[PATCH] D37287: [X86] Implement broadcastf32x2 and broadcasti32x2 intrinsics using __builtin_shufflevector instead builtins

Ayman Musa via Phabricator via cfe-commits cfe-commits at lists.llvm.org
Wed Aug 30 00:39:30 PDT 2017


aymanmus added a comment.

Did you make sure the resulted IR was lowered to the expected X86 instructions?


https://reviews.llvm.org/D37287





More information about the cfe-commits mailing list