diff --git a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_wmma_cshuffle_v3.hpp b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_wmma_cshuffle_v3.hpp
index 0d3b2b8e04..2a1a210398 100644
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_wmma_cshuffle_v3.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_wmma_cshuffle_v3.hpp
@@ -40,7 +40,7 @@ __launch_bounds__(CK_MAX_THREAD_PER_BLOCK, MinimumOccupancy)
 #if(defined(__gfx11__) || defined(__gfx12__))
 #if defined(__gfx11__)
     // gfx11 does not support *_atomic_pk_add_f16/bf16 instructions
-    using EdataType = remove_cvref_t<remove_pointer_t<decltype(karg.p_e_grid)>>;
+    using EDataType = remove_cvref_t<remove_pointer_t<decltype(karg.p_e_grid)>>;
     if constexpr(!(EGlobalMemoryDataOperation == InMemoryDataOperationEnum::AtomicAdd &&
                    (std::is_same_v<EDataType, ck::half_t> ||
                     std::is_same_v<EDataType, ck::bhalf_t>)))