Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -33173,8 +33173,26 @@
   if (Mst->isCompressingStore())
     return SDValue();
 
-  if (!Mst->isTruncatingStore())
-    return reduceMaskedStoreToScalarStore(Mst, DAG);
+  if (!Mst->isTruncatingStore()) {
+    if (SDValue ScalarStore = reduceMaskedStoreToScalarStore(Mst, DAG))
+      return ScalarStore;
+
+    // If the mask is checking (0 > X), we're creating a vector with all-zeros
+    // or all-ones elements based on the sign bits of X. AVX masked store only
+    // cares about the sign bit of each mask element, so eliminate the compare:
+    // mstore val, ptr, (pcmpgt 0, X) --> mstore val, ptr, X
+    SDValue Mask = Mst->getMask();
+    if (Mask.getOpcode() == X86ISD::PCMPGT &&
+        ISD::isBuildVectorAllZeros(Mask.getOperand(0).getNode())) {
+      assert(Mask.getValueType() == Mask.getOperand(1).getValueType() &&
+             "Unexpected type for PCMPGT");
+      return DAG.getMaskedStore(
+          Mst->getChain(), SDLoc(N), Mst->getValue(), Mst->getBasePtr(),
+          Mask.getOperand(1), Mst->getMemoryVT(), Mst->getMemOperand());
+    }
+
+    return SDValue();
+  }
 
   // Resolve truncating stores.
   EVT VT = Mst->getValue().getValueType();
Index: test/CodeGen/X86/masked_memop.ll
===================================================================
--- test/CodeGen/X86/masked_memop.ll
+++ test/CodeGen/X86/masked_memop.ll
@@ -1140,21 +1140,18 @@
   ret <8 x double> %res
 }
 
-; FIXME: The mask bit for each data element is the most significant bit of the mask operand, so a compare isn't needed.
+; The mask bit for each data element is the most significant bit of the mask operand, so a compare isn't needed.
+; TODO: Is the SKX code optimal?
 
 define void @trunc_mask(<4 x float> %x, <4 x float>* %ptr, <4 x float> %y, <4 x i32> %mask) {
 ; AVX-LABEL: trunc_mask:
 ; AVX:       ## BB#0:
-; AVX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vpcmpgtd %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vmaskmovps %xmm0, %xmm1, (%rdi)
+; AVX-NEXT:    vmaskmovps %xmm0, %xmm2, (%rdi)
 ; AVX-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_mask:
 ; AVX512F:       ## BB#0:
-; AVX512F-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX512F-NEXT:    vpcmpgtd %xmm2, %xmm1, %xmm1
-; AVX512F-NEXT:    vmaskmovps %xmm0, %xmm1, (%rdi)
+; AVX512F-NEXT:    vmaskmovps %xmm0, %xmm2, (%rdi)
 ; AVX512F-NEXT:    retq
 ;
 ; SKX-LABEL: trunc_mask: