[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Intel StrataFlash support



Thanks for the MTD list links; I hadn't searched for "Strata Flash".
Clearly basic StrataFlash support exists, but there's more to do...

What I was driving at is that the "flash is more expensive than RAM"
argument against XIP has just gone out the window in some important cases.

On the PXA262 & 261, flash is essentially free - up to 256Mb!
And for reading, this flash performs like RAM.

In this setting, RAM is not only more expensive, it can be a power drain as
well.

I feel this setting calls for XIP and writable/compressed segments on the
same chip, with whole-chip wear-leveling. (I'd guess by dividing the chip
into romfs and jffs2 partitions, and continually trading blocks between
them...)


Liam Breck, Director
PointServers.org                                  liam@xxxxxxx.org
Boston, Massachusetts                           http://pointservers.org/


At 02:23 PM 1/1/03 +0100, tglx@xxxxxxx.de wrote:
>On Tuesday 31 December 2002 21:59, Liam Breck wrote:
>> I'm wondering what support exists in JFFS2 and/or MTD for Intel
>> StrataFlash. This type of flash includes a RAM bit for each flash bit in
>> the device, providing flash reads at RAM speeds.
>http://www.google.com/search?q=site:lists.infradead.org+strata
>
>> This technology also re-raises the XIP issue. Parts of this flash should be
>> treated as uncompressed ROM for XIP, but *which* parts would need to shift
>> over time in order to do wear-leveling over the whole device.
>http://www.google.com/search?q=site:lists.infradead.org+xip
>http://www.google.com/search?q=site:lists.arm.linux.org.uk+xip
>
>> Intel StrataFlash is likely to become a common component in embedded
>Really ?
>http://www.intel.com/pressroom/archive/releases/flo91797.htm
>
>> systems, as it is part of the XScale PXA26x CPUs (and they have recently
>> discontinued the PXA250, which lacked it).
>
>> Thoughts?
>Yes. Happy New Year !
>
>-- 
>Thomas
>____________________________________________________
>linutronix - competence in embedded & realtime linux
>http://www.linutronix.de
>mail: tglx@xxxxxxx.de


To unsubscribe from this list: send the line "unsubscribe jffs-dev" in
the body of a message to majordomo@xxxxxxx.com