Intel is developing its own take on the mini-tablet, with a new ultra-mobile PC platform to be announced at this week’s Intel Developer Forum in Beijing. The big surprise? It’s based on Linux. In the meantime, Intel announced new details of its forthcoming Santa Rosa PC platform, including a significant revision of the Core 2 Duo chip.
Too bad I really don’t use my computer in an intensive enough way to justify the cost. The dynamic speed enhancement technology is a really good idea in this world of mostly single-threaded compute-intensive tasks. Unless the task is naturally parallel, a single-threaded, efficient algorithm will do it faster on a fast processor than on two moderate processors due to lower cache-sync overheads and contention over memory, I presume.
When hybrid HDDs become widely available, the flash cache thing will be my first upgrade. Vista is more aggressive with embedded flash caches because it can be guaranteed that they will never be surprise removed. Keeping the HDD off for minutes at a time will cause a significant improvement in battery life and noise.
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.
dip in.
Then they will claim they invented it.
you know who.
Nokia?
“you know who.”
Intel?
“MID tablets will run a simplified “finger-friendly” user interface optimised for the small screens, based on the Gnome desktop but with an Intel-developed “master user interface” layer to serve as an equivalent to the desktop.”
I like the sound of that.
What about running HaikuIA ?
Microsoft has been banging away at tablets for years. It’s Bill Gates’ personal baby, and yet, absolutely no one wants one and everyone who has tried one has found it impractical apart from some very niche uses. Nokia have also had a multipurpose tablet running Linux, and it has also largely been a commercial failure. The best they have managed is using it as a test-bed for some software, and giving it away to some Gnome developers.
I see absolutely nothing different about this one that Intel is producing, nor why they haven’t learned their lessons from others. I mean, what on Earth is a ‘prosumer’ for crying out loud?
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.
Anyone have any facts on this?
So far, in my not-very-humble opinion, sub/micro/nano/etc devices like this have not been very successful. I would like somebody to succeed. How successful was the Toshiba Libretto?
BTW, how’s that Microsoft micro-notebook going? I haven’t heard much about it in a long time.
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.
Oh dear, the always predictable segetroll, if is mono related or something remarking the success or GNOME/GTK you will magictly appear, I wonder if you are an employee of Trolltech or some troll with no life at all, I think are both, btw, how was the last #kde-promo meeting?
Oh dear, the always predictable segetroll, if is mono related or something remarking the success or GNOME/GTK you will magictly appear
Hmmmm. You’ve been presented with evidence that Nokia’s tablets are not selling, and you’ve also been presented with a perfectly reasonable review which tallies with my poor experiences…….and you’ve gone from that to assuming this is an attack on Gnome and GTK? Well, that’s a troll if ever I saw one.
It’s the reason why I also said that there seems to be a great deal of emotion attached to the Nokia 770, for reasons I can’t quite work out ;-). An awful lot of people seem to have this idea that the Nokia 770 was going to propel GTK and Gnome into the mobile mainstream for some reason, and are bitterly disappointed that that hasn’t materialised.
The fact that you have an inferiority complex over that is not my problem, nor is it related to my actual point.
I wonder if you are an employee of Trolltech or some troll with no life at all, I think are both, btw, how was the last #kde-promo meeting?
I don’t know where I mentioned KDE or Trolltech at all anywhere, or what relevance this load of claptrap has. My point is that tablets are simply not selling, whether they are Nokia’s running GTK, Windows or something running Qt. That’s it.
You asked for some evidence of Nokia’s tablet sales, which you got and obviously didn’t think you were going to get, and you just don’t want to read a perfectly legitimate review detailing how woefully poor the device actually is and you don’t want to respond to that.
That’s being a troll if ever I saw it, and just look at your comment history (full of modded down comments in the red) of trolling on anything related to KDE or Qt (and Linux, to boot). What a shocker! Wonder why you bother………
Edited 2007-04-17 15:21
An awful lot of people seem to have this idea that the Nokia 770 was going to propel GTK and Gnome into the mobile mainstream for some reason, and are bitterly disappointed that that hasn’t materialised.
Ha ha ha. You wang.
Edited 2007-04-18 06:34
by ‘viable’ I mean: with a decent open source community around it. The success of the 770 has been the success of building the maemo community.
I think that Nokia has realised, astutely, that there isn’t any value in open source unless you can create a community around the platform — otherwise you may as well just do proprietary development in house. Contrast with the ‘launch and forget’ approach of Sharp with the Zaurus.
You have to recognise a basic chicken and egg problem with open source mobile platforms: if there is no device that can be used to develop the platform then there will be no community around it. What you end up with is things like Qtopia that are developed more or less entirely in house and, as a result, might as well be a proprietary platform.
by ‘viable’ I mean: with a decent open source community around it. The success of the 770 has been the success of building the maemo community.
Unfortunately, the device and software is just far too unstable for mainstream usage and has not justified Nokia’s development methods for the device.
I think that Nokia has realised, astutely, that there isn’t any value in open source unless you can create a community around the platform
Nope. There isn’t any value unless you can use open source software to lower development costs and produce a device that is stable enough and of a good enough quality to sell to a mass market. I don’t know whether Nokia succeeded with the former (I doubt it), but it has obviously failed with the latter.
You have to recognise a basic chicken and egg problem with open source mobile platforms: if there is no device that can be used to develop the platform then there will be no community around it.
To what end? You can’t just put open source software on to a device just for the sake of it. The thing has to work, and it has to justify the usage of open source software’s existence on the device. It achieves nothing just by virtue of it being there.
What you end up with is things like Qtopia that are developed more or less entirely in house and, as a result, might as well be a proprietary platform.
Projects like OPIE (Open Palmtop Integrated Environment) are a successful offshoot of Qtopia, and produced a very good environment and set of applications for many mobile devices (at least, most of it worked the last I checked) so you can hardly call that in-house.
An awful lot of people just don’t grok what is required for software on mobile devices in the open source community, even less than they do for the desktop. Maemo is not going to be carried anywhere in the mobile world simply on a bubble of hype. The outside, mainstream, real world just does not get how exciting, amazing and cool it is to have Linux and Maemo on there, how, it’s like, open source, and you you can go about tinkering to get it to work moderately well. They have better things to do.
So, let me get this straight. You are saying that nobody should try and create a community-supported mobile platform unless it’s instantly commercially successful? That’s crazy.
The point about Linux on the desktop is that at least there was an existing hardware platform (the Pc) to develop on. That doesn’t exist with mobile devices. Any mobile hardware maker keen to take advantage of the potential cost savings of open source development has to get something out there that kickstarts that development. In many ways the Trolltech Greenphone is a similar idea, except they are targeting it only at developers and not end users (and given the price, only very committed developers are going to be able to afford it — not a criticism, Trolltech don’t have the same finances as Nokia).
OPIE came about, by the way, if I remember correctly not as an offshoot to the Qtopia firmware but as an alternative. I don’t doubt that OPIE has (had?) much to commend it but if OPIE is such a successful set of applications why didn’t Nokia select that as a starting point? Why aren’t Intel?
Incidentally it seems at least some endorsement of the success of the mameo platform that Intel are choosing to use its Hildon components for their own platform.
You keep talking about people’s failure to grok how the commercial adoption of Linux can/cannot work but you never present any alternative view. It’s always very easy to sit in the corner and criticise all these companies’ efforts when you have nothing of your own to offer…
As opposed to your own emotional investment in deriding anything Gtk, Gnome or Mono related at every possible opportunity?
You certainly seem to have a remarkably negative attitude to what seems, on the face of it, to be encouraging developments. The fact that it’s not a commercial success now — if that is a fact, something you’ve consistently failed to produce evidence of — doesn’t mean that it won’t be a success long term.
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.
Well, it’s nice to see Hildon componetes in this device. The work done in N770 and N800 will cary on this devices too!
Some nice details about this “UMPCs” in this PDF:
https://intel.wingateweb.com/published/UMGS003/UMGS003_100eng.pdf
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.
The problem with the UMPC is the PC part. It has to be there in order to run XP/Vista, but it bogs down the whole design with heavy hardware and power requirements that give you and underpowered PC in return that requires 20/20 vision to use.
Kicking Microsoft’s design in the ass brings great benefits: No hard drive, one fourth the RAM, no shitty BIOS, the possibility to tailor existing apps for the platform and so on.
Compared with Nokia’s N800, which is an impressive piece of engineering, Intel’s design is way more powerful. Much faster processor, more storage, 3D acceleration that should be enough at this resolution, and with free drivers from the word go. It also has much more familiar hardware — not quite a PC, but very close! This will ease running proprietary software such as codecs and browser plug-ins (flash). And being part of the same ecosystem, code will flow and improvements will pile up.
I hope they manage to offer decent battery life, and at an affordable price!
It remains to be seen whether tablets do have a place in the world or not. If they do, this will be an incredible showcase for Intel’s technology, and their opportunity to show the world they did well selling the XScale to Marvell, because their x86 architecture can scale well from handheld to megacluster.
I want one.
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.