[OLPC-devel] Re: NAND flash controller speed.

[Tom Sylla]

Just to follow up here, '010' has been deemed "ok" by simulations from 
the silicon team.

Tom

David Woodhouse wrote:
> On Fri, 2006-06-02 at 17:33 -0600, Tom Sylla wrote:
>> Yes, that makes it a little faster. I was holding off on recommending 
>> that until I asked the silicon designers if it was safe (from the spec, 
>> it seems like it could cause problems, but other things may slow it down 
>> enough not to matter) 
> 
> I did wonder if during a 'burst' 32-bit read it would lead to 4
> consecutive cycles with RE# asserted, without ever deasserting it in
> between. That doesn't seem to happen though, and I'm sure the docs
> wouldn't say "you can set this to 0" on both the pre-cycle and
> post-cycle hold times without a warning if that _were_ the case.
> 
> Surprisingly, it does also seem to work if I set them _all_ to zero.
> It's just slow.
>