[LLVMdev] Performance regression on ARM (original) (raw)

Anton Korobeynikov anton at korobeynikov.info
Sun Oct 19 10:05:58 PDT 2014

I also thought about intrinsic, however I decided not to go this way mostly due to possible issues with ABI - it's much better to deal with them into frontend, than in the backend. However, I'm not opposed to this solution.

On Sun, Oct 19, 2014 at 7:03 PM, Tim Northover <t.p.northover at gmail.com> wrote:

Some patch which shows this approach (and the whole problem) is attached :) I wonder if it wouldn't be better to add an intrinsic. LLVM already deals quite happily with emitting compiler-rt calls having different calling conventions (& names -- it's entirely possible ARM will add an _aeabimul*c3 for example). It seems a bit nasty to make Clang understand all that too, unless we have to. Cheers. Tim.

-- With best regards, Anton Korobeynikov Faculty of Mathematics and Mechanics, Saint Petersburg State University

More information about the llvm-dev mailing list