On 3/6/18 12:16 PM, Sitsofe Wheeler wrote: > On 6 March 2018 at 19:09, Jens Axboe <axboe@xxxxxxxxx> wrote: >> On 3/6/18 12:00 PM, Sitsofe Wheeler wrote: >>> Right and I'm saying change the how we add the flag and the configure >>> test. If the user explicitly sets sse on the configure line then >>> assume the user knows what they're doing and add it to the CFLAGS and >>> but always detect (via comping a program that would only work if the >>> user really had told the compiler to use SSE) if its already enabled >>> later (rather than only if the user turned it on). My thinking is that >>> platforms like x86_64 will nearly always have SSE so it would be nice >>> to detect if the compiler somehow already has it on. >> >> Ah I see, yes that might make sense. You could already just do that with >> configure --extra-cflags="-msse", though. > > Yes you might but having the explicit option means people won't have > to remember gcc flag names if they don't want to (but I don't really > mind either way). That is true, it's definitely more user friendly. > The change I was suggesting would also mean if you set an option that > somehow included lower ones (e.g. --enable_avx512) you would all the > lower flags automatically. Feel free to run with the patch if you want, I wasn't going to pursue it much further. -- Jens Axboe -- To unsubscribe from this list: send the line "unsubscribe fio" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
