News for hackers. Stuff that matters.
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by ianlevesque on Monday February 12, 2024 @12:52PM (#39347993)
And indeed more than succeed, they invented x86_64.
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by sangnoir on Monday February 12, 2024 @01:27PM (#39348424)
x86_64's win was helped by Intel's Itanium misstep. AMD can't bank on Nvidia making a mistake, and Nvidia seems content with incremental changes to CUDA, contrasted with Intel's 32-bit to 64-bit transition. It is highly unlikely that AMD can find and exploit a similar chink in the amor against CUDA.
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by LamaOfRuin on Monday February 12, 2024 @01:55PM (#39348767)
If they're content with incremental changes to CUDA then it doesn't cost much to keep updated compatibility and do it as quickly as any users actually adopt changes.
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by stcredzero on Monday February 12, 2024 @01:07PM (#39348177)
And indeed more than succeed, they invented x86_64.

If AMD invented the analogous to x86_64 for CUDA, this would increase competition and progress in AI by some huge fraction.

Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by pjmlp on Monday February 12, 2024 @02:03PM (#39348847)
Only works if NVidia misteps and creates the Itanium version of CUDA.
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by stcredzero on Monday February 12, 2024 @02:15PM (#39348980)
You don't think someone would welcome the option to have more hardware buying options, even if the "Itanium version" didn't happen?
Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I... by jvanderbot on Monday February 12, 2024 @06:05PM (#39351796)
Why "if only". Intel had been around forever when AMD showed up. CUDA isn't unassailable