Core marchatecture but w/o the L2 and VT tech. There wasn't much of a difference and Intel couldn't make a huge "Core X Duo" marketing push then change the name for the Core 2 chips because it was a different march. As Penryn is the natural progression of the line, the name Core 3 *should* make sense, then we can progress to Core 4 (yuk) or Intel SUPERPOWER X processor with the Nehalem march. With Intel saying that they want a die shrink and a marked improvement on the march (you just can't make a whole new microarchitecture in two years, they're not making a huge change on the one before it) they may/may not change the name.
Core 1 has VT -- the missing ingredient added in Core 2 was actually 64-bit support (EM64T/IA-32e/x86_64/whatever you want to call it). When I first installed Parallels Desktop on the Mac mini it required a firmware update to enable VT support, so I distinctly remember it's there
Core2 Duo- Based on the Merom core which means Conroe/Woodcrest
They are most definitely different cores. The FP units in Merom are more closely aligned with Netburst arch CPU. Intel basically took the best of Pentium M power management and took Netburst arch...bred them and voila. Merom.
Nehalem should be called a different core since it's quite a significant change as Melgross has stated.
They are most definitely different cores. The FP units in Merom are more closely aligned with Netburst arch CPU. Intel basically took the best of Pentium M power management and took Netburst arch...bred them and voila. Merom.
That's just Intel's marketing talk because they don't want to admit how much of a screw-up Netburst was. In reality, the Core 2 microarchitecture is almost entirely an evolutionary step from Pentium M.
That's just Intel's marketing talk because they don't want to admit how much of a screw-up Netburst was. In reality, the Core 2 microarchitecture is almost entirely an evolutionary step from Pentium M.
Netburst wasn't really a screwup though.
No one anticipated the leakage and other problems they would have. That affected everyone. Remember IBM's 3 GHz promise? That was due to that problem as well. We were supposed to see 4 GHz G5's, at least. IBM was talking about 5 and 6 GHz successors as well. What happened there?
AMD was lucky on two fronts. They had designs that were actually closer to the G5 in some ways, so had higher performance at lower clocks. And they were so far behind on process, that they were able to benieit from the solutions that both Intel and IBM came up with.
It hasn't helped them now though. As we can now see, their designs aren't that good. It's only the on-board memory controller that's keeping them in the race, and it was the only thing that kept them slightly ahead of Netburst back then.
It's not that there won't be a Core 3, just that it's Unlikely that Intel will name their newer chips Core 3. One reason why they named them Core was because they had one core, then Core had up to 2 Cores. Recently that numvering scheme was broken with the 4 core chips. So, it wasn't gust the itewration of two new designs.
Penyrn will have some improvements over the present chips, in addition to being a die shrink. But, nothing like what we will see with Nehalen. That will be a break with Intel's past with the on-die controller. The other major impovements (such as built-in WiMax for the mobile chips) will make these chips seriously heavy performers indeed.
Don't worry, time isn't standing still as it was with the PPC.
Core Solo - single core
Core Duo - two cores
Core Quad - four cores
Solo, Duo, Quad, Octo - to mention no of cores rite?
Core, Core 2, Core 3 - to mention architecture changes rite?
After reading all the posts, i am confused now
Core Solo - single core
Core Duo - two cores
Core Quad - four cores
Solo, Duo, Quad, Octo - to mention no of cores rite?
Core, Core 2, Core 3 - to mention architecture changes rite?
After reading all the posts, i am confused now
The original number of cores for those lines was only one reason Intel used those naming conventions, and not the most important one at all.
About the confusion: Don't worry, we are all confused, as always.
Netburst wasn't really a screwup though.
No one anticipated the leakage and other problems they would have. That affected everyone. Remember IBM's 3 GHz promise? That was due to that problem as well. We were supposed to see 4 GHz G5's, at least. IBM was talking about 5 and 6 GHz successors as well. What happened there?
AMD was lucky on two fronts. They had designs that were actually closer to the G5 in some ways, so had higher performance at lower clocks. And they were so far behind on process, that they were able to benieit from the solutions that both Intel and IBM came up with.
It hasn't helped them now though. As we can now see, their designs aren't that good. It's only the on-board memory controller that's keeping them in the race, and it was the only thing that kept them slightly ahead of Netburst back then.
The engineers at Intel knew there would be problems. Netburst was the bastard child of marketers who had no idea what went into chip design.
And for you to say that AMD's core design "isn't that good", you should stop acting like you know about core design, because that's entirely untrue.
The engineers at Intel knew there would be problems. Netburst was the bastard child of marketers who had no idea what went into chip design.
And for you to say that AMD's core design "isn't that good", you should stop acting like you know about core design, because that's entirely untrue.
Really? How very interesting.
So, Netburst was designed by marketing people? Perhaps you should read up on the technical history of the chip familly. At the time they were doing it, there were very few people who criticized what they were doing.
The reason why I said that AMD's design weren't very good, is because, even as Netburst failed to advance the last 18 months of its life because of the finally realised leakage problems, AMD's "superior designs, even with the on die memory controller, only managed to eck out about a 15%, on average, performance advantage.
As soon as Intel understood that Netburst was going nowhere, they changed. Even using old Pentium 3 designs, with improvements, they were able to move ahead of AMD. With Core 2, they moved well beyond AMD. As much as 40%
During the last 18 months, a long time in processor design, AMD has gone nowhere. The new socket, the updated K8, nothing has made a dent in Intel's leading position.
Barcelona is the first shot they have of catching up, and it will debut at only 2.3 GHz, because they can't get it any higher, on the same process shrink that Intel is delivering 3 GHz 4 core parts.
So, I'm not impressed with AMD's designs.
They only looked good because Intel had problems moving Netburst up in speed due to the unexpected leakage problems. Once Intel changed their direction, the poverty of AMD's design labs became apparent.