Hi,
as complementary work to the one done to "Add FP64 support to the i965
shader backends" at:
https://bugs.freedesktop.org/show_bug.cgi?id=92760
I've been working to add piglit tests that would check the new features
added by this addition.
One of the topics we have been creating tests for is
Hi,
I haven't had any other feedback than Ilia's (thanks Ilia!) so my
doubts still stand.
I'd welcome more info regarding this topic.
Thanks!
Br.
On Tue, 2016-03-15 at 17:46 +0200, Andres Gomez wrote:
> Hi,
>
> as complementary work to the one done to "Add FP64 support to the
> i965
> shader
Pretty sure this should be all undefined. double->int isn't really any
different than float->int there where you can have values which are too
large too.
Note that for float->int (and it should be the same for doubles) d3d10
requires that you clamp to destination type range, and NaN gets
converted
Thanks a lot for the comments, Roland. This confirms my understanding.
Since there seems not to be any more feedback, I will now send the
patch for conversion tests I was working on for piglit's review.
Thanks again. :)
On Tue, 2016-04-05 at 16:29 +0200, Roland Scheidegger wrote:
> Pretty sure t
Not really an answer to your question, but you may be interested in
this model of the NVIDIA Tesla FPU that mwk RE'd, including fp64
(which was available on the G200 only in that series). I have no
reason to believe that Fermi+ are substantially different:
https://github.com/envytools/envytools/bl
On Tue, 2016-03-15 at 12:38 -0400, Ilia Mirkin wrote:
> Not really an answer to your question, but you may be interested in
> this model of the NVIDIA Tesla FPU that mwk RE'd, including fp64
> (which was available on the G200 only in that series). I have no
> reason to believe that Fermi+ are subst
