It's "MIPS-derived", probably meaning they didn't pay any licensing fees. MIPS is the simplest ISA, and lots of networking equipment is based on MIPS. The question is not "why MIPS?" but "why not MIPS?"
Tilera doesn't use HyperTransport; except for AMD most SoC vendors are using PCI Express for I/O.
I'll believe it when I see RHEL shipping with KVM. And unless they can run Xen VMs on KVM, RHEL will have to continue to include Xen to run old Xen VMs. Gotta love legacy code.
Can someone explain why the future of all virtualization isn't simply kvm?
XenSource/Citrix, Virtual Iron, Red Hat, and Novell have invested millions in Xen, and for the sake of backwards compatibility they are now stuck with it.
ESX lite would have the exact same problem as regular ESX: the BIOS boots the service OS (Linux 2.4), then the service OS loads VMkernel, then VMkernel shims itself under the service OS.
And yet MPEG-4 can be expanded to use sprites/panorama, animated textures, 2-D animated meshes, 3d-Meshes, natural sound...
Too bad nobody knows how to encode that stuff. Out of the codecs that actually work, the BBC is probably using one of the most efficient ones (Windows Media Video 9).
The guide data from your digital box is formatted to be easy to read for a human, while the data for TiVo/Myth/whatever must be formatted to be easy to read for a computer.
Sorry, I don't see the distinction. My cable box is a (embedded) computer and a PVR. My cable box can use the guide data sent by the cable company to record shows.
Clearly the reason why TiVo/Myth/whatever cannot access cable guide data is political, not technical.
So you pay for satellite or cable TV, but the television networks are un-willing to provide a few bytes of information in the form of scheduling information for future programming?
Yeah, I never understood this. My cable box can download guide data from the cable company, but a TiVo/MythTV/whatever can't? I'm not paying again for data that's already available on my cable system.
Let's be clear; Dell is talking about servers with built-in hypervisors. Extrapolating these plans to desktop PCs is just unfounded speculation.
Their Hypervisor will enforce DRM, so even linux can't override it.
Servers don't care about DRM.
They'll make it so all device drivers must be signed to go into the Hypervisor which will be the only thing with any I/O privs that aren't virtualized.
OK, this is true. ESX requires special drivers.
They'll make it so new hardware has closed interfaces and can only be supported by a driver at the Hypervisor level.
On the contrary; Dell has been driving companies like Broadcom and Adaptec to open up and offer open source drivers. AFAIK the only reason we have the tg3 driver is because Dell told Broadcom to provide Linux drivers.
I'm not too interested in talking about theoretical chips. I suppose Sun will sell a partial-good quad-core Niagara 2 which will be lower power than desktop x86 chips, but desktop apps would still run so slowly that it wouldn't be worth buying Niagara 2 for desktop use.
Sitting on the same FSB sucked rather badly for SMP scalability.
If the quads are cheap enough, it doesn't matter. Sure, you only get 50% performance improvement instead of 100%, but if the price is only 20% higher then it's a net win.
When the shortage hits, it will be worldwide. My point is that there's no reason why any particular country (such as China) would be worse off than any other.
When you say "the way addresses were distributed", you are ignoring the fact that there are millions of unused, un-distribued addresses free for the taking.
CableCard will succeed only when cable companies stop scrambling premium channels.
Uh, the whole point of CableCard is to descramble premium channels. If the cable companies used clear QAM for everything, then you wouldn't need CableCard.
Slashdot Mirror
It's "MIPS-derived", probably meaning they didn't pay any licensing fees. MIPS is the simplest ISA, and lots of networking equipment is based on MIPS. The question is not "why MIPS?" but "why not MIPS?"
Tilera doesn't use HyperTransport; except for AMD most SoC vendors are using PCI Express for I/O.
The cost of the Internet is in the routers, not the fiber.
I'll believe it when I see RHEL shipping with KVM. And unless they can run Xen VMs on KVM, RHEL will have to continue to include Xen to run old Xen VMs. Gotta love legacy code.
Those who use Xen for VPS hosting, how hard would it be to switch to ESX
Considering the price of ESX, it would be out-of-business hard to switch to it. Smart VPS hosts are using OpenVZ/Virtuozzo anyway.
Can someone explain why the future of all virtualization isn't simply kvm?
XenSource/Citrix, Virtual Iron, Red Hat, and Novell have invested millions in Xen, and for the sake of backwards compatibility they are now stuck with it.
I know Web 2.0 is full of buzzwords, but actually naming a product Buzzword is brilliant. Finally truth in advertising.
Performance counters could be used by JITs to generate more optimized code. I wonder which programming languages use JITs...
ESX lite would have the exact same problem as regular ESX: the BIOS boots the service OS (Linux 2.4), then the service OS loads VMkernel, then VMkernel shims itself under the service OS.
And yet MPEG-4 can be expanded to use sprites/panorama, animated textures, 2-D animated meshes, 3d-Meshes, natural sound...
Too bad nobody knows how to encode that stuff. Out of the codecs that actually work, the BBC is probably using one of the most efficient ones (Windows Media Video 9).
The guide data from your digital box is formatted to be easy to read for a human, while the data for TiVo/Myth/whatever must be formatted to be easy to read for a computer.
Sorry, I don't see the distinction. My cable box is a (embedded) computer and a PVR. My cable box can use the guide data sent by the cable company to record shows.
Clearly the reason why TiVo/Myth/whatever cannot access cable guide data is political, not technical.
So you pay for satellite or cable TV, but the television networks are un-willing to provide a few bytes of information in the form of scheduling information for future programming?
Yeah, I never understood this. My cable box can download guide data from the cable company, but a TiVo/MythTV/whatever can't? I'm not paying again for data that's already available on my cable system.
So where are all the ESX exploits?
Let's be clear; Dell is talking about servers with built-in hypervisors. Extrapolating these plans to desktop PCs is just unfounded speculation.
Their Hypervisor will enforce DRM, so even linux can't override it.
Servers don't care about DRM.
They'll make it so all device drivers must be signed to go into the
Hypervisor which will be the only thing with any I/O privs that aren't
virtualized.
OK, this is true. ESX requires special drivers.
They'll make it so new hardware has closed interfaces and can only be
supported by a driver at the Hypervisor level.
On the contrary; Dell has been driving companies like Broadcom and Adaptec to open up and offer open source drivers. AFAIK the only reason we have the tg3 driver is because Dell told Broadcom to provide Linux drivers.
Sure, sometimes you actually have two runnable threads on a desktop, so for silky smoothness you want two fast cores, not eight slow ones.
* This puppy comes ahead of Power5 and top-dog (till now) Power6
* Highest single CPU integer and floating point performance
In two benchmarks: SPECint_rate and SPECfp_rate. Now let's see some real-world application performance.
I'm not too interested in talking about theoretical chips. I suppose Sun will sell a partial-good quad-core Niagara 2 which will be lower power than desktop x86 chips, but desktop apps would still run so slowly that it wouldn't be worth buying Niagara 2 for desktop use.
1.4 GHz * 8 cores * 8 threads = 89.6 fake GHz.
I wonder how many BogoMIPS that is equivalent to.
Desktop processors from Intel and AMD are in the 40-65W range; do you still want a desktop Niagara machine?
Also, desktop apps run dog-slow on Niagara because they mostly only use one core.
Apparently Sun will sell the chips to you already manufactured if you want.
Go look at the performance of Windows games on UltraSPARC T1. Now, figure that UltraSPARC T2 still doesn't run Windows.
They don't need to track power consumption; they track capacity. So if you pay for a 30A circuit they assume that you will use all of it all the time.
Sitting on the same FSB sucked rather badly for SMP scalability.
If the quads are cheap enough, it doesn't matter. Sure, you only get 50% performance improvement instead of 100%, but if the price is only 20% higher then it's a net win.
When the shortage hits, it will be worldwide. My point is that there's no reason why any particular country (such as China) would be worse off than any other.
When you say "the way addresses were distributed", you are ignoring the fact that there are millions of unused, un-distribued addresses free for the taking.
Internet Protocol v4 Address Space.
See all those blocks marked "IANA - Reserved"? Those are unused addresses. Any ISP in China can ask APNIC for more addresses, and APNIC will give them addresses. There is no shortage.
CableCard will succeed only when cable companies stop scrambling premium channels.
Uh, the whole point of CableCard is to descramble premium channels. If the cable companies used clear QAM for everything, then you wouldn't need CableCard.