On Sun, Dec 17, 2000 at 12:52:59AM -0800, Drew Hess wrote:
> It also contains an experimental patch to drivers/pci/quirks.c that forces
> standby mode for pool C RDRAM devices. I've seen some benchmarks
> comparing the Intel D850GB motherboard to the ASUS P4T and attributing the
> better performance of the P4T to the fact that Intel's BIOS puts pool C
> RDRAM in nap mode and has no option to change it, whereas the P4T does.
> On my D850GB, the patch doesn't seem to change the performance of STREAM
> one way or the other; but when I change the value written into the RDST
> register to set nap mode and shrink the A and B pools to 1 device each, I
> see about a 20-30MB/s drop-off on STREAM, so I'm pretty sure the code does
> what it's supposed to.
>
> This code isn't strictly a 'quirk' in the sense that some of the bug
> workarounds in drivers/pci/quirks.c are, but I didn't see a more
> appropriate place to put it. Suggestions are welcome.
sounds like powertweak is what you want.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sat Dec 23 2000 - 21:00:18 EST