[Mesa-dev] TGSI 16-bit support
maraeo at gmail.com
Tue Aug 22 18:06:48 UTC 2017
On Tue, Aug 22, 2017 at 7:55 PM, Ilia Mirkin <imirkin at alum.mit.edu> wrote:
> On Tue, Aug 22, 2017 at 1:32 PM, Marek Olšák <maraeo at gmail.com> wrote:
>> On Tue, Aug 22, 2017 at 7:28 PM, Ilia Mirkin <imirkin at alum.mit.edu> wrote:
>>> How do you propose defining the semantics for e.g. loading a 16-bit
>>> value from a constbuf/ssbo? Would those get separate instructions?
>> st/mesa should use UP2H, PK2H and similar opcodes for I16 and U16, and
>> drivers can replace them with MOV if HalfPrecision == 1.
> The idea I had been toying with was to instead mark TEMP's as 16-bit
> precision and letting ops like ADD infer whatever they need from that.
> I don't know whether that's any different from your suggestion, and if
> it is, whether it's better or worse though. Just mentioning it.
The question is which one is easier to implement?
More information about the mesa-dev