OSNews

My only comment on the dynamic core-to-core power shifting is how they worked around the issue of power density. It's been shown that the IHS doesn't really spread the heat effectively at all, it primarily distributes the pressure of the heatsink. Doubling the power dissipation on one side of the die would double the maximum power density and impact the leakage current. I bet that these processors will have lower performance per watt than its competition when running single-threaded workloads.

I question the theory behind flash caches. The storage hierarchy works because the various levels are each over an order of magnitude faster/slower than their neighbors in the worst case. Flash is an odd medium for caching hard disks because while it's about an order of magnitude faster than the disk for random access, it's comparable or even slower than today's commodity SATA drives in sequential access. Managing a flash cache is tricky because you not only need to worry about evicting least-recently-used filesystem pages, but you also want to bypass the cache during sequential I/O and evict pages that are usually accessed sequentially. I wonder if they even bother implementing these considerations.

Now that the world is being thrust toward Vista, all three major platforms effectively use main memory as a disk cache, and DRAM wipes the floor with any mass storage medium, including an enterprise-class SAN. It's about 20x as expensive as flash, but typical working sets for desktop applications are likely to fit in the memory left over for the disk cache. There's no substitute for plenty of DRAM. At least not until MRAM or PRAM hits the market. Flash is a great removable storage medium, but it's being shoe-horned into a new role as a cache, and it just isn't a good fit. Wear-leveling will make it feasible, but nothing will make it a strong performer.

As for the tablet device, this doesn't surprise me at all. These days, you should expect almost any new computing device (not marketed by Apple or Microsoft) to support Linux. How do you think they test the hardware during development? Linux is the bring-up platform of choice for device manufacturers. All of IBM's new hardware is debugged on Linux before AIX, i5/OS, z/OS, or Windows enters the picture. It's easier, more flexible, and cost-effective. It just makes more sense. As the "PC" evolves to take on new shapes and sizes, free software platforms will have a pragmatic advantage.

One advantage of a flash cache is that it eliminates the need for the drive to spin up every 10 minutes (by default) in laptop mode, while eliminating the danger of losing data while in laptop mode, in the event of an unexpected power off.

That's more important to me on a mobile device than the speed issues.

That's a good reason. I've also been planning a nifty AppleTV mod that involves replacing the HDD with a CF card and using it as an LTSP client with cachefs on the CF to speed access its NFS volumes on the terminal server. But this is caching a network resource, where flash should be a strong performer.

Flash caches are also popular amongst the SPCR crowd, since the sound of a hard drive spinning up is enough to make them cry. They like to hear the sound of their own digestive system over their computer.

"""
Flash caches are also popular amongst the SPCR crowd, since the sound of a hard drive spinning up is enough to make them cry. They like to hear the sound of their own digestive system over their computer.
"""

True. But I've always figured that most of them need a life more than they a flash cache. ;-)

Computers making "computer sounds" is a time honored tradition dating back to the original Star Trek series, and Forbidden Planet before that.

"Managing a flash cache is tricky because you not only need to worry about evicting least-recently-used filesystem pages, but you also want to bypass the cache during sequential I/O and evict pages that are usually accessed sequentially. I wonder if they even bother implementing these considerations. "

Of course they bypass the cache for sequential I/O. Perhaps not in the spun-down case, but how likely is it that you're going to be doing significant multi-block sequential I/O while expecting your disk to remain spun down?

The Robson/ReadyDrive Flash Cache is supposed to have two components: a write cache to keep the drive spun down (something's always writing to the drive in Windows... probaby logs no one ever looks at or NTFS MetaData... who knows?). There's also a read-cache that stores what would normally go into the paging file and some pages of executable code. This is the kind of data that is NOT generally accessed in long sequential reads, but instead more or less random small reads.

Sure, the memory page caching algorithms in widespread use can do a good job of keeping relevant pages around for program code, but this only works based on short term behavior of programs. The whole point of Windows SuperFetch, which is the underlying cache policy engine for these systems, is to find long term trends in page usage and to prewarm the cache with pages that the shorter-term algorithms have no way of knowing about. Given this level of long-term paging, the flash cache makes sense as a location that doesn't cost as much as main memory to store random-access code pages. Is Flash ideal to replace memory or HDDs? No! Ready* is just a matter of using a technology that's widely extant for a task it's well-suited to.

Windows NT has of course had disk caching since the original 3.1 version of NT. The memory manager and filesystem drivers both interact with the Cache Manager (Cc* subsystem) and have done so for ages. It's all pretty heavily tied in with the VM system, so there's pretty much a unified cache for both memory pages and disk file pages. Files are mapped in 256 KB FIFO views, but when a page falls out of a view, it isn't evicted from memory immediately... instead it's put on a standby list whence it can be retrieved quickly through a "soft" page-fault.

I think you should reconsider your notions that Windows is not as advanced as Linux on the Kernel level. It doesn't seem to move as quickly as Linux does in terms of new user-visible features, but that's largely because the kernel is hidden away and you don't have this nice /proc filesystem to see detailed data in. Instead, you have to go look through not-so-well-documented performance counters. You also can't see the source code and you don't pick and choose which features you want while compiling it. It is also the case that Linux does move faster into more niches than NT does because anyone can take it and adapt it to their needs. Microsoft only spends efforts on optimizing NT in areas and for machines where it makes business sense for them to do so.

Nokia?

"you know who."
Intel?

Nokia have also had a multipurpose tablet running Linux, and it has also largely been a commercial failure.

Till you show some documentation proving it ain't nothing but FUD.

Till you show some documentation proving it ain't nothing but FUD.

Do look up the definition of FUD.

http://www.businessweek.com/technology/content/feb2006/tc20060207_7...

"Sales of the 770 are still neglible for Nokia, which booked 2005 revenues of $41 billion. It won't say how many 770s have shipped, but analysts figure the number is fewer than 25,000 units."

When a company doesn't tell you how many have been sold, you know the news is bad. The 770 is nothing more than a somewhat unstable test-bed for some open source software with Linux shoe-horned on to a tablet device:

http://www.osnews.com/story.php/15079/Review-Nokia-770-Internet-Tab...

Thx for linkg a 2 years old news, do you have an updated one? I mean, one if at least less than 1 year old?, do you base your FUD in such old article?, so pathetic.

Thx for linkg a 2 years old news, do you have an updated one? I mean, one if at least less than 1 year old?, do you base your FUD in such old article?, so pathetic.

Intelligent comeback there. I'm suitably impressed.

This is an article written a year ago, not two years ago, and I can find no article anywhere that suggests the situation has changed. If you have some spectacular sales figures somewhere for Nokia's tablets, I'm all ears. However, you won't find them.

The second link was a legitimate review detailing just how poor the device actually is.

Edited 2007-04-17 00:23

Nokia have also had a multipurpose tablet running Linux, and it has also largely been a commercial failure.

Except Nokia tablets are in fact commercially successful, that's why Intel is developing it's own mini-tablet, and HTC is going to enter this market too with Athena tablet communicator.

Except Nokia tablets are in fact commercially successful

No they're not, and there are no sales figures to support that in any way, shape or form.

I also don't know why you say that Nokia Tablets are selling well (plural), because Nokia don't have many tablets to sell at all. What they do sell are the Nokia 770, and the N800, which is just an evolution of the same thing. They're just unstable beta test pieces of kit for Linux, with some open source software on them, for the open source Linux enthusiast crowd to lap up. That's not commercially successful.

Actually, you haven't given any figures to show they are not commercially successfule, just as the previous poster had not demonstrated that they were.

I have. The last estimate was around 25,000 units sold (see the link), and there has been no word on it since. If you have some spectacular sales figures for Nokia's tablets, again, I'm all ears. You ain't going to find any though.

Nokia have not pushed the device particularly hard commercially; they seem to have been pretty clear from the outset that the strategic aim is to create a viable Linux mobile platform. In that sense the project seems to have been fairly successful. There is a chicken and egg situation here: without there being a viable device for linux development there will be no successful open platform. Contrast with this the Motorola approach: writing their own interface to sit on top of Linux with virtually no Linux community around it.

By the way, from what I can tell the N770/N800 are far from being unusable pieces of beta kit. I assume that segedunum you are basing this on actually trying the device and not just on rumour and speculation?

they seem to have been pretty clear from the outset that the strategic aim is to create a viable Linux mobile platform.

Depends what you mean by viable.

By the way, from what I can tell the N770/N800 are far from being unusable pieces of beta kit.

Then you just haven't used one, or you have a lot of emotion invested in it as several people seem to have ;-).

I assume that segedunum you are basing this on actually trying the device and not just on rumour and speculation?

Yes. Also, read the reviews that OSNews had once:

http://www.osnews.com/story.php/15079/Review-Nokia-770-Internet-Tab...

That sums up all my gripes having tried to use one for a day:

http://blogbeebe.blogspot.com/2006/03/using-nokia-770-internet-tabl...
http://blogbeebe.blogspot.com/2006/07/nokia-770-internet-tablet-os-...

It's a toy for tinkerers and those who want to spend an inordinate amount of time on it. It is by no means an acceptable product for normal people.

first of the 770 was never intended as a mass market device. it was a deveopers device for interested devs.

the N800 is the first device of this series thats aimed at the mass market directly.

therefor i would not go about using the sales figures for the 770 as a indication that the N800 will crash and burn.

not to long ago i read about a person that had used it with great success to order tickets online during a festival. as in, rather then standing hours in a queue he just pull out his N800, accessed the festivals web page and ordered up some tickets from there.

So it seems from the linked pdf as if they are basically using Hildon apps as with Maemo but with a different front end?

It looks from the screenshots as if they are using Helix/Real for the media player.

I wouldn't know why an UMPC should have an x86 processor when an ARM Cortex-V8 derivative such as the upcoming TI OMAP 3430 could be just as powerful and uses a lot less power.

That's not to say that the next generation x86 processors from Intel that are designed from the ground up for mobile use won't be good. It's just that they are not there yet wrt power use.

The only reason I can think of is Windows compatibility. GNU/Linux runs on any platform, the only thing holding it back is architecture specific closed source software such as Flash 9.

Yeah, you're right, an ARM is probably better tailored for the job, but Intel's x86 brings some advantages:

* x86 is way faster than ARM
* x86 has vastly better floating point
* Intel has hardware-accelerated media decoding
* Intel has 3D hardware with free drivers that will work fine at the resolution these devices use.

So the batteries migh not last as long, but while they last, the experience may be very, very good.

And don't forget that
* Intel has no ARM anymore
* Intel needs to push their low-power devices, and Microsoft's clumsy design is doing them a disservice.
* Intel only makes chips, and needs to sell millions of units in order to make a profit.
* Intel is not the owner of a competing software platform, and its linkage with MS is hurting it in this arena.

While Nokia may be only trying the waters with a skunkworks device that should not compete with their core products, Intel seems to be proactively seekig the killer platform that will propel their ultra low power devices to the stratosphere, with sales into the millions of devices. If it does work, it will be good for Intel, Linux, and even Nokia. Not as good for Microsoft, though.