On Sun, Dec 11, 2022 at 01:57:13PM -0500, Daniel Dickman wrote:
> I have a laptop with these Transmeta devices:
>
> pchb0 at pci0 dev 0 function 0 vendor "Transmeta", unknown product 0x0060 rev
> 0x00
> ppb0 at pci0 dev 1 function 0 vendor "Transmeta", unknown product 0x0061 rev
> 0x00
>
> NetBSD describes device 0061 as the integrated North Bridge, but I think
> this is incorrect as this is actually an AGP bridge:
>
> product TRANSMETA TM8000NB0x0061 TM8000 Integrated North Bridge
>
> The PCI repository has these entries, which I feel is more correct than
> NetBSD:
>
> 0060 TM8000 Northbridge
> 0061 TM8000 AGP bridge
>
> However, reading the "Efficeon BIOS Programmers Guide", I chose to
> describe device as 0060 as HyperTransport instead.
>
> The Efficeon processor has a virtual north bridge that can communicate
> with the south bridge over HyperTransport and can communicate with the
> graphics controller over an AGP bridge. For reference, see Chapter 2,
> Figure 1 showing the system block diagram.
>
> Some contemporaneous news coverage on HyperTransport is available here for
> reference:
> https://www.eetimes.com/transmeta-links-next-generation-processor-to-hypertransport/
>
> ok?
ok jsg@
>
> Index: pcidevs
> ===
> RCS file: /cvs/src/sys/dev/pci/pcidevs,v
> retrieving revision 1.2014
> diff -u -p -u -r1.2014 pcidevs
> --- pcidevs 4 Dec 2022 03:13:52 - 1.2014
> +++ pcidevs 11 Dec 2022 18:51:04 -
> @@ -9030,6 +9030,8 @@ product TOSHIBA2 TFIRO 0x0701 Infrared
> product TOSHIBA2 SDCARD 0x0805 SD
>
> /* Transmeta products */
> +product TRANSMETA TM8000_HT 0x0060 TM8000 HyperTransport
> +product TRANSMETA TM8000_AGP 0x0061 TM8000 AGP
> product TRANSMETA NB 0x0295 Northbridge
> product TRANSMETA LONGRUN_NB 0x0395 LongRun Northbridge
> product TRANSMETA SDRAM 0x0396 SDRAM
>
>
