Read more.New OS install technique allows 16GB Windows 8.1 devices to have 12GB free space.
Read more.New OS install technique allows 16GB Windows 8.1 devices to have 12GB free space.
No mention if it has a detrimental effect on OS speed either!
Old puter - still good enuff till I save some pennies!
Nice and clever, extending the use of tech they have been using for years.
They may be late to the party but I do like some of the things they have been doing to play catchup.
Main PC: Asus Rampage IV Extreme / 3960X@4.5GHz / Antec H1200 Pro / 32GB DDR3-1866 Quad Channel / Sapphire Fury X / Areca 1680 / 850W EVGA SuperNOVA Gold 2 / Corsair 600T / 2x Dell 3007 / 4 x 250GB SSD + 2 x 80GB SSD / 4 x 1TB HDD (RAID 10) / Windows 10 Pro, Yosemite & Ubuntu
HTPC: AsRock Z77 Pro 4 / 3770K@4.2GHz / 24GB / GTX 1080 / SST-LC20 / Antec TP-550 / Hisense 65k5510 4K TV / HTC Vive / 2 x 240GB SSD + 12TB HDD Space / Race Seat / Logitech G29 / Win 10 Pro
HTPC2: Asus AM1I-A / 5150 / 4GB / Corsair Force 3 240GB / Silverstone SST-ML05B + ST30SF / Samsung UE60H6200 TV / Windows 10 Pro
Spare/Loaner: Gigabyte EX58-UD5 / i950 / 12GB / HD7870 / Corsair 300R / Silverpower 700W modular
NAS 1: HP N40L / 12GB ECC RAM / 2 x 3TB Arrays || NAS 2: Dell PowerEdge T110 II / 24GB ECC RAM / 2 x 3TB Hybrid arrays || Network:Buffalo WZR-1166DHP w/DD-WRT + HP ProCurve 1800-24G
Laptop: Dell Precision 5510 Printer: HP CP1515n || Phone: Huawei P30 || Other: Samsung Galaxy Tab 4 Pro 10.1 CM14 / Playstation 4 + G29 + 2TB Hybrid drive
Cue the £60-70 7 inch tablets - 1GB RAM/16GB Flash and zero Windows licensing fees.
I'm thinking more towards a Microsoft surface 'mini', an 8 inch, which has been rumoured for quite a while now, with 16gb storage as the base capacity. It makes sense to 'maximise' storage space considering how people are now complaining about the lack of storage after the os and junk is installed... supposedly performance can in some cases be 'better' than normal install, not sure on this mind lol
Can believe this - slow flash, cpu that uncompresses quickly and the net effect can mean better performance than chugging stuff out of flash uncompressed (it was like this in the old days with windows 3.1 and doublespace on my 386 - it improved performance as well as saving space).
Would love an 8" surface, as long as it has intel not arm and 3G built in.
On the other hand, it reads less from the disk, so it could go either way. My guess would be that it will result in a small speedup, considering that that flash on these tablets is 100MB/s max (probably much lower for low cost devices) and the CPU typically has a free core to do the decompression.
Edit: heh, didn't see gagaga's post.
Interesting thought, yes I suppose if (compressed disk read + uncompress)time < (uncompressed read)time then there could be a speed up, wouldn't it hit the CPU hard though? And in that case is CPU or disk the worse drain on battery?
If this is actually good for speed why isn't it done by default in non-power constrained environments like desktops with old spinning rust disks?
The file has to be decompressed by the CPU before the PC can read it though. The sandforce ones compress as it's storing it on the disk (and cannot be seen by any operating system, it is at the hardware level), that is independent to any other compression.
So, yes, it will effect CPU......but in some cases you might find the saving on disk time vs decompression time means a faster system.
Main PC: Asus Rampage IV Extreme / 3960X@4.5GHz / Antec H1200 Pro / 32GB DDR3-1866 Quad Channel / Sapphire Fury X / Areca 1680 / 850W EVGA SuperNOVA Gold 2 / Corsair 600T / 2x Dell 3007 / 4 x 250GB SSD + 2 x 80GB SSD / 4 x 1TB HDD (RAID 10) / Windows 10 Pro, Yosemite & Ubuntu
HTPC: AsRock Z77 Pro 4 / 3770K@4.2GHz / 24GB / GTX 1080 / SST-LC20 / Antec TP-550 / Hisense 65k5510 4K TV / HTC Vive / 2 x 240GB SSD + 12TB HDD Space / Race Seat / Logitech G29 / Win 10 Pro
HTPC2: Asus AM1I-A / 5150 / 4GB / Corsair Force 3 240GB / Silverstone SST-ML05B + ST30SF / Samsung UE60H6200 TV / Windows 10 Pro
Spare/Loaner: Gigabyte EX58-UD5 / i950 / 12GB / HD7870 / Corsair 300R / Silverpower 700W modular
NAS 1: HP N40L / 12GB ECC RAM / 2 x 3TB Arrays || NAS 2: Dell PowerEdge T110 II / 24GB ECC RAM / 2 x 3TB Hybrid arrays || Network:Buffalo WZR-1166DHP w/DD-WRT + HP ProCurve 1800-24G
Laptop: Dell Precision 5510 Printer: HP CP1515n || Phone: Huawei P30 || Other: Samsung Galaxy Tab 4 Pro 10.1 CM14 / Playstation 4 + G29 + 2TB Hybrid drive
It's a curious one. I've run a Windows to Go workspace off a USB 2.0 micro-SD card reader and get a nice responsive system, which suggests that slow flash isn't actually that much of a barrier to performance. Then again, decompression is a task that threads really nicely and both AMD and Intel have high core count low end CPUs targetting the mobile space. Plus decompression also responds nicely to GPU acceleration - although this may be too low level for MS to build nice GPU-accelerated routines for decompressing the OS on the fly...
Still, I assume MS wouldn't do this if they felt it would have any significant performance impact on the level of systems it will be employed in, so presumably they reckon decompression performance in Atom/Kabini and modern ARM cores is more than sufficient to keep pace with the requests from the OS. Add it to the announcement about free Windows for smaller devices and it does look very much like a move to make < £200 Windows tablets viable. It'll be very interesting to watch how pricing moves with this...
It also decompressed the 'compressed' data on the read - it was aimed more at making the drive last longer than performance so like I say it 'could' remove the need for the cpu if the chipset is designed to support it, I only used sandforce as a reference to ssd's chipsets that are already using compression at some level.
The likelihood is that MS have 'spoken' to a few ssd chipset manufacturers about this feature to make sure it works well or it would be counter productive to make such a big announcement about it.
Just ... no. This doesn't need special SSD technology - which doesn't work the way you seem to think it does anyway.
The whole point is to free up more storage. Sandforce's technology doesn't do that - the compression is used to reduce wear on the flash memory, and as a side effect this speeds up the storage - but a 16GB sandforce based drive would still only hold 16GB of data. The Windows system files would take up exactly the same proportion of that space, regardless of who manufactured the drive. You can't magically get more storage that way (if you could companies would be selling sandforce drives with 128GB of flash chips as 256GB drives - they're not). For one thing you can't guarantee how much any given file will compress by - so uncompressable files would suddenly take up massively more storage than you' expect. It'd be horrendous.
You seem to think this is some big new technology, but it isn't. The Windows installer has worked this way for many years: the install CD/DVD has several compressed Windows Image files on it, and the installer runs from one of them and expands another to perform the install. MS have a lot of experience with running systems using on the fly decompression of an image file. They've probably got performance benchmarks stretching back many generations of CPUs, just lying around.
So what is more likely, that MS polled lots of SSD manufacturers to test proprietary technologies that aren't currently available before annnouncing a technology that they're already using in a different context anyway, or that they bought a $200 last-generation netbook with a weak Atom CPU and benchmarked performance on that?
So, has anyone dared to actually take the plunge and try this yet? I doubt I'm unique in having a fairly small SSD (120 Gb) and a big Windows install eating about 20 Gb of it, I'd like to save the space if I can do so without a measurable performance impact.
Core i5 2500K clocked to 4.4 GHz so I doubt the CPU impact will be noticable.
There are currently 1 users browsing this thread. (0 members and 1 guests)