Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -8302,6 +8302,44 @@
     }
   }
 
+  // If this extload is directly stored, and that store's input value was
+  // loaded before still, try to avoid the roundtrip through memory and
+  // extload directly from the original memory location.
+  //
+  // This can't be caught by the store-to-load forwarding above, because
+  // the extload's memory type might not be legal.
+  // Instead, try to match this:
+  // v4i32 load %ptr2, zext from v4i8
+  //   store i32 %value, %ptr2
+  //     %value = load i32 %ptr1
+  // to turn the extload into:
+  // v4i32 load %ptr1, zext from v4i8
+  if (!ISD::isNON_EXTLoad(N) && !LD->isVolatile() &&
+      ISD::isNON_TRUNCStore(Chain.getNode())) {
+    SDLoc DL(N);
+    StoreSDNode *PrevST = cast<StoreSDNode>(Chain);
+    EVT ValVT = PrevST->getValue().getValueType();
+    EVT MemVT = LD->getMemoryVT();
+    if (PrevST->getBasePtr() == Ptr &&
+        (ValVT.getStoreSize() == MemVT.getStoreSize() &&
+         ValVT.getSizeInBits() == MemVT.getSizeInBits()) &&
+        ISD::isNormalLoad(PrevST->getValue().getNode())) {
+      LoadSDNode *PPrevLD = cast<LoadSDNode>(PrevST->getValue());
+      if (LD->getAddressSpace() == PPrevLD->getAddressSpace() &&
+          LD->getAlignment() == PPrevLD->getAlignment()) {
+        SDValue NewLoad = DAG.getExtLoad(
+            LD->getExtensionType(), DL, LD->getValueType(0),
+            PPrevLD->getChain(), PPrevLD->getBasePtr(),
+            PPrevLD->getPointerInfo(), MemVT, /*isVolatile=*/false,
+            PPrevLD->isNonTemporal(), PPrevLD->isInvariant(),
+            PPrevLD->getAlignment(), PPrevLD->getAAInfo());
+        SDValue Token = DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Chain,
+                                    SDValue(NewLoad.getNode(), 1));
+        return CombineTo(N, NewLoad, Token, true);
+      }
+    }
+  }
+
   // Try to infer better alignment information than the load already has.
   if (OptLevel != CodeGenOpt::None && LD->isUnindexed()) {
     if (unsigned Align = DAG.InferPtrAlignment(Ptr)) {
Index: test/CodeGen/X86/widen_load-2.ll
===================================================================
--- test/CodeGen/X86/widen_load-2.ll
+++ test/CodeGen/X86/widen_load-2.ll
@@ -193,9 +193,7 @@
 ; CHECK-NEXT:    movd    %[[CONSTANT1]], %e[[R1:[abcd]]]x
 ; CHECK-NEXT:    movw    %[[R1]]x, (%[[PTR1:.*]])
 ; CHECK-NEXT:    movb    $1, 2(%[[PTR1]])
-; CHECK-NEXT:    movl    (%[[PTR0]]), [[TMP1:%e[abcd]+x]]
-; CHECK-NEXT:    movl    [[TMP1]], [[TMP2:.*]]
-; CHECK-NEXT:    pmovzxbd [[TMP2]], %[[X0:xmm[0-9]+]]
+; CHECK-NEXT:    pmovzxbd (%[[PTR0]]), %[[X0:xmm[0-9]+]]
 ; CHECK-NEXT:    pextrd  $1, %[[X0]], %e[[R0:[abcd]]]x
 ; CHECK-NEXT:    shrl    %e[[R0]]x
 ; CHECK-NEXT:    movd    %[[X0]], %e[[R1:[abcd]]]x