disallow nbits_in_non_outlier == 0 in acc16 conv; option to fallback to acc32 (#15708)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/15708
nbits_in_non_outlier == 0 doesn't make sense because it means everything is outlier and we can just use 32-bit accumulation.
Depending on architecture, break-even point between acc16 and acc32 can be different. Adding thresholds for falling back to acc32.
Reviewed By: jianyuh
Differential Revision: D13574832
fbshipit-source-id: b7a37aacbfdc7867e31838dafcdd5f7c2ac282af
