Intel's Core i7 870 & i5 750, Lynnfield: Harder, Better, Faster Stronger
by Anand Lal Shimpi on September 8, 2009 12:00 AM EST- Posted in
- CPUs
Homework: How Turbo Mode Works
AMD and Intel both figured out the practical maximum power consumption of a desktop CPU. Intel actually discovered it first, through trial and error, in the Prescott days. At the high end that's around 130W, for the upper mainstream market that's 95W. That's why all high end CPUs ship with 120 - 140W TDPs.
Regardless of whether you have one, two, four, six or eight cores - the entire chip has to fit within that power envelope. A single core 95W chip gets to have a one core eating up all of that power budget. This is where we get very high clock speed single core CPUs from. A 95W dual core processor means that individually the cores have to use less than the single 95W processor, so tradeoffs are made: each core runs at a lower clock speed. A 95W quad core processor requires that each core uses less power than both a single or dual core 95W processor, resulting in more tradeoffs. Each core runs at a lower clock speed than the 95W dual core processor.
The diagram below helps illustrate this:
| Single Core | Dual Core | Quad Core | Hex Core | |
| TDP |  |  |  |  |
| Tradeoff |  |  |  |  |
The TDP is constant, you can't ramp power indefinitely - you eventually run into cooling and thermal density issues. The variables are core count and clock speed (at least today), if you increase one, you have to decrease the other.
Here's the problem: what happens if you're not using all four cores of the 95W quad core processor? You're only consuming a fraction of the 95W TDP because parts of the chip are idle, but your chip ends up being slower than a 95W dual core processor since its clocked lower. The consumer has to thus choose if they should buy a faster dual core or a slower quad core processor.
A smart processor would realize that its cores aren't frequency limited, just TDP limited. Furthermore, if half the chip is idle then the active cores could theoretically run faster.
That smart processor is Lynnfield.
Intel made a very important announcement when Nehalem launched last year. Everyone focused on cache sizes, performance or memory latency, but the most important part of Nehalem was far more subtle: the Power Gate Transistor.
Transistors are supposed to act as light switches - allowing current to flow when they're on, and stopping the flow when they're off. One side effect of constantly reducing transistor feature size and increasing performance is that current continues to flow even when the transistor is switched off. It's called leakage current, and when you've got a few hundred million transistors that are supposed to be off but are still using current, power efficiency suffers. You can reduce leakage current, but you also impact performance when doing so; the processes with the lowest leakage, can't scale as high in clock speed.
Using some clever materials engineering Intel developed a very low resistance, low leakage, transistor that can effectively drop any circuits behind it to near-zero power consumption; a true off switch. This is the Power Gate Transistor.
On a quad-core Phenom II, if two cores are idle, blocks of transistors are placed in the off-state but they still consume power thanks to leakage current. On any Nehalem processor, if two cores are idle, the Power Gate transistors that feed the cores their supply current are turned off and thus the two cores are almost completely turned off - with extremely low leakage current. This is why nothing can touch Nehalem's idle power:
Since Nehalem can effectively turn off idle cores, it can free up some of that precious TDP we were talking about above. The next step then makes perfect sense. After turning off idle cores, let's boost the speed of active cores until we hit our TDP limit.
On every single Nehalem (Lynnfield included) lies around 1 million transistors (about the complexity of a 486) whose sole task is managing power. It turns cores off, underclocks them and is generally charged with the task of making sure that power usage is kept to a minimum. Lynnfield's PCU (Power Control Unit) is largely the same as what was in Bloomfield. The architecture remains the same, although it has a higher sampling rate for monitoring the state of all of the cores and demands on them.
The PCU is responsible for turbo mode.
Facebook
Twitter
RSS
343 Comments
View All Comments
maddoctor - Tuesday, September 8, 2009 - link
Yeah, I'm agree. I think AMD will be no more as a company next year. I hope it will be happen. I think it is better you throw your AMD rubbish products into the trash. Because, I don't see any valuable of it.Eeqmcsq - Tuesday, September 8, 2009 - link
Well, I hope that it does NOT happen, because we NEED competition to keep Intel honest. Secondly, I would not go as far as calling AMD stuff rubbish. They're good if they fit one's needs at the right price, but they are definitely getting pushed further down the totem pole.JonnyDough - Tuesday, September 8, 2009 - link
KEEP them honest? Where have you been?bupkus - Tuesday, September 8, 2009 - link
A Core i5 750 with HT would not only defeat the purpose of most of the i7s, but it would also widen the performance gap with AMD. Intel doesn't need to maintain a huge performance advantage, just one that's good enough.maddoctor - Tuesday, September 8, 2009 - link
I don't believe Intel will increasing its products because AMD does not have any competitive products.klatscho - Tuesday, September 8, 2009 - link
actually, they do - if you would care to have a look at price/performance, especially considering that amd has already quietly thinned out its portfolio to make room for price improvements in order to stay in the game.maddoctor - Tuesday, September 8, 2009 - link
Intel doesn't need to be honest. I hope Intel will lifts AMD licensee as AMD has been breached the Intel - AMD CLA. I believe Intel will always be innovating and makes more cheaper and performance wise products. AMD will be no more and you will not need to miss it, AMD had been doing its duty to made Intel more stronger and competitive.PrinceGaz - Tuesday, September 8, 2009 - link
You are a fool if you think AMD is no longer needed. The only reason these Lynnfield chips start at just $196 is because AMD is still here and were selling competitive chips at around that price point. No AMD means newer better chips are introduced at high price points and stay there for a long time, just look at Bloomfield's prices to see what happens when AMD offers no competition. The $284 i7 920 is for a slightly higher performing chip than any Phenom and is priced accordingly, but you have to pay $562 and then $999 for performance where there is truly no competition.No AMD would mean these Lynnfields starting at $284 if you're lucky (that's for something like the i5 750) with the HT enabled ones at the $562 price point, and the only chips you'd find for under $200 would be old Core 2 Duos and Quads. Thankfully AMD are here which is why new chips are introduced at competitive prices. No competition (from AMD) means no competitive prices, so if AMD go bust today, the next generation of Intel chips will start expensive, and stay expensive until they are replaced with the model after it, which won't be for a long time when nobody else can offer anything like their current product. I guess you don't remember the days of the original Pentium in the mid 90's.
ClagMaster - Tuesday, September 8, 2009 - link
I agree. We need AMD and it's foolish to assert otherwise.AMD has been very good to us over the last 10 years. If it was not for AMD, Intel would have a monopoly and we would have not have Lynnfield or Bloomfield today. Intel created Lynnfield because they wanted to be more competitive with AMD in the mainstream market. Bloomfield/X58 was simply too expensive for mainstream and AMD's Phenon II was a better value.
I am discouraged that people have so easily forgotten AMD's past leadership such as the efficient instruction schedulers, first on-chip memory controller,the first single-die dual and quad core chips to market, the first consumer 64-bit processors, the x86-64 architecture extension that Intel followed, and the K8 architecture that kicked Intel Netburst architecture's butt black and blue.
That's why Intel was motivated to drop Netburst and introduce the Core 2 Duo/P965 in 1996. Then adopt the aggressive tick-tock strategy ever since that has given us the 45nm Lynnfield today. Lynnfield has these AMD inspired innovations, and Intel has built upon these innovations with the on-die PCIe controller.
I have a lot of respect for AMD. Don't ever accuse AMD of not being innovative. AMD does not suffer from lack of technological innovation. They have demonstrated plenty of innovation. AMD suffers from lack of capital investment that allows acceleration of technological development and manufacturing infrastructure.
strikeback03 - Wednesday, September 9, 2009 - link
You can't really say Lynnfield is a response to PhenomII when it was on the Intel roadmap before they knew how PhenomII would perform or be priced. It is simply the next progression in their architecture. So you might be able to argue that Intel wouldn't have rolled out the Nehalem architecture as quickly without AMD, but you can't really say any one family is a response to another in that short a timescale.