Sync verification flow with GPU kernel

d6dff178 · rocking · ea6b9481 · d6dff178
Commit d6dff178 authored Jan 29, 2022 by rocking
Hide whitespace changes
Inline Side-by-side

Showing with 3 additions and 1 deletion

example/2_gemm_xdl_bias/gemm_xdl_bias.cpp example/2_gemm_xdl_bias/gemm_xdl_bias.cpp +3 -1

No files found.
--- a/example/2_gemm_xdl_bias/gemm_xdl_bias.cpp
+++ b/example/2_gemm_xdl_bias/gemm_xdl_bias.cpp
@@ -100,7 +100,9 @@ static void host_verify(const Tensor<AType>& a_m_k,
                 static_cast<AccDataType>(b_element_op(b_k_n(k, n)));
        }

-        c_element_op(c_m_n(m, n), v, c0_k_n(m, n));
+        CType y = static_cast<CType>(v);
+
+        c_element_op(c_m_n(m, n), y, c0_k_n(m, n));
    };

    make_ParallelTensorFunctor(f_mk_kn_mn,