BasePtr = DAG.getNode(ISD::ADD, dl, BasePtr.getValueType(), BasePtr,
DAG.getIntPtrConstant(Increment));
+ SDValue L;
if (LdWidth < NewVTWidth) {
// Our current type we are using is too large, find a better size
NewVT = FindMemType(DAG, TLI, LdWidth, WidenVT, LdAlign, WidthDiff);
NewVTWidth = NewVT.getSizeInBits();
- }
-
- SDValue LdOp = DAG.getLoad(NewVT, dl, Chain, BasePtr,
+ L = DAG.getLoad(NewVT, dl, Chain, BasePtr,
LD->getPointerInfo().getWithOffset(Offset),
isVolatile,
isNonTemporal, isInvariant,
MinAlign(Align, Increment));
- LdChain.push_back(LdOp.getValue(1));
- LdOps.push_back(LdOp);
+ LdChain.push_back(L.getValue(1));
+ if (L->getValueType(0).isVector()) {
+ SmallVector<SDValue, 16> Loads;
+ Loads.push_back(L);
+ unsigned size = L->getValueSizeInBits(0);
+ while (size < LdOp->getValueSizeInBits(0)) {
+ Loads.push_back(DAG.getUNDEF(L->getValueType(0)));
+ size += L->getValueSizeInBits(0);
+ }
+ L = DAG.getNode(ISD::CONCAT_VECTORS, dl, LdOp->getValueType(0),
+ &Loads[0], Loads.size());
+ }
+ } else {
+ L = DAG.getLoad(NewVT, dl, Chain, BasePtr,
+ LD->getPointerInfo().getWithOffset(Offset), isVolatile,
+ isNonTemporal, isInvariant, MinAlign(Align, Increment));
+ LdChain.push_back(L.getValue(1));
+ }
+
+ LdOps.push_back(L);
+
LdWidth -= NewVTWidth;
}
--- /dev/null
+; RUN: llc < %s -march=x86 -mcpu=corei7-avx -mattr=+avx -mtriple=i686-pc-win32 | FileCheck %s
+
+;CHECK: add18i16
+define void @add18i16(<18 x i16>* nocapture sret %ret, <18 x i16>* %bp) nounwind {
+;CHECK: vmovups
+ %b = load <18 x i16>* %bp, align 16
+ %x = add <18 x i16> zeroinitializer, %b
+ store <18 x i16> %x, <18 x i16>* %ret, align 16
+;CHECK: ret
+ ret void
+}
+