Don't use __restrict__
for CUDA by StephanTLavavej · Pull Request #5097 · microsoft/STL (original) (raw)
#5079 was a nice try, but it doesn't work. We need to revert this before 17.13 Preview 3 branches for release.
It broke NVIDIA's Cutlass again. @CaseyCarter observed:
In both the old and new preprocessed repros, our
_RESTRICT
s in the declaration of_Adjacent_difference_no_overlap
are being expanded to plainrestrict
. If I had to guess, I'd say that CUDA is replacing__restrict__
withrestrict
under the expectation that__restrict__
is only used in C mode.
Fixes VSO-2295101 / AB#2295101 again.