News for hackers. Stuff that matters.
Re:Jim Keller criticizes Nvidia's CUDA, x86 by imtringued on Friday February 23, 2024 @06:05PM (#39487292)
There are two ways to interpret this statement. First is that ISA is completely irrelevant since you can just convert to whatever is best. This is bad for RISC since there is literally no advantage gained by losing backwards compatibility.

The other interpretation is that micro ops are actually a microarchitectural optimization and that RISC processors should use it too. The compressed instruction set of RISC-V is leaning towards that direction. RISC-V processors internally convert RISC-V instructions to RISC-V.

It is kind of hollow to talk about it, since it is hardly clear to say that this is a unique disadvantage or advantage.

Re:Jim Keller criticizes Nvidia's CUDA, x86 by snvzz on Sunday February 25, 2024 @03:01AM (#39498641)
>This is bad for RISC since there is literally no advantage gained by losing backwards compatibility.

I respectfully disagree. There's a major advantage of losing backwards compatibility with established ISAs, and that is freedom from licensing.

e.g. The main strength of RISC-V is not even its technical superiority; It is the free license.