yxsamliu wrote: AMDGPU also treats zero-sized shared objects as dynamic LDS. Could we qualify the fixed-storage statement with “nonzero-sized” and avoid saying “only unsized arrays”?
https://github.com/llvm/llvm-project/pull/183879 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
