Index: llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -5283,6 +5283,31 @@
       return N1;
     if (ISD::isBuildVectorAllOnes(N1.getNode()))
       return N0;
+
+    // fold (and (masked_load) (build_vec (x, ...))) to zext_masked_load
+    MaskedLoadSDNode *MLoad = dyn_cast<MaskedLoadSDNode>(N0);
+    BuildVectorSDNode *BVec = dyn_cast<BuildVectorSDNode>(N1);
+    if (MLoad && BVec && MLoad->getExtensionType() == ISD::EXTLOAD &&
+        N0.hasOneUse() && N1.hasOneUse()) {
+      EVT LoadVT = MLoad->getMemoryVT();
+      EVT ExtVT = VT;
+      if (TLI.isLoadExtLegal(ISD::ZEXTLOAD, ExtVT, LoadVT)) {
+        // For this AND to be a zero extension of the masked load the elements
+        // of the BuildVec must mask the bottom bits of the extended element
+        // type
+        if (ConstantSDNode *Splat = BVec->getConstantSplatNode()) {
+          TypeSize ElementSize =
+              LoadVT.getVectorElementType().getScalarSizeInBits();
+          if (Splat->getAPIntValue().isMask((uint64_t)ElementSize)) {
+            return DAG.getMaskedLoad(
+                ExtVT, SDLoc(N), MLoad->getChain(), MLoad->getBasePtr(),
+                MLoad->getOffset(), MLoad->getMask(), MLoad->getPassThru(),
+                LoadVT, MLoad->getMemOperand(), MLoad->getAddressingMode(),
+                ISD::ZEXTLOAD, MLoad->isExpandingLoad());
+          }
+        }
+      }
+    }
   }
 
   // fold (and c1, c2) -> c1&c2
Index: llvm/test/CodeGen/Thumb2/mve-zext-masked-load.ll
===================================================================
--- llvm/test/CodeGen/Thumb2/mve-zext-masked-load.ll
+++ llvm/test/CodeGen/Thumb2/mve-zext-masked-load.ll
@@ -7,7 +7,6 @@
 ; CHECK-NEXT:    vmovlb.s16 q0, q0
 ; CHECK-NEXT:    vpt.s32 lt, q0, zr
 ; CHECK-NEXT:    vldrht.u32 q0, [r0]
-; CHECK-NEXT:    vmovlb.u16 q0, q0
 ; CHECK-NEXT:    vcvt.f32.u32 q0, q0
 ; CHECK-NEXT:    bx lr
 entry:
@@ -23,7 +22,6 @@
 ; CHECK-NEXT:    vmovlb.s8 q0, q0
 ; CHECK-NEXT:    vpt.s16 lt, q0, zr
 ; CHECK-NEXT:    vldrbt.u16 q0, [r0]
-; CHECK-NEXT:    vmovlb.u8 q0, q0
 ; CHECK-NEXT:    vcvt.f16.u16 q0, q0
 ; CHECK-NEXT:    bx lr
 entry:
@@ -37,11 +35,9 @@
 ; CHECK-LABEL: foo_v4i8:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    vmovlb.s8 q0, q0
-; CHECK-NEXT:    vmov.i32 q1, #0xff
 ; CHECK-NEXT:    vmovlb.s16 q0, q0
 ; CHECK-NEXT:    vpt.s32 lt, q0, zr
 ; CHECK-NEXT:    vldrbt.u32 q0, [r0]
-; CHECK-NEXT:    vand q0, q0, q1
 ; CHECK-NEXT:    vcvt.f32.u32 q0, q0
 ; CHECK-NEXT:    bx lr
 entry: