Use PMULDQ for v2i64 multiplies when SSE4.1 is available. And add
load-folding table entries for PMULDQ and PMULLD.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@51489 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index caa81c4..2a9cef1 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -700,6 +700,7 @@
   if (Subtarget->hasSSE41()) {
     // FIXME: Do we need to handle scalar-to-vector here?
     setOperationAction(ISD::MUL,                MVT::v4i32, Legal);
+    setOperationAction(ISD::MUL,                MVT::v2i64, Legal);
 
     // i8 and i16 vectors are custom , because the source register and source
     // source memory operand types are not the same width.  f32 vectors are