Re: Idea: extend gcc to save C from the hell of intel vector instructions

2019-02-20 Thread Alexander Monakov
On Wed, 20 Feb 2019, Warren D Smith wrote: > but if I try to replace that with the nicer (since more portable) >c = __builtin_shuffle(a, b); > then > error: use of unknown builtin '__builtin_shuffle' > [-Wimplicit-function-declaration] Most likely you're on OS X and the 'gcc' command actually

Re: Idea: extend gcc to save C from the hell of intel vector instructions

2019-02-20 Thread Warren D Smith
On 2/18/19, Andrew Pinski wrote: > GCC already has most of this support. See > https://gcc.gnu.org/onlinedocs/gcc-8.2.0/gcc/Vector-Extensions.html#Vector-Extensions > > The dot in the typenames are not going to supported though. > > Thanks, > Andrew --what #include files and/or compiler flags ar

Re: Idea: extend gcc to save C from the hell of intel vector instructions

2019-02-18 Thread Andrew Pinski
On Mon, Feb 18, 2019 at 11:15 AM Warren D Smith wrote: > > There are a lot of weird intel vector instructions like > #include > > __m128i alignas(16) A, B, C, D, X, Y; > A = _mm_shuffle_epi8(D, Y); > C = _mm_unpackhi_epi16(A, B); > where my gcc seems to know about the latter but not the former >

Idea: extend gcc to save C from the hell of intel vector instructions

2019-02-18 Thread Warren D Smith
There are a lot of weird intel vector instructions like #include __m128i alignas(16) A, B, C, D, X, Y; A = _mm_shuffle_epi8(D, Y); C = _mm_unpackhi_epi16(A, B); where my gcc seems to know about the latter but not the former (I have no idea why, and it is very annoying to arbitrarily support the s