On Wed, 2019-08-21 at 23:41 +0100, Chris Wilson wrote: > Quoting Stuart Summers (2019-08-21 00:05:43) > > Add a new function to copy subslices for a specified slice > > between intel_sseu structures for the purpose of determining > > power-gate status. > > And ss_stride happens to be one in all cases so far? True. > > For one hsw variant, it is 2 if I am not mistaken. But that isn't > converted. I believe this is for the eu stride, not the subslice stride. We have the HSW_F1_EU_DIS_10EUS flag to represent this. > > Could you please drop a note saying that ss_stride is 1! No problem though. I'll add this to the commit message. > > > Signed-off-by: Stuart Summers <stuart.summers@xxxxxxxxx> > > Reviewed-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> Thanks! -Stuart
Attachment:
smime.p7s
Description: S/MIME cryptographic signature
_______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
