wschmidt accepted this revision. wschmidt added a comment. This revision is now accepted and ready to land.
Please double-check the divide code generation. So long as we aren't scalarizing the code, this LGTM. ================ Comment at: test/CodeGen/builtins-ppc-vsx.c:131 @@ -118,2 +130,3 @@ +// CHECK: fdiv <2 x double> /* vec_max */ ---------------- Have you verified that we still generate the xvdiv*p instructions when this is done end-to-end? I want to be sure this doesn't accidentally scalarize the code. Repository: rL LLVM http://reviews.llvm.org/D11184 _______________________________________________ cfe-commits mailing list cfe-commits@cs.uiuc.edu http://lists.cs.uiuc.edu/mailman/listinfo/cfe-commits