Slashdot Mirror

I guess you would agree Phoronix is qualified to install the first beta of a Linux based OS? How about they being unable to boot anything but Windows 8 (.1) on hardware with UEFI after lot of trying?

It was a problem with that specific device's bootloader only reading 32bit EFI. Im not sure what agenda you are trying to serve by attempting to generalize this, it is clearly a very specific problem on a specific device that has already been worked around.

Depends on who that someone is. How about Phoronix ?

Looks more like their problem is they didn't use EFI-compatible bootable image, it's nothing to do with SecureBoot at all, the process is pretty straightforward and documented here.

Depends on who that someone is. How about Phoronix ?

I guess you would agree Phoronix is qualified to install the first beta of a Linux based OS? How about they being unable to boot anything but Windows 8 (.1) on hardware with UEFI after lot of trying?

Bcache, merged in 3.11, improves IO up to 100X. Not 100%, 100X, or 10,000%. It may well be worth an upgrade if you're running a distro 2.3x and have random IO on multi TB storage.

The multi-queue block layer which is merged in kernel 3.13 gives a 3.5x to 10x increase in IOPS. This change is mostly targeted for SSDs, but gives similar improvements on HDs as well. However, it's not clear whether this improvement is relative to 3.11 or not.

No because GCC is reacting to what Clang does and Clang is still choosing which existing optimizations to enable at which -O levels. Don't expect any improvements of any consequence from either GCC or Clang, while they're still competing over what colors their error messages should be, because hipster coderz these days are so incredibly dumb that colored error messages are seriously important fashion statements that they actually care about. The clangy-gee-see-see rivalry is laughably idiotic.

ATI Linux drivers have traditionally been crappy, but since they were bought by AMD, they've opened up a lot, and have been steadily contributing to the main kernel. The kernel drivers (as opposed to the proprietary Linux drivers) have been improving by leaps and bounds lately. Kernel 3.5 saw 3D performance improvements of over 35% with some AMD cards, and 3.12 is supposed to have a similar huge boost.

I don't know how they compare to the closed source drivers from Nvidia *or* ATI, but I'm currently running 3.10, and the in-kernel drivers are definitely working very well for me.

Phoronix on 3.5 drivers

Phoronix on 3.12 drivers.

ATI Linux drivers have traditionally been crappy, but since they were bought by AMD, they've opened up a lot, and have been steadily contributing to the main kernel. The kernel drivers (as opposed to the proprietary Linux drivers) have been improving by leaps and bounds lately. Kernel 3.5 saw 3D performance improvements of over 35% with some AMD cards, and 3.12 is supposed to have a similar huge boost.

I don't know how they compare to the closed source drivers from Nvidia *or* ATI, but I'm currently running 3.10, and the in-kernel drivers are definitely working very well for me.

Phoronix on 3.5 drivers

Phoronix on 3.12 drivers.

• "Faster Zombies!" [Valve Linux] - http://blogs.valvesoftware.com/linux/faster-zombies/
• "The AMD Radeon Performance Is Incredible On Linux 3.12" - http://www.phoronix.com/scan.php?page=article&item=amd_linux312_major&num=1
• "Here's Why Radeon Graphics Are Faster On Linux 3.12" - http://www.phoronix.com/scan.php?page=article&item=linux_312_performance&num=1

Both NVidia and AMD have lifted their game a lot recently for Linux. Plus Valve has been working hard to improve things - with its Steam Box in the pipeline (which is Linux based). I suggest you take a look at Linux drivers again, they are very competitive on modern GPUs.

• "Faster Zombies!" [Valve Linux] - http://blogs.valvesoftware.com/linux/faster-zombies/
• "The AMD Radeon Performance Is Incredible On Linux 3.12" - http://www.phoronix.com/scan.php?page=article&item=amd_linux312_major&num=1
• "Here's Why Radeon Graphics Are Faster On Linux 3.12" - http://www.phoronix.com/scan.php?page=article&item=linux_312_performance&num=1

Both NVidia and AMD have lifted their game a lot recently for Linux. Plus Valve has been working hard to improve things - with its Steam Box in the pipeline (which is Linux based). I suggest you take a look at Linux drivers again, they are very competitive on modern GPUs.

Watch again Gabe Newell's presentations about Steam on Linux.
The whole point of Steam of Linux is to avoid the loss of freedom that Windows is taking a path.

They don't want to move to a proprietary stack, and thus replace Microsoft with Canonical (if they depend on Ubuntu's specific quirks) or with Nvidia (if they depend on a precise graphical stack thighly controlled by them). They need a not tighly controlled platform on which to develop.

That means at least several independent companies collaborating, which means an open standard, which in the FLOSS means we'll always end up with at least 2 different implementation of said standard.

As a 12+ year Linux users, I have to give Shuttleworth some rope to hang or prove himself. For example, back in Gnome 2x-3x transition days, Gnome panel was broken for widescreen devices like LCD monitors and netbooks.[1] Unity turned out a bloated for my taste, but I fully understand his frustration with Gnome. In the end, for heavy weight desktops, I prefer Unity over Gnome 3.

PulseAudiois fine for playing music, but a real PITA for many hardcore gamers[2][3] including myself. I found latency was terrible with Wine + PA and later saw the developers had an issue with PA too.[4] After countless hours lost trying to debug some PA issues, I lost all respect for Poettering. The only worse sound server that I’ve encountered is AudioFlinger, and at least that has the excuse of being optimized for battery life over latency. So like Shuttleworth, I'm skeptical about any of Poettering's work.

Now to the meat of the debate, Mir. It's clear X11 is fundamentally broken for modern desktop/GPUs. [5] It needs to die and I don't care if it is replaced by Mir or Wayland. I have been hearing about Wayland for years now, and only after Mir was announced did I start to hear about it actually reaching a usable state. I wish they'd work together but maybe a little competition will help us all to finally rid Linux of X11.

[1] https://bugzilla.gnome.org/show_bug.cgi?id=86382

[2] http://www.techrepublic.com/blog/linux-and-open-source/pulse...

[3] http://ubuntuforums.org/showthread.php?t=960195

[4] http://www.phoronix.com/scan.php?page=news_item&px=MTEyODM

[5] https://www.youtube.com/watch?v=RIctzAQOe44

There is also a huge performance boost to AMD Cards with the 3.12 Kernel;

That is only because a problem with the ondemand performance governor was corrected.

I still have an AMD based system though (cpu, chipset, and gpu).

Thanks for that - I wasn't aware ATI gaming support had improved that much under Linux. An article posted today promises still more improvements in various games under the soon-to-be-released 3.12

http://www.phoronix.com/scan.php?page=article&item=amd_linux312_preview&num=1

There was reportedly a huge jump in performance with the 3.5 kernel series (as high as 38% in at least one case), and a lot more work was done with 3.6 through 3.10.

Well, actually Valve will release SteamBoxes with AMD cards too: http://www.phoronix.com/scan.php?page=news_item&px=MTQ4Mjc
Just the first batch of prototypes focuses on Nvidia.

The Kickstarter is for a code drop, no hardware.

According to Francis Bruno, the 2D version fits on a Cyclone II 25 or a Spartan 3.

Can you recommend a board with a GPU that has acceleration with an opensource driver. The current state of opensource ARM seems a bit basic http://www.phoronix.com/scan.php?page=news_item&px=MTQ3MTM . Even intels minowboard uses one of the powervr GPUs that tainted half the netbooks back in the day.

The old CPU is a shame, but its been fast enough for me so far. For my MPD server I replaced a Beagleboard with RaspberryPI, which is plenty fast for streaming playing FLACs and MP3s.

If you compare benchmarks where multiple generations of GPUs compete against each other, such as the Passmark benchmark, later AMD GPUs seem to have a better ratio of benchmark scores to theoretical computing power (as given on http://en.wikipedia.org/wiki/Comparison_of_AMD_graphics_processing_units )

Examples:
Radeon HD 3850: 427.5 GFLOPS, Passmark score of 532
Radeon HD 3870: 497.3 GFLOPS, Passmark score of 744
Radeon HD 4850: 1000 GFLOPS, Passmark score of 1043
Radeon HD 4870: 1200 GFLOPS, Passmark score of 1361
Radeon HD 5750: 1008 GFLOPS, Passmark score of 1399
Radeon HD 7750: 922 GFLOPS (at 900 MHz), Passmark score of 1624

The 38xx surprise by bucking the trend - maybe some AMD developer had a bright moment there? But in general, drivers for current cards seem more efficient. In the 7750, the change in architecture may have helped.

For Linux in particular, the open source drivers are gradually getting closer (at least to the AMD Catalyst driver). For some older and presumably simpler games, the reviews on http://www.phoronix.com/ already show 80% of the performance of Catalyst. In other, more demanding, tests they still suck but the long term trend is encouraging.

NV hasn't had "great proprietary Linux drivers" for a while. Performance is good, yes, but Optimus supportd has been denied, older cards are given the shaft (not keeping up with newer Xorg APIs in a timely manner can be excused - marking severe rendering issues on Gnome Shell, Unity and Cinnamon as a wontfix on three generations of their cards cannot) and you can get funny stories such as these: http://www.phoronix.com/scan.php?page=news_item&px=MTQ3NDE

So, while NV has the edge in performance still, for owners of particular cards/features the experience can be incredibly frustrating, which is why I would never say their proprietary drivers for Linux are "great". I"d save that for a driver that works as well as NV's on Windows.

My god the horror. That old line drawing code from the 80's. Sitting all alone, stable and debugged in some source file somewhere. And paged out on disk taking up no resources if it's really not being used.

Yes the horror. It's junk which must be maintained and tested and impedes development of new functionality.

Maybe. But the thing is which I find mildly disturbing is that while X11 has many, many defincies, the Wayland folks seem to enjoy making up straw men and picking on things which are easily refutable.

They're not straw men and you didn't refute them so much as pretended that the brokenness didn't matter. Many of the people supporting Wayland are former X11 developers fed up with having to work around broken design. There are some good technical articles describing what is wrong with X11 such as this one.

Yay duellng with URLs:

http://www.phoronix.com/scan.php?page=article&item=amd_fx8350_visherabdver2&num=1

That's versus IVB, not Haswell, but Haswell doesn't seem hugely faster than IVB. In some cases intel win. In some cases AMD beat the i5 handily. In others, AMD beat the i7 handily.

Looks like you're right. I didn't realise AMD's Open Source driver was so good (or their proprietary driver so bad? I don't know how it compares to Windows).

Meanwhile, Intel have only an Open Source driver. Good for them. (I don't know that it's documented (I'm thinking BSD), but it's a good start.)

Looks like you're right. I didn't realise AMD's Open Source driver was so good (or their proprietary driver so bad? I don't know how it compares to Windows).

Meanwhile, Intel have only an Open Source driver. Good for them. (I don't know that it's documented (I'm thinking BSD), but it's a good start.)

Phoronix Benchmarks will give you an idea of the perfomance differences. Btrfs is usually middle of the pack, so nothing to write home about. The big deal with btrfs is the new features like COW, snapshots, filesystem compression, etc. If you are looking for more performance btrfs is not going to impress. If you are looking for better RAID perfomance, snapshots, compression, etc. Then btrfs is going to be huge for linux. It is probably the closest linux will get to having a ZFS clone.

http://www.phoronix.com/scan.php?page=news_item&px=MTQzMTU "GNOME 2 Fork MATE Desktop Aims For Wayland"

You're thinking spherical cow.

This is the spherical chicken reference.

I'm deeply disappointed that this issue was decided over philosophical instead of technical merits. If Clang was superior to GCC in the majority of benchmarks, then I would support this decision. But that’s not the case, GCC is still leading in most benchmarks and can be an order of magnitude faster when the popular OpenMP library is used.[1] Sadly, BSD users are the losers here.

[1] http://www.phoronix.com/scan.php?page=article&item=llvm_33svn_competes&num=5

So what would you prefer? That BSD threw out their entire licensing policy and adopted the GPL3? Or that they stuck with an old version of GCC that was licensed under the just about permissible to them GPL2 but that got no updates.

Maybe they could have forked GCC then tried to maintain a version that was licensed under GPL2 and backported GPL3 GCC fixes into their fork but that strikes me as being a legal nightmare to be honest.

It would have been more useful it phoronix compared LLVM/Clang 3.3 to GCC 4.2.1 and you posted that as that is the only thing the BSD community could use instead.

This decision was forced by the GCC adopting the GPL3 but was probably always going to happen sooner or later. The BSD community and the FSF have VERY different ideas of what constitutes "free" software with the FSF actually wanting their code to be less free in order to make sure that if you use it you have to let other people see how you use it and keep any derivatives free.

gcc being gpl v3 does not effect the output of the complier only code linked to or borrowed from it

Your linked comparison isn't relevant to the FreeBSD situation. The GCC version in FreeBSD is 4.2.1, the last available under GPLv2. Clang is overall an improvement In comparison to that version.

http://www.phoronix.com/scan.php?page=article&item=freebsd_91_llvmgcc&num=2

I'm deeply disappointed that this issue was decided over philosophical instead of technical merits. If Clang was superior to GCC in the majority of benchmarks, then I would support this decision. But that’s not the case, GCC is still leading in most benchmarks and can be an order of magnitude faster when the popular OpenMP library is used.[1] Sadly, BSD users are the losers here.

[1] http://www.phoronix.com/scan.php?page=article&item=llvm_33svn_competes&num=5

So what would you prefer? That BSD threw out their entire licensing policy and adopted the GPL3? Or that they stuck with an old version of GCC that was licensed under the just about permissible to them GPL2 but that got no updates.

Maybe they could have forked GCC then tried to maintain a version that was licensed under GPL2 and backported GPL3 GCC fixes into their fork but that strikes me as being a legal nightmare to be honest.

It would have been more useful it phoronix compared LLVM/Clang 3.3 to GCC 4.2.1 and you posted that as that is the only thing the BSD community could use instead.

This decision was forced by the GCC adopting the GPL3 but was probably always going to happen sooner or later. The BSD community and the FSF have VERY different ideas of what constitutes "free" software with the FSF actually wanting their code to be less free in order to make sure that if you use it you have to let other people see how you use it and keep any derivatives free.

I'm deeply disappointed that this issue was decided over philosophical instead of technical merits. If Clang was superior to GCC in the majority of benchmarks, then I would support this decision. But that’s not the case, GCC is still leading in most benchmarks and can be an order of magnitude faster when the popular OpenMP library is used.[1] Sadly, BSD users are the losers here.

[1] http://www.phoronix.com/scan.php?page=article&item=llvm_33svn_competes&num=5

No its slower. Phoronix benchmark GCC vs Clang all the time. http://www.phoronix.com/scan.php?page=article&item=llvm_clang33_3way&num=1

Except FreeBSD is not using GCC 4.8. They're using GCC 4.2.1, the last version that was GPLv2.

While the current version of GCC may be faster than Clang/LLVM, that doesn't mean Clang/LLVM isn't faster than what is in use now, so the switch may even boost performance compared to the ancient version of GCC in use.

No its slower. Phoronix benchmark GCC vs Clang all the time. http://www.phoronix.com/scan.php?page=article&item=llvm_clang33_3way&num=1 [phoronix.com]

Interesting that they use -O3, which is not clang's fastest optimisation setting (which is -Ofast). Also, they are comparing the speed of the compiled code (which was my second point, that it produces faster code), not the speed of the compiler. Clang is currently (in my brief tests) roughly 4 times faster (as in, the compiler's exception time is 4 times faster) than gcc at compiling C, and 2 times faster than gcc at compiling C++ when set to -O0.

For many reasons.

Clang is faster...

No its slower. Phoronix benchmark GCC vs Clang all the time. http://www.phoronix.com/scan.php?page=article&item=llvm_clang33_3way&num=1

The AMD APUs really are a great melding of price vs performance....

Even though I loath the 70% gross margin that Intel insists on. They have http://www.phoronix.com/scan.php?page=news_item&px=MTI5MTI 20-30 people working on Linux Drivers vs 5 from AMD. There is more than one way to measure bang for buck. That said when I buy a separate graphics card it will be AMD.

You can get the 'advance' toolchain. It's basically an upstream gnu toolchain, with a lot more optimizations and support for ppc chips.

Looks like LLVM is getting improved as well.

What is this, a high school paper? Need to fill space much?

That's mostly harmless. If you want to see a much better space filler, look here. Moronix indeed.

http://www.phoronix.com/scan.php?page=article&item=ubuntu_xmir_benchmark&num=3

The power management situation is about to be drastically improved.

Your analogy holds true only if both projects, being Wayland and Mir, are serving the same purpose - They aren't.

Yes, they are both a display server/protocol, and yes, they are designed to replace X, but the goals of each project couldn't be more dissimilar.

Wayland is a long needed update to X that will fix a number of issues and allows for secure buffers that only the application and server can access. Wayland is being designed for the existing Linux desktop market and is a much needed project.

Mir, while adopting some ideas from Wayland, is a completely different beast that will focus on achieving two primary objectives: A display server that runs natively on both desktop and mobile, and, being actively developed and supported by new commercial partner Valve. It makes little sense for Canonical to wait for Wayland and then extend it for these two purposes as doing so will leave Canonical years behind on a shift that is happening NOW.

Wayland is absolutely being developed with mobile and desktops in mind: From the official wayland site itself (http://wayland.freedesktop.org/): "Part of the Wayland project is also the Weston reference implementation of a Wayland compositor. Weston can run as an X client or under Linux KMS and ships with a few demo clients. The Weston compositor is a minimal and fast compositor and is suitable for many embedded and mobile use cases."

And that's just the reference compositor.

But there's more. Work to get Wayland running on android about a year before (april 2012) Canonical's Mir announcement : http://lists.freedesktop.org/archives/wayland-devel/2012-April/003149.html

In fact, while we're on the topic of Android, Canonical took someone else's code (libhybris) for running Wayland on Android drivers to achieve Mir support for android drivers. Here's an article about it from the author of libhybris: http://mer-project.blogspot.fi/2013/04/wayland-utilizing-android-gpu-drivers.html
Quote from the article "Earlier this year however, I discovered that a well-known company had taken the code - disappeared underground with it for several months, improved upon it, utilized the capability in their advertisements and demos and in the end posted the code utilizing their own source control system, detached from any state of that of the upstream project's. Even to the extent some posters around the web thought libhybris was done by that company itself."

Oh yeah, Canonical's criticisms of Wayland (ie, their stated reasons for creating their own display server instead of going with Wayland) were so awful that they had to retract them: http://www.phoronix.com/scan.php?page=news_item&px=MTMxODY

Regarding Valve's support... Citation please. Last I heard Valve was sticking with X and hadn't made any further comments. Unfortunately I'm unable to find a link to back this up at the moment. I *suspect* Valve is taking a wait and see approach, and they're probably silently hoping Wayland wins as Canonical has stated that Mir has no stable API/ABI, which would make it a nightmare for application developers to support. It's unclear if they'll stabilize the ABI/API in the future, but it's sounding like they won't. This is one of the major reasons why the major desktops don't want to support Mir.

Everyone has been waiting for the Year of Linux on the Desktop; this will bring the goal one step closer. The same goes for an unadulterated Linux on the Mobile where graphical applications are more easily ported from their desktop counterparts.

There is nothing stopping Wayland importing code from Mir and vice versa.

Mir can use Wayland code as Wayland is under the extremely permissive MIT lice

What's outdated about X11? And no, the presence of old API calls for backwards compatibility does not make it outdated.

Answer: http://www.phoronix.com/scan.php?page=article&item=x_wayland_situation&num=1

You've got quite a selective memory there, bud. The only parties that are hurling Molotov's are in the Wayland and KDE camps (mostly from the deranged kwin dev).

The mere existence of Mir is "hurling Molotovs" at Wayland: http://www.phoronix.com/scan.php?page=news_item&px=MTMxODA
To claim that anybody other than Canonical started that "war", is simply lying.

He's talking BS.
Martin Graesslin, the KWin maintainer, began to prepare KWin for Wayland before Mir was even announced. So he designed the transition path to support two and only two back ends. See https://plus.google.com/115606635748721265446/posts/136nV4uojKH for details (public post, no need for a G+ account).

Graesslin also made it repeatedly clear that he won't support single-distro solutions. That means no support for MS Windows in KWin, OSX' Quartz, or Android's SurfaceFlinger. Somehow nobody ever had a problem with that decision. Only after Canonocal announced Mir Ubuntu fanboys began to whine.

There are no technological benefits for Mir over Wayland. Canonical made false claims as outlined on http://www.phoronix.com/scan.php?page=news_item&px=MTMxODA but they've since redacted the statements. Wayland even works with Android drivers: http://mer-project.blogspot.fi/2013/04/wayland-utilizing-android-gpu-drivers.html

The reasons for Mir are not technological, they are purely economical. Canonical wants to establish asymmetric licensing to have an economic advantage over the competition: http://mjg59.dreamwidth.org/25376.html
Wayland OTOH is under MIT/X11 license for everybody. This means that not only can any Linux vendor grab it and to anything with it, incl. to make an Android version that uses Wayland: http://ppaalanen.blogspot.com/2012/09/wayland-on-android-upgrade-to-404-and.html
Mir's licensing makes it forever impossible to become part of any major BSD variant. Wayland, however, is being ported to FreeBSD: http://www.phoronix.com/scan.php?page=news_item&px=MTMwMzE

Wayland is being pushed by industry giants such as Intel and Red Hat, as well as smaller companies like Collabora (creators of many technologies commonly used on GNU-based Linux such as Telepathy, WebKit-GTK, etc.: https://www.collabora.com/projects/ ).
Mir is just backed by Canonical who, while claiming to be the most popular Linux distributor, still makes no money: http://www.internetnews.com/blog/skerner/canonical-ubuntu-linux-is-still-not-profitable.html

He's talking BS.
Martin Graesslin, the KWin maintainer, began to prepare KWin for Wayland before Mir was even announced. So he designed the transition path to support two and only two back ends. See https://plus.google.com/115606635748721265446/posts/136nV4uojKH for details (public post, no need for a G+ account).

Graesslin also made it repeatedly clear that he won't support single-distro solutions. That means no support for MS Windows in KWin, OSX' Quartz, or Android's SurfaceFlinger. Somehow nobody ever had a problem with that decision. Only after Canonocal announced Mir Ubuntu fanboys began to whine.

There are no technological benefits for Mir over Wayland. Canonical made false claims as outlined on http://www.phoronix.com/scan.php?page=news_item&px=MTMxODA but they've since redacted the statements. Wayland even works with Android drivers: http://mer-project.blogspot.fi/2013/04/wayland-utilizing-android-gpu-drivers.html

The reasons for Mir are not technological, they are purely economical. Canonical wants to establish asymmetric licensing to have an economic advantage over the competition: http://mjg59.dreamwidth.org/25376.html
Wayland OTOH is under MIT/X11 license for everybody. This means that not only can any Linux vendor grab it and to anything with it, incl. to make an Android version that uses Wayland: http://ppaalanen.blogspot.com/2012/09/wayland-on-android-upgrade-to-404-and.html
Mir's licensing makes it forever impossible to become part of any major BSD variant. Wayland, however, is being ported to FreeBSD: http://www.phoronix.com/scan.php?page=news_item&px=MTMwMzE

Wayland is being pushed by industry giants such as Intel and Red Hat, as well as smaller companies like Collabora (creators of many technologies commonly used on GNU-based Linux such as Telepathy, WebKit-GTK, etc.: https://www.collabora.com/projects/ ).
Mir is just backed by Canonical who, while claiming to be the most popular Linux distributor, still makes no money: http://www.internetnews.com/blog/skerner/canonical-ubuntu-linux-is-still-not-profitable.html

But Flash/SSD really offers an intermediate performance level, and I haven't seen much from either Linux or Windows to take advantage of it without lots of customization or niche applications (such as Readyboost, or mounting /usr/share on a flash stick or whatever.) Has anybody seen anything interesting happening to take advantage of flash?

Did you look hard?

Try this: http://www.phoronix.com/scan.php?page=news_item&px=MTM2ODM

Linux 3.10 Kernel Integrates BCache HDD/SSD Caching

...

BCache comes down to being a Linux kernel block layer cache where one or more SSDs (or other fast storage devices) can act as a cache for slower rotating disk drives, in somewhat a similar manner to some of the "SSHD" hybrid drives now on the market. BCache is similar to the L2Arc feature exposed on Oracle's ZFS file-system, but with being at the block device level, it's file-system agnostic.

Ah, yes because he said "we could probably do better" it's instantly terrible and doomed.

Hyperbole considered bad.

I read it as someone who was confident of their solution but unsure of the final form

"Probably" was not the only qualifier in the paragraph, pretty much everything he wrote was explicitly qualified. However you are welcome to support your beliefs with a citation to some documentation for even alpha level protocols for remoting wayland apps.

What I've seen is stuff like this GSoC participant who discovered that its not as simple as he thought. No one's touched his work since. Seems like the only work to come since then has been RDP based DESKTOP forwarding, not application remoting.

weaker processor: What's your CPU usage right now? http://www.phoronix.com/scan.php?page=article&item=samsung_exynos5_dual&num=4

100%, whenever I play some games (Civ 5 being the obvious popular one)

less powerful video card: My phone's GPU is more powerful than the most common desktop one (Intel integrated).

Yeah... anyone who uses Intel integrated does not want decent graphics. Anyone who wants decent graphics does not use Intel, or a phone.

less control: I replaced my phone & tablet OS with a different userspace, kernel & all. Less savvy users get info on what an app will do before they install it.

Some phones have less control, some don't. I'm a lot happier with a system not designed to make it difficult to install another OS on it. How many dual booting phones are there about?

less Ram: My Phone has 2GB LPDDR3. Tablets have more. It resembles PCs 5 years ago.

My PC is 5 years old, and it has 16GB.

less drive space: 64gb micro-SD cards & first-class wireless-N to a fileserver. This problem is minor.

My Steam folder is almost 1/3 a terabyte alone - I think if I installed all my games, it'd be about a terabyte. Loading textures in game over a wireless link sounds a lot of fun. Currently I have striped SATA drives.

Windows 8 made it even more complicated to install Linux. Not only because of UEFI but also because of Fast Boot.

http://www.phoronix.com/scan.php?page=news_item&px=MTM4MDY

The stupid thing is, it also makes it harder to fix Windows.

It might even make it legally very complicated to get a refund from Microsoft if you want a refund for the pre-installed software.

As for Network Manager, try running it with any USB networking (direct connect, like with a phone, rather than an USB-connected ethernet card): it will kill the interface every roughly 30 seconds. Its upstream refused to fix that saying they don't aim to support every possible device.
Or, bridged setups. Or, basically anything more complex than a plain ethernet or wifi interface.

NetworkManager has supported bridging since version 0.9.8.

Fedora Project Wiki: Networking/Bridging
NetworkManager Now Supports Bridging, AP-Mode Hotspot

So if the i7 is more energy efficient per-workload, that makes it even more onesided.

As I recall, the fight gets even more brutal when doing things like AES or anything optimized with an instruction set, or anything bound by memory bandwidth.

http://www.phoronix.com/scan.php?page=article&item=samsung_exynos5_dual&num=6
Thats the first-gen Core series vs an A15. Note that it completes its work in 1/3 the time. Ivy bridge is ~30% faster for the same parts, and uses less power (~1/2), and thats not a particularly optimal processor either. Im not sure if anyone has ever compared one of the low-power i7s or Xeons (ie, E3 1220Lv2) to ARM, but I imagine it wouldnt be pretty.