[Unmoderated] ArticiaS: mystery finaly solved ? | ANN.lu |
Posted on 08-Jul-2004 06:47 GMT by brotheris | 140 comments View flat View list |
Here's the summary of the last posts from hot topic. It may finaly put some dots on I's. Up to now we have heared a lot of small bits from variuos parties and finaly we can put the puzzle together. Read more about it.
I'll play Amon_Re of the past:
It all started when Chris Hogdes started explaining few things (in this thread and @226 comment).
During DMA transfers, the ArticiaS does not flag accessed memory as "dirty", therefore the CPU does not automatically know, that it has to update/flush its caches
Later (@ comment 247, 248 and others) Bernie Meyer explained how such a lack of feature (or call it a bug) affects stability, performance and may cause data corruption even in AmigaOS-like enviroment while using CachePreDMA()/CachePostDMA().
And then we discover quotes from ArticiaS documentation:
"The snoop cycle is used to probe the primary and secondary cache for updated data when the PCI
accesses DRAM. This is done to maintain data coherency between the Floating Buffer, DRAM and both
caches. The Articia S performs the Snoop cycle. When there is a snoop hit on a modified cache line in
either level one or two cache, the contents are written back directly to the Floating Buffer. A PCI Bus
master can subsequently later on fetch the data directly from the Floating Buffer. The Floating Buffer is
flushed back to DRAM during a PCI write cycle. The corresponding line in level one or level two cache is
thus invalidated. Snoops are hidden, meaning the CPU can continue its current data access without
being interrupted while the Articia S simultaneously queries both caches."
You can find similar information using google cache. It seems like some people lied. Is lack of Cache Coherency a bug or a feature (it was advertised that there is Cache Coherency, so it had to work) ? We may now put this case to rest.
|
|
List of all comments to this article |
ArticiaS: mystery finaly solved ? : Comment 113 of 140 | ANN.lu |
Posted by Janne on 11-Jul-2004 17:11 GMT | In reply to Comment 103 (Sammy Nordström): >>To date, and this is more than two year old chip, we have no fully working DMA
>>hard-disk driver in the public for Articia S.
>To date, and this is more than two year old hardware, we still have no fully
>working *operating system*.
Well, that is certainly one way of putting it. :) That is the very nature of circumstantial evidence, isn't it. You could also claim programmer incompentency, incomplete documentation or whatnot. But coupled with claims from other parties (namely bPlan, AFAIK Tratech too), and the fact that Linux runs quite nicely on a lot of hardware, things look a little more suspect.
Enough for you? Obviously not. Enought for suspicion? Sure, in my opinion.
Look, I would be personally very surprised - and have been saying this from the get go - if DMA doesn't turn up working on AmigaOne running AmigaOS 4.0 and later Linux too. They're bound to find a way sooner or later. Fault or peculiarity, usually there is a work-around and we may never really know is there a defect or is there not. I certainly hope they get it working.
However, what I find rather worrying is the way this issue is brushed under the carpet by some people. Obviously people running Linux on AmigaOne have been disappointed even very recently. Some thought the problem was already solved and obviously it is not. I would welcome a more open approach by everyone involved, even if the meant discussing unfortunare subjects in public.
>> bPlan engineers saying it is broken and making an expensive switch-over
>Yet another empty claim from a rather unbiased source(TM).
But was the source unbiased? If anything, they used to be biased towards MAI. They had a product that depended on it, for crying out loud. The switch-over must have been expensive as hell. I'm sure they didn't want to invent April and the rest. They felt like they had to, because they felt the chip didn't work. You can dismiss that all you want, but for me it is one testimony.
That, obviously, doesn't mean bPlan engineers couldn't have made a mistake. Sure, maybe they are wrong. But just dismissing them as biased makes no sense.
>> AFAIK Tratech/Barbie engineers saying it is broken, canceling product
>Never heard of that one before. I know they cancelled their product, but I >have seriously never heard that it would be because of the Articia S chipset. >I would appreciate if you have something to back this up,
Well, others covered that ground already and you found your way to dismiss it. For me, again, it adds more credibility to the argument that Articia S doesn't work as advertised.
But, again, I'd be surprised if they don't get DMA working just fine in the end. Work-arounds, using features or whatever. |
|
List of all comments to this article (continued) |
|
- User Menu
-
- About ANN archives
- The ANN archives is powered by #AmigaZeux. It was updated daily (news last: 22-Oct-2004; comments last: 18-May-2005).
ANN.lu was created, previously owned and maintained by Christian Kemp, www.ckemp.com.
- Contribute
- Not possible at this time!
- Search ANN archives
- Advanced search
- Hosting
- ANN.lu was hosted by Dreamhost. Sign up through this link, mention "ckemp" as referrer and he will get a 10% commission on any account you purchase.
Please show your appreciation for any past, present and future work on ANN.lu by making a contribution via PayPal.
|