Speeding up Flash... in a flash
WE ALL KNOW that if you put together four or eight flash devices together, you'll get a storage medium with performance far superior to any HDD: read or write, latency or bandwidth - name it. Only DRAM with battery backup would be faster.
However, the current interfaces and related controller ICs are the main roadblock from unlocking all that performance potential. Yeah, Firewire (OCZ has one) and e-SATA or even old IDE PATA are way better than USB 2 in both real performance and CPU usage, but, neither of these interfaces was really optimised for the flash (NAND or NOR) memory.
Not to mention the controllers currently used: there is more potential to be gained by ganging many flash memory ICs in parallel, multiplying the bandwidth or even adding ECC while keeping that low latency. Also, while similar, none of these are identical in terms of protocol or command set - why not standardise it and make life easier for everyone?
During one of those obscure hidden tech sessions at the recent IDF, Intel showed something that caught my eye: ONFI. What the hell is that? By the name alone, one would think of Paris Hilton's next puppy...
Well, ONFI is more than that - it is a part of an initiative to optimise the flash memory integration and performance in the PCs, starting with NVMHCI "Non Volatile Mem Host Controller Interface" akin to SATA AHCI.
NVMHCI is a standard programming interface for multiplatform OS support for flash as native storage at low level, enabling a single driver for both hard disks and flask memory. It can be used to support both the cache-like flash drive supplements like ReadyBoost or ReadyDrive, and full SSD storage devices.
Now, ONFI, or Open NAND Flash Interface, is a flash-optimised, uniform electical and protocol interface, with 1.0 ratified spec since end of last year. Intel and Micron are right now shipping ONFI-compliant chips. The current 60+ ONFI members include pretty much all major names, including ATI, Nvidia and a host of memory and controller vendors.
That's just the start - the upcoming ONFI 2.0 improves performance drastically by changing the NAND interface to almost quadruple the transfer rate from the NAND array to the memory buffer - from 40 MB/s to 150 MB/s per die, not bad eh?
Then, they borrow some thingies from SDRAM and DDR DRAM, like source synchronous data strobes and dual data rate timings with a clock speedup generational chart, ranging from Gen1 at 133 MB/s to Gen2 at 266 MB/s and Gen3 at 400 MB/s - or 10x above the current flash dies. The only pinout change? An extra source sync pin, that's it.
With that in place, why not follow the DRAM one step further, and create a standard ONFI DIMM connector for direct mainboard insertion? Rather than, say, cumbersome USB or eSATA or PCIe to NAND conversion, you might see future chipsets incorporate a few ONFI channels directly on the South Bridge. Once the ONFI controller is in there, you just need to add flash dies on a DIMM module - just like normal DRAM.
In a few months, you'll see a standardised ONFI NAND flash DIMM connector, for both horizontal and vertical module mounting. Take a look at the early concept here from the Intel presentation - I hope it enables multichannel DIMMs, i.e up to four ONFI channels per DIMM, one for each die or two - plus maybe an extra ECC channel too.
That would enable up to half a gigabyte per second net transfer rate our of, say, a single 32 GB four-chip ONFI 2.0 Gen1 flash DIMM next year, with near DRAM latencies too. Compare that to any current hard drives, and the picture is clear - you wouldn't want to boot your OS from a hard disk anymore, even if RAID 10.
With standardisation come higher volumes, easier implementation and, yeah, lower prices. I believe hard disks will still have their place as second storage device to handle data, etc, but, nevertheless, ONFI brought in the last piece of the puzzle needed to make NAND flash the primary storage device of most PCs from late next year onwards. µ
Share this:
Business Intelligence Software
Customer Relationship Management (CRM)
Enterprise Accounting Software
Enterprise Resource Planning (ERP)
Enterprise Systems Management
You know what I don't understand? Why the COASt module disappeared. 
Yeah, I know, the more "advanced" processors integrated L2 cache directory onto the die, but even the old K6-III, when placed inside a system with L2 cache on board could use the (board's) L2 cache as L3 cache. 
Why can't we add any L3 cache to our motherboards anymore today? A COASt module was a great way to upgrade your older system. Imagine buying an Athlon 64 today and plugging in 64 MB L3 cache next year. 
AMD has extremely fast HyperTransport connections and the HTX slot... why aren't they creating something like a COASt standard for this slot? It would be THE way to one-up Intel now that their processors are not up to snuff.

Seriously, what gives?
It took some time to get from 6 mb/s to 40 mb/s & incorporate so many windows & linx compatibilities. Years, All those years "You Can Flash O/S", was Theme, did it ever work for that?

RediWhip is thing that gave Flash taste & taught quality when boot up was too much with so much XP Driver Problems. Then someone got speeds up to O/S loadup FOR flash,TOO, Next particularly intresting hope is intialzation of o/s from disc to Flash (Don't Snicker, I Don't Know How To.) & NOW uses, internal to mainboard became in sight.

Hurray for FLASH, its like little portable computer on Stick. It will have just oddles of More uses & Lets' be quick about it, as well. Built in or Stick in: Super Fast Flash, World Awaitis your Usefulness.Its another big step, especially when Ultimate strains data load thru harddrive interface, its like breath of Fresh performance gaining Sweet Air of Life.

To Light In Tunnel, Boys.

Signed:PHYSICIAN THOMAS STEWART VON DRASHEK M.D.

Yum... been looking at Volesoft for ages now, and it has started to use this type of contextual advertisting....

dump it please!
It's great that we're someday going to end up with semi-permanent storage (almost) as fast as volatile memory, but I'm still waiting for them to figure out how to make it so I can write to this storage medium as many times as I want. 
You'd be smoking crack if you think I'm going to install an OS like Windows (any flavor) on flash memory that has a limited write life. Find me an OS that doesn't constantly write and rewrite (and rewrite some more) its own files and (maybe) we'll talk, but I wouldn't even count on it then. 
I should choose to replace my storage medium because of technological advances. I shouldn't be forced to replace it because it wore out and lost all my data (EVER.) Leave that to power supplies.
This looks like a nice technology. But it would probably be too small to be used as a drive and ReadyBoost is marginally useful at best.
I'm not sure where you think you think you can purchase a device that will never wear out and lose all your data today: if you're relying on your hard disk for that, you're quite possibly in for a very unpleasant surprise. And with good wear-leveling algorithms flash is equally robust for any sane workload (even 24/7 writes at multiple MB/second).

At the same time, using flash to hold even today's already over-weight OSs just to save a bit of boot-up time seems fairly wasteful, given that flash is closer to RAM in price/MB than to disk storage: if OSs took the time to stream themselves out to contiguous space on disk immediately after booting and then loaded this back on reboot (checking to ensure that the hardware configuration hadn't changed), that would probably help boot times about as much as flash will.

Now flash as disk cache, and especially as write-back disk cache - that's more exciting. Takes all the pain out of using a medium-sized transaction log, for one thing, making log-protected file systems and databases considerably faster without sacrificing an ounce of reliability/availability. And it lets data updates accumulate for a while before having to spin up the disk on a laptop (not to mention allowing them to be consolidated in a write-anywhere file system or at least destaged to disk in optimal order). Using it as additional read cache is less clearly a win, since RAM (though perhaps more expensive) does a better job of this while allowing other uses as well.

But until the retail price of flash falls well under $1/GB it will remain a luxury for use as general secondary storage, even on laptops (where the saved power just isn't very significant given how much processors and displays use).
With "Wear Leveling" a flash drive will last probably over 10 years, under pretty heavy use, that's 5 years longer than most mechanical HD warranty, and about as long as a mechanical drive lasts when Im being lucky.

As for size - yeah its small, but 32GB is plenty for a copy of XP and a copy of most my frequently used apps. The rest can live on a second mechanical drive. Hell I can fit any linux distro I want on one of those drives no problem and get insanely fast boot times and application execution.

Personally I cant wait. bout time we sped up our slowest component.