Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
Unless you desperately need one (read: don't have an iPod), I would wait until a 32GB model comes out. With the prices that USB flash drives are at, I'm really surprised that the iPhone and iPod Touch don't have more memory already. Don't they all use the same type of memory?

I would guess that the issue with storage is due to the number of chips. There propably isn't enough room for more flash-chips. So even if prices come down, we might not see an increase in capacity until flash-chips with higher capacities become available.

I will also tell you that cnet said the Touch's display is nowhere near the uber-high quality that the iPhone's is. Might be better to wait for the 2.0 version. First-gen products usually have plenty of bugs to work out. It took Apple until either the 4th or 5th generation to put the click-wheel on iPods.

Wasn't that with the very first units that shipped? They had issues with displaying blacks. I can say that my week 40 touch has perfect screen
 
Actually, HyperThreading was always a win on a single CPU (that is, a single core system). It would sometimes be quite a bit faster, more often a little bit faster, but never slower.

There have been some unfortunate cases where a CPU with HyperThreading did more work, but achieved less. A simplified view is that a single core CPU with hyperthreading can work either as _one_ CPU running at 100% speed, or as _two_ CPUs running each at 60% speed. If you run Handbrake, for example, two CPUs at 60% speed are 20 percent faster in total.

But things went wrong for some applications that had one task that should have used 90 percent of available CPU, and another task that should have used 10 percent of the available CPU. It could happen that each task got one complete CPU for itself, so the first task got one CPU at 60% speed, and the second task got that as well.

And on a multi-core system obviously the OS must know about this, otherwise if you have two threads and run them on the same core instead of separate cores, you lose lots of performance (instead of two threads running at 100 percent, you could have two threads running at 60% speed, and two threads doing nothing if the OS is stupid).
 
Hey gnasher & numbsafari! Better let Jackal-Head here know that he doesn't know what he's talking about!

Jackal-Head wrote: "How effective hyper-threading is depends on [lots of things]". He is absolutely right. I talked about something entirely different: Hyperthreading is not very difficult to implement, out-of-order execution is difficult to implement.

What is quite interesting is that, as Jackal-Head said, hyperthreading is quite effective to fix a messed-up architecture like Netburst (Pentium IV), not very effective for a well-designed architectures like AMDs over the last year and Core / Core 2, and _very_ effective if you leave out out-of-order execution on purpose and use hyperthreading to get the same performance gain at lower cost.
 
But things went wrong for some applications that had one task that should have used 90 percent of available CPU, and another task that should have used 10 percent of the available CPU.

It could happen that each task got one complete CPU for itself, so the first task got one CPU at 60% speed, and the second task got that as well.

You are right, I'm wrong in that there would be cases where code written explicitly for a single CPU would do worse with dual HT CPUs than with two full CPUs.

I think that most software engineers would agree, however, that depending solely on thread priority to schedule the CPU(s) is an inherently broken design, and inherently single processor.

Even with two cores, using priority as the "tool" could lead to problems. Since the "low priority" thread could get 100% CPU, it could cause I/O or other bandwidth issues (net/memory) that could affect the primary thread.
 
nevermind, I've sort of answered by own post in a newer post..



Unless I'm mistaken, I think this article is somewhat misleading... And many people here are perpetuating this idea of a Silverthorne in an iPhone.
Unless I've missed a huge technological breakthrough, even using 45nm and dropping OOO execution is not going to get an x86 CPU like this anywhere close to the power consumption of the Samsung ARM in the iPhone.
Don't the modern ARM chips have much smaller power consumption at Idle vs Silverthorne? Is it possible for the Silverthorne CPU to all but shut down while the phone idles away waiting for a phone call??

Could someone with much more knowledge than I comment on the power consumption at load/idle of the Iphone ARM vs the 45nm Silverthorne???
 
The ARM uses a lot less power because it's a lot simpler. The x86 will always be an energy hog no matter how many billions of dollars Intel spends. Note too that MIPS (despite its demise in the mainline-CPU space) is still very popular in embedded applications, precisely because it's low power and has good performance.
 
Silverthorne VS ARM, what I have found...

Unless I'm mistaken, I think this article is somewhat misleading... And many people here are perpetuating this idea of a Silverthorne in an iPhone.
Unless I've missed a huge technological breakthrough, even using 45nm and dropping OOO execution is not going to get an x86 CPU like this anywhere close to the power consumption of the Samsung ARM in the iPhone.
Don't the modern ARM chips have much smaller power consumption at Idle vs Silverthorne? Is it possible for the Silverthorne CPU to all but shut down while the phone idles away waiting for a phone call??

Could someone with much more knowledge than I comment on the power consumption at load/idle of the Iphone ARM vs the 45nm Silverthorne??

Ok, yes, I am responding to my own post. lol. But I have taken some time to research this myself on Google to find out more details on Silverthorne vs ARM.
Based on a number of different articles and Intel presentation slides, it looks like the Silverthorne will have a PEAK TDP of between 0.6W -> "sub-2W" depending on model, which are supposed to range between 1Ghz and 2Ghz. The power consumption at Idle is said to be between 0.01W -> 0.1W depending on model, with these figures EXCLUDING chipset. Also Silverthorne is said to have a new low-power state, called C6.

From Arstechnica, "In order to alleviate some of the power difference between its chips and ARM's, Intel has equipped Silverthorne with a new low-power state, called C6. When Silverthorne is in C6, the only components that it leaves turned on are the SRAM that saves the existing processor state and some circuitry that can wake up the processor again when it's needed. (Getting out of C6 takes about 100 microseconds.) Intel claims that their testing indicates that Silverthorne can spend as much as 90 percent of its time in C6; if that's true, then that will bring the chip's average power dissipation far below its stated TDP. So Intel is counting on a combination of sleep-enabled lower average power and support for the full, awesome expanse of the extended x86 instruction set architecture to make Silverthorne a compelling basis on which to build a generation of mobile internet devices."

For the first generation, Silverthorne will initially be combined with the "Menlow" platform which has a seperate chipset and other components. Second generation Silverthorne chips will be integrated with the "Morrestown" platform which is a System-on-a-chip (SoC) design. This means that all the components needed to run the platform will be integrated onto one chip, including the processor, chipset/memory controller, Wifi/Ethernet, USB, etc. Possibly even graphics acceleration and video decoding DSPs will be embedded as well.This should allow the platform to further reduce power consumption.

Silverthorne specs:
- performance equivalent to first generation Pentium M (Banias)
- 45nm
- 47M transistors
- 25mm^2
- 533MT/s FSB
- In-order execution with hyperthreading

Competition
Silverthorne is going to have some very strong competition from the ARM SoC world. The most likely direct competitor looks to be the next gen ARM Cortext series, specifically the Cortext-A9 (out-of-order core) which is based on a 65nm process and will run in a 0.25W TDP. I was unable to find info on the Idle state power consumption of this chip, but it is assumed to be as low as or lower than Silverthorne based upon earlier generation ARM SoCs.

This is a different ARM core than what is currently on the iPhone (iPhone has an ARM11) and one which will be more powerful, reaching speeds of 1Ghz or more. ARM even claims the Cortext-A9 will have the same power consumption as the iPhone "ARM11" chip, but increase performance by a factor of FOUR. Also, there are both single-core and multi-core versions of the Cortext A9.

Based on all that information and what the analysts say, it looks like the 1st generation Silverthorne (Menlow platform) may be relegated to UMPC and Intel's new "Mobile Internet Device" (MID) type devices and not quite ready for the smartphone sphere. But this will probably change with the SoC "Morrestown" platform which will reduce power consumption by integrating all the components into one chip.
Here is how Jon Stokes of ArsTechnica ends his article from today (Tues. 5th)
http://arstechnica.com/news.ars/pos...side-intels-silverthorne-ultramobile-cpu.html)

" Having tried a few of Intel's Silverthorne-based prototypes, I must say that I wasn't particularly impressed. I own a Nokia N800 and an iPhone, both of which are ARM-based and both of which give a nearly complete Internet experience in a smaller form factor than Silverthorne will ever fit into. Indeed, at one point during a sit-down with Intel the rep told me that the warm, bulky prototype I was holding would give me the "full Internet in your pocket." I started chuckling, pulled out my iPhone, and said, "I already have that." He gamely responded that the iPhone's browser doesn't support Flash (in my opinion that's a feature, not a bug), but my point was made.

So Silverthorne is really a transitional product; it's Intel's first, slightly awkward foray into a market that it intends to eventually dominate by doing what it always does, and that's produce ever smaller, cheaper, and faster chips that support the world's most popular ISA. This recipe may ultimately work for Intel in the embedded market the way that it has worked elsewhere, but that day won't come just yet.

... So Silverthorne is just the start of something, and to ARM, MIPS, and the other established chipmakers who currently own the embedded space, it's Intel's way of saying "game on."



For more info on Silverthorne, see:
http://arstechnica.com/news.ars/pos...side-intels-silverthorne-ultramobile-cpu.html
http://en.wikipedia.org/wiki/Silverthorne_(CPU)
http://blogs.zdnet.com/Ou/?p=987
http://www.news.com/8301-10784_3-9859616-7.html


For more info on the ARM Cortext-A9, see:
http://en.wikipedia.org/wiki/ARM_architecture
http://newlc.com/arm-unveils-cortex-a9-processors-scalable-performance-and-low-power-designs
http://www.arm.com/products/CPUs/ARMCortex-A9_MPCore.html
http://www.linuxdevices.com/news/NS2917028234.html
 
Atomic Iphone on the way?

http://www.news.com/Intel-picks-Atom-as-name-for-new-chip-family/2100-1006_3-6232776.html


Intel has picked "Atom" as the new brand name for its latest microprocessor, the world's largest semiconductor company said.

The Intel Atom processor is the name for the new family of low-power processors, the brains of digital devices, that will power mobile Internet devices and ultra low-cost and small notebook and desktop personal computers.

Intel sees a big market for the Internet-connected devices that can fit in one's pocket and for what it is calling the netbook, a low-cost PC costing around $250.

The Intel Atom processor is based on a new microarchitecture designed for small devices and low power consumption, Intel said. The chip is less than 25 square millimeters, and 11 of the chip's dies--the slivers of silicon with 47 million transistors each--would fit in an area the size of a U.S. penny.

The new chips, previously code-named Silverthorne and Diamondville, are made on Intel's 45-nanometer chipmaking technology and slated for introduction toward the middle of this year.

"Diamondville and Silverthorne both represent an attempt by Intel to sell chips profitably for a whole lot less," said Nathan Brookwood, an analyst at market research firm Insight 64. "This is the first new processor design coming out of Intel since the Pentium Pro in 1995."
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.