http://www.intel.com/cd/ids/developer/asmo-na/eng/dc/threading/294188.htm?page=2 said:Why Multi?
Why is multi-core and multithread so important? An Intel Fellow, now retired, named Fred Pollack postulated that a single-threaded processor will provide a diminishing return in performance versus power. That is, performance will scale more slowly than power for a single-thread processor. Multiple-thread processors can scale performance much better. The demand for increased performance does not diminish, so it’s important to find more efficient ways to deliver that performance.
Multi at the Logic Level
An example of power and performance scaling at the logic level is shown here. Consider a logic block, which can be any function – an ALU for example. Assume that this logic block has an operating Voltage of 1 unit, a Frequency of 1, Throughput of 1, Active Power of 1 and Leakage Power of 1. If the Voltage is reduced to .7, then the Frequency must also reduce to .7. That causes a reduction in Throughput to .7. However, the Active and Leakage Power both reduce to .35. If the Logic block is then replicated, so that two blocks operate in parallel, then the total power for the two blocks is .7, but the Throughput is 1.4. This logic-level example illustrates how parallel processing can increase performance while reducing power consumption.
this mainly deals with the second paragraph and the second graphic, but the first paragraph and graphic were included to set up some background info.
--------------
ok - somethings i see wrong here:
-if we have one voltage unit, and have a freqency of one unit, as well as a power leakage of one unit... how the hell do you have one unit of throughput? ( throughput = work )
one volt enters the chip
chip works at one frequency, using one volt to do the one unit of work.
yet the chip loses one volt to leakage. how can this be?
-if we reduce the voltage level to .7 of an unit of voltage, you will still have one frequency. the frequency is how fast a certain amount of work is performed. so the frequency will still be 1. so for one freqency, the chip gets .7v to work with, and produces .7 work. no - it will still produce 1 work unit. because whats the point of having something doing only 70% of the work? doesnt quite make sense intel. and if reducing the voltage by 30% lets the voltage leakage cut the input voltage in half for its value, why did it not happen when the input voltage was 1v? if at 70% of the original voltage produces a 50% leakage, then either they are bullshitting, and they have snorted too much silicone, or they are letting marketing people run their manufacturing people, and probably are still snorting too much silicone.
-so, when we increase the number of chips to 2, intel still says they use the same number of volts. ( that doesnt make sense... wouldnt the voltage level double? im not an electrical engineer, so someone correct me in this sense, if needed ) .. even so - the leakage would still be equal to the amount of voltage inputed to the circuits, based on the evidence they provide at 1v to 1 circuit/chip.
--------------
i dont know who they are trying to fool - not me, because i know that intel makes much heat ( a direct relation to the amount of power their processors and other chips consume ) so they need to figure out the truth - and to also just abandon "moore's law" - they use it basically as their business model and one day its going fail them.
-------
sorry, i was just browsing around, looking at what intel was up to in their research labs. and i read a few pages ( the link is page number 2, if it isnt obvious
), and just got fed up with the marketing bullshit in research... 
