I updated the BIOS on the machine for other reasons - I found that my
non-acpi kernel then hung partway through the boot.  It went further
with a acpi kernel, actually crashed in the same place but I managed
to snag this:

kernel: double fault trap, code=0
Stopped in pid 17.1 (pagedaemon) at     netbsd:Xintr_legacy7+0x34:      movq    %r13,0x48(%rsp)
db{1}> 

So, it looks like a double fault in an interrupt handler on CPU 1.

-- 
Brett Lymn