This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [PATCH 9/17][ARM] Add NEON FP16 arithmetic instructions.
- From: Joseph Myers <joseph at codesourcery dot com>
- To: Matthew Wahab <matthew dot wahab at foss dot arm dot com>
- Cc: gcc-patches <gcc-patches at gcc dot gnu dot org>
- Date: Wed, 18 May 2016 00:58:29 +0000
- Subject: Re: [PATCH 9/17][ARM] Add NEON FP16 arithmetic instructions.
- Authentication-results: sourceware.org; auth=none
- References: <573B28A3 dot 9030603 at foss dot arm dot com> <573B2CA9 dot 5060703 at foss dot arm dot com>
On Tue, 17 May 2016, Matthew Wahab wrote:
> As with the VFP FP16 arithmetic instructions, operations on __fp16
> values are done by conversion to single-precision. Any new optimization
> supported by the instruction descriptions can only apply to code
> generated using intrinsics added in this patch series.
As with the scalar instructions, I think it is legitimate in most cases to
optimize arithmetic via single precision to work direct on __fp16 values
(and this would be natural for vectorization of __fp16 arithmetic).
> A number of the instructions are modelled as two variants, one using
> UNSPEC and the other using RTL operations, with the model used decided
> by the funsafe-math-optimizations flag. This follows the
> single-precision instructions and is due to the half-precision
> operations having the same conditions and restrictions on their use in
> optmizations (when they are enabled).
(Of course, these restrictions still apply.)
--
Joseph S. Myers
joseph@codesourcery.com