Subject: Re: PMAZ-A option card on 3MIN and MAXINE
To: None <port-pmax@NetBSD.ORG>
From: Toru Nishimura <nisimura@is.aist-nara.ac.jp>
List: port-pmax
Date: 06/05/1998 10:41:31
> I don't have any devices on the PMAZ-A card normally - it's too slow.
> (Direct DMA access to memory is a big PLUS!).
> ...
> If the disk can sustain a faster transfer
> rate, you would be unlikely to see much difference:  the overhead of
> copying to/from the PMAZ-A buffer and all the other I/O overhead in
> doing the SCSI operation will mask any difference.

That was my original suspection.  Gee... the PMAZ-A figure I posted is
worse than AHA-1542B with 486DX2/66.  IOASIC SCSI DMA outperforms
12.5MHz PMAZ-A completely.

BTW, I'm interested in IOASIC DMA "chaining".  How can we program "DMA
pointer update"?  (I can not believe commented-out asc_dma_intr() has
ever worked so far, although it seems to be there for-loooog-time).
That would also contribute the drivers for 7990, 79C30 and floppy. 

Tohru Nishimura
Nara Institute of Science and Technology