Despite what many other commenters will say, no, it isn't a power hog compared to ARM. Or at least it doesn't have to be. Intel/AMD/VIA don't yet offer processors that have as low power as ARM (although some are pretty power/performance efficient depending on your workload), but they will within the next year for smartphones and tablets. On modern manufacturing processes the "x86 tax" becomes almost non-existant.

Atom has 64-bit support built in, and Intel disables it on most parts to a) to provide market segmentation and b) to save a bit of power. If MS had made Win7 64-bit only, Intel simply would have flipped the switch and sold the Atoms as 64-bit.

Thank you, I will check this out.

Yes, you could have stopped after the word "think".

We have and use VNC. It's supported and we depend on it. I did install and enable unsupported VNC clients like TightVNC to try to get some more speed. NX is the next step. You can argue whether or not users should be installing potentially insecure networking servers, and you can argue about productivity.

When working remotely everything is over VPN anyway.

I work for a large corporation that uses VNC,and several years ago I tried to install NX at work, hoping to get a speed boost when working remotely. Unfortunately, the creation of a user "nx" was required. I'm not in the IT department, I don't have root access, and they IT department had no interest in deploying NX. So I gave up.

I saw this announcement and hoped that an "nx" user would no longer be required, but it appears this is still necessary. If I could get it installed and it actually worked better I know the other engineers would jump on it and eventually IT would be forced to support it.

Anyone have a workaround?

Completely disagree. A CompE master's gets you nothing except a bit of a pay increase (but it will take years before the increase makes up for the year(s) you could have been working with a BS), and many many microprocessor designers have a BS.

2. Never use, or even think of, the word "goddess" in reference to yourself or other women.

But this ISN'T that old, craptastic, power-hungry chipset used by most Atom netbooks. It's a new chipset code-named Poulsbo designed specifically to go with Atom. Quoting a tomshardware.com article:

"The Atom Z500 has a TDP that varies between 0.85 W (for the 800 MHz version without HyperThreading) and 2.64 W (for the 1.86 GHz model with HyperThreading enabled). The SCH consumes approximately 2.3 W in its most evolved version, which brings the SCH + CPU together to under 5 W. By comparison with existing solutions, thatâ(TM)s obviously a big step forward â" the Via Nano, for example, is announced at 25 W for the 1.8 GHz version and a Celeron-M ULV at 5 W at 900 MHz."

http://www.tomshardware.com/reviews/intel-atom-cpu,1947-3.html

In addition, the Atom Z-series/Poulsbo combo supports the C6 idle power state where the CPU saves away its architectural state in a small SRAM which remains powered up while the rest of the CPU shuts off entirely. Idle power for the processor is somewhere from .01W - .1 W (this is from what I remember reading somewhere, but I can't find a link right now). Not sure what the chipset's powercomsumption is like when idle.

The biggest known downside to this chipset is that it supports 1 GB of RAM max.

From what I've read elsewhere, the chipset involved does have video decode acceleration support. After googling, anandtech.com has an article that says that the chipset can support 1080i and 720p decode. A tomshardware.com article says that it can do hardware decode of H.264, MPEG2, MPEG4, VC1, and WMV9 formats.

>I'm suspicious of the suggestion that a log-based
>filesystem will cure all the ills of the limited flash-
>controller based wear leveling.

Yeah. Total bull.

Anybody who thinks the filesystem can do really well has
bought into the crud from most existing vendors about how
you have to use those things differently. If you really
do believe that, you shouldn't touch an SSD with a ten-foot
pole.

If the flash vendor talks about "limits" in the wear
levelling, and how you have to write certain ways, just
start running away. Don't walk. Run away as fast as you
can.

>A question keeps coming up in my mind about what happens
>when you split an SSD into multiple partitions, and what
>*you want to happen*. I use separate partitions for root,
>boot, and var, because I tend to make root and boot
>read-only.

Again, if your SSD vendor says "align to 64kB boundaries"
or anything like that, you really should tell them to go
away, and you should do what Val said - just get a real
disk instead. Let them peddle their crap to people who are
stupider than you, but don't buy their SSD.

So what you want to happen if you split an SSD into multiple
partitions is exactly nothing. It shouldn't matter
one whit. If it does, the SSD is not worth buying. If it is
so sensitive to access patterns that you can't reasonably
write your data where you want to, just say "No, thank you".

Anyway, I have a good SSD now, so I can actually
give some data:
- Most flash-based SSD's currently suck.

      I don't have these ones myself, but last week we had the
      yearly kernel summit here in Portland, and a flash
      company that shall remain nameless (but is one of the
      absolute biggest and most recognizable names in flash)
      was selling their snake-oil about how you need to write
      in certain patterns.

      So I called them on it, and called them idiots. Probably
      one reason why I didn't get one of the drives they were
      handing out, but one of the people who did get a drive
      was the Linux block system maintainer. So he ran some
      benchmarks.

      Those things suck. You will never get any decent
      performance of anything but a very specialized filesystem
      out of them, unless you use them as essentially read-only
      devices.

      For a basic 4kB blocksize random write test, the SSD got
      around 10 IOps. That's ten, as in "How many fingers do
      you have?" or as in "That's really pathetic". It means
      that you cannot actually use it as a disk at all, and
      you need some special filesystem to make it worthwhile,
      and certainly means that wear levelling is probably not
      working right.

      (For the math-challenged, 10 IOps at a 4kB blocksize
      means 40kB/s throughput and 100ms+ latencies for those
      things. It also means that even if some operations are
      fast, you can never trust the drive)

- In contrast, the Intel SSD's are performing exactly as
      advertised.

      I did get one of these, with warnings about how
      if I want to get low-power operation etc I need to make
      sure that disk-initiated power management is enabled etc.

      Whatever. The important thing is that the Intel SSD does
      not care one whit where you write stuff, or how you do
      it. With the same 4kB random write benchmark test, the
      Intel SSD gets 8,000+ IOps (34MB/s throughput) with
      absolutely zero tuning. With bigger blocks and multiple
      outstanding requests, I got the promised 70MB/s. And it
      didn't matter one whit whether it was random or linear,
      the difference between 34MB/s and 70MB/s was purely in
      block sizes (ie there is some per-command overhead, which
      should not surprise anybody).

      On the read side throughput, if you can feed it enough
      requests, it was actually limited by the 1.5Gbps link
      I had on my realistic test-system (yeah, I have other
      machines that have full 3Gbps SATA links, but in mobile,
      1.5Gbps is common). And once more, it made no real
      difference whether accesses were random or linear.

So I finally have an SSD that really lives up to the
promise. And I can tell you - it makes an absolutely
huge difference in how the system performs. Just
try running Firefox for the first time - that mobile
platform is now snappier than my main desktop machine with
a new Nehalem and two fast disks in it.

And the write performance is important to that snappy
feeling. I can untar trees, install packages, do any amount
of writes etc and you can't even really tell. The system
still feels snappy.

As to reliability - sure, it's new technology, but since
I've been averaging around one dead harddisk per year, I'm
not so convinced about the old technology being superior
as Val is. So if the vendor gets the wear levelling right,
it's likely to be at least as reliable as those (not very
reliable) spinning platters are.

And right now, I do have numbers. Just based on behaviour,
I can pretty much guarantee that the Intel SSD's do a fairly
good job at wear levelling. At least they don't care about
your write patterns, and that should make people feel a lot
better about them.

So I can absolutely unequivocally say: if you want an SSD
today, you really can get a better disk than a traditional
disk. But as far as I can tell, it has to be an Intel drive.
Everything else is utter crap.

And no, Intel doesn't pay me to say so. Yes, I get early
access to some of their technology. But I'm an opinionated
bastard, and if it was bad I'd tell you so. As people here
should know (Itanium, anyone?).

That thing flies. The moment I can buy one more, I'll
spend my money where my mouth is. Because the difference
really is so clear. Right now, that tiny Mac Mini
(obviously running Linux ;) is actually nicer to use than
my main machine in many scenarios. All thanks to the SSD.

                                Linus

PS. The reason I tested mainly 4kB block sizes is that that
is what I use in the normal filesystems. I actually did test
512-byte writes too, and they perform perfectly fine and
got higher IOps than the 4kB case (but lower throughput:
the IOps didn't improve that much ;). I just don't
care too much personally, since nobody uses 512-byte blocks
anyway. But the thing really does act as a 512-byte sector
disk, with no access restrictions I can find.