Re: [PATCH] [x86] Don't use builtins for SIMD shifts

2016-12-13 Thread Marc Glisse
On Tue, 13 Dec 2016, Richard Biener wrote: On Sat, Dec 10, 2016 at 7:59 PM, Marc Glisse wrote: On Sat, 10 Dec 2016, Allan Sandfeld Jensen wrote: On Saturday 10 December 2016, Marc Glisse wrote: On Sat, 10 Dec 2016, Marc Glisse wrote: On Sat, 10 Dec 2016, Allan Sandfeld Jensen wrote: Re

Re: [PATCH] [x86] Don't use builtins for SIMD shifts

2016-12-13 Thread Richard Biener
On Sat, Dec 10, 2016 at 7:59 PM, Marc Glisse wrote: > On Sat, 10 Dec 2016, Allan Sandfeld Jensen wrote: > >> On Saturday 10 December 2016, Marc Glisse wrote: >>> >>> On Sat, 10 Dec 2016, Marc Glisse wrote: On Sat, 10 Dec 2016, Allan Sandfeld Jensen wrote: > > Replaces the definit

Re: [PATCH] [x86] Don't use builtins for SIMD shifts

2016-12-10 Thread Marc Glisse
On Sat, 10 Dec 2016, Allan Sandfeld Jensen wrote: On Saturday 10 December 2016, Marc Glisse wrote: On Sat, 10 Dec 2016, Marc Glisse wrote: On Sat, 10 Dec 2016, Allan Sandfeld Jensen wrote: Replaces the definitions of the shift intrinsics with GCC extension syntax to allow GCC to reason about

Re: [PATCH] [x86] Don't use builtins for SIMD shifts

2016-12-10 Thread Marc Glisse
On Sat, 10 Dec 2016, Marc Glisse wrote: On Sat, 10 Dec 2016, Allan Sandfeld Jensen wrote: Replaces the definitions of the shift intrinsics with GCC extension syntax to allow GCC to reason about what the instructions does. Tests are added to ensure the intrinsics still produce the right instru

Re: [PATCH] [x86] Don't use builtins for SIMD shifts

2016-12-10 Thread Marc Glisse
On Sat, 10 Dec 2016, Allan Sandfeld Jensen wrote: Replaces the definitions of the shift intrinsics with GCC extension syntax to allow GCC to reason about what the instructions does. Tests are added to ensure the intrinsics still produce the right instructions, and that a few basic optimizations