================ @@ -946,7 +946,9 @@ Let ``VT`` be a vector type and ``ET`` the element type of ``VT``. Each builtin accesses memory according to a provided boolean mask. These are provided as ``__builtin_masked_load`` and ``__builtin_masked_store``. The first -argument is always boolean mask vector. +argument is always boolean mask vector. The ``__builtin_masked_load`` builtin +takes an optional third argument for the result of the masked-off lanes, +otherwise it is poison. These builtins assume the memory is always aligned. ---------------- jhuber6 wrote:
Updated it to make it more obvious that it's basically `mask ? *val : thru.` https://github.com/llvm/llvm-project/pull/155652 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
