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

Re: JFFS is not broken (Was: JFFS broken?)

jonas.holmberg@xxxxxxx.com said:
>  Yes, but the flash chips are slow so it doesn't help. The CPU has to
> wait for every word to be read into the cache. 

Just to check we're talking about the same thing here - are you really 
doing synchronous burst reads, or just filling a cache line with normal 
async reads from the flash?

I don't expect much performance gain unless you do the former. 

http://developer.intel.com/design/flcomp/datashts/290737.htm has details on 
how some of the Intel StrataFlash chips do it...

"To perform synchronous burst-mode read, an address is driven onto A[max:1], 
and CE# and OE# are asserted. WE# and RST# must be de-asserted. ADV# is 
asserted, then de-asserted to latch the address. <...>

"<...> After the initial access delay, the first word is output from the 
data buffer on the next valid CLK edge. Subsequent buffer data is[sic] 
output on valid CLK edges. Synchronous burst-mode reads can only step 
through the data buffer once, and can only do so in a sequential manner; 
starting from the address latched at the beginning of the burst cycle."


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