[NVPTX] Fixed vectorized LDG for f16.

v2f16 is a special case in NVPTX. v4f16 may be loaded as a pair of v2f16
and that was not previously handled correctly by tryLDGLDU()

Differential Revision: https://reviews.llvm.org/D45339

llvm-svn: 329456

1 files changed, 6 insertions, 0 deletions

diff --git a/llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp b/llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
index 99305440eef..9538d795cc9 100644
--- a/llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
@@ -1239,6 +1239,12 @@ bool NVPTXDAGToDAGISel::tryLDGLDU(SDNode *N) {
   if (EltVT.isVector()) {
     NumElts = EltVT.getVectorNumElements();
     EltVT = EltVT.getVectorElementType();
+    // vectors of f16 are loaded/stored as multiples of v2f16 elements.
+    if (EltVT == MVT::f16 && N->getValueType(0) == MVT::v2f16) {
+      assert(NumElts % 2 == 0 && "Vector must have even number of elements");
+      EltVT = MVT::v2f16;
+      NumElts /= 2;
+    }
   }
 
   // Build the "promoted" result VTList for the load. If we are really loading