News for hackers. Stuff that matters.
Re:Apple AMX instruction set (M1/M2 matrix coprocessor) by saboot on Monday September 05, 2022 @07:41AM (#32723210)
Not too bad, I do scientific computing and choose Intel/Nvidia as their APIs for accelerated math operations are documented and supported for developers.

I've been paying attention to what Apple has been pushing with their M1/M2 chips, and I'm pretty tempted to try it out, but unless these features are documented and supported I can't feel comfortable writing programs relying on them.

Re:Apple AMX instruction set (M1/M2 matrix coprocessor) by mhh__ on Monday September 05, 2022 @07:44AM (#32723230)
The API apple wants you to use is documented and presumably is here to stay.

That doesn't help if there's some edge case you'd need access to the raw ISA but still.

Re:Apple AMX instruction set (M1/M2 matrix coprocessor) by Someone on Monday September 05, 2022 @07:55AM (#32723286)
Also, BLAS is part of that interface (https://developer.apple.com/documentation/accelerate/blas)

Of course it is a black box in that you can’t (realistically) try and speed it up. You still run the risk of Apple’s priorities being different from yours.

Re:Apple AMX instruction set (M1/M2 matrix coprocessor) by kergonath on Monday September 05, 2022 @03:53PM (#32728625)
OTOH the interfaces are standard. Using Accelerate instead of the standard BLAS is just a compiler switch.
Re:Apple AMX instruction set (M1/M2 matrix coprocessor) by kergonath on Monday September 05, 2022 @03:52PM (#32728611)
They are not supported directly, but you can ue them through the Accelerate framework, which has an optimised BLAS and FFT implementations (amongst many other things).