On Fri, Apr 12, 2024 at 02:10:30AM +0200, Konrad Dybcio wrote: > > > On 4/12/24 01:49, Elliot Berman wrote: > > On Thu, Apr 11, 2024 at 10:24:08PM +0200, Konrad Dybcio wrote: > > > > > > > > > On 4/11/24 22:09, Elliot Berman wrote: > > > > On Thu, Apr 11, 2024 at 10:05:30PM +0200, Konrad Dybcio wrote: > > > > > > > > > > > > > > > On 4/11/24 20:55, Elliot Berman wrote: > > > > > > On Fri, Apr 05, 2024 at 10:41:29AM +0200, Konrad Dybcio wrote: > > > > > > > In preparation for parsing the chip "feature code" (FC) and "product > > > > > > > code" (PC) (essentially the parameters that let us conclusively > > > > > > > characterize the sillicon we're running on, including various speed > > > > > > > bins), move the socinfo version defines to the public header and > > > > > > > include some more FC/PC defines. > > > > > > > > > > > > > > Signed-off-by: Konrad Dybcio <konrad.dybcio@xxxxxxxxxx> > > > > > > > --- > > > > > > [...] > > > > > > > > > > > 0xf is the last one. > > > > > > One more question, are the "internal/external feature codes" referring to > > > internality/externality of the chips (i.e. "are they QC-lab-only engineering > > > samples), or what else does that represent? > > > > Yes, QC-lab-only engineering samples is the right interpretation of > > these feature codes. > > Do you think it would be beneficial to keep the logic for these ESes in > the upstream GPU driver? Otherwise, I can yank out half of the added lines. > Should be fine to yank, IMO.