[X86][APX] Do optimizeMemoryInst for v1X masked load/store (llvm#151331)

Fix redundant LEA: https://godbolt.org/z/34xEYE818

Author: phoebewang

llvm/lib/CodeGen/CodeGenPrepare.cpp

@@ -2769,6 +2769,29 @@ bool CodeGenPrepare::optimizeCallInst(CallInst *CI, ModifyDT &ModifiedDT) {
       return optimizeGatherScatterInst(II, II->getArgOperand(0));
     case Intrinsic::masked_scatter:
       return optimizeGatherScatterInst(II, II->getArgOperand(1));
+    case Intrinsic::masked_load:
+      // Treat v1X masked load as load X type.
+      if (auto *VT = dyn_cast<FixedVectorType>(II->getType())) {
+        if (VT->getNumElements() == 1) {
+          Value *PtrVal = II->getArgOperand(0);
+          unsigned AS = PtrVal->getType()->getPointerAddressSpace();
+          if (optimizeMemoryInst(II, PtrVal, VT->getElementType(), AS))
+            return true;
+        }
+      }
+      return false;
+    case Intrinsic::masked_store:
+      // Treat v1X masked store as store X type.
+      if (auto *VT =
+              dyn_cast<FixedVectorType>(II->getArgOperand(0)->getType())) {
+        if (VT->getNumElements() == 1) {
+          Value *PtrVal = II->getArgOperand(1);
+          unsigned AS = PtrVal->getType()->getPointerAddressSpace();
+          if (optimizeMemoryInst(II, PtrVal, VT->getElementType(), AS))
+            return true;
+        }
+      }
+      return false;
     }
 
     SmallVector<Value *, 2> PtrOps;

llvm/test/CodeGen/X86/apx/cf.ll

@@ -194,3 +194,24 @@ entry:
   call void @llvm.masked.store.v1i64.p0(<1 x i64> %3, ptr %p, i32 4, <1 x i1> %0)
   ret void
 }
+
+define void @sink_gep(ptr %p, i1 %cond) {
+; CHECK-LABEL: sink_gep:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    testb $1, %sil
+; CHECK-NEXT:    cfcmovnel %eax, 112(%rdi)
+; CHECK-NEXT:    cfcmovnel 112(%rdi), %eax
+; CHECK-NEXT:    movl %eax, (%rdi)
+; CHECK-NEXT:    retq
+entry:
+  %0 = getelementptr i8, ptr %p, i64 112
+  br label %next
+
+next:
+  %1 = bitcast i1 %cond to <1 x i1>
+  call void @llvm.masked.store.v1i32.p0(<1 x i32> zeroinitializer, ptr %0, i32 1, <1 x i1> %1)
+  %2 = call <1 x i32> @llvm.masked.load.v1i32.p0(ptr %0, i32 1, <1 x i1> %1, <1 x i32> zeroinitializer)
+  store <1 x i32> %2, ptr %p, align 4
+  ret void
+}