Re: [PATCH 1/6] rs6000: Support SSE4.1 "round" intrinsics

2021-08-19 Thread Segher Boessenkool
Hi! On Thu, Aug 19, 2021 at 01:16:16PM -0500, Paul A. Clarke wrote: > On Wed, Aug 18, 2021 at 05:46:58PM -0500, Segher Boessenkool wrote: > > There are __builtin_set_fpscr_rn and friends, please use those, those > > are optimised for any platform. > > I do. (Unless I missed an opportunity somewh

Re: [PATCH 1/6] rs6000: Support SSE4.1 "round" intrinsics

2021-08-19 Thread Paul A. Clarke via Gcc-patches
On Wed, Aug 18, 2021 at 05:46:58PM -0500, Segher Boessenkool wrote: > On Mon, Aug 09, 2021 at 03:23:50PM -0500, Paul A. Clarke wrote: > > Suppress exceptions (when specified), by saving, manipulating, and > > restoring the FPSCR. Similarly, save, set, and restore the floating-point > > rounding mo

Re: [PATCH 1/6] rs6000: Support SSE4.1 "round" intrinsics

2021-08-18 Thread Segher Boessenkool
On Mon, Aug 09, 2021 at 03:23:50PM -0500, Paul A. Clarke wrote: > Suppress exceptions (when specified), by saving, manipulating, and > restoring the FPSCR. Similarly, save, set, and restore the floating-point > rounding mode when required. > > No attempt is made to optimize writing the FPSCR (by

Re: [PATCH 1/6] rs6000: Support SSE4.1 "round" intrinsics

2021-08-18 Thread Segher Boessenkool
On Wed, Aug 18, 2021 at 02:01:33PM -0500, Bill Schmidt wrote: > On 8/9/21 3:23 PM, Paul A. Clarke via Gcc-patches wrote: > Reminder:  Please specify what testing you've done and on which > platforms, Yes please. > and where you want to apply the patches (i.e., do you want > backports?). Backpo

Re: [PATCH 1/6] rs6000: Support SSE4.1 "round" intrinsics

2021-08-18 Thread Bill Schmidt via Gcc-patches
Hi, Paul! On 8/9/21 3:23 PM, Paul A. Clarke via Gcc-patches wrote: Suppress exceptions (when specified), by saving, manipulating, and restoring the FPSCR. Similarly, save, set, and restore the floating-point rounding mode when required. No attempt is made to optimize writing the FPSCR (by chec

[PATCH 1/6] rs6000: Support SSE4.1 "round" intrinsics

2021-08-09 Thread Paul A. Clarke via Gcc-patches
Suppress exceptions (when specified), by saving, manipulating, and restoring the FPSCR. Similarly, save, set, and restore the floating-point rounding mode when required. No attempt is made to optimize writing the FPSCR (by checking if the new value would be the same), other than using lighter wei