diff --git a/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp b/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
index bd09d78cd0eb6..6bcec7e54be4a 100644
--- a/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
+++ b/clang/lib/CIR/CodeGen/CIRGenExprScalar.cpp
@@ -676,6 +676,10 @@ class ScalarExprEmitter : public StmtVisitor<ScalarExprEmitter, mlir::Value> {
   mlir::Value VisitRealImag(const UnaryOperator *e,
                             QualType promotionType = QualType());
 
+  mlir::Value VisitUnaryExtension(const UnaryOperator *e) {
+    return Visit(e->getSubExpr());
+  }
+
   mlir::Value VisitCXXDefaultInitExpr(CXXDefaultInitExpr *die) {
     CIRGenFunction::CXXDefaultInitExprScope scope(cgf, die);
     return Visit(die->getExpr());
diff --git a/clang/test/CIR/CodeGen/vector-ext.cpp b/clang/test/CIR/CodeGen/vector-ext.cpp
index 8b5379a2b1a88..8bca48d8ffe0c 100644
--- a/clang/test/CIR/CodeGen/vector-ext.cpp
+++ b/clang/test/CIR/CodeGen/vector-ext.cpp
@@ -1322,3 +1322,23 @@ void logical_not() {
 // OGCG: %[[RESULT:.*]] = icmp eq <4 x i32> %[[TMP_A]], zeroinitializer
 // OGCG: %[[RESULT_VI4:.*]] = sext <4 x i1> %[[RESULT]] to <4 x i32>
 // OGCG: store <4 x i32> %[[RESULT_VI4]], ptr %[[B_ADDR]], align 16
+
+void unary_extension() {
+  vi4 a;
+  vi4 b = __extension__ a;
+}
+
+// CIR: %[[A_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["a"]
+// CIR: %[[B_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["b", init]
+// CIR: %[[TMP_A:.*]] = cir.load{{.*}} %[[A_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: cir.store{{.*}} %[[TMP_A]], %[[B_ADDR]] : !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>
+
+// LLVM: %[[A_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[B_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// LLVM: store <4 x i32> %[[TMP_A]], ptr %[[B_ADDR]], align 16
+
+// OGCG: %[[A_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[B_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// OGCG: store <4 x i32> %[[TMP_A]], ptr %[[B_ADDR]], align 16
diff --git a/clang/test/CIR/CodeGen/vector.cpp b/clang/test/CIR/CodeGen/vector.cpp
index d8fdeea179288..f242779502148 100644
--- a/clang/test/CIR/CodeGen/vector.cpp
+++ b/clang/test/CIR/CodeGen/vector.cpp
@@ -1390,3 +1390,23 @@ void logical_not_float() {
 // OGCG: %[[RESULT:.*]] = fcmp oeq <4 x float> %[[TMP_A]], zeroinitializer
 // OGCG: %[[RESULT_VI4:.*]] = sext <4 x i1> %[[RESULT]] to <4 x i32>
 // OGCG: store <4 x i32> %[[RESULT_VI4]], ptr %[[B_ADDR]], align 16
+
+void unary_extension() {
+  vi4 a;
+  vi4 b = __extension__ a;
+}
+
+// CIR: %[[A_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["a"]
+// CIR: %[[B_ADDR:.*]] = cir.alloca !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>, ["b", init]
+// CIR: %[[TMP_A:.*]] = cir.load{{.*}} %[[A_ADDR]] : !cir.ptr<!cir.vector<4 x !s32i>>, !cir.vector<4 x !s32i>
+// CIR: cir.store{{.*}} %[[TMP_A]], %[[B_ADDR]] : !cir.vector<4 x !s32i>, !cir.ptr<!cir.vector<4 x !s32i>>
+
+// LLVM: %[[A_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[B_ADDR:.*]] = alloca <4 x i32>, i64 1, align 16
+// LLVM: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// LLVM: store <4 x i32> %[[TMP_A]], ptr %[[B_ADDR]], align 16
+
+// OGCG: %[[A_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[B_ADDR:.*]] = alloca <4 x i32>, align 16
+// OGCG: %[[TMP_A:.*]] = load <4 x i32>, ptr %[[A_ADDR]], align 16
+// OGCG: store <4 x i32> %[[TMP_A]], ptr %[[B_ADDR]], align 16