std::find_if(Mask.begin(), Mask.end(), FromV2Predicate) - Mask.begin();
}
+ unsigned SrcIndex = Mask[DestIndex] % 4;
if (MayFoldLoad(From)) {
// Trivial case, when From comes from a load and is only used by the
// shuffle. Make it use insertps from the vector that we need from that
// load.
SDValue NewLoad =
- NarrowVectorLoadToElement(cast<LoadSDNode>(From), DestIndex, DAG);
+ NarrowVectorLoadToElement(cast<LoadSDNode>(From), SrcIndex, DAG);
if (!NewLoad.getNode())
return SDValue();
}
// Vector-element-to-vector
- unsigned SrcIndex = Mask[DestIndex] % 4;
SDValue InsertpsMask = DAG.getIntPtrConstant(DestIndex << 4 | SrcIndex << 6);
return DAG.getNode(X86ISD::INSERTPS, dl, VT, To, From, InsertpsMask);
}
%result = shufflevector <4 x float> %a, <4 x float> %2, <4 x i32> <i32 4, i32 undef, i32 0, i32 7>
ret <4 x float> %result
}
+
+; Test for a bug in X86ISelLowering.cpp:getINSERTPS where we were using
+; the destination index to change the load, instead of the source index.
+define <4 x float> @pr20087(<4 x float> %a, <4 x float> *%ptr) {
+; CHECK-LABEL: pr20087:
+; CHECK: insertps $48
+; CHECK: ret
+ %load = load <4 x float> *%ptr
+ %ret = shufflevector <4 x float> %load, <4 x float> %a, <4 x i32> <i32 4, i32 undef, i32 6, i32 2>
+ ret <4 x float> %ret
+}