20 comments

[ 2.8 ms ] story [ 41.6 ms ] thread
(comment deleted)
Did Cyrix cease to exist or is this someone using their x86 license?

EDIT: That's exactly what it is! They are a joint venture with VIA which acquired most of Cyrix in 1999:

https://en.wikipedia.org/wiki/VIA_Technologies

VIA has their own license and joint CPU project w/ a Chinese company apparently, could be related to that?
> They are a joint venture with VIA which acquired most of Cyrix in 1999

FYI: Zhaoxin (兆芯) [1] is a Joint Venture between VIA Technologies (威盛電子) and the Shanghai Municipal Government. Zhaoxin is mentioned in the article:

"As pointed out in the Phoronix Forums, it could be Zhaoxin. But as they have contributed GCC patches, Glibc patches, Linux kernel patches, etc, over the years it's not clear why they would go unnamed or have to relay the message via Ludloff rather than their prior direct mailing list posts."

[1] https://en.wikipedia.org/wiki/Zhaoxin

Cyrix… that's a name I've not heard in a long time
By what legal mechanism is it restricted that not any random company can make their own independent implementation of hardware that interoperates with x86 software?
You mean in 2025 someone is getting paid in their job to mess with x86 segment registers? I'd do that stuff for free.
They're just using the encoding for PUSH CS, presumably the actual instruction doesn't concern segment registers… I hope…
(comment deleted)
This is something I heard through the grape vine years ago, but when you're a very large corporation negotiating CPU purchasing contracts in quantities of millions, you can get customizations that aren't possible outside of gigantic data centers. Things like enabling custom microcode (and development support) for adding new instructions for the benefit of your custom JIT-ed server infrastructure. The corporate entity here is likely a hyperscaler that everyone knows.
Historically the large buyer that could do this was NSA. Men in black would show up and tell you to add a bit population count instruction to your CPU..
Oracle Cloud used to boast this as something they had. Tuned for OracleDB with more cache, different core count.

And every homelabber has had one of the 7B13 or 9654-variant processors

> I was asked to relay this to binutils/LKML.

> As of 2025, the following are in active use by a corporate entity other than Intel/AMD.

> Any collisions with them should be avoided.

What's the purpose of sending this email to these mailing lists -- who cares about assigning x86 instruction opcodes other than Intel and AMD? Do Linux and binutils need to know about unused x86 opcodes in some way? And even if they did...why do unaffiliated open-source projects need to care about a nonstandard architecture extension from a company so secretive about it they won't even name themselves?

Last month, Nvidia and Intel announced jointly developed 'Intel x86 RTX SOCs' + custom Nvidia data center x86 processors.[0]

Opcodes 0Fh,3Ah,E0h...EFh combined with VEX/EVEX encoding suggests wide (256/512-bit) vector SIMD, possibly for matrix multiplication, tensor operations, or arbitrary neural network activation functions.

[0]: https://nvidianews.nvidia.com/news/nvidia-and-intel-to-devel...

Possibly a legacy ISA acceleration feature in an upcoming RISC-V processor.