[X86] Teach the backend how to lower vector shift left into multiply rather than scalarizing it.

Instead of expanding a packed shift into a sequence of scalar shifts,
the backend now tries (when possible) to convert the vector shift into a
vector multiply.

Before this change, a shift of a MVT::v8i16 vector by a
build_vector of constants was always scalarized into a long sequence of "vector
extracts + scalar shifts + vector insert".
With this change, if there is SSE2 support, we emit a single vector multiply.

This change also affects SSE4.1, AVX, AVX2 shifts:
 - A shift of a MVT::v4i32 vector by a build_vector of non uniform constants
is now lowered when possible into a single SSE4.1 vector multiply.
 - Packed v16i16 shift left by constant build_vector are now expanded when
possible into a single AVX2 vpmullw.
This change also improves the lowering of AVX512f vector shifts.

Added test CodeGen/X86/vec_shift6.ll with some code examples that are affected
by this change.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@201271 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 33 insertions, 0 deletions

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 85656d8091..4ce2ea36c0 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -13156,6 +13156,39 @@ static SDValue LowerShift(SDValue Op, const X86Subtarget* Subtarget,
       return Op;
   }
 
+  // If possible, lower this packed shift into a vector multiply instead of
+  // expanding it into a sequence of scalar shifts.
+  // Do this only if the vector shift count is a constant build_vector.
+  if (Op.getOpcode() == ISD::SHL && 
+      (VT == MVT::v8i16 || VT == MVT::v4i32 ||
+       (Subtarget->hasInt256() && VT == MVT::v16i16)) &&
+      ISD::isBuildVectorOfConstantSDNodes(Amt.getNode())) {
+    SmallVector<SDValue, 8> Elts;
+    EVT SVT = VT.getScalarType();
+    unsigned SVTBits = SVT.getSizeInBits();
+    const APInt &One = APInt(SVTBits, 1);
+    unsigned NumElems = VT.getVectorNumElements();
+
+    for (unsigned i=0; i !=NumElems; ++i) {
+      SDValue Op = Amt->getOperand(i);
+      if (Op->getOpcode() == ISD::UNDEF) {
+        Elts.push_back(Op);
+        continue;
+      }
+
+      ConstantSDNode *ND = cast<ConstantSDNode>(Op);
+      const APInt &C = APInt(SVTBits, ND->getAPIntValue().getZExtValue());
+      uint64_t ShAmt = C.getZExtValue();
+      if (ShAmt >= SVTBits) {
+        Elts.push_back(DAG.getUNDEF(SVT));
+        continue;
+      }
+      Elts.push_back(DAG.getConstant(One.shl(ShAmt), SVT));
+    }
+    SDValue BV = DAG.getNode(ISD::BUILD_VECTOR, dl, VT, &Elts[0], NumElems);
+    return DAG.getNode(ISD::MUL, dl, VT, R, BV);
+  }
+
   // Lower SHL with variable shift amount.
   if (VT == MVT::v4i32 && Op->getOpcode() == ISD::SHL) {
     Op = DAG.getNode(ISD::SHL, dl, VT, Amt, DAG.getConstant(23, VT));