perf(dnn/cuda): sass int8 epilogue remove shared load

GitOrigin-RevId: 2b49f5069b

dnn/test/cuda/conv_bias_int8.cpp

@@ -1142,7 +1142,7 @@ TEST_F(CUDA, BENCHMARK_CUTLASS_CONV_BIAS_INT8_NCHW4_DET_FIRST) {
 }
 
 #endif
-}
+}  // namespace conv
 }  // namespace test
 }  // namespace megdnn