This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [PATCH] SPU float format: Round towards zero
- From: "Joseph S. Myers" <joseph at codesourcery dot com>
- To: Ulrich Weigand <uweigand at de dot ibm dot com>
- Cc: gcc-patches at gcc dot gnu dot org, trevor_smigiel at playstation dot sony dot com, andrew_pinski at playstation dot sony dot com, rguenther at suse dot de
- Date: Mon, 4 Aug 2008 19:57:01 +0000 (UTC)
- Subject: Re: [PATCH] SPU float format: Round towards zero
- References: <200808041929.m74JT12G017513@d12av02.megacenter.de.ibm.com>
On Mon, 4 Aug 2008, Ulrich Weigand wrote:
> In addition, it turned out that the SPU back-end didn't always follow
> round-towards-zero itself: for DImode to SFmode conversions, the default
> libgcc routine was used (which implements round-to-nearest). The patch
> adds inline implementations of those conversions that round towards zero,
> as already specified in the SPU Language Extensions specification.
If the C libgcc function is not correct for this target, you should stop
it being built - and to support existing objects that may refer to it, you
should provide an SPU-specific implementation (whether in C or assembly).
--
Joseph S. Myers
joseph@codesourcery.com