TELVM

I'd expect that setup to hit the same 'sonic wall' @ 4K random read QD1. 4x Samsung 840 Pro (among the fastest consumer SATA III SSDs) in raid 0: ^ Everything scales up nicely except 4K random read QD1, which stalls at almost exactly the same point that the Intel P3700 beast above.

Jaclaz, if you don't mind me asking, could you please tell me what do you think about this email provider: http://www.autistici.org/en/

Ouch ouch. From Anandtech: "Small block random read operations have inherent limits when it comes to parallelism. In the case of all of the drives here, QD1 performance ends up around 20 - 40MB/s. The P3700 manages 36.5MB/s (~8900 IOPS)" ^ This breaks the party as far as I'm concerned. Any good SATA III SSD can manage those 4K reading speeds @ QD1 . There seems to be some sort of hard to pierce 'sonic wall' precluding huge leaps in random 4K reading.

Have a look at this beast : Intel SSD DC P3700 800GB Review - Ludicrous Speed for the Masses! Any chance NVMe might somehow work in W7?

^ Exactly my feeling. In the not-too-distant future everything is going to be dumbed-down, walled-gardened, clouded, monthly-subscribed, and in general screwed up for the users in every form imaginable. Enjoy W7 while it lasts, for beyond Se7en lies the abyss ...

"... the reason might be that Microsoft's own hardware was starting to look pretty bad using the Index. For example its expensive Surface Pro gets a 5.6 on the WEI scale when it was possible for a rubbish PC to get a score of 7.0 ..." http://news.techeye.net/software/microsoft-returns-to-its-dark-roots

^ Found it, it was just my poor searching skills: http://www.tomshardware.com/reviews/graphics-card-myths,3694-5.html "... These tests were run on a Windows 7 x64 setup with Aero disabled. If you’re using Aero (or Windows 8/8.1, which doesn't have Aero), you should add ~300 MB to each and every individual measure you see listed below ..." I'd add "and if you're using The Tiles Wonder @ 1920x1080 you're wasting 120~160 MB of VRAM at idle, courtesy of the Metro crap." Almost double the VRAM draw in exchange for losing aero and "gaining" Metro, boy that's progress!

^ I remember that Tom's article, but I'm also unable to find it now. Weird.

If this isn't old enough I've got them older in my Jurassic Park : I like how this table illustrates the pecking order in a more human-friendly time scale. On the rightmost column, if we assume 1 CPU cycle = 1 second, then ... ^ RAM is miles faster than anything else outside the processor die, SSDs included.

Windows 8.1 Finally Passes Windows 8 in Market Share "... It might be hard to get hold of Windows 7 these days, but that hasn’t stopped the OS packing on growth. It went from 49.27 percent in April to 50.06 percent in May -- finally breaking through the 50 percent barrier -- for an increase of 0.79 percent, nearly double that of Windows 8.x. ..."

Blind shot: Could it be that the DVD is plugged into one of the dreaded Marvell ports? If that's the case try plugging into a standard SATA port.

You've got significant variation only in the 4K-64th read. The reason total score varies so much is because 4K read and 4K-64th read 'weigh the heaviest' in the calculations for total score that AS SSD does. For typical use the really important thing is the 4K random read/write (though SSD makers love to mesmerize us with the sequential numbers ). I see no significant variations in Seq, 4K, or Access Time (all within the normal fluctuations). Always before running AS SSD benchmark, shut down as many applications and processes as possible, manually send a TRIM command to the SSD, and then leave the system idling logged-off for an hour or so (this allows the controller to perform its garbage collection and housekeeping to bring back the SSD to optimal condition for the benchmark ). EDIT - So much for the latest version delivering better results: In the second test the SSD hadn't been allowed time for housekeeping after a previous run, and all numbers went south.

No no that pic isn't mine . I wouldn't mind having an Areca but don't really need it. Then you're gonna love this :

Also there are toys nowadays able to deliver over 4GB/s sequential straightforwardly : Areca 1883

Ramdisks / RAM caches, if you remember.

Problem being that many real world files (music, photos, video, etc.) have a nasty habit of being incompressible . If that defeats controllers like the early Sandforces, I prefer the benchmark showing it (even if that ruins our bragging rights ).

I don't like ATTO for SSD benchmarking, it was designed for spinners and just 'blows a gasket' above ~1000MB/s. Much prefer AS SSD Benchmark, great little program. CrystalDiskMark is fine too. Aida64 has many useful tests, like its Cache & Memory benchmark: Linx for CPU GFLOPS horsepower. Cinebench.

Exactly like the Tiles crap is just the sucker bait to force us into the MS store. "All sheep proceed inmediately into the walled gardens. It's for your own good and protection. Resistance is futile - you will be assimilated".

Another milestone in the road to the Gulag: Google Is Now Blocking Chrome Extensions Outside of the Web Store All for your protection, you know .

CCL gives a report of all registry issues it finds before taking any action: We can then review and untick at will before fixing. Another of the many useful things that little mighty CCL can do is browser database compacting:

Any takers for this gauntlet?

Can't tell about The Tiles Wonder but I've been using CCleaner for years on XP & Se7en, and it works like a charm for housekeeping. In 'Options' => 'Include' you can specify a list of folders that will be purged of crap whenever you run CCleaner, which is useful in spades. Also I routinely run its registry cleaning with all options ticked, and never have had a problem. Ccleaner is always one of the first things I install on every system. Just my 2c.

I do exactly that by placing a vestigial pagefile* in a ramdisk, which dematerializes on shutdown and rematerializes on startup. * (Some stupid programs start bitching when they can't find a frigging pagefile).

Could you have imagined, just ten years ago, that we'd someday need institute directors to explain us that we need serious computers to do serious computing?

You might try a combination of the above and some RAM caching program like this: http://www.romexsoftware.com/en-us/primo-cache/