Where should the type information be 163
DMA was used because it was "fast enough". Windows didn't support multi-tasking so the processor couldn't do anything during I-O anyway. Since OS-2 could walk and chew gum at the same time, it used DMA long before ATA33. Windows 3x would use it too, but there really wasn't much point.
...different in speed only. The ATA specification included Modes 0 thru 2 (3, 5, and 8MB-s) and the ATA-2 specification added modes 3 and 4 (12MB-s and 16MB-s).
There were also six DMA modes in the ATA specs. The original ATA spec included Single-word modes 0 thru 2 (2, 4, and 8MB-s), and Multi-word mode 0 (4MB-s). The ATA-2 spec added multi-word mode 1 (13MB-s) and mode 2 (16MB-s).
Where should the type information be 164
On Thu, 31 Mar 2005 07:48:19 GMT in alt.folklore.computers, "Stephen IIRC 3380 and 3390 had sector cells related to RPS which made space calculations...
All of the above operated on 40 conductor cables. The 80 conductor cables didn't come about until ATA-33 (and really weren't needed there).
Windows didn't multi-task, so there was no reason for DMA. As I said, OS-2 did, so used DMA whenever possible. My first Pentium system ('94) was doing DMA I-O. So yes, M$ did choose to use PIO, but not because it was better, rather because it was "good enough" given the OS limitations.
Ok, so Windows was-is broken by design. Any surprises here?