> On Dec 5, 2016, at 13:20, Jan Vesely <[email protected]> wrote:
>
> On Mon, 2016-12-05 at 09:48 -0800, [email protected]
> <mailto:[email protected]> wrote:
>> From: Matt Arsenault <[email protected] <mailto:[email protected]>>
>>
>> ---
>> tests/cl/program/execute/sign_extend_inreg.cl | 387
>> ++++++++++++++++++++++++++
>> 1 file changed, 387 insertions(+)
>> create mode 100644 tests/cl/program/execute/sign_extend_inreg.cl
>
> this looks very GCN specific, the name should IMO indicate it.
It’s completely a completely generic test, just the testcases are intended to
stress the important cases for GCN
>
>
> why 14 different arguments? does scalarization not work transitively on
> global pointers?
This is the most reliable way to get an SGPR value of the correct type. I could
change it to a uniformly indexed constant pointer (but even that may someday
only be an optimization that may not always happen)
>
>> + int shift0)
>> +{
>> + long args[] =
>> + {
>> + a0, a1, a2, a3,
>> + a4, a5, a6, a7,
>> + a8, a9, a10, a11,
>> + a12, a13
>> + };
>
> I assume the private copy is just to have an array and use for loop?
>
Yes
_______________________________________________
Piglit mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/piglit
