[PATCH] D20568: [X86][SSE] Replace (V)CVTDQ2PD(Y) and (V)CVTPS2PD(Y) lossless conversion intrinsics with generic IR
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Tue May 24 10:43:41 PDT 2016
RKSimon added inline comments.
================
Comment at: lib/IR/AutoUpgrade.cpp:416
@@ +415,3 @@
+ if (NumDstElts < SrcTy->getNumElements()) {
+ SmallVector<int, 8> ShuffleMask;
+ for (int i = 0; i != (int)NumDstElts; ++i)
----------------
mkuper wrote:
> Shouldn't the 8 here be 2? I think we only get into this case of NumDstElts == 2 (and SrcTy->getNumElements() == 4, which it always is).
Nice catch! Thanks Michael.
Repository:
rL LLVM
http://reviews.llvm.org/D20568
More information about the llvm-commits
mailing list