This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [RFC][PATCH 0/2] aarch64: Add optimized ASIMD versions of sinf/cosf
- From: Joseph Myers <joseph at codesourcery dot com>
- To: Wilco Dijkstra <Wilco dot Dijkstra at arm dot com>
- Cc: "libc-alpha at sourceware dot org" <libc-alpha at sourceware dot org>, Szabolcs Nagy <Szabolcs dot Nagy at arm dot com>, nd <nd at arm dot com>, "Ashwin dot Sekhar at cavium dot com" <Ashwin dot Sekhar at cavium dot com>
- Date: Tue, 13 Jun 2017 15:43:59 +0000
- Subject: Re: [RFC][PATCH 0/2] aarch64: Add optimized ASIMD versions of sinf/cosf
- Authentication-results: sourceware.org; auth=none
- References: <VI1PR0802MB2621726CB1BDC628BFC30A6A83C20@VI1PR0802MB2621.eurprd08.prod.outlook.com>
On Tue, 13 Jun 2017, Wilco Dijkstra wrote:
> Agreed. I recently committed an AArch64 fix for int<->FP moves
> (https://gcc.gnu.org/ml/gcc-patches/2017-04/msg01282.html), so the
> particular issue Szabolcs mentions is fixed. I've got several other
> improvements inspired by non-optimal sequences in math functions
> in review or development. It's fairly trivial to get GCC generate the
> expected code, so there is no excuse for using assembly code.
And this discussion reminded me to file a bug -
<https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81085> - for inefficient
code I'd previously observed on 32-bit x86 when accessing long double
function arguments.
--
Joseph S. Myers
joseph@codesourcery.com