[X86][SSE] Use PMADDWD for v4i32 multiplies with 17 or more leading zeros

If there are 17 or more leading zeros to the v4i32 elements, then we can use PMADD for the integer multiply when PMULLD is unavailable or slow.

The 17 bits need to be zero as the PMADDWD performs a v8i16 signed-mul-extend + pairwise-add - the upper 16 so we're adding a zero pair and the 17th bit so we don't incorrectly sign extend.

Differential Revision: https://reviews.llvm.org/D41484

llvm-svn: 321516

1 files changed, 14 insertions, 0 deletions

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index ad2d4b55bda..ba3b02e25a9 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -22086,6 +22086,13 @@ static SDValue LowerMUL(SDValue Op, const X86Subtarget &Subtarget,
     assert(Subtarget.hasSSE2() && !Subtarget.hasSSE41() &&
            "Should not custom lower when pmulld is available!");
 
+    // If the upper 17 bits of each element are zero then we can use PMADD.
+    APInt Mask17 = APInt::getHighBitsSet(32, 17);
+    if (DAG.MaskedValueIsZero(A, Mask17) && DAG.MaskedValueIsZero(B, Mask17))
+      return DAG.getNode(X86ISD::VPMADDWD, dl, VT,
+                         DAG.getBitcast(MVT::v8i16, A),
+                         DAG.getBitcast(MVT::v8i16, B));
+
     // Extract the odd parts.
     static const int UnpackMask[] = { 1, -1, 3, -1 };
     SDValue Aodds = DAG.getVectorShuffle(VT, dl, A, A, UnpackMask);
@@ -32259,6 +32266,13 @@ static SDValue reduceVMULWidth(SDNode *N, SelectionDAG &DAG,
   if ((NumElts % 2) != 0)
     return SDValue();
 
+  // If the upper 17 bits of each element are zero then we can use PMADD.
+  APInt Mask17 = APInt::getHighBitsSet(32, 17);
+  if (VT == MVT::v4i32 && DAG.MaskedValueIsZero(N0, Mask17) &&
+      DAG.MaskedValueIsZero(N1, Mask17))
+    return DAG.getNode(X86ISD::VPMADDWD, DL, VT, DAG.getBitcast(MVT::v8i16, N0),
+                       DAG.getBitcast(MVT::v8i16, N1));
+
   unsigned RegSize = 128;
   MVT OpsVT = MVT::getVectorVT(MVT::i16, RegSize / 16);
   EVT ReducedVT = EVT::getVectorVT(*DAG.getContext(), MVT::i16, NumElts);