OK, so the vulnerable machines are a Wyse Winterm 9455XL, and an HP t5125.

I actually have a Winterm 9450XE, which is simply a smaller version of the 9455XL - the same EPIA 5000AW motherboard overclocked to 550 MHz from 533.

I'm not familiar with the HP t5125, but the 9450XE/9455XL's BIOS was pretty janky, I reflashed it with the latest official EPIA BIOS.

I should probably actually figure out how to test this when I get home...

I would be completely unsurprised if VIA had a thin client custom build of the BIOS that was broken, or even just managed to forget to shut off ALTINST in release builds of the main EPIA BIOS...

Also, the author managed to find the patents that Centaur had on this, but couldn't find the datasheets for the Samuel-2 or Nehemiah processors under test? True, that wouldn't have given away the actual Alternate Instruction Set, but...

bhtooefr
Follow

The slides also put way too much emphasis on Glenn Henry's attempts to run x86 and ARM on the same core (which was a much later thing), rather than what the C3 actually did...

Sign in to participate in the conversation
Mastodon

Follow friends and discover new ones. Publish anything you want: links, pictures, text, video. This server is run by the main developers of the Mastodon project. Everyone is welcome as long as you follow our code of conduct!