diff --git a/include/cutlass/arch/mma.h b/include/cutlass/arch/mma.h
index a050c7a3..7385d882 100644
--- a/include/cutlass/arch/mma.h
+++ b/include/cutlass/arch/mma.h
@@ -49,61 +49,61 @@ namespace arch {
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
 /// Tag indicating the operation implied by MMA.
-struct OpMultiplyAdd;
+struct OpMultiplyAdd {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
 /// Tag indicating the result is saturated to MAX_FLOAT|MIN_FLOAT or MAX_INT|MIN_INT
-struct OpMultiplyAddSaturate;
+struct OpMultiplyAddSaturate {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
 /// Tag indicating the input is converted to a narrower type (BF16)
-struct OpMultiplyAddFastBF16;
+struct OpMultiplyAddFastBF16 {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
 /// Tag indicating the input is converted to a narrower type (F16)
-struct OpMultiplyAddFastF16;
+struct OpMultiplyAddFastF16 {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
 /// Tag indicating the input is converted to 2 (big and small) TF32 components
 //  Perform 3xTF32 or 4xTF32 for every F32 output element
-struct OpMultiplyAddFastF32;
+struct OpMultiplyAddFastF32 {}
 
 /// Tag indicating the input is converted to 2 (big and small) TF32 components
 //  Perform 3xTF32 or 4xTF32 for every complex<F32> output element
-struct OpMultiplyAddComplexFastF32;
+struct OpMultiplyAddComplexFastF32 {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
 /// Tag indicating the complex multiply-add operation
-struct OpMultiplyAddComplex;
+struct OpMultiplyAddComplex {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
 /// Tag indicating the gaussian complex multiply-add operation
-struct OpMultiplyAddGaussianComplex;
+struct OpMultiplyAddGaussianComplex {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
 /// Tag indicating the inner product is defined by (XOR, POPC)
-struct OpXorPopc;
+struct OpXorPopc {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
 /// Tag classifying math operators as thread-level operations.
-struct OpClassSimt;
+struct OpClassSimt {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////
 
 /// Tag classifing operators as Tensor Core operations.
-struct OpClassTensorOp;
+struct OpClassTensorOp {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////
 /// Tag classifing operators as WMMA Tensor Core operations
-struct OpClassWmmaTensorOp;
+struct OpClassWmmaTensorOp {};
 
 /////////////////////////////////////////////////////////////////////////////////////////////////