return EltsFromConsecutiveLoads(VT, Elts, dl, DAG);
}
-/// PerformTruncateCombine - In some cases a sequence with "truncate"
-/// operation may be simplified.
+/// PerformTruncateCombine - Converts truncate operation to
+/// a sequence of vector shuffle operations.
+/// It is possible when we truncate 256-bit vector to 128-bit vector
static SDValue PerformTruncateCombine(SDNode *N, SelectionDAG &DAG,
TargetLowering::DAGCombinerInfo &DCI,
const X86Subtarget *Subtarget) {
- EVT VT = N->getValueType(0);
- if (DCI.isBeforeLegalize() || !VT.isVector())
- return SDValue();
-
- SDValue In = N->getOperand(0);
- // Optimize the sequence setcc -> truncate
- if (In.getOpcode() == ISD::SETCC) {
- DebugLoc DL = N->getDebugLoc();
- EVT InVT = In.getValueType();
-
- // The vector element is all ones or all zero. Just take a half of it.
- EVT HalfVT = EVT::getVectorVT(*DAG.getContext(), InVT.getScalarType(),
- InVT.getVectorNumElements()/2);
- SDValue HalfVec = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, HalfVT, In,
- DAG.getIntPtrConstant(0));
- assert(HalfVT.getSizeInBits() == VT.getSizeInBits());
- return DAG.getNode(ISD::BITCAST, DL, VT, HalfVec);
- }
return SDValue();
}
ret <8 x i16>%B
}
-define <8 x i16> @trunc_after_setcc(<8 x float> %a, <8 x float> %b, <8 x float> %c, <8 x float> %d) {
-; CHECK: trunc_after_setcc
-; CHECK: vcmpltps
-; CHECK-NOT: vextract
-; CHECK: vcmpltps
-; CHECK-NEXT: vandps
-; CHECK-NEXT: vandps
-; CHECK: ret
- %res1 = fcmp olt <8 x float> %a, %b
- %res2 = fcmp olt <8 x float> %c, %d
- %andr = and <8 x i1>%res1, %res2
- %ex = zext <8 x i1> %andr to <8 x i16>
- ret <8 x i16>%ex
-}
-